a4:I[903690,["/chat-static/_next/static/immutable/chunks/2s2arn416x8n1.js","/chat-static/_next/static/immutable/chunks/1oa3bat8-m8-8.js","/chat-static/_next/static/immutable/chunks/2zhua0cu86l_c.js","/chat-static/_next/static/immutable/chunks/0r3s70ucno8tj.js","/chat-static/_next/static/immutable/chunks/047caungpv2oe.js","/chat-static/_next/static/immutable/chunks/0ur16xcze8_1h.js","/chat-static/_next/static/immutable/chunks/37c0b4etzd24w.js","/chat-static/_next/static/immutable/chunks/17anht-a4gnim.js","/chat-static/_next/static/immutable/chunks/30wqhens5cioe.js","/chat-static/_next/static/immutable/chunks/00hu8fdgh1j4v.js","/chat-static/_next/static/immutable/chunks/2-a0_ndam39nj.js","/chat-static/_next/static/immutable/chunks/1pywt1h873bd3.js","/chat-static/_next/static/immutable/chunks/3h47h0tu6ra94.js","/chat-static/_next/static/immutable/chunks/3py7oec8qvsc4.js","/chat-static/_next/static/immutable/chunks/2mp0_j1home_r.js","/chat-static/_next/static/immutable/chunks/0ge-25es7o8xp.js","/chat-static/_next/static/immutable/chunks/3i83l5x0zfxvu.js","/chat-static/_next/static/immutable/chunks/3he0or6nwp7ka.js","/chat-static/_next/static/immutable/chunks/0f2nmau4qedmf.js","/chat-static/_next/static/immutable/chunks/3ms522oj0w1q6.js","/chat-static/_next/static/immutable/chunks/1eb1rdocf1tga.js","/chat-static/_next/static/immutable/chunks/33g364dont6bc.js","/chat-static/_next/static/immutable/chunks/02yydb8nw8axw.js","/chat-static/_next/static/immutable/chunks/2dfjxmcoo1tp2.js","/chat-static/_next/static/immutable/chunks/1juzrssbfor2n.js","/chat-static/_next/static/immutable/chunks/3_zne-oxp3ex8.js","/chat-static/_next/static/immutable/chunks/3r6d4w8uj6sbf.js","/chat-static/_next/static/immutable/chunks/0j-1w-w1bwtmq.js","/chat-static/_next/static/immutable/chunks/0ww_cp_o5vt2h.js","/chat-static/_next/static/immutable/chunks/0s0np_ga9hm45.js","/chat-static/_next/static/immutable/chunks/0ffu4on7pnel3.js","/chat-static/_next/static/immutable/chunks/1ngt7fq_ny-x8.js","/chat-static/_next/static/immutable/chunks/2-ea-d4zcky46.js","/chat-static/_next/static/immutable/chunks/19b_xu75c_h5i.js","/chat-static/_next/static/immutable/chunks/0mxm_71t-5ggi.js","/chat-static/_next/static/immutable/chunks/0l--bazl3wxtg.js","/chat-static/_next/static/immutable/chunks/2_1uite16tuap.js","/chat-static/_next/static/immutable/chunks/2ap68on7a2mkj.js","/chat-static/_next/static/immutable/chunks/14xmhcwc5tega.js","/chat-static/_next/static/immutable/chunks/365bukdi-txbr.js","/chat-static/_next/static/immutable/chunks/23pqwf8g6d7y_.js","/chat-static/_next/static/immutable/chunks/3jrmet23z3lfb.js","/chat-static/_next/static/immutable/chunks/12gan94eva2bh.js","/chat-static/_next/static/immutable/chunks/0wa14r29vk-50.js","/chat-static/_next/static/immutable/chunks/3af4iuglo00u7.js","/chat-static/_next/static/immutable/chunks/2nsejysme7n9p.js","/chat-static/_next/static/immutable/chunks/3ua-hupun3u5v.js","/chat-static/_next/static/immutable/chunks/00d7gkojwd_33.js","/chat-static/_next/static/immutable/chunks/3wwsnbaar43b2.js","/chat-static/_next/static/immutable/chunks/0ghizcopsggxp.js","/chat-static/_next/static/immutable/chunks/0ilzxtsq9fh87.js"],"ExplicitChatIdProvider"] a5:I[838238,["/chat-static/_next/static/immutable/chunks/2s2arn416x8n1.js","/chat-static/_next/static/immutable/chunks/1oa3bat8-m8-8.js","/chat-static/_next/static/immutable/chunks/2zhua0cu86l_c.js","/chat-static/_next/static/immutable/chunks/0r3s70ucno8tj.js","/chat-static/_next/static/immutable/chunks/047caungpv2oe.js","/chat-static/_next/static/immutable/chunks/0ur16xcze8_1h.js","/chat-static/_next/static/immutable/chunks/37c0b4etzd24w.js","/chat-static/_next/static/immutable/chunks/17anht-a4gnim.js","/chat-static/_next/static/immutable/chunks/30wqhens5cioe.js","/chat-static/_next/static/immutable/chunks/00hu8fdgh1j4v.js","/chat-static/_next/static/immutable/chunks/2-a0_ndam39nj.js","/chat-static/_next/static/immutable/chunks/1pywt1h873bd3.js","/chat-static/_next/static/immutable/chunks/3h47h0tu6ra94.js","/chat-static/_next/static/immutable/chunks/3py7oec8qvsc4.js","/chat-static/_next/static/immutable/chunks/2mp0_j1home_r.js","/chat-static/_next/static/immutable/chunks/0ge-25es7o8xp.js","/chat-static/_next/static/immutable/chunks/3i83l5x0zfxvu.js","/chat-static/_next/static/immutable/chunks/3he0or6nwp7ka.js","/chat-static/_next/static/immutable/chunks/0f2nmau4qedmf.js","/chat-static/_next/static/immutable/chunks/3ms522oj0w1q6.js","/chat-static/_next/static/immutable/chunks/1eb1rdocf1tga.js","/chat-static/_next/static/immutable/chunks/33g364dont6bc.js","/chat-static/_next/static/immutable/chunks/02yydb8nw8axw.js","/chat-static/_next/static/immutable/chunks/2dfjxmcoo1tp2.js","/chat-static/_next/static/immutable/chunks/1juzrssbfor2n.js","/chat-static/_next/static/immutable/chunks/3_zne-oxp3ex8.js","/chat-static/_next/static/immutable/chunks/3r6d4w8uj6sbf.js","/chat-static/_next/static/immutable/chunks/0j-1w-w1bwtmq.js","/chat-static/_next/static/immutable/chunks/0ww_cp_o5vt2h.js","/chat-static/_next/static/immutable/chunks/0s0np_ga9hm45.js","/chat-static/_next/static/immutable/chunks/0ffu4on7pnel3.js","/chat-static/_next/static/immutable/chunks/1ngt7fq_ny-x8.js","/chat-static/_next/static/immutable/chunks/2-ea-d4zcky46.js","/chat-static/_next/static/immutable/chunks/19b_xu75c_h5i.js","/chat-static/_next/static/immutable/chunks/0mxm_71t-5ggi.js","/chat-static/_next/static/immutable/chunks/0l--bazl3wxtg.js","/chat-static/_next/static/immutable/chunks/2_1uite16tuap.js","/chat-static/_next/static/immutable/chunks/2ap68on7a2mkj.js","/chat-static/_next/static/immutable/chunks/14xmhcwc5tega.js","/chat-static/_next/static/immutable/chunks/365bukdi-txbr.js","/chat-static/_next/static/immutable/chunks/23pqwf8g6d7y_.js","/chat-static/_next/static/immutable/chunks/3jrmet23z3lfb.js","/chat-static/_next/static/immutable/chunks/12gan94eva2bh.js","/chat-static/_next/static/immutable/chunks/0wa14r29vk-50.js","/chat-static/_next/static/immutable/chunks/3af4iuglo00u7.js","/chat-static/_next/static/immutable/chunks/2nsejysme7n9p.js","/chat-static/_next/static/immutable/chunks/3ua-hupun3u5v.js","/chat-static/_next/static/immutable/chunks/00d7gkojwd_33.js","/chat-static/_next/static/immutable/chunks/3wwsnbaar43b2.js","/chat-static/_next/static/immutable/chunks/0ghizcopsggxp.js","/chat-static/_next/static/immutable/chunks/0ilzxtsq9fh87.js"],"SWRDataProvider"] a6:[] a7:[["b_zONYToqTb6p",null]] a8:[["b_zONYToqTb6p",{"templateVersionId":null,"templateCanonId":null}]] a9:[["b_zONYToqTb6p","$D2026-08-05T06:29:43.740Z"]] aa:[["b_zONYToqTb6p",false]] ab:[["b_zONYToqTb6p",{"git":{"ref":"main","sha":"981d492b22cedc4a3a38d4652d4136428e21aeb5","type":"github","repoId":0,"repoName":"v0-1-team_brG2lZVpF5zHOKMuTw1oOqqz-lAblOd60G0T","ownerName":"v0-git-s3-storage","commitMessage":"Initial commit from v0\n\nV0-Initial-Commit: v1"}}]] ac:[["b_zONYToqTb6p",null]] ad:[["b_zONYToqTb6p",true]] ae:[["b_zONYToqTb6p",true]] af:[] b0:T752,was our submission and we were cooked hard, and were awarded 9/15, with the comments liks "Comment 1:You are assuming joint familes?Too many health issues?20M+ working parents seem like a huge TAM, but there will be so many filtersThe percentage of people taking proactive mediclaim policies is already abysmal. The penetration of these doctor appointment apps like DocOnline etc is also super low.Comment 2:sa-ba, sab.....its like you are putting many things in one, diffused positioning.. What about partnering with day care centers which can keep partents updated on what the child is upto during the time she is in the day care.proposed MVP is much too large, don't you think?AN did habit-forming in his class - how would you bring in the hook framework? let's say for parents - would say structured caregiver updates create enough value and habit for parents?bring a little more clarity - for instance - how would you translate “meaningful care activity” ? Needs to be more clearly defined. Wouldn't it reflect repeated coordination between caregiver and parent rather than just any isolated app action?" so for that, we are thinking of pivoting to the ASHA workers. First of all is this pivot correct. 2nd our final submission includes "Students are expected to use the frameworks discussed in class and will be expected to submit a 15 slide deck and a 10 minute in-class presentation. The final submission should cover as many of the following as possible: · Market/Business Context · Revisit Target Persona · Justification · Assumptions · Solution Design (mention any experiments you will conduct if you have multiple alternatives) · Key Metrics · Risks · Go-to-Market Plan " Our in class material includes "b1:T10ba6e, TABLE OF CONTENTS S.No.Title Page No. 1.1 Strengthening Health Systems To Improve Health Outcomes. WHO’s Framework For Action. 3 1.2 National Health Policy, 2017. Revealing Public Health Chicanery. 59 1.3 Concepts and definitions of health and health-related values in the knowledge landscapes of the digital society. 67 2.1 Innovation in healthcare – a special case? 72 2.2 The Promise of Digital Health: Then, Now, and the Future. 103 2.3 Perspectives of Digital Health Innovations in Low and Middle-Income Health Care Systems From South and Southeast Asia. 127 3.1 India’s evolving digital health strategy. 136 3.2 Inception of the Indian Digital Health Mission: Connecting...the...Dots. 139 3.3 Digital health ecosystem in India: Present status, challenges, and way forward. 146 4.1 Mobile Phones for Maternal Health in Rural Bihar: Reducing the Access Gap? 151 4.2 From lab to life: How wearable devices can improve health equity. 161 4.3 Mind the Gap: A fairer way forward for AI in health care 165 5.1 ACCESS Health India and the Ayushman Bharat Digital Mission. In-class 5.2 The Ayushman Bharat Digital Mission (ABDM): making of India’s Digital Health Story. 168 5.3 The Ayushman Bharat Digital Mission of India: An Assessment. 175 6.1 Exploring health information system resilience during the COVID-19 pandemic: case studies from Norway, Sri Lanka & Rwanda. 187 6.2 A tale of ‘politics and stars aligning’: analysing the sustainability of scaled-up digital tools for front-line health workers in India. 205 7.1 Developing and commercializing healthcare technologies. 219 7.2 Digital monitoring for data-driven antimicrobial stewardship: a process perspective from resource-constrained contexts in India. 275 8.1 Ethical challenges of digital health technologies: Aadhaar, India 287 8.2 Where Is All Our Health Data Going? 293 9.1 Smart Cards for All: Digitalisation of Universal Health Coverage in India. 301 9.2 “When the Government Changes, the Card Will Also Change”: Questioning Identity Biometric Smartcards for National Health Insurance (RSBY) India. 320 E V E R Y B O D Y ’ S B U S I N E S S S T R E N G T H E N I N G H E A LT H S Y S T E M S T O I M P R OV E H E A LT H O U T C O M E S W H O ’ S F R A M E WO R K F O R AC T I O N 3 WHO Library Cataloguing-in-Publication Data : Everybody business : strengthening health systems to improve health outcomes : WHO’s framework for action. 1 .Delivery of health care - trends. 2.Health systems plans. 3.Outcome assessment (health care). 4. Health policy. I.World Health Organization. I SBN 978 92 4 159607 7 (NLM classification: W 84.3) © World Health Organization 2007 All rights reserved. Publications of the World Health Organization can be obtained from WHO Press, World Health Organization, 20 Avenue Appia, 1211 Geneva 27, Switzerland (tel.: +41 22 791 3264; fax: +41 22 791 4857; e-mail: bookorders@who.int). Requests for permission to reproduce or translate WHO publications – whether for sale or for noncommercial distribution – should be addressed to WHO Press, at the above address (fax: +41 22 791 4806; e-mail: permissions@who.int). The designations employed and the presentation of the material in this publication do not imply the expression of any opinion whatsoever on the part of the World Health Organization concerning the legal status of any country, territory, city or area or of its authorities, or concerning the delimitation of its frontiers or boundaries. Dotted lines on maps represent approximate border lines for which there may not yet be full agreement. The mention of specific companies or of certain manufacturers’ products does not imply that they are endorsed or recommended by the World Health Organization in preference to others of a similar nature that are not mentioned. Errors and omissions excepted, the names of proprietary products are distinguished by initial capital letters. All reasonable precautions have been taken by the World Health Organization to verify the information contained in this publication. However, the published material is being distributed without warranty of any kind, either expressed or implied. The responsibility for the interpretation and use of the material lies with the reader. In no event shall the World Health Organization be liable for damages arising from its use. Printed by the WHO Document Production Services, Geneva, Switzerland 4 C O N T E N T S L I S T O F A B B R E V I A T I O N S ii F O R E W O R D iii E X E C U T I V E S U M M A R Y v I N T R O D U C T I O N 1 Objectives 1 Health system basics 2 H E A L T H S Y S T E M S C H A L L E N G E S AN D O P P O R T U N I T I E S 7 Managing multiple objectives and competing demands 7 A significant increase in funding for health 8 ‘Scaling-up’ is not just about increasing spending 8 The health systems agenda is not static 10 Development partners have their impact on health systems 11 W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S 13 A. A single framework with six building blocks and priorities 14 B. Health systems and programmes: getting results 26 C. A more effective role for WHO at country level 28 D. The role of WHO in the international health systems agenda 31 I M P L I C A T I O N S F O R T H E W A Y W H O W O R K S 35 New ways of working across the Organization 35 Enhancing staff competencies and capacity 36 Strengthen WHO’s convening role, and role in health system partnerships 37 Next Steps 37 Annex 1 W H O ’ S C O R E F U N C T I O N S A N D M E D I U M - T E R M S T R A T E G I C O B J E C T I V E S 38 Annex 2 R E F E R E N C E S 39 Annex 3 U S E F U L W E B L I N K S 44 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S i 5 ii E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S L I S T O F A B B R E V I A T I O N S AC R O N Y M F U L L T I T L E AU African Union CCS WHO Country Cooperation Strategies EURO WHO, Regional Office for Europe GATS General Agreement Trade in Services GAVI Global Alliance on Vaccines Initiative GAVI-HSS GAVI Health System Strengthening GDP Gross Domestic Product GHPs Global Health Partnerships GOARN Global Outbreak And Response Network HIV/AIDS Human Immunodeficiency Virus / Acquired Immunodeficiency Syndrome HSAN Health Systems Action Network IMAI Integrated Management of Adult Illness IMCI Integrated Management of Child Illness LHW Lady Health Worker MDG Millennium Development Goal MOH Ministry of Health MTSP Medium-Term Strategic Plan NEPAD New Partnership for Africa’s Development NGO Non-Governmental Organization OECD Organisation for Economic Co-operation and Development SARS Severe Acute Respiratory Syndrome TB T uberculosis TTR Treat, Train and Retain initiative UN United Nations UNITAID International Drug Purchasing Facility WHO World Health Organization 6 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S iii F O R E W O R D The strengthening of health systems is one of six items on my Agenda for WHO. The strategic importance of Strengthening Health Systems is absolute. The world has never possessed such a sophisticated arsenal of interventions and technologies for curing disease and prolonging life. Yet the gaps in health outcomes continue to widen. Much of the ill health, disease, premature death, and suffering we see on such a large scale is needless, as effective and affordable interventions are available for prevention and treatment. The reality is straightforward. The power of existing interventions is not matched by the power of health systems to deliver them to those in greatest need, in a comprehensive way, and on an adequate scale. This Framework for Action addresses the urgent need to improve the performance of health systems. It is issued at the midpoint in the countdown to 2015, the year given so much significance and promise by the Millennium Declaration and its Goals. On present trends, the health-related Goals are the least likely to be met, despite the availability of powerful drugs, vaccines and other tools to support their attainment. The best measure of a health system’s performance is its impact on health outcomes. International consensus is growing: without urgent improvements in the performance of health systems, the world will fail to meet the health-related Goals. As just one example, the number of maternal deaths has stayed stubbornly high despite more than two decades of efforts. This number will not fall significantly until more women have access to skilled attendants at birth and to emergency obstetric care. As health systems are highly context-specific, there is no single set of best practices that can be put forward as a model for improved performance. But health systems that function well have certain shared characteristics. They have procurement and distribution systems that actually deliver interventions to those in need. They are staffed with sufficient health workers having the right skills and motivation. And they operate with financing systems that are sustainable, inclusive, and fair. The costs of health care should not force impoverished households even deeper into poverty. This Framework for Action moves WHO in the right direction, on a course that must be given the highest international priority. WHO staff, working at all levels of the Organization, are its principal audience, but basic concepts, including the fundamental “building blocks” of health systems, should prove useful to policy-makers within countries and in other agencies. Margaret Chan Director-General 7 WHO/Jonathan Perugia 8 v It will be impossible to achieve national and international goals – including the Millennium Development Goals (MDGs) – without greater and more effective investment in health systems and services. While more resources are needed, government ministers are also looking for ways of doing more with existing resources. They are seeking innovative ways of harnessing and focusing the energies of communities, non-governmental organizations (NGOs) and the private sector. They recognize that there is no guarantee the poor will benefit from reforms unless they are carefully designed with this end in mind. Furthermore, they acknowledge that only limited success will result unless the efforts of other sectors are brought to bear on achieving better health outcomes. All these are health systems issues. The World Health Organization (WHO) faces many of the same challenges faced by countries: making the health system strengthening agenda clear and concrete; creating better functional links between programmes with mandates defined in terms of specific health outcomes and those with health systems as their core business; ensuring that the Organization has the capacity to respond to current issues and identify future challenges; and ensuring that institutional assets at each level of the Organization (staff, resources, convening power) are used most effectively. The primary aim of this Framework for Action is to clarify and strengthen WHO’s role in health systems in a changing world. There is continuity in the values that underpin it from its constitution, the Alma Ata Declaration of Health For All, and the principles of Primary Health Care. Consultations over the last year have emphasized the importance of WHO’s institutional role in relationship to health systems. The General Programme of Work (2006-2015) and Medium-term Strategic Plan 2008-2013 (MTSP) focus on what needs to be done. While reaffirming the technical agenda, this Framework concentrates more on how the WHO secretariat can provide more effective support to Member States and partners in this domain. There are four pillars to WHO’s response, each with its set of strategic directions: A single Framework with six building blocks A key purpose of the Framework is to promote common understanding of what a health system is and what constitutes health systems strengthening. Clear definition and communication is essential. If it is argued that health systems need to be strengthened, it is essential to be clear about the problems, where and why investment is needed, what will happen as a result, and by what means change can be monitored. The approach of this Framework is to define a discrete number of “building blocks” that make up the system. These are based on the functions defined in World health report 2000. The building blocks are: service delivery; health workforce; information; medical products, vaccines and technologies; financing; and leadership and governance (stewardship). The building blocks serve three purposes. First, they allow a definition of desirable attributes – what a health system should have the capacity to do in terms of, for example, health financing. Second, they provide one way of defining WHO’s priorities. Third, by setting out the entirety of the health systems agenda, they provide a means for identifying gaps in WHO support. While the building blocks provide a useful way of clarifying essential functions, the challenges facing countries rarely manifest themselves in this way. Rather, they require a more integrated response that recognizes the inter-dependence of each part of the health system. E X E C U T I V E S U M M A R Y E V E R Y B O D Y ’ S B U S I N E S S S – E X E C U T I V E S U M M A R Y 9 vi Health systems and health outcome programmes: getting results WHO’s involvement in all aspects of health and health systems constitutes a comparative advantage. Nevertheless, it is clear that, in too many instances, WHO’s support can be fragmented between advice focusing on particular health conditions (that may not always take systems or service delivery issues into account) and advice on particular aspects of health systems provided in isolation. While there are good examples of how both streams of activity can work together, the challenge is to develop a more systematic and sustained approach that responds better to the needs of Member States. Several productive relationships have been established, bringing together “programme” and “systems” expertise. These include work on costing and cost-effectiveness; the Treat, Train and Retain (TTR) initiative linking systems work on health service staffing with improving access to HIV/AIDS care and treatment, and the work across WHO stimulated by the Global Alliance on Vaccines Initiative (GAVI) Health Systems Strengthening window. Three complementary directions to a more strategic response are proposed: extending existing interactions; better and more systematic communication and awareness among all WHO staff on how to think systematically about health system processes, constraints and what to do about them; greater consistency, quality and efficiency in the production of methods, tools and data reporting across WHO. Attention to institutional incentives is also needed. A more effective role for WHO at country level Countries at different levels of development look for different forms of engagement with WHO as they seek to improve their health systems’ performance. Some are primarily interested in exchanging ideas and experiences in key aspects of policy (such as health worker migration); getting wider international exposure for important domestic agendas (such as patient safety or the health of indigenous populations); and developing norms and standards for measuring performance. Countries at all levels of development look to WHO for comparative experience in relation to different aspects of reform. But it is countries at a lower level of income – as evidenced increasingly in WHO Country Cooperation Strategies (CCS) – that seek more direct involvement in overall policy and health systems development. THe six building blOcks Of a HealTH sysTem E V E R Y B O D Y ’ S B U S I N E S S S – E X E C U T I V E S U M M A R Y • Good health services are those which deliver effective, safe, quality personal and non-personal health interventions to those that need them, when and where needed, with minimum waste of resources. • A well-performing health workforce is one that works in ways that are responsive, fair and efficient to achieve the best health outcomes possible, given available resources and circumstances (i.e. there are sufficient staff, fairly distributed; they are competent, responsive and productive). • A well-functioning health information system is one that ensures the production, analysis, dissemination and use of reliable and timely information on health determinants, health system performance and health status. • A well-functioning health system ensures equitable access to essential medical products, vaccines and technologies o f assured quality, safety, efficacy and cost-effectiveness, and their scientifically sound and cost-effective use. • A good health financing system raises adequate funds for health, in ways that ensure people can use needed services, and are protected from financial catastrophe or impoverishment associated with having to pay for them. It provides incentives for providers and users to be efficient. • Leadership and governance in volves ensuring strategic policy frameworks exist and are combined with effective oversight, coalition- building, regulation, attention to system-design and accountability. 10 vii Four strategic directions are proposed. First, there is a need to improve capacity to diagnose health systems constraints. Second, WHO should seek more active and consistent engagement in overall sector policy processes and strategies. In this context, engagement in key policy events should involve all levels of the Organization. Third, WHO’s efforts should be directed towards building national capacity in policy analysis and management. Lastly, tracking trends in health systems performance needs to be geared first and foremost towards national decision making. The role of WHO in the international health systems agenda In addition to supporting health systems strengthening in individual Member States, WHO has an international role. The international health environment is increasingly crowded. There are three main directions for WHO. First, the Organization continues to produce global norms, standards and guidance. These include health systems concepts, methods and metrics; synthesizing and disseminating information on “what works and why”, and building scenarios for the future. The second direction concerns the building or shaping of international systems that impact on health. These include systems and networks for identifying and responding to outbreaks and emergencies. They also include WHO’s role as a key actor in influencing aid architecture as it affects health systems. The third direction concerns how WHO is working more directly with other international partners on their support for health systems strengthening. This can be through global health partnerships (GHPs), such as the Global Fund to Fight HIV/AIDS, Tuberculosis and Malaria and GAVI, the larger philanthropic foundations, the World Bank and regional development banks and bilaterals, as well as stakeholders in the non-government and corporate sector. Success will depend on how well WHO uses its institutional assets and instruments. WHO must make greater use of existing staff: by strengthening their capacity in health sector policy and strategy development; by developing a professional network of staff working on health systems; and by getting a better match between supply and demand in specific policy areas. It must look at the business rules that govern planning and budgeting, and explore ways in which the integrity of WHO’s MTSP can be maintained, while promoting joint work across different programmes. Several health systems specific partnerships have been launched in the last two years, including the Global Health Workforce Alliance and the Health Metrics Network. WHO needs to leverage the benefits these partnerships offer to countries and international partners, and negotiate ways for partnerships to support WHO core functions. In terms of judging results, the MTSP defines specific results for WHO’s activities in health systems development. E V E R Y B O D Y ’ S B U S I N E S S S – E X E C U T I V E S U M M A R Y 11 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S viii WHO/Jonathan Perugia 12 1 Health outcomes are unacceptably low across much of the developing world, and the persistence of deep inequities in health status is a problem from which no country in the world is exempt. At the centre of this human crisis is a failure of health systems. Much of the burden of disease can be prevented or cured with known, affordable technologies. The problem is getting drugs, vaccines, information and other forms of prevention, care or treatment – on time, reliably, in sufficient quantity and at reasonable cost – to those who need them. In too many countries the systems needed to do this are on the point of collapse, or are accessible only to particular groups in the population. Failing or inadequate health systems are one of the main obstacles to scaling-up interventions to make achievement of internationally agreed goals such as the MDGs a realistic prospect. There is widespread acceptance of the basic premise underlying this Framework – that only through building and strengthening health systems will it be possible to secure better health outcomes. The key question is what does this mean in practice? The growing recognition of the importance of health systems increases the urgency of this question. Objectives • Promote common understanding We need a common understanding of what a health system is, and what activities are included in health systems strengthening – in countries at different levels of development and with different social, institutional and political histories. • Address new challenges and set priorities Health systems worldwide are having to cope with a changing environment: epidemiologically, in terms of changing age structures, the impact of pandemics and the emergence of new threats; politically, in terms of changing perceptions about the role of the state and its relation with the private sector and civil society; technically, in terms of the growing awareness that health systems are failing to deliver – that too often they are inequitable, regressive and unsafe, and so constitute one of the rate limiting factors to achieving better development outcomes; institutionally, especially in low-income countries, in having to deal with an increasingly complex aid architecture. Some of the main challenges and priorities, both old and new, are discussed in the next section. • Address questions of health system financiers For those who finance healthcare – from the general public, through national ministries of finance, development banks, bilateral agencies and global funds – the issue is not just one of refining definitions and concepts. If health systems are to be strengthened, where is more spending most needed? How and by whom should it be financed and how can that financing be sustained? How can financiers monitor the progress of change? What indeed are the characteristics of a “strengthened system” and how can they be measured? • Strengthen WHO’s role in health systems, in a changing world There is a growing demand for WHO to do more in health systems. While this may include greater levels of investment, it will also require a consideration of whether WHO could use its resources more effectively, either through different patterns of allocation or different ways of working. The importance of health systems as part of the global health agenda and in terms of WHO’s response is reflected in the 11 th General Programme of Work (2006-2015) and the Medium-term Strategic Plan (2008-2013). This Framework spells out in more detail the policy challenges faced by countries, and the steps for a more effective institutional response by the WHO Secretariat. I N T R O D U C T I O N E V E R Y B O D Y ’ S B U S I N E S S S – I N T R O D U C T I O N 13 2 How will the Framework for Action add value to WHO’s work? Support for health systems strengthening is the most frequently mentioned priority in WHO Country Cooperation Strategies 1 (CCSs). Two sorts of expertise are wanted from WHO: first, in specific technical areas of health systems; second, in strategic support to governments as they strive to reconcile competing priorities and sources of advice. That said, however, establishing WHO’s position as a key provider of health systems support at country level – given the many actors in this area – needs to be based on a clear understanding of priorities, capacity and comparative advantage. Several regional offices have defined regional health systems strategies and/or technical strategies in specific areas such as health financing. Similarly, several technical programmes in WHO are developing work programmes on systems strengthening. This document sets them within a Framework for Action for the Organization as a whole. The Framework is about ways of working in WHO. Two sets of issues are particularly important. How can we develop more synergistic working relationships between the technical programmes, which focus on particular health outcomes, and the specialist health systems groups in the organization? And, how can we ensure better links between WHO’s engagement in policy processes at country level and the health systems strengthening activities that flow from them? The importance of working in new ways gives the Framework for Action its title. Health systems strengthening is “everybody’s business”. Health system basics Any strategy for strengthening health systems needs a basic shared perception of what a health system is, what it is striving to achieve, and how to tell if it is moving in the desired direction. • What is a health system? A health system consists of all organizations, people and actions whose primary intent is to promote, restore or maintain health 2 . This includes efforts to influence determinants of health as well as more direct health-improving activities. A health system is therefore more than the pyramid of publicly owned facilities that deliver personal health services. It includes, for example, a mother caring for a sick child at home; private providers; behaviour change programmes; vector-control campaigns; health insurance organizations; occupational health and safety legislation. It includes inter-sectoral action by health staff, for example, encouraging the ministry of education to promote female education, a well known determinant of better health. • Guiding values and principles The directions set out for WHO in this document are determined by the values and goals enshrined in the Alma Ata Declaration; WHO’s commitments on gender and human rights 3 and the World health report 2000. • Health system goals Health systems have multiple goals. The World health report 2000 defined overall health system outcomes or goals as: improving health and health equity, in ways that are responsive, financially fair, and make the best, or most efficient, use of available resources. There are also important intermediate goals: the route from inputs to health outcomes is through achieving greater access to and coverage for effective health interventions, without compromising efforts to ensure provider quality and safety. WHO country Presence 2005: ccss provide the medium-term strategic framework for WHO’s work at country level. 2 This is an expanded version of the definition given in the World health report 2000 Health systems: improving Performance. declaration of alma ata, 978; universal declaration on Human Rights 948; WHO gender Policy 2002. The Right to Health and other human rights instruments institutionalise in law many aspects of Primary Health care. E V E R Y B O D Y ’ S B U S I N E S S S – I N T R O D U C T I O N THe WHO HealTH sysTem fRameWORk 14 3 • Health system building blocks To achieve their goals, all health systems have to carry out some basic functions, regardless of how they are organized: they have to provide services; develop health workers and other key resources; mobilize and allocate finances, and ensure health system leadership and governance (also known as stewardship, which is about oversight and guidance of the whole system). For the purpose of clearly articulating what WHO will do to help strengthen health systems, the functions identified in the World health report 2000 have been broken down into a set of six essential ‘building blocks’. All are needed to improve outcomes. This is WHO’s health system framework. • Desirable attributes Irrespective of how a health system is organized, there are some desired attributes for each building block that hold true across all systems. THe six building blOcks Of a HealTH sysTem: aims and desiRable aTTRibuTes E V E R Y B O D Y ’ S B U S I N E S S S – I N T R O D U C T I O N • Good health services are those which deliver effective, safe, quality personal and non-personal health interventions to those who need them, when and where needed, with minimum waste of resources. • A well-performing health workforce is one which works in ways that are responsive, fair and efficient to achieve the best health outcomes possible, given available resources and circumstances. I.e. There are sufficient numbers and mix of staff, fairly distributed; they are competent, responsive and productive. • A well-functioning health information system is one that ensures the production, analysis, dissemination and use of reliable and timely information on health determinants, health systems performance and health status. • A well-functioning health system ensures equitable access to essential medical products, vaccines and technologies o f assured quality, safety, efficacy and cost-effectiveness, and their scientifically sound and cost-effective use. • A good health financing system raises adequate funds for health, in ways that ensure people can use needed services, and are protected from financial catastrophe or impoverishment associated with having to pay for them. • Leadership and governance in volves ensuring strategic policy frameworks exist and are combined with effective oversight, coalition- building, the provision of appropriate regulations and incentives, attention to system-design, and accountability. THe WHO HealTH sysTem fRameWORk FINANCING ServIC e deLI very LeAderSHIP / GOverNANCe IMPrOved HeALTH (LeveL ANd eQUITy) reSPONSIveNeSS SOCIAL ANd FINANCIAL rISK PrOTeCTION IMPrOved eFFICIeNCy sysTem building blOcksOVeRall gOals / OuTcOmes ACCeSS COverAGe QUALITy SAFeTy HeALTH WOrKFOrCe INFOrMATION MedICAL PrOdUCTS, vACCINeS & TeCHNOLOGIeS 15 4 E V E R Y B O D Y ’ S B U S I N E S S S – I N T R O D U C T I O N • Multiple, dynamic relationships A health system, like any other system, is a set of inter-connected parts that must function together to be effective. Changes in one area have repercussions elsewhere. Improvements in one area cannot be achieved without contributions from the others. Interaction between building blocks is essential for achieving better health outcomes. • Health system strengthening Is defined as improving these six health system building blocks and managing their interactions in ways that achieve more equitable and sustained improvements across health services and health outcomes. It requires both technical and political knowledge and action. • Access and coverage Since notions of improved access and coverage lie at the heart of this WHO health system strengthening strategy, there has to be some common understanding of these terms. • Is progress being made? A key concern of governments and others who invest in health systems is how to tell whether and when the desired improvements in health system performance are being achieved. Convincing indicators that can detect changes on the ground are needed. Throughout the world, countries try to protect the health of their citizens. They may be more or less successful, and more or less committed, but the tendency is one of trying to make progress, in three dimensions. First, countries try to broaden the range of benefits (programmes, interventions, goods, services) to which their citizens are entitled. Second, they extend access to these health goods and services to wider population groups, and ultimately to all citizens: the notion of universal access to these benefits. Finally, they try to provide citizens with social protection against untoward financial and social consequences of taking up health care: of particular interest is protection against catastrophic expenditure and poverty. In health policy and public health literature the shorthand for these entitlements of universal access to a specified package of health benefits and social protection is universal coverage. The words access and coverage are also used to denote measurable targets, as well as aspirational goals. For example, many epidemiologists and disease control programme managers use the term “coverage” to measure the proportion of a target population that benefits from an intervention. On the other hand, when policy makers or health economists in Thailand, France or the USA talk about moving towards universal coverage, they are striving for access to a broadening range of benefits, for all citizens without exclusion, and with the necessary social protection. Depending on the context, the accent may be primarily on broadening the package; or on extending coverage in excluded groups; or on improving social protection. In all cases though, what is at stake is the public responsibility for ensuring all citizens’ entitlements to the protection of their health – the political idea that led WHO to promote Health For All. These differences in usage are a fact of life in the multi-disciplinary field o f health. What is important is that the differences are understood. ‘access’ and ‘cOVeRage’: undeRsTanding cuRRenT usage 16 5 WHaT can We leaRn fROm THe PRimaRy HealTH caRe Values and aPPROacH? E V E R Y B O D Y ’ S B U S I N E S S S – I N T R O D U C T I O N Primary Health Care, as articulated in the Alma Ata declaration of 1978, was a first international attempt to unify thinking about health within a single policy framework. Developed when prospects for growth in many countries were bright, Primary Health Care remains an important force in thinking about health care in both the developed and developing world. Although often honoured more in the breach than in the observance, its underpinning values – universal access, equity, participation and intersectoral action – are central to WHO’s work and to health policies in many countries today. The Primary Health Care approach also emphasizes the importance of health promotion and the use of appropriate technology. As the non-communicable disease burden rises and the menu of diagnostic and therapeutic technologies expands, these principles – backed up by an increasing body of evidence on intervention cost-effectiveness – are as important for health policy makers to keep in mind today as they were thirty years ago. The term Primary Health Care is important in a second way. The term signifies an important approach to health care organization in which the primary, or first contact, level – u sually in the context of a health district – acts as a driver for the health care delivery system as a whole. Again, while the language may have changed – for example the term ‘close-to-client’ care is also used, and a wide range of service delivery models have evolved – the principle of providing as much care as possible at the first point of contact effectively backed up by secondary level facilities that concentrate on more complex care, r emains a key aim in many countries. The concept of integrated P rimary Health Care is best viewed from the perspective of the individual: the aim being to develop service delivery mechanisms that encourage continuity of care for an individual across health conditions, across levels of care, and over a lifetime. The values and principles of Primary Health Care remain constant, but there are lessons from the past, which are particularly important when looking ahead. First, despite increased funding, resources for health will always be limited, and there is a responsibility to achieve the maximum possible with available resources. Second, past efforts to implement a Primary Health Care approach focused almost exclusively on the public sector. In reality, for many people – poor, as well as rich – private providers are the first point of contact, and responsible health system oversight involves taking account of private as well as public providers. Third, while keeping its focus on the community and first contact care, Primary Health Care needs to recognize the problems associated with relying on voluntarism alone. leadeRsHiP and gO VeRnance ServIC e deLI very HUMAN reSOUrCeSINFOrMATION FINANCING MedICINeS ANd TeCHNOLOGIeS 17 WHO/Jim Holmes 18 7 Health systems have to deal with many challenges. As the spectrum of ill-health changes, so health systems have to respond. Their capacity to do so is influenced by a variety of factors. Some operate at a national or sub-national level, such as the availability of financial and human resources, overall government policies in relation to decentralization and the role of the private sector. Some operate through other sectors. Increasingly, however, national health systems are subject to forces that affect performance, such as migration and trade factors, operating at an international level. Some health policy challenges are primarily of concern to low-income countries. However, despite national differences, many policy issues are shared across remarkably different health systems. Concerns such as the impact of aging populations, the provision of chronic care or social security reform are no longer the concern of industrialized countries alone. Similarly, the threat posed by new epidemics, such as avian or human pandemic influenza, requires a response from all countries rich and poor. The differences lie in the relative severity of challenges being faced, the way a particular health system has evolved, and the economic, social and political context – all of which determine the nature and effectiveness of the response. Given the size of global spending on health and concerns about health systems performance, the question is, “Why aren’t health systems working better?” Managing multiple objectives and competing demands In the face of fierce competition for resources, governments worldwide have to manage multiple objectives and competing demands. As they strive for greater efficiency and value for money, they must seek ways to achieve more equity in access and outcomes and to reduce exclusion. They are under pressure to ensure that services are effective, of assured quality and safe, and that health providers are responsive to patients’ demands. Progress in one direction may mean compromise in another. For example, the pressure to increase access to HIV/AIDS care and treatment, which has helped bring visibility to the human resources crisis in Africa, brings its own pressures on the capacity of the health system to handle other causes of ill-health. Progress in increasing staff retention in the public sector through better pay packages may mean compromise in containing costs. Competition for resources may be between hospitals and primary level care; between prevention and treatment; between professional groups; between public and private sectors; between those engaged in efforts to treat one condition versus another; between capital and recurrent expenditures. This means health system strengthening requires careful judgement and hard choices. It can be better informed by evidence and by the use of technical tools, but ultimately it is a political process and reflects societal values. A national health sector strategy is one way to reconcile multiple objectives and competing demands. To be robust, a sector strategy requires sound logic and sufficient support. Plans need to be costed; budgets have to balance ambition with realism. The necessary processes have to be managed in an inclusive way, and linked with national development planning processes such as poverty reduction strategies. These, together with transparent systems to track effects, are the key to unlocking more resources. H E A L T H S Y S T E M S C H A L L E N G E S A N D O P P O R T U N I T I E S E V E R Y B O D Y ’ S B U S I N E S S S – H E A L T H S Y S T E M S C H A L L E N G E S A N D O P P O R T U N I T I E S 19 8 A significant increase in funding for health Health systems are a means to the end of achieving better health outcomes. In many countries, resources for health have increased from both domestic budgets and, in lower- and middle-income countries, from external development partners as well. There is growing interest in the array of domestic financing mechanisms that can be drawn upon to move towards universal coverage, including tax-based funding, social health insurance, community or micro-insurance, micro-credit and conditional cash transfers. All of these mechanisms make major demands on managerial capacity. On the other hand, where providers depend largely on out-of-pocket payments for their income, there is over-provision of services for people who can afford to pay, and lack of care for those who cannot. Much of the increase in investment by external partners has focused on particular diseases or health conditions. The global health landscape has been transformed in the last ten years with the emergence of multiple, billion-dollar global health partnerships such as the Global Fund and the GAVI Alliance. These have helped generate growing political support for increasing access to care and treatment for many critical health conditions, and have also thrown a spotlight on longstanding systems issues such as logistics, procurement and staffing. Moreover the growing demands for provision of lifelong treatments highlights the need for policies that protect people from catastrophic spending. ‘Scaling-up’ is not just about increasing spending It is increasingly recognized that scaling-up is not just about increasing investment. Close scrutiny of what is involved points to a set of health systems challenges, most of which are equally pertinent in higher as well as low-income settings. Countries both rich and poor are looking for ways of doing more with existing resources. In many health systems, existing health workers could be more productive if they had access to critical material and information resources, clearly defined roles and responsibilities, better supervision and an ability to delegate tasks more appropriately. Changes in overall intervention-mix and skill- mix could create efficiencies. In many instances, extending coverage or quality cannot be achieved simply by replicating existing models for service delivery or focusing only on the public sector. In addition, decision- makers seek innovative ways to engage with communities, NGOs and the private sector. Promising experiences, such as working with informal providers to expand TB care, the social marketing of bed-nets or contracting with NGOs, need to be shared. It is important to take note of what did and did not work in the past. Careful analysis is needed about which local initiatives are genuinely amenable for replication and expansion. Multiple barriers cannot all be addressed or overcome at once. Judgements have to be made between pushing to quickly get specific outcomes and building systems and institutions. Managing the tension between saving lives and livelihoods and starting the process of re-building the state is a particular challenge in fragile states. There is no guarantee that the poor will benefit from reforms unless they are carefully designed with this end in mind. It is well-known that the child health MDG target can be reached with minimal gains among the poorest. And in many countries, groups such as the poor – and too often women more than men – migrants and the mentally ill are largely invisible to decision- makers. These require specific attention, but introducing strategies that promote equity rather than the converse is not straightforward, as the debates around rapidly scaling-up HIV/AIDS treatment showed. Demand-side factors also determine use, so understanding the incentives and disincentives for seeking care is also important. E V E R Y B O D Y ’ S B U S I N E S S S – H E A L T H S Y S T E M S C H A L L E N G E S A N D O P P O R T U N I T I E S 20 9 HealTH sysTems: a sHORT His TORy HealTH sysTem cHallenges: a feW facTs and figuRes • Globally, health is a US$3.5 trillion industry, or equal to 8% of the world's GDP. • Large health inequalities persist: even within rich countries such as USA and Australia, life expectancy still varies across the population by over 20 years. • Recent essential medicines surveys in 39 mainly low- and low-middle-income countries found that, while there was wide variation, average availability was 20% in the public sector, and 56% in the private sector. • Each year, 100 million people are impoverished as a result of health spending. • Extreme shortages of health workers exist in 57 countries; 36 of these are in Africa. • In over 60 countries, less than a quarter of deaths are recorded by vital registration systems. • An estimated 50% of medical equipment in developing countries is not used, either because of a lack of spare parts or maintenance, or because health workers do not know how to use it. • Private providers are used by poor as well as rich people. For example, in Bangladesh, around ¾ of health service contacts are with non-public providers. • In 2000, less than 1% of publications on Medline were on health services and systems research. • Globally, about 20% of all health aid goes to support governments' overall programmes (i.e. is given as general budget or sector support), while an estimated 50% of health aid is off budget. • There has been a rapid increase in global health partnerships. More than 80 now exist, of which WHO houses over 30. E V E R Y B O D Y ’ S B U S I N E S S S – H E A L T H S Y S T E M S C H A L L E N G E S A N D O P P O R T U N I T I E S Health systems of some sort have existed as long as people have tried to protect their health and treat disease, but organized health systems are barely 100 years old, even in industrialized countries. They are political and social institutions. Many have gone through several, sometimes parallel and sometimes competing, generations of development and reform, shaped by national a nd international values and goals. Primary Health Care a s articulated in the Alma Ata declaration of 1978 was a first attempt to unify thinking about health within a single policy framework. Developed when prospects for growth in many countries were bright, Primary Health Care remains an important force in thinking about health care in both the developed and developing world. The financial optimism of the 1970s was soon dispelled in many parts of the world by a combination of high oil prices, low tax revenues and economic adjustment. Countries seeking to finance essential health care were faced with two difficult prescriptions: focus public spending on interventions that are both cost-effective and have public good characteristics (the message of the World Development Report 1993), and boost financing through charging users for services. Whilst many governments started to levy fees, most recognized the political impossibility of focusing spending on a few essential interventions alone. The results were predictable. The poor were deterred from receiving treatment and user fees yielded limited income. Moreover, maintaining a network of under- resourced hospitals and clinics, while human and financial resources were increasingly pulled into vertical programmes, increased pressures on health systems sometimes to the point of collapse. As the crisis in many countries deepened in the 1990s, so many governments looked to the wider environment for new solutions. If the health district was not working well it was because insufficient power was decentralized within government. If health workers were unproductive, then look to civil service reform. If hospitals were a drain on the budget, reduce capacity in the public sector. Infused with ideas from market-based reforms in Europe’s public services, and with new experiences emerging from transitional economies, health sector reform f ocused above all on doing more for less. Efficiency remained the watchword. It was not until towards the end of the decade that the international community started to confront the reality that running health systems on $10 per capita or less is just not a viable proposition. In this regard, the work of the Commission on Macroeconomics and Health and costing the global response to the HIV/AIDS pandemic finally broke the mould, making it acceptable to talk more realistically about resource needs. In the first decade of the 21st Century, many of the pressures remain. In the developed world, the public looks for signs that increased spending delivers results, while planners look nervously at the impact of ageing populations. In the d eveloping world, there are more resources for health but most are linked to specific programmes. But there are also signs of change. There is a wider recognition of inter-dependence and the importance of wider policy choices on health systems, particularly the impact of migration and trade. Similarly, it is clear that governments do not have all the answers. Productive relations with the private sector and voluntary groups are both possible and desirable. Governments have a much wider range of policy levers at their disposal. The challenge for WHO as their adviser, is to understand the whole menu and know when a nd how to mix the right combination of ingredients. 21 10 Success will be limited unless efforts of other sectors are brought to bear on achieving health outcomes. Scaling-up requires the following: working with ministries of finance to justify budget demands in the context of macroeconomic planning, and ensuring health is well reflected in poverty reduction strategies and medium-term expenditure frameworks; working with ministries of labour, education and the civil service on issues of pay, conditions, health worker training and retention; working with ministries of trade and industry around access to drugs and other supplies; and, with increasing decentralization, working with local government. Attention to health determinants must be maintained, as investments in education, housing, transport, water and sanitation, improved governance or environmental policy can all benefit health. Actions by other sectors can also have adverse effects on health, something that is recognized by the growing requirement for health impact assessments. The health systems agenda is not static Patterns of disease, care and treatment are changing. Eighty per cent of non-communicable disease deaths today are in low- and middle-income countries. Systems for managing the continuum of care – be it for HIV/AIDS or hypertension – pose different demands from those needed for acute intermittent care. New delivery strategies may create new demands on the health system. For example, the shift from traditional birth attendants to skilled birth attendants has implications for staffing, for referral systems, and in terms of upgrading facilities to deliver emergency obstetric care. New approaches to mental health and non-communicable diseases emphasize primary prevention, community care and well informed patients, all of which entail shifts from the traditional focus of institutional care. The introduction of new drugs, vaccines and technologies have an impact on staffing and training, but equally on health financing and service delivery. For example, some hospital-based treatments can now be delivered through day care centres. This is leading to a reappraisal of traditional service delivery models and strategies for increasing efficiency. Health systems are at the heart of how countries respond to new disease threats such as Severe Acute Respiratory Syndrome (SARS), avian flu, pandemic human influenza. International networks for identifying and responding to such security threats depend for their effectiveness on the ‘weakest link’. Accordingly, disease control efforts must be internationally coordinated. As well as testing the alert and response capacity of weak health systems, the attention such outbreaks generate presents important opportunities to catalyse and orchestrate support for improving them: by building epidemiological and laboratory capacity in the context of revised International Health Regulations, addressing patents and intellectual property rights, improving supply chain management and so forth. An estimated 25 million people are displaced today as a result of conflict, natural or man- made disasters. In such situations, local health systems become rapidly over-whelmed and multiple agencies often move in to assist. This leads to the paradoxical situation in which leadership is weaker than usual because it has been disrupted or divided, but the need for leadership is even greater. The continuing search for ways to strengthen leadership at such times includes emergency preparedness programmes, norms and standards, creating contingency funds and more interaction between UN agencies and other actors. Changes in public policy and administration, particularly decentralization, makes new demands on local authorities and may change fundamentally the role of central ministries. After years of relative inattention, there is now a resurgent interest in the role of the state. However, the emphasis is on ‘good governance’ and effective stewardship, rather than a return to earlier ‘command and control’ models. The public in most countries no longer accepts a passive role and rightly demands a greater say in how health services are run, including how health authorities are held accountable for their work. The information technology revolution has accelerated this change. E V E R Y B O D Y ’ S B U S I N E S S S – H E A L T H S Y S T E M S C H A L L E N G E S A N D O P P O R T U N I T I E S 22 11 There is a major emphasis on demonstrating results and value for money, not just in terms of health outcomes but also in being able to demonstrate progress in systems strengthening. There is also greater focus on corruption in the health sector, with distinctions being made between grand larceny, mismanagement and behaviours such as salary supplementation through informal payments. development partners have their impact on health systems Development partners impact health systems through support for the new global health partnerships – as well as through measures that can increase the predictability of aid – ideally making it easier for finance ministries to finance the long-term recurrent costs of salaries or life- saving medicines. Perhaps most importantly, the barriers to more rapid progress at country level observed by GHPs have helped to dispel the simple notion that health systems can be built around single diseases or interventions. At the same time, the emergence of new funds has highlighted challenges already faced by countries in managing multiple sources of finance. Multiple parallel policy processes or reporting systems have led to unnecessarily high transaction costs, and a concern that narrowly focused support is drawing scarce personnel away from other essential services and compromising a healthy balance of health services. As a result, many GHPs, along with bilateral agencies, are searching for ways to better harmonize and align their activities with national policies and systems. In short, countries face many challenges: making the case for more effective investment in health systems in a competitive funding environment; creating better functional links between programmes with mandates defined in terms of specific health outcomes and those with health systems as their core business; ensuring capacity to respond to current issues and identify future challenges; and ensuring that resources are used as effectively as possible. WHO faces these same challenges. Reducing HealTH inequaliTies in THailand E V E R Y B O D Y ’ S B U S I N E S S S – H E A L T H S Y S T E M S C H A L L E N G E S A N D O P P O R T U N I T I E S Between 1990 and 2000, Thailand significantly reduced its level of child mortality and at the same time halved inequalities in child mortality between the rich and the poor. These impressive results can be explained partly by substantial economic growth and reduced poverty over this period. However there were a number of other important strategies that contributed, many of which began to be put in place before 1990 but which were extended and maintained. These include improved insurance coverage and more equitable distribution of primary health care infrastructure and intervention coverage. From the 1970s onwards, a series of pro-poor health insurance schemes improved health service coverage. The initial step was to waive user charges for low-income families. This was followed by subsidized voluntary health insurance, then the extension of the government welfare scheme in the 1990s to all children under 12, the elderly and disabled, and to universal coverage from 2001. Also from the 1970s, health infrastructure and services were scaled up with a particular focus on Primary Health Care and community hospitals targeting the poorer, rural populations. Increased production, financial incentives and educational strategies led to a more equitable allocation of doctors in rural areas in the 1980s. This combination l ed to increased utilization of health services. For example, vaccination coverage rose from 20%-40% in the early 1980s to over 90% in the 1990s; skilled birth attendance rose from 66% to 95% between 1987 and 1999. Sources (see Annex 2, References): Vapattanawong P et al, 2007; Tangcharoensathien V et al 2004. 23 WHO/ christopher b lack 24 13 The analysis of challenges in the previous section provides some clear messages. WHO needs to communicate about health systems, in plain language, to the increasing range of actors involved in health. Health systems are clearly a means to an end, not an end in themselves. There needs to be a focus on providing support to countries in ways that better respond to their needs. Lastly, there is a major role for WHO at the international level. These messages determine the four inter-connected pillars of WHO’s response: A. A s ingle framework with six clearly defined building blocks B. Health systems and programmes: getting results C. A more effective role for WHO at country level d. The role of WHO in the international health systems agenda As the UN technical agency in health, WHO draws on its core functions in addressing these challenges. Some of the functions are not unique to WHO: other agencies are actively involved in, for example, developing tools or technical support. However, WHO’s mandate, neutral status and near-universal membership give it unique leverage and advantage. Indeed, having so many players active in health today does not reduce but rather accentuates the importance of WHO’s role in strengthening health systems. • WHO is involved in all aspects of health and health systems. It is therefore well-placed to understand how health system strengthening affects service delivery on the ground. • W HO is perceived by governments as a trusted adviser in a value-laden area because it is directly accountable to its Member States, and because it is not a major financier, so its advice is independent of loans or grants. • I n addition to its normative role, WHO’s network of 144 country and six regional offices puts it in a strong position to link national and international policy and strategy. • C ontinuous country presence makes WHO well-placed to support rapid responses to crises and also longer-term interventions needed for sustained improvement in health systems. In WHO’s key strategy documents, health systems are a priority. The General Programme of Work, “Engaging for Health”, provides the broad agenda for WHO in health systems development. The draft Medium-term Strategic Plan 2008-2013 has two strategic objectives explicitly concerned with health systems. However, other strategic objectives (listed in Annex 1) also include activities designed to strengthen health systems. As such, all WHO programmes are involved in some aspect of systems development. This reinforces a central principle of this health system strengthening Framework – it is “everybody’s business.” WHO’s involvement in all aspects of health and health systems is a strength and, too often, an under-utilized resource. Advice on health systems strengthening must be informed by: an understanding of what is needed to make sure that clinic staff address major causes of child or adult mortality; recognizing that the way hospitals deal with major accidents or complicated deliveries determines whether people are impoverished by the catastrophic cost of treatment; taking experience of the HIV/AIDS community in getting governments to work more effectively with private providers and those living with the disease. At the same time, of course, one cannot advise on health systems financing from the perspective of malaria or child health alone. WHO needs to set priorities. However, WHO cannot focus on one aspect of health systems development at the expense of another. Indeed, adopting a more holistic approach is a priority in itself. This section provides a broad view of where the main focus will be for each pillar of the strategy. The last section then sets out some of the implications that implementing the four pillars will have for the way WHO works. W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S 25 14 A. A single Framework with six clearly defined building blocks and priorities As previously mentioned, a health system, like any other system, is a set of inter-connected parts that have to function together to be effective. This pillar summarizes the main directions of WHO’s work in each of the health system building blocks, and where there are important linkages between them. PRiORiTies by building blOck 1 Service delivery: packages; delivery models; infrastructure; management; safety & quality; demand for care 2 Health workforce: n ational workforce policies and investment plans; advocacy; norms, standards and data 3 Information: f acility and population based information & surveillance systems; global standards, tools 4 Medical products, vaccines & technologies: n orms, standards, policies; reliable procurement; equitable access; quality 5 Financing: n ational health financing policies; tools and data on health expenditures; costing 6 Leadership and governance: h ealth sector policies; harmonization and alignment; oversight and regulation 1. ServIC e deLIvery In any health system, good health services are those which deliver effective, safe, good quality personal and non-personal 4 care to those that need it, when needed, with minimum waste. Services – be they prevention, treatment or rehabilitation – may be delivered in the home, the community, the workplace or in health facilities. Although there are no universal models for good service delivery, there are some well- established requirements. Effective provision requires trained staff working with the right medicines and equipment, and with adequate financing. Success also requires an organizational environment that provides the right incentives to providers and users. The service delivery building block is concerned with how inputs and services are organized and managed, to ensure access, quality, safety and continuity of care across health conditions, across different locations and over time. Attention is needed on the following: • D emand for services. Raising demand, appropriately, requires understanding the user’s perspective, raising public knowledge and reducing barriers to care – cultural, social, financial or gender barriers. Doing this successfully requires different forms of social engagement in planning and in overseeing service performance. • P ackage of integrated services. This should be based on a picture of population health needs; of barriers to the equitable expansion of access to services, and available resources such as money, staff, medicines and supplies. • O rganization of the provider network. The purpose of an organized provider network is to ensure close-to-client care as far as possible, contingent on the need for economies of scale; to promote individual continuity of care where needed, over time and between facilities; and to avoid unnecessary duplication and fragmentation of services. This means considering the whole network of providers, private as well as public; the package of services (personal, non-personal); whether there is over – or under – supply; functioning referral systems; the responsibilities of and linkages between different levels and types of provider including hospitals; the suitability of different delivery models for a specific setting; and the repercussions of changes in one group of providers on other groups and functions (e.g. on staff supervision or information flows). 4 non-personal services are also called population-based services. S e r v i c e d e l i v e r y E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S 26 15 • Management. The aim is to maximize service coverage, quality and safety, and minimize waste. Whatever the unit of management (programme, facility, district, etc.) any autonomy, which can encourage innovation, must be balanced by policy and programme consistency and accountability. Supervision and other performance incentives are also key. • I nfrastructure and logistics. This includes buildings, their plant and equipment; utilities such as power and water supply; waste management; and transport and communication. It also involves investment decisions, with issues of specification, price and procurement and considering the implications of investment in facilities, transport or technologies for recurrent costs, staffing levels, skill needs and maintenance systems. WHO is strongest in defining which health interventions should be delivered, with associated guidelines, standards and indicators for monitoring coverage. Most of this work is carried out on a programme-by-programme basis (e.g. for malaria, maternal or mental health). Increasingly, however, it is evident that there is a need to be sure that health systems in countries with differing levels of resources can accommodate the ideals that these norms imply. A further strength of many individual programmes is in exploring innovative models of service delivery, for example, involving private providers in the care of TB. Initiatives such as the Integrated Management of Child, or Adult, Illness (IMCI, IMAI) are responding to increasing interest in delivering packages of care. Priorities Building on the above, WHO will increase its attention to the challenges associated with delivering packages of care (prevention, promotion and treatment for acute and chronic conditions). The aim is to help develop mechanisms for integrated service delivery where possible, that is to say, mechanisms that encourage continuity of care for an individual where needed across health conditions and levels of care and over a lifetime. Priorities are as follows: • Integrated service delivery packages WHO will continue to produce and disseminate cost-effectiveness data for prevention and treatment, and define service standards and measurement strategies for tracking trends and inequities in service availability, coverage and quality. It will help define integrated packages of services, and the roles of primary and other levels of care in delivering the agreed packages, as part of its health policy development support. • Service delivery models WHO will increase efforts to capture experience with models for delivering personal and non-personal services in different settings, including fragile states. It will consider the whole network of public and private providers in order to enhance equitable access, quality and safety. It will synthesize and share experience of the costs, benefits and conditions for success of strategies to improve service delivery. These may include community health workers, task shifting, outreach, contracting, accreditation, social marketing, uses of new technologies such as telemedicine, hospital service organization and management, delegation to local health authorities, other forms of decentralization, etc. It will concentrate especially on lessons from those strategies that have been implemented on a large scale, and that have helped to improve services for the poor and other disadvantaged groups. It will consider the stewardship and governance implications of different service delivery models, for example, legislation for non-communicable diseases, approaches to regulating private providers and the consequences for health services of decentralization to local government. • Leadership and management WHO will support Member States to improve management of health services, resources and partners by health authorities, as a means to expand coverage and quality. This will be done through: promoting tools for analysing barriers to care, and management weaknesses; generating and sharing knowledge on strategies to improve management, often in the context of decentralization; developing local resource institutions’ capacity to support local health managers; and developing methods to monitor progress. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S S e r v i c e d e l i v e r y 27 16 2. HeALTH WOrKFOrCe Health workers are all people engaged in actions whose primary intent is to protect and improve health. A country’s health workforce consists broadly of health service providers and health management and support workers. This includes: private as well as public sector health workers; unpaid and paid workers; lay and professional cadres. Countries have enormous variation in the level, skill and gender-mix in their health workforce. Overall, there is a strong positive correlation between health workforce density and service coverage and health outcomes. In any country, a “well-performing” health workforce is one which is available, competent, responsive and productive. To achieve this, actions are needed to manage dynamic labour markets that address entry into and exits from the health workforce, and improve the distribution and performance of existing health workers. These actions address the following: • H ow countries plan and, if needed, scale-up their workforce asking questions that include: What strategic information is required to monitor the availability, distribution and performance of health workers? What are the regulatory mechanisms needed to maintain E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S • Patient safety and quality of care WHO will continue its focus on patient safety, and systems and procedures that improve safety. Related work on quality will foster approaches that take account of the full spectrum of interventions needed: treatment protocols and clinical management schedules; supportive supervision and performance assessment; training and continuing education; procedures for registration, licensing and inspection; and fora for dialogue and motivating providers. • Infrastructure and logistics The challenge of how to handle major capital investment decisions, such as hospitals, deserves more attention by WHO. Currently the effectiveness of its contributions in, for example, complex emergencies is limited. WHO will review current work on infrastructure and logistics, both investment decisions and developing sustainable infrastructure and logistics systems, identifying the gaps, what other agencies are doing and how WHO should position itself. • Influencing demand for care WHO will communicate international agreements on rights and responsibilities of citizens with regard to their health, and support their incorporation into national policy and practice. It will encourage effective use of the media in promoting health and the engagement of civil society organizations in service delivery planning and oversight, as a means to provide all those who need care, especially the poor and other vulnerable groups, with the confidence that they will be treated decently, fairly and with dignity. sTRengTHening PRimaRy HealTH caRe in laO PeOPle’s demOcRaTic RePublic Source (see Annex 2, References): Perks C et al 2006. A comprehensive Primary Health Care programme has been in place in the remote Sayaboury province since 1991. It has achieved impressive results. Between 1996 and 2003 health facility utilization tripled, maternal mortality dropped 50%, and by 2003 infant and child mortality were less than one- third the national average. These impressive changes are the result of a suite of interventions, coupled with modest but sustained support. Key interventions included: provincial and district management strengthening (training; regular supervision and performance assessment); training and regular supervision of dispensary staff village health volunteers and traditional birth attendants; construction and upgrading of dispensaries; staff development opportunities and incentives such as free medical treatment for volunteers; provision of essential equipment and seed capital for the revolving drug fund. Technical and financial support were provided throughout the 12 years. The external financial investment, roughly US$4 million, was equivalent to US$1 per person per year. H e a l t h W o r k f o r c e 28 17 quality of education/training and practice? In countries with critical shortages of health workers, how can they scale-up numbers and skills of health workers, in ways that are relatively rapid and sustainable? Which stakeholders and sectors need to be engaged (e.g. training institutions, professional groups, civil service commissions, finance ministries)? • H ow countries design training programmes so that they facilitate integration across service delivery and disease control programmes. • H ow countries finance scaling-up of education programmes and of numbers of health workers in a realistic and sustainable manner and in different contexts. • H ow countries organize their health workers for effective service delivery, at different levels of the system (primary, secondary, tertiary), and monitor and improve their performance. • H ow countries retain an effective workforce, within dynamic local and international labour markets. Traditionally, much of WHO’s focus in countries has been on training, especially in-service training. More recently, WHO has mobilized greater international awareness of health workforce shortages and performance challenges, especially in Africa, and has been instrumental in creating the Global Health Workforce Alliance, a partnership intended to tackle them in a more coherent way. It has also shed light on the available but still limited knowledge base on workforce policy options through its World health report 2006. Priorities • International norms, standards and databases WHO will maintain and strengthen the Global Atlas on the health workforce. It will facilitate the generation and exchange of information on health workforce availability, distribution and performance by supporting regional workforce observatories. • Realistic strategies WHO will increase its support for realistic national health workforce strategies and plans for workforce development. These will consider the range, skill-mix and gender balance of health workers (health service providers and management and support workers) needed to deliver the agreed package of services across priority programmes. They will address workforce education, recruitment, retention and performance and define regulatory options to improve quality of practice, such as licensing and accreditation. • Crisis countries In countries with a workforce crisis, WHO will act on the basis of agreed multi-stakeholder health workforce strategies (such as the Treat, Train, Retain Initiative) and best knowledge to take rapid action. Workforce strategies will be developed in collaboration with priority programmes and with key stakeholders in other sectors as needed. • Costing WHO will generate knowledge about the financial costs of scaling-up and then maintaining the expanded health workforce, as well as ways to address financial sustainability, and use this in dialogue with international financing institutions. • Training WHO will support the redesign of training programmes to produce the spectrum of health workers (service providers and management and support workers) to deliver health services. It will explore and document ways to maximise the use of priority programme training initiatives, and mechanisms such as accreditation to assure quality of training programmes. • Evidence WHO will synthesize and disseminate evidence on the following: ways to organize the health workforce for more effective service delivery and improved health worker performance; E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S H e a l t h W o r k f o r c e 29 18 E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S 3. INFOrMATION The generation and strategic use of information, intelligence and research on health and health systems is an integral part of the leadership and governance function. In addition, however, there is a significant body of work to support development of health information and surveillance systems, the development of standardized tools and instruments, and the collation and publication of international health statistics. These are the key components of the Information building block. This is increasingly more than just a national concern. As part of efforts to create a more secure world, countries need to be on the alert and ready to respond collectively to the threat of epidemics and other public health emergencies. A well functioning health information system is one that ensures the production, analysis, dissemination and use of reliable and timely health information by decision-makers at different levels of the health system, both on a regular basis and in emergencies. It involves three domains of health information: on health determinants; on health systems performance; and on health status. To achieve this, a health information system must: deVel OPing neW cadRes: lady HealTH WORkeRs in PakisTan Sources (see Annex 2, References): Oxford Policy Management, 2002; Arif GM Asian Development Bank, 2006. Desplats M, et al, Médecine Tropicale, 2004. In 1994, the Government of Pakistan launched the National Family Planning and Primary Care Programme, to prevent and treat common ailments at the community level in a cost-effective manner. The lynch pin of this programme was the “Lady Health Worker” (LHW). These are salaried community health workers with eight years of schooling, who receive a 15-month training session followed by one year of field practice. By the end of 2006, there were 96,000 LHWs, and another 14,000 LHWs will be deployed by end 2008. Each LHW serves a population of 1000-1500, of whom 75% live in rural areas. Each LHW is attached to a government health facility, from which they receive regular in-service training and medical supplies. They are supervised by LHW supervisors. Their annual salary is around US$343. The cost of the programme for the first eight years was US$155 million, and the approved budget for 2003-2008 is US$357 million. Government is the main funder, with 11% coming from external sources. The overall yearly cost of one LHW is approximately US$745 . This gives an average cost per person per year of less than 75 cents. Evaluations of this programme have found significant impact on health knowledge and health service utilization, especially in rural areas. For example, in areas with LHWs, there are a higher proportion of births attended by a skilled attendant; more babies exclusively breast-fed; more mothers who know about oral rehydration, and who give it to children with diarrhoea; and more children fully vaccinated, compared with areas without LHWs. I n f o r m a t i o n strategies to better retain health workers that include attention to both salaries and working conditions and differential effects on male and female staff; and ways to monitor health worker performance. • Advocacy International and regional advocacy will focus on: developing strategies to manage migration, such as the International Code of Practice; promoting better understanding of the implications of international labour markets for developing countries; and ways to mobilize better technical support to countries. It will facilitate agreements between agencies on more effective financing mechanisms for workforce development. • Working with international health professional groups S uch as the International Council of Nursing, the World Medical Association, the Federation of International Pharmacists and the World Federation of Medical Education, WHO will maintain its function in setting norms and standards for the health workforce, including the development of internationally agreed definitions, classification systems and indicators. 30 19 • Generate population and facility based data: from censuses, household surveys, civil registration data, public health surveillance, medical records, data on health services and health system resources (e.g. human resources, health infrastructure and financing); • H ave the capacity to detect, investigate, communicate and contain events that threaten public health security at the place they occur, and as soon as they occur; • H ave the capacity to synthesize information and promote the availability and application of this knowledge. WHO supports countries in developing and applying different data collection and data management tools, from personal medical records to population data records, and in analysing the data produced. It develops tools and standards, such as the International Classification of Diseases, maintains the global mortality and causes of death database, and produces regular reports on health statistics, disaggregated where appropriate by age and sex. It supports the development of strong public health surveillance systems, as part of an inter-connected global system to collectively reduce international vulnerability to public health threats. Priorities • National information systems Support improved population and facility-based information systems, so that they can generate, analyse and use reliable information from multiple data sources, in collaboration with partners (e.g. UN, other agencies, the Health Metrics Network partnership, the Institute of Health Metrics and Evaluation). • Reporting Avoid parallel reporting systems where possible, and promote single reporting to development partners. WHO will support the use of new data collection and data management technologies where appropriate. • Stronger national surveillance and response capacity Public health systems that are equipped with up-to-date technologies and dedicated personnel and are able to detect, investigate, communicate and contain threats to public health security, and be part of an unbroken international line of defence against such threats. • Tracking performance Establish a set of core and additional health system metrics to track health system performance for use by countries and external agencies financing investments in health systems. • Standards, methods and tools These include the International Classification of Diseases, Global Burden of Disease updates, MDG monitoring tools; development and measurement of Health System Metrics; and standards for electronic medical records. A key role will be played by expert groups, including the Advisory Committee for Health Monitoring and Statistics. • Synthesis and analysis of country, regional and global data This includes comprehensive WHO databases populated with more uniform data, disaggregated as needed by age and sex; regular publication of World Health Statistics. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S I n f o r m a t i o n 31 20 4. MedICAL PrOdUCTS, vACCINeS ANd TeCHNOLOGIeS A well-functioning health system ensures equitable access to essential medical products, vaccines and technologies of assured quality, safety, efficacy and cost-effectiveness, and their scientifically sound and cost-effective use. To achieve these objectives, the following are needed: • N ational policies, standards, guidelines and regulations that support policy; • I nformation on prices, international trade agreements and capacity to set and negotiate prices; • R eliable manufacturing practices and quality assessment of priority products; • P rocurement, supply, storage and distribution systems that minimize leakage and other waste; • S upport for rational use of essential medicines, commodities and equipment, through guidelines, strategies to assure adherence, reduce resistance, maximize patient safety and training. WHO has a strong track record in helping countries frame national policies. It promotes evidence-based selection of medicines, vaccines and technologies by developing international standards, norms and guidelines through WHO’s Expert Committees and consultation processes. WHO/UN pre-qualification programmes for priority vaccines, medicines and diagnostics will be boosted significantly by the establishment of UNITAID, the new international drug purchase facility. WHO provides information on medicine and vaccine prices and supports the development of systems for post-marketing surveillance. It promotes equitable access and rational use, for example, through essential medicines lists, clinical guidelines, strategies to assure adherence and safety, training and working with consumer organizations. It also supports technology assessments and policy development. Priorities • Establish norms, standards and policy options Set, validate, monitor, promote and support implementation of international norms and standards to promote the quality of medical products, vaccines and technologies, and ethical, evidence-based policy options and advocacy. • Procurement Encourage reliable procurement to combat counterfeit and substandard medical products, vaccines and technologies, and to promote good governance and transparency in procurement and medicine pricing. M e d i c a l p r o d u c t s , v a c c i n e s a n d t e c h n o l o g i e s E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S HealTH sysTem sTRengTHening: mOniTORing PROgRess http://www.who.int/healthinfo/health_system_metrics_glion_report.pdf Source: Health systems strengthening: Monitoring progress: Proposed indicators and data collection strategies. T Boerma, WHO 2007. Securing more investment in health system strengthening will depend on being able to demonstrate progress. Moreover, agreement on consistent ways of measuring change in key dimensions of the health system can guide resource allocation to where it is needed most and will improve accountability. A monitoring system for health systems strengthening needs to capture trends in health system inputs and outputs, supported by coverage data with a small set of indicators. Progress can be summarized with a country “dashboard” that includes key indicators for these core areas and describes progress on an annual or bi-annual basis. The dashboard should also provide contextual information such as the country health situation in relation to its level of economic development or health expenditure. 32 21 • Access and use Promote equitable access, rational use of and adherence to quality products, vaccines and technologies through providing technical and policy support to health authorities, professional networks, consumer organizations and other stakeholders. • Quality and safety Monitor the quality and safety of medical products, vaccines and technologies by generating, analysing and disseminating signals on access, quality, effectiveness, safety and use. • New products Stimulate development, testing and use of new products, tools, standards and policy guidelines, emphasizing a public health approach to innovation, and on adapting successful interventions from high-income countries to the needs of lower-income countries, with a focus on essential medicines that are missing for children and for neglected diseases. 5. SUSTAINABLe FINANCING ANd SOCIAL PrOTeCTION A good health financing system raises adequate funds for health, in ways that ensure people can use needed services, and are protected from financial catastrophe or impoverishment associated with having to pay for them. Health financing systems that achieve universal coverage in this way also encourage the provision and use of an effective and efficient mix of personal and non-personal services. 5 Three interrelated functions are involved in order to achieve this: the collection of revenues – from households, companies or external agencies; the pooling of pre-paid revenues in ways that allow risks to be shared – including decisions on benefit coverage and entitlement; and purchasing, or the process by which interventions are selected and services are paid for or providers are paid. The interaction between all three functions determines the effectiveness, efficiency and equity of health financing systems. Like all aspects of health system strengthening, changes in health financing must be tailored to the history, institutions and traditions of each country. Most systems involve a mix of public and private financing and public and private provision, and there is no one template for action. However, important principles to guide any country’s approach to financing include: • Raising additional funds where health needs are high, revenues insufficient, and where accountability mechanisms can ensure transparent and effective use of resources; • R educing reliance on out-of-pocket payments where they are high, by moving towards pre- payment systems involving pooling of financial risks across population groups (taxation and the various forms of health insurance are all forms of pre-payment); • T aking additional steps, where needed, to improve social protection by ensuring the poor and other vulnerable groups have access to needed services, and that paying for care does not result in financial catastrophe; • I mproving efficiency of resource use by focusing on the appropriate mix of activities and interventions to fund and inputs to purchase, aligning provider payment methods with organizational arrangements for service providers and other incentives for efficient service provision and use including contracting, strengthening financial and other relationships with the private sector and addressing fragmentation of financing arrangements for different types of services; • P romoting transparency and accountability in health financing systems; • I mproving generation of information on the health financing system and its policy use. 5 Resolution WHA58.33 on «Sustainable health financing, universal coverage and social health insurance» defined universal coverage as ensuring that the population has access to needed services without the risk of financial catastrophe. S u s t a i n a b l e f i n a n c i n g a n d s o c i a l p r o t e c t i o n E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S 33 22 The most pressing challenge is to provide technical advice to the large number of countries seeking support to develop their financing systems to move more quickly towards universal coverage. Key global public goods produced by WHO include standardized tools and guidelines, for example, for costing, cost-effectiveness analysis and national health accounts. In addition, WHO provides information to countries and works with them to improve their own data collection and to incorporate it into policy development, including analysis of health expenditures and catastrophic spending. Emerging issues relate to using debt relief and medium-term expenditure frameworks to raise more funds for health, and the need to collaborate with priority health programmes, many of which are seeking to develop sustainable financing plans for their particular country-level activities. Priorities • Health financing policy option Assess and disseminate information about what works and what does not work in health financing strategies; facilitating the sharing of country experience in various types of health financing reforms; sharing of key information required by country policy makers; and the development of tools, norms and standards including those required to assist countries to generate and use information in their own settings. • Improve or develop pre-payment, risk pooling a nd other mechanisms to reduce the extent of financial catastrophe and impoverishment due to out-of-pocket payments, and to extend financial and social protection. • Ensure adequate funding from domestic sources In some countries, the ministry of health has the potential to attract a higher share of government funding. In others, the health sector can become engaged in debates about fiscal policies that directly affect health (e.g. taxes on products that are harmful to health), as well as by ensuring that health activities are included in poverty reduction strategy papers and medium-term expenditure frameworks. Funding might also be increased through financial arrangements between the government and non-government sectors. Various mixes of tax funding with social, community and private health insurance, provide the alternative institutional frameworks for such arrangements. WHO will support countries to make the case for health funding, as well as to develop new sources of finance. • Used funds Ensure available funds are used equitably and efficiently, by appropriate provider payment mechanisms, aligning financing and service delivery incentives; addressing fragmented financing systems; appropriate use of tools, such as contracting, to achieve appropriate balance between activities, programmes, inputs, capital versus recurrent expenditures, and ensuring protection of vulnerable population groups. • Promote international dialogue t o increase funding for health in poor countries from domestic and external sources, ensure the predictability of funding, and ensure that new external sources contribute to the development of sustainable domestic financial institutions. • Increase availability of key information for use by country policy makers in areas such as how much is spent on health, by whom, whether it results in financial catastrophe and who benefits. This also requires information on the costs of scaling-up interventions and the impact on population health of doing so, as well as the costs and impact of reducing system constraints to scaling-up. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S S u s t a i n a b l e f i n a n c i n g a n d s o c i a l p r o t e c t i o n 34 23 6. LeAderSHIP ANd GOverNANCe The leadership and governance of health systems, also called stewardship, is arguably the most complex but critical building block of any health system. It is about the role of the government in health and its relation to other actors whose activities impact on health. This involves overseeing and guiding the whole health system, private as well as public, in order to protect the public interest. It requires both political and technical action, because it involves reconciling competing demands for limited resources, in changing circumstances, for example, with rising expectations, more pluralistic societies, decentralization or a growing private sector. There is increased attention to corruption, and calls for a more human rights based approach to health. There is no blueprint for effective health leadership and governance. While ultimately it is the responsibility of government, this does not mean all leadership and governance functions have to be carried out by central ministries of health. Experience suggests that there are some key functions common to all health systems, irrespective of how these are organized. • Policy guidance. Formulating sector strategies and also specific technical policies; defining goals, directions and spending priorities across services; identifying the roles of public, private and voluntary actors and the role of civil society. • I ntelligence and oversight. Ensuring generation, analysis and use of intelligence on trends and differentials in inputs, service access, coverage, safety; on responsiveness, financial protection and health outcomes, especially for vulnerable groups; on the effects of policies and reforms; on the political environment and opportunities for action; and on policy options. • C ollaboration and coalition building.Across sectors in government and with actors outside government, including civil society, to influence action on key determinants of health and access to health services; to generate support for public policies, and to keep the different parts connected - so called ‘joined up government’. • R egulation. Designing regulations and incentives and ensuring they are fairly enforced. • S ystem design. Ensuring a fit between strategy and structure and reducing duplication and fragmentation. • A ccountability. Ensuring all health system actors are held publicly accountable. Transparency is required to achieve real accountability. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S exTending sOcial and financial PROTecTi On in cOlOmbia Sources (see Annex 2, References): Florez and Hernandez, 2005; Pinto D and Hsaio W, 2007. Colombia’s national health insurance scheme was part of a package of health reforms introduced nation-wide in 1993, with the aim of improving service access, efficiency and quality. Two insurance schemes were created that targeted different populations. First, a compulsory contributory regime that included all formal sector employees and independent workers able to pay, plus their families. This was largely financed from payroll taxes. Second, a subsidized regime targeted the poor by subsidizing their insurance premiums using dedicated public resources and cross subsidies from the ‘contributory regime’. The benefit package for the subsidized regime was initially limited to essential clinical services, a few surgeries plus the treatment of catastrophic diseases, but gradually made more generous as more resources became available. By 2004, the subsidized regime benefit package covered a wider range of inpatient care, but was still smaller than that of the contributory regime. T he subsidized regime played a key role in increasing coverage for the poor and people living in rural areas. Insurance coverage rose from 3% to 57% for the poorest quintile between 1995 and 2005. In rural areas insurance coverage increased from 6% to 46%. Total impoverishment due to health spending (using Florez and Hernandez’s comprehensive definition) declined from 18% to 8% over six years between 1997 and 2003. Access to and use of health services increased in rural areas over 15 years up to 2000: for example, there was a 49% increase in pre-natal care, and a 66% increase in assisted deliveries. L e a d e r s h i p a n d g o v e r n a n c e 35 24 An increasing range of instruments and institutions exist to carry out the range of functions required for effective leadership and governance. Instruments include sector policies and medium-term expenditure frameworks; standardised benefit packages; resource allocation formulae; performance- based contracts; Patient’s Charters; explicit government commitments to non-discrimination and public participation; public fee schedules. Institutions involved may include other ministries, Parliaments and their committees, other levels of government, independent statutory bodies such as professional councils, inspectorates and audit commissions, NGO ‘watch dogs’ and a free media. WHO’s tendency at present is to focus on the development of specific technical health policies. This is important, but the added challenge for governments is to provide vision and direction for the whole health system, and oversee implementation of agreed health policies through systems that are faced with critical governance and stewardship challenges. These include: reconciling competing demands for resources; working across government to promote health outcomes; managing growing private sector provision; tackling corruption, responding to decentralization; engaging with an increasingly vocal civil society, and a growing array of international health agencies. This is an area in which WHO needs to enhance its capacity to support ministries of health. Priorities All governments are faced with the challenge of defining their role in health in relation to other actors. For many this is changing, for example, with decentralization. Any approach to leadership and governance must clearly be contingent on national circumstances. WHO will help governments as follows: • Develop health sector policies and frameworks t hat fit with broader national development policies and resource frameworks, and are underpinned by commitments to human rights, equity and gender equality. As part of this, it will promote international debate on the central but changing role of governments in health. • Regulatory framework Design, implement and monitor health related laws, regulations and standards, especially in the areas of International Health Regulations; regulation of medical products, vaccines and technologies; regulation concerning occupational health and workplace safety. WHO will also engage in trade debates in areas affecting health systems. • Accountability Support greater accountability through the Organization’s work on monitoring health system performance as set out in the building block on information. • Generate and interpret intelligence a nd research on policy options 6 . At the international level, it will facilitate access to knowledge on approaches to policy and systems development: by promoting a more systematic health systems research agenda; through the Alliance on Health Policy and Systems Research; by building capacity in regional observatories or their equivalent; and by increasing access to and use of new knowledge management technologies. It will work to strengthen national capacity in health policy analysis and links to policy decision-making. • Build coalitions a cross government ministries, with the private sector and with communities: to act on key determinants of health; to protect workers’ health; to ensure the health needs of the most vulnerable are properly addressed; to anticipate and address the health impact of public and commercial investments. • Work with external partners t o promote greater harmonization and alignment with national health policies. Research for Health: a Position Paper on WHO’s Roles and Responsibilities in Health Research. WHO 200. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S L e a d e r s h i p a n d g o v e r n a n c e 36 25 E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S Oecd-WHO ReVie W Of THe sWiss HealTH sysTem At the request of the Swiss Federal Office of Public Health, WHO and Organisation for Economic Co-operation and Development (OECD) jointly undertook an independent review of the Swiss health care system in 2005– 2006. The review assessed institutional arrangements and the performance of the health system against key policy goals of effectiveness and quality, access and responsiveness, efficiency and financial sustainability. It discussed factors affecting performance, future system challenges, and potential areas for reform. Findings were discussed at a national seminar of Swiss health experts from the public and private sector. sTRengTHening insTiTuTiOnal caPaciTy fOR POlicy analysis in kyRgyzsTan Source: Box prepared by WHO/EURO, 2007, based on the Manas Health Care Reform Programme. The WHO Health Policy Analysis Project was launched in Kyrgyzstan in 2000. It was designed to support the government’s Manas Health Care Reform Programme, whose goal was to improve the sustainability, efficiency and quality of the Kyrgyz health system. The project had four types of activities: policy analysis; linking evidence to policy; capacity building for policy analysis and evidence based policy design; and dissemination of results. Capacity building in monitoring and evaluation of health s ystem performance, and in policy analysis more broadly, has been carried out in four ways. There were frequent interactions with senior policy makers to present findings and implications of studies, to demonstrate their political usefulness and stimulate demand. Round table discussions on key health policy topics were a way to inject technical input and build political consensus. The Ministry of Health (MOH) health management courses targeted at managers of primary care and inpatient facilities were a crucial way to inform and engage health care managers in health policy issues. The health policy courses for Central Asia and Caucasus in collaboration with the World Bank Institute and WHO European Region allowed cross-country learning for a large number of Kyrgyz policy makers. Lastly, a group of young health policy analysts have been mentored through the six years to become independent researchers providing continuous support to the MOH. These core activities have now been institutionalised through the creation of a Department of Strategic Planning and Reform Implementation within the MOH, which has taken on core health system performance monitoring, and a Centre for Health System Development, which is an autonomous public entity created by the MOH to support policy development and implementation through knowledge g eneration and training. Support to these two young institutions will continue until at least 2010. 37 26 E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S B. Health systems and programmes: getting results WHO’s involvement in all aspects of health and health systems constitutes a real comparative advantage. It is better placed than many other international agencies to identify competing demands across health priorities, and to understand how efforts to strengthen health systems affect services on the ground. There is a growing body of experience with cross-departmental relationships that bring together ‘programme’ and ‘system’ expertise. Much existing collaboration focuses on ‘normative’ issues, such as costing of programme scale-up, estimates of disease burden or the dense network of relationships between those concerned with pharmaceutical policy and technical departments with a stake in essential drug lists, pre-qualification of manufacturers and treatment guidelines. Collaboration on more operational aspects of health systems strengthening is less common. Many technical departments operate their own country support networks through which they provide independent advice on service delivery and systems issues. Sometimes, awareness of parallel efforts is lacking. This is beginning to change. Examples include the TTR initiative linking systems work on health service staffing with improving access to HIV/AIDS care and treatment; the Taskforce on TB control and health system strengthening; joint work on HIV/AIDS and TB scale- up in the Baltic countries, and work across WHO stimulated by the opening of the GAVI Health System Strengthening window. Nevertheless it is clear that, in too many instances, WHO’s support remains fragmented between advice focusing on particular health conditions (which may not always take account of systems or delivery issues) and advice on particular aspects of health systems provided in isolation. While there are good examples of how both streams can work together, the challenge is to develop a more systematic and sustained approach that responds better to the needs of Member States. Improve and extend existing interactions Learning from TTR, GAVI, etc., WHO will establish more systematic ways to work together to ensure priority programme policies and delivery strategies are designed in ways that can take account of a country’s overall health system organization and resources that can identify whether appropriate solutions to barriers to care lie in or outside programme control, and that ensure gains in coverage do not occur at the expense of other health priorities. Much of this work has to happen at country level. However, there is room for more interaction at other levels of WHO. In this regard, there is interesting work as part of the new Stop TB Strategy. Guiding principles are being developed for national TB programmes and partners, to contribute to health system strengthening without losing gains made in TB control (known as the ‘do’s, don’ts and non-negotiables’). Work will also involve exploring how to build on packages of care such as the Integrated Management of Childhood Illness. More pro-active engagement is needed across Strategic Objectives on approaches to service delivery (for example, to ensure continuing personal care for diabetes and HIV; service delivery in emergencies, or the delivery of non-personal services). These will help identify and exploit common systems requirements across interventions, and promote joint learning. More active engagement is also needed in the area of health systems with global health partnerships concerned with HIV, TB, malaria and maternal, neonatal and child health. Create better and more systematic communication A pragmatic view of the basic relationship between systems and programmes is that outcome- oriented programmes – in WHO and in countries – will continue to exert a certain dominance because of their capacity to attract resources. This means that health system specialists have to be prepared to be responsive and act in advisory mode. They must also be opportunistic, and use programme requests such as costing as entry points to identify issues such as financing policy that cannot be adequately addressed on a programme by programme basis. WHO needs a strong group of staff and consultants able to adapt the analytic approach to health systems for country support. 38 27 Altogether, better communication is needed to think systematically about health system processes, constraints and what to do about them. Achieve greater consistency, quality and efficiency We must ensure greater consistency, quality and efficiency in the production of methods, tools and data reporting across WHO, building on current work in areas such as programme costing or the reporting of health statistics. This is covered further in the specific building blocks. Other actions are listed here, and discussed further in the last section. For example, improved health system awareness among all WHO staff – in other words, a basic familiarity with health system issues – needs to be combined with improved ‘outcome literacy’ among systems staff, plus the establishment of a professional network for health systems staff in all parts of WHO. Better relationships also require careful thought about incentives, and top-level managerial support. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S a ‘ diagOnal’ aPPROacH TO HealTH sysTem sTR engTHening • Taking the desired health outcomes as the starting point for identifying health systems constraints that «stop» effective scaling-up of services; • Addressing health systems bottlenecks in such a way that specific health outcomes are met while system-wide effects are achieved and other programmes also benefit; • Addressing primarily health systems policy and capacity issues; • Encouraging the development of national health sector strategies and plans, and reducing investment in isolated plans for specific aspects of health systems; • Robust monitoring and evaluation frameworks. selecTed sysTem cOnsTRainTs and POssible disease-sPecific and HealTH-sysTem Res POnses ConstraintPossible disease-specific responsePossible health system response Financial access difficult e .g inability to pay, informal fees Payment exemptions for an individual, for a specific disease P ooling pre-paid funds (from households, external agencies, companies) in ways that allow risks to be shared, and decrease individual payments when sick Physical access difficult e.g. distance to facility Out-reach for specific diseases; engage private providersRevising plans for the location, construction or upgrading of health facilities Knowledge and skills low ( public and private providers) W orkshops and other continuing education for specific diseases Revised pre-service training curricula; systems for licensing, accreditation, supervision Staff are poorly motivatedS taff get financial incentives to deliver specific servicesClear job descriptions; performance and salary review; fair, transparent promotion procedures Weak leadership and management W orkshops to develop skills in managing staff, budgets etc. (e.g. in public and NGO facilities) Additional actions such as giving managers more control over resources; more accountability for results Ineffective intersectoral action and partnershipD isease-specific cross-sectoral committees, usually national level Building local government systems with cross-sector representation, and explicit procedures for public accountability Source (see Annex 2, References): Adapted from Travis et al, 2004. 39 28 E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S C. A more effective role for WHO at country level Countries at different levels of development look to engage with WHO as they seek to improve their health systems. Some countries are primarily interested in exchanging ideas and experiences in key aspects of policy (such as health worker migration), in getting wider international exposure for important domestic agendas (such as patient safety or the health of indigenous populations), or in the development of norms and standards for measuring performance. All countries look to WHO for comparative experience in relation to different aspects of reform in areas such as health financing, and for WHO’s convening role where action may be needed across countries. However, it is countries at a lower level of income – as evidenced increasingly in WHO CCSs – that seek more direct involvement in overall policy and health systems development, often in conjunction with other partners such as the World Bank. This area, above others, requires improvement. In states recovering from emergencies or emerging from conflict, WHO may also be called on to act as the coordinator of the many organizations concerned with health work; to ensure that health remains central to the security and humanitarian agenda and to advise on reconstruction of the health system as a whole. Improved capacity to diagnose and act on health system constraints There are many different entry points to the analysis of health system weaknesses and barriers to improving service delivery. The purposes, depth and quality of analyses may vary widely. Some are done as part of broad sector review processes by ministries and partners. Some are done as part of an external agency’s individual strategy development 7 . Some are done for specific programmes or for specific aspects of the health system such as the health workforce. Programme-specific diagnostic tools are being developed by many agencies. Consultations suggest that WHO needs to improve capacity to diagnose and act on health system constraints. • W HO will support the use of consistent approaches to identifying health system constraints, that incorporate a system-wide perspective, but are sufficiently flexible to be used by programme and systems groups with different entry points. These approaches need to be able to inform major planning exercises, medium-term expenditure frameworks, the health components of poverty reduction strategies, etc. WHO will work to ensure that core technical frameworks inform the assessment of health system challenges and priorities. • T o reduce duplication, WHO will undertake diagnostic exercises preferably through MOH- led reviews and, where appropriate, jointly with other development partners. It may also undertake independent reviews if requested. More intensive engagement in sector policy processes and investment strategies Helping a country decide on the best ways to invest in order to strengthen health systems requires two interconnected responses: having an over-arching vision and strategy for the health sector, and the development of more detailed policies and investment plans in specific technical areas. As stated in the building block on leadership and governance, WHO’s work at country level will be significantly enhanced if it engages more effectively with partners in overall policy processes. Many of WHO’s senior interlocutors at country level (ministers, permanent secretaries, directors- general) seek support in assessing overall sectoral needs or on how to deal with varying advice on policy issues from different partners. This function – “helping to sort the wood from the trees” and putting technical advice in a political context – is an area of potentially great comparative advantage and influence. In specific policy areas, demand from countries for WHO advice nearly always exceeds supply. For example, in health financing – one of the most common areas in which advice is sought 7 for example, the WHO ccs process provides some information on constraints but is not designed to do this in sufficient detail for national policy purposes. 40 29 E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S – WHO has well-recognized strengths in costing, in national health accounts and in analysing financial catastrophe and impoverishment. It is less well equipped at present to support countries on domestic financing policy. The same is true in other specific areas. WHO will increase its engagement in high level policy dialogue. It will: • s upport the development of evidence-based health sector strategies and costed plans linked to the macro-economic framework. This will entail more active and consistent engagement in key policy events by all levels of the Organization; • i ncrease its capacity for policy advice in specific aspects of systems, such as health workforce strategies and investment plans, health financing policies, etc.; • w ork with development partners, GHPs and funding agencies to improve harmonization and alignment with national health policies and systems, through harmonization plans, mutual accountability Memoranda of Understanding, institutional performance contracts, etc. • a ssist governments in the implementation of International Health Regulations, international agreements on trade, human rights and gender, by identifying their implications for the national health system. Build national capacity, especially in policy analysis and management WHO will focus on building national capacity in health policy analysis and management, recognizing that the Organization itself needs greater capacity in these areas. Policy analysis involves analysing problems from several standpoints: the problem, and who is affected; possible solutions; and the political and institutional feasibility as well as technical desirability of implementing any of them. Management is about managing services, resources and partners. Aid management is a particularly important and difficult task in many poorer countries. It is about tracking aid flows and managing external partners - and the funds and technical assistance they provide - in ways that maximise their contribution to national strategies with minimum transaction costs. WHO’s focus will be on the development of institutional not just individual capacity. Actions will include: • c atalysing structured discussions by different stakeholders on key policy concerns, and making independent appraisals of experience with use of different tools for policy analysis and management available; • s ustained technical support to dedicated policy ‘think-tanks’ or ‘observatories’, to identify problems of national concern, gather intelligence, and generate policy options for debate. This includes promoting different forms of informal and formal ‘experience-exchange’ in managing specific policy challenges across countries. • s upport national approaches to develop managerial capacity, through networks of resource institutions, a greater WHO role in harmonizing development partners support to management strengthening and linking activities to national instruments such as poverty reduction strategy papers. This includes helping managers tackle difficult management issues such as workforce productivity and performance, budgeting and procurement, and taking advantage of vehicles such as the Global Health Workforce Alliance and GAVI HSS. • s upporting national mechanisms for tracking aid flows and managing partners. In exceptional circumstances, such as countries emerging from conflict or health emergencies, it may involve temporarily taking on the role of co-ordinator of external health aid organizations. Support countries’ monitoring of trends in health systems and performance The generation and use of information is at the heart of WHO’s mandate. A major part of its work must be to support health ministries to track trends in their health systems’ performance, in ways that are geared primarily to national decision-making, but also to enable them to make comparisons with, and learn from, other countries. For greatest positive effect, this requires 41 30 consistent approaches shared and supported by all levels of WHO. And it requires engagement with other international players, especially the Health Metrics Network. Priorities, below, here link with those in the information building block.. • E ffective communication of internationally agreed concepts, language and metrics on health systems. • I mproved country data collection systems that capture health system inputs, services and outcomes, using validated tools, at national and sub-national level. • Gr eater joint monitoring by external agencies, using nationally led processes and systems. E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S caPaciTy building: WHaT is knOWn abOuT gOOd PRacTice? Capacity building in practical terms involves ensuring that a combination of the tools, skills, staff and support systems re quired for chosen functions are available and operational. There is no blueprint on how to build capacities in policy and strategy development, but there are some clear lessons from past efforts. The demand for tools for policy analysis is longstanding, with expectations of what they can achieve often exceeding experience on the ground. Available tools vary widely in purpose and scope; more are focused on assessing specific system components than on assisting political analysis. Key tools for aid management are credible policies and costed plans. One important way of building skills in, for example, analysing how different interest groups are positioned, or brokering agreements between them, is through on-the-job practice coupled with exchanges of experience between individuals and institutions. Another lesson is that tools and skills alone are not enough to improve performance: attention to improving any required support systems (such as for tracking aid flows) may be needed. Lastly, attention to creating demand for staff with these capabilities may be needed, and a long-term view for any support provided is essential. 42 31 E V E R Y B O D Y ’ S B U S I N E S S S – W H O ’ S R E S P O N S E T O H E A L T H S Y S T E M S C H A L L E N G E S D. The role of WHO in the international health systems agenda WHO’s international work complements and supports its more direct engagement in countries, through the production of global public goods such as norms, standards, policies and guidance. In addition, WHO’s international work has a value in its own right, through increasing the effectiveness of international systems such as the surveillance and response network, or through shaping international health aid architecture. Produce global public goods: norms, standards, policies and guidance WHO needs to respond to the consistent demand from countries and development partners for a common language to describe the components of health systems and the actions needed to make them function more effectively. Although there is progress, more remains to be done to simplify and communicate health systems terminology to a wider variety of audiences. The development of standardized methods and tools, such as for national health accounts in low and middle-income countries, will also continue to be core business of WHO. There is a need for a more systematic approaches to research and learning. Evidence on effective strategies for health systems strengthening is scarcest where need is greatest. Each reform and innovation constitutes a learning opportunity 8 . The question is how we best learn about what works and why. Broader social, political and institutional factors need to be taken into account as we amass evidence either from one-off case studies or in the ongoing work of emerging health systems observatories. Knowledge Networks of the Commission for Social Determinants on Health are amassing evidence on critical determinants and effective ways of influencing country policy and practice. The 2008 World health report will draw on three decades of experience with PHC principles and practices and show how these may inform pathways to improve health in the 21 st Century. Health systems will be prominent in the new health research agenda being prepared by WHO 9 . The Alliance for Health Policy and Systems Research has a new ten-year strategy that focuses on stimulating the generation, synthesis and use of policy relevant health systems knowledge. WHO will also support approaches to more informal learning and sharing tacit knowledge, taking advantage of progress in information technology, and leveraging e-health networks within and between countries. To make the case that health systems strengthening merits greater investment, a key priority is to agree on a set of measurements that can capture the status of a health system and demonstrate whether its performance is improving (see box 13). The purpose of such health system metrics is twofold: for comparing systems one to another, but more importantly to enable decision makers and investors to track progress of their own health system over time and take action as needed. It is also important to forecast trends and look ahead and consider the implications for health systems and health equity of aging populations, developments in medical therapies, information technologies, etc., and at how these changes will affect the interaction between health systems and human health security. An important part of WHO’s global stewardship function is to generate awareness and informed debate on future policy challenges and options. Coherent international systems for better health A core function of WHO is to use its convening power effectively to work with global and regional systems for better health. Of growing importance in strengthening country support are the networks of regional institutions of which WHO is an integral part. In Africa, for example, WHO will work towards ensuring consistent health systems messages from the New Partnership for 8 frenk J, bridging the divide: global lessons from evidence-based health policy in mexico. lancet, 200. 9 Research for Health: a Position Paper on WHO’s Roles and Responsibilities in Health Research. WHO 200. 43 32 Africa’s Development (NEPAD) and the African Union (AU), the Regional Economic Commissions, and the newly reorganized African Development Bank. There is also an important relationship between how aid for health is organized and how health systems develop. The principles agreed by countries and development partners at the High-level forum on Aid Effectiveness in Paris (to which WHO was a signatory) aim for greater ownership by government, alignment with national priorities, and harmonization between development partners. Greater predictability in aid finance makes it more likely that finance ministries will budget for the long term recurrent costs that all functioning health systems need. WHO will continue to work with the OECD Development Assistance Committee and others to increase development partner accountability in health, focusing on ways in which applying the Paris Principles support health systems development. WHO is also evolving the way it works with GHPs, such as Stop TB and Roll Back Malaria, in order to bring the Paris ‘best practice’ Principles to bear, recognizing the importance of GHPs for strengthening health systems as well as accelerating achievement of health outcomes. The development of systems for a more secure world includes, but is not limited to, systems for epidemic outbreak surveillance and response such as the Global Outbreak And Response Network (GOARN). It includes systems for predicting and preventing exposure to environmental health hazards. In addition, health systems contribute to human security, as poor health and the lack of health services can trigger instability (conversely, in many conflicts health facilities and health workers become the target of warring parties). A robust health system is a vital part of any governments’ response, to avoid a vicious cycle of deteriorating health leading to deteriorating security. WHO’s role in health security is addressed in the World health report 2007. Work with partners Given its critical role for health systems development, strengthened coordination with the World Bank is a priority. WHO will aim to leverage the capacity of other development banks and bilateral agencies to pursue health outcomes through investments in other sectors. WHO will work with the Bretton Woods Institutions and finance ministries to ensure health is properly reflected in national development planning and expenditure frameworks. The major health financing partnerships have recognized the need to engage in health systems strengthening and are doing so in different ways. The Global Fund is currently developing its systems strengthening approach. GAVI has targeted funds for a new health systems strengthening window. WHO is committed to working with GAVI and the Global Fund to operationalize those opportunities in a way that will provide effective financing for health systems development. WHO will draw on the strengths of international NGOs with an interest in health systems. Two groups are of particular concern. A first emerging group is the international lobby for health systems development. Previously the province of a few international NGOs, a new Health Systems Action Network (HSAN) has been formed. Activist members are beginning to ensure that health systems messages are heard in major developmental fora. Their demand for clarity in messaging, costing and impact is something to which WHO will respond. Second, is the growing number of organizations responding to demands for technical support. WHO will seek to engage them. Where appropriate, WHO can play a role in creating technical support networks and ensuring their quality through accreditation of individuals or institutions. International agreements between governments impact on health systems. Prominent among these are interactions – both bilateral and through the World Trade Organization – that have influenced the price of and access to pharmaceuticals. Public health is an area in which innovation and Intellectual Property Rights will play an increasingly prominent role 10 . Other trade agreements likely to influence health systems, such as the General Agreement Trade in Services (GATS), have 0 Public Health innovation and intellectual Property Rights. Report of the commission on intellectual Property Rights, innovation and Public Health. World Health Organization, 200. 44 33 received less attention. Their potential impact, through liberalization of insurance markets and granting access to foreign private providers of health care, may be significant in many countries. International agreements will also influence the management of migration both of health workers and those seeking care. How these issues are handled between countries will have a lasting impact on health sector effectiveness. Over the last three years, partly stimulated by having a UN Special Rapporteur of the Commission on Human Rights on the right to health, there has been increasing interest in how a focus on the realization of this right can be used to focus on the need for investment in health workers and health systems. WHO will work to influence international agreements that impact on health and health systems. It will help in making linkages across governments (for instance between ministries of trade and health); and it will help ministries of health anticipate and act on changes that will come about as a result of international agreements. gaVi and HealTH sys Tem sTRengTHening (gaVi-H ss ) Since the GAVI Board decision in December 2005 to earmark US$500 million for health system strengthening (HSS), the GAVI-HSS window has developed rapidly. Applications for funds are expected to address health system barriers known to impede the demand for and delivery of immunization and other child and maternal health services. Three priority areas are identified, focusing on the district level and below: health workforce mobilization, distribution and motivation; organization and management of health services; supply, distribution and maintenance systems for drugs, equipment and infrastructure. Three proposal rounds have now been completed, with a total of US$266 million approved. 45 WHO/ christopher b lack 46 35 “Everybody’s Business” is a framework that signals directions and priorities in the health systems agenda for the whole of WHO, so that it can provide more effective support, directly and indirectly, to Member States. It is not a detailed implementation plan. Indeed an implementation plan in the conventional sense would not be appropriate, given that it has Organization-wide implications. The Framework can be used in a number of ways, for example, as the basis for dialogue with partners, to inform internal staff development and learning, or as an input into operational planning at all levels. More detailed guidance on the ways in which it can be used will be ready by end 2007. The Framework’s success will depend on how well WHO uses its institutional assets and instruments. Its translation into action will involve a wide range of WHO structures and processes, to ensure that planning, management, staff skill mix, etc. are geared to achieving the outcomes that are set out here. This section outlines some of the implications of the Framework for Action for the way WHO works. It signals where innovation is already occurring, and where further, more detailed work is planned in the coming months to make the Framework operational. It focuses on three key areas. New ways of working across the Organization The previous section argued for the need to bridge the gap between programmes and systems departments, and the need for a more coherent approach to country support involving all levels of WHO. There are several ways of doing this. The first involves working within existing arrangements. • Improved communication on what is meant by health system strengthening, better documentation of actual experience, convincing metrics for tracking improvements in health systems and clear deliverables will create greater confidence that health systems strengthening involves clear strategies, specific actions and gets results. • D eveloping acceptable criteria for prioritizing country support: to strike the elusive ‘right balance’ between responding to demands from a large number of countries and ensuring impact through focusing on a few. • B uilding on opportunities for collaboration, and ensuring a prompt response. There are already a number of examples. The cluster of Family and Child Health is involved in two major, well-resourced initiatives (GAVI and the Oslo Initiative to achieve MDGs 4 and 5). I M P L I C A T I O N S F O R T H E W A Y W H O W O R K S HeALTH SyST eM STreNGTHeNING:WHO’S FrAMeWOrK FOr ACTION • A single framework with six clearly defined building blocks • S ystems and programmes: getting results • A m ore effective role on systems for WHO at country level • T he role of WHO in the international health systems agenda E V E R Y B O D Y ’ S B U S I N E S S S – I M P L I C A T I O N S F O R T H E W A Y W H O W O R K S 47 36 These have recognized health systems constraints as major obstacles to scaling-up, and are prepared to commit significant funds to overcome them. By engaging early on, with several departments working together, WHO has been able to shape the new policies and funding windows these initiatives are developing. The volume of funds disbursed to countries for HIV/AIDS means that here, too, there are real opportunities to strengthen health systems, and collaboration needs to be intensified. • R eappraisal of the use of expert guidance and external scrutiny, and experience with instruments such as expert advisory committees. The second route involves organizational changes to create stronger incentives for joint work. Here, there are some interesting regional developments. WHO European Region has introduced significant changes to its country support planning and budgeting system, to make it more responsive to country needs. WHO African Region is introducing sub-regional offices, to bring technical support closer to the country level. WHO will review the organization-wide relevance of structural changes already happening in some regional offices. enhancing staff competencies and capacity More analysis of WHO’s health system workforce is needed but even without it, WHO will review how to do better with existing staff. • Strengthen capacity in health sector policy and strategy development As mentioned previously, much of the responsibility for sector policy dialogue with senior policy makers falls to WHO Representatives and Liaison Officers. The challenge is to ensure that they have adequate back-up support and advice from regional offices and headquarrters, and to consider where such a function should be located and how it should be resourced. It also requires a more responsive approach to country requests for support (e.g. participation in joint health system reviews). This has implications for how WHO plans, as it runs counter to the current system of advance planning. W HO will increase its capacity and skill base so that it has more staff equipped to respond to senior policy makers. Building on existing activities of WHO regional offices, and the WHO Learning Committee (including the Core Functions workshop), it will define the competencies required more precisely, decide what form of staff development is necessary and consider how staff with these capabilities can fit into WHO’s strategic objective/ departmental structure. • Develop a professional network of staff working on health systems The key change in recent years is that there are rising numbers of health system professionals in technical programmes. W HO will work to build up a network of health system professionals across the Organization, to improve communication and share experience on health systems issues. The network will not replace independent work on specific issues. It will foster informal and more formal interactions, based on a review of existing staff, their level, distribution and skill-mix. Activities could include seminar series, cross-cluster groups or facilitated electronic debates on key topics, and possibly some form of health systems ‘help desk’. It will build on past and current experience, such as the informal cross-cluster group on non-state providers that has been established. • Make a better match between supply and demand in specific areas. W HO is looking at ways to better respond to requests for specific policy advice. To expand its response capability, it will investigate the potential of WHO accredited support networks. E V E R Y B O D Y ’ S B U S I N E S S S – I M P L I C A T I O N S F O R T H E W A Y W H O W O R K S 48 37 Strengthen WHO’s convening role, and role in health system partnerships • Maintain its convening role WHO has immense convening power. A key role for WHO is to detect and raise visibility for neglected or critical health systems issues that affect many countries, or those which require a trans-national response. WHO will continue to do this through informal meetings or through expert committees. • Address opportunities and challenges of health system partnerships The various emerging partnerships referred in previous sections are giving prominence to a wide range of health systems issues that might not have been possible in other ways. WHO will work to leverage the benefits that these partnerships offer to countries and international partners. It will clearly define its roles on a case-by-case basis and negotiate ways for partnerships to support WHO in its core functions. • Work with UN partners As part of the UN family, WHO will be active in promoting a more coherent UN presence at country level. Working as part of the UN country team, WHO will seek to ensure a clear division of responsibilities among UN partners in responding to national needs for health systems support. Next steps The Framework for Action will be judged by the extent to which it is made operational. Based on the outline provided above, over the next months it will be complemented by additional documents to elaborate how this will be done. Like all such documents, this Framework for Action is introduced into a complex and continually changing world. It should, therefore, be regarded as a ‘living document’ that sets direction but makes course corrections as needed. In terms of judging results, this is a corporate Framework for Action. The Medium-term Strategic Plan defines specific results for WHO activities in health systems development and will be the main instrument used for tracking progress. maTcHing seRVices TO needs: a neW aPPROacH TO cOunTRy suPPORT E V E R Y B O D Y ’ S B U S I N E S S S – I M P L I C A T I O N S F O R T H E W A Y W H O W O R K S Work at country level throughout the European Region is characterized in terms of its influence on, or contribution to, four basic health systems functions. The Bi-ennial Collaborative Agreements between EURO and individual Member States contain the joint priorities for co-operation by the Ministry of Health and WHO. For each priority (or Strategic Objective), they identify expected results, the products under each expected result and set out how the budget is allocated. Each product – regardless of which technical unit is responsible – is categorized according to one or more health system functions: health policy and stewardship; health system financing; health system resource generation; health service delivery. 49 38 WHO Core Functions as defined in the 11 th General Programme of Work • Providing leadership; engaging in partnerships where joint action is needed • Stimulating knowledge generation, translation and dissemination • Setting norms and standards • Articulating ethical and evidence-based policy options • Providing technical support; catalysing change; building sustainable institutional capacity • Monitoring and assessment of trends WHO’s Medium-term Strategic Objectives SO1 To reduce the health, social and economic burden of communicable diseases SO2 To combat HIV/AIDS, tuberculosis and malaria SO3 To prevent and reduce disease, disability and premature death from chronic noncommunicable conditions, mental disorders, violence and injuries SO4 To reduce morbidity and mortality and improve health during key stages of life, including pregnancy; childbirth; neonatal period; childhood and adolescence, and improve sexual and reproductive health and promote active and healthy ageing for all individuals SO5 To reduce the health consequences of emergencies, disasters, crises and conflicts, and minimize their social and economic impact SO6 To promote health and development, and prevent or reduce risk factors for health conditions associated with tobacco, alcohol, drugs and other psychoactive substance use, unhealthy diets, physical activity and unsafe sex SO7 To address the underlying social and economic determinants of health through policies and programmes that enhance health equity and integrate pro-poor, gender-responsive and human-rights based approaches SO8 To promote a healthier environment, intensify primary prevention and influence public policies in all sectors so as to address the root causes of environmental threats to health SO9 To improve nutrition, food safety and food security throughout the life-course and in support of public health and sustainable development SO10 To improve health services through better governance, financing, staffing and management, i nformed by reliable and accessible evidence and research SO11 To ensure improved access, quality and use of medical products, vaccines and technologies SO12 To provide leadership, strengthen governance and foster partnership and collaboration in engagement with countries, the United Nations system, and other stakeholders in order to fulfil the mandate of WHO in advancing the global health agenda as set out in the 11 th General Programme of Work SO13 To develop and sustain WHO as a flexible, learning Organization, enabling it to carry out its mandate more efficiently and effectively A n n e x 1 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 50 39 RefeRences 2 0 0 7 Pinto D and Hsaio W. Colombia: Social health insurance with managed competition to improve health care delivery. In Social Health Insurance for Developing Nations. Eds W Hsaio and P Shaw, The World Bank Institute and Harvard University, 2007. Regional Strategy on Human Resources for Health: 2006- 2015. Manila, World Health Organization for the Western Pacific Region, 2007. Resolution WHA59.23. Rapid scaling up of health workforce production. In fifty-ninth World Health Assembly, Geneva, 22-27 May 2006, Volume 1, Resolutions and decisions. (WHA59/2006/REC/1) p. 37-8. ed. Geneva, World Health Organization, 2007. The right to health - the fact sheet. Geneva, World Health Organization, 2007. Towards better leadership and management in health: report on an international consultation on strengthening leadership and management in low-income countries. (WHO/HSS/healthsystems/2007.3, Working Paper No. 10). Geneva, World Health Organization, 2007. Vapattanawong P, Hogan M, Hanvoravongchai P, Gakidou E, Vos T, Lopez A, Lim S. Reductions in child mortality levels and inequalities in Thailand: analysis of two censuses. The Lancet, Volume 369, Number 9564, 2007. Workers health: draft global plan of action. Report by the Secretariat. (EB12028/28 Rev.1). Geneva, World Health Organization, 2007. World health statistics 2007. Geneva, World Health Organization, 2007. The World health report 2007 - A safer future: global public health security i n the 21st century. Geneva, World Health Organization, 2007. 2 0 0 6 A decade of measuring the quality of governance - governance matters 2006: Worldwide governance indicators. The World Bank, 2006: 1-20. Approaching health financing policy in the WHO European Region. (EUR/RC56/BD/1). Copenhagen, World Health Organization Regional Office for Europe, 2006. Arif GM. Targeting efficiency of Poverty Reduction Programs in Pakistan. Working Paper no. 4. Pakistan Resident Mission Working Paper Series. Asian Development Bank, 2006. Benn H. Meeting our promises: basic services for everyone, everywhere. Fourth White Paper speech, UNISON, 16 February 2006. London. Bennett S. and Eichler R. Taking forward the health systems agenda: report of a consultation on developing the health systems action network . Partners for Health Reformplus Project, 2006. Cahill K, Caines K, Cassels A, Chen L, Conway M, Devillé L et al. High-Level Forum on the Health Millennium Development Goals: selected papers, 2003-200 5. Geneva, World Health Organization, 2006. Colombo F, Zurn P, Oxley H. OECD Reviews of Health Systems: Switzerland. Paris: Organisation for Economic Co-operation and Development and World Health Organization, 2006. Commission on Social Determinants of Health. Geneva, World Health Organization, 2006. Delivering as one. Report of the Secretary-General’s High- Level Panel. New York, United Nations, 2006. Department of Health. Our health, our care, our say: making it happen. London, Department of Health, 2006. Developing health-programme competencies: a learning initiative for WHO and its staff. (A discussion paper for the WHO Global Learning Committee). Geneva, World Health Organization, 2006. Doherty J and Gilson L. Proposed areas of investigation for the KN: an initial scoping of the literature. Health Systems Knowledge Network (KN), Discussion Document No. 1. Geneva, World Health Organization, draft, 2006. Dwyer J, Paskavitz M, Vriesendorp S, and Johnson S. An urgent call to professionalize leadership and management in health care worldwide. (MSH Occasional Paper No. 4). Cambridge, MA, Management Sciences for Health, 2006. A n n e x 2 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 51 40 Equity and health sector reform in Latin America and the Caribbean from 1995 to 2005: approaches and limitations. Sao Paolo, International Society for Equity in Health, 2006. Flores W, Riutort M, and Starfield B. Equity and health sector reform in Latin America and the Caribbean from 1995 to 2005: approaches and limitations. Toronto, Canada, The International Society for Equity in Health, 2006. Frenk J. Bridging the divide: global lessons from evidence- based health policy in Mexico. Lancet 2006;368:954-61. Greenhill, R. Real aid 2: making technical assistance work. Johannesburg, ActionAid International, 2006. Hamid Salim MA, Uplekar M, Daru P, Aung M, Declerq E, Lonnroth K Turning liabilities into resources: informal village doctors and tuberculosis control in Bangladesh. Bulletin of the World Health Organization 84(6) 479-484, 2006. Health action in crises: annual report 2005. (WHO/HAC/ AR/06.1). Geneva, World Health Organization, 2006. Health Metrics Network: what it is, what it will do and how countries can benefit. Geneva, World Health Organization, 2006. H unt P. ‘Right to health’ or ‘right to the highest attainable standard of health’. Statement by Paul Hunt, Special rapporteur on the right of everyone to the enjoyment of the highest attainable standard of health, 21 September 2006. UN Human Rights Council, 2006. Lob-Levyt J, Affolder R. Innovative financing for human development. Lancet 2006;367:885-7. Mills A, Rasheed F, Tollman S. Strengthening health systems. In: Jamison DT, Breman JG, Measham AR, Alleyne G, Claeson M, Evans DB et al., editors. Disease control priorities in developing countries. 2nd ed. ed. Washington, DC: The World Bank; 2006. p. 87-102. Knowledge for better health systems and better health. The Alliance strategic plan: 10-year outlook and 2006- 2008 plan. WHO/AHPSR/06.1. Geneva, World Health Organization. 2006. Making the money work through greater UN support for HIV/AIDS responses. The 2006-7 consolidated technical support plan for HIV/AIDS. Geneva, UNHIV/AIDS, 2006. Medium-term strategic plan 2008-2013 and Proposed programme budget 2008-2009. (A/MTSP/2008-2013; PB2208-2009). Geneva, World Health Organization, 2006. Mills A. Mass campaigns versus general health services: what have we learnt in 40 years about vertical versus horizontal approaches? Bulletin of the World Health Organization 2005 ;83(4):315-6. Opportunities for global health initiatives in the health system action agenda. Working paper no. 4 (WHO/EIP/ healthsystems/2006.1). Making health systems work. Geneva, World Health Organization. 2006. Perks C, Toole MJ and Phouthonsy K. District health programs and health-sector reform: case study in the Lao People’s Democratic Republic. Bulletin of the World Health Organization. 84(2): 132-138, 2006. Pillars of the health system. In: Jamison DT, Breman JG, Measham AR, Alleyne G, Claeson M, Ev ans DB et al., editors. Priorities in health. Washington, DC, The World Bank, 2006. p. 155-77. Public health innovation and intellectual property rights. Report of the Commission on Intellectual Property Rights, Innovation and Public Health. Geneva, World Health Organization; 2006. Research for health: a position paper on WHO’s role and responsibilities in health research. (ACHR45/05.16 Rev.1). Geneva, World Health Organization, 2006. Resolution WHA58.3. International health regulations. In: Fifty-eight World Health Assembly, Geneva, 16- 25 May 2005. Volume 1. Resolutions and decisions, Annexes. (WHA58/2005/REC/1). Geneva, World Health Organization, 2006. Scaling-up the HIV/AIDS response: from alignment and harmonisation to mutual accountability. London, Overseas Development Institute, 2006. Sen G, Östlin P. Women and gender equity knowledge network: interim report. Commission on Social Determinants of Health, 2006. Strengthening country health information systems: assessment and monitoring tool , Version 1.97. Health Metrics Network, 2006. Strengthening national capacities for epidemic preparedness and response in support to national implementation of IHR(2005). Report of a WHO meeting. (WHO/CDS/EPR/LYO/2006.4). Geneva, World Health Organization, 2006. A n n e x 2 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 52 41 Tackling the barriers to scaling up in health. Discussion at a special session for Ministers on 1st September 2006: 56th WHO Regional Committee for Africa, 2006. Taking stock: health worker shortages and the response to HIV/AIDS. (WHO/HIV/2006.5). Geneva, World Health Organization, 2006. The challenge of capacity development: working towards good practice. Paris, Organisation for Economic Co- operation and Development (OECD). (DAC Guidelines and Reference Series/A DAC Reference Document), 2006 The global plan to stop TB, 2006-2015. Geneva, World Health Organization, 2006. The high-level forum (HLF) on the Health Millennium Development Goals. Note prepared by the Department for Health Policy, Development and Services (HDS). Geneva, World Health Organization, 2006. The World health report 2006 - working together for health. Geneva: World Health Organization, 2006. Transparency International. Global corruption report 2006 - special focus: corruption and health. London, Pluto Press, 2006. What should be RHR’s contribution to the strengthening of health systems? Twenty-third Scientific and Technical Advisory Group (STAG), 23rd Meeting, Geneva, 14-16 February 2006. (RHR/STAG(23)/2006/8.3). Geneva, World Health Organization, 2006. 2 0 0 5 Bill & Melinda Gates Foundation and McKinsey & Company. Global health partnerships: assessing country consequences. McKinsey & Company, 2005. Evans DB, Adam T, Tan-Torres T, Lim S, Cassels A, Evans T. Education and debate. British Medical Journal 2005;331:1133-6. Fiscal space and sustainability from the perspective of the health sector. Report prepared for the High-Level Forum on the Health MDGs. Paris, 14-15 November 2005. High- Level Forum on the Health MDGs, 2005. Florez CE and Hernandez D Financing and the health system: Colombia Case Study, unpublished, 2005 HealthCast 2020: creating a sustainable future. PricewaterhouseCoopers, 2005. Health in fragile states: an overview note. Paris, 14-15 November 2005. High-Level Forum on the Health MDGs, 2005. Heller PS. Understanding fiscal space. IMF Policy Discussion Paper. (PDP/05/4). Washington, DC, International Monetary Fund. 2005. Integrating maternal, newborn and child health programmes (The World health report 2005, Policy Brief 1). Geneva, World Health Organization, 2005. Lewis M. Addressing the challenge of HIV/AIDS: macroeconomic, fiscal and institutional issues. (CGD Working Paper Number 58). Washington, DC, Centre for Global Development, 2005. Next phase of the WHO Regional Office for Europe’s Country Strategy: strengthening health systems. In: Fifty-fifth Session of the Regional Committee for Europe, Bucharest, 12-15 September 2005 . Provisional agenda item 6(e). (EUR/RC55/9 Rev.1 +EUR/RC55/COnf.Doc./5). Copenhagen, World Health Organization Regional Office for Europe, 2005. Östlin P. What evidence is there about the effects of health care reforms on gender equity, particularly in health? (Health Evidence Network report; http://www.euro.who. int/Document/E87674.pdf, accessed 01 November 2005). Copenhagen, WHO Regional Office for Europe. Paris declaration on aid effectiveness: ownership, harmonisation, alignment, results and mutual accountability (High-level forum, Paris, February 28 - March 2, 2005). Paris: High-level forum, 2005. Proposal for GAVI to invest in health systems strengthening (HSS) support. Background paper for the Delhi GAVI Board Meetings, 6-7 December 2005 2005. Quick J, Wibulpolprasert S, Shakow S, and Kasper T. Global task team working group 2: harmonization of technical support. Geneva, UNHIV/AIDS, 2005. Rantanen J. Basic occupational health services - strategy, structures, activities, resources. Helsinki, Finnish Institute of Occupational Health, 2005. Regional consultation on human resources in health: critical challenges. S eventh Regional Meeting of the Observatory of Human Resources in Health, Toronto, Canada, 4-7 October 2005. Washington DC, Pan American Health Organization, 2005. A n n e x 2 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 53 42 Resolution WHA58.28. eHealth. In Fifty-eighth World Health Assembly, Geneva, 16-25 May 2005, Volume 1, Resolutions and decisions. p. 121-3. Geneva, World Health Organization, 2005. Resolution WHA58.33. Sustainable health financing, universal coverage and social health insurance. In: Fifty- eight World Health Assembly, Geneva, 16-25 May 2005. Volume 1. Resolutions, decisions, Annexes. (WHA58/2005/ REC/1). Geneva, World Health Organization, 2005. Scaling up versus absorptive capacity: challenges and opportunities for reaching the MDGs in Africa. London, Overseas Development Institute, 2005. Strategic orientations for WHO action in the African Region, 2005-2009. Brazzaville, World Health Organization Regional Office for Africa, 2005. Strategy on health care financing for countries of t he Western Pacific and South-East Asia regions (2006-2010). In: Fifty- sixth session of the WHO Regional Committee, Noumea, New Caledonia, 19-23 September 2005. Provisional agenda item 13. (WPR/RC56/9). Manila, World Health Organization Regional Office for the Western Pacific, 2005. Toronto call to action: towards a decade of human resources for health in the Americas (2006-2015). Washington, DC, Pan American Health Organization, 2005. WHO knowledge management strategy. (WHO/EIP/ KMS/2005.1). Geneva, World Health Organization, 2005. WHO country presence 2005. (CCO/2005.01). Geneva, World Health Organization, 2005. Working together towards universal coverage (PowerPoint presentation: Maputo Joint Planning Workshop, Maputo, 31 August-1 September 2005). Geneva, World Health Organization, 2005. Wibulpolprasert S, Tangcharoensathien V, Kanchanachitra C. Are cost effective interventions enough to achieve the millennium development goals? Money, infrastructure, and information are also vital. British Medical Journal 2005;331:1093-4. 2 0 0 4 Berwick D. Lessons from developing nations on improving health care. British Medical Journal 2004;328:1124-9. Desplats D, Koné Y, Razakarison C Pour une medicine générale communautaire en première ligne. Médecine Tropicale, 64:539-544, 2004. Health system priorities in the Eastern Mediterranean Region: challenges and strategic directions. (EM/RC51/5). Cairo, World Health Organization Regional Office for the Eastern Mediterranean, 2004. Molyneux DH, Nantulya VM. Linking disease control programmes in rural Africa: a pro-poor strategy to reach Abuja targets and m illennium development goals. British Medical Journal 2004 ;328:1129-32. Potter C, Brough R. Systemic capacity building: a hierarchy of needs. Health Policy and Planning 2004;19(5):336-45. Sachs JD. Health in the developing world: achieving the Millennium Development Goals. Bulletin of the World Health Organization 2004; 82:947-9. Sexual and reproductive health and health systems development. Health Policy and Planning 2004;19(Suppl. 1). Strengthening WHO support for effective national health systems and better health outcomes: the Nairobi report. 20-22 April 2004 [draft 1a:26-4-04]. Geneva, World Health Organization, 2004. Tangcharoensathien V, Wibulpolprasert S, Nitayaramphong S. Knowledge-based changes to the Thai health system. Bulletin of the World Health Organization 2004; 82: 750–56. Travis P, Bennett S, Haines A, Pang T, Bhutta Z, Hyder A et al. Overcoming health-systems constraints to achieve the Millennium Development Goals. Lancet 2004;364:900-6. WHO medicines strategy 2004-2007 - countries at the core. (WHO/EDM/2004.5)ed. Geneva, World Health Organization, 2004. 2 0 0 3 Alwan A, MacLean D, Mandil A. Assessment of national capacity for noncommunicable disease prevention and control: the report of a global survey. WHO/MNC/01.2. Geneva, World Health Organization, 2001. Caines K, Vaughan JP. A review of WHO country cooperation strategy documents. Geneva, World Health Organization, 2003. Declaration on health development in the South-East Asia Region in the 21st century: review of progress. In Fifty-sixth WHO Regional Committee, New Delhi, 10-13 September 2003. Provisional agenda item 13. (SEA/RC56/ Inf 3). New Delhi, World Health Organization Regional Office for South-East Asia, 2003. A n n e x 2 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 54 43 Freedman L, Wirth M, Waldman R, Chowdhury M, Rosenfield A. Millennium Development Project Task Force 4 Child Health and Maternal Health - Interim report. New York, UN Millennium Project, 2003. Resolution WHA56.1. WHO framework convention on tobacco control. In: Fifty-sixth World Health Assembly, Geneva, 19-28 May 2003, Volume 1. Resolutions and decisions, Annexes. (WHA56/2003/ REC/1). Geneva, World Health Organization, 2003. 2 0 0 0 - 2 0 0 2 Lady Health Worker Programme. External Evaluation of the National Programme for the Family Planning and Primary Health Care. Quantitative Survey Report. Islamabad, Oxford Policy Management, 2002. Trade in health services - global, regional, and country perspectives. Washington DC, Pan American Health Organization, 2002. Brown A. Integrating vertical health programmes into sector wide approaches: experiences and lessons. Bern, Swiss Agency for Development and Co-operation, 2001. Sachs JD. Macroeconomics and health: investing in health for economic development. Report of the Commission on Macroeconomics and Health. Geneva, World Health Organization, 2001. Resolution A/RES/55/2. Resolution adopted by the General Assembly: 55/2. United Nations Millennium Declaration, 2000. The World health report 2000 - Health systems: improving performance. Geneva, World Health Organization, 2000. B e f o r e 2 0 0 0 Health systems development. In: Implementation of resolutions and decisions: report by the Director-General. Executive Board, 102nd Session, Geneva, 27 March 1998. Provisional agenda item 6. (EB102/7), 2-4. Geneva, World Health Organization. 1998. Policy objective: to make health sector development a cross dimensional aspect of every programme. Draft paper of the Health Sector Development Satellite Meeting, Geneva, 27 April 1998. Geneva, World Health Organization, 1998. Health systems development programme: a medium-term strategy. Geneva, World Health Organization, 1997. World development report 1993 - Investing in health. Washington DC, The World Bank,1993. Cohen JM. Building sustainable public sector managerial, professional, and technical capacity: a framework for analysis and intervention. (Development Discussion Paper No. 473) Cambridge, MA, USA, Harvard University: Harvard Institute for International Development. 1993. Declaration of Alma-Ata. In: International Conference on primary health care, Alma-Ata, USSR, 6-12 September 1978. Geneva, World Health Organization, 1978. A n n e x 2 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 55 44 useful Weblinks Africa health workforce observatory: http://www.afro.who.int/hrh-observatory eu ropean Observatory on health systems and policies www.euro.who.int/observatory Global Observatory for eHealth: http://www.who.int/goe Global atlas of the health workforce: h ttp://www.who.int/globalatlas/default.asp The global health library: http://www.who.int/ghl G TZ-ILO-WHO Consortium on Social Health Protection in developing Countries: h ttp://www.socialhealthprotection.org/ Health systems www.who.int/healthsystems H ealth evidence Network: http://www.euro.who.int/HEN The health academy: http://www.who.int/healthacademy H ealth InterNetwork Access to research Initiative: http://www.who.int/hinari Knowledge management for public health: h ttp://www.who.int/km4ph. Latin America and Caribbean Observatory of Human resources: h ttp://www.observatoriorh.org/eng/index.html Management for Health Services delivery (MAKer): http://www.who.int/management/en Patient safety: http://www.who.int/topics/patient_safety Service Availability Mapping: http://www.who.int/healthinfo/systems/serviceavailabilitymapping/en W HO-CHOICe = CHOosing Interventions that are Cost-effective: http://www.who.int/choice/en/ W HO european Ministerial Conference on Health Systems 2008: h ttp://www.euro.who.int/healthsystems2008. World Health Statistics: http://www.who.int/healthinfo/statistics W HO eastern Mediterranean regional Health System Observatory: http://gis.emro.who.int/HealthSystemObservatory/Main/Forms/Main.aspx A n n e x 3 E V E R Y B O D Y ’ S B U S I N E S S S – S T R E N G T H E N I N G H E A L T H S Y S T E M S T O I M P R O V E H E A L T H O U T C O M E S 56 57 Health Systems and Services (HSS) 20, Avenue Appia 1211 Geneva 27 Switzerland http://www.who.int/healthsystems isbn 978 92 4 5907 7 58 National Health Policy, 2017: Revealing Public Health Chicanery Date: July 14, 2018 From: Economic & Political Weekly Publisher: Athena Information Solutions Pvt. Ltd. Document Type: Article Length: 4,497 words Lexile Measure: 1490L Full Text: Byline: Vikas Bajpai Vikas Bajpai (drvikasbajpai@gmail.com) teaches at the Centre for Social Medicine and Community Health, Jawaharlal Nehru University, New Delhi. The National Health Policy, 2017 reflects the perfunctory attitude towards public health, so deeply entrenched among the mandarins of the health ministry. The policy paves the way for the contraction of public healthcare systems, thereby reducing the government's involvement in the delivery of health services, and facilitates the dominance of the private sector in curative care. However, in the absence of a robust public healthcare system, the goal of achieving "healthcare for all" becomes even more onerous. After a long hiatus, perhaps contemplative, the government finally came out with the National Health Policy (NHP), 2017 (MoHFW 2017a). Since the policy document has been finalised after almost two years, one hoped for changes being incorporated in the health policy in light of the debate around the Draft National Health Policy (DNHP), 2015 document. In an earlier article published in this journal, this author along with others had analysed this draft document (Rao et al 2015). However, concerns raised in this critique have remained unaddressed in the 2017 policy document. There can be little satisfaction in stating that the basic premises of our critique not only remain valid but seem to have been further strengthened by some baleful changes that have been strategically deployed in the NHP, 2017. It is immensely important that we absorb the import of these changes to calibrate our response to the new health policy; however, we shall begin by mentioning the points where credit is due to the policymakers. Additionally, the arguments made in the earlier critique (Rao et al 2015) shall not be revisited, except to facilitate the argument being made here. Giving Credit Where It Is Due It is heartening that the health policy reaffirms its objective to "improve health status through concerted policy action in all sectors and expand preventive, promotive, curative, palliative and rehabilitative services provided through the public health sector with focus on quality" (MoHFW 2017a: 3). In order to make funds available to achieve this laudable objective, the policy reaffirms the earlier resolve of raising the public expenditure on health to 2.5% of the gross domestic product (GDP) in a time-bound manner. Additionally, the preferred method of funding healthcare shall continue to be by way of general taxation (MoHFW 2017a: 5). Nothing could be more desirable than this solemn commitment coming true. However, our enthusiasm needs to be tempered by realpolitik. The previous United Progressive Alliance (UPA) government had committed to raise the contribution of the public exchequer to health to up to 3% of the GDP over the period of the implementation of the first phase of the National Rural Health Mission from 2005 to 2011, a promise that remained as elusive as ever. The current Narendra 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r1/8 59 Modi government, in its very first budget, presented in 2014, slashed the healthcare budget by 20% in one go, imperilling even day-to-day activities of many disease control programmes. Further, Arvind Panagariya, the vice-chairman of the NITI (National Institute for Transforming India) Aayog, which has replaced the erstwhile Planning Commission, feels that the healthcare needs of all poor can well be taken care of in just about three-quarters of 1% of the GDP (qtd in Kurian 2015). What is all the more intriguing is that the magnanimity of our rulers towards their countrymen seems to have dried up precisely at a time when they are making claims of India being the fastest-growing economy in the world. Nevertheless, though the odds remain onerous, one can always hope for a turnaround. The novelty of the policy document over and above the DNHP, 2015 is that it has incorporated "Specific Quantitative Goals and Objectives." The policy states: The indicative, quantitative goals and objectives are outlined under three broad components viz (a) health status and programme impact, (b) health systems performance and (c) health system strengthening. These goals and objectives are aligned to achieve sustainable development in health sector in keeping with the policy thrust. (MoHFW 2017a: 3) The salience of these quantitative goals and objectives lies in their being a benchmark against which the achievements of the health policy can be judged in time to come. This may also serve to hold the government and the health machinery to account with respect to success or failure in achieving these benchmarks. Dismal Track Record However, India's accomplishments with respect to past benchmarks are disappointing. With respect to the achievement of Millennium Development Goals (MDGs), the "Situation Analysis" document, which provides a backdrop to the NHP, 2017, states: India is close to reaching the Millennium Development Goals (MDGs) . From a baseline of 556 in 1990, the nation has achieved Maternal Mortality Ratio (MMR) of 167 by 2011-13. Assuming that the Annual Compound Rate of decline observed during 2007-09 and 2011-13 continues, the MMR is likely to reach the MDG-5 target of 139. In case of under-5 mortality rate (U5MR) the MDG target is 42. From a baseline of 126 in 1990, the nation has reached an U5MR of 49 in 2013, and if the rate of reduction over the past decade is sustained, the achievement in 2015 will be very close to the target. (MoHFW 2017b: 1) It is difficult to infer much in regard to the country's public health capacity and achievements from such kind of analysis and how to use this so as not to repeat the same mistakes over and over again. To put things in perspective, a newspaper article citing the Global Burden of Disease (GBD) study published in the Lancet said that "newborns in India have a lesser chance of survival than babies born in Afghanistan and Somalia"(Hindu 2017). The same article further stated: In the GBD (Global Burden of Disease) rankings for healthcare access and quality (HAQ), India has fallen 11 places, and now ranks 154 out of 195 countries. Further, India's healthcare index of 44.8 is the lowest among the sub-continental countries, as Sri Lanka (72.8), Bangladesh (51.7), Bhutan (52.7), and Nepal (50.8) all fared better. India's downward slide in the rankings indicates that it has failed to achieve healthcare targets, especially those concerning neonatal disorders, maternal health, tuberculosis, and rheumatic heart disease. Last year, India was ranked 143 among 188 countries. In the case of neonatal mortality, on a scale of 1 to 100, India scored 14 in the HAQ index, while Afghanistan scored 19/100 and Somalia, 21/100. Access to tuberculosis treatment in India was scored 26 out of 100, lower than Pakistan (29), Congo (30) and Djibouti (29). (Hindu 2017) 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r2/8 60 There were many other observations in the article worth worrying about, but with the numero uno of our national concerns being "cow vigilantism," we could not care less about such irresponsible and blatantly "anti-national" reports. Little wonder then that these findings were soon forgotten, leaving little chance of any deliberation. Reducing Government's Liability The lackadaisical and perfunctory attitude towards public health, deeply entrenched among the mandarins of the health ministry, is also reflected in the paragraph regarding the "social determinants of health" which mercifully has been included in the "Situation Analysis" document. The concerned paragraph states: This policy recognises the causal links between health outcomes and social determinants of health.Health of the population is determined largely by lifestyle (50%) followed by biological and environmental factors (20% each), whereas health systems related factors contribute only 10%.Achievement of national health goals would require addressing all the social determinants (distal and proximal) in the context of rapid economic growth and changing life styles with a focus on the most vulnerable and marginalised. This preventive aspect needs to be adequately addressed through assessing the impact of existing and future non-health sector programmes and policies through the health lens. (MoHFW 2017b; emphasis added) In their enthusiasm to assert that they have already arrived at the international high table, the use of words "context of rapid economic growth and changing life styles" by the mandarins seems to have entirely eclipsed the phenomenon of "poverty" that constitutes the most important context of the lives of those hundreds of millions of people whose interests are most affected by this policy. It might help reminding our mandarins of the findings of the National Commission for Enterprises in the Unorganised Sector (NCEUS), popularly known as the Arjun Sen Gupta Committee report. The committee had famously declared that 77% of Indians subsisted on less than Rs 20 a day and a daily per capita expenditure of merely Rs 96 put a person in the "high income group" (Sengupta et al 2008). This reflects both on the extent of poverty and the much-trumpeted rising level of affluence of our common people. This was as far back as 2007. However, since the world economic crisis of 2008, it has been a downward slide for the economy and for the people, the novel ways of recalibrating the country's GDP notwithstanding. On the social determinants of health, the "Situation Analysis" document (MoHFW 2017b: fn 18) cites a World Health Organization (2008) report, "Closing the Gap in a Generation: Health Equity through Action on the Social Determinants of Health." If the authors had cared to look at the large body of literature on the social determinants of health from India other than this one reference, they would have realised that those being referred to as "vulnerable and marginalised" in the document are not just any people. They have a definite social and political identity as members of certain caste groups, tribes and religious minorities just like the United States (US) where the "vulnerable and marginalised" communities comprise primarily of blacks and some other racial minorities. Perhaps, there is a fear that recognition of these identities might lead the government to acknowledge a systemic and systematic discrimination prevalent in the society against these people. This is a particularly touchy issue with the present Modi government, which perceives such articulation as denigration of "Bharat Mata" (Mother India) by left-leaning intellectuals. The "Situation Analysis" document (MoHFW 2017b: fn 19) also refers to a report by the surgeon general of the US on the physical activity and health of US citizens (US Department of Health and Human Services 1996). The percentages of 50, 20, 20, and 10 allocated to "lifestyle factors," "biological factors," "environmental factors" and "health system related factors," respectively, which shape the health of the population, are taken from the surgeon general's report and cited in the "Situation Analysis" document, and may strictly apply to the people of the US. All of these factors, while remaining relevant to Indian conditions as well, will not carry the same weight as they may in the context of American society. 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r3/8 61 For example, in the US, the majority of the population is urban, living in a society with much higher levels of mechanisation; the society is characterised by lower levels of poverty, and the poverty line in the US is not the same as our poverty line, which actually is a destitution line. As opposed to this, in India, an overwhelming number of people live in villages, in societies with very low levels of mechanisation, and where poverty is deeply entrenched. These are also the people who are most in need of caring social sector policies so that they can exist with a modicum of dignity. Can it be said then that the lifestyle of these Indians is the same as that of the Americans and contributes up to 50% in the shaping of their health, while the contribution of health system related factors is a mere 10%? In the US, diabetes and hypertension could well be an outcome of sedentary lifestyles and consumption of fast foods leading to obesity. However, in India the epidemic of diabetes even among the poor is not explained by lifestyles as much it perhaps is by Barker's hypothesis, which privileges intergenerational impact of malnutrition as the triggering mechanism. The health of a landless agricultural labourer and a casual manual labourer living in a shanty in an average Indian city is far more likely to be shaped by health system (which includes not just the system of health services, but almost the entire development sector) related factors than by their starved lifestyle. The use of this reference drawn from a country like the US is not just a matter of casual oversight. It is on purpose. After all, if lifestyles shape peoples' health to as high an extent as 50%, then the overwhelming responsibility of improving their health also lies on individuals. Perhaps, only little can be done by either individuals or by health systems about the 20% impact of biological factors in shaping the health of the people. And, even if the public health systems are dysfunctional, it can at its worst adversely affect your health only to the extent of 10%. Such a reductionist approach also reduces the government's liability towards peoples' health. Any rationale that supports a reduced liability on part of the government paves the way for contraction of public healthcare systems, leaving the field wide open for private players. This is precisely what the NHP, 2017 argues, albeit in a roundabout manner; and it is in doing this that the chicanery of the health planners plays out. Corporate Hospitals Just like the DNHP, 2015, NHP, 2017 also lauds the high growth rates of the healthcare industry in the country. It also proclaims as an achievement the fact that "The Government has invested heavily in the last 25 years in building a positive economic climate for the healthcare industry." However, the DNHP, 2015 was more forthright in acknowledging that corporate hospitals cannot be expected to toe the public health goals set by the government. Hence, it proposed that Given that the private sector operates within the logic of the market and that they contribute to the economy through their contribution to the growth rate and by the national earnings from medical tourism, there need not be any major effort to persuade them to care for the poor, as long as their requirements and perceptions do not influence public policy towards universal healthcare. Where corporate hospitals and medical tourism earnings are through a high degree of associated hospitality arrangements, one could consider forms of taxation/cess, especially for certain procedures and services as a form of resource mobilisation towards the health sector. (MoHFW 2014: 36; emphasis added) The NHP, 2017 has sought to reinfuse, with little academic finesse, a sense of altruism in what is otherwise a purely profit-oriented hospital industry. It has modified the above formulation thus: The policy enunciates the core principle of societal obligation on the part of private institutions to be followed. This would include: * Operationalisation of mechanisms for referral from public health system to charitable hospitals. * Ensuring that deserving patients can be admitted on designated free / subsidised beds. 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r4/8 62 The policy proposes to consider forms of resource generation, where corporate hospitals and medical tourism earnings are through a high degree of associated hospitality arrangements and on account of certain procedures and services, as a form of resource mobilisation towards the health sector. (MoHFW 2017a: 15; emphasis added) However, what is left unexplained in the policy document is how our policymakers shall reconcile the two diametrically opposite aims, that of the imperative to maximise profits of the corporate hospitals, and that of the government to provide healthcare to people irrespective of their ability to pay, and that too when the energies of these hospitals shall be focused on generating revenue through "hospitality arrangements" and through "certain procedures and services" (read unnecessary procedures and services). Is there even one example from across the world where this has been possible with any measure of success? The DNHP, 2015 had at least acknowledged this and mentioned that Though there is an obligation imposed by their access to considerable tax exemptions and public acquisition of land, it is only a rare private commercially run hospital that meets these obligations (those towards fulfilment of public health objectives). A number of not-for-profit hospitals however offer this, but these are few. (MoHFW 2014: 36) However, this acknowledgement has been removed without a trace from both the "Situation Analysis" document for the NHP, 2017 and the policy per se. It might be argued nonetheless that the government can facilitate affordable curative care for the people by becoming a net purchaser of the expertise offered by these private tertiary care hospitals. Moreover, considerable experience from across the country and the world is now available to show as to how these publicly funded health insurance schemes have been an utter failure in achieving their desired goals and have worked towards rendering the already weak public sector further effete (Reddy K S et al 2011; Shukla et al 2011; Reddy S 2013; Prasad and Raghavendra 2012; Mohanan et al 2014; Reddy and Mary 2013; Selvaraj and Karan 2012; Narasimhan et al 2014; Sujatha Rao 2014; Averill and Marriott 2013; Bajpai and Saraya 2012). A particularly pithy indictment of publicly funded health insurance schemes is provided by the following statement: Universal Health Coverage (UHC) is being widely promoted as a panacea for health inequities yet there are fundamental differences in its interpretation and implementation especially on financing. health insurance schemes, often promoted by the World Bank and other donors, invariably disadvantage the poorest and unhealthiest. Without more equitable, tax based approaches, inequalities in health will continue to grow and threaten us all. (qtd in Averill and Marriott 2013) As far as the question of affordability and fair pricing of services is concerned, the government can achieve that only if it retains the ability to provide curative health services to a considerable extent through a robust public sector healthcare system. The absence of a robust public sector and thereby the government's inability to provide curative services can only beget a helpless dependence for these services on the private sector. The consequence will either be a huge cost to the public exchequer for purchasing these services or else the government may simply abdicate its responsibility, leading to huge out-of-pocket expenditures for the people or economic inaccessibility of curative care. The policy does talk of "purchasing care after due diligence from non-Government hospitals as a short-term strategy till public systems are strengthened" (emphasis added). However, prudence demands that we go not by the words of the government, but by its deeds. The behemoth of the private healthcare industry, led by the corporate tertiary care hospitals, is a result of concerted efforts by various governments since 1990 to bring it into existence. While there have been several inquiry committees that have documented the various instances of how private tertiary care hospitals reneged on their mandatory obligations towards poor patients over the years, it is difficult to recall if ever an example was made of any of these hospitals by any government in the 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r5/8 63 country. On the other hand though, the government's policy commitment to further the interests of the private healthcare industry seems absolute. Addressing Malnutrition The commitment towards furthering the interests of the private sector can also be seen in other sectors that have an impact on health; for example, let us take up something as fundamental as "nutrition." The extent and depth of malnutrition in India allows many poorer countries to humble us. Nutrition was one public health problem that was given short shrift in the DNHP, 2015, and to that extent the inclusion of a separate section on nutrition, "Interventions to Address Malnutrition and Micronutrient Deficiencies," in the NHP, 2017 is creditworthy. The one fundamental truth about human nutrition is that so long as people have their staple diets to their fill, they manage to get all the energy and nutrients, including micronutrients, required by the body to remain healthy even in harsh environments such as the Kalahari, desert in South Africa and the Arctic (Kuhnlein and Receveur 1996; Lang 2014). It cannot possibly be anyone's case that all the bushmen of Kalahari and Eskimos in the polar region are malnourished. The inability of people to get adequate amounts of their staple diet leads to deficiency of dietary energy derived from macronutrients (carbohydrates, proteins and fat) and micronutrients (vitamins and minerals). With the exception of iron and vitamin B12 deficiency, which can be derived only from animal source foods, rarely does micronutrient deficiency occur in the absence of dietary energy or macronutrient deficiency (Kennedy et al 2003; Black 2003). Additionally, poverty is the foremost cause of dietary energy deficiency worldwide. In defiance of these fundamentals of human nutrition, NHP, 2017 states: Malnutrition, especially micronutrient deficiencies, restricts survival, growth and development of children. It contributes to morbidity and mortality in vulnerable population, resulting in substantial diminution in productive capacity in adulthood and consequent reduction in the nation's economic growth and well-being. Recognising this, the policy declares that micronutrient deficiencies would be addressed through a well-planned strategy on micronutrient interventions. Focus would be on reducing micronutrient malnourishment and augmenting initiatives like micro nutrient supplementation, food fortification, screening for anemia and public awareness. Policy recommends exploring fortified food and micronutrient sprinkles for addressing deficiencies through Anganwadi centers and schools. (MoHFW 2017a: 11) So, the whole problem of malnutrition has been rendered into a problem of micronutrient deficiencies which seem to occur in the absence of the problem of hunger; and if there is no hunger, then poverty as the biggest cause of under-nutrition has no business to be in the reckoning. So, the solution to India's massive problem of malnutrition is micronutrient sprinklers and fortified foods, both of which shall be supplied by companies and the people shall be mere recipients. Let us just try and think of what could have been achieved if the government were to roll out poverty alleviation programmes centred around well-thought-out land reforms, accompanied with agrarian reforms in rural areas and simultaneously initiate measures to create sustainable livelihoods in the urban areas by curbing the rapacious urge for maximisation of profits by the corporates. These changes would have given the people the agency to try and overcome their poverty and hunger, and take their destiny in their own hands rather than being passive recipients of help. Enhanced economic productivity would just have been a byproduct in this march for social transformation. There could not be a better way of soliciting collaboration between sectors to address wider determinants of health of which we find many a laudable references in the policy document. Alas, this has never been the intention of India's ruling elite. The solution to the public health problems of the people suggested in the form of the NHP, 2017 is nothing but chicanery of the highest order, designed to benefit the big corporate healthcare providers at the cost of public healthcare. It seeks to reduce the meaning of "health" to just 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r6/8 64 provisioning of "curative care," rather than being a state of "complete physical, mental and social well-being" as enshrined by the World Health Organization. References Averill, C and Anna Marriott (2013): "Universal Health Coverage: Why Health Insurance Schemes are Leaving the Poor Behind," Oxfam GB for Oxfam International, Oxford, October. Bajpai, V and Anoop Saraya (2012): "Rashtriya Swasthya Beema Yojna-A Public Health Perspective," Indian Journal of Social Work, Vol 73, No 2, pp 265-86. Black, M M (2003): "Micronutrient Deficiencies and Cognitive Functioning," Journal of Nutrition, Vol 133 (11 Suppl 2), pp 3927S-31S. Hindu (2017): "Chance of Newborn Survival: Somalia Better off than India," 19 May, viewed on 17 June 2017, http://www.thehindu.com/news/national/chance-of-newborn-survival-somalia- better-off-than-india/article18511050.ece. Kennedy, G, G Nantel and P Shetty (2003): "The Scourge of Hidden Hunger: Global Dimensions of Micronutrient Deficiencies," Food, Nutrition and Agriculture, P Dasgupta and R Hauspi (eds), Food and Agriculture Organization, Rome, viewed on 19 June 2017, http://www.fao.org/docrep/005/Y8346M /y8346m02.htm. Kuhnlein, H V and Olivier Receveur (1996): "Dietary Change and Traditional Food Systems of Indigenous Peoples," Annual Review of Nutrition, Vol 16, pp 417-42. Kurian, O C (2015): "Financing Healthcare for All in India: Towards a Common Goal," Oxfam India. Lang, Ondrej (2014): "Dietary Adequacy Among the Native Eskimo," Bachelor's Diploma Diss, Masaryk University, Czech Republic, viewed on 19 June 2017, https://is.muni.cz/th/382859/ff_b/BA_Thesis.rtf. MoHFW (2014): "Draft National Health Policy 2015," Ministry of Health and Family Welfare, Government of India, New Delhi, December. - (2017 a): "National Health Policy 2017," Ministry of Health and Family Welfare, Government of India, New Delhi. - (2017 b): "Situation Analysis: Backdrop to the National Health Policy 2017," Ministry of Health and Family Welfare, Government of India, New Delhi. Mohanan, M, Sebastian Bauhoff, Gerard La Forgia, Kimberly Singer Babiarz, Kultar Singhe and Grant Millerf (2014): "Effect of Chiranjeevi Yojana on Institutional Deliveries and Neonatal and Maternal Outcomes in Gujarat, India: A Difference-in-differences Analysis," Bulletin of the World Health Organization, Vol 92, No 3, pp 187-94, http://dx.doi.org.ezproxy.uio.no/10.2471/BLT.13. 124644. Narasimhan, H, V Boddu, P Singh, A Katyal, S Bergkvist and M Rao (2014): "The Best Laid Plans: Access to the Rajiv Aarogyasri Community Health Insurance Scheme of Andhra Pradesh," Health, Culture and Society, Vol 6, No 1, https://hcs-pitt- edu.ezproxy.uio.no/ojs/index.php/hcs/article/view/163. Prasad, N P and P Raghavendra (2012): "Healthcare Models in the Era of Medical Neo- liberalism: A Study of Aarogyasri in Andhra Pradesh," Economic & Political Weekly, Vol 47, No 43, 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r7/8 65 pp 118- 26. Rao, Sujatha (2014): "For Public Health as Political Priority," Hindu, 13 October, viewed on 20 October 2014, http://www.thehindu.com/opinion/lead/for-public-health-as-political- priority/article6493944.ece. Rao, M, Prachin Godajkar, Rama Baru, Ramila Bisht, Ritu Priya Mehrotra, Rajib Dasgupta, Sunita Reddy and Vikas Bajpai (2015): "Draft National Health Policy 2015: A Public Health Analysis," Economic & Political Weekly, Vol 50, No 17, pp 94-101. Reddy, K S, S Selvaraj, K D Rao, M Chokshi, P Kumar, V Arora, S Bhokare and I Ganguly (2011): "A Critical Assessment of the Existing Health Insurance Models in India," Public Health Foundation of India, New Delhi. Reddy, S (2013): "Aarogyasri Scheme in Andhra Pradesh, India: Some Critical Reflections," Social Change, Vol 43, No 2, pp 245-61. Reddy, S and Immaculate Mary (2013): "Rajiv Aarogyasri Community Health Insurance Scheme in Andhra Pradesh, India: A Comprehensive Analytic View of Private Public Partnership Model," Indian Journal of Public Health, Vol 57, No 4, pp 254-59. Sengupta, A, K P Kannan and G Raveendran (2008): "India's Common People: Who Are They, How Many Are They and How Do They Live?" Economic & Political Weekly, Vol 43, No 11, pp 49 -63. Shukla, R, Veena Shatrugna and R Srivatsan (2011): "Aarogyasri Healthcare Model: Advantage Private Sector," Economic & Political Weekly, Vol 4, No 49, pp 38-42. Selvaraj, S and Anup K Karan (2012): "Why Publicly-Financed Health Insurance Schemes Are Ineffective in Providing Financial Risk Protection," Economic & Political Weekly, Vol 47, No 11, pp 60-68. US Department of Health and Human Services (1996): "Physical Activity and Health: A Report of the Surgeon General," Atlanta, GA: US Department of Health and Human Services, Centers for Disease Control and Prevention, National Center for Chronic Disease Prevention and Health Promotion. World Health Organization (2008): "Closing the Gap in a Generation: Health Equity through Action on the Social Determinants of Health," Final Report of the Commission on Social Determinants of Health, Geneva. Copyright 2018 Economic and Political Weekly, distributed by Contify.com Copyright: COPYRIGHT 2018 Economic & Political Weekly http://athena.co.in/ Source Citation (MLA 9th Edition) "National Health Policy, 2017: Revealing Public Health Chicanery." Economic & Political Weekly, 14 July 2018. Gale Academic OneFile, link.gale.com/apps/doc/A546509914/AONE? u=oslo&sid=bookmark-AONE&xid=86326948. Accessed 4 Jan. 2025. Gale Document Number: GALE|A546509914 04/01/2025, 18:14National Health Policy, 2017: Revealing Public Health Chicanery - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/i.do?p=AONE&u=oslo&id=GALE|A546509914&v=2.1&it=r8/8 66 431 www.cmj.hr Anna Lydia Svalastog 1 , Doncho Donev 2 , Nina Jahren Kristoffersen 1 , Srećko Gajović 3 ¹ Østfold University College, Department of Health and Social Studies, Fredrikstad, Norway ²University “Ss Cyril and Methodius”, Faculty of Medicine, Institute of Social Medicine, Skopje, Republic of Macedonia ³University of Zagreb School of Medicine, Croatian Institute for Brain Research, Zagreb, Croatia srecko.gajovic@hiim.hr Concepts and definitions of health and health-related values in the knowledge landscapes of the digital society KNOWLEDGE LANDSCAPES Croat Med J. 2017;58:431-5 https://doi.org/10.3325/cmj.2017.58.431 The knowledge landscapes (http://knowledge-landscapes. hiim.hr/) represent multidimensional environments, which individuals encounter when searching for knowledge, par- ticularly, knowledge related to health (1,2). In digital soci- ety, knowledge is well distributed virtually and online. A substantial fraction of knowledge landscapes is also locat- ed in the digital environment. Both health and knowledge need to be understood today as a part of the digital soci- ety. It is important to estimate the impact that digital so- ciety has on knowledge landscapes and on health. This is especially relevant in relation to the 90th anniversary of Za- greb Andrija Štampar School of Public Health and the work of its founder, Andrija Štampar, with ongoing ambition of the School to be on the leading edge of public health un- derstanding in the present society (3). Hence, this article deals with the concepts of health in relation to the present digital environment. How knowledge relevant to health and well-being is dis- tributed in the digital society, and how the search for this knowledge, ie, navigating knowledge landscapes, influ- ences everyday life and health needs to be clarified. We present different definitions of health and health-relat- ed values. The usual approach to explaining health def- initions would be to give a historical and chronological overview showing the development of the ideas over time to better understand the current position. In con- trast to this, in the online environment, the overload of in- formation and limitless opportunities of content presen- tation result in co-existence of different views. We claim that, today, we need a historical overview to identify and understand this multiplicity of views and standpoints co- existing in the digital environment. This co-existence be- ing the product of digital society could be referred to as “digital anachronism”. HISTORICAL OVERVIEW OF ATTITUDES AND CONSIDERATIONS ABOUT HEALTH – FROM CONCEPTS OF BALANCE TO IDEAS ABOUT HEALTH AS ECONOMIC CATEGORY The concept of health as a balance between a person and the environment, the unity of soul and body, and the natu- ral origin of disease, was the backbone of the perception of health in ancient Greece. Similar concepts existed in an- cient Indian and Chinese medicine (4,5). In the 5th centu- ry BC, Pindar defined health as “harmonious functioning of the organs”, emphasizing the physical dimension of health, the physical body and the overall functionality, accompa- nied by the feeling of comfort and absence of pain. Even today, his definition bears importance as a prerequisite for the overall health and wellness. Plato (429-347 BC) in his “Dialogues” pointed out that a perfect human society could be achieved by harmonizing the interests of the in- dividual and the community, and that the ideal of ancient Greek philosophy “a healthy mind in a healthy body” could be achieved if people established internal harmony and harmony with the physical and the social environment. Ac- cording to Aristotle’s teaching, man is a social being by his very nature; he tends to live in communities with the duty to respect the moral standards and ethical rules. Aristotle emphasized the necessity for regulating the relations in the society to achieve harmonious functioning and pres- ervation of health of its members. Democritus connected health with behavior, wandering why people prayed to God for health, which was essentially under their 67 KNOWLEDGE LANDSCAPES 432 Croat Med J. 2017;58:431-5 www.cmj.hr own control. Hippocrates explained health in connection with the environmental factors and lifestyle. Hippocrates was the creator of the concept of “positive health”, which depended on the primary human constitution (we consid- er it today as genetics), diet, and exercise. He thought that proper diet and exercise were essential for health, and that seasons’ changes had a profound effect on the mind and body, resulting in different types of predominant diseases during the winter (respiratory tract diseases) and summer (digestive tract diseases) (4,5). A lot might be said about the long standing philosophical discussion about body and soul, and in present society between body and mind, as an active dichotomy (Plato and Hellenism) or as an integrated unity (usually reference to Aristotle), which is important to know about in the current online environment. In the Middle Ages, health perception was strongly influ- enced by religion and the church. After Roman Empire fell apart, the church was left as an only important infra- structure providing care for the people and collecting the knowledge on remedies, eg, herbs grown in monas- tery gardens (6). The “forgotten” knowledge of antiquity was re-discovered during the Renaissance and re-framed up to the present. During the period of Industrial Revolu- tion, health became an economic category, which was to allow good condition and working ability and reduce lost work days due to illness. Accordingly, the value of health was such as enabling economic profit. The health was in- tertwined with Darwinian understandings of strength and being the fittest, where meaning of life was tied to physi- cal survival. Another health aspect considered the ability of the individual to adapt to the influences from the environ- ment to the extent that the individual could tolerate and resist. When the adjustment is over, the disease occurs as a natural consequence. This approach first reflected only biological mechanisms of adaptation, later adding on in- fluences from the environment, which needed to be gov- erned and modified (4,5). MODERN CONCEPTS OF HEALTH – FROM INDIVIDUAL TO SOCIETAL RISKS AND BACK TO THE INDIVIDUAL All modern concepts of health recognize health as more than the absence of disease, implying a maximum capac- ity of the individual for self-realization and self-fulfillment. This should equilibrate the human inner forces and pos- sibilities with the feeling of pleasure or dissatisfaction in their relations with the environment (7). Social medicine and public health approach to health advocate that we should not only observe the health of the indi- viduals, but also the health of the groups and the commu- nity, as a result of the interaction of the individuals with the social environment. The holistic concept of health is contained in the expres- sion of wholeness. Health is a relative state in which one is able to function well physically, mentally, socially, and spiri- tually to express the full range of one’s unique potentiali- ties within the environment in which one lives. Both health and illness are dynamic processes and each person is lo- cated on a graduated scale or continuous spectrum (con- tinuum) ranging from wellness and optimal functioning in every aspect of one’s life, at one end, to illness culminating in death, at the other (3,8). The theory of salutogenesis takes a different view of what creates health and what factors support health, as op- posed to the conventional approach of pathogenesis to study the factors that cause disease (9). To find the “origins of health”, one needs to search for factors that support the human health and welfare (10). DEFINITION OF HEALTH BY THE WORLD HEALTH ORGANIZATION To establish social welfare and to facilitate, encourage, and secure individual autonomy and dignity are key challenges in the present time and society. The modern understanding of health became official when the World Health Organiza- tion (WHO), at the time of its establishment in 1948, includ- ed the definition of health in its Constitution. The definition was proposed by Dr Andrija Štampar, a prominent schol- ar from Croatia in the field of social medicine and public health and one of the founders of the WHO. This generally accepted definition states that “health is a state of complete physical, mental, and social well-being and not merely the absence of disease or infirmity” (11). This definition promot- ed for the first time that, in addition to physical and mental health, social welfare is an integral component of the over- all health, because health is closely linked to the social envi- ronment and living and working conditions. Respecting this definition as a global concept, many re- searchers and theorists subsequently advocated for adop- tion of working, practical, and operational definitions of health. In 1977, with the adoption of the WHO Global Strat- egy “Health for All by the Year 2000”, a pragmatic concept of health – the ability to conduct a socially and economi- cally productive life – was accepted indirectly, which was an essential goal of this Strategy (12). 68 433 Svalastog et al: Concepts and definitions of health and health-related values in the knowledge landscapes of the digital society www.cmj.hr To define health in operational and working terms was vi- tal for creating policies and programs for maintaining and improving health, and it considerably managed to exceed the widely rooted notion that health simply means the ab- sence of disease. The Ottawa Charter from the 1st Inter- national Conference on Health Promotion, held in Ottawa, Canada, in 1986, says that health is created in the context of everyday life and environment, where people live, love, work, and play. Thus, active and interactive understanding of health was introduced. The goal of health promotion is to combine the approach for addressing the social de- terminants with the resolution and commitment to mo- tivate and encourage the individuals and the communi- ty for their active approach toward health and embracing healthy lifestyles (13-16). Within the last few decades, the WHO definition of health has been increasingly amended and supplemented by the fourth dimension – spiritual health. Generally speaking, spiritual health involves a sense of fulfillment and satisfac- tion with our own lives, system of values, self-confidence and self-esteem, self-awareness and presence, peaceful- ness and tranquility with dynamic emotional balance, both internal and toward the environment, morality and truth- fulness, selflessness, positive emotions, compassion and willingness to help and support others, responsibility and contribution to the common good, and successful man- agement of everyday life problems and demands as well as social stress (17). HOW THE HEALTH IS PERCEIVED IN THE CURRENT DIGITAL ENVIRONMENT – A LAY PERSON’S PERSPECTIVE The digital society, where information technology has led to fundamental societal shifts, is a carrier of particular char- acteristics. It got new organizing principles (relations and arenas) for public institutions and private agents, and it has also altered the relation between public and private (18). In digital society, information technology has become some- thing more than a tool for communication, storage, and sharing of information. Therefore, it should not be reduced to another story we add to the former stories of society. Instead, the society has altered as such, and it needs to be described on its own terms. To act as a citizen in a digital society presupposes having particular skills on how to get hold on knowledge and how to access, interpret, and use it in the online environment. In the digital society, knowledge is organized in dynamic ten- tative online infrastructures and made available to users through different search tools and engines and their op- erative algorithms. This means that digital society frames, alters, and produces knowledge in a complex way, and the individuals today need skills to read these continuously changing landscapes critically and navigate them safely (1,2,19,20). We have conceptualized this multidimensional, technology-enabled environment, open to individual ac- cess, as the knowledge landscapes (1). As a citizen, the in- dividual needs to know how to navigate these knowledge landscapes to gain health-related information and be able to decide on strategies and services for one’s own life and the lives of others one cares for. The wide array of producers contribute to the contents to be found online, which enables them to express their own thoughts and visions, in particular in regard to health. An important question is whether societally prescribed values and theoretical positions are also reflected in lay people’s empirical understandings and perceptions of health. Health professionals and politicians also need to know what people themselves perceive as the most im- portant issues regarding health, in particular what health is, and which factors in people’s lives constitute health. This knowledge is needed to meet individuals in various health care settings and to deal with health issues across the digital realm. Research on individual perceptions regarding health and illness has been accumulating for some time, and it is be- coming apparent that they have significant consequences on the person’s health behavior (21). It is found that gender and age influence people’s perceptions of health as much as their background and environmental factors. Overall, lay people’s perspective on health and illness should not be viewed as constructs on opposite ends of a single contin- uum, but rather as two distinct but overlapping constructs (22). Experiences of health are more intangible and elu- sive than experiences of illness, making the former much more challenging to study (23). Health could be taken for granted and not brought to the persons attention before it’s challenged in situations characterized mainly by the ac- tual or threat of change, disease, or loss. Zahra et al (24) studied lay people’s perceptions of health and factors affecting health across 29 countries. People belonging to different backgrounds had different per- ceptions regarding determinants of health. The high- est percentage of people agreed that environment was the determinant of health, which was consistent with the scientific view of increased burden of diseases 69 KNOWLEDGE LANDSCAPES 434 Croat Med J. 2017;58:431-5 www.cmj.hr caused by environmental factors. Fugelli & Ingstad (25,26) conducted a multi-sited ethnographic study to explore lay people’s perceptions of health in different contexts, envi- ronments, and sites. They interviewed people in their own homes, in five different locations in Norway, in rural areas, small and big cities, people from different socioeconomic and cultural background, living on the coast, inland, in fish- ing-, agriculture- and industrial communities. They identi- fied six essential elements in people’s conceptualization of health in their actual situations: well-being, function, na- ture, a sense of humor, coping, and having energy. The lay perspective on health appears to be characterized by three qualities: wholeness, pragmatism, and individu- alism. Wholeness is related to health as a holistic phenom- enon. Health is an aspect interwoven with all other aspects of life, everyday life, working life, family life, and commu- nity life. Health is viewed a resource and a total, personal, situation-specific phenomenon. Absence of disease is not enough – the life situation as a whole must be taken into consideration. Family functioning and children’s welfare is an important part of experiencing health as wholeness. To be able to live according to one’s personal values is also an important issue. Pragmatism reflects the health as a relative phenomenon. Health is experienced and evaluated accord- ing to what people find reasonable to expect, given their age, medical conditions, and social situation. In this way, health is not necessarily freedom from disease or loss of functional abilities. Other positive values in life can com- pensate for different types of losses. Most people are realis- tic in their life-expectations. Finally, individualism relates to health as a highly personal phenomenon. The perception of health depends on who you are as a person. To be part of a society and to feel close to some other persons seems to be important to all. Furthermore, values are individual and, as every human being is unique, strategies for improving health must be individualized. HEALTH DEFINITIONS AT THE INTERSECTION OF TECHNOLOGY, MEDICINE, AND INDIVIDUALS IN THE DIGITAL SOCIETY The digital society allows different perspectives to co-ex- ist and dynamically evolve in the different forms of online environment. Subsequently, the different views on health are present online in the same time, competing for atten- tion of the visitors, users, and creators of the digital con- tent. Some of these ideas, although seemingly new and appealing, frequently represent refurbished historical concepts. Moreover, every public health-related in- tervention should consider its online context. To be able to identify and recognize the individual understanding of health is important, in particular when this conception of health contradicts recommendations for diseases that need medical intervention. The plurality of health definitions reflects the variety of con- texts in which health is elaborated. A concept ‘home con- text’ is the context in which the concept originates. It makes sense predominantly inside but not necessarily outside its home context. Conceptualizing is a verbal act that sets out to identify and shape phenomena’s border and content. The conceptualization localizes and attributes identity, con- tent, or meaning. The definitions of health obviously reflect socially and culturally constructed and tentative catego- ries. The relation between an individual and society is im- plied in most concepts of health. In particular, in the digital environment, critical analysis of health concepts helps us to understand better health policies and politics and their consequences. As they frequently represent societal pow- ers rather than phenomenological differences, they are ac- cordingly accepted, criticized, or even rejected. Today’s society is a complex, high-cost, high-tech society where citizens constantly need to learn and update their knowledge and skills to be able to manage their own lives. As digital society is built on software that is constantly re- newed or replaced by new software, navigation has be- come a new ‘skill of hunting and gathering’. To appreciate concepts and conceptualizations, knowledge has become a key quality in digital society. The health concepts – partic- ularly concepts we use to explain, treat, heal or cope with disease – are words we also use as search tools. A feature of digital society is that past and present categories and un- derstandings are available at the same time, undermining the traditional western schooling system, where accumu- lation of past knowledge is understood and acknowledged as predecessor to present, updated knowledge. We refer to this syncreticity, co-existence of different views without hi- erarchy and without precedence, as “digital anachronism”. Subsequently, public information and public interven- tions in regard to health should consider this variety of ap- proaches online and thus themselves be explicit and also argue for why and how a particular approach to health is chosen. The definitions of health presented here are also understood as navigation-tools to be applied within online environment. Being aware of them can help the naviga- tor to understand and interpret the information, texts, or documents that occur in online encounters of the health related issues. 70 435 Svalastog et al: Concepts and definitions of health and health-related values in the knowledge landscapes of the digital society www.cmj.hr References 1 Svalastog AL, Allgaier J, Martinelli L, Gajović S. Distortion, confusion, and impasses: could a public dialogue within Knowledge Landscapes contribute to better communication and understanding of innovative knowledge? Croat Med J. 2014;55:54- 60. Medline:24577828 doi:10.3325/cmj.2014.55.54 2 Gajović S, Svalastog AL. When communicating health-related knowledge, beware of the black holes of the knowledge landscapes geography. Croat Med J. 2016;57:504-9. Medline:27815941 doi:10.3325/cmj.2016.57.504 3 Kujundžić Tiljak M. The 90th anniversary of Andrija Štampar School of Public Health. Croat Med J. 2017;58:330-1. Medline:29094810 doi:10.3325/cmj.2017.58.330 4 Donev D. Human health – definition, concept and content. How the disease occurs and the natural course of disease. Modern concept and definition of healthcare [In Macedonian]. In: Nikodijevic B, editor. Contemporary diagnostics and therapy in medicine. Skopje: Faculty of Medicine; 2000. p. 5-19. 5 Grmek MD, Budak A. Introduction to medicine [In Croatian]. Zagreb: Nakladni zavod “Globus”; 1996. p. 247. 6 Media F. Saint Hildegard of Bingen. Available at: https://www. franciscanmedia.org/saint-hildegard-of-bingen/. Accessed: December 27, 2017. 7 Rutter M. Psychological resilience and protective mechanisms. Am J Orthopsychiatry. 1987;57:316-31. Medline:3303954 doi:10.1111/ j.1939-0025.1987.tb03541.x 8 The Free Dictionary - Medical dictionary. Holistic health. Available at: http://medical-dictionary.thefreedictionary.com/ holistic+health. Accessed: December 27, 2017. 9 Antonovsky A. The salutogenic model as a theory to guide health promotion. Health Promot Int. 1996;11:11-8. doi:10.1093/ heapro/11.1.11 10 Lindström B, Eriksson M. Salutogenesis. J Epidemiol Community Health. 2005;59:440-2. Medline:15911636 doi:10.1136/ jech.2005.034777 11 World Health Organization. About World Health Organization. Constitution. Available at: http://www.who.int/governance/eb/ constitution/en/. Accessed: December 27, 2017. 12 World Health Organization. World Health Report Executive Summary - achieving health for all. Available at: http://www.who. int/whr/1998/media_centre/executive_summary6/en/. Accessed: December 27, 2017. 13 World Health Organization. Global conferences on health promotion – charters, declarations and other documents: Ottawa 1986, Adelaide 1988, Sundsvall 1991, Jakarta 1997, Mexico 2000 and Bangkok 2005. Available at: http://www.who.int/ healthpromotion/conferences/en. Accessed: December 27, 2017. 14 Tulchinski T, Varavikova EA. The new public health. 3rd ed. San Diego: Elsevier Academic Press; 2014. p. 884. 15 Noack H. Concepts of health and health promotion. Copenhagen: WHO Regional Office for Europe. 1994. 16 Pavleković G, Donev D, Zaletel Kragelj L. Concept and principles in health promotion. In: Donev D, Pavleković G, Zaletel Kragelj L, editors. Health promotion and disease prevention. Stability Pact Forum for Public Health Cooperation in SEE. Lage: Hans Jacobs Publishing Co; 2007. p. 3-14. 17 Donev D. Toward the fourth dimension of health – the spiritual health. [in Macedonian]. Vox Medici. 2014;23:318-21. 18 Pariser E. The filter bubble: what the Internet is hiding from you. London: Penguin UK; 2011. 19 Svalastog AL, Allgaier J, Gajović S. Navigating knowledge landscapes: on health, science, communication, media, and society. Croat Med J. 2015;56:321-3. Medline:26321023 doi:10.3325/cmj.2015.56.321 20 Allgaier J, Svalastog AL. The communication aspects of the Ebola virus disease outbreak in western Africa–do we need to counter one, two, or many epidemics? Croat Med J. 2015;56:496. Medline:26526888 doi:10.3325/cmj.2015.56.496 21 Downey CA, Chang EC. Assessment of everyday beliefs about health: the lay concepts of health inventory, college student version. Psychol Health. 2013;28:818-32. Medline:23346999 doi:10. 1080/08870446.2012.762099 22 Millstein SG, Irwin CE Jr. Concepts of health and illness: different constructs of variations on a theme? Health Psychol. 1987;6:515- 24. Medline:3691452 doi:10.1037/0278-6133.6.6.515 23 Lawton J. Lay experiences of health and illness: past research and future agendas. Sociol Health Illn. 2003;25:23-40. Medline:14498928 doi:10.1111/1467-9566.00338 24 Zahra A, Lee EW, Sun LY, Park JH. Perception of lay people regarding determinants of health and factors affecting it: an aggregated analysis from 29 countries. Iran J Public Health. 2015;44:1620-31. Medline:26811813 25 Fugelli P, Ingstad B. Helse på norsk. God helse slik folk ser det. [In Norwegian]. Oslo: Gyldendal Akademisk; 2009. 26 Fugelli P, Ingstad B. Helse – slik folk ser det. [in Norwegian]. The Journal of the Norwegian Medical Association. 2001;121:3600-4. Medline:11808025 71 Chapter 3 of James Barlow (2017) Managing Innovation in HealthCare The Promise of Digital Health: Then, Now, and the Future Amy Abernethy, MD, PhD, Verily; Laura Adams, MS, National Academy of Medicine; Meredith Barrett, PhD, ResMed; Christine Bechtel, MA, X4 Health; Patricia Brennan, RN, PhD, FAAN, National Library of Medicine; Atul Butte, MD, PhD, University of California, San Francisco; Judith Faulkner, MS, Epic Systems; Elaine Fontaine, BS, National Academy of Medicine; Stephen Friedhoff, MD, Anthem, Inc.; John Halamka, MD, Mayo Clinic; Michael Howell, MD, MPH, Google Health; Kevin Johnson, MD, University of Pennsylvania; Peter Long, PhD, Blue Shield of California; Deven McGraw, JD, MPH, Ciitizen Corporation; Redonda Miller, MD, MBA, Johns Hopkins Hospital; Peter Lee, PhD, Microsoft Corporation; Jonathan Perlin, MD, PhD, MSHA, The Joint Commission; Donald Rucker, MD, 1upHealth; Lew Sandy, MD, MBA, UnitedHealth Group; Lucia Savage, JD, Omada Health, Inc.; Lisa Stump, MS, Yale New Haven Health System and Yale School of Medicine; Paul Tang, MD, MS, Stanford University; Eric Topol, MD, The Scripps Research Institute; Reed Tuckson, MD, FACP, Tuckson Health Connections, LLC; and Kristen Valdes, b.well Connected Health June 27, 2022 Perspectives | Expert Voices in Health & Health Care DISCUSSION PAPER Digital Health in the 21st Century Over the past several decades, the development and ac- celerated advancement of digital technology has prompted change across virtually all aspects of human endeavor. The positive and negative effects of these changes have been and will remain the focus of active speculation, including the implications for human health. Application of mechanical and digital recording and capture of physical status, experi- ences, and narratives have set the stage for revolutionary progress in individual health and medical management, population-wide health strategies, and integrated real-time generation of new knowledge and insights. Together, these developing digitally mediated capacities are termed digital health. Digital health has evolved as a broad term encompass- ing electronically captured data, along with technical and communications infrastructure and applications in the health care ecosystem. Revolutionary advances in digital health are transforming health, medicine, and biomedical sci- ence, and redefining and re-engineering the tools needed to create a healthier future. Developments such as cloud computing, artificial intelligence, machine learning, block- chain, digitally mediated diagnostics and treatment, tele- health, and consumer-facing mobile health applications are now routinely used in self-management, health care, and biomedical science. These developments promise to drive earlier diagnoses and interventions, improve outcomes, and support more engaged patients (McGinnis et al., 2021). In the mid-20th century, the newly established World Health Organization (WHO) defined the concept of health as “a state of complete physical, mental and social well- being and not merely the absence of disease or infirmity” (WHO, 2006). As an integrative concept, this definition is a vision for the planet that is at once bold and elusive, even for the United States as the world’s wealthiest nation. The WHO definition is clear that health derives from much more than medical care. Since WHO’s founding, much has been learned about how different factors, including but extending far beyond medical care, interact to shape health prospects. Indeed, research indicates that social and behavioral fac- tors both outweigh medical care in determining health sta- tus and modulate the contributions of genetics and physical environments (Kottke et al., 2016; McGovern et al., 2014; Schroeder, 2007; McGinnis et al., 2002). Unfortunately, U.S. health policies and health system in- vestments remain misaligned with these insights. In the U.S., approximately 90% of all health expenses go to disease and injury treatment rather than to addressing the predis- posing factors of these illnesses and injuries. By 2020, U.S. health expenditures had grown to $4.1 trillion. Spending in the health sector is projected to increase to over $6 trillion 72 DISCUSSION PAPER Page 2Published June 27, 2022 annually and encompass 20% of the nation’s gross domes- tic product by 2028 (Keehan et al., 2020; CMS, 2019). The U.S. is falling far short of the WHO vision, despite spend- ing nearly twice as much as other high-income countries. The U.S. currently has a lower life expectancy, higher rate of death by suicide, higher chronic disease burden, higher rates of preventable hospitalizations, higher use of unneces- sary expensive testing and procedures, and lower use of primary care than its peer countries (Tikkanen and Abrams, 2020). Despite important gains in the last two decades, made possible by significant investment by payers, providers, and the federal government in electronic health records (EHRs), progress toward interoperable systems, and advanced tech- nology to coordinate care and manage disease, the prom- ise of digital health remains illusory. The ability to use in- teroperable digital technology to improve the effectiveness, efficiency, equity, and continuity of care remains substan- tially conceptual. For example, digital interfaces in inpatient care systems are often clumsy; volumes of health data are mostly sequestered, inaccessible, and difficult to aggregate in a meaningful and actionable way, in part due to the on- going need for evolving data standards. In addition, digital tools and data are relatively ineffective in assisting clinicians in better understanding patient and family preferences and circumstances that facilitate health progress outside of the clinic. The notion of digital tools that can be applied in wide- spread fashion to coordinate health care organizations and public health efforts to identify and engage those at particu- lar risk from behavioral, social, and environmental public health risks remains rudimentary at best. The expansive vi- sion of real-time generation of evidence in a learning health system that links datasets and analyzes them using artificial intelligence and machine learning is nascent and limited to a few pilots. Ongoing and accelerated progress must be made to fully realize the vision of a learning health system. In the digital age, regardless of the specific barrier to the creation and support of individual and population health (e.g., COV- ID-19, staff burnout, challenging financial outlook, equity, etc.), digital health can and should act as a “force multi- plier” of the interventions to combat these challenges. As active participants in advancing prospects and practices in digital health, the authors of this paper hope to: • highlight the compelling possibilities and unresolved challenges for advancing trustworthy digital technol- ogy for the benefit of all people at every stage of their lives; • underscore the importance of ensuring that the ben- efits are equally shared across society; • identify the structural, technical, and policy precon- ditions for long-term progress; and • identify critical priorities for cooperation and col- laboration between policy makers, practitioners, and industry leaders to propel the development and application of best-in-class digital health tools. This paper aims to provide a comprehensive review of digital health tools and their promise and to identify critical priorities for cooperation and collaboration among policy makers and industry leaders. The challenge is addressing both the breadth and depth of the issues, which are multi- factorial and overlapping. It is important to note that the narrative and suggestions here represent the views of the individual authors, not nec- essarily those of the National Academy of Medicine or the organizations with which the authors are affiliated. In de- veloping the text, the authors have been informed by their respective roles and responsibilities in those organizations. These include various efforts in contending with the digital health challenges and opportunities of the COVID-19 pan- demic. The discussion paper Digital Health COVID-19 Im- pact Assessment: Lessons Learned and Compelling Needs was produced in parallel to and in coordination with this work and serves as a use case of the key concepts present- ed here (Lee et al., 2022). In addition, the development of this paper was informed by the National Academy of Medi- cine Leadership Consortium’s Digital Health Action Collab- orative (DHAC) and DHAC’s prior work stewarding devel- opment of the international statement on Digital Health and the Learning Health System, issued collectively in 2020 by national academies of science and medicine of 14 countries (NASEM, 2020). Digital Innovation and Medical Care Digital technology has now been developed and applied to every aspect of health and health care. Figure 1 groups the various digital health tools into a dozen application arenas, but the individual applications number in the thousands. The authors see the potential in digital innovation in health care delivery in the following areas: advancing diagnosis and treatment, ensuring care continuity, facilitating off-site patient management through telemedicine, partnering with individuals to support self-management, and reducing error and waste in the delivery system. Advancing Diagnosis and Treatment Research shows that a significant proportion of health spending is attributed to chronic diseases, with individuals experiencing multiple comorbidities accounting for a dis- proportionate share of expenditures (Buttorff et al., 2017). Although additional research is necessary, a recent review 73 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 3 FIGURE 1 | Evolving Applications of Digital Technology in Health and Health Care SOURCE: National Academy of Medicine. 2019. Digital Health Action Collaborative, NAM Leadership Consortium: Collaboration for a Value & Science-Driven Health System. concluded that self-management as part of a treatment program for patients with chronic conditions has small-to- moderate impacts on health behaviors, health outcomes, and service utilization and should be an ongoing priority in promoting population health (Allegrante et al., 2019). Thus, the market appetite and the necessity exist to facili- tate diagnosis, reduce disease burden, and improve care for those who experience chronic disease. To address these problems, innovators, software vendors, payers, and gov- ernment regulators are investing heavily in digital health so- lutions for diagnosis and treatment, with particular attention to high-need, high-cost populations (The Commonwealth Fund, 2016). An example of a diagnostic tool enhanced by digital health includes smartphone-based photoplethysmography (using a smartphone camera to capture video from the sub- ject’s index fingertip), combined with a deep neural net- work, a form of artificial intelligence (AI), to detect diabetes (Avram et al., 2020). While not widely adopted, such tools could be used for self-administered, low-cost, widespread screening. AI is also used in radiology and pathology to augment human interpretation of diagnostic (e.g., ocular, x-ray, or magnetic resonance imaging) and pathology slide images, supporting potentially more accurate and timely diagnosis and individualized treatment plans for various cancers and renal disease (Barisoni et al., 2020). Drug re- searchers and manufacturers are also leveraging various forms of AI for patient recruitment, virtual engagement, and literature review, and using the technologies to assist in de- tecting and refining pharmaceutical targets (Lamberti et al., 2019). Treatment decisions can be augmented by clinical deci- sion support (CDS) systems and enriched with advanced analytics. An editorial in the New England Journal of Medi- cine succinctly summarized the challenge: “The complexity of medicine now exceeds the capacity of the human mind” (Eddy, 1982). While AI-based systems are currently unable to discern a grimace, notice sweating, or hear a tremor in a patient’s voice—skills at which humans excel—these sys- tems offer the unique opportunity to augment clinician per- formance by creating order and transforming vast amounts of mostly unstructured data into clinically actionable infor- mation to support optimal care. This field, although nascent, is rapidly advancing. For example, AI has been used to im- prove the speed of prediction and diagnosis of sepsis (Goh et al., 2021). Integrated with the care delivery workflow, 74 DISCUSSION PAPER Page 4Published June 27, 2022 these technologies could identify patterns, form linkages between disparate data sources, and suggest treatment op- tions for clinicians to review. In addition, AI-powered CDS systems might offer opportunities for improving efficiency and mitigating clinician burnout, another potential down- stream benefit. Ensuring Care Continuity Even the most sophisticated digital diagnostics will have little impact on clinical outcomes if they are implemented in a fragmented health care ecosystem. Regulations promul- gated by the 21st Century Cures Act Final Rule (Cures Act) have the potential to address this shortcoming by promoting seamless interoperability and supporting increased control for the individual regarding their health data (HealthIT.gov, 2020). The Cures Act addresses foundational standards, in- cluding technical, syntactic, and semantic issues surrounding health data interoperability and prioritizes ensuring patients have choices when managing their own health data. Further complexities associated with a robust trust framework, data accuracy, identity matching, and privacy protections of in- dividual data managed by noncovered entities will likewise be critical to confront. Significant progress on interoperability has occurred over the past decade with the implementation of foundational data standards such as Health Level 7 Fast Healthcare In- teroperability Resources (FHIR) (HL7 International, n.d.), SNOMED (SNOMED International, n.d.), RxNorm (NLM, 2022), and the United States Core Data for Interoperability (USCDI) (HealthIT.gov, n.d.). Still, the broad interoperability of health care data platforms is incomplete in many settings due to incomplete record availability, lack of terminology standards, and concern about bidirectional incorporation of data between health systems using different EHRs. In a 2019 study of primary care physicians in high-income countries, the Commonwealth Fund (2019) found that just over 50% of American primary care physicians surveyed were able to electronically exchange data with physicians outside of their practice. In addition, since health is not primarily produced by health care, interoperability with data outside of EHRs may add to a holistic picture of an individual and support continuity of care. However, this level of interoperability is nascent, as demonstrated by a recent review of data ex- change capacity of wearables, which found limited ability to transfer data from mobile monitoring systems into medi- cal records (Muzney et al., 2019). The power of EHR sys- tems to capture and organize clinical data allows for rapid cycle learning and organizational agility, but barriers—both technical and economic—to transmitting non-native data into the EHR limit the comprehensive view of individuals and populations needed to transform health care delivery and the health system writ large. To facilitate data interop- erability, the U.S. health system must expand embedded, open-source interoperability beyond nationally regulated technologies like EHRs. Research has documented the potential for Health Infor- mation Exchange (HIE) and interoperability to improve care coordination and reduce costs (Walker et al., 2005), and will likely also benefit public health reporting. An example of HIE use to support care coordination is the delivery of near real-time dashboards to primary care and substance use disorder providers about inpatient and emergency de- partment admissions and discharges for their patient panels, supporting post-discharge care coordination (HealthIT.gov, 2017). Still, patients and providers will struggle to realize these benefits at scale as the existing reimbursement system continues to disincentivize care coordination, which results in duplicative service utilization. The ongoing transition to value-based payment can support the realignment of finan- cial incentives and serve as a significant driver for expand- ing interoperability (Biel et al., 2019). In this regard, banking, which provides ubiquitous, near real-time, standardized access to account information glob- ally, provides lessons about industry-wide information ex- change that might be adopted in health care. The Society for Worldwide Interbank Financial Communications (SWIFT) established a financial transaction messaging system in the 1970s with a focus on essential transactions, a strong busi- ness case for participation, and an industry-supported over- sight organization (Glaser, 2019). The Office of the National Coordinator for Health IT (ONC), through the Trusted Ex- change Framework and Common Agreement (TEFCA), has made inroads toward this vision with the formal recognition of an industry-supported oversight organization through the Recognized Coordinating Entity (RCE), which was awarded to the Sequoia Project in 2019 (HealthIT.gov, 2022). Facilitating Off-Site Patient Management through Telemedicine Digital tools that collect data and support interventions out- side the clinical setting offer meaningful opportunities to identify risks and engage patients. Consumer-facing apps and clinical monitors that actively or passively collect data can also serve as an early warning system for prevention and disease management. During the COVID-19 pandem- ic, digital contact tracing apps provided patients with no- tifications about potential exposure to COVID-19. Beyond COVID-19, some tools generate warnings to individuals or caregivers regarding changes in environmental risks, such as pollen or air pollution alerts, while other platforms gen- erate alerts to patients, families, and providers in the event of disease exacerbation. Additionally, while not widely ac- 75 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 5 ceptable or accessible by all populations, use of remote pa- tient monitoring (RPM) tools increased during the COVID-19 pandemic. RPM enables clinicians to assess symptoms for patients at home with mild cases of COVID-19 and observe non-COVID-19-related health outcomes in the context of daily living for patients with chronic conditions (e.g., Blue- tooth scales for patients with congestive heart failure, con- nected blood pressure cuffs for patients with hypertension). Digital tools have also expanded care delivery for pro- viders beyond the hospital or exam room. A 2020 analysis found that virtual urgent care visits could reduce the need for emergency room care by approximately 20%, and 20% of all office care, outpatient, and home health services could be delivered virtually or near-virtually (Bestsennyy, et al., 2020; Cigna Newsroom, n.d.). Non-acute care visits for many conditions were implemented virtually during the COVID-19 pandemic to reduce risk of exposure for patients and providers. Even with the sharp decline in telehealth in 2021—after the steep rise associated with COVID-19 in 2020—a review by a large payer in 2022 supported the value of virtual care (Cigna, 2022). Even acute care can be delivered outside the health care delivery setting, as witnessed during the COVID-19 pan- demic when severely ill patients occupied many hospital beds (Heller et al., 2020). Virtual intensive care units can deliver remote 24/7 monitoring of patients by intensivists who can manage patients in multiple locations, allowing patients to get intensive care unit-level care in community hospitals. Partnering with Individuals to Support Self-Man- agement Given that most chronic disease management occurs out- side of the traditional health care setting, partnering with individuals so that they can fully engage in their own care and meeting people where they are physically and mentally is essential to achieving better health outcomes, improving quality of life, and reducing health care spending (Allegran- te et al., 2019). However, meeting individuals on their own terms may present multiple challenges to both individuals and the delivery system. Basic knowledge gaps about anat- omy and physiology are worsened by issues of language fluency, health and reading literacy, numeracy, conflicting cultural beliefs, and limitations in cognitive capacity. These same challenges may be further exacerbated by poor medi- cation tolerance and complex clinical care plans, including polytherapy and polypharmacy (Settineri et al., 2019). Ac- cess issues, including distance from the delivery system for rural residents, lack of transportation, and difficulty taking time away from work, all affect attendance at provider visits and can result in delays in seeking care. Financial barriers force individuals to choose between needed health care and medication and other household expenses, can result in not taking medicines as prescribed, including pill splitting and dose skipping (Kearny et al., 2021). These barriers of- ten lead to clinical inertia and are amplified by structural racism, furthering health disparities among underresourced communities. By applying digital tools successfully used in other indus- tries, such as consumer-directed, preference-based sched- uling; personalized recommendations; and regular text communications, the health care system may be positioned to develop a more robust partnership between individuals, families, and providers. Data and digital health tools serve as a bonding agent in their shared understanding of the in- dividual’s state of health and a shared health management plan. Individuals and families have grown accustomed to mobile and online tools in other aspects of their lives, such as airline booking, car services, and banking. Developing a robust partnership between individuals, families, and pro- viders requires further adoption of systems that function the same way that these other tools do, offering patient-centric, easy, and secure two-way communication for appointment booking, self-check-in, and feedback surveys. Such tools can and should be seamlessly interoperable within health systems workflows. While patient portals support many of these functions, adoption among adults in the U.S. is below 50% (HINTS, 2018). Strategies should acknowledge user comfort with technology and offer multiple communication modes, including text messaging, audio, and video, de- pending on the user preference (Zachrison et al., 2021). These approaches also need to consider form and frequen- cy of communication to ensure maximum engagement and understanding. Reducing Error and Waste in the Delivery System Extensive research indicates that health care resources are inappropriately allocated within the current system. Waste has been shown to carry consequences for quality outcomes and patient safety (e.g., medical errors and delays) and economic efficiency (e.g., unnecessary spending) (Shrank et al., 2019). In the context of safety, since the Institute of Medicine’s (IOM) report titled To Err Is Human: Building a Safer Health System was published in 2000, health care providers have made progress in reducing harm in hospi- tal settings, but that progress varies widely (IOM, 2000). Equally troubling is the inability to accurately measure the harm associated with the lack of timely, standardized, and accurate information movement across systems (Bates and Singh, 2018). As identified in a 2010 report from the IOM ti- tled The Healthcare Imperative: Lowering Costs and Improv- ing Outcomes, disruptive innovation has been foundational 76 DISCUSSION PAPER Page 6Published June 27, 2022 across sectors to reduce waste and increase efficiency, and its use as a strategy to address these issues in health care is essential (IOM, 2010). The digitization of health data has long been considered the foundation for patient safety, operational efficiency, and quality of care. It was also a driving force behind the Health Information Technology for Economic and Clinical Health (HITECH) Act, which incentivized the adoption of EHRs (IOM, 2004; HealthIT.gov, 2009). By 2017, 80% of office-based physicians and 96% of non-federal acute care hospitals had adopted certified EHRs (Health IT Dash- board, 2016). Multiple studies have documented improve- ments in care quality (Atasoy et al., 2019; Buntin et al., 2011). However, in a recent survey of over 5,000 physi- cians across specialties, perceived EHR usability was poor. Results showed a “dose-response relationship between EHR usability and physician burnout”, which is negatively asso- ciated with patient safety (Melnick et al., 2020; Panagioti et al., 2018). However, patient safety is improved regardless of physician experience (Tanner et al., 2015). In addition, ongoing opportunities to better integrate clinical and ad- ministrative functions, streamline documentation (e.g., via voice technologies), automate quality metrics reporting, and embed AI and advanced CDS systems represent mean- ingful advancements that EHR vendors are pursuing as these platforms mature—either as new functionality within their platforms or by connecting to external third-party vendors, creating a “both/and” approach to maximizing efficiency. When it is clinically appropriate to address health con- cerns without an exam or with good quality video or still images, telehealth can reduce delays for specialty consulta- tions and primary care, as the constraints of a shared physi- cal space for an exam are eliminated. Advanced analytics can also reduce waste by helping health care professionals work at the top of their licenses. Advanced analytics can improve clinical risk stratification, allowing less skilled care team members to address the needs of patients who require minimal care. Higher skilled care team members are freed up to spend additional time with patients with complex med- ical needs, resulting in the delivery of the right care, to the right patients, at the right time, in the right place, by the right clinical team members. Machine learning (ML) and natural language processing (NLP) algorithms have outperformed nursing staff and provided comparable levels of accuracy to skilled physicians in assessing acuity risk in emergency departments (Ivanov et al., 2021). However, caution must be used because algorithms can inadvertently perpetuate significant bias (Tanner et al., 2015). Process automation is another area of opportunity to use digital health technology to improve efficiency in both am- bulatory care and inpatient settings. Barcoding has been widely used in hospital pharmacies for over a decade, re- sulting in a reduction in adverse drug events (Boyde and Chaffee, 2019). Repetitive tasks such as scheduling, billing, capacity coordination, and asset management are amena- ble to automation, optimizing use of system resources and creating a frictionless experience for patients. For example, health care organizations can emulate the airline industry in maximizing automation and self-service functionality in scheduling while addressing customer demand, service supply, and equipment needs (ONC, 2020). Digital Innovation and Population Health Figure 1 also identifies various tools applicable to improving population health and drivers of health that are upstream from medical care—e.g., geospatial and environmental sensors, personal health devices, and knowledge genera- tors and integrators. The importance of using digital tools in helping to integrate critical social services into care delivery has been clearly demonstrated by the nation’s experience with COVID-19 and the disproportionate impacts on com- munities of color and other economically disadvantaged and underresourced populations (Isasi et al., 2021; Health IT Dashboard, 2016). Innovations in digital health hold the potential to help identify and address many of the barriers to achieving the vision of a healthy society. When thoughtfully designed, equitably deployed, and effectively used, digital health tools have the potential to improve the identification, measurement, and modification of the root sources of illness, health, and well-being. Without the precise analytic infor- mation possible through a robust digital infrastructure, the nation will not be able to accelerate the identification and engagement of the causes and consequences of structural racism, which plays such a perverse and pervasive role in the health disparities of far too many Americans. As digital health tools become increasingly sophisti- cated and capable of capturing social, behavioral, and environmental determinants of health, clinicians and care- givers can learn more about the individual in the context of their daily lives, including individual preferences, values, interactions, and exposures, to deliver targeted preventive and acute care and to restore health after illness. This digi- tally enabled health ecosystem has the potential to create long-term partnerships between individuals and their care teams that support healthy behaviors. Similarly, if thought- fully designed, equitably deployed, and effectively used, such digital health applications have the potential to help prevent, mitigate, and reduce disparities in access and care (Craig et al., 2020). In such a system, health information flows freely within a trust-enabled and robust security and 77 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 7 privacy framework across both the health care industry and nontraditional commercial entrants into the market. Digital Innovation and the Social Determinants of Health Kaiser Family Foundation defines the social determinants of health (SDoH) as “the conditions in which people are born, grow, live, work and age that shape health,” with these conditions including “socioeconomic status, education, neighborhood and physical environment, employment, and social support networks, as well as access to health care” (Artiga and Hinton, 2018). Although approximately 15% of premature deaths are attributed to SDoH, these upstream drivers of health have largely been considered out of scope and not yet routinely addressed by providers or health care systems (McGinnis et al., 2002). For digital technology to have a meaningful effect on SDoH, information about nonmedical factors and services must be better collected and integrated into mobile apps and standardized, aggregated, and integrated into EHRs to promote trust and ensure secure and private management. Digital tools could play a role in screening and identifying SDoH factors that impact a patient, alerting the provider to discuss them with the patient at the next visit, and connecting the patient with relevant community services. While existing digital health tools are already capable of supporting the collection, exchange, and integration of SDoH to support risk stratification and shared care planning, the benefits of these tools have been limited by inconsistent use across care delivery settings and the significant risk of algorithmic bias (Meyer et al., 2020; Lindau, 2019). For example, schedul- ing algorithms designed to identify patients who frequently miss appointments may both stigmatize people of lower so- cioeconomic status and distort the real issues. Many of these “no shows” cannot afford childcare or to leave work for a medical appointment, or they may have health problems that cause disability or reduced cognitive function, caus- ing them to miss appointments (Murray et al., 2020). Un- derstanding and intervening on SDoH and systems factors could reduce missed appointments, helping patients to get needed care and reducing lost care capacity for the system. These issues highlight the need for transparency in data col- lection and encoding and the criticality of proactive action to mitigate unintended consequences and biases when de- veloping algorithms. Digital health technologies are also developing new use cases to address various environmental factors, including air pollution and climate change. Digital inhaler sensors have been used to monitor when and where patients with asthma used medications and needed adjustments to treatment plans and are associated with a reduction in rescue inhaler use, an improvement in symptom-free days for individuals, and a reduction in health care resource utilization (Mer- chant et al., 2018; Barrett et al., 2013). Furthermore, “ag- gregated data on inhaler use, combined with environmental data, led to policy recommendations”, a community asthma notification system, community-wide improvements in asth- ma symptoms, and reductions in asthma-related emergency department use (Barrett et al., 2018; Barrett et al., 2013). Consumer-facing tools also can provide smartphone alerts for heat or air pollution data at the neighborhood level, making public health efforts more efficient. The use of tele- health and HIE can also support coordinated patient care during natural disasters. Of course, none of these tools ad- dress the root causes of these environmental problems—for example, a person might be able to know that their drinking water contains lead, but the tool cannot assist in solving the underlying drinking water problem. These SDoH must be addressed at the root level to realize improved health and well-being for all. Digital Innovation and Health Behavior Digital health technologies are also developing new use cases to address various environmental factors, including air pollution and climate change. Digital inhaler sensors have been used to monitor when and where patients with asthma used medications and needed adjustments to treatment plans and are associated with a reduction in rescue inhaler use, an improvement in symptom-free days for individuals, and a reduction in health care resource utilization (Mer- chant et al., 2018; Barrett et al., 2013). Furthermore, “ag- gregated data on inhaler use, combined with environmental data, led to policy recommendations”, a community asthma notification system, community-wide improvements in asth- ma symptoms, and reductions in asthma-related emergency department use (Barrett et al., 2018; Barrett et al., 2013). Consumer-facing tools also can provide smartphone alerts for heat or air pollution data at the neighborhood level, making public health efforts more efficient. The use of tele- health and HIE can also support coordinated patient care during natural disasters. Of course, none of these tools ad- dress the root causes of these environmental problems—for example, a person might be able to know that their drinking water contains lead, but the tool cannot assist in solving the underlying drinking water problem. These SDoH must be addressed at the root level to realize improved health and well-being for all. Although consumer demand for interventions that support behavior change is high, and successes have been evident in areas such as tobacco use and the consumption of foods high in saturated fat, the complexity of behavioral interven- tions can be vexing. Consider the case of weight manage- 78 DISCUSSION PAPER Page 8Published June 27, 2022 ment programs. The overall weight loss market in the U.S. in 2020 was estimated at $71 billion, yet many programs elicit only marginal and temporary changes in weight, with par- ticipants often experiencing weight regain (LaRosa, 2020; Hall and Kahan, 2018). As such, interest in digital and virtual weight loss programs is mounting as an alternative (LaRosa, 2020). However, while several well-controlled studies have demonstrated improved clinical outcomes when incorporat- ing digital tools relative to usual care, most applications in the consumer marketplace are not supported by evidence, nor are they produced by subject matter experts in health behavior change (Gordon et al., 2020; Pagoto and Ben- nett, 2020; Steinmetz et al., 2020). This example illustrates some of the broader challenges and opportunities for digital tools to support self-manage- ment of individual health behaviors. In their ideal form, evidence-based digital health tools that focus on health behavior can improve self-awareness, provide on-demand health information and education, support improved self- efficacy, and promote accountability with social support networks, health coaches, and providers. The resulting data can also be analyzed to identify behavioral risk factors that contribute to chronic disease, resulting in real-time, person- alized feedback and messaging to support health behavior change in a way that is more compelling than traditional patient education (Shegog et al., 2020; Barrett et al., 2013). Similarly, these data can be aggregated at the community level to more accurately measure the health behaviors and activities of populations, supporting resource allocation and data-driven public health decision making at the local level (Barrett et al., 2013). Digital health tools designed to support adherence to treatment plans also present an important opportunity. Con- nected self-monitoring tools (e.g., glucometers), wearables, digital inhaler sensors, and SMS messages and reminder systems have shown promise in patients with a variety of conditions, including epilepsy, asthma, chronic obstructive pulmonary disease (COPD), diabetes, depression, and hy- pertension (De Keyser et al., 2020; Kaye et al., 2020; An- derson et al., 2019; Shan et al., 2019; Patel et al., 2013). For example, objective, passive data about adherence to asth- ma medication treatment plans identified issues with medi- cation-taking technique errors and presented an opportu- nity for intervention and education (Anderson et al., 2019). Interestingly, patients with asthma and COPD who received digital support (reminders for missed medication doses and education) increased their medication adherence during the early months of COVID-19 (Kaye et al., 2020). Digital Innovation, Genomics, and Precision Health Digital technologies are accelerating the “genomics revolu- tion”—advances in understanding the health implications of structural and functional variations in the human genome. These are often discussed in terms of augmented abilities to target individual medical interventions more precisely. While this is certainly an important likelihood, broader scale ben- efits in terms of reduced mortality and morbidity are likely to result from “precision public health”—the ability to better identify populations at greater risk from certain character- istics or exposures and implement protective interventions. Whole genome sequencing and digitally enabled risk scores generated by such sequencing will help identify in- dividuals and groups at risk for common health conditions in their earliest stages. These data can be used to support mitigation strategies such as behavior change, medication use, or early screening to decrease the risk of sequelae from a genetic disease or gene variants. Examples of existing consumer-facing mobile health apps today draw from sev- eral data sources and partnerships, including self-reported family history data, laboratory results from personal genet- ics companies, and collaboration with providers, payers, or employers (Tung et al., 2018). The ongoing integration of genetic or genomic data and clinical histories, accelerated by emerging AI and ML technologies, increases the feasi- bility of leveraging precision medicine into clinical practice (Luchini et al., 2022). For example, AI is currently used in oncology, including FDA-approved AI used in support of care for breast, lung, and prostate cancers (Luchini et al., 2022). Advanced computational analytics used on such datasets could ultimately be employed to deliver near real- time feedback to individuals to promote health using a voice assistant, much like a digital health coach (Topol, 2019). Digital Innovation and the Learning Health System The application of digital technologies at scale serves as the nervous system for the continuously learning health care system: “one in which science, informatics, incentives, and culture are aligned for continuous improvement, innovation, and equity—with best practices and discovery seamlessly embedded in the delivery process, individuals and fami- lies active participants in all elements, and new knowledge generated as an integral by-product of the delivery experi- ence” (NAM, 2020). Digital health will serve a critical role, and its promise must be fully leveraged. Effectively applied, digital health tools have the potential to catalyze progress on each of the key principles for a digitally facilitated learn- ing health system, presented below in Box 1. 79 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 9 Leveraging Big Data for Knowledge Generation Much of the data collected in clinical care or recorded in consumer apps are available for further research and learn- ing. Currently, the broader application of available health data is more likely to be used in service of product devel- opment rather than for learning, discovery, or continuous improvement of the health of individuals, families, or popu- lations. There is an unrealized opportunity to share, aggre- gate, and analyze that data in alignment with the goals of a learning health system while also protecting and tightening the processes and procedures for unwarranted access to and use of personal data and inadvertent sharing of sen- sitive data, including medical records, via third-party con- sumer apps. The investment, innovation, and amassing of data pres- ent important opportunities to affect not just health and the health care delivery system but also knowledge develop- ment in a learning health system. If appropriately managed and analyzed, datasets that incorporate structured and unstructured clinical data, SDoH information, genomics, digital phenotype data collected from wearables, and other data can make it possible to change baseline understand- ings of health and disease (Engelhard et al., 2020; Jain et al., 2015). Statistical tools and techniques, including AI and ML, can be used to develop dataset assessment tools and to support evolving research designs that meld traditional randomized controlled trials (RCTs) with observational stud- ies. Similarly, analytical models can be applied across at- risk populations to ensure equity in opportunities to create health and treat disease. Development of virtual health data trusts, with shared governance and individuals controlling and contributing their data to support scientific discovery, present an important opportunity to distribute the costs and maximize research output while protecting individual agency and privacy (Baker et al., 2016; Ideas for Change, 2016; MiDATA, n.d.). If successful, this digitally enhanced approach to research could allow multiple stakeholders, in- cluding professional societies, health care providers, patient advocacy groups, individuals, families, legal experts, medi- cal administrators, the private sector, and governments, to share data, experiences, and research priorities. Leveraging Big Data for Population-Level and Public Health Insights Fully realizing the benefit of vast datasets with informa- tion collected in near real time across the health continuum promises to improve population and public health. Some noteworthy examples of these public datasets include the National Patient-Centered Clinical Research Network (PCORnet) (PCORNet, n.d.), the Research Data Assistance Center (ResDAC) for CMS data (ResDAC, 2022), the Ob- servational Health Data Sciences and Informatics program (OHDSI) (OHDSI, 2022). This promise includes the active and passive collection of real-time data from patients’ daily living activities, gathered in clinical systems and payer sys- tems and the analysis of that data to make well-reasoned decisions using standard analytics and AI/ML (Singhal et al., 2020; Bughin et al., 2017). To apply analytics tools to health care will require significant investment; fortunately, the Cures Act authorized $1.5 billion over 10 years to support the NIH’s All of Us Research Program, which is designed to build and make available to researchers a se- cure and expansive database, including EHR, survey, and biometrics data of one million people to support medical discovery (NIH, 2020). While NIH did not explicitly create the All of Us program for AI/ML, as a by-product of the BOX 1 | Core Principles for Stewards of the Digital Health Infrastructure and Data Personal: Discretion on control and use of personal data resides with the individual or their designee. Safe: Data stewardship protocols safeguard against use resulting in personal harm. Effective: Data are collected and maintained according to validated stewardship protocols. Equitable: Data systems are designed to identify and counter bias or disparities. Efficient: Every digital equipment acquisition or service license enhances health system interoperability. Accessible: Data are available when and where needed for decision-making. Measurable: Digital health performance is continuously monitored for accuracy and interoperability. Transparent: Personal data sources and uses are clearly indicated, including timing and context. Adaptive: Data strategies are regularly calibrated to ensure continuity, currency, and utility. Secure: Data sharing protocols are considered secure by users. SOURCE: National Academy of Medicine Leadership Consortium: Collaboration for a Learning Health System. n.d. Digital Health Action Collaborative Strategic Framework. 80 DISCUSSION PAPER Page 10Published June 27, 2022 program, researchers will have access to new datasets and platforms upon which they can train their models. As health systems, payers, and community organizations collaborate and share data to serve specific populations, public health agencies are positioned to seamlessly collect data and apply advanced analytics for health surveillance and community intervention. Interoperability links health systems, community agencies, geographical information systems, and public health agencies to address medical, environmental, and SDoH (Buckeridge, 2020). Interoper- ability can also create opportunities, via big data and preci- sion public health, to tailor interventions to subpopulations, which will help ensure equity (Buckeridge, 2020). During COVID-19, the public health sector is experiencing an op- portunity to test a variety of new precision public health tools, including the use of cell phone location data, activ- ity trackers, and sewage data to intervene early to identify outbreaks and to limit morbidity and mortality (Rasmussen et al., 2020). Requirements for the Digital Health Infra- structure Digital technology serves as the nervous system for the learning health system and accelerates the identification and elimination of wide-scale disparities in individual, lo- cal, regional, and global health care. As individuals gain more access to their health data via application program- ming interfaces (APIs), and as providers use these data for critical clinical decision making using AI/ML, it is essential to consider several foundational infrastructure requirements. Figure 2 presents the essential infrastructure requirements for progress in digital health. While there has been some prog- ress, opportunities remain in each interrelated component. Each area must be carefully reviewed and addressed to fully establish the framework to allow the benefits of digital health to be fully realized. Of particular interest for priority action are individual access and engagement, equity and ethics, privacy and identifier protocols, cybersecurity, data quality and reliability, data storage, sharing, and steward- ship, interoperability, AI/ML, and workforce. Individual Access and Engagement and Equity and Ethics To ensure digitally facilitated health for all, access to digital health writ large, supported by widespread broadband in- ternet access, is essential across all economic strata and all FIGURE 2 | Infrastructure Requirements for Progress in Digital Health SOURCE: National Academy of Medicine. 2019. Digital Health Action Collaborative, NAM Leadership Consortium: Collaboration for a Value & Science-Driven Health System. 81 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 11 regions of the U.S. Unfortunately, while COVID-19 resulted in the practical and essential application of telehealth, key gaps in consumer access to such technologies—“the digital divide”—were also exposed. Equity in available broadband access will spur growing consumerism and engagement in health and health care. The public has routine exposure to digitally facilitated con- venience, agency, transparency, and privacy based on their experience with other industries and now expects the same from the health care ecosystem (Accenture, 2019). As the understanding of what creates health and well-being grows, it is imperative to engage patients, families, and communities in the design of new structures, processes, and solutions to support health and well-being. It is also essential to address systemic racism and institutional health inequities and disparities within the U.S. when designing these new structures, processes, and solutions (Feagin and Bennefield, 2014). These steps are necessary to mitigate the risk that new technologies will deepen the existing digital divide or perpetuate historical mistrust in the health system. In addition, it will be important to translate what is learned through the collection of digital health data writ large (e.g., better insight into environmental determinants of health, Bar- rett et al., 2013) into local and national policies to make these learnings applicable at the individual and population level. These improved policies should, in turn, translate into community improvements (e.g., urban planning decisions about not placing schools next to freeways, informing na- tional air quality standards with research into the associa- tion between air pollutants and respiratory symptoms) to im- prove the health of those who live in that community. Privacy and Identifier Protocols The opportunity to share, aggregate, and analyze health data to improve individual health and to advance the learn- ing health system is significant, as is the risk of loss of privacy for individuals sharing their most sensitive data via third-par- ty consumer apps. Consumers have a limited but growing understanding of the risks (including loss of privacy) and benefits of sharing their health data and express a range of views about sharing health information. For example, a 2019 focus group on consumers’ perception of interoper- ability found that “participants overwhelmingly supported greater access to data both for health care providers and for themselves” (The Pew Charitable Trusts, 2020). In the intervening decades since the enactment of the Health Insurance Portability and Accountability Act of 1996 (HIPAA), health data systems have grown exponentially. A new industry of health-related applications was launched, giving individuals the ability to readily share their most pri- vate data with a variety of health sector and commercial actors. Some apps serve as a core communication device between individuals and their physicians and sit squarely within HIPAA. In contrast, other tools and vendors are un- regulated by HIPAA, creating uneven protection and confu- sion for consumers. The expansion of HIPAA to redefine and protect health information outside of covered entities could mitigate risks to individuals. Another critical area requiring progress in support of digitally facilitated health is accurately matching individu- als across systems (The Pew Charitable Trusts, 2018). A unique national patient identifier was envisioned as a foun- dational element of HIPAA, but privacy and security con- cerns prevented the enactment of necessary regulatory ac- tion. Promulgating such regulations remains a valuable aim to support efficient, accurate matching. In 2021, the ONC advanced efforts to accurately match patient data across systems with Project US@, which was established “to de- velop a unified, cross-standards, health care industry-wide specification for representing patient addresses to improve patient matching” (HHS, 2021). Correctly matching an in- dividual’s data across organizations (with sufficient gold standard matches that allow for appropriate algorithm de- velopment) remains an essential component for the learning health system to support the right care for the right person today and to support the use of AI and research to ensure the best outcomes for tomorrow. Cybersecurity Cybersecurity and privacy concerns are major obstacles to digital health adoption, continue to erode patient trust, and reinforce health systems’ reluctance to share data. Psycho- logical resistance, the risk of ubiquity of data, consequences of a breach, and patchwork of local and national privacy protections—or lack thereof—have created barriers to the use of pioneering, forward-looking digital health tools, and as such, cybersecurity must not be an afterthought. These critical challenges require technologic, governance, and legal protocols. A public-private partnership is neces- sary to develop a superstructure framework to ensure the safety, security, and privacy of digital health architecture. As noted earlier, the cybersecurity framework produced by the National Institute of Standards and Technology (NIST) provides such guidance (NIST, 2018). Transparency and consent for consumers and patients regarding data shar- ing, agency, and privacy within and across platforms and stakeholders—including those not covered by HIPAA—must be simplified and standardized, including understandable consent forms and the extension of HIPAA protections to currently noncovered entities like third-party app vendors. In addition, privacy and security risks with big data and AI require special attention to avoid intentional corruption of 82 DISCUSSION PAPER Page 12Published June 27, 2022 AI/ML training datasets (training data poisoning), use of AI by attackers, or anti-privacy designs in digital health (Hartz- og, 2018). Data Quality and Reliability, Storage, and Stew- ardship Foundational to digital health, the standards and curation protocols for data and information (e.g., Findability, Acces- sibility, Interoperability, and Reusability [FAIR] principles), while best-practice, are not required by regulation. How- ever, such standards and protocols are required to achieve uniform value between and among stakeholders. Data stan- dards and stewardship guidelines and national cooperation are critical, while simultaneous attention must be paid to “economic, legal, philosophical, and practical issues” relat- ing to health data (NASEM, 2020). In principle, the indi- vidual, the source of health data, controls access to and use of the data derived from their health care and interaction with digital platforms. In practice, the organization collecting and managing the data has differing custody and control of the data, depending on the nature of the individual’s data and regulations to which the data’s collector and custodian is subjected. Differences among organizations concerning “data access, control, and monetization” limit the potential of digital health, and expanding structures for cooperation and exchange are essential (NASEM, 2020). The availability of patient portals in most EHR systems and consumer-facing digital health tools and the data associated with these applications represent a meaningful opportunity to improve patient care. However, significant challenges, including the digital divide, issues of systemic racism, data curation, integration into the care setting, and data sharing for research, impede progress toward realizing improved patient care. Further, the strong drive to innovate and rapidly market mHealth tools has led to product development outpacing the capacity of regulators to establish standards and com- municate clear guidance to various stakeholders, including consumers and payers. These unclear standards and lack of regulatory guidance and oversight have created a market- place where promising digital health solutions that provide superior quality, impact, and value are difficult to distinguish from poor quality innovations and work to the disadvantage of rigorously studied digital health products . For example, emerging scientific evidence indicates that some RPM de- vices can predict five-year mortality in adults between 50 and 85 years and empower patients to better manage their health and participate in health care (Halamka and Cerrato, 2020). Clear standards and widespread rigorous review of innovations, including the evaluation of technical design, clinical value, and usability, could increase confidence in and meaningful adoption of new consumer-facing digital health tools. Finally, decisions will need to be made about how data are stored in cloud-based systems to advance the com- mon good. Virtual data repositories must be structured and controlled to protect the integrity and privacy of the data through all aspects of data management - acquisition, stor- age, access, maintenance and release. (NASEM, 2020) Si- multaneously, computing power should migrate to the cloud to support this future vision, as the cloud has both sophisti- cated security and economies of scale. Cloud-based com- puting will require a paradigm shift for organizations with on-premises systems. Interoperability Through the work of ONC, data and interoperability stan- dards have grown increasingly sophisticated over the past decade. While more work is needed, early progress with HIEs, APIs, and EHR integration has yielded improvements in care coordination, and recent efforts during the COVID-19 pandemic demonstrated the capacity of HIEs to deliver value by generating public health reporting (Dixon et al., 2021). In addition, interoperability standards need to extend be- yond the current focus on EHRs. Existing interoperability of health care data systems neither adequately supports op- timal longitudinal care delivery nor advances the nation’s health needs. The COVID-19 pandemic illuminated the needs and opportunities for digital health and transforma- tive preparedness and response capacity. The rapid pace of the pandemic’s spread emphasized the need for a rapid learning system that relies on capturing, organizing, sharing, and analyzing large amounts of data digitally across public health, research, and clinical systems. An effective response to public health crises is highly dependent on interoperable data, without which there is an inability to understand what is needed in terms of resources and capacity and to under- stand the impact of interventions. While data was critical for forecasting and coordination, its collection, sharing, and ag- gregation were, at times, chaotic and burdensome for clini- cians and administrators. The post-COVID-19 era can help ensure the interoper- ability of all mediums of digital recordkeeping used to sup- port health and deliver health care services, including labs, certified EHRs, home-grown EHRs, digital devices, consumer electronics with health features, and databases to support research and public health. Before the pandemic, the Cen- ters for Disease Control and Prevention (CDC) had launched a data modernization initiative to undergird disease surveil- lance systems. The Coronavirus Aid, Relief, and Economic Security (CARES) Act allocated $500 million to the CDC 83 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 13 to implement a “modern, interoperable, and real-time pub- lic health data and surveillance systems that will protect the American public” (CDC, 2020). Artificial Intelligence and Machine Learning As the U.S. moves to value-based payment models, trans- parent and advanced analytics are needed to calculate population risk, the foundation upon which medical budgets are established in contracts between payers and providers. AI-driven predictive modeling and other sophisticated statis- tical techniques can be used to identify subpopulations for intense care management to prevent inappropriate emer- gency room use or early intervention for an acute worsen- ing event to reduce hospital admissions. For example, in the inpatient environment, AI has been used to identify patients at risk of decompensation using data collected in the back- ground during clinical care (Lin et al., 2019). A recent lit- erature review of AI algorithms for sepsis models found the models to be highly predictive but noted several issues with algorithmic standards (Deng et al., 2021). As digital health tools incorporate increasingly disparate data into predictive models using various AI techniques, standard outcome and data definitions, bias in training datasets and final models, and frequently updated algorithms must be considered. Harnessing AI will depend on coherent data architecture and diverse training datasets, which are large, sampled adequately, and represent subgroups adequately (e.g., by gender, race, age, socioeconomic status). The Food and Drug Administration (FDA) has released guiding principles for “Good Machine Learning Practice for Medical Device Development,” which are practical and should be consid- ered when embarking upon model development (FDA, n.d.). The regulatory framework for AI as a medical device is na- scent and must address certification of constantly changing algorithms and maintenance of accountability of vendors to ensure reliable and valid processes. There are alterna- tive ways to regulate AI, including principles and standards developed by multi-stakeholder collaboration that can cre- ate adaptable standards and guidelines. Components of the European Union’s proposed rules governing AI might be considered in the U.S. (EC, 2021). Additional standards to consider include the International Medical Device Regu- lators Forum “Software as a Medical Device (SaMD): Ap- plication of Quality Management System,” FDA Center for Devices and Radiological Health “Software as a Medical Device (SaMD): Clinical Evaluation Guidance for Industry,” and “Artificial Intelligence/Machine Learning (AI/ML)- Based Software as a Medical Device (SaMD) Action Plan” (IMDRF, 2015; IMDRF, 2017; FDA, 2021). These strategies could work in tandem with regulations updated for rapidly changing capacities. Workforce To support digitally enabled health in a learning health sys- tem, the workforce of the future will require a comprehen- sive set of skills that are currently rarely seen. Besides basic competency on core organizational applications (e.g., EHR functionality), clinicians, health system staff and manage- ment, and vendors/innovators will all require at least basic or conceptual knowledge of data management (collection, storing, normalizing), interoperability, basic statistics and data science, data governance and collaboration, ethics, process improvement, and implementation science. Finally, diversity training is critical to all engaged in supporting digi- tally facilitated health in the learning health system and must mitigate disparities and build awareness among all parties— especially those individuals producing AI algorithms—to the consequences of bias for vulnerable populations. The technical workforce of the future will also need exper- tise in user-centered design, which seeks to involve end users throughout the product development life cycle. The earliest digital health care applications did not incorporate these principles, and as such, use cases were limited to the auto- mation of paper processes rather than the reimagination of care delivery and payment. This issue remains a problem to- day, as evidenced by burnout and frustration among provid- ers using EHRs (Melnick et al., 2020). In seeking to achieve better health, better care quality, lower costs, and greater satisfaction among individuals and providers, user-centered design will be an essential ingredient of any infrastructure strategy. Particular attention to culturally appropriate design and addressing the needs of historically underrepresented populations has shown early positive effects when deliver- ing interventions to populations in need and is another criti- cal issue when ensuring that unintentional bias does not fur- ther the digital divide (Schueller et al., 2019). Stewarding Digital Innovation for Our Health Futures To achieve the full potential of digital health, the health care industry and governmental leaders must collaborate, coop- erate, and develop shared governance, creating a unified digital health system architecture from independently func- tioning infrastructure building blocks. Key priorities must be identified and pursued within both the environmental and the technical contexts to achieve the full potential of digital health. The key priorities in the environmental context include focusing on the individual, embedding equity and transparency as first principles, re- forming health system payments in support of outcomes and value, and nurturing a learning health system ethos. From the technical perspective, the priorities include establishing 84 DISCUSSION PAPER Page 14Published June 27, 2022 seamless system interoperability, ensuring cybersecurity, and expanding algorithm validation and real-world testing. Focusing on the Individual Fully engaging individuals in their health and well-being through digital health, responding to public demand for participation in the growing digital health ecosystem, and balancing demand for consistent, transparent protections for health data within and outside of the health care system is a priority in achieving a fully realized future for digital health. Health data are intensely personal, and uninten- tional or nefarious exposure of that data has the potential to upend an individual’s life. Capturing the full potential of digital health will require broad confidence in health sys- tems and commercial ventures to protect the individual from negative outcomes. Transparent stewardship standards are needed to ensure individual agency in using their data. A critical first step in building trust in health data governance is a public dialogue about digital health—bringing together stakeholders into the policy process to address individual rights regarding data sharing, issues of consent, transparency, secondary uses of data, common patient identifiers, consideration of health data as a public good, and regulation of AI/ML. These dia- logues will build comfort levels and demands for expanded applications while also maintaining safeguards against abuse and unintended consequences. Central to the critical priorities for fully actualized digital health is the need to promote a sector-wide culture of trans- parency and truthfulness without fear of retribution. Similar to how To Err Is Human called upon the health care indus- try to acknowledge where their practices were worsening health, a critical next step in advancing digital health is to take definitive action to ensure that people feel comfortable reporting errors without fear of punitive actions (Shrank et al., 2019). Beyond individual agency over health data, engaging consumers in their own health and health care via digital platforms will require both systems developers and health system leaders to include the customer’s voice in the devel- opment, execution and evaluation of digital health tools and platforms. A model for patient and family engagement in digital health initiatives is in development in Canada and could serve as a starting point for advancing a model in the U.S. (Shen et al., 2021). Embedding Equity and Transparency as First Prin- ciples The rapid development and application of digital health is also accompanied by the need for vigilance on equity and equality issues that include availability and access to the benefits of digital health, racial bias in AI, and misuse of personal information in discriminatory practices. For digi- tal health to improve health and well-being, a data-centric and patient-centric approach to developing and deploy- ing these tools is essential, and data must reflect the diverse communities and populations across the U.S. Here again, the health system, researchers, and commercial ventures must address issues of mistrust with transparent, account- able, and unbiased protections so that the benefits of digital health are shared equally across society. Reforming Health System Payments in Support of Outcomes and Value COVID-19 has provided a further reminder of the systemic shortcomings of fee-for-service reimbursement, renew- ing the impetus for restructuring health care financing in America. Given the tremendous uptake of platforms such as telehealth and RPM during the COVID-19 pandemic, forth- coming payment reforms must account for the role of digital health writ large in driving delivery system transformation. Policy makers will also need to address concerns that ex- tending digital technologies will increase costs and the risk of fraud and abuse or otherwise negatively impact quality or provider-patient engagement. Furthermore, the infrastructure improvements required to advance the digital functions of a learning health system (e.g., population health management, data and analytics for risk stratification) are often unfunded activities that would benefit from additional incentives and investments such as those that accompanied HITECH. The financial benefits of payer and provider organizations must align with the health benefits of digital tools. This align- ment will require data sharing from industry, evaluations from academia and regulators, and collaboration across sectors to develop progressive payment structures across payers that allow flexibility for innovation. The path forward for value-based payment will therefore require a renewed commitment to building trust and collaboration and aligning incentives to balance the drive to innovate with stewardship of cost, quality, outcomes, and safety. Nurturing a Learning Health System Ethos The vision of digitally facilitated health depends on a con- tinuously learning health system and a dramatically short- ened interval between evidence generation, deployment to the field, and incorporation into standard practice. There is also a need to use real-world data (from wearables to am- bulatory care to robotics) to generate real-world evidence that complements the results of randomized controlled tri- als, which often suffer from limited racial or socioeconomic diversity in patient recruitment. Rapid cycle learning must 85 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 15 also be employed, as it will enable the necessary organiza- tional agility to respond to an accelerated rate and nature of change that has become the norm. Digital health tools must be well integrated into the health care delivery system to enable the continuously learning health system. With expanded data assets and improved in- teroperability, the delivery system has an opportunity to rei- magine and recreate a care system that is culturally attuned, personalized, holistic, and comprehensive—one unlike our current system, which consists of specialty, sector, and system silos. New care models can be developed with an understanding of disease and digital phenotypes and en- virotypes that will each have different treatment responses. Advanced analytics are needed to create cohorts of similar patients for more effective population health management to address the high prevalence of chronic disease and cre- ate a feedback loop regarding outcomes and evidence- based treatment in the care delivery system. Establishing Seamless System Interoperability Seamless connectivity and communication among health care-related devices are essential prerequisites for promot- ing optimal health. Incompatible interfaces, corrupted data written between systems, or mismatched patient data have the potential to have dire consequences, requiring collec- tive action to ensure adherence to standards to protect data integrity. Technological advancement and national policies have made possible the vision for a digital infrastructure that can facilitate seamless interfaces and real-time interop- erability of devices and data streams. Released in March 2020, the Cures Act final rules set forth penalties for infor- mation blocking and expanded the access of individuals to their health records by leveraging the FHIR specifications. Such standards allow information to be shared and pro- cessed consistently. In addition, there are several industry- led initiatives, such as the Integrating Healthcare Enterprise, Argonaut Project, and others, aimed at promoting seamless data exchange (IHE International, 2021; USF Morsani Col- lege of Medicine, 2021). As a promising indicator, many health systems have aligned organizational priorities to- ward interoperability objectives. Nonetheless, a great deal of work remains to achieve full system interoperability, as semantic interoperability is lim- ited. Progress is uneven across the industry, with some health systems being pioneers in real-time data sharing while oth- ers are lagging. Moreover, interoperability continues to be stunted by the systemic misalignment of incentives, competi- tive forces, and lack of coordination. Ensuring Cybersecurity The rapidly evolving landscape of cyberattacks highlights the urgent need for collaboration across the government, health organizations, and consumer-facing vendors to de- velop consensus on security protocols and upgrade secu- rity infrastructure. Existing approaches such as multi-factor authentication, intrusion detection monitoring, etc., must be employed as we explore more advanced strategies, such as adopting blockchain technologies to share immutable re- cords of transactions among network participants. Places to start could be expansion of HIPAA, national application of the California Consumer Protection Act, and a comprehen- sive privacy regime similar to the European Union’s Gen- eral Data Protection Regulation to protect all types of data deemed essential for health improvement. Expanding Algorithm Validation and Real-World Testing There is a clear need to invest in the capacity and coopera- tion necessary to advance data science and AI. AI/ML and deep learning that apply transparent algorithms and deci- sion rule architecture to large, diverse databases present the opportunity to develop increasingly precise insights for indi- viduals and populations. Critical issues include explicit and implicit bias in the development and application of mod- eling, visualization, explainability, validity, and regulation (The Lancet Digital Health, 2019; Buolamwini and Gebru, 2018). A regulatory framework must address certification of constantly changing algorithms and must hold vendors ac- countable for valid and reliable processes and must include codes of conduct and the development of “data science tools, ...pathways, agreements, and protocols for estab- lishing curated virtual health data trusts” (NASEM, 2020). The FDA’s AI/ML-based Software as a Medical Device (SaMD) Action Plan proposes such a framework and shares valuable stakeholder feedback (FDA, 2021). The capacity to advance data science and AI is depen- dent on a highly skilled digital health workforce, and “the training challenge for leveraging digital health is vast—in health care, public health, and biomedical science” (NAS- EM, 2020). In addition, as AI/ML is applied to CDS tools, it is essential to address unintended bias in algorithm creation. Tools designed for the clinical system and providers can be evaluated on their impacts on health outcomes and costs, as well as their impact on both patient and provider satisfac- tion. Real-world testing across unique health systems is re- quired to understand impacts on usability, clinical workflow, provider burden, and staff time requirements that benefit providers and patients. While time consuming, these pilots are useful and must be tied to scaling opportunities if suc- 86 DISCUSSION PAPER Page 16Published June 27, 2022 cessful. When relevant, testing of devices and AI-supported CDS must achieve FDA clearance. While the availability of digital health tools and associat- ed data sharing has better positioned America to face CO- VID-19 and harness opportunities for long-term prepared- ness and system resiliency, limitations such as the ability to aggregate data have emerged. The full potential benefits of these tools has not been realized, and the adoption and application of digital health remains uneven and subject to significant structural, technical, social, geographic, political, and economic impediments, limiting the nation’s ability to be as nimble as needed in such crisis. Priority Near-Term Actions The progress of digital technologies writ large is undisputed and can be observed in the millions of enthusiastic viewers who use streaming video services; the countless customers who shop online; and the growing number of consumers, patients, and clinicians who are embracing mobile health apps, AI-enabled diagnostic aids, and many other CDS tools. However, while the predictive analytics used to sug- gest a person’s next favorite movie may be similar to the analytics used to suggest a medical diagnosis or treatment option, one key difference remains: when a streaming ser- vice recommends a new movie, viewers may find it helpful, annoying, or even amusing—not life threatening. When al- gorithms are used to assist in the diagnosis of diabetic reti- nopathy or the recommendation of a therapeutic approach to sepsis, the stakes are much higher (Lin et al., 2019). To fully realize the goal of health and well-being for every indi- vidual, these concerns must be considered as all stakehold- ers in the health care ecosystem make intense and sustained efforts to improve the capabilities of the health care deliv- ery system, impact SDoH, ensure equal benefit from digital health, and establish an overarching architecture and gov- ernance framework that engages the public. ONC has made significant inroads toward an overarch- ing digital health blueprint for fully enabling digital health. Augmented by broader authority, continued progress on in- teragency collaboration, and robust public-private partner- ships, this progress will ensure a digital health superstructure that: • ensures equitable and ethical use of data; • supports the collection, storage, protection, and seamless sharing of accurate datasets and gener- ated insights in near-real time; • ensures the curation of that data into actionable intel- ligence; and • enables transformative advances in medical care and patient safety based on the actionable intelli- gence generated. Below is a sampling of specific, actionable items for consid- eration within this national blueprint, with specific reference to the key priorities identified above. • A multi-stakeholder panel should be convened to develop recommendations to meaningfully engage the diverse individual consumers of health care in all health care sectors. This panel should follow the ad- age “nothing about me without me” to ensure the pri- orities of focusing on the individual and embedding equity and transparency as a first principle. • A multi-stakeholder panel should be convened to establish use cases and support the development of guidelines for applications laboratories to advance the learning health system ethos and expand algo- rithm validation and real-world testing. • Congress should promulgate rational, right-sized, risk-based regulation, standards, and frameworks to enable the seamless flow of data while protect- ing privacy and ensuring transparency and account- ability to advance system interoperability and cyber- security, as well as focusing on the individual and expanding ethical and effective algorithm develop- ment, validation and real-world testing. • ONC should develop and implement a governance infrastructure and policy framework regarding data, virtual health data trusts, privacy, and regulations to advance focus on the individual, seamless system interoperability, and cybersecurity, working collab- oratively with industry to ensure broad coverage of these principles. • CMS should lead the effort to ensure sustainable payment coverage to ensure equal access to digital health tools for all individuals and providers, regard- less of private versus public payer source. In addi- tion, CMS should significantly accelerate the move to value-based payments to support outcomes, innova- tion, and aligned incentives. • ONC should ensure the timely, full implementation of standards of structure, coding, security, and common APIs, as these standards are foundational for most progress on digital health. Envisioning and achieving a seamless, healthier future through digital innovation will require a deeper investment in evidence-based research, more clinical and field studies, and commitment from diverse stakeholders. But the poten- tial for rewards is enormous. Validated information, curated across the health data continuum and easily shared, can de- liver insight at the point of care, easing provider burden and augmenting clinical reasoning skills. An “Internet of Things” in health care serves the public’s need for accurate health 87 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 17 advice, and a digital health ecosystem that provides high- quality, personalized, equitable care to all who need it is achievable and worthy of our best individual and collective efforts. References 1. Accenture. 2019. Today’s consumers reveal the future of healthcare. Available at: https://www.accenture. com/us-en/insights/health/todays-consumers-re- veal-future-healthcare (accessed January 26, 2022). 2. Allegrante, J. P., M. T. Wells, and J. C. Peterson. 2019. Interventions to Support Behavioral Self-management of Chronic Diseases. Annual Review of Public Health 40:127-146. https://doi.org/10.1146/annurev-publ- health-040218-044008. 3. Anderson, W. C., R. Gondalia, H. E. Hoch, L. Kaye, S. J. Szefler, and D. A. Stempel. 2019. Screening for inhalation technique errors with electronic medica- tion monitors. Journal of Allergy and Clinical immu- nology: In Practice 7(6):2065-2067. https://doi. org/10.1016/j.jaip.2019.02.006. 4. Artiga, S., and E. Hinton. 2018. Beyond Health Care: The Role of Social Determinants in Promoting Health and Health Equity. Available at: https://www.kff.org/ racial-equity-and-health-policy/issue-brief/beyond- health-care-the-role-of-social-determinants-in-pro- moting-health-and-health-equity/ (accessed October 5, 2020). 5. Atasoy, H., B. N. Greenwood, and J. S. McCullough. 2019. The Digitization of Patient Care: A Review of the Effects of Electronic Health Records on Health Care Quality and Utilization. Annual Review of Public Health 40:487-500. https://doi.org/10.1146/annurev- publhealth-040218-04420. 6. Avram, R., J. E. Olgin, P. Kuhar, J. W. Hughes, G. M. Marcus. M. J. Pletcher, K. Aschbacher, and G. H. Ti- son. 2020. A digital biomarker of diabetes from smartphone-based vascular signals. Nature Medicine 26:1576-1582. https://doi.org/10.1038/s41591- 020-1010-5. 7. Baker, D. B., J. Kaye, and S. F. Terry. 2016. Privacy, Fairness, and Respect for Individuals. eGEMS 4(2):7. https://doi.org/10.13063/2327-9214.1207. 8. Barisoni, L., K. J. Lafata, S. M. Hewitt, A. Madabhushi, and U. G. J. Balis. 2020. Digital pathology and com- putational image analysis in nephropathology. Na- ture Reviews Nephorology 16:669-685. https://doi. org/10.1038/s41581-020-0321-6. 9. Barrett, M., V. Combs, J. G. Su, K. Henderson, and M. Tuffli. 2018. AIR Louisville: Addressing Asthma With Technology, Crowdsourcing, Cross-Sector Col- laboration, And Policy. Health Affairs 37(4):525-534. https://doi.org/10.1377/hlthaff.2017.1315. 10. Barrett, M. A., O. Humblet, R. A. Hiatt, and N. E. Adler. 2013. Big data and disease prevention: From quanti- fied self to quantified communities. Big Data 1(3):168- 175. http://doi.org/10.1089/big.2013.0027. 11 . Bates, D. W., and H. Singh. 2018. Two Decades Since To Err Is Human: An Assessment of Progress And Emerging Priorities In Patient Safety. Health Affairs 37(11):1736- 1743. https://doi.org/10.1377/hlthaff.2018.0738. 12. Bestsennyy, O., G. Gilbert, and A. Harris. 2020. Tele- health: A quarter-trillion-dollar post-COVID-19 real- ity? Available at: https://www.mckinsey.com/indus- tries/healthcare-systems-and-services/our-insights/ telehealth-a-quarter-trillion-dollar-post-covid-19-reali- ty (accessed October 5, 2020). 13 . Biel, D., M. DeLone, W. Gerhardt, and C. Chang. 2019. Radical Interoperability. Available at: https://www2. deloitte.com/us/en/insights/industry/health-care/ radical-data-interoperability-survey.html (accessed October 5, 2020). 14. Boyde, A. M. and B. W. Chaffee. 2019. Critical Evalu- ation of Pharmacy Automation and Robotic Systems: A Call to Action. Hospital Pharmacy 54(1):4-11. https:// doi.org/10.1177/0018578718786942. 15 . Buckeridge, D. L. 2020. Precision, Equity, and Pub- lic Health and Epidemiology Informatics—A Scoping Review. Yearbook of Medical Informatics 29(1):226- 330. https://doi.org/10.1055/s-0040-1701989. 16. Bughin, J., E. Hazan, S. Ramaswamy, M. Chu, T. Allas, P. Dahlstrom, N. Henke, and M. Trench. 2017. Artifi- cial Intelligence: The Next Digital Frontier? McKinsey Global Institute. Available at: https://www.mckinsey. com/~/media/mckinsey/industries/advanced%20 electronics/our%20insights/how%20artificial%20in- telligence%20can%20deliver%20real%20value%20 to%20companies/mgi-artificial-intelligence-discus- sion-paper.ashx (accessed February 24, 2022). 17. Buntin, M. B., M. F. Burke, M. C. Hoaglin, and D. Blu- menthal. 2011. The benefits of health information tech- nology: a review of the recent literature shows predom- inantly positive results. Health Affairs 30(3):464-471. https://doi.org/10.1377/hlthaff.2011.0178. 18. Buolamwini, J., and T. Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. Proceedings of Machine Learn- ing Research 81:1-15. Available at: http://proceed- ings.mlr.press/v81/buolamwini18a/buolamwini18a. pdf (accessed February 14, 2022). 19. Buttorff, C., T. Ruder, and M. Bauman. 2017. Multiple 88 DISCUSSION PAPER Page 18Published June 27, 2022 Chronic Conditions in the United States. Santa Monica: RAND Corporation. Available at: https://www.rand. org/pubs/tools/TL221.html (accessed February 14, 2022). 20. Byrne, D. W., L. A. Rolando, M. H. Aliyu, P. W. Mc- Gown, L. R., Connor, B. M. Awalt, M. C. Holmes, L. Wang, and M. I. Yarbrough. 2016. Modifiable Healthy Lifestyle Behaviors: 10-Year Health Outcomes From a Health Promotion Program. American Journal of Preventive Medicine 51(6):1029-1037. https://doi. org/10.1016/j.amepre.2016.09.012. 21 . Centers for Disease Control and Prevention (CDC). 2020. Public Health Surveillance and Data. Available at: https://www.cdc.gov/surveillance/surveillance- data-strategies/dmi-investments.html (accessed Janu- ary 26, 2022). 22. Centers for Medicare & Medicaid Services (CMS). 2 019. Historical. Available at: https://www.cms. gov/Research-Statistics-Data-and-Systems/Statistics- Trends-and-Reports/NationalHealthExpendData/ NationalHealthAccountsHistorical (accessed October, 5, 2020). 23. Cigna Newsroom. n.d. Convenient, Cost-Effective, and High-Quality Virtual Care Is Here to Stay. Available at: https://newsroom.cigna.com/convenient-cost- effective-and-high-quality-virtual-care-is-here-to-stay (accessed May 18, 2022). 24. Craig, K. J. T., N. Fusco, K. Lindsley, J. L. Snowdon, V. C. Willis, Y. E. Arriaga, and I. Dankwa-Mullan. 2020. Rapid review: Identification of digital health interven- tions in atherosclerotic-related cardiovascular disease populations to address racial, ethnic, and socioeco- nomic health disparities. Cardiovascular Digital Health Journal 1(3):139-148. https://doi.org/10.1016/j. cvdhj.2020.11.001. 25. De Keyser, H. E. H., L. Kaye, W. C. Anderson, R. Gondalia, B. Theye, S. J. Szefler, and D. A. Stempel. 2020. Electronic medication monitors help determine adherence subgroups in asthma. Respiratory Medicine 164. https://doi.org/10.1016/j.rmed.2020.105914. 26. Deng, H. F., M-.W. Sun, Y. Wang, J. Zeng, T. Yuan, T. Li, D-. H. Li, W. Chen, P. Zhou, Q. Wang, and H. Jiang. 2021. Evaluating machine learning models for sep- sis prediction: A systematic review of methodologies. iScience 25(1):103651. https://doi.org/10.1016/j. isci.2021.103651. 27. Department of Health and Human Services (HHS). 2021. HHS Releases Project US@ Draft Technical Specification Version 1.0 for Comment. Available at: https://www.hhs.gov/about/news/2021/06/16/ hhs-releases-project-us-draft-technical-specification- for-comment.html (accessed January 26, 2022). 28. Dixon, B. E., S. J. Grannis, C. McAndrews, A. A. Bro- yles, W. Mikels-Carrasco, A. Wiensch, J. L. Williams, U. Tachinardi, and P. J. Embi. 2021. Leveraging data visualization and a statewide health information ex- change to support COVID-19 surveillance and re- sponse: Application of public health informatics. Jour- nal of the American Medical Informatics Association 28(7):1363-1373. https://doi.org/10.1093/jamia/ ocab004. 29. Eddy, D. M. 1982. Clinical Policies and the Qual- ity of Clinical Practice. New England Journal of Medicine 307:343-347. https://doi.org/10.1056/ NEJM198208053070604. 30. Engelhard, M. M., J. A. Oliver, and F. J. McClernon. 2020. Digital envirotyping: quantifying environmental determinants of health and behavior. npj Digital Medi- cine 3(36):1-3. https://doi.org/10.1038/s41746- 020-0245-3. 31 . European Commission (EC). 2021. Proposal for a regulation of the European parliament and of the council laying down harmonised rules on ar- tificial intelligence (artificial intelligence act) and amending certain union legislative acts. Available at: https://eur-lex.europa.eu/legal-content/EN/ TXT/?uri=CELEX%3A52021PC0206 (accessed Janu- ary 26, 2022). 32. Food and Drug Administration (FDA). n.d. Good Ma- chine Learning Practice for Medical Device Develop- ment: Guiding Principles. Available at: https://www. fda.gov/medical-devices/software-medical-device- samd/good-machine-learning-practice-medical-de- vice-development-guiding-principles (accessed Janu- ary 26, 2022). 33. FDA. 2021. Artificial Intelligence and Machine Learn- ing in Software as a Medical Device. Available at: https://www.fda.gov/medical-devices/software- medical-device-samd/artificial-intelligence-and-ma- chine-learning-software-medical-device (accessed February 14, 2022). 34. Feagin, J., and Z. Bennefield. 2014. Systemic racism and U.S. health care. Social Science & Medicine 103:7-14. https://doi.org/10.1016/j.socscimed.2013.09.006. 35. Glaser, J. 2019. What Banking Can Teach Health Care About Handling Customer Data. Available at: https:// hbr.org/2019/10/what-banking-can-teach-health- care-about-handling-customer-data (accessed Octo- ber 5, 2020). 36. Goh, K. H., L. Wang, A. Y. K. Yeow, H. Poh, K. Li, J. J. L. 89 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 19 Yeow, and G. Y. H. Tan. 2021. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature Communications 12:711. https://doi.org/10.1038/s41467-021-20910-4. 37. Gordon, W. J., A. Landman, H. Zhang, and D. W. Bates. 2020. Beyond validation: getting health apps into clinical practice. Npj Digital Medicine 3(14):1-14. https://doi.org/10.1038/s41746-019-0212-z. 38. Halamka, J., and P. Cerrato. 2020. The Digital Recon- struction of Health Care. NEJM Catalyst Innovations in Care Delivery 1(6):1-12. https://doi.org/10.1056/ CAT.20.0082. 39. Hall, K. D., and S. Kahan. 2018. Maintenance of Lost Weight and Long-Term Management of Obesity. Med- ical Clinics of North America 102(1)183-197. https:// doi.org/10.1016/j.mcna.2017.08.012. 40. Hartzog, W. 2018. Privacy’s Blueprint: The Battle to Control the Design of New Technologies. Boston: Har- vard University Press. 41. HealthIT.gov. 2022. Trusted Exchange Framework and Common Agreement (TEFCA). Available at: https:// www.healthit.gov/topic/interoperability/trusted- exchange-framework-and-common-agreement-tefca (accessed January 26, 2022). 42. HealthIT.gov. 2020. About ONC’s Cures Act Final Rule. Available at: healthit.gov/curesrule/overview/ about-oncs-cures-act-final-rule (accessed February 14, 2022). 43. HealthIT.gov. 2017. Rhode Island Quality Institute Tran- sitions of Care. Available at: https://www.healthit. gov/success-story/rhode-island-quality-institute-tran- sitions-care (accessed January 26, 2022). 44. HealthIT.gov. 2009. Index for Excerpts from the Ameri- can Recovery and Reinvestment Act of 2009 (ARRA). Available at: https://www.healthit.gov/sites/default/ files/hitech_act_excerpt_from_arra_with_index.pdf (accessed February 14, 2022). 45. HealthIT.gov. n.d. United States Core Data for Interop- erability (USCDI). Available at: https://www.healthit. gov/isa/united-states-core-data-interoperability-usc- di (accessed May 18, 2022). 46. Health IT Dashboard. 2016. Quick Stats. Available at: https://dashboard.healthit.gov/quickstats/quickstats. php (accessed September 17, 2020). 4 7. Heller, D. J., K. A. Ornstein, L. V. DeCherrie, P. Saenger, F. C. Ko, C.-P. Rousseau, and A. Siu. 2020. Adapting a Hospital‐at‐Home Care Model to Respond to New York City’s COVID‐19 Crisis. Journal of the American Geriatrics Society 68(9):1915-1916. https://doi. org/10.1111/jgs.16725. 48. Health Information National Trends Survey (HINTS). 2021. HINTS Briefs Number 45. Available at: https:// hints.cancer.gov/docs/Briefs/HINTS_Brief_45.pdf (accessed May 18, 2022). 49. HL7 International. n.d. FHIR® (HL7 Fast Healthcare Interoperability Resources). Available at: https:// www.hl7.org/implement/standards/product_brief. cfm?product_id=491 (accessed May 18, 2022). 50. Hruby, A., H. R. Lieberman, and T. J. Smith. 2018. Self- reported health behaviors, including sleep, correlate with doctor-informed medical conditions: data from the 2011 Health Related Behaviors Survey of U.S. Active Duty Military Personnel. BMC Public Health 18:1-16. https://doi.org/10.1186/s12889-018-5781-2. 51 . Ideas for Change. 2016. SalusCoop Report. Avail- able at: https://www.ideasforchange.com/en/tools/ saluscoop-report (accessed February 14, 2022). 52. IHE International. 2021. Integrating the Healthcare En- terprise (IHE). Available at: https://www.ihe.net/ (ac- cessed March 3, 2021). 53. International Medical Device Regulators Forum Soft- ware as a Medical Device Working Group (IMDRF). 2 015 . Software as a Medical Device (SaMD): Appli- cation of Quality Management System. Available at: https://www.imdrf.org/sites/default/files/docs/ imdrf/final/technical/imdrf-tech-151002-samd-qms. pdf (accessed February 14, 2022). 54. IMDRF. 2017. Clinical Evaluation. Available at: https:// www.imdrf.org/sites/default/files/docs/imdrf/fi- nal/technical/imdrf-tech-170921-samd-n41-clinical- evaluation_1.pdf (accessed February 14, 2022). 55. Institute of Medicine (IOM). 2010. The Healthcare Imperative: Lowering Costs and Improving Out- comes: Workshop Series Summary. Washington, DC: The National Academies Press. https://doi. org/10.17226/12750. 56. IOM. 2004. Patient Safety: Achieving a New Standard for Care. Washington, DC: The National Academies Press. https://doi.org/10.17226/10863. 57. IOM. 2000. To Err Is Human: Building a Safer Health System. Washington, DC: The National Academies Press. https://doi.org/10.17226/9728. 58. Isasi, F., M. D. Naylor, D. Skorton, D. C. Grabowski, S. Hernández, and V. Montgomery Rice. 2021. Pa- tients, Families, and Communities COVID-19 Impact Assessment: Lessons Learned and Compelling Needs. NAM Perspectives. Discussion Paper, National Acad- emy of Medicine, Washington, DC. https://doi. org/10.31478/202111c. 59. Ivanov, O., L. Wolf, D. Brecher, E. Lewis, K. Masek, 90 DISCUSSION PAPER Page 20Published June 27, 2022 K. Montgomery, Y. Andrieiev, M. McLaughlin, S. Liu, R. Dunne, K. Klauer, and C. Reilly. 2020. Improving ED Emergency Severity Index Acuity Assignment Us- ing Machine Learning and Clinical Natural Language Processing. Journal of Emergency Nursing 47(2):265- 278. https://doi.org/10.1016/j.jen.2020.11.001. 60. Jain, J. S., B. W. Powers, J. B. Hawkins, and J. S. Brown- stein. 2015. The digital phenotype. Nature Biotech- nology 33(5):462-463. https://doi.org/10.1038/ nbt.3223. 61. Kaye, L., B. Theye, I. Smeenk, R. Gondalia, M. A. Bar- rett, and D. A. Stempel. 2020. Changes in medication adherence among patients with asthma and COPD during the COVID-19 pandemic. The Journal of Aller- gy and Clinical Immunology: In Practice 8(7): 2384- 2385. https://doi.org/10.1016/j.jaip.2020.04.053. 62. Kearney, A, L. Hamel, M. Stokes, and M. Broadie. 2021. Americans’ Challenges with Health Care Costs. Kaiser Family Foundation, December 14. Available at https://www.kff.org/health-costs/issue-brief/amer- icans-challenges-with-health-care-costs/ (accessed May 18, 2022). 63. Keehan, S. P., G. A. Cuckler, J. A. Poisal, A. M. Sisko, S. D. Smith, A. J. Madison, K. E. Rennie, J. A. Fiore, and J. C. Hardesty. 2020. National Health Expenditure Pro- jections, 2019–28: Expected Rebound In Prices Drives Rising Spending Growth. Health Affairs 39(4):704- 714. https://doi.org/10.1377/hlthaff.2020.00094. 64. Kottke, T. E., M. Stiefel, and N. P. Pronk. 2016. “Well-Being in All Policies”: Promoting Cross-Sec- toral Collaboration to Improve People’s Lives. NAM Perspectives. Discussion Paper, National Acad- emy of Medicine, Washington, DC. https://doi. org/10.31478/201604c. 65. Lamberti, M. J., M. Wilkinson, B. A. Donzanti, G. E. Wohlhieter, S. Parikh, R. G. Wilkins, and K. Getz. 2019. A Study on the Application and Use of Artificial Intel- ligence to Support Drug Development. Clinical Thera- peutics 41(8):1414-1426. https://doi.org/10.1016/j. clinthera.2019.05.018. 66. LaRosa, J. 2020. $71 Billion U.S. Weight Loss Indus- try Pivots to Survive Pandemic. Available at: https:// blog.marketresearch.com/71-billion-u.s.-weight-loss- market-pivots-to-survive-pandemic (accessed January 26, 2022). 6 7. Lee, P., A. Abernethy, D. Shaywitz, A. V. Gundlapalli, J. Weinstein, P. M. Doraiswamy, K. Schulman, and S. Madhavan. 2022. Digital Health COVID-19 Im- pact Assessment: Lessons Learned and Compelling Needs. NAM Perspectives. Discussion Paper, National Academy of Medicine, Washington, DC. https://doi. org/10.31478/202201c. 68. Lin, S. Y., M. R. Mahoney, C. A. Sinky. 2019. Ten Ways Artificial Intelligence Will Transform Primary Care. Jour- nal of General Internal Medicine 34(8):1620-1630. https://doi.org/10.1007/s11606-019-05035-1. 69. Lindau, S. T. 2019. CommunityRx, an E-Prescribing System Connecting People to Community Resources. American Journal of Public Health 109(4):546-547. https://doi.org/10.2105/AJPH.2019.304986. 70. Luchini, C., A. Pea, and A. Scarpa. Artificial intelligence in oncology: current applications and future perspec- tives. British Journal of Cancer 126:4–9. https://doi. org/10.1038/s41416-021-01633-1. 71 . McGinnis, J. M., H. V. Fineberg, and V. J. Dzau. 2021. Advancing the Learning Health System. New England Journal of Medicine 385:1-5. https://doi. org/10.1056/NEJMp2103872. 72. McGinnis, M. J., P. Williams-Russo, and J. R. Knickman. 2002. The Case For More Active Policy Attention To Health Promotion. Health Affairs 21(2):78-93. https:// doi.org/10.1377/hlthaff.21.2.78. 73. McGovern, L., G. Miller, and P. Hughes-Cromwick. 2014. The Relative Contribution of Multiple Determi- nants to Health Outcomes. Available at: https://www. rwjf.org/en/library/research/2014/08/the-rela- tive-contribution-of-multiple-determinants-to-health- out.html (accessed October 5, 2020). 74. Melnick, E. R., L. N. Dyrbye, C. A. Synsky, M. Trockel, C. P. West, L. Nedelec, M. A. Tutty, and T. Shanafelt. 2020. The Association Between Perceived Electronic Health Record Usability and Professional Burnout Among US Physicians. Mayo Clinic Proceedings 95(3):476-487. https://doi.org/10.1016/j.mayocp.2019.09.024. 75. Merchant, R., S. J. Szefler, B. G. Bender, M. Tuffli, M. A. Barrett, R. Gondalia, L. Kaye, D. V. Sickle, and D. A. Stempel. 2018. Impact of a digital health interven- tion on asthma resource utilization. World Allergy Or- ganization Journal 11(28). https://doi.org/10.1186/ s40413-018-0209-0. 76. Meyer, D., E. Lerner, A. Phillips, and K. Zumwalt. 2020. Universal Screening of Social Determinants of Health at a Large US Academic Medical Center. American Journal of Public Health 110(S2):S219-S221. https:// doi.org/10.2105/AJPH.2020.305747. 7 7. MiDATA. n.d. My Data—Our Health. Available at: https://www.midata.coop/en/home/ (accessed October 5, 2020). 78. Murray, S. G., R. M. Wachter, and R. J. Cucina. 2020. Discrimination By Artificial Intelligence In A Commer- 91 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 21 cial Electronic Health Record— A Case Study. Avail- able at: https://www.healthaffairs.org/do/10.1377/ hblog20200128.626576/full/ (accessed March 3, 2021). 79. Muzney, M., A. Henriksen, A. Giordanengo, J. Muzik, A. Grøttland, H. Blixgård, G. Hartvigsen, and E. År- sand. 2020. Wearable sensors with possibilities for data exchange: Analyzing status and needs of differ- ent actors in mobile health monitoring systems. Interna- tional Journal of Medical Informatics 133:1-8. https:// doi.org/10.1016/j.ijmedinf.2019.104017. 80. National Academy of Medicine (NAM). 2020. NAM Leadership Consortium: Collaboration for a Value & Science-Driven Health System. Available at: https:// nam.edu/programs/value-science-driven-health- care/ (accessed October 5, 2020). 81 . National Academies of Sciences, Engineering, and Medicine (NASEM). 2020. Joint Science Academies Statements on Global Issues (G-Science). Available at: https://www.nationalacademies.org/our-work/ joint-science-academies-statements-on-global- issues#sectionProjectScope (accessed January 26, 2022). 82. National Institute of Standards and Technology (NIST). 2018. Framework for Improving Critical In- frastructure Cybersecurity, Version 1.1. Available at https://nvlpubs.nist.gov/nistpubs/CSWP/NIST. CSWP.04162018.pdf (accessed May 13, 2022). 83. National Institutes of Health (NIH). 2020. All of Us Research Program Backgrounder. Available at: https://allofus.nih.gov/news-events/press-kit/all-us- research-program-backgrounder (accessed October 26, 2020). 84. National Library of Medicine (NLM). 2022. RxNorm Overview. Available at: https://www.nlm.nih.gov/ research/umls/rxnorm/overview.html (accessed May 18, 2022). 85. Observational Health Data Sciences and Informatics (OHDSI). 2022. Home. Available at: https://www. ohdsi.org/ (accessed May 18, 2022). 86. Office of the National Coordinator for Health Informa- tion Technology (ONC). 2020. Health IT Workflow Automation: Background Report, Industry Lessons for Health Care. Available at: https://www.healthit.gov/ sites/default/files/topiclanding/2021-07/Work- flow_Automation_Background_Report_FINAL.pdf (accessed May 18, 2022). 87. Pagoto, S., and G. G. Bennett. 2020. How behav- ioral science can advance digital health. Translation- al Behavioral Medicine 3(3):271-276. https://doi. org/10.1007/s13142-013-0234-z. 88. Panagioti, M., K. Geraghty, J. Johnson, A. Zhou, E. Panagopoulou, C. Chew-Graham, A. Hodkinson, R. Riley, and A. Esmail. 2018. Association Between Physi- cian Burnout and Patient Safety, Professionalism, and Patient Satisfaction: A Systematic Review and Meta- analysis. JAMA Internal Medicine 178(10):1317-1331. https://doi.org/10.1001/jamainternmed.2018.3713. 89. Patel, S., L. Jacobus-Kantor, L. Marshall, C. Ritchie, M. Kaplinski, P. S. Khurana, and R. J. Katz. 2013. Mobi- lizing Your Medications: An Automated Medication Reminder Application for Mobile Phones and Hyper- tension Medication Adherence in a High-Risk Urban Population. Journal of Diabetes Science and Technol- ogy 7(3):630-639. https://doi.org/10.1177/19322 9681300700307. 90. The National Patient-Centered Clinical Research Net- work (PCORNet). n.d. Home. Available at: https:// pcornet.org/ (accessed May 18, 2022). 91. Rasmussen, S. A., M. K. Khoury, and C. Del Rio. 2020. Precision Public Health as a Key Tool in the COVID-19 Response. JAMA 324(10):933-934. https://doi. org/10.1001/jama.2020.14992. 92. Research Data Assistance Center (ResDAC). 2022. Home. Available at: https://resdac.org/ (accessed May 18, 2022). 93. Schroeder, S. A. 2007. We Can Do Better—Improv- ing the Health of the American People. New England Journal of Medicine 357(12):1221-1228. https://doi. org/10.1056/NEJMsa073350. 94. Schueller, S. M., J. F. Hunter, C. Figueroa, and A. Agu- ilera. 2019. Use of Digital Mental Health for Margin- alized and Underserved Populations. Current Treat- ment Options in Psychiatry 6:243-255. https://doi. org/10.1007/s40501-019-00181-z. 95. Settineri, S., F. Frisone, E. M. Merlo, D. Geraci, and G. Martino. 2019. Compliance, adherence, concordance, empowerment, and self-management: five words to manifest a relational maladjustment in diabetes. Journal of Multidisciplinary Healthcare 12:299-314. https:// doi.org/10.2147/JMDH.S193752. 96. Shan, R., S. Sarker, and S. S. Martin. 2019. Digital health technology and mobile devices for the manage- ment of diabetes mellitus: state of the art. Diabetologia 62:877-887. https://doi.org/10.1007/s00125-019- 4864-7. 97. Shegog, R., L. Braverman, and J. D. Hixson. 2020. Digital and technological opportunities in epilepsy: toward a digital ecosystem for enhanced epilepsy management. Epilepsy & Behavior 102. https://doi. 92 DISCUSSION PAPER Page 22Published June 27, 2022 org/10.1016/j.yebeh.2019.106663. 98. Shrank, W. H., T. L. Rogstad, and N. Parekh. 2019. Waste in the US Health Care System: Estimated Costs and Potential for Savings. JAMA 322(15):1501-1509. https://doi.org/10.1001/jama.2019.13978. 99. Shen, N., D. Jankowicz, and G. Strudwick. 2021. Pa- tient and Family Engagement Approaches for Digi- tal Health Initiatives: Protocol for a Case Study. JMIR Research Protocols 10(7):e24274. https://doi. org/10.2196/24274. 100. Singhal, S., B. Kayyali, R. Levin, and Z. Greenberg. 2020. The next wave of healthcare innovation: The evolution of ecosystems. Available at: https://www. mckinsey.com/industries/healthcare-systems-and-ser- vices/our-insights/the-next-wave-of-healthcare-inno- vation-the-evolution-of-ecosystems (accessed October 5, 2020). 101. SNOMED International. n.d. Who We Are. Available at: https://www.snomed.org/snomed-international/ who-we-are (accessed May 18, 2022). 102. Steinmetz, M., C. Rammos, T. Rassaf, and J. Lortz. 2020. Digital interventions in the treatment of car- diovascular risk factors and atherosclerotic vascular disease. International Journal of Cardiology Heart & Vasculature 26:1-8. https://doi.org/10.1016/j.ij- cha.2020.100470. 103. Tanner, C., D. Gans, J. White, R. Nath, and J. Pohl. 2015. Electronic Health Records and Patient Safety. Applied Clinical Informatics 6:136-147. https://doi. org/10.4338/ACI-2014-11-RA-0099. 104. The Commonwealth Fund. 2019. 2019 Common- wealth Fund International Health Policy Survey of Pri- mary Care Physicians. Available at: https://www. commonwealthfund.org/publications/surveys/2019/ dec/2019-commonwealth-fund-international-health- policy-survey-primary (accessed March 3, 2021). 105. The Commonwealth Fund. 2016. High-Need, High-Cost Patients: Who Are They and How Do They Use Health Care? Available at: https://www.com- monwealthfund.org/publications/issue-briefs/2016/ aug/high-need-high-cost-patients-who-are-they-and- how-do-they-use (accessed January 26, 2022). 106. The Lancet Digital Health. 2019. There is no such thing as race in health-care algorithms. The Lancet Digital Health 1(8):e375. https://doi.org/10.1016/ S2589-7500(19)30201-8. 107. The Pew Charitable Trusts. 2020. Patients Seek Bet- ter Exchange of Health Data Among Their Care Pro- viders. Available at: https://www.pewtrusts.org/ en/research-and-analysis/issue-briefs/2020/03/ patients-seek-better-exchange-of-health-data-among- their-care-providers (accessed January 26, 2022). 108. The Pew Charitable Trusts. 2018. Enhanced Pa- tient Matching Is Critical to Achieving Full Prom- ise of Digital Health Records. Available at: https:// www.pewtrusts.org/en/research-and-analysis/re- ports/2018/10/02/enhanced-patient-matching-crit- ical-to-achieving-full-promise-of-digital-health-records (accessed January 26, 2022). 109. Tikkanen, R., and M. K. Abrams. 2020. U.S. Health Care from a Global Perspective, 2019: Higher Spending, Worse Outcomes? Available at: https:// www.commonwealthfund.org/publications/issue- briefs/2020/jan/us-health-care-global-perspec- tive-2019 (accessed October 5, 2020). 110. Topol, E. J. 2019. A decade of digital medicine inno- vation. Science Translational Medicine 11(498):1-3. https://doi.org/10.1126/scitranslmed.aaw7610. 111 . Tung, J. Y., R. J. Shaw, J. M. Hagenkord, M. Hack- mann, M. Muller, S. H. Beachy, V. M. Pratt, S. F. Terry, A. K. Cashion, and G. S. Ginsburg. 2018. Accelerating precision health by applying the lessons learned from direct-to-consumer genomics to digital health technolo- gies. NAM Perspectives. Discussion Paper, National Academy of Medicine, Washington, DC. https://doi. org/10.31478/201803c. 112. USF Morsani College of Medicine. 2021. What is the Argonaut Project? Available at: https://www. usfhealthonline.com/resources/health-informatics/ what-is-the-argonaut-project/ (accessed January 26, 2022). 11 3 . Walker, J., E. Pan, D. Johnston, J. Adler-Milstein, D. W. Bates, and B. Middleton. 2005. The Value of Health Care Information Exchange and Interoperability. Health Affairs 24(S1):W5-10-W5-18. https://doi. org/10.1377/hlthaff.w5.10. 114. World Health Organization (WHO). 2006. Constitu- tion of the World Health Organization. Available at: https://www.who.int/governance/eb/who_constitu- tion_en.pdf (accessed February 13, 2022). 11 5 . Zachrison, K. S., Z. Yan, T. Sequist, A. Licurse, A. Tan- McGrory, A. Erskine, and L. H. Schwamm. 2021. Pa- tient characteristics associated with the successful transition to virtual care: Lessons learned from the first million patients. Journal of Telemedicine. https://doi. org/10.1177/1357633X211015547. DOI https://doi.org/10.3147/202206e 93 The Promise of Digital Health: Then, Now, and the Future NAM.edu/Perspectives Page 23 Suggested Citation Abernethy, A., L. Adams, M. Barrett, C. Bechtel, P. Brennan, A. Butte, J. Faulkner, E. Fontaine, S. Friedhoff, J. Halamka, M. Howell, K. Johnson, P. Lee, P. Long, D. McGraw, R. Miller, J. Perlin, D. Rucker, L. Sandy, L. Savage, L. Stump, P. Tang, E. Topol, R. Tuckson, and K. Valdes. 2022. The Promise of Digi- tal Health: Then, Now, and the Future. NAM Perspectives. Discussion Paper, National Academy of Medicine, Wash- ington, DC. https://doi.org/10.31478/202206e. Author Information Amy Abernethy, MD, PhD, is President, Clinical Research Platforms, at Verily. Laura Adams, MS, is Senior Advisor at the National Academy of Medicine. Meredith Barrett, PhD, is Vice President, Population Health Research, at ResMed. Christine Bechtel, MA, is Co-Founder at X4 Health. Patricia Brennan, RN, PhD, FAAN, is Director at the National Library of Medicine. Atul Butte, MD, PhD, is Priscilla Chan and Mark Zuckerberg Distinguished Professor and inaugural Director, Bakar Computational Health Sciences Institute at University of California, San Francisco. Judith Faulkner, MS, is Founder and Chief Executive Officer at Epic Systems. Elaine Fontaine, BS, is Consultant at the National Academy of Medicine. Stephen Friedhoff, MD, is Senior Vice President, Clinical Strategy and Programs, at Anthem, Inc. John Halamka, MD, is President, Mayo Clinic Platform, at the Mayo Clinic. Michael Howell, MD, MPH, is Chief Clinical Officer at Google Health. Kevin Johnson, MD, is Penn Integrates Knowledge University Professor at the University of Pennsylvania. Peter Lee, PhD, is Corporate Vice President at the Microsoft Corporation. Peter Long, PhD, is Executive Vice President, Strategy and Health Solutions at Blue Shield of California. Deven McGraw, JD, MPH, is Chief Regulatory Officer at Ciitizen Corporation. Redonda Miller, MD, MBA, is President of Johns Hopkins Hospital. Jonathan Perlin, MD, PhD, MSHA, is President of The Joint Commission. Donald Rucker, MD, is Chief Strategy Officer at 1upHealth. Lewis Sandy, MD, MBA, is Senior Vice President, Clinical Advancement, at UnitedHealth Group. Lucia Savage, JD, is Chief Privacy and Regulatory Officer at Omada Health, Inc. Lisa Stump, MS, is Senior Vice President and Chief Information Officer at Yale New Haven Health System and Yale School of Medicine. Paul Tang, MD, MS, is adjunct professor, Clinical Excellence Research Center at Stanford University. Eric Topol, MD, is Executive Vice President and Professor at The Scripps Research Institute. Reed Tuckson, MD, FACP, is Managing Director at Tuckson Health Connections, LLC. Kristen Valdes is Founder and CEO at b.well Connected Health. Drs. Brennan, Butte, Halamka, Johnson, Miller, Lee, Perlin, Tang, Topol, and Tuckson are members of the National Academy of Medicine. Acknowledgments This paper benefited from the thoughtful input of John Gla- ser, Siemens Healthcare; Clement McDonald, National Library of Medicine; and Marc Overhage, Anthem. The authors would like to recognize Paul Cerrato with the Mayo Clinic for contributing to earlier drafts of this publica- tion and to thank Mahnoor Ahmed and Asia Williams with the National Academy of Medicine Leadership Con- sortium for assistance with research and fact-checking. Conflict-of-Interest Disclosures Amy Abernethy discloses employment by Verily, an Al- phabet Company; employment by the U.S. FDA while this paper was being drafted; and serving as member of the Board of Directors or EQRx. Laura Adams discloses em- ployment as Senior Advisor to the National Academy of Medicine. Meredith Barrett discloses receiving personal fees from ResMed and Propeller Health. Atul Butte dis- closes receiving grants and non-financial support from Pro- genity; personal fees and other support from NuMedii, Per- sonalis, Assay Depot, GNS Healthcare, uBiome, and Nuna Health; grants and personal fees from NIH and Genentech; grants from L’Oreal and Samsung; personal fees and non- financial support from Merck, Lilly, Geisinger Health, and Roche; and serving as consultant to Wilson Sonsini Goorich & Rosati, Orrick Herrington & Sutcliffe, Verinata, 10x Ge- nomics, Pathway Genomics, Guardant Health, and Gerson Lehrman Group. Elaine Fontaine discloses employment as a consultant to the National Academy of Medicine. Stephen Friedhoff discloses employment by Anthem BC while this paper was being drafted; current employ- ment by BCNC; serving as board member to Agape Care and Medical Review Institute of America; and advisor to Rialtic. Michael Howell discloses employment and eq- uity in Google, an Alphabet company. Kevin Johnson discloses employment by University of Pennsylvania. Peter Lee discloses employment by Microsoft. Deven McGraw discloses employment by Invitae Corporation and Ciitizen Corporation; personal fees from Datavant and All of Us Re- search Program; and serving as board member for CARIN Alliance and Manifest Medex. Redonda Miller discloses 94 DISCUSSION PAPER Page 24Published June 27, 2022 employment by the Johns Hopkins University. Jonathan Perlin discloses former employment by HCA Healthcare. Donald Rucker discloses former employment by the Na- tional Coordinator for Health IT; current employment by 1up Health; and personal fees from Cync Health. Paul Tang discloses employment by IBM Watson Health. Eric Topol discloses receiving personal fees from Illumnia and serving on the board of directors at Dexcom. Kristen Valdes dis- closes employment by b.well Connected Health. Correspondence Questions and comments about this paper should be direct- ed to Laura Adams at LAdams@nas.edu. Additional inqui- ries should be sent to NAMedicine@nas.edu. Disclaimer The views expressed in this paper are those of the authors and not necessarily of the authors’ organizations, the Na- tional Academy of Medicine (NAM), or the National Academies of Sciences, Engineering, and Medicine (the National Academies). The paper is intended to help inform and stimulate discussion. It is not a report of the NAM or the National Academies. Copyright by the National Academy of Sciences. All rights reserved. 95 Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. Authors: Siyan Yi, Esabelle Lo Yan Yam, Kochukoshy Cheruvettolil, Eleni Linos, Anshika Gupta and Latha Palaniappan Date: Nov. 25, 2024 From: Journal of Medical Internet Research(Vol. 26, Issue 5) Publisher: Journal of Medical Internet Research Document Type: Report Length: 5,168 words Lexile Measure: 1390L DOI: http://dx.doi.org.ezproxy.uio.no/10.2196/57612 Abstract: Digital health innovations have emerged globally as a transformative force for addressing health system challenges, particularly in resource-constrained settings. The COVID-19 pandemic underscored the critical importance of these innovations for enhancing public health. In South and Southeast Asia, a region known for its cultural diversity and complex health care landscape, digital health innovations present a dynamic interplay of challenges and opportunities. We advocate for ongoing research built into system development and an evidence-based strategy focusing on designing and scaling national digital health infrastructures combined with a vibrant ecosystem or “marketplace” of local experiments generating shared experience about what works in which settings. As the global digital health revolution unfolds, the perspectives drawn from South and Southeast Asia—including the importance of local partnerships—may provide valuable insights for shaping future strategies and informing similar initiatives in low- and middle- income countries, contributing to effective digital health strategies across diverse global health contexts. Full Text: Introduction The rapid development of digital health—encompassing technologies like mobile health (mHealth), telemedicine, digital health information systems, Internet of Things, machine learning and artificial intelligence (AI), personalized digital nudges, large language models, and generative AI—has ushered in a new era of health care possibilities [1]. Digital health technology has been proposed as an effective solution to address health care access, cost, and quality issues. While the promise of digital health is universal, the context in which it is applied varies across communities and regions. This viewpoint paper critically examines the diverse challenges and opportunities encountered in digital health innovations in low- and middle-income countries (LMICs), drawing on perspectives from the experiences of health systems in South and Southeast Asia, a vibrant and multifarious region. Just as many have highlighted the advantages of a “human-in-the-loop” approach to AI, we emphasize the potential benefits of a “researcher-in-the-loop” approach to digital health innovations in LMICs. This approach aims to ensure objective evaluation, continuous improvement, and effective dissemination of successes and failures, ultimately enhancing patient outcomes while reducing disparities, costs, and the burden and burnout of health professionals. A trilateral team comprising policy makers, researchers, and development partners can expedite the identification and dissemination of best practices across different LMIC settings. Additionally, 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...1/9 96 partnering with trusted global organizations or catalytic funders—such as the Bill & Melinda Gates Foundation (BMGF), National Institutes of Health Fogarty International Center, Abdul Latif Jameel Poverty Action Lab, and the International Initiative for Impact Evaluation—can provide essential resources to low-resource settings, mitigate risks during the initial adoption phase, and support adapting interventions to the local context before scaling up to larger populations. This collaboration also helps build a regional or global “toolkit” of use cases and experiences that can benefit other LMICs [2]. The following sections will first articulate our analytic framework and examine the foundational elements of digital health innovations, focusing on their architecture, standards, and issues related to privacy and security. Next, we will explore the digital health solutions marketplace in South and Southeast Asia, emphasizing the importance of local community partnerships and the need for a continuous cycle of learning and improvement through impact evaluation, research, and development. We emphasize the need for cultural sensitivity and prioritizing equity to ensure that digital health solutions are effectively adapted to local contexts. Improving the Social Net Benefit From Digital Health Innovation: Analytic Framework Our analytic framework considers balancing the social benefits of digital health innovations with the social costs of adoption, recognizing (1) the positive spillovers from evidence generation and (2) the opportunity costs of not adopting innovations that might otherwise have improved health and equity at affordable cost. Critically, the social benefits should consider the incremental global public good of collecting evidence and experience about what works in diverse local settings. If these spillover benefits for other LMICs are ignored, resource constraints will lead to underinvestment in digital health innovation for low-resource communities. To leverage additional resources to align with social benefit (to internalize this externality, in economics jargon), partners can support local experimentation and evidence generation. Regional or global partners can help leverage existing technology platforms and standards to generate economies of scale and global public goods. Cutting-edge applications can be tailored and redeployed in multiple low-resource settings, allowing LMICs to decrease implementation costs, foster the development of reusable tools and methodologies, and nurture culturally relevant communities of practice. To balance social benefit and cost while taking account of these spillovers, ongoing research should be built into system development. We advocate for a 2-pronged top-down and bottom-up innovation approach: an evidence-based strategy focusing on designing and scaling national digital health infrastructures combined with a vibrant ecosystem or “marketplace” of local experiments generating shared experience. Importantly, evidence about failures and successes is essential to reduce the costs of deploying ineffective strategies. This dual approach of top-down design and bottom-up experimentation, enabled through careful evaluation of effectiveness and impact, allows economies with different starting conditions to seize opportunities to “leapfrog” toward more robust, resilient health systems fitting their contexts rather than imitate the development path of any given current high-income country or region. This theoretical framework emphasizes that the incremental social net benefit of digital innovations depends critically upon the “starting point” and desired “end point”—both of which rely on local context and require local partner input to accurately assess benefits and costs. For example, the starting point for any “leapfrog” in technology may differ in light of significant technological disparities—“the digital divide.” Despite the rapidly advancing technological landscape in LMICs, substantial disparities in digital access and digital literacy persist. Across South and Southeast Asia, less than half of the population in Myanmar uses the internet, and only 2% of people in Cambodia and the Lao People’s Democratic Republic have a fixed broadband subscription compared to an average of 4% in LMICs [3]. Cambodia has low digital literacy [4], whereas in countries like Singapore, digital literacy and technology use are relatively high, even among older adults [5]. Digital literacy can impact one’s ability and attitude toward using digital technology [5,6]. The scarcity of technological resources in LMICs can also hamper the introduction, adoption, and integration of digital health interventions into the broader health 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...2/9 97 system and compound existing inequities in access to health care, potentially exacerbating disparities in health outcomes [7,8]. Yet, we emphasize that the incremental benefits of digital technologies could be significant— even transformational—in LMICs. By providing access to quality care in remote settings, the incremental benefits could be considerably higher than in high-income health systems if sufficient oversight and stewardship uphold the tenet “First, do no harm.” The ethical complications of denying access to the social value of digital health innovations cannot be ignored. Local partnerships can reduce the social costs of developing appropriate digital technologies and enhance their social benefits by creating trust for engagement and evidence aligned with local community goals. To emphasize the net benefit of understanding existing traditions or policies before attempting to change them, we use the concept of “Chesterton’s Fence” based on the writer Chesterton [9]: “If you come across a fence blocking a road and do not know why it was built, you should not remove it until you understand its purpose.” Digital health innovations should not blindly “leapfrog” Chesterton’s Fence: reforms or changes should not be made until the reasons for the current situation are fully understood. Incorporating historical knowledge and avoiding hasty or uninformed decision-making can enhance the net social value of changes. For balancing the social benefits and costs of digital health innovation, Chesterton’s Fence suggests the importance of actively involving local communities, respecting local decision- making processes, and partnering with local governments, nongovernmental organizations (NGOs), and other stakeholders to tailor proposed solutions to the cultural, economic, and environmental context. Implementing small-scale pilot projects can provide valuable insights, allowing for adjustments before broader application, considering both the direct and indirect consequences for the community. Moreover, the social benefits and costs should be measured over a forward-looking time frame, not limited to short-term results. Sustainable change often requires investments in local skills and institutions to ensure long-term effectiveness. Patience and persistence are vital in these efforts to harness the potential of digital technology to improve the health of disadvantaged individuals and communities. Ongoing evaluation and willingness to adapt strategies based on feedback are critical for maximizing the social net benefit of digital health innovations. Data Architecture, Standards, Privacy, and Security For digital health technology to have a long-lasting impact on health systems, technology must be developed around an extensible architecture that can be efficiently scaled for new use cases and apps. While we are at the very early stages of technology adoption, it is essential to understand how critical these foundational concepts are to a proper digital solution for health care. An essential aspect of this adaptable architecture is incorporating data governance to facilitate the development of use cases and technology deployment. Electronic medical records have been used to streamline patient data management and improve health care service delivery, exemplifying digital health’s potential to improve health care efficiency [10]. The Indonesian and Singaporean governments are making electronic medical records accessible to the population [11,12], while an electronic information registry for routine immunization is being introduced in Cambodia and the Lao People’s Democratic Republic. However, with specific data standards for organization and sharing, data elements may be digitally exchanged between clinical systems. The process of exchanging digital information is known as interoperability. Most high-income countries have either implemented or are in the process of introducing legislation mandating interoperability [13]. However, many legacy health information technology solutions are designed primarily for providers, hospitals, or clinics, which supports organizational goals but presents challenges for data sharing and exchange as patients move across different providers. In contrast, only some LMICs have achieved comparable levels of interoperability. Nevertheless, 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...3/9 98 LMICs may have the most promising opportunities to “leapfrog” older standards by directly adopting a patient-centered data architecture. Rather than developing a data architecture that mirrors the health ministry organizational chart, policy makers should consider technology solutions centered on patients, such as personal health records. In Singapore, the government has launched the Next Generation Electronic Medical Record system to consolidate data and harmonize processes across health establishments, including private care providers, providing a longitudinal view of patient’s health data [14]. Such efforts to integrate digital health solutions into existing health care frameworks hold promise in optimizing resource allocation and health care delivery. Mobile phones have greatly facilitated personal health records but could include cloud-based models or an innovative blockchain model such as that used in Estonia [15]. Personal health records could have distinct advantages for patients, such as having patient records available when making clinical decisions. Launched in 2021, India’s national Ayushman Bharat Digital Mission (ABDM) was built based on a decade of digitalization experiences in the national identity system, personal digital records, and payment systems (Figure 1[16-19]). ABDM uses the Ayushman Bharat Health Account as a digital health identity number that can be shared freely while keeping the underlying information secure. Over 268,000 health professionals have been included in the national registry, irrespective of the medical systems they practice. More than 229,000 health facilities have been registered with the facility registry [20]. A key lesson from India’s experiences with ABDM is building an integrated data ecosystem instead of disparate information systems. The integration will be crucial to support personalized health care and evidence-based policy making. The overall data architecture at a country or market level should also anticipate the interest in developing these tools and their challenges. Individual tools should anticipate updates to the overall data architecture and regulation at the country and market level. Apart from data architecture for storage and exchange, data standards vary across countries, leading to incomparability [21]. The same concept (eg, blood glucose) may be represented in various ways from one setting to the next. The World Health Organization has developed a data architecture to support countries’ capacity to collect, manage, analyze, and use health data from population-based sources such as household surveys and institutional sources such as health facilities [22]. Similarly, Digital Health Europe attempts to develop comprehensive data standards, including international patient summaries that provide primary medical data for supporting cross-border care [23]. The European case of regional harmonization is a model for regional organizations such as the Association of Southeast Asian Nations, a political and economic union of 10 Southeast Asian states, to work toward fostering data exchange and improving data comparability between countries. Finally, moving from paper to digital records raises the risk of data breaches and unauthorized access to sensitive health data, which poses ethical and legal dilemmas. Some countries have tightened regulations to increase protection. Singapore’s Personal Data Protection Act is a regulatory model for safeguarding personal health data [24]. In Thailand, Indonesia, and Vietnam, data protection was embedded in several laws before its personal protection law was passed in 2019, 2022, and 2023, respectively [25-27]. India has adopted the Digital Personal Data Protection Act, which empowers individuals and specifies requirements for any data fiduciary involved in handling personal data, as well as for the National Health Authority, which serves as a consent manager rather than a data repository [28]. India’s ABDM also includes a consent artifact that empowers users to decide how, when, where, and what record types they allow to be shared between one health provider and another (Figure 2). However, inadequate data protection regulations in some countries risk the security and privacy of health data [29], which could undermine individuals’ willingness to engage with digital health platforms. An example is the apprehension surrounding Indonesia’s new Health Bill, which allows for collecting and using health data, including genomic data, outside the country [30]. Clear 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...4/9 99 guidelines for data collection, storage, and sharing, along with measures to safeguard sensitive health information, are critical. These architectural elements are designed for 3 primary functions: interoperability of health records, interoperability of services through the unified health interface for all providers, and interoperability of health claims so that hospitals or other providers are manageable when dealing with multiple payers to submit claims. Together, these layers create a citizen-centric view of public health by building the infrastructure underpinning a vibrant ecosystem. Featuring 3 main exchanges—the Unified Health Interface, the Health Information Exchange consent manager, and the Health Claims Exchange—this system has succeeded in integrating more than 1280 different public and private apps and laying the foundation of digital health public infrastructure for ongoing public and private innovation (Figure 2). India continues to explore strategies to drive further adoption and social value. Figure 1. India’s digitalization policies, strategies, and experiences [16-19]. [Please download the PDF to view the image] Figure 2. India’s ABDM data architectural elements and underpinning services and features. ABDM: Ayushman Bharat Digital Mission; ABHA: Ayushman Bharat Health Account; API: application programming interface; UPI: Unified Payments Interface. [Please download the PDF to view the image] Marketplace—Digital Health Solutions The genuine excitement surrounding digital health care solutions stems not from data architecture but from the services they enable. Data architectures are not a final use case for a technology; they are merely an enabler of a broader digital health care services ecosystem. Digital services use an underlying data architecture to provide patient information, tools, reports, and recommendations. Digital services can be built on a standard data architecture or stand- alone solutions. The former requires a means to access and potentially update or add to the data, while the latter runs the risk of creating noninteroperable data silos. We advocate for adopting both approaches while systematically assessing the latter and designing in anticipation of interoperable solutions in the near future. Digital solutions must be tested to ensure they perform as expected, including concepts such as the user interface; data access, storage, manipulation, and reporting; and clinical validity. A vibrant ecosystem of apps shown to be effective in different settings, in turn, lays the foundation for a “marketing strategy” to disseminate and encourage the take-up of digital health solutions such as digital health records among individuals and organizations. Building the personal health report system means little if patients and providers do not engage. To drive meaningful adoption and use, the digital health ecosystem must create value for every player or stakeholder, fostering trust and spurring curiosity about the possibilities for more manageable, cheaper, higher quality, more accessible, and more resilient services. The patients and providers need evidence from use cases that improve their lives, transforming inertia and fear of new technology into excitement and fear of missing out. Digital solutions must also easily integrate into existing workflows and systems, reducing the barriers to uptake. For example, the Indian government started by ensuring that all the government programs, such as ABDM-enabled health and laboratory management information systems for government hospitals, are ABDM-enabled. Such deployment creates the demonstration space to study integration into existing workflows and make these low-cost “plug and play” solutions available to all participants so that even the smallest local provider need not invest much time and money to adopt them. While the goal is to avoid creating siloed platforms—an HIV platform, a TB platform, and so on— as much as possible, health systems may benefit from a vibrant ecosystem or “marketplace” of local apps and experiments generating shared experience about what works in diverse settings 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...5/9 100 to enhance access while reducing disparities. One noteworthy example from Southeast Asia comes from a recent randomized controlled trial that demonstrated the benefits of digital health interventions for accessing health care and support services among female entertainment workers, a social and gender-marginalized population in Cambodia [31]. The study used a mobile intervention to connect the vulnerable population to critical health and gender-based violence services, showcasing the transformative potential of digital health in addressing pressing societal challenges even without a national-level integrated digital health ecosystem. The potential of digital health to bridge geographical gaps, extend health care services to underserved populations, and support the health system in moving care from hospitals to communities is promising. In archipelagic countries like Indonesia and the Philippines, as well as in countries such as Cambodia, where 75% of the population lives in rural areas [3], digital health interventions such as teleconsultation can be used to improve health care accessibility. Digital health additionally holds potential in countries reliant on community health workers to bridge geographic gaps. For example, Accredited Social Health Activist workers in India, who are employed by the Ministry of Health and Family Welfare through India’s National Rural Health Mission, have successfully leveraged mHealth for disease surveillance and treatment in a country where low-cost smartphones are increasingly prevalent [32,33]. A mobile phone can be considered a valid medical device equipped with multiple sensors: a camera, a microphone, a screen, a global positioning system, and data. Organizations like BMGF are working with local partners to develop apps leveraging the ubiquity of mobile phones to enhance care in low-income settings, such as scanning to assess a newborn’s anthropometrics and monitor malnourishment. mHealth has been proven effective to varying degrees in health education, disease screening, and linkages to care and treatment services [34- 38], while wearable devices can increase physical activity and improve health [39], and Internet of Things–enabled systems can support community eldercare [40]. An app for counseling women about contraceptive methods showed that for the informed adoption of unfamiliar technologies, personalized information could be just as effective and far cheaper than subsidies [41]. The power of social media as a platform for health education also holds considerable promise both for large-scale public health campaigns and specifically tailored interventions that are culturally sensitive and build on trusted community figures or institutions [42]. AI has demonstrated significant potential in supporting precision health, including the use of large language models and generative AI for diagnosing complex medical conditions [43]. For example, integrating a deep learning algorithm into Thailand’s national diabetic retinopathy screening program has shown that this system can provide real-time detection of diabetic retinopathy with accuracy comparable to that of retina specialists in community-based settings [44]. AI-enabled solutions for precision public health extend beyond diagnostics to clinical decision support and health care delivery, particularly in low-resource settings where staffing, training, funding, and equipment are often limited. While AI solutions may rely on effective collaboration with academic and industry partners, NGOs can also play a crucial role in data acquisition and technology adoption, as detailed in the following section [45]. Ultimately, digital health solutions aim to augment, not replace, the services provided by frontline health workers—we need to avoid the “Turing Trap” [46] and focus on innovations that augment the social value created by the existing health workforce. In the most recent and rigorous studies, generative AI and related technologies tend to boost the productivity of new and less- experienced health workers more than their more-experienced counterparts [47]. The potential for AI and other digital health assistants to upskill and extend the limited health professional resources of LMICs underscores the social value of experimenting and assessing real-time effectiveness without waiting for the design of national architecture where it is lacking. Digital health innovation also needs to consider the financing levers in both the public and private sectors to understand the feasibility of adopting and scaling up digital health interventions. A private philanthropy like BMGF can provide catalytic funding to derisk the technology early and gather evidence about what works in practice before turning over implementation at scale to 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...6/9 101 governments and civil society. For example, BMGF successfully helped deploy a platform developed in India in 2 other countries, Cambodia and Nigeria [48,49]. Using technologies to support health system strengthening through health financing also holds promise for increasing health care efficiency, accountability, and transparency [50]. Digital technologies have been used to collect health insurance premiums and taxes through mobile wallet services, support pay-for- performance strategic purchasing models, and raise awareness of benefit packages and cost schedules [50]. Local Partnerships for Successful Digital Health Implementation The architecture on which digital technologies are built may be universal, but the services they provide must be localized to address local needs and be sufficiently engaging to promote adoption. One example of the importance of tailoring digital health innovations to the local context comes from maternal and child health in India [51]. Many Indians, especially in rural areas, are not born in their parents’ houses or even their parents’ towns but rather in their maternal grandparents’ houses or communities. Typically, in the third trimester of pregnancy, the pregnant woman will move to her parents’ house, and the baby will be born there. Since the third trimester is a critical time for the mother and child, customized software supported by the BMGF alerts community workers to gather 2 addresses for each pregnant woman and then sends an alert to the maternal grandparents’ community in the third trimester. This allows for follow-up care and management continuity, ensuring that health care workers in each jurisdiction are aware of incoming cases, thereby reducing the number of pregnant women lost to follow-up at this critical time. Local champions and partnerships are critical in providing cultural nuances, context, and advocacy, and in some instances, in creating a network of users and customers for realizing the full social benefit of digital technologies. NGO Arogya World led one example of local champions and partnerships enabling successful digital health implementation in India. Arogya World has developed and implemented several diabetes prevention programs that have successfully incorporated digital tools. Their program mDiabetes, a text messaging intervention delivering diabetes education, significantly improved health behaviors and nutrition [52]. The Healthy Schools Program, a school-based intervention targeting 11- to 14-year-olds, incorporated digital curricula in light of the COVID-19 pandemic. Healthy Schools Program achieved a broader reach through digital campaigns, yielding notable gains in knowledge about diabetes, its risk factors, and behaviors spanning nutritious food consumption and physical activity. Another example comes from the NGO Noora Health, which has successfully leveraged digital health across India, Bangladesh, and Indonesia to improve access to caregiver training using multimedia. Successful features of their programs include mobile chat services and digital curricula integrated into comprehensive care delivery models that use local health care systems. Through meaningful technology adoption and partnerships with local governments, policy makers, and community health workers, NGOs like Arogya World and Noora Health are well- poised to launch large-scale public health campaigns that cater to increasingly technology-savvy populations. Local partnerships are crucial in successfully implementing community-based digital health interventions, as evidenced by the Mobile Link and i-MoMCARE projects in Cambodia. Led by the Khmer HIV/AIDS NGO Alliance, a leading local NGO, the Mobile Link used a participatory approach to involve representatives of the female entertainment worker community, civil society organizations, and policy makers in formative studies and intervention development, implementation, and evaluation [31]. This partnership with local stakeholders has significantly increased access to services and improved health outcomes in the target population. Similarly, i- MoMCARE leverages primary health care providers, community health workers (known as village health support groups in Cambodia), a local university, and the national maternal and child health program to provide maternal and child health education and reminders via a mobile app [49]. This enables real-time data collection and personalized care plans, ensuring timely antenatal, delivery, and postnatal care for mothers and children in rural Cambodia. These partnerships 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...7/9 102 facilitate trust, cultural relevance, and sustainability, ultimately enhancing the effectiveness and reach of digital health technologies. Additionally, the involvement of trusted and reliable local sources of information improves the credibility and acceptance of these digital health interventions. A rigorous impact evaluation is part of the design for i-MoMCARE so that this experience can contribute evidence sound for other low-resource settings globally. Local champions and advocates provide the social legitimacy necessary for the adoption and effective use of digital technologies for health and well-being. This is particularly important in the realm of AI, where apps still need to be thoroughly tested at the population level and where security breaches have undermined public confidence. In some contexts, these technologies could even be seen as tools for surveillance and propaganda. Social legitimacy thus seeds the trust required for the adoption and effective use of the technology. For example, a large-scale randomized controlled trial in West Bengal, India, found that SMS text messages from West Bengal native and 2019 Nobel laureate Abhijit Banerjee doubled the reporting of health symptoms to community health workers and had other positive spillover impacts on their communities [53]. This example illustrates the power of communication technology and potentially social media as platforms for health education and public health information for large- scale campaigns and specifically tailored interventions that build on trusted community figures or institutions. Digital Health Innovations—A Cycle of Learning and Improvement The rapid proliferation of digital health technologies requires rigorous research and impact evaluation to generate the evidence to assist LMICs in identifying the most effective strategies. Mobile phones and their voice and AI apps provide many opportunities to enhance individual health knowledge and deliver helpful information. They also call for careful ongoing research to address inappropriate advice or information concerns. For example, standard smartphone voice systems (eg, Siri or S Voice) have failed to recognize issues about mental health, interpersonal violence, or physical health [54]. The accuracy of AI-generated information about diabetes is also questionable [55]. Many ethical issues need to be addressed when adopting monitoring devices or contactless sensors and contact-based wearable devices installed in health care settings, otherwise called “ambient intelligence,” to collect data in health and elderly care [56]. AI or machine learning also relies on models that require significant amounts of data for development and attention to the potential errors introduced by data that may be flawed or biased [57]. Validation of the models across health care markets and populations is essential [58]. Digital health research requires an interdisciplinary team of researchers in public health, data science, information technology, social sciences, and engineering. Researchers must work with policy makers and end users such as health care professionals, communities, and individuals in designing interventions that are problem- or need-driven and set in the broader policy environment. The principle of equity must guide the innovation cycle to prevent inadvertently deepening health disparities through underdiagnosis and undertreatment of individuals historically with limited access to care or who face biases due to language, race, or education. For example, using medical spending to predict medical needs can result in significant racial bias [59]. Strategies to reach marginalized populations, including migrants and underserved communities, are imperative. Initiatives such as using mobile phones to deliver health information to key HIV population communities in Cambodia reflect a commitment to advancing health equity [31,60]. In addition, ensuring that participants comprehensively understand the implications of digital health research, especially in linguistically and culturally diverse contexts, is paramount. Countries in the region have taken steps to develop culturally sensitive informed consent processes to uphold ethical standards and respect individuals’ autonomy [30]. The digitization experience of the banking and financial industry in the region can also offer valuable lessons for digital health research and interventions. The banking sector has learned that retaining a human touch in the technological interface with customers is essential [34]. In some countries where public health services have been underused due to the lack of trust in the system, the 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...8/9 103 introduction of digital health interventions must be carefully designed to instill confidence in the intent, quality, and integrity of the technology [35]. Retaining a human element in digital health interventions could be one way to instill confidence. The key to success will be alacrity in the stewardship of health sectors to address priority population health needs and improve equity. Policies should support the generation of evidence assessing digital health apps so that patients, providers, and policy makers can ask and answer the right questions in a suitable time frame to enable a virtuous cycle of learning and improvement. In LMICs, where governments lack resources to try many new things, private philanthropy can bring resources, take the risk, and generate evidence about “what works” and scalability. While some may perceive the term “leapfrogging” as imposing a development paradigm that prioritizes Western values and homogenizes diverse cultures, we suggest that each culture and economy may choose its leapfrog developmental path tailored to its unique circumstances. Although space limitations preclude a full exploration of alternative development models within this brief perspective piece, future research should prioritize an in-depth discussion of related theories and evidence. This includes conducting cost-benefit analyses of heterogeneous digital health interventions across LMIC contexts. Conclusions Digital health programs and research in South and Southeast Asia illustrate that innovation can deliver a social net benefit to communities while generating positive spillovers for other LMICs based on a comprehensive understanding of technological, cultural, and ethical dimensions of the intervention and community context. While technological challenges persist, opportunities for supplementing traditional health care, strengthening health systems, and enhancing epidemic preparedness hold promise. At the current unprecedented time in humanity’s digital transformation, these discussions are topical and urgent. Ethical considerations underscore the importance of equitable access, cultural sensitivity, robust data governance, and partnering with local communities. Collaborative efforts among researchers, policy makers, health care professionals, and civic organizations or other community representatives within and outside the health sector will be instrumental in harnessing digital health’s potential to improve health outcomes and promote health equity in LMICs. Copyright: COPYRIGHT 2024 Journal of Medical Internet Research http://www.jmir.org/ms/index.php Source Citation (MLA 9th Edition) Yi, Siyan, et al. "Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia." Journal of Medical Internet Research, vol. 26, no. 5, 25 Nov. 2024. Gale Academic OneFile, dx.doi.org.ezproxy.uio.no/10.2196/57612. Accessed 6 Jan. 2025. Gale Document Number: GALE|A817675046 06/01/2025, 11:55Perspectives of Digital Health Innovations in Low- and Middle-Income Health Care Systems From South and Southeast Asia. ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=dbdc18...9/9 104 npj | digitalmedicineComment Published in partnership with Seoul National University Bundang Hospital https://doi.org/10.1038/s41746-024-01279-2 India’s evolving digital health strategy Aditya Narayan, Indu Bhushan & Kevin Schulman Check for updates India’s evolving digital health strategy leverages innovative technologies to enhance access to healthcare services. This paper explores the key components of India’s digital health transformation, including the Ayushman Bharat Digital Mission (ABDM) and India’s integration of biometric identification and digital infrastructure to improve healthcare delivery. The lessons learned from India’s large-scale implementation of digital health provide valuable insights for global health markets and digital transformations in healthcare systems. India’s healthcare landscape is a vast and interdependent network com- prising both public and private sectors, with each playing distinct roles in delivering medical servicesto its 1.4 billion population 1 .Thepublic healthcare system is designed to offer free or low-cost services for low- income and rural populations. However, these public facilities are often overwhelmed as a consequence of inadequate infrastructure, shortages of medical supplies, and a paucity of healthcare professionals 2 .Thisgap between supply and demand for healthcare services is exacerbated in rural areas where nearly 71% of the population resides but where only one-third of the country’sphysiciansarelocated 3–5 . The recognition that fragmented governance and unequal access to healthcare were major impediments to achieving equitable health outcomes led to the drive for a cohesive national health strategy. The concept of Universal Health Coverage (UHC) became central to India’s healthcare policy, aiming to ensure that all citizens, regardless of income or location, have access to necessary health services without facingfinancial hardship. This push for UHC led to the development of the National Health Policy (NHP) in 2017, which laid the groundwork for leveraging digital technol- ogies to strengthen the healthcare system 6 .Specifically, the National Health Policy of 2017 aimed to achieve universal health coverage by increasing access to quality healthcare services, reducing the cost of healthcare, and leveraging digital technologies to enhance the efficiency of service delivery. The Pradhan Mantri Jan Arogya Yojana (PM-JAY), launched in 2018 as part of this policy 6 .PM-JAYisaflagship health insurance scheme providing coverage of up to INR 5 lakhs per family per year for secondary and tertiary care hospitalization (approximately USD 6000), targeting the bottom 50% of the population by income, or approximately 500 million people 7 . As the strategy developed, policymakers envisioned a significant role for digital innovation as a means of supporting the overall healthcare strategy. The foundation for this insight was known as“Digital India”—the moniker of an evolving federal government strategy aimed at deploying technology to address the chronic economic and social challenges of India’s diverse population. The technological backbone of Digital India is the India Stack, which began in 2009 to digitize government andfinancial services. India Stack had four key components: a digital identification system for all citizens, unified interoperable transactions between individuals and busi- nesses, digital document verification, and the scaffolding regulation sur- rounding consent in data sharing 8 . The digital identification system, Aadhaar, offers a unique 12-digit biometric ID to 1.3 billion people and could be leveraged to ensure the fidelity of public services. Based on these digital identities, the Pradhan Mantri Jan Dhan Yojana (PMJDY) was launched to provide a virtual bank account to all Indian citizens free of cost to bring the most underserved citizens into the formal economy 9 . Together, these systems have facilitated the creation of over 510 million bank accounts and integrated over 98% of the population into Aadhaar 10 . Building upon this foundation, the Unified Payments Interface (UPI) was established. UPI provided a secure and interoperable digital infrastructure that could facilitate instant fund transfers via smartphones, leading to 117 billion transactions in 2023 alone 11 .This system overcame common obstacles such as a lack of interoperability between public, private, and retail payment systems as well as geographic barriers to transferring funds for small businesses. As a consequence of this elegant infrastructure, innovation in thefinancial markets continues to developatarapidpace. Digital health care On the foundation of this success, the government of India turned to the health sector and committed to“a paradigm shift from the existing silo systems to a holistic and comprehensive health eco-system, founded on the latest digital architectures and technologies”. 12 The development of India’s digital health strategy began with a global survey of best practices, in an effort to“leapfrog many of the traps that bedevil health information systems even in developed economies”. 12 The United States’HITECH Act, for example, highlighted the importance of a cohesive data architecture and interoperability. The UK’sNHSDigital illustrated the importance of developing and deploying integrated digital health platforms that ensure data privacy while enabling efficient health information exchanges. South Korea’s approach to integrating personal health records with national identifiers and Singapore’s“One Patient, One Health Record”modeloffered lessons on the value of ensuring patient access to their health data for enhancedcare coordination and privacy. Drawing from these global models, India launched the ABDM in 2021 with a focus on creating a secure, integrated digital health ecosystem that emphasizes personal health records, ensuring that each citizen’shealthdata is accessible, interoperable, and under their control. This ambitious project introducedfive key innovations designed to enhance the delivery and management of healthcare services across the nation. Central to the ABDM was a unique 14-digit health identifier for every citizen, the Ayushman Bharat Health Account (ABHA). Notably, the ABHA was primarily built upon Aadhaar (although other sources of identification are allowed) - India’s robust biometric identification system, leveraging its technological underpinnings to securely authenticate and manage health records. TheABDMmobileapplicationprovides individuals with an accessible electronic personal health record (PHR) that adheres to national inter- operability standards. Unlike traditional Electronic Medical Records npj Digital Medicine| (2024) 7:284 1 1234567890():,;1234567890():,; 105 architectures, the PHR is managed, shared, and controlled by the patient themselves with the ability to make records visible or invisible to providers. This architecture is a unique feature of the ABDM program. The Healthcare Professionals Registry and Healthcare Facilities Reg- istry catalog enrolled healthcare professionals and facilities nationwide. By creating standardized, accessible databases of healthcare providers and institutions, the ABDM facilitated easier verification and provider cre- dentialing processes, which in turn helped patients make more informed choices about their healthcare. Finally, the Unified Health Interface is the patient-facing platform supporting healthcare transactions. It was designed as an“open protocol for various digital health services,”including, but not limited to, appointment bookings, teleconsultations, and patient service delivery. Its open network structure allows for the integration of End-User Applications—such as data from health apps used by patients—and Health Service Provider applica- tions—digital tools used by hospitals, clinics, and laboratories to manage patient data or facilitate operations. Of note, the ABDM concept was conceived as a catalyst for private investment in the digital health sector. Accordingly, ABDM has put in place a“digital sandbox”that provides access to APIs from ABDM registries to private sector digital application developers aimed at providing novel ser- vices for patients and providers. To date, ABDM has integrated over 1,000 private companies into the ecosystem 13 . Examples include diagnostics companies that allow patients to link lab results (e.g., TB tests, blood tests, urine drug screens) with their ABHA records.Further,arangeofHospital Management Information Systemsallow hospitals to link patients’ABHA records to data management platforms, which offer monitoring of patients’ health status, secure telemedicine channels, organized appointment book- ings, and other“quality of life”upgrades. Scale and adoption The COVID-19 pandemic served as a catalyst for the ABDM, accelerating the deployment of digital health technologies. A prime example of this acceleration is the CoWIN platform, a federal digital platform designed to facilitate the registration, scheduling, and management of COVID-19 vaccinations for citizens. Alongside this platform, a mobile health applica- tion, Aarogya Setu, emerged as a means of conducting remote COVID-19 contact tracing 13 . ABHA numbers were created rapidly through the CoWIN initiative, leading to 130 million new accounts while ensuring efficient record keeping 14 . For patients, the ability to readily access personal health records allowed for rapid verification of vaccination status, exemplifying the potential of digital tools in managing public health emergencies 14 . As of March 2024, the country has seen the creation of 568 million ABHA accounts and the integration of over 350 million health records into the digital ecosystem 13 .Theprogram’s reach, encompassing over 230,000 health facilities and 285,000 registered providers, underscores the scale of the effort 14 . Telemedicine has evolved alongwiththeABDMprogram.The eSanjeevani telemedicine platform,launched by the Ministry of Health and Family Welfare in 2019, facilitated over 270 million teleconsultations as of August 2024 15 . eSanjeevani was initially designed for physician-to-physician consultations, facilitating collaborative care. However, in response to the COVID-19 pandemic, it expanded rapidly into a physician-to-patient ser- vice, known as eSanjeevani OPD (outpatient). Notably, eSanjeevani scaled healthcare delivery during the pandemic, with 57% of beneficiaries being female and 12% senior citizens 15 . The second phase of this effort, eSanjee- vani 2.0, integrates information from Point of Care Diagnostic devices for rapid diagnosis. Challenges in implementation. One of the most persistent challenges to the scale-up of India’s digital healthcare ecosystem is the uneven techno- logical and infrastructural landscape across the country. While urban areas have largely benefited from improved connectivity and digital literacy, rural regions continue to struggle with limited access to the internet and necessary IT infrastructure 16 . Although there are over 400 million internet subscribers in rural areas as of 2024, the quality and reliability of this connectivity often fall short of what is needed to sustain robust digital health services 17 . Data privacy and security concerns also loom large over the adoption of ABDM 18 . The digitalization ofhealth records necessitates stringent data Table 1 | Barriers and Facilitators of ABDM Adoption FacilitatorsBarriers Governmental support and policy frameworksInfrastructure challenges Public initiatives like the Digital India campaign and Ayushman Bharat Digital Mission (ABDM) Limited internet connectivity and digital infrastructure, particularly in rural areas Variations in access to electricity and other essential services Robust digital infrastructureRegulatory challenges The success of Aadhaar as a biometric identification system, laid the foundation for unique digital identification Complexities in enforcing data privacy and security across India’s diverse and federated healthcare system Unified Payments Interface (UPI) facilitating securefinancial transactionsChallenges with cross-border data transfers under the Digital Personal Data Protection Act (DPDPA) Public–private partnershipsDigital literacy and socio-cultural barriers Incentives and collaborations between the government and private sector to innovate and scale Low levels of digital literacy, particularly in rural and underserved areas Development of user-centric digital health solutionsSocio-cultural preferences for in-person consultations over digital health services Patient empowerment and educationFinancial constraints Increased awareness and education on the benefits of digital health toolsHigh costs associated with establishing and maintaining digital health tools like EHRs Tools such as personal health records (PHRs) enable patient control over health data Limited public health spending (1–2% of GDP), which hampers widespread adoption npj | digitalmedicineComment npj Digital Medicine| (2024) 7:284 2 106 protection measures to safeguard sensitive patient information, particularly given the scale of ABDM. To this end, the Digital Personal Data Protection Act (DPDPA) of 2023 represents a step forward in India’s efforts to regulate the processing of personal data and ensure data privacy 19 . While the Federal government has direct control over thefinancial sector and could implement the India Stack strategy, the responsibility for oversight of the health sector is a state responsibility. The states of Andhra Pradesh and Karnataka have made notable progress in the adoption of ABDM.Karnataka,inparticular, has seen higher engagement from private healthcare centers, offering valuablelessons on provider onboarding and navigating provider concerns regarding increased accountability 14 .A summary of facilitators and barriers to ABDM may be seen in Table1. Looking forward The ABDM is an exciting initiative for India and offers a vision for a national digital health architecture. Importantly, after assessing the utilization of electronic health records in the USand globally, India has made significantly different strategic choices on how a digital health strategy can be accom- plished. Specifically, the backbone of their strategy is the development of a set of unique patient identifiers, and the implementation of a personal health record architecture to collect data and provide digital health services for patients. This massive experiment at scale should provide important insights into the digital transformation of the United States and global healthcare markets. Aditya Narayan 1 , Indu Bhushan 2 & Kevin Schulman 1,3,4 1 Stanford University School of Medicine, Stanford, CA, USA. 2 India National Health Plan, New Delhi, India. 3 Clinical Excellence Research Center, Stanford University, Stanford, CA, USA. 4 Graduate School of Business, Stanford University, Stanford, CA, USA. e-mail:Kevin.Schulman@Stanford.edu Received: 25 April 2024; Accepted: 18 September 2024; References 1. World Health Organization. India Data.World Health Organization. https://data.who.int/ countries/356(2023). 2. Balarajan, Y., Selvaraj, S. & Subramanian, S. V. Health care and equity in India.Lancet377, 505–515 (2011). 3. Pengpid,S.&Peltzer,K.Rural-urbanhealthdifferencesamongagingadultsinIndia.Heliyon10, e23397 (2024). 4. Banerjee, S. Determinants of rural-urban differential in healthcare utilization among the elderly population in India.BMC Public Health21, 939 (2021). 5. Menon, G. R. et al. National Burden Estimates of healthy life lost in India 2017: an analysis using direct mortality data and indirect disability data.Lancet Glob. Health7, e1675–e1684 (2019). 6. Ministry of Health and Family Welfare.National Health Policy 2017. https://mohfw.gov.in/sites/ default/files/9147562941489753121.pdf(2017). 7. Bajaj Finserv. Ayushman Bharat—Pradhan Mantri Jan Arogya Yojana (PMJAY).Bajaj Finserv. https://www.bajajfinserv.in/insurance/ayushman-bharat-yojana(2023). 8. IndiaStack. IndiaStack—Technology for 1.2 Billion Indians.India Stack. https://indiastack. org/ (2023). 9. Government of India. PM Jan Dhan Yojana.PMJDY. https://pmjdy.gov.in/(2021). 10. Aadhaar Dashboard.UIDAI. https://uidai.gov.in/aadhaar_dashboard/index.php(2023). 11. NationalPaymentsCorporationofIndia. UPIProductStatistics.NPCI. https://www.npci.org.in/ what-we-do/upi/product-statistics(2023). 12. Ministry of Health and Family Welfare. Final Report on National Digital Health Blueprint (NDHB). https://main.mohfw.gov.in/sites/default/files/Final%20Report%20-%20Lite%20Version. pdf (2019). 13. National Health Authority. Aarogya Setu: COVID-19 Contact Tracing and Self-Assessment Mobile App.Ministry of Health and Family Welfare.https://www.mohfw.gov.in/aarogyasetu. html (2022). 14. ABDM-Insights.National Health Authority. https://dashboard.abdm.gov.in/abdm/(2024). 15. eSanjeevani.Ministry of Health and Family Welfare. https://esanjeevani.mohfw.gov. in/#/(2024). 16. Campanozzi, L. L. et al. The role of digital literacy in achieving health equity in the third millennium society: A literature review.Front Public Health11, 1109323 (2023). 17. Roy, A. How India is using the Internet. Economic Times. https://economictim es.indiatimes. com/tech/technology/how-india-is-using-the-internet/articleshow/108354854.cms?from= mdr (2024). 18. Sharma, R. S., Rohatgi, A., Jain, S. & Singh, D. The Ayushman Bharat Digital Mission (ABDM): making of India’s Digital Health Story.CSI Trans. ICT11,1–12 (2023). 19. Government of India. Digital Personal Data Protection Act 2023.Ministry of Electronics and Information Technology. https://www.meity.gov.in/writereaddata/files/Digital%20Personal% 20Data%20Protection%20Act%202023.pdf(2023). Acknowledgements The authors wish to thank Krishna Reddy MD of Access Health India and Suhel Bidani of the Bill and Melinda Gates Foundation for their help in collating data for this article. No specific funding was received for this work. Author contributions A.N. conceived the paper idea, conducted the primary writing, and contributed to the analysis of available data and policy documentation. I.B. provided policy expertise, specifically regarding the National Health Plan and universal health coverage, and contributed to critical revisions of the paper. K.S. supervised the project, provided strategic guidance on the content, and critically revised the paper. All authors (A.N., I.B., K.S.) have read and approved thefinal version of the paper. Competing interests The authors declare no competing interests. Additional information Correspondenceand requests for materials should be addressed to Kevin Schulman. Reprints and permissions informationis available at http://www.nature.com/reprints Publisher’snoteSpringerNatureremainsneutralwithregardtojurisdictionalclaimsinpublishedmaps and institutional affiliations. Open AccessThis article is licensed under a Creative Commons Attribution-NonCommercial- NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence,and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visithttp:// creativecommons.org/licenses/by-nc-nd/4.0/ . © The Author(s) 2024 npj | digitalmedicineComment npj Digital Medicine| (2024) 7:284 3 107 DOI: 10.1002/hcs2.67 COMMENTARY Inception of the Indian Digital Health Mission: Connecting...the...Dots Gerard Marshall Raj 1,2 |Sathian Dananjayan 3 |Neeraj Agarwal 4 1 Department of Pharmacology, All India Institute of Medical Sciences (AIIMS) Bibinagar, Hyderabad, Telangana, India 2 Hospital Management Information System (HMIS), All India Institute of Medical Sciences (AIIMS) Bibinagar, Hyderabad, Telangana, India 3 School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu, India 4 Department of Community and Family Medicine, All India Institute of Medical Sciences (AIIMS) Bibinagar, Hyderabad, Telangana, India Correspondence: Gerard Marshall Raj, Department of Pharmacology, All India Institute of Medical Sciences (AIIMS) Bibinagar, Hyderabad 508 126, India. Email:drgmr1111@gmail.com Funding information None 1 | NATIONAL DIGITAL HEALTH MISSION (NDHM): THE BEGINNING Ever since the National Health Policy, 2017 was released, the drive to digitalize the Indian healthcare system has been given more importance, in line with the United Nations' Sustainable Development Goals (SDGs). The Policy empha- sizes the implementation of digital health in all levels of care—primary, secondary, and tertiary—to maintain the continuity of patient care. The application of digital technology tools and their integration in all facets of healthcare services is expected to improve the functional efficiency and outcomes of the Indian healthcare system [1]. The National Digital Health Blueprint (NDHB) was placed in the public domain after relevant stakeholder comments were incorporated [2]. The NDHB lays the foundation for how to proceed with the digitalizing process throughout the country [3]. More specifically, the proposed NDHM aims to break the existing internal barriers in the digital healthcare system. The National Health Authority (NHA) [4] is the apex body entrusted with the mandate for implementation and management of the NDHM across the country. The NDHB envisages the following 5‐year action plan: planning and stabilizing the NDHM (Year 1); establishingtheprerequisiteinfrastructure(Year2);execu- tion (Year 3); analytics and innovation (Year 4); and sustenance and research (Year 5) [3]. In 2018, the National Institute for Transforming India (NITI Aayog) proposed digitalizing the Indian healthcare system through the National Health Stack (NHS) [5]. The NHS was formulated with the following key foundational components of the national digital health initiative: National Health Electronic Registries, a Coverage and Claims platform, a Federated Personal Health Records (PHR) Framework, a National Health Analytics Frame- work, and others. The NHS was orchestrated in such a way that the national digital infrastructure would be utilized by all parties—central and state governments, and public and private players. The multiple components of the NHS were later transformed and configured into the NDHM. Health Care Sci. 2023;2:345–351.wileyonlinelibrary.com/journal/hcs2 | 345 This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. © 2023 The Authors.Health Care Sciencepublished by John Wiley & Sons Ltd on behalf of Tsinghua University Press. Abbreviations:ABDM, Ayushman Bharat Digital Mission; EHR, Electronic Health Records; EMR, Electronic Medical Records; HFR, Health Facility Registry; HPR, Healthcare Professionals Registry; NDHB, National Digital Health Blueprint; NDHM, National Digital Health Mission; PHR, Personal Health Records; UHI, Unified Health Interface. 108 Healthcare in India, one of the most populous countries, requires connectedness among its different participants to sustain both essential and vital healthcare activities across the nation. Despite the intensification of the digitizing process in the health sector—like in any other industry—this process was primarily fragmented, and sharing of healthcare information across stakeholders was highly restricted, if not impossible at times [6]. However, the proposed digital ecosystem would be more transparent, connecting healthcare providers (doc- tors), healthcare seekers (patients), and healthcare facilities (hospitals, clinics, laboratories, pharmacies). Accordingly, the three different domains are the Health Facility Registry (HFR), the Healthcare Professionals Registry (HPR), and the Unified Health Interface (UHI) (Figure1)[7, 8 ]. The HFR and HPR are the twin core building blocks of the NDHM. The HFR is a comprehensive and all‐ inclusive data repository of healthcare facilities, includ- ing hospitals, clinics, diagnostic laboratories, pharmacies, health and wellness centers, mobile vans, and ambu- lances. The HPR encompasses healthcare professionals from all domains and all systems of medicine, including doctors, dentists, nursing professionals, paramedical staff, laboratory technicians, physiotherapists, midwives, community health workers, dieticians, and nutritionists. Each facility must designate a facility manager who can enroll and register their facility. Once registered, a Health Facility ID (FID) is generated [7, 8 ]. As of April 2023, more than 200,000 health facilities have been registered in the HFR. Healthcare professionals can link their Healthcare Professional ID (HPID) with their affiliated facility. To generate the HFID and HPID, certain information is mandatory, whereas other information is optional. For some information, verification is required, such as the registration license number of a physician, to be verified by the concerned medical councils, and educational qualification, to be verified by the concerned universities or medical colleges [7, 8 ]. As of April 2023, more than 160,000 healthcare professionals have been registered in the HPR. Along similar lines with the present unified payment interface for monetary transactions, the planned UHI shall pave the way for the bidirectional flow of digital health service requests between end‐users and health service providers on an open platform. Broadly, the UHI gateway works through the following sequential compo- nents: from service discovery, service booking, service FIGURE 1National digital health mission. 346 | COMMENTARY 27711757, 2023, 5, Downloaded from https://onlinelibrary.wiley.com/doi/10.1002/hcs2.67 by University Of Oslo, Wiley Online Library on [05/01/2025]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License 109 fulfillment, and financial settlement, to post fulfillment. Consultation bookings, ambulance bookings, availability of intensive care beds, enquiries about laboratory services, and house visits for sample collection are some of the digital health services envisioned [7, 8 ]. Under the UHI, individual patient health records would be managed through three different health infor- mation management schemes, namely, Electronic Medical Records (EMR) maintained in a particular health facility; Electronic Health Records (EHR) maintained across multiple doctors or facilities; and Personal (longitudinal) Health Records (PHR) maintained at the individual/ patient level [3]. A Unique Health Identifier (UHID) or personal health identifier would also be created for uninterrupted service. As needed, there is also provision for cloud storage of health records in so‐called“Health Lockers”similar to the currently existent DigiLocker [7, 8]. These three prongs of NDHM were moderated and consolidated following due consultation with all stake- holders through a series of public webinars before finalization [8, 9 ]. The most lingering part of any digital system is its virtual existence and, consequently, its data security and data privacy; accordingly, the Health Data Management Policy of the NDHM was launched and subsequently updated. This policy upholds the importance of data protection and acts as the guiding document with minimum standards for an optimal‐cum‐advanced National Digital Health Ecosystem (NDHE) [10]. The NDHB was established based on the principle of“Zero Trust Architecture.”The proposed cloud storage, Health‐ Cloud (H‐Cloud), would be monitored through both Security Operations Center and Privacy Operations Center [7]. The ultimate purpose is to make the available EMR‐ EHR‐PHR data more usable [11] and stakeholder‐friendly [12], yet confidential [13]. Though the current system would be functioning entirely without restrictions, its individual autonomy would be still maintained with a co‐ operative federated architecture (Table1)[3, 5, 7]. During the unprecedented COVID‐19 pandemic, the practical and clinical relevance of technology in delivering healthcare services—including the ArogyaSetu app, Co‐ WIN, and e‐Sanjeevani, to name a few—was very much appreciated. The success of the Ayushman Bharat–Pradhan Mantri Jan Arogya Yojana scheme relies on its robust IT‐enabled system linking nearly 500 million beneficiaries. Some other examples of government‐managed health applications include NIKSHAY, an online tuberculosis patient monitoring application; the Integrated Disease Surveillance Program module of the Integrated Health Information Platform, a digital decentralized state‐based surveillance system; and the Mera Aspatal (My Hospital) patient feedback system. The underlying principles of NDHM are to“capture data once and use many times,”to“move from silos to systems”by transcending isolated disparate electronic services to more integrated digital health services, and to act as a“single source of truth.”Leveraging the“JAM trinity”of Jan Dhan Yojana, Aadhaar and Mobile number can also fuel the process of digitalizing the Indian health system [7]. 2 | NDHM: THE PATH AHEAD The importance of continuity of care has been much deliberated across all countries, irrespective of economic backgrounds [14, 15]. For this continuity of care to materialize optimally in a nation, adequate support is necessary to ease the passage of medical information between different areas of the country [16]. The major hurdle in accomplishing this exchange and usage of medical information is organizational [17]; hence, the onus lies with the health management authority of the concerned regions. This all‐inclusive pattern of the proposed NDHM would be beneficial at all levels from primary to advanced care settings and in both public and private segments—the evidence of which is appreciated in the real‐world Indian context with regard to utilization of EHR [18]. Furthermore, the negative impact of medical informational discontinuity is strongly felt among Indian doctors, particularly in clinical decision‐making [19]. In 2005, the World Health Assembly urged its member countries to implement eHealth services through which equitable, affordable, and universal access to healthcare services could be delivered. Accordingly, more than 120 countries have developed strategies and policies to strengthen eHealth services. In the subsequent World Health Assemblies (in 2013 and 2018), the impetus was shifted to national and global eHealth strategies—spreading the boundaries of the digital health initiative to all areas [20]. According to data from the World Economic Forum, there is a perceptible increase in digital health worldwide [21]. Broadly, the digital health market is larger in the Americas and Europe compared with those in Asia, the Middle East, or Africa, which translates to a direct correlation between per‐capita Gross Domestic Product and the digitalization of the healthcare system. However, there can be intraregional differences, as in Europe: Denmark, England, and Sweden are relatively better placed with regard to progress in digitalization of health compared with Ireland, Switzerland, and the Netherlands [21]. Even high‐income countries are confronting numer- ous obstacles in implementing the national digital health COMMENTARY | 347 27711757, 2023, 5, Downloaded from https://onlinelibrary.wiley.com/doi/10.1002/hcs2.67 by University Of Oslo, Wiley Online Library on [05/01/2025]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License 110 TABLE 1Features of National Digital Health Mission in comparison to the prevailing system. Pre‐NDHMProposed NDHM Isolated and functions in silo (Platform‐centric model)Integrated and interoperable—breaking barriers (Open‐source software products and standards) Centralized and sometimes, even decentralized architectureFederated architecture •Regional‐level •State‐level •District‐level •Facility‐level Fragmented and disrupted provision of healthcareContinuity of care at all levels–primary, secondary, and tertiary– public and private Interrupted and complex health governanceImproved efficiency, effectiveness, and accountability in health service delivery Contemplation on hidden chargesTransparency in pricing of services rendered Previous Health Facility Registries •No real‐time updates •Fragmented •Not complete •Lack of confidentiality and transparency Health Facility Registry (HFR) •Dynamic—provision for real‐time updates •Universal—covers all systems of medicine and also both public and private organizations •Comprehensive—includes all relevant information (basic, financial, civil and medical infrastructure) •Data verified and audited regularly Previous Registries •Less representative ∘Predominantly doctors of modern medicine •Less participatory Healthcare Professionals Registry •Encompasses all healthcare professionals ∘Doctors (from all systems of medicine) ∘Dentists ∘Nursing professionals ∘Allied healthcare professionals ∘Miscellaneous health workers •Voluntary‐yet‐conducive for all stakeholders ∘Medical Councils ∘Medical Colleges/Universities ∘Employer • Electronic Health Records (EHR) are not easily accessible whenever required •Demand‐driven, consent‐based, authenticate, and secure access to Electronic Health Records (Unified Health Interface) •Discrete and multiple EHRs (application‐centric)•Longitudinal, sequential, and standardized EHRs (citizen‐/patient‐ centric) •Health Identifier is facility‐specific•Universal, unique, and secure Personal Health Identifier [Ayushman Bharat Health Account (ABHA) number] •Healthcare providers exist as mere health information generators •Healthcare providers act as Health Information Providers (HIPs) also referred to as Health Data Fiduciaries •Healthcare providers can also act as Health Information Users (HIUs) •Only healthcare providers can generate health data•Incorporation of individual/patient generated data in the EHR is possible •Multiple heath Apps with no transfer of content across parties, even when needed •Multiple front‐end Apps with provision for authorized transfer of data. However, they can neither download individual patient data nor act as data repositories. •Each government health program/scheme has its own exclusive ID which leads to multiple IDs for each user •Government health programs/schemes can be accessed through a single Health ID (ABHA number) •Each member in a family has discrete Health IDs•Proposal for linkage of Health IDs of all members in a family 348 | COMMENTARY 27711757, 2023, 5, Downloaded from https://onlinelibrary.wiley.com/doi/10.1002/hcs2.67 by University Of Oslo, Wiley Online Library on [05/01/2025]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License 111 systems [22]. Hence, like any other national programs, the NDHM must be periodically monitored and eval- uated for its expected outcomes [23]. The MEASURE Evaluation's Health Information System Strengthening Model provides guidance in the establishment and follow‐up of health information systems, particularly in low‐and middle‐income countries. This model works in the four key areas, namely, the human element (workforce), the enabling environment (planning, imple- mentation, and maintenance), information generation (operationalization), and performance (measurement of outcomes). Along with these key areas, the model also incorporates contextual factors, which vary by country [24]. In India, which has notably diverse, dense, and disproportionate distribution of populations and health- care facilities, digitizing, compiling, and moderating health‐related data are indeed a significant task. How- ever, if the processes continue as planned, the fruits of this noble pursuit of demand‐and consent‐driven seamless transfer of health data will be far‐reaching, positively reflecting on all aspects of the health sector, if not the entire general economy of our country. More importantly, both providers and seekers of healthcare would become more empowered with timely and precise access to health information, which could have positive implications on the health status of every Indian. Eventually, overall public health is bound to improve with this strategic use of health care data [25]. Because the digital technologies are already in hand in India, the policy regulations (governance), infrastructure develop- ment, and capacity‐building are the only remaining necessities [26]. Hence, some of the expected challenges in implementing the Digital Health Mission could be nontechnological, including organizational, physical, political, social, cultural, and ethical bottlenecks [27]. Indian community medicine experts have provided possible solutions for the broad challenges in implement- ing the NDHM [28]. Some of their anticipated challenges were creating awareness and educating all players, reaching out to less‐privileged populations, manpower engagement and professional training, monetary con- straints and sustainability, and data security matters. Other possible hurdles in adopting the NDHM model may relate to IT infrastructure (connectivity), digital literacy (understanding and knowledge), transformation inertia (application and functional issues), and coopera- tion from all stakeholders (social acceptability) [23]. Digital India is embracing four pillars, namely, the price of the device, the digital connectivity, the cost of data, and the idea of“digital first”. With the recent launch of 5 G services in India [29]—reportedly the fastest 5 G roll‐out in the world, deployed in 200,000 sites covering 700 districts in 8 months—the IT infrastructure has gained the necessary momentum to overcome obstacles to NDHM implementation. The initial lag in the number of HFR and HPR registrations has been compensated for by a marked increase in HFR and HPR registrations following mass media campaigns. Additionally, the NHA has also announced the Digital Health Incentive Scheme to increase adoption by means of extending monetary bonuses for adopting the NDHM system. The experience of countries such as Korea and the Netherlands in integrating national digital healthcare data into national health information systems could be an early learning exposure for India in overcoming possible obstacles [26]. Nevertheless, in the longer term, this Indian model of digital healthcare system can be a forerunner for other countries with similar economic and demographic backgrounds. The establishment of the NDHM would not only strengthen the healthcare delivery services but also greatly reinforce other healthcare sectors such as health surveillance, health literature, and health education, knowledge, and research. The first building principle of the NDHE—“to think big”—is partially achieved by the promulgation of the NDHM, and this may make it easier to succeed in the other two principles, namely,“to start small”and“to scale fast.”Furthermore, in accordance with the above building principle, implementation of NDHM is planned in a phased manner with Phase 1 being a roll‐out in Union Territories, Phase 2 being expansion of services to other states, and Phase 3 being a nationwide roll‐out [7]. This phased establishment of the NDHM reflects positively on the sustainability of the national digital health system. The NDHM was later rechristened as the Ayushman Bharat Digital Mission (ABDM) with the 14‐digit unique Ayushman Bharat Health Account (ABHA) Number as the UHID equivalent and the ABHA Mobile Application as the PHR equivalent. As of April 2023, nearly 380 million ABHA numbers have been generated and more than 262 million health records of Indian citizens have been digitized and linked with their ABHA number. Furthermore, as of March 2023, the ABHA‐based“Scan and Share”service has been utilized by more than 1 million patients for hassle‐free time‐saving outpatient registrations. As stated by the Prime Minister during the launch of the ABDM,“Our brothers and sisters living in the remotest villages of the country will get better health facilities, through the launch of this mission today, we will go one step further in improving their lives.”[30] Hopefully, with the implementation of the Indian Digital Health Mission, we are on track to achieve this goal. COMMENTARY | 349 27711757, 2023, 5, Downloaded from https://onlinelibrary.wiley.com/doi/10.1002/hcs2.67 by University Of Oslo, Wiley Online Library on [05/01/2025]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License 112 AUTHOR CONTRIBUTIONS Gerard Marshall Raj:Conceptualization (lead); meth- odology (lead); project administration (lead); writing— original draft preparation (lead); writing—review and editing (lead).Sathian Dananjayan:Methodology (supporting); project administration (supporting); visual- ization (lead); writing—review and editing (supporting). Neeraj Agarwal:Supervision (supporting); writing— review and editing (supporting). ACKNOWLEDGMENTS No special funding was obtained for writing this manuscript. CONFLICT OF INTEREST Authors declare no conflict of interest. DATA AVAILABILITY STATEMENT Data sharing is not applicable to this article as no data sets were generated or analyzed during the current study. ETHICS STATEMENT This article does not contain any studies with human or animal participants. INFORMED CONSENT Not applicable. ORCID Gerard Marshall Raj http://orcid.org/0000-0001- 7499-7219 Sathian Dananjayan http://orcid.org/0000-0002- 6103-7267 REFERENCES 1. National Health Policy, 2017 [Internet]. 2017 [cited 2023 Apr 18]. Available From:https://main.mohfw.gov.in/sites/default/ files/9147562941489753121.pdf 2. National Health Portal. National Digital Health Blueprint (NDHB)—Comments Invited [Internet]. 2019 [cited 2023 Apr 18]. Available From:https://www.nhp.gov.in/NHPfiles/National_ Digital_Health_Blueprint_Report_comments_invited.pdf 3. MoHFW. National Digital Health Blueprint (NDHB). [Inter- net]. 2019 [cited 2023 Apr 18]. Available From:https://main. mohfw.gov.in/sites/default/files/Final%20Report%20-%20Lite %20Version.pdf 4. National Health Authority (NHA). About NHA [Internet]. 2021 [cited 2023 Apr 18]. Available From:https://pmjay.gov. in/about/nha 5. Ayushman Bharat Digital Mission. National Health Stack— Strategy and Approach [Internet]. 2018 [cited 2023 Apr 18]. Available From:https://old.abdm.gov.in/publications/NHS_ Strategy_and_Approach 6. Nundy S. Digital connections to improve India's health. BMJ. 2021;375:n2586.https://doi.org/10.1136/bmj.n2586 7. Ayushman Bharat Digital Mission. National Digital Health Mission—Strategy Overview [Internet]. 2020 [cited 2023 Apr 18]. Available From:https://www.niti.gov.in/sites/default/ files/2021-09/ndhm_strategy_overview.pdf 8. Ayushman Bharat Digital Mission. Consultation Papers [Internet]. 2021 [cited 2023 Apr 18]. Available From:https:// abdm.gov.in/publications 9. Ayushman Bharat Digital Mission. Press Release. National health authority (NHA) to conduct an open house on NDHM [Internet]. 2021 [cited 2023 Apr 18]. Available From:https:// abdm.gov.in/press-releases?page=2 10. Ayushman Bharat Digital Mission. Press release. National Digital Health Mission: Health Data Management Policy [Internet]. 2022 [cited 2023 Apr 18]. Available From:https://abdm.gov.in:8081/ uploads/Draft_HDM_Policy_April2022_e38c82eee5.pdf 11. Harrington L. Can health care survive current electronic health record usability? AACN Adv Crit Care. 2015;26:194–6. https://doi.org/10.4037/NCI.0000000000000081 12. Matthews JB. The electronic medical record has ruined it all, including the physician‐patient relationship. Ann Surg. 2020;272: 231–3. https://doi.org/10.1097/SLA.0000000000003847 13. Fernández‐Alemán JL, Señor IC, Lozoya PÁO, Toval A. Security and privacy in electronic health records: a systematic literature review. J Biomed Inf. 2013;46:541–62.https://doi. org/10.1016/j.jbi.2012.12.003 14. Schwamm LH. Digital health strategies to improve care and continuity within stroke systems of care in the United States. Circulation. 2019;139:149–51.https://doi.org/10.1161/CIRCU LATIONAHA.117.029234 15. Mostert‐Phipps N, Pottas D, Korpela M. A socio‐technical approach to continuity of care and electronic records in the South African context. Stud Health Technol Inform. 2010;160: 406–10. 16. Dickerson AE, Sensmeier J. Sharing data to ensure continuity of care. Nurs Manage. 2010;41:19–22.https://doi.org/10.1097/ 01.NUMA.0000384142.04693.58 17. Oyeyemi A, Scott P. Interoperability in health and social care: organisational issues are the biggest challenge. BMJ Health Care Informat. 2018;25:196–7. https://doi.org/10.14236/jhi. v25i3.1024 18. Kalra A, Bhatt DL, Wei J, Anderson KL, Rykowski S, Kerkar PG, et al. Electronic health records and outpatient cardiovascular disease care delivery: insights from the Ameri- can college of cardiology's PINNACLE India quality improve- ment program (PIQIP). Indian Heart J. 2018;70:750–2. https:// doi.org/10.1016/j.ihj.2018.03.002 19. Gowda NR, Kumar A, Arya SK, H V. The information imperative: to study the impact of informational discontinuity on clinical decision making among doctors. BMC Med Inform Decis Mak. 2020;20:175.https://doi.org/10.1186/s12911-020- 01190-2 20. World Health Organization. Global strategy on digital health 2020‐2025 [Internet]. 2021 [cited 2023 Apr 18]. Available From:https://www.who.int/docs/default-source/documents/ gs4dhdaa2a9f352b0445bafbc79ca799dce4d.pdf 21. World Economic Forum. Health and Healthcare. How can countries achieve digital maturity in healthcare? [Internet]. 2022 [cited 2023 Apr 18]. Available From:https://www. weforum.org/agenda/2022/08/countries-achieve-digital- maturity-healthcare/ 350 | COMMENTARY 27711757, 2023, 5, Downloaded from https://onlinelibrary.wiley.com/doi/10.1002/hcs2.67 by University Of Oslo, Wiley Online Library on [05/01/2025]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License 113 22. Wilson K, Khansa L. Migrating to electronic health record systems: a comparative study between the United States and the United Kingdom. Health Policy. 2018;122:1232–9. https:// doi.org/10.1016/j.healthpol.2018.08.013 23. Sharma RS, Rohatgi A, Jain S, Singh D. The Ayushman Bharat Digital Mission (ABDM): making of India's digital health story. CSI Transactions on ICT. 2023;11:3–9. https://doi.org/ 10.1007/s40012-023-00375-0 24. MEASURE Evaluation. Health information system strength- ening model: a summary [Internet]. 2017 [cited 2023 Apr 18]. Available From:https://www.measureevaluation.org/ resources/publications/fs-16-171.html 25. Sharfstein JM. Using health care data to track and improve public health. JAMA. 2015;313:2012–3. https://doi.org/10.1001/ jama.2015.4795 26. OECD. Health. Digital Health [Internet]. 2023. [cited 2023 Apr 18]. Available Fromhttps://www.oecd.org/health/digital- health.htm 27. Challenges in digital medicine applications in under‐resourced settings. Nat Commun. 2022;13:3020.https://doi.org/10.1038/ s41467-022-30728-3 28. Samudyatha U, Kosambiya J, Madhukumar S. Community Medicine in Ayushman Bharat Digital Mission: the hidden cornerstone. Indian J Commun Med. 2023;48:326–3. https:// doi.org/10.4103/ijcm.ijcm_343_22 29. PIB. Ministry of Communications, Prime Minister Launches 5G services in India [Internet]. 2022 [cited 2023 Jul 12]. Available From:https://pib.gov.in/PressReleasePage.aspx? PRID=1864246 30. PIB. MoHFW, Prime Minister of India launches country- wide Ayushman Bharat Digital Mission [Internet]. 2021 [cited 2023 Apr 18]. Available From:https://pib.gov.in/ PressReleaseIframePage.aspx?PRID=1758511 How to cite this article:Raj GM, Dananjayan S, Agarwal N. Inception of the Indian Digital Health Mission:Connecting...the...Dots. Health Care Sci. 2023;2:345–351.https://doi.org/10.1002/hcs2.67 COMMENTARY | 351 27711757, 2023, 5, Downloaded from https://onlinelibrary.wiley.com/doi/10.1002/hcs2.67 by University Of Oslo, Wiley Online Library on [05/01/2025]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License 114 Digital health ecosystem in India: Present status, challenges, and way forward. Author: Suraj Kapoor Date: Oct-Dec 2022 From: D Y Patil Journal of Health Sciences(Vol. 10, Issue 4) Publisher: Medknow Publications and Media Pvt. Ltd. Document Type: Article Length: 2,330 words Lexile Measure: 1400L Full Text: Byline: Suraj. Kapoor Digital technology has been a revolutionary foray in various sectors and domains such as education, industry, research, and, recently, healthcare. With digital health increasing its presence and importance in the country, it is imperative to assess the present digital health system in the country, its challenges, and the way ahead. Secondary data from Govt. official sites, press information, latest articles, and newspapers were extracted and discussed in the article. The existing digital health infrastructure along with a discussion on electronic health card, role, and importance of digital health in immunization, reproductive, and child health are discussed. The use of digital tools by grass root workers has also been highlighted in the study. In the current system, a lot of data including Outpatient department (OPD) data, Operation theatre(OT) data is not captured, which leads to the loss of vital information. There is a need for a capacity building like availability and accessibility of the Internet in the periphery, and training for building an effective digital health care system in the country. There is a necessity to emphasize the first important step of collection of a 'good quality' data point through the implementation of electronic medical records by the health care providers. Digital health is a rapidly emerging and evolving entity with an overwhelming impact on geopolitical and socioeconomic realities in the future. The benefits of public goods, results, and services under this group must be maximized, with minimum disruption to the society. Digital technology has been a revolutionary foray in various sectors and domains such as education, industry, research, and recently, healthcare. The concept of digital health is an evolving entity and has gained tremendous importance in the time of the Pandemic with social distancing and lockdowns forcing the entire globe to adopt digital health and health technologies on a large scale. With digital health increasing its presence and importance in the country, it is imperative to assess the present digital health system in the country, its challenges, and the way ahead. Secondary data from Govt. official sites, press information, latest articles, and newspapers were extracted and discussed in the article. Digital health tools are used in various domains of health right from grass-root workers to health planners in India. Although digital health appears to be a new norm in pandemic times, still there are issues of accessibility, transparency, and confidentiality. Training of users and healthcare provider is equally important along with capacity availability in the expansion of digital health across the country. There is a need for a capacity building like availability and accessibility of Internet in the periphery, and training for building an effective digital healthcare system in the country. There is a necessity to emphasize the first important step of collection of a 'good quality' data point through the implementation of electronic medical records (EMR) by the healthcare providers. Health literacy in the community is an equally important entity. Digital technology has been a revolutionary foray in various sectors and domains such as education, industry, research, and recently, healthcare. The concept of digital health is an 06/01/2025, 11:56Digital health ecosystem in India: Present status, challenges, and way forward. - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=300803...1/5 115 evolving entity and has gained tremendous importance in the time of the Pandemic with social distancing and lockdowns forcing the entire globe to adopt digital health and health technologies on a large scale. The digital health concept was first introduced in 2000 by Seth Frank,[1] which largely encompasses Internet-based applications and media to enhance medical subject matter, commerce, and connectivity. With the advancement in technology, digital health has expanded to encompass a much wider set of scientific concepts and technologies, including the Internet of things, big data technology, artificial intelligence techniques, genomics, analytics, wearables, mobile applications, and telemedicine. The various domains of digital health have been explained by World Health Organization (WHO) in 2018.[2] With the advancement in digital health and literacy rate in the country, The Government of India laid importance on digitalization in India's healthcare sector in the National Health Policy, 2017 using the National Digital Health Mission (NDHM) which can act as the foundation on which national digital health ecosystem can be built. On the occasion of the 74th Independence Day, the Government of India embarked on its journey to achieve Universal Health Coverage by launching NDHM.[3] NDHM aims to build a holistic, integrated, and comprehensive digital health ecosystem that will lay the foundation of a strong public digital infrastructure, digitally empower individuals, patients, healthcare staff, and health institutions, and aid streamline the healthcare delivery system of the country. This will help inequitable, affordable, and accessible health care to all. It may be useful for health planners and policymakers as well in monitoring and surveillance of health-related events better and in an efficient way. With digital health increasing its presence and importance in the country, it is imperative to assess the present digital health system in the country, its challenges, and the way ahead. Methodology: Secondary data from Govt. official sites, press information, latest articles, and newspapers were extracted and discussed in the article. Existing digital healthcare delivery system: The digital health ecosystem in the country as per healthcare hierarchy is highlighted in [Table 1] . The details of the digital healthcare system in India are highlighted below:{Table 1} Digital Health at the Community Level Electronic health record (EHR) cards The government of India intends to introduce a uniform system of EMR/EHR by the Hospitals and healthcare providers throughout the country.[4] With NDHM launched across the nation, EHR cards may aid in effective and faster surveillance. Digital health tools/gadgets With digital literacy in the country improving at a greater pace and the existence of a relatively younger population, it enables the advancement and increase user availability of various digital tools like apps, gadgets, and wearables useful in monitoring, screening, adherence of diseases as well as monitoring of risk factors. With the epidemiological transition and rise in life expectancy, lifestyle and non-communicable diseases are bound to get prevalent in India which is reflected in NFHS-5 data recently published. India has a prevalence of diabetes of 13% in females and 15% in males. Similarly, the prevalence of hypertension is estimated to be 21% in females and 24% in males.[5] These diseases particularly require long-term monitoring of risk factors like diet and exercise as well as adherence to drugs which can be aided by easily available online tools like apps, wearable, gadgets, etc. Equally important are the helplines for substance abuse counseling like quit tobacco helpline, and the helpline for diseases associated with a stigma like HIV. Ministry of Health and Family Welfare, Government of India Mera Aspataal (My Hospital) enterprise to gather patient feedback on the services availed from both public and empaneled private health facilities. It works through various communication mechanisms, 06/01/2025, 11:56Digital health ecosystem in India: Present status, challenges, and way forward. - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=300803...2/5 116 including short message service (SMS), outbound dialling (OBD), a mobile application, and a web portal. Digital tools for grassroot workers To achieve equitable health, decentralization of the health sector with community participation and empowerment is very important. Community health grass-root workers such as ASHA (accredited social health activist), ANM (auxiliary nurse midwife), and AWW (anganwadi worker) have been empowered with certain digital tools with proper training which was effectively utilized during the COVID-19 pandemic times. ICDS-CAS (common application software) has been specifically devised to improve the Service Delivery System as well as the system for real-time monitoring (RTM) for nutritional outcomes in the anganwadis.[6] Digital tracking of services of ASHA has been implemented in various states like ASHA Nidhi, an initiative by the government of Karnataka. It is an online system that enables to obtain beneficiary-wise lists of services given by ASHA to the community. Simultaneously there is a provision for Online payment of ASHA to their bank accounts.[7] ANMOL(ANM online) is a tablet-based version of the RCH (rReproductive and child health) portal which tracks eligible couples, and pregnant women for ANC and tracks childhood immunization. Digital Tools in Health Institutions Under the Ayushman Bharat scheme, with upgradation of existing subcentre to health and wellness centers to provide holistic health to the community. There is a provision of teleconsultation under the scheme at the subcenter. In this specialist opinion can be taken and there will be the provision of availability of regular and routine medications at the subcenter itself, like for non-communicable diseases. National Teleconsultation Service of the Ministry of Health and Family Welfare is the first of its kind online outpatient department (OPD) service offered by a country's government to its citizens. National Teleconsultation Service aims to provide healthcare services to patients in their homes. Safe and structured video-based clinical consultations between a doctor in a hospital and a patient in the confines of his home are being enabled.[8] Reproductive and child health Reproductive and child health ( RCH portal ) is specially made for the reproductive lifecycle of women and monitors the health condition of both newborn babies and pregnant women. Immunization Electronic Vaccine Intelligence Network (eVIN) is an innovative technological solution aimed at supporting vaccine supply chain systems across the country. It is a blend of information technology (IT) structure and skilled human resources to enable real-time monitoring of stock and storage temperature of the vaccines kept in multiple locations across the country. IT infrastructure consists of software and SIM-enabled temperature loggers (product) specially designed to improve vaccine stock keeping practices and temperature monitoring (processes) across eVIN states.[9] One of the largest vaccination drives initiated in India used CoWIN app for the registration of beneficiaries. Surveillance Surveillance is a continuous process, and the use of digital tools like geographical information system (GIS) enables the process easier, more effective, and time-saving. Arogya Setu for effective surveillance, risk assessment, and contact tracing for COVID-19 was used extensively during the pandemic. The role of the integrated surveillance project (IDSP) and the inclusion of the integrated health information platform (IHIP) are highlighted in [Table 2].{Table 2} Communicable diseases 06/01/2025, 11:56Digital health ecosystem in India: Present status, challenges, and way forward. - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=300803...3/5 117 There are various software for various infectious diseases as highlighted in [Table 1], which enables real-time monitoring, notification, and case management purposes. Artificial intelligence The use of machine learning, the Internet of things, and other artificial intelligence tools in screening, diagnosis, and management of health-related events is a novel strategy that needs further advancement in the country. Challenges in digital health in India Although digital health appears to be a new norm in pandemic times, still there are issues of accessibility, transparency, and confidentiality. Linking complex confidential health-related information with the Aadhaar identification system may present concerns of potential breaches of privacy, data ownership and use, and the autonomy of individuals.[10] There are ethical concerns as well as concerns about the quality of health care through digital health.[11] The migrant population, lack of bandwidth, infrastructure, lack of scalability and sustainability of the digital solutions, and unavailability of timely information are some of the challenges to adoption.[12] Health literacy of the community especially among the rural, tribal, hard-to-reach population is a matter of concern in empowering them with digital health. Way ahead Data-driven machine learning (ML) and other artificial intelligence tools have emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems and may be useful in various domains like early diagnosis, screening, treatment and monitoring of morbidity and mortality trends.[13] However, in the current system, a lot of data, including OPD data and operation theater (OT) data, are not captured, which leads to the loss of vital information. There is a need for a capacity building such as availability and accessibility of Internet in the periphery, and training for building an effective digital healthcare system in the country. There is a necessity to emphasize the first important step of collection of a 'good quality' data point through the implementation of EMR by the healthcare providers.[14] Health technology assessment is required to ensure that technology choice is participatory and is guided by considerations of scientific evidence, safety, consideration on cost-effectiveness, and social values.[15] Health literacy in the community is an equally important entity. Digital health is a rapidly emerging and evolving entity with an overwhelming impact on geopolitical and socioeconomic realities in the future. The benefits of public goods, results, and services under this group must be maximized, with minimum disruption to the society. Financial support and sponsorship Not applicable. Conflicts of interest There are no conflicts of interest. References 1. Frank SR Digital health care: The convergence of health care and the internet. J Ambul Care Manage 2000;23:8-17. 2. World Health Organization. Classification of digital health interventions v1. 0: A shared language to describe the uses of digital technology for health (No. WHO/RHR/18.06). World 06/01/2025, 11:56Digital health ecosystem in India: Present status, challenges, and way forward. - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=300803...4/5 118 Health Organization; 2018. [Last accessed on 05 May 2022]. 3. Bajpai N, Wadhwa M India's National Digital Health Mission. 2020. 4. Available from: https://www.EHR Standards | National Health Portal of India (nhp.gov.in). [Last accessed on 05 May 2022]. 5. Available from: https://www.National Family Health Survey (NFHS-5) (rchiips.org). [Last accessed on 05 May 2022]. 6. Available from: https://pib.gov.in/Pressreleaseshare.aspx?PRID= 1536456. [Last accessed on 05 May 2022]. 7. ASHA-MIS (karnataka.gov.in). [Last accessed on 05 May 2022]. 8. Available from: https://esanjeevaniopd.in. [Last accessed on 05 May 2022]. 9. Electronic Vaccine Intelligence Network (eVIN) | National Health Portal Of India (nhp.gov.in). [Last accessed on 05 May 2022]. 10. Gopichandran V, Ganeshkumar P, Dash S, Ramasamy A Ethical challenges of digital health technologies: Aadhaar, India. Bull World Health Organ 2020;98:277-81. 11. Dhingra D, Dabas A Global strategy on digital health. Indian Pediatr 2020;57:356-8. 12. Ramachandran A, Sarbadhikari SN. Digital Health for the post-COVID-19 Pandemic in India: Emerging Technologies for Healthcare. 2021 8th International Conference on Computing for Sustainable Global Development (INDIACom), 2021, pp. 244-9. [Last accessed on 05 May 2022]. 13. Rieke N, Hancox J, Li W, Milletarì F, Roth HR, Albarqouni S, et al . The future of digital health with federated learning. Npj Digit Med 2020;3:119. 14. Das AV People to policy: The promise and challenges of big data for India. Indian J Ophthalmol 2021;69:3052-7. 15. Sarbadhikari SN Digital health in India-As envisaged by the National Health Policy (2017). BLDE Univ J Health Sci 2019;4:1. Copyright: COPYRIGHT 2022 Medknow Publications and Media Pvt. Ltd. https://dypatiljhs.com/ Source Citation (MLA 9th Edition) Kapoor, Suraj. "Digital health ecosystem in India: Present status, challenges, and way forward." D Y Patil Journal of Health Sciences, vol. 10, no. 4, Oct.-Dec. 2022, p. 202. Gale Academic OneFile, link.gale.com/apps/doc/A757596695/AONE?u=oslo&sid=bookmark- AONE&xid=df811140. Accessed 6 Jan. 2025. Gale Document Number: GALE|A757596695 06/01/2025, 11:56Digital health ecosystem in India: Present status, challenges, and way forward. - Document - Gale Academic OneFile https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=300803...5/5 119 Disclaimer: This is a machine generated PDF of selected content from our products. This functionality is provided solely for your convenience and is in no way intended to replace original scanned PDF. Neither Cengage Learning nor its licensors make any representations or warranties with respect to the machine generated PDF. The PDF is automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. CENGAGE LEARNING AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGEMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the machine generated PDF is subject to all use restrictions contained in The Cengage Learning Subscription and License Agreement and/or the Gale Academic OneFile Terms and Conditions and by using the machine generated PDF functionality you agree to forgo any and all claims against Cengage Learning or its licensors for your use of the machine generated PDF functionality and any output derived therefrom. Mobile Phones for Maternal Health in Rural Bihar: Reducing the Access Gap? Date:Mar. 17, 2018 From:Economic & Political Weekly Publisher:Athena Information Solutions Pvt. Ltd. Document Type:Article Length:8,078 words Lexile Measure:1420L Full Text: Byline: Marine Al Dahdah, Alok Kumar Marine Al Dahdah (marine.aldahdah@gmail.com) is a sociologist at Centre de Recherche, Medecine, Sciences, Sante, Sante Mentale, Societe (Cermes3), CNRS - Universite Paris Descartes-EHESS, Paris and a research associate at Centre for Social Sciences and Humanities, Delhi. Alok Kumar (aalokkashyap.in@gmail.com) is an independent consultant for the World Bank in Bihar. Health programmes that are using mobile phones to improve maternal health in rural India are examined. Presented by its promoters as a universal, accessible and "smart" empowering technology, how mobile devices transform gender inequalities on the ground is analysed. By using empirical data collected on a global mHealth programme deployed in Bihar, how mHealth devices negate the multifactorial dimension of gender and health inequalities is explained, and also how these devices can reinforce inequalities on the ground is examined. In 2016, seven billion people were mobile phone users, thus propelling the mobile phone ahead of other information and communication technologies (ICTs). Whether it be mobile personal health records or confidential clinical data sent via text messaging, these devices are increasingly used to provide "better" health services in a context of reduced health expenditure and increased involvement of patients. Substantial research has been conducted on eHealth-health on the internet-in recent years, mainly regarding the nature and the value of health information on the web (Adams and Berg 2004), the redefinition of the roles of lay and expert in health, and the subsequent transformation of the patient-caregiver relationship (Henwood et al 2003). Yet, very little research has been conducted on the use of the mobile phone and wireless technology within health programmes, called mHealth or mobile health, and especially in the global South, or in development contexts. However, the impact of mobile technologies on healthcare in such contexts raises critical questions that become particularly acute in the context of increased access to mobile phones in India. The recent multiplication of mHealth worldwide illustrates the overall trend towards the globalisation and technologisation of biomedicine. The widespread idea, that digital technologies improve the quality of care, reduce health disparities and optimise health systems, takes shape in a diverse set of technical devices: mHealth, telemedicine, big data, etc. This paper offers a glance at this new field of mHealth through the study of a particular maternal mHealth project deployed in Bihar, based on fieldwork conducted in 2015 in two districts and five blocks, among almost 100 women, 30 community health workers (CHWs) and 20 implementers, all involved in a maternal mobile health project. We propose to focus more specifically on gender inequalities that these socio-technical devices are revealing and even enhancing on the ground, and how these are entangled with socio-economic and health inequalities. Whereas mobile health is presented by its implementers as a neutral, universal, accessible and "smart" technology to improve health in Bihar, we will analyse how it, in fact, reinforces inequalities on the ground. A 'Simply Brilliant' Innovation Using mobile phones to access and relay health information in developing countries is the topic everyone in health and technology is talking about right now. There's a reason for that, of course. It's one of those "simply brilliant" innovations that seem to make perfect sense. Can a cell phone save a life? It's extremely possible. (Newman 2011) Access to mobile phones is becoming increasingly common over the globe, and is expanding much faster than access to the internet (ITU 2013). mHealth figures are mainly coming from mobile operators and mobile technology providers. They estimated the global 120 market in 2013 between 23,000 and 1,00,000 apps worldwide, a rather approximate estimation that focuses only on apps that are accessible on the major United States-based app stores (Pew Research Centre 2012). Only smartphones can use those kinds of apps. Thus, most of them are not yet reachable for the majority of the developing countries. Thereby, most of the projects deployed in resource-poor settings are SMS-based or vocal services, which can be used on a basic handset. Mobile health projects and applications emerged at the beginning of the 2000s, and have been popping up in the developing countries for the past five years. Aware of the growing deployments of mobile technology, international health actors have been trying to better characterise this phenomenon. In 2011, the World Health Organization (WHO) described mHealth as the practice of medicine and public health assisted by mobile technologies, such as mobile phones, patient monitors, "personal digital assistants" (PDAs) and other wireless technologies (WHO 2011). The WHO segments mHealth according to a typology of projects that include: communication from individuals to health services (call centres, helplines or hotlines), communication from health services to individuals (appointment or treatment reminders, awareness and mobilisation campaigns on health issues), and communication between health professionals (mobile telemedicine, patient monitoring, aid to diagnosis and decision-making). The innovative and transformative component of mHealth constitutes a central argument to promote its spread. "Mobile phones and wireless internet end isolation, and will therefore prove to be the most transformative technology of economic development of our time," as Jeffrey Sachs had already advocated in 2008 (World Bank 2012: 1). This call for technological change-its future and promises-is structuring the field of mHealth, its organisation and actors. Actually, innovation studies identified those dynamics as characteristic of innovative devices. In line with the work of Joly et al (2013) on the economy of technoscientific promises, or Flichy (2003) on imaginaries of innovation, or Rajan (2012) on promise as a symptom of technoscientific capitalism, our corpus analysis1 brings out a clear "promising communication" at stake in mHealth discourses. All these promises come together to promote the mobile phone as a "simply brilliant" innovation for health. Some of these promises- unrelated to health-are fed by the general hopes and hypes related to the mobile phone. Its ubiquity and accessibility allow everybody to be easily connected with anybody, anywhere, and at anytime, making this technology omnipotent and universal at the same time. Mobile phones are key to the economic growth of developing countries. "Studies have suggested that increased mobile ownership is linked to higher economic growth. It is also likely to have twice as large an impact on economic growth in developing countries as in developed ones because the starting point of infrastructure in poorer countries is so much lower in terms of landlines and broadband access" (UNDP 2012: 10). These devices serve as substitutes for a whole bunch of useful tools that you could hardly find in the poorest countries: "In developing countries mobile phones not only complement other technologies but also substitute for them-for example, as cameras, debit cards, or voice recorders" (World Bank 2012: 4). In addition to these "mobile promises," promises linked to the health sector are expanding the whole promising tendency of these discourses: "The use of mobile and wireless technologies to support the achievement of health objectives (mHealth) has the potential to transform the face of health service delivery across the globe" (WHO 2011: 9). More Than Just Healthcare? Three major promises-effectiveness, cost efficiency and empowerment-are constantly used to promote mHealth: "Mobile applications can lower costs and improve the quality of healthcare as well as shift behaviour to strengthen prevention, all of which can improve health outcomes over the long term" (Qiang et al 2012: 9). These three promises are at the foundation of mHealth. While these provide content and credit to this new field, these also raise expectations that might not be fulfilled. Effectiveness of healthcare and health workers has improved thanks to mobile and digital health data. Instantly updated data, collected on-site, facilitate emergency and crisis management (Callaway et al 2012). Mobile apps can improve the quality and accuracy of diagnosis by compiling "good practices," international protocols, analysis of personal health records, and offering personalised treatments in accordance with these indicators (Alepis and Lambrinidis 2013). mHealth can reach patients wherever they are, even if there are no health facilities around. In developed countries, isolated patients can call and exchange health data directly with health professionals through mobile apps (Sankaranarayanan and Sallach 2014). This new connectivity can emerge even without mobile phones, through CHWs sent to the isolated communities to collect health data via the mobile phone, evaluate the needs and connect these populations instantly with health facilities (Kallander et al 2013). Meanwhile, mHealth is also presented as a low-cost mean of health expenses rationalisation and even a way of downsizing health expenditure. By optimising medical time, by avoiding unnecessary hospitalisations, redundant exams or superfluous medicines, by preventing missed appointments or interruption of treatment, mHealth reduces health costs. Moreover, mHealth combined with mBanking will ensure secure out-of-pocket payments even if patients do not have any bank accounts, and will allow uninsured patients to apply for micro-insurance schemes to cover their health expenses (World Bank 2012). Finally, the promise of "empowerment" is crucial as it is the only "human" or "patient-centred" justification for these devices, the only one involving citizens and not only the optimisation of healthcare services (Qiang et al 2012: 39). Far from its original meaning-a grass-roots acquisition of power or reinforcement of power-empowerment, in the case of mHealth, is mainly reduced to a relative autonomy or a limited accountability of patients. This promise echoes the individualistic and liberal vision of empowerment adopted by international aid agencies in early 2000 and described by several scholars. Initially, the term was most commonly associated with alternative approaches to development, with their concern for local, grassroots community-based movements and initiatives, and their growing disenchantment with mainstream, top-down approaches to development. More recently, empowerment has been adopted by mainstream development agencies as well, albeit more to improve productivity within the status quo than to foster social transformation. Empowerment has thus become a 'motherhood' term, comfortable and unquestionable, something very different institutions and practices seem to be able to agree on. (Parpart et al 2003: 24) 121 The empowering effect of mHealth is seen in the idea of an increased degree of autonomy for patients from the healthcare system and also the vision of shared accountability. Thus, health cannot fully be delegated to health professionals; patients have to shoulder their share of responsibility, too. For mHealth promoters, mobile phones play a key role in this empowerment through the optimisation of prevention and treatments: (i) Easy access to health information via mobile phones will lead to sound health behaviour. By improving the understanding of preventive actions, risky behaviour will be avoided. These "positive health-seeking behaviours" will improve the health of entire populations in the long run. (ii) A better understanding of treatments will help patients follow medical instructions and prescriptions. Studies have been already conducted on treatment adherence for chronic diseases in Western countries to show that alerts, reminders and follow-ups through the mobile phone help patients follow instructions and treatments, thus the "empowered chronic patient" does not have to go to the health facility too often and is more in charge of their own health. Closer to a liberal than a liberating vision of empowerment, the technological empowerment of mHealth maximises individual interest and thus will ensure the efficiency of healthcare. Maternal mHealth projects deployed in the developing world constitute fascinating illustrations of this techno-liberal vision of empowerment. We shall now introduce the project we selected to do an in-depth study of mHealth. The 'Most Promising mHealth Project' Sub-Saharan Africa and South Asia have in common the highest mobile phone and mobile internet growth rate worldwide (+40% in 2013, twice the rate of the rest of the world). However, these regions also have the shortest life expectancy at birth, the highest infant and maternal mortality rates worldwide, and the worst indicators related to the different development goals fixed by the United Nations. The idea that the growing phenomenon of the mobile phone could lead to a better health situation for Africans and South Asians rose and took shape in more and more mHealth projects in these regions. To better understand this phenomenon, we did fieldwork in Ghana and India in 2014 and 2015 to study several mHealth projects,2 and among them Mobile Technology for Community Health (Motech), the "most promising mHealth project." The most promising mHealth project that I have seen, called Motech, focuses on maternal and child health in Ghana. Community health workers with phones visit villages and submit digital forms with vital information about newly pregnant women. The system then sends health messages to the expectant mothers, such as weekly reminders about good pre-natal care. The system also sends data to the health ministry, giving policymakers an accurate and detailed picture of health conditions in the country. Those working on AIDS, tuberculosis, malaria, family planning, nutrition, and other global health issues can use the same platform, so that all parts of a country's health system are sharing information and responding appropriately in real-time. This is the dream, but it works only if frontline workers are inputting data, health ministries are acting on it, and patients are using the information that they receive on their phones. (Gates 2012) The Motech project was launched in 2010 in Ghana by the Grameen Foundation with the financial support of the Bill and Melinda Gates Foundation. The goal of Motech is to improve maternal, newborn and child health outcomes in rural developing contexts. Its aim is to support women during their pregnancy and until a year after birth. This project combines modules of health information for women and health professionals, identification and tracking of patients, collection and processing of health data, SMS alerts and voice messages. The aim for Motech is to become a global platform used worldwide for different health issues, to sustain and increase the quality and accessibility of health information and care. The Motech project was then launched in India (in Bihar) in 2012 based on the Ghanaian experience. In this paper, we are presenting a part of our analysis on the Bihar experiment of the "direct to consumer" application of Motech called Kilkari. Kilkari was launched in Bihar in 2013 as a part of a bigger project that encloses three mHealth applications. It was first launched in eight "innovative" districts and extended to 20 districts afterwards. Kilkari is the only application directly targeting pregnant women. It is a vocal messaging system that provides maternal health information to pregnant women and mothers with children younger than 12 months. The weekly messages on pregnancy address context-specific factors like nutritional advice, and encourage women to seek antenatal and postnatal care by sending alerts and reminders for clinical care and visits. It is a fee-based mobile phone service, that for Rs 1 sends one voice message in "rural Hindi." We went to two of the eight pilot districts where the subscriptions rates to Kilkari were the highest in the state. We selected five blocks among those with the highest subscription rates to organise the fieldwork. We met implementers of Kilkari in Delhi and the selected districts, and the managers of the primary health centres of the blocks that connected us with the facilitators (accredited social health activist [ASHA] facilitators) of the cWhs. We then organised focus groups with community health workers involved in Kilkari and, thanks to them, organised focus groups with women in 13 villages. All the interviews were conducted by Marine Al Dahdah and Alok Kumar, and were fully transcribed in English and imported in nVivo software along with the field notes to conduct a qualitative analysis. This analysis revealed the various power issues and inequalities at stake. We will focus first on gender inequalities. Kilkari: A Gendered Technology? From the beginning, the project perfectly integrated gender issues and tried to encompass it by talking only to men: When you see our promotion around Kilkari, you see a man on the theme, who says if you are the best father of the village you should subscribe to Kilkari. it's a service that was targeted to men, since they hold the money and the service need to be bought, the service was targeted to men. All the promotion that happened was targeted to males.3 122 However, those campaigns did not work at all and the implementers had to turn towards a more efficient way to reach the women through the CWHs: ASHAs and anganwadi workers (AWWs). We met 99 women in Bihar, 90 young women between 18 years and 30 years of age and nine mothers-in-law and mothers who subscribed to Kilkari for their daughters-in-law or daughters. Even in our sample that was structured to find Kilkari users, more than one quarter of our interviewees never subscribed to the service. And among the one that subscribed to it, less than half of them listened to more than four messages. Less than 10% of the 99 interviewed women listened to the messages for more than six months, which is too short a period to provide a follow up of women during pregnancy and until the the infant turns one year old. So, why do they not subscribe to or why do they drop out of the system so quickly? There are a lot of reasons for the non-adherence to Kilkari, but we will only evoke the ones that are related to gender. The first one is access to a mobile phone: "I did not subscribe because my husband carries mobile for his work, how would I listen to it if I subscribe."4 The second one is the fee issue, the fact that the service costs Rs 1 is a major cause of disruption: "Deduction of Rs 1 is expensive for me." And, the third major issue is related to serious technical problems that lead to the discontinuity of the service even if the client paid for it: "Calls stopped coming even when there was credit in the mobile account."5 The service is creating conflicts between men and women on these three major points: "My husband said that it's not necessary to listen to it and money gets deducted. He wasn't ready to understand when I tried to convince him." "My brother told that lot of money gets deducted, so he deactivated it. He said he would not give me the mobile anymore." "My husband disconnects the calls anyway. Since money gets deducted. He would deactivate it."6 This can tell us that the service is not working well, but it also tells us how gender inequalities are accentuated by this technical device. Several science and technology studies scholars have clearly shown that access to ICTs is harder for women, because they do not have free access to hardware-computers or mobile phones are owned by the husband-but also because those technologies are conceptualised, developed and deployed by men (Henwood and Wyatt 2000). Among ICTs, mobile phones are particularly interesting, because gender inequalities are accentuated less than with using computers or accessing the internet. Because, mobile phones are cheaper and easier to use than computers or the internet, they seem to be a more "egalitarian" technology, but a woman is still 14% less likely to own a mobile phone than a man in the Global South. This figure increases to 38% if she lives in South Asia, and goes even higher in rural and poor areas (GSMA 2013). Almost half of the women we met in Bihar had their own phone, but these women are over-represented in our study as compared to the general population because they were the ones targeted to subscribe to Kilkari. In rural India, accessing mobile phones is still an important issue for women. Women still rely a lot on men to access this technology. Half of the women we met in Bihar were relying on men (husband, or brothers or fathers-in-law) to access mobile phones: "There when I was with my husband, he kept the mobile with him, here at my mother's home, my brother keeps it."7 "Their husbands or in-laws may have mobiles but they (women) would not be able to use it."8 We found that 70% of the women who own a mobile are married to men who work outside Bihar and are not at home. So, women whose husbands work and live outside Bihar are more likely to own a phone. Ownership of the mobile is not the only gendered issue. Its uses are also very interesting to study and provide insight on the failure of Kilkari. Gendered Mobile Use During the interviews, we asked about what a mobile can do. Perceptions of this are different from the real use of this object. These perceptions show only the possibilities of the object: "Mobile has made our lives much more convenient. If something happens, one can communicate using it right away. In case of an emergency, mobile can be used to transmit information."9 "Earlier it took lot of time to communicate; now it is faster. In case of emergency, one can make a call. It can be used to call people at distant places or to use internet and know new things. News can be read on mobiles." However, when you ask about what they can do with the mobile, you realise that mobile services are not so accessible to these women: "The benefit of mobile is not much because call rates is not affordable."10 "Sometimes for two months, there is no credit in the mobile. Only if there is an emergency and someone is going to the market, I will ask the person to get it recharged."11 Women are facing multiple difficulties in accessing and using mobile phones in Bihar. First, access to mobile phones is still a male prerogative: "I do not touch the mobile. He (husband) says that I don't know how to operate it, I may spoil it and it may stop working."12 Women who own a mobile phone often get old ones that are not functional, with broken screens that freeze or shut down and cannot be charged: "I have my own mobile but it does not work since last 15 days. (Another woman, reacting) I also have a mobile which is not functional, it doesn't get charged. It has to be repaired."13 Women who do have functional mobile phones, most of them are using it for incoming calls and emergency calls. They do not have smartphones (most of the rural Bihari men too do not). But, they do not even have phones with basic functionalities like a music player or basic access to 2G internet, which we can find frequently on the men's phones. Almost none of them have ever sent a text message, mostly because of literacy issues in the most illiterate state of India where 50% of the women are illiterate. Also, the basic phones they use cannot support the Devanagari script, the only script that they know, if they know, how to read and write. None of them have ever accessed the internet via their mobile phone or used any mobile banking service. For women who own a mobile phone, men are still controlling their usage through phone credit. Nearly all the women we met are depending on men to recharge their phone: "I give a missed call to his number using another mobile and then he calls me back. Sometimes it takes 10 days, sometimes even one month to get it recharged. What to do, I am helpless."14 None of the women we met regularly recharge their mobile credit by themselves. It is most of the time their husbands or the men in their household (brothers, fathers-in-law) who take care of it. They can be called, but never have enough credit to place calls on a regular basis. This woman, like many others, explained to us that her husband wants to know why and who she wants to call: "He tells me, why do you always 123 need to have credit in it when I get it recharged whenever you want to make a call."15 Thus, studying the use of mobile phones among these women shows important gender inequalities, in terms of access to phones, credit and functionalities of the phone. Financial inequalities are also very wide in terms of credit expenses. When a woman owns a phone, she will spend 20 times less credit than her husband in one month: "In my husband's mobile, the expenditure is always much more, Rs 300-Rs 400 per month, but in my mobile, I get it recharged only by Rs 10-Rs 20 per month."16 These inequalities are reflecting the current gender inequalities of Indian society and more specifically of rural Bihar, where only 10% of the women are getting any job or salary for their farm work. They have little control over the household expenditure.17 These uses of mobile phones also highlight mobility inequalities that seem antithetical to the promises of mobile phones: "We are women. Some family allow women to go out, others do not."18 "I am not allowed outside because I am daughter-n-law."19 Women are not allowed to go outside the house or to roam around unnecessarily. It is also the reason why they cannot recharge the phone by themselves: "Here the recharge is not available in shops. One has to go to 'B' for this (2-3 km away). How will the ladies go there?"20 And, mobile phones reinforce this confinement in the house since women can be contacted from afar without their going out. By studying this programme in Bihar, we realised that mobile phones are a new way to limit women's mobility and also to exert a new form of control from afar for husbands who are around or not staying in the village at all. Our Bihar fieldwork shows how mobile phone can objectify male domination (Bourdieu 2002). Uses of mobile phones are different for a woman and a man in Bihar. Mobile phones can reinforce male authority on women, and embody the existing male domination that is well-rooted in rural Bihar. This fieldwork highlights how a technical object can enhance men's power over women and limit women's autonomy further more. We would like to bring this analysis to a more complex level by putting gender at the intersection of other inequalities, thanks to the concept on intersectionality (Crenshaw 1989; Yuval-Davis 2015). Indeed, if mobile phones can constitute an instrument of male domination, the varying degrees of determination of the device are set by broader socio-economic and political factors. mHealth and Intersecting Inequalities Used as a dominant analytical frame, gender reveals inequalities between men and women, and male domination at stake in the studied technological artefacts. However, gender, to be relevant, has to be envisioned as consubstantial with other forms of inequalities, which will play a fundamental role in the way mHealth is shifting and transforming unequal relationships of power. The concept of situated intersectionality analyses intersecting inequalities and forms of power at stake in specific contexts and the offsetting mechanisms that technological devices can generate: Situated intersectionality analysis, therefore, in all its facets, is highly sensitive to the geographical, social and temporal locations of the particular individual or collective social actors examined by it, contested, shifting and multiple as they usually are. (Yuval-Davis 2015: 95) From micro to macro, from the individual to the political level, we examine the different domains where technological inequalities are revealed and generated by Motech. This study paper is not exhaustive; it draws attention to some of the major inequalities and forms of domination we identified on the ground, and their articulation with gender. Interpersonal level: Subscription to Motech is always done by the intermediary, that is, the CWHs. Yet, the patient-caregiver relationship has already been analysed as very unequal and a source of symbolic, and sometimes physical violence, especially in developing contexts (d'Oliveira et al 2002). This interpersonal relation is going to play an important role in the enrolment of women in the Motech project. In Bihar, where Motech is a fee-based service, CHWs are key actors. Mostly, it is because they have been convinced or pushed by health workers that women will subscribe to it. In Bihar, women have a trust-based, but also subordinate, relationship with CHWs. ASHAs and AWWs might be the only interlocutors in the village on health issues, and the majority of our interviewees declared that the CHW of their village is a reference person for them and that CHWs were really supportive during their pregnancies: "We believe and do what ASHA tells us. ASHA gives us the right information."21 Thus, women subscribe to Kilkari because the CHW they know asked them to do so. They do it on a voluntary basis, but most of the time they trust the CHW, they do not know exactly what the service is about, and in some cases that they have to pay for it: "AWW and ASHA, whatever they say, I trust it."22 "I asked her (the ASHA) why is she asking me to give her my mobile. She told me that she would subscribe me to Kilkari and Dr Anita would call me and I would receive calls related to care during pregnancy and every week Rs 1 will be deducted for this service."23 "I was not told that money would get deducted for the calls."24 From the beginning, the relationship between women and CHWs is not egalitarian, like any other patient-caregiver relationship, but financial inequalities are a major issue in the context of Kilkari. The CHWs are receiving a salary (for AWWs) or incentives (for ASHAs) for the community work they are doing. Thanks to this, they can have greater financial autonomy than the other women of the community and Kilkari can widen this difference further. Indeed, Kilkari offers phone credit incentives for CHWs who subscribe women to the service. Women are paying Rs 1 per message, and the CHW that subscribed them gets Rs 10 of phone credit per subscription after four weeks and Rs 20 after eight weeks of continuous subscription. This incentive system, the fact that women have to pay per message, and that CHWs are getting phone credit for that, generates frictions that both women and CHWs reported during the fieldwork: "One woman told me: credit gets deducted from my account and goes to your mobile account."25 The phone balance credited as incentive to CHWs is low and many times they do not receive it because the subscriptions do not last long enough, but this system still creates a visible financial imbalance. Thus, Motech is in fact making more apparent and aggravates the inequalities between women and CHWs. Community level: Community constitutes another nexus of inequalities revealed by Motech. Community can take a variety of forms depending on the social structure of the studied group of people. But, for our Bihar study, we will focus on family and caste, on their impact on Motech and vice versa. In Bihar, access to mobile phones and to Kilkari is easier for women who live or went back to their 124 mother's family during their pregnancy and for delivering the baby. Their mother's family might be more liberal and attentive to their daughters' well being than the in-laws' family, and ready to pay for a service that can help their daughters during their pregnancy. Almost one quarter of the Motech subscribers we met were effectively staying at their mother's house. Going back to their own family is a favourable factor for women to access Kilkari and can temporarily offset the in-laws' domination over daughters-in-law. At a meso level, the caste system also plays an important role to access mobile phones and Kilkari. Far from being representative of caste diversity, our sample does not give us the possibility to study in detail the inequalities linked to the extremely complex caste stratification. Here, we just give a broad view on the caste-gender intersection in accessing mobile technologies and mHealth because this intersection was brought many times by our interviewees on the ground. Thus, caste apparently played a role in the inclusion or exclusion of women in the Kilkari project. The Scheduled Castes (SCs) and Scheduled Tribes (STs) still represent the majority of poor people and face tremendous discriminations everyday (Jaffrelot 2002). As we have seen in the villages of Bihar, caste is still a structure-giving authority in rural India. Thus, women as well as CHWs state that access to mobile phones and Kilkari is more difficult for women from the SC community: "Out of a population of 2,500 individuals, not even a single woman subscribed to Kilkari. Here, most of the people belong to SC and do not have access to mobile phones."26 Women from these communities would then be almost systematically excluded from a programme like Motech, either because they really do not have access to mobile phones and would be excluded like any other women, or because CHWs are less inclined to working these communities and to convince lower-caste women to subscribe to Kilkari. Economic level: The financial accessibility of Motech is multiform and implies different kinds of economic inequalities. Financial resources are first necessary to acquire a mobile phone, then to make it functional, by bearing the regular costs of battery charging and phone credit (two additional and unavoidable costs), and finally to pay for it messages every week. In addition to that, Kilkari messages are encouraging women to attend health facilities, which incurs substantial costs for women. Indeed, to be fully efficient, it is supposed to change women's behaviour and to bring them to health facilities. However, health facilities are not financially or geographically accessible for the women we met in Bihar. For instance, women in the study related the dire financial situations arising from institutional deliveries: "Transport to the hospital is through a jeep and it charges Rs 500-Rs 600 to take us to the hospital. Ambulance never comes here."27 "I had to spend money on each and everything, medicines, injections, food. The nurse also demanded money saying that I gave birth to a boy. Even when a girl is born, she demands money but more money is demanded if a boy is born."28 The cost of healthcare constitutes for many a central problem to accessing health facilities and delivery there. These healthcare and mobile costs are adding up. Kilkari provides messages that speak of free access to maternity services at the facility level, even if women will in fact pay for these informally. Any health programme that encourages women to attend health facilities should put equal emphasis on improving quality of care and its financial accessibility before advertising for it. In rural India, men would be automatically involved to meet these financial needs, since most of the women in rural Bihar have no financial autonomy. And, even if these women are among the 10% of Bihari women who earn money for their work and can cover mobile expenses by themselves, the money needed for healthcare is too much and remains dependent on the men of the household. These gendered inequalities in accessing healthcare have been identified by many scholars (Kuhlmann and Annandale 2010) and have led to specific policies to make up for the inaccessibility that women face. These compensatory policies invite us to move to the last nexus of inequalities we want to analyse here: the political. Political level: Healthcare structural reforms in the 1990s have led to a wider "commodification" of health, through fee-based health services and increased out-of-pocket expenses (Kuhlmann and Annandale 2010). In India, like in many other emerging countries, the government has experienced a diminishing role in the health sector by subcontracting many health activities to private stakeholders (Shewade and Kumar Aggarwal 2012). These structural reforms have been clearly identified as disproportionately placing women at a disadvantage (Sen and Ostlin 2010). Because women are heavily dependent on public primary health centres (PHCs) that are providing maternal and infant care, healthcare reforms that are affecting public structures strike them harder than males and lead to a significant increase in maternal mortality (Ekwempu et al 1990). India recently put in place specific maternal entitlement policies to make up for the financial difficulties pregnant women face in accessing health facilities. The Janani Suraksha Yojana (JSY) launched in 2005 is a national programme to promote institutional delivery. It targets specifically the 10 states of India where institutional deliveries are the lowest (low-performing states), Bihar among them, where financial entitlements are twice as much as those of other states (high-performing states). To benefit from the JSY, women have to be registered and gave birth at a PHC or public hospital. Women will need a bank account, a birth certificate, and proof of delivery in a public facility. In Bihar, she will then get Rs 1,400 if she lives in a rural area and Rs 1,000 in an urban area. Women in our sample think that accessing this scheme is too complicated and expensive because of the mandatory requirement of a bank account and formalities that entail bribes: "For the registration of the birth we have to give Rs 200, normally this is supposed to be almost free."29 "To receive the maternity benefit of Rs 1,400, I have to have a bank account. If I need a bank account, I will have to maintain a minimum balance of Rs 500 in it, only then they open the bank account. Also for a bank account to be opened, I would need identity documents (ID proofs). To get these documents, I will have to pay bribes everywhere."30 And, even if they fulfil these eligibility criteria, women do not get the money on time. Sometimes it even takes eight-nine months after delivery to reach them because the district itself receives funds very late to transfer money to the beneficiaries: "We have not received maternity benefit. They said that it would take two-three months because there are no funds available now."31 Further, women state that the scheme does not even cover the costs of delivery, and certainly not antenatal and postnatal care costs. They describe point-by-point the different expenses that an institutional delivery entails. From transportation to birth certificate, to multiple bribes, food and medicines, they have to pay, each and everything and each and every person to deliver at a public facility. In all, they will spend between Rs 1,500 and Rs 2,000 to deliver at the PHC: "There is no fixed amount, sometimes for delivery in total 125 one would spend Rs 1,000 and sometimes it is Rs 2,000. But the minimum is Rs 1,000 to Rs 1,200. The amount that we get under maternity scheme is not of much use."32 "We spend more than the Rs 1,400 of the maternity benefit scheme on informal payments made to nurse, transport and medicine."33 According to the National Family Health Survey (NFHS)-4 data, the average out-of-pocket expenditure per delivery in a public health facility is Rs 1,724. Few studies that have evaluated the scheme show that the JSY is troublesome, and generates new inequalities between districts and even among women from the same district (Centre for Equity Studies 2015). But, still, as the latest figures released by NFHS-4 show, the scheme has had an impact, with institutional deliveries in public facilities having risen to 47.7 % in Bihar from NFHS-3 (2005-06), when it was a meagre 3.5%. However, this scheme, compared to universal coverage or free access to healthcare for pregnant women, deals with healthcare accessibility in a very narrow and partial way. It does not take into account the multiple costs implied by antenatal and postnatal follow-ups. According to NFHS-4, less than 4% of women in Bihar had a full antenatal check-up as recommended by the WHO; around 58% of mothers never had any postnatal contact in the 48 hours after delivery as recommended by the WHO (MoHFW 2015-16). Though the recent implementation of the JSY increased institutional delivery, it will not solve on its own the issue of maternal mortality on the long run since it does not take into account the full process of maternity follow-ups from antenatal to postnatal care. In the long run, the quality of healthcare provided at PHCs and the experience of women there is still going to be an issue, if it does not improve: The expense on delivery exceeds the amount we get under the maternity benefit scheme. It is just that people go to the PHC thinking that there are facilities there, which are better than delivering at home. But in fact, there is no benefit from delivering at hospital, and it is too expensive.34 Conclusions Using situated intersectionality and examining the nexus of inequalities, we have offered a nuanced and complex analysis of unequal situations at stake in mHealth. Through the study of several particular intersections, from individuals to public health policies, we highlighted the complex inclusion of a technical device in a situated context. Thus, we pointed out the inequalities sometimes reinforced and sometimes offset by the technical artefact. This paper shows how the implementation of a technology is context-dependent, and implies different degrees of interactions and determinations. Envisioning that the reception of an automated vocal message once a week can make up for such varied and entangled inequalities enmeshed in Motech seems nothing but wishful thinking. However, the Government of India is now investing in these new technologies to improve health, and in 2017 the Ministry of Health and Family Welfare extended Kilkari to Madhya Pradesh, Rajasthan, Jharkhand and Uttarakhand (Chamberlain 2014). The modalities of implementation at a national level have to be further studied, but the numerous difficulties encountered on the field in Bihar should be taken into account to avoid the failure of Kilkari and the potential increase in health inequalities through this mechanism. Notes 1 Qualitative corpus analysis of four corpuses: (i) Worldwide general press: Factiva (English and French), "Mobile and Health," 446 articles (2011-13). (ii) Techno and Health specialised press: Factiva, for the four most evoked regions in the general press (Africa, India, UK and US), 581 articles (2011-13). (iii) Scientific press: PubMed, "Mobile and Health," 213 articles (January 2010-14). (iv) International reports: 20 reports (United Nations, European Union, World Bank, World Health Organization, United Nations Development Programme, Internationla Telecommunication Union, UNICEF, Organisation for Economic Co-operation and Development, United States Food and Drug Administration, Indian government, Institute for Healthcare Informatics) published during 2010-14 on ICT4D (information and communication technologies for development) or on "mHealth," 50 reports from GSM Association on ICT4D and 20 reports frommHealth Alliance. 2 This research was part of Marine Al Dahdah's PhD dissertation. Broader results of this doctoral research have been recently published inGender, Technology and Development (Al Dahdah 2017). 3 Interview with K, employee at BBC Media Action, Delhi, 2015. 4 Focus group discussion (FGD) with woman n2, District A, 2015. 5 FGD with woman n3, District A, 2015. 6 FGD with woman n1, District A, 2015. 126 7 FGD with woman n1, District A, 2015. 8 FGD with community health worker n2, District A, 2015. 9 FGD with woman n1, District A, 2015. 10 FGD with woman n9, District B, 2015. 11 FGD with woman n3, District A, 2015. 12 FGD with woman n7, District B, 2015. 13 FGD with woman n9, District B, 2015. 14 FGD with woman n13, District B, 2015. 15 FGD with woman n12, District B, 2015. 16 FGD with woman n3, District A, 2015. 17 World Bank Data, India, viewed on 14 September 2015, http://data.worldbank.org.ezproxy.uio.no/country/india. 18 FGD with woman n12, District B, 2015. 19 FGD with woman n7, District B, 2015. 20 FGD with woman n1, District A, 2015. 21 FGD with woman n3, District A, 2015. 22 FGD with woman n11, District B, 2015. 23 FGD with woman n12, District B, 2015. 24 FGD with woman n11, District B, 2015. 25 FGD with community health worker n2, District A, 2015. 26 FGD with community health worker n2, District A, 2015. 27 FGD with woman n10, District B, 2015. 28 FGD with woman n7, District B, 2015. 29 FGD with woman n10, District B, 2015. 30 FGD with woman n8, District B, 2015. 31 FGD with woman n9, District B, 2015. 32 FGD with woman n12, District B, 2015. 33 FGD with woman n3, District A, 2015. 34 FGD with woman n10, District B, 2015. References Adams, Samantha and Marc Berg (2004): "The Nature of the Net: Constructing Reliability of Health Information on the Web," Information Technology & People, Vol 17, No 2, pp 150-70. Alepis, Efthimios and Christos Lambrinidis (2013): "M-Health: Supporting Automated Diagnosis and Electonic Health Records," SpringerPlus, Vol 2, No 1, p 103. Al Dahdah, Marine (2017): "Health at Her Fingertips: Development, Gender and Empowering Mobile Technologies," Gender, Technology and Development, Vol 21, Nos 1-2, pp 135-51, https://www-tandfonline- com.ezproxy.uio.no/doi/full/10.1080/09718524.2017.1385701. Bourdieu, Pierre (2002): La Domination Masculine, Edition Augmentee d'une Preface, Collection Points Essais, Paris: Editions du 127 Seuil. Callaway, David W, Christopher R Peabody, Ari Hoffman, Elizabeth Cote, Seth Moulton, Amado Alejandro Baez and Larry Nathanson (2012): "Disaster Mobile Health Technology: Lessons from Haiti," Prehospital and Disaster Medicine, Vol 27, No 2, pp 148-52. Centre for Equity Studies (2015): "Broken Lives and Compromise: Report on Maternity Entitlement in India," http://centreforequitystudies.org/. Chamberlain, Sara (2014): "Scaling BBC Media Action mHealth Services pan-India," BBC Media Action (blog), 7 November, viewed on 21 April 2016, http://www.rethink1000days.org/2014/11/scaling-bbc-media-action-mhealth-.... Crenshaw, Kimberle (1989): "Demarginalizing the Intersection of Race and Sex: A Black Feminist Critique of Antidiscrimination Doctrine, Feminist Theory and Antiracist Politics," University of Chicago Legal Forum, Vol 140, pp 139-67. d'Oliveira, Ana Flavia Pires Lucas, Simone Grilo Diniz and Lilia Blima Schraiber (2002): "Violence against Women in Healthcare Institutions: An Emerging Problem," Lancet, Vol 359, No 9, 318, pp 1, 681-85. Ekwempu, C C, D Maine, M B Olorukoba, E S Essien and M N Kisseka (1990): "Structural Adjustment and Health in Africa," Lancet, Vol 336, No 8706, pp 56-57. Flichy, Patrice (2003): L'innovation Technique: Recents Developpements En Sciences Sociales, Vers Une Nouvelle Theorie de L'innovation, Sciences et Societe, Paris: Editions La Decouverte. Gates, Bill (2012): "The Optimist's Timeline," Livemint, 31 December, http://www.livemint.com/Opinion/V50SZzLeXeMDyrSmleT34I/The-optimists-tim.... GSMA (2013): "Women & Mobile: A Global Opportunity, A Study on the Mobile Phone Gender Gap in Low and Middle-Income Countries," https://www.gsma.com/mobilefordevelopment/wp-content/uploads/2013/01/GSM.... Henwood, Flis and Sally Wyatt (2000): "Persistent Inequalities? Gender and Technology in the Year 2000," Source: Feminist Review, No 64, Spring, pp 128-31 Henwood, Flis, Sally Wyatt, Angie Hart and Julie Smith (2003): "'Ignorance Is Bliss Sometimes': Constraints on the Emergence of the 'Informed Patient' in the Changing Landscapes of Health Information," Sociology of Health & Illness, Vol 25, No 6, pp 589-607. ITU (2013): "Statistics," International Telecommunication Union, Geneva, viewed on 13 May 2014, http://www.itu.int/en/ITU- D/Statistics/Pages/stat/default.aspx. Jaffrelot, Christophe (2002): "Inde: L'avenement Politique de la Caste," Critique Internationale, Vol 17, No 4, p 131. Joly, Pierre-Benoit, Arie Rip and Michel Callon (2013): "Reinventer l'innovation?" October, http://webcom.upmf- grenoble.fr/lodel/innovacs/index.php?id=108#tocto1n3. Kallander, Karin, J K Tibenderana, O J Akpogheneta, D L Strachan, Z Hill, A H ten Asbroek et al (2013): "Mobile Health (mHealth) Approaches and Lessons for Increased Performance and Retention of Community Health Workers in Low- and Middle-Income Countries: A Review," Journal of Medical Internet Research, Vol 15, No 1, e17. Kuhlmann, Ellen and Ellen Annandale (eds) (2010): The Palgrave Handbook of Gender and Healthcare, Basingstoke: Palgrave Macmillan. MoHFW (2015-16): " State Fact Sheet: Bihar," National Family Health Survey-4, Ministry of Health and Family Welfare, Government of India, New Delhi, http://rchiips.org/NFHS/pdf/NFHS4/BR_FactSheet.pdf. Newman, Amie (2011): "Impatient Blogger's News of the Day," blog post, Impatient Optimists, Bill & Melinda Gates Foundation, 3 October, https://www.impatientoptimists.org/Posts/2011/10/Impatient-Bloggers-News.... Parpart, Jane L, Shirin Rai and Kathleen A Staudt (eds) (2003): Rethinking Empowerment: Gender and Development in a Global/Local World, London/New York: Routledge. Pew Research Centre (2012): "Mobile Health 2012," November, http://www.pewinternet.org/2012/11/08/mobile-health-2012/. Qiang, Christine Zhenwei, Masatake Yamamichi, Vicky Hausman and Robin Miller (2012): Mobile Applications for the Health Sector, Washington, DC: World Bank. Rajan, K S (2012): Lively Capital: Biotechnologies, Ethics, and Governance in Global Markets, Durham: Duke University Press. Sankaranarayanan, Jayashri and Rory E Sallach (2014): "Rural Patients' Access to Mobile Phones and Willingness to Receive 128 Mobile Phone-Based Pharmacy and Other Health Technology Services: A Pilot Study," Telemedicine Journal and E-Health: The Official Journal of the American Telemedicine Association, Vol 20, No 2, pp 182-85. Sen, Gita and Piroska Ostlin (eds) (2010): Gender Equity in Health: The Shifting Frontiers of Evidence and Action, Routledge Studies in Health and Social Welfare 5, New York: Routledge. Shewade, Hemant Deepak and Arun Kumar Aggarwal (2012): "Health Sector Reforms: Concepts, Market Based Reforms and Health Inequity in India," Educational Research, Vol 3, No 2, pp 118-25. Yuval-Davis, Nira (2015): "Situated Intersectionality and Social Inequality," Raisons Politiques, Vol 58, No 2, pp 91-100. UNDP (2012): "Mobile Technologies and Empowerment: Enhancing Human Development through Participation and Innovation," 19 February, United Nations Development Programme, New York. WHO (2011): "mHealth: New Horizons for Health through Mobile Technologies," World Health Organization, Geneva. World Bank (2012): Information and Communications for Development 2012: Maximizing Mobile, World Bank, Washington DC. Copyright 2018 Economic and Political Weekly, distributed by Contify.com Copyright: COPYRIGHT 2018 Economic & Political Weekly http://athena.co.in/ Source Citation (MLA 9th Edition) "Mobile Phones for Maternal Health in Rural Bihar: Reducing the Access Gap?" Economic & Political Weekly, 17 Mar. 2018. Gale Academic OneFile, link.gale.com/apps/doc/A531294744/AONE?u=oslo&sid=bookmark-AONE&xid=44bbb097. Accessed 4 Jan. 2025. Gale Document Number: GALE|A531294744 129 Comment https://doi.org/10.1038/s41467-023-44634-9 From lab to life: how wearable devices can improve health equity Jessica R. Walter, Shuai Xu & John A. Rogers Check for updates Medical wearables, non-invasive devices that measure physiological biomarkers, are poten- tially disruptive and powerful tools to promote health equity at scale. Here we describe our experiences designing, validating, and deploy- ing wearable sensors in vulnerable patient populations to improve health outcomes. The Centers for Disease Control and Prevention defines health equity as the“state in which everyone has a fair and just opportunity to attain their highest level of health” 1 . Barriers to achieving health equity include poverty, institutionalized racism, environmental factors, and geography. Advances in technology expedited by the COVID-19 pan- demic have increased interest in digital health, such as telemedicine, electronic health records, and artificial intelligence, as a tool to address health disparities. Comparatively less focus has been given to a narrower, but fun- damental component of the evolving digital health landscape—wear- ables. Medical wearables are noninvasively connected to the body and measure, store, and in some cases interpret biomarkers of clinical significance. Medical wearables are not confined to hospital settings, and ideally seamlessly coexist in clinical and non-clinical environ- ments, remotely interfacing with the broader healthcare delivery ecosystem 2 . Early wearables gained traction as personalfitness devi- ces, leveraging familiar form factors like watches, wristbands, or rings. The development of alternative, more discrete form factors (e.g., patches), variable mounting locations (e.g., chest), and additional biophysical and biochemical sensing capabilities (e.g., electro- cardiogram, blood glucose levels), broadened potential applications in healthcare. Future innovations in this device class are expansive, including therapeutic drug or haptic delivery systems, miniaturization, transient technologies, population-level remote monitoring-enabled disease detection, and incorporation of artificial intelligence 3 . Wearables, in cost-effective embodiments, are uniquely poised to promote health equity at scale, as these devices physically interact with a single patient, often in the lived environment, yet virtually connect this individual to families, caregivers, healthcare providers and their social and healthcare networks more generally. With inten- tion and effort, the biomedical engineering community can steer the field of advanced wearables andflexible bioelectronics toward inclu- sive, accessible, and powerfully disruptive tools to promote health equity and reduce disparities. In this commentary we will share our experiences and those of others who are building, deploying, and scaling wearable sensors informed by the needs of arguably the most vulnerable patients—neonates and pregnant people—across a wide spectrum of resourced environments, to highlight wearable technology’s potential to improve clinical outcomes and promote health equity (Fig.1). Our team in the Querrey-Simpson Institute of Bioelectronics at Northwestern University, in partnerships with a startup company (Sibel Health), and corporate collaborators (Drager) developed a wireless wearable sensor system providing ICU-grade vital sign mon- itoring. The system was deployed in programs funded by the National Institutes of Health, the Bill and Melinda Gates Foundation, and Save the Children, to address the unmet challenge of caring for neonates, which is evidenced by a persistently highly mortality rate—with 1 mil- lion neonates dying on thefirst day of life, and 2 million more perishing within thefirst week of life globally 4 . Though outside the scope of this piece, it bears mentioning that neonatal outcomes vary profoundly, with a disproportionate burden of morbidity and mortality born by low- and middle-income countries (LMICs). Regardless of clinical set- ting, neonatal vital signs are traditionally collected with cumbersome, wired devices. Such devices are often adapted from those originally intended for adult use, and can result in iatrogenic injury, scarring, and disruption of the therapeutic skin-to-skin contact, known as Kangaroo Care, by a caregiver 5,6 . Advanced medical wearables, in soft, skin-like formats with capabilities in continuous wireless operation, are uniquely suited to serve their needs. Limitations of current care informed the development of our system. Key innovations included a wireless, ultrathin,flexible, skin- like engineering design with a miniaturized physical footprint, com- promising neither measurement accuracy nor comprehensiveness. In- sensor data analytics and real-time continuous data streaming provide access to pertinent biomarkers including heart rate, respiratory rate, pulse oxygenation, and skin temperature 7,8 . Furthermore, neonatal skin is fragile, requiring careful attention to mechanisms for skin adherence. We developed alternative adhesives and coupling mechanisms, leveraging weak Van der Waals forces to prioritize skin safety, while ensuring functionality and robust skin coupling. Advanced versions enhance skin tolerance through“holey archi- tectures”increasing mechanical compliance and stretchability while also wicking moisture away from the skin-device interface, and redu- cing interface stresses and skin irritation with routine wear and removal 9 . Finally, engineering designs that prolong battery life, enable a reusable and wirelessly rechargeable mode of operation without external ports or receptacles, with low-cost consumables are critically important in scaling hardware solutions from the bench to hospitals, especially in challenging care environments. Our earlyfield testing on infants as young as 26 weeks (weighing <1500 g) relied upon local, well-resourced tertiary care facilities affili- ated with Lurie Children’s Hospital and Northwestern Medicine Pre- ntice Women’s Hospital. We additionally deployed devices for further validation and usability testing in Aga Khan University, Nairobi (AKU- N), a tertiary healthcare facility in Kenya 10 . nature communications (2024) 15:123 |1 1234567890():,;1234567890():,; 130 Others innovating in this emergent market include Neopenda, a public benefit corporation with extensive implementation work in Uganda and Kenya, who developed the neoGuard TM ,aforehead- mounted device measuring neonatal vital signs. Laerdal Global Health is a Norwegian based not-for-profit sister company to Laerdal Medical, and markets (among other devices), the NeoBeat, a reusable and consumable-free device which is placed on the abdomen to measure newborn heart rate. Neobeat is functional on wet skin and can facilitate rapid neonatal resuscitation and risk stratification. In addition to general physiological monitoring, others have reported a specialized, low-cost wearable placed on the forehead to non-invasively detect jaundice and personalize phototherapy treatment through a transcu- taneous bilirubinometer 11 . In related efforts, we translated our experiences to another highly vulnerable health state—pregnancy. High rates of morbidity and mor- tality during pregnancy continue to occur in the United States and abroad, with more than 80% estimated as preventable 12 . Deepening health disparities underscore the urgency to revolutionize how we approach safety and monitoring of pregnant individuals to ensure equitable care and outcomes. Pregnancy indiscriminately occurs across the spectrum of the well to chronically ill, a broadening age range, and is further defined by progressive physiological changes superimposed on this baseline health. Antepartum and postpartum care occurs in a wide range of variably resourced environments (home, clinics, hospitals). Faced with increasing provider shortages that wor- sen geographically based inequities, remote patient monitoring with wearables has become increasingly relevant 13 . Finally, monitoring requires capabilities beyond routine vital signs, including measure- ments of uterine activity and fetal well-being (most often assessed by fetal heart rate, but also fetal electrocardiography and oximetry). Principles of low profile, unobtrusive, yet comprehensive equip- ment for vital sign monitoring resonate with pregnant patients and staff. We expanded the sensor system to include an integrated mon- itoring platform using a wirelessly linked collection of threeflexible electronic sensors to monitor the pregnant patient’s core vitals, uter- ine, and fetal activity. The sensors are time-synchronized via wireless connectivity and compatible with various low-cost mobile devices. The sensors additionally report advanced biomarkers including Fig. 1 | Application of advanced wearable devices for comprehensive mon- itoring of vulnerable patients at scale.Patient centered engineering and inclusive device design promote broad validation and various use cases. Deployment of low- profile sensors capable of comprehensive monitoring can encourage use in various vulnerable patient populations. Sensors can monitor an individual patient, pro- ducing physiological biomarkers for both personal and provider review in clinical and home environments. Low cost and reusable sensors facilitate scale. Comment nature communications (2024) 15:123 |2 131 continuous cuffless blood pressure, electrohysterography-derived uterine monitoring, and automated body position classification. The system’s capacity to comprehensively monitor pregnant patients during labor has been validated via deployment in a large-scale long- itudinal study in Zambia, India, and Ghana, of thousands of patients as part of the Limiting Adverse Birth Outcomes in Resource-Limited Settings (LABOR) study (NCT04102644) 14 . Future studies of this cohort are currently ongoing to assess if leveraging large volume datasets can produce population-specific predictive models designed to identify patients at risk of adverse outcomes, informing risk stratification and earlier intervention. InnAccel, an Indian-based company, is also investing in affordable and accessible pregnancy monitoring and has commercialized Fetal Lite, a single, wireless probe placed at the pregnant individual’s umbilicus that measures vital signs and fetal heart rate with remote connectivity and streaming capabilities, con- veniently housed in an easily portable laptop-sized bag. Advanced wearable technologies can be designed with cap- abilities well suited to overcome historical barriers to equitable global distribution and their meaningful use. It is estimated that more than 90% of medical devices used in LMICs are imported, having been neither designed, validated, nor produced locally. Sustainable use is further hampered by more than a third of these devices being ren- dered unusable by insufficient training, accessories, or incomplete supply chains 15 . However, wearables are intentionally designed to operate with equal effectiveness and accuracy in the clinic and home, with robust, ruggedized designsfunctional in various settings, including those often encountered in remote locations and/or LMICs (humidity, dust, extreme temperatures), in contrast to traditional medical devices used in sterile, controlled healthcare environments. In our experience, more than 5000 systems described herein have been deployed in 22 countries, used by 15,000 patients (including 500 neonates), aged 26 weeks to 98 years. Though tempting to focus efforts on scaling more simple devices, we hope our work and others demonstrate the highest levels of technological innovation belong and even thrive in low resource settings through intentional engineering and strategic partnerships. The clinical experiences of wearable tech- nologies are still in the early stages, and a stepwise approach is war- ranted, defined by intentional and patient-informed engineering, rigorous validation of device accuracy, and pilot implementation stu- dies. Ultimately, wearables should be expected to demonstrate a measurable improvement in health. We note, however, the trajectory of medical wearables to promote health equity is not inevitable. To the contrary, the false assumption of device benevolence and data objectivity can perpetuate harm and generational injustices. For example, photoplethysmography (PPG)- derived heart rate and oxygen saturation, an affordable approach found in many devices, relies on green light signaling, which is notoriously inaccurate in patients with darker skin 16,17 . If measurement inaccuracies of wearable devices are disproportionately borne by his- torically marginalized populations, research, machine learning, or artificial intelligence built on these measures may perpetuate systemic racism and deepen health inequities, rather than uplift these com- munities. Another example, the continuous glucose monitor (CGM), is arguably one of few medical wearables with unequivocal demon- stration of superior patient outcomes resulting from use, including improved glycemic control, quality of life, and morbidity among patients with Type 1 Diabetes with broad endorsements from guiding institutions such as the American Diabetes Association, and highlights disparities in access and use. Historically marginalized groups are less likely to use CGM at baseline or initiate use, even after controlling for patient age, disease, and socioeconomic factors 18 . Finally, generated data must be judiciously curated, interpreted, and evaluated to pre- vent reinforcing racial stereotypes or hierarchies. Consideration of population-specific comfort and amenability to use wearables due to concerns of data security and privacy, though outside the scope of this commentary, will be paramount to ensure devices and technologies at their core do not increase vulnerabilities. The technical infrastructure and digital platforms housing data derived from wearables cannot be an afterthought and should be built and regulated in parallel with their companion devices. Transparent information and formalized guide- lines about best practices related to data ownership, storage, acces- sibility, and duration of data retention will all be essential to maintain user trust in wearables and algorithms derived from the data. These challenges are not insurmountable; engineers, clinicians, scientists, and early adopters can actively work to promote tenets of equity and inclusion directly into the design process. Wearables can promote health equity at the individual patient level by prioritizing accurate and reproducible capture of physiology independent of the characteristics of the user, such as skin color, weight, or gender. Transparent validation testing in diverse patient populations, in both optimal laboratory conditions and real-world environments, will ensure accuracy of monitoring across the full range of patient characteristics 17,19 . In order to achieve meaningful impacts, technolo- gies must obtain the relevant regulatory approvals (e.g., CE Mark or FDA clearance) and be designed specifically to enable scaled manu- facturing at an affordable cost for all patients, independent of socio- economic status. Formalized regulation of devices helps to ensure safe deployment and appropriate clinical application. Achievement of these clearances requires programmatic and institutional preparation, rigorous and transparent demonstration of system safety, device accuracy in alignment with industry standards, cybersecurity, and comprehensive risk assessments. Although labor intensive and expensive, these clearances are critical to maintaining patient and provider confidence, integrity of wearables and the data collected by them. A vast majority of morbidity and mortality, particularly among the vulnerable patient populations highlighted in this perspective, is pre- ventable with early detection and intervention. Wearables offer a unique opportunity to redefine what biomarkers we measure, how we capture this information, where data is collected, and thefinal frontier of how we make this physiological data actionable. Wearables are a unique part of the digital health revolution because they rely on a physical connection to a patient but can remotely connect that person to a vast healthcare infrastructure. Advanced wearables need not be overly complicated nor costly. To the contrary, prioritizing elegant, simple, and miniaturized designs through innovative engineering approaches will maximize their ability to promote health equity. Reporting summary Further information on research design is available in the Nature Portfolio Reporting Summary linked to this article. Jessica R. Walter 1 ,ShuaiXu 2,3 & John A. Rogers 2,4,5,6 1 Department of Obstetrics and Gynecology, Northwestern University, Chicago, IL 60611, USA. 2 Querrey Simpson Institute for Bioelectronics, Northwestern University, Evanston, IL 60611, USA. 3 Sibel Health, Chicago, IL 60614, USA. 4 Department of Biomedical Engineering, Northwestern University, Evanston, IL 60208, USA. 5 Department of Comment nature communications (2024) 15:123 |3 132 Materials Science and Engineering, Northwestern University, Evanston, IL 60208, USA. 6 Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Chicago, IL 60611, USA. e-mail:jrogers@northwestern.edu Received: 25 August 2023; Accepted: 20 December 2023; References 1. Centers for Disease Control and Prevention, Office of Health Equity. What is Health Equity? https://www.cdc.gov/healthequity/whatis/index.html(2022). 2. Xu, S., Kim, J., Walter, J. R., Ghaffari, R. & Rogers, J. A. Translational gaps and opportunities for medical wearables in digital health.Sci. Transl. Med.14, eabn6036 (2022). 3. Xu, S., Jayaraman, A. & Rogers, J. A. Skin sensors are the future of health care.Nature571, 319–321 (2019). 4. You, D. et al. Global, regional, and national levels and trends in under-5 mortality between 1990 and 2015, with scenario-based projections to 2030: a systematic analysis by the UN Inter-agency Group for Child Mortality Estimation.Lancet386,2275–2286 (2015). 5. Bonner, O., Beardsall, K., Crilly, N. & Lasenby, J.‘There were more wires than him’:the potential for wireless patient monitoring in neonatal intensive care.BMJ Innov.3,12–18 (2017). 6. Tottman, A. C., Alsweiler, J. M., Bloomfield, F. H., Harding, J. E. & Team, P. S. Presence and pattern of scarring in children born very preterm.Arch. Dis. Child Fetal Neonatal Ed. https:// doi.org/10.1136/archdischild-2016-311999(2017). 7. Chung, H. U. et al. Binodal, wireless epidermal electronic systems with in-sensor analytics for neonatal intensive care.Science363, eaau0780 (2019). 8. Chung, H. U. et al. Skin-interfaced biosensors for advanced wireless physiological mon- itoring in neonatal and pediatric intensive-care units.Nat. Med.26,418–429 (2020). 9. Kwak, S. S. et al. Skin-integrated devices with soft, holey architectures for wireless phy- siological monitoring, with applications in the neonatal intensive care unit.Adv. Mater.33, e2103974 (2021). 10. Coleman, J. et al. Evaluation of Sibel’s Advanced Neonatal Epidermal (ANNE) wireless continuous physiological monitor in Nairobi, Kenya.PLoS ONE17,e0267026(2022). 11. Inamori, G. et al. Neonatal wearable device for colorimetry-based real-time detection of jaundice with simultaneous sensing of vitals.Sci. Adv.7, eabe3793 (2021). 12. Wang, S., Rexrode, K. M., Florio, A. A., Rich-Edwards, J. W. & Chavarro, J. E. Maternal mor- tality in the United States: trends and opportunities for prevention.Annu. Rev. Med.74, 199–216 (2023). 13. Julian, Z. et al. Community-informed models of perinatal and reproductive health services provision: a justice-centered paradigm toward equity among Black birthing communities. Semin. Perinatol.44,151267(2020). 14. Ryu, D. et al. Comprehensive pregnancy monitoring with a network of wireless, soft, and flexible sensors in high- and low-resource health settings.Proc. Natl Acad. Sci. USA118, e2100466118 (2021). 15. Malkin, R. A. Design of health care technologies for the developing world.Annu. Rev. Biomed. Eng.9,567–587 (2007). 16 . Sjoding, M. W., Dickson, R. P., Iwashyna, T. J., Gay, S. E. & Valley, T. S. Racial bias in pulse oximetry measurement.N. Engl. J. Med.383, 2477–2478 (2020). 17. Fallow, B. A., Tarumi, T. & Tanaka, H. Influence of skin type and wavelength on light wave reflectance.J. Clin. Monit. Comput.27,313–317 (2013). 18. Vrany, E. A. et al. Continuous glucose monitors and virtual care in high-risk, racial and ethnic minority populations: toward promoting health equity.Front. Endocrinol.14, 1083145 (2023). 19. Danzig, R., Wang, M., Shah, A. & Trotti, L. M. The wrist is not the brain: estimation of sleep by clinical and consumer wearable actigraphy devices is impacted by multiple patient- and device-specificfactors.J. Sleep Res.29, e12926 (2020). Acknowledgements The authors would like to acknowledge Kelly Cao and Halie Kwon for their assistance withfigure design. Author contributions All authors contributed to the article conception. J.R.W. was responsible for drafting the initial manuscript. S.X. and J.A.R. provided critical revisions to the manuscript. All authors approve of thefinal version of the manuscript. Competing interests J.A.R. is a co-founder and advisor to Sibel Health and holds patents associated with this com- pany. S.X. is a co-founder of Sibel Health with equity interest and royalty interest in patents associated with technology. J.R.W.’s spouse has equity interest in Sibel Health. The authors declare no additional competing interests. Additional information Supplementary informationThe online version contains supplementary material available at https://doi.org/10.1038/s41467-023-44634-9. Correspondenceand requests for materials should be addressed to John A. Rogers. Peer review informationNature Communicationsthanks the anonymous reviewers for their contribution to the peer review of this work. Reprints and permissions informationis available at http://www.nature.com/reprints Publisher’snoteSpringer Nature remains neutral with regard to jurisdictional claims in pub- lished maps and institutional affiliations. Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visithttp://creativecommons.org/licenses/by/4.0/. © The Author(s) 2024 Comment nature communications (2024) 15:123 |4 133 26 SEPTEMBER 2019 | VOL 573 | NATURE | S103 DIGITAL HEALTHOUTLOOK BY LINDA NORDLING W hen data scientists in Chicago, Illinois, set out to test whether a machine-learning algorithm could predict how long people would stay in hospital, they thought that they were doing everyone a favour. Keeping people in hospital is expen- sive, and if managers knew which patients we re most likely to be eligible for discharge, they could move them to the top of doctors’ priority lists to avoid unnecessary delays. It would be a win–win situation: the hospital would save money and people could leave as soon as possible. Starting their work at the end of 2017, the scientists trained their algorithm on patient data from the University of Chicago academic hospital system. Taking data from the previ- ous three years, they crunched the numbers to see what combination of factors best predicted length of stay. At first they only looked at clini- cal data. But when they expanded their analysis to other patient information, they discovered that one of the best predictors for length of stay was the person’s postal code. This was puz- zling. What did the duration of a person’s stay in hospital have to do with where they lived? As the researchers dug deeper, they became increasingly concerned. The postal codes that correlated to longer hospital stays were in poor and predominantly African American neigh- bourhoods. People from these areas stayed in hospitals longer than did those from more affluent, predominantly white areas. The rea- son for this disparity evaded the team. Perhaps people from the poorer areas were admitted with more severe conditions. Or perhaps they were less likely to be prescribed the drugs they needed. The finding threw up an ethical conun- drum. If optimizing hospital resources was the sole aim of their programme, people’s postal codes would clearly be a powerful predictor for length of hospital stay. But using them would, in practice, divert hospital resources away from poor, black people towards wealthy white peo- ple, exacerbating existing biases in the system. “The initial goal was efficiency, which in iso- lation is a worthy goal,” says Marshall Chin, who studies health-care ethics at University of Chicago Medicine and was one of the scientists who worked on the project. But fairness is also important, he says, and this was not explicitly EQUALITY Mind the gap Artificial intelligence has great potential to improve health care, but without careful implementation, only a privileged portion of society will benefit. TOTTO RENNA ©2019SpringerNatureLimited.Allrightsreserved. 134 S104 | NATURE | VOL 573 | 26 SEPTEMBER 2019 DIGITAL HEALTHOUTLOOK considered in the algorithm’s design. This story from Chicago serves as a timely warning as medical researchers turn to artifi- cial intelligence (AI) to improve health care. AI tools could bring great benefits to people who aren’t currently served well by the medical system. For example, an AI tool for screening chest X-rays for signs of tuberculosis, devel- oped by start-up Zebra Medical Vision in She- fayim, Israel, is being rolled out in hospitals in India to speed up diagnosis of people with the disease. Machine-learning algorithms could also help scientists to tease out which people are likely to respond best to which treatments, ushering in an era of tailor-made medicine that might improve outcomes. But this revolution hinges on the data that are available for these tools to learn from, and those data mirror the unequal health system we see today. “In some health-care systems, there are very basic things that are being ignored, basic quality of care that peo- ple are not receiving,” says Kadija Ferryman, an anthropologist at the New York University Tandon School of Engineering who studies the social, cultural and ethical impacts of the use of AI in health care. These inequalities are preserved in the terabytes of health data being generated around the world. And these data have primed the health-care industry for the kind of disruption that is being driven by ride- sharing platforms in the transport sector and home-rental platforms such as Airbnb in the hotel industry, Ferryman says. “Apple, Google, Amazon — they are all making inroads into the health-care space.” But because AI algo- rithms learn from existing data, there is a risk, Ferryman says, that the tools that result from this gold rush could entrench or deepen inequalities — such as the fact that black peo- ple in US emergency rooms are 40% less likely to receive pain medication than are white peo- ple 1 . The Chicago story is an example of bias being documented in a system before it is implemented. But not all occurrences are caught. In January, at the Conference on Fair- ness, Accountability and Transparency in Atlanta, Georgia, scientists from the Univer- sity of California, Berkeley, and the University of Chicago presented evidence of “significant racial bias” in an algorithm that determines health-care decisions for more than 70 million people in the United States 2 . The algorithm in question allocates ‘risk scores’, which are used to enrol people at high risk of future complex health needs into specially resourced care programmes. The researchers found that black people had signif- icantly more chronic illnesses than did white people with the same risk scores. This means that white people are more likely to be enrolled in targeted programmes than are black peo- ple with the same level of health. If the algo- rithm scored black and white people equally, the researchers said, black people would be enrolled into the programmes at more than twice the current rate. RUBBISH IN, RUBBISH OUT Impaired access to care for certain people is just one way in which AI tools could widen the health gap globally. Another problem is mak- ing sure that AI-powered tools can be applied equally to different groups of people. Informa- tion from certain population groups tends to be missing from the data with which these tools learn, meaning that the tool might work less well for members of those communities. White, adult men are strongly over-rep- resented in existing medical data sets, at the expense of data from white women and children and people of all ages from other ethnic groups. This lack of diversity in the data is likely to result in biased algorithms 3 . There are some efforts to plug these gaps. In 2015, the US National Institutes of Health (NIH) created the All of Us initiative with US$130 million in funding. The research pro- gramme aims to form a database of genetic and health data from one million volunteers, expanding the data sets available for guiding the development of precision medicine to provide better quality care for everyone in the United States. It specifically targets previously under- represented communities for data collection. As of July, more than 50% of the fully enrolled par- ticipants in the programme were from minority ethnic groups. But even such diverse data sets might not translate to AI tools that can be rolled out reli- ably in low-income countries, where disease profiles often differ from those in high-income nations. In sub-Saharan Africa, women are diagnosed with breast cancer younger, on aver- age, than are their peers in developed countries, and their disease is more advanced at diagnosis 4 . Diagnostic AI tools trained on mammograms from Europe are primed to identify disease in its early stages in older women, therefore might not travel well, says Kuben Naidu, president of the Radiological Society of South Africa in Cape To w n . The obvious way to solve this problem is to give AI developers access to data from low- income countries. But doing so raises concerns related to data protection for vulnerable popula- tions, says Naidu. Medical data is highly sensi- tive — information such as HIV status could be used to discriminate against certain popula- tions, for instance. Naidu recalls feeling troubled by the eagerness he was met with when visiting a gathering of radiologists in the United States a few years ago. AI companies among the exhibi- tors “were very excited to hear that I was from Africa, and asked how they could get access to our data”, he says. Companies offer to pay for such data, he says, which might tempt cash-strapped national health systems or individual researchers to part with patient data, perhaps without thinking hard about the rights of the those whose data they are sharing. A number of developing coun- tries are introducing data-protection laws, but in those countries where law enforcement is lax, such regulations could be circumvented. Of course, privacy isn’t just a worry in devel- oping countries. Even in nations with strong data-protection legislation, such as the United States, keeping personal data private might be harder than expected. The University of Chi- cago is currently facing a class-action lawsuit f or sharing patient records with Google. The project stripped out identifiers such as social security numbers and names from the data, in Anthropologist Kadija Ferryman studies the cultural and ethical impacts of using AI in health care. ELISABETH SMOLARZ © 2019 Springer Nature Limited. All rights reserved.© 2019 Springer Nature Limited. All rights reserved. 135 26 SEPTEMBER 2019 | VOL 573 | NATURE | S105 DIGITAL HEALTHOUTLOOK accordance with the country’s privacy laws. But the plaintiffs in the lawsuit argue that the dates of patient visits, which were not excised from the data, could be combined with other information held by Google, such as smartphone locations, to match people to their health records. A related concern is that data companies could tempt people to give up their privacy in return for medical care or financial reward. Such practices could create a privacy divide between rich and poor along the same lines as the digital divide that already separates different socio-economic groups 5 . Ferryman, who sits on the institutional review board of the All of Us programme, admits that she struggles with the tension between the push — no matter how benevolent — to gather data from historically marginalized and maligned populations, and the need to protect those very populations from being exploited. “On the one hand, we want to help these people by gathering more information about them. But on the other hand, what’s to say that data will not be used in ways that discriminate against them?” PROMOTING FAIRNESS THROUGH AI One way to ensure that AI tools don’t worsen health inequalities is to incorporate equity into the design of AI tools. The University of Chicago Medicine data team did this after discovering the issues with its proposed hos- pital-discharge optimization algorithm. Its data science unit now partners closely with the university’s diversity, inclusion and equity department. This means addressing equity in AI is not an afterthought “but rather, a core of how we implement AI in our health system,” says John Fahrenbach, a data scientist with the university’s Center for Healthcare Delivery Sci- ence and Innovation. Fahrenbach worries that not enough atten- tion is being paid to equity in the design of most machine-learning models. “There are so many machine-learning models in health care being developed, deployed and pitched, and I rarely hear them even mention these concerns. This really has to change and formalized regu- lation is likely the best way for this to happen,” he says. There is some way to go in this respect. The UK’s National Health Service has received criticism 6 for not giving enough attention to the potential for AI to widen health gaps in its updated Code of Conduct for Data-driven Health and Care Technologies, released in February. Similarly, the US Food and Drug Administration (FDA), which regulates and approves new medical technologies, has been urged by the American Medical Asso- ciation to highlight bias as a significant risk of machine-learning in its approval process for medical software. A modification to the pro- cess, proposed in April, would allow AI tools that continually improve their performance by learning from new data to do so without having to undergo another review by the FDA. Some research funders are tackling the issue head on, by launching research programmes to study how the introduction of AI tools affects access to care and its quality. Wellcome, a Lon- don-based biomedical charity, launched such a programme in June this year. The £75-million (US$90-million), five-year programme will look at ways to make sure that innovations in the use of health data will benefit everyone — not just in the United Kingdom, but also in other parts of the world, such as East and Southern Africa and India, where Wellcome has a strong presence. Determining whether patchy or biased data could be resulting in unequal health care will play a part in the programme, says Nicola Perrin, head of data for science and health at Well- come, but it won’t be the primary focus. The initiative will drill down into how the unique make-up of individual hospitals — such as the availability of doctors, medicine or equipment, and the hospital’s relationship with the communities that depend on it for care — affects whether the AI tools deliver. “That’s the bit that’s always neglected, the unglamorous, unsexy part,” she says. In devel- oping countries, especially, it’s about making sure that tools are actually meeting demand on the ground, and building trust and buy-in from the communities they are intended to help, she says. “We need to understand peo- ple’s expectations, and where the boundaries should be.” This point echoes that of Naidu. Rolling out health-care tools in developing countries is never easy, he says, and it requires an intimate understanding of the existing bottlenecks in the health system. For example, the AI that can identify people with tuberculosis from chest X-rays, primed for use in India, could also save time, money and lives in South Africa — especially in rural areas where there aren’t specialists to examine such images, he says. But to obtain images in the first place, communities will need X-ray machines and people to operate them. Failure to provide those resources will mean that AI tools will simply serve those already living near better- resourced clinics. Ferryman thinks it is right to be cautious about new medical technologies. “There is no absolute guarantee that the tools will have benefits that outweigh the potential harm they can do,” she says. But she also thinks that most people working in health care in the United States want a more equitable sys- tem. Health systems are built around highly trained specialists whose primary motivation is caring for people, and many doctors are hungry for innovations that make the system fairer, she says. “That gives me hope.” ■ Linda Nordling is a science journalist in Cape Town, South Africa. 1. Lee, P. et al. Am. J. Emer. Med. https://doi. org/10.1016/j.ajem.2019.06.014 (2019). 2. Obermeyer , Z. & Mullainathan. S. in Proc. Conf. Fairness, Accountability, and Transparency 89 (ACM, 2019). 3. Blasimme, A. & V ayena, E. in Oxford Handbook of Ethics of Artificial Intelligence Preprint at https://doi. org/10.2139/ssrn.3368756 (2019). 4. Blac, E. & Richmond, R. Glob. Health 15, 3 (2019). 5. Montgomery , K., Chester, J. & Kopp, K. J. Info. Policy 8, 34–77 (2018). 6. Smallman, M. Nature 567, 7 (2019). A member of the US National Institutes of Health All of Us team collects samples from a participant. “We need to understand people’s expectations, and where the boundaries should be.” COURTESY OF THE NATIONAL INSTITUTES OF HEALTH ALL OF US RESEARCH PROGRAM © 2019 Springer Nature Limited. All rights reserved.© 2019 Springer Nature Limited. All rights reserved. 136 Vol.:(0123456789) 1 3 CSIT (April 2023) 11(1):3–9 https://doi.org/10.1007/s40012-023-00375-0 ORIGINAL RESEARCH The Ayushman Bharat Digital Mission (ABDM): making of India’s Digital Health Story R. S. Sharma 1 · Aishwarya Rohatgi 2 · Sandeep Jain 2 · Dilip Singh 2 Received: 3 February 2023 / Accepted: 14 March 2023 / Published online: 31 March 2023 © CSI Publications 2023 Abstract Technology is being leveraged worldwide to deliver services to citizens in all domains, including healthcare. The COVID-19 pandemic has pushed everyone to embrace digital transformation and reconsider current healthcare trends. In response to the emerging need for digitization of healthcare in India, the Ayushman Bharat Digital Mission was launched in September 2021. It creates and uses Digital Public Goods in increasing the availability, accessibility, affordability and acceptability of health care through different building blocks. The purpose of this mission is to establish a national digital health ecosystem that is integrated, effective and inclusive. The interoperable frameworks, open protocols and consent artefact enable citizens, public and private healthcare providers, digital innovations and other stakeholders to come together and drive equitable digitization of healthcare across the country. Keywords Ayushman Bharat Digital Mission (ABDM) · Digital Health and India 1 Introduction Healthcare is at an inflection point in India. Digital tech- nology is emerging as an enabler to ensure accessible, affordable, and quality health services, supporting the goal of achieving of universal health coverage (UHC). Digitiza- tion across industries is rapidly increasing and is inevitably being embraced. The intersection of technology and health around the world has exhibited the potential to augment cur- rent models of delivery of care, steer them toward patient centricity, and improve overall health outcomes. 2 Global Digital Health Practices A broad overview of global best practices in digital health can lend an informed understanding of how the world imple- mented e-health initiatives. The NHS of the UK, one of the highest ranked health service models, adopted digitisa- tion beginning with an NHS electronic care records which allowed sharing of patient records with their consent. This streamlined the process for general physicians and other staff working in primary care to schedule appointments with doctors at hospitals, providing a system for electronic transmission of prescriptions, exchange of patient data, and electronic referrals to higher centres. The NHS architecture represents an easily replicable model in designing digital architecture for health and social services [1]. Australia became the first country to develop a popu- lation-centric approach to implement My Health Record (MHR), a national repository of electronic health histories of patients, built with the goal of easing the patient’s journey to seek care. To curb fears of data breaches and mistrust among people, MHR provided the flexibility to opt in or opt out as and when patients consider it appropriate, at any time point. This strategy imparts important lessons for India where personal data protection, consent, and health data pri- vacy are critical issues [2]. South Korea’s Ministry of Health developed a master plan for National Healthcare Information and Communication Technology about two decades ago. In Korea, healthcare institutions have become increasingly digitized, with almost *Aishwarya Rohatgi riya1774@gmail.com; yp1.ceooffice@nha.go v.in 1 Former CEO, National Health Authority, MoHFW, New Delhi, India 2 Young Professional National Health Authority, MoHFW, New Delhi, India 137 4 CSIT (April 2023) 11(1):3–9 1 3 all hospitals adopting computerized provider order entry sys- tems, patient management systems, electronic health record keeping, and insurance claim systems that use electronic data interchange, enabling better clinical decision support and access to healthcare. The promising ICT intervention in Korean healthcare institutions provides important lessons for our country, which is currently developing a digitally enabled health claims platform [1]. Estonia began its digital transformation of its healthcare system approximately 25 years ago with the unified health information system, which linked public and private medical records, granted patients access to their records, and linked them to public information systems and registries. E-health technologies, electronic health records (EHRs), digital imaging, digital registration, unique identifier allocation, and e-prescriptions were built on existing public IT infra- structure and previous experiences with many cross-institu- tional digital integrations, such as e-banking, e-taxation, and e-school. The Estonian digital health experience is similar to the path India is taking to build a comprehensive digitally enabled healthcare ecosystem [1]. 3 Indian Digital Health Landscape Many Indian states like Kerala, Tamil Nadu, and Rajasthan have made significant leaps towards launching digital health initiatives. Tamil Nadu was the one of first states in the coun- try to implement a digital health program. A comprehensive state-wide Health Management Information System (HMIS) was developed with the assistance of the World Bank so that clinical, logistical, administrative processes are streamlined. This will help the state’s public health system become opera- tionally efficient [3]. Rajasthan has started e-Health initiatives in 2015 by incorporating digital initiatives under central level national health programs such as–, RMNCHA+, NIKSHAY, e-Aus- hadhi, Non-Communicable Disease programs. Health Information System for government, Computerized Human Resource Information System, E-mitra, ASHA Soft are some other digital applications rolled out to support community health workers [4]. On similar lines, Kerala had taken lead digitizing healthcare sector by launching e-Health Kerala scheme in 2017. It provides unique ID for each patient which help to create and link comprehensive medical history of the patient [5]. The private sector has evolved a lot in the last few years, and large and small players in health technology have ben- efitted from the wave of digitization in health. The rapid adoption of smartphones and the internet, combined with supportive government policies, has propelled the health market forward. In 2021, the digital healthcare market in India was estimated to be worth INR 524.97 billion. It is expected to reach INR 2528.69 Bn by 2027, growing at a CAGR of 28.50% between 2022 and 2027 [6]. However, immense fragmentation, lack of dialogue, poor data portability, and interoperability have plagued the digi- tal health domain, leading to siloed and incoherent efforts towards developing a digital health architecture for India [7]. Furthermore, the World Health Organisation (WHO) also laid down the Global Strategy on Digital Health 2020–2025 to create a better health experience for everyone, every- where, for all ages [8] and the Indian Government, in its effort to achieve SDG 3, responded to the above-mentioned challenges by taking the initiative to build a National Digital Health Ecosystem that would complement global efforts to accelerate digital health and innovation [9]. 4 Digital Public Goods and infrastructure The adaptation of information technology across sectors reflects our digital prowess as a country. We have success- fully established Digital Public Goods (DPGs), based on the principles of equity and access [10]. With nearly 1.2 bil- lion wireless connections, 600 million smartphone users, 800 million internet connections [11], digitization is reach- ing the last mile. With more than 90% penetration of Aad- haar, it acts as the foundation of DPGs built under Digital India [12, 13]. The layers of JAM–Jandhan Bank Accounts, Aadhaar, and Mobile linked with one another plugged the leakages of government subsidies leveraging digital tools [14]. The creation of our indigenous payment protocol, Uni- fied Payments Interface (UPI) added to the success story of our digital public infrastructure [14]. Open networks and protocols, as used in other Digi- tal India initiatives, would enable interoperable connec- tions nationwide, decentralizing and securing information exchange among all stakeholders. Enabling open access among various health-care providers and patients can sig- nificantly expand demand–supply ecosystems. India’s tech- nology revolution, the change in people’s attitudes towards healthcare due to the pandemic and appropriate government interventions are testimony to the pace at which digitization is going to thrive in the near future. 5 Innovation in Digital Health amidst the pandemic The Covid-19 pandemic had created numerous challenges for healthcare services worldwide, leading to one of the larg- est societal crises in the last century. Until the pandemic, the use of telehealth solutions, e-pharmacies, etc. was minimal. Most patients and providers preferred traditional means of in-person/offline engagement for healthcare care delivery, 138 5CSIT (April 2023) 11(1):3–9 1 3 but lockdown and physical restrictions led to an increased demand for digital health solutions, underscoring the need for better incorporation of cutting-edge digital technologies into healthcare services in areas such as telemedicine, sur- veillance and remote clinical management [15]. Among some notable public digital solutions built amidst the Covid-19 pandemic include the Covid Vaccine Intel- ligence Network (CoWIN) and Aarogya Setu [16]. CoWIN enabled the registration of around a billion people with vac- cines and the administration of more than 1.78 billion doses of the Covid-19 vaccine, which could be tracked remotely [17]. With many countries interested in using the open source technology of the application in their vaccination drives, the CoWIN digital certificate became a secure and trustworthy proof of universal vaccination [18]. The Ministry of Electronics and Information Technol- ogy developed Aarogya Setu, another digital application that guided our nation’s efforts to manage Covid, in col- laboration with the private sector. Real-time information on active cases and containment zones was sent to front-line workers and regular people, helping them assess the risk in their communities, making information exchange easier in emergency situations [16]. Around 85% of clinicians used teleconsultation during the lockdown, and 65% of doctors said they would continue to use telemedicine in the post-Covid era, according to a Boston Consulting Group survey [19]. This transition from in-person medical visits to telehealth solutions denotes not just an increase in patient uptake but also an expansion of the market’s supply of digital solutions. Therefore, as evidenced by rising engagement as well as public and private investment in digital healthcare, India is emerging as one of the leaders with enormous growth potential in this domain. 6 The making of ABDM Digitisation in the Indian health landscape began with the government’s intent and vision of providing quality health- care using accessible and affordable technology through the National Health Policy in 2017 [20]. In 2018, NITI Aayog released the National Health Stack that envisaged the crea- tion of common public goods for healthcare [9]. Based on these recommendations, the National Digital Health Blue- print was launched in 2019 laying out the architectural framework for an integrated national digital health ecosys- tem [21]. The vision of the policies, combined with a deter- mination to effectively address our current health challenges, sowed the seeds for the Hon’ble Prime Minister’s Ayushman Bharat Digital Mission (ABDM), which was launched in September 2021 [22]. Technology is persistently employed in the ABDM to streamline procedures and improve the availability, afford- ability, accessibility, inclusiveness, and safety of healthcare. This mission has combined best practices from around the world and redesigned systems to align with the Indian healthcare context. ABDM’s architecture is based on com- mon protocols that serve health needs, includes privacy by design, and employs a federated architecture. The federated nature allows for the flow of current and future health infor- mation through the system, such as between providers and patients, wearables and EHR/EMRs, consumers and phy- sicians, labs, institutions, and payers and not get centrally stored. This allows for multiple entities to securely manage health data about users, allowing it to sit at the source and be accessible on demand [22]. The ABDM safeguards the autonomy and privacy of per- sonal health information being shared by patients to health professionals through the Health Information Exchange and Consent Manager (HIE–CM). It refers to digital sys- tem which facilitates exchange of health information and management of consent. Through these means, the ABDM envisions an open, interoperable, secure and standards-based digital system. 7 Building blocks of ABDM India is on its way to revolutionizing healthcare in the coun- try by constructing a digital health system that will serve all citizens. There is an unmistakable need to accelerate digitization in order to bridge the existing gap between dif- ferent stakeholders in the healthcare ecosystem via digital highways in order to capitalize on the ongoing digital wave and achieve improved health outcomes, supporting Universal Health Coverage (UHC). In this quest, ABDM has rolled out key building blocks and verified registries to unite, enable, and catalyze all stake- holders in the digital healthcare ecosystem. The Ayushman Bharat Health Account (ABHA) number is the primary building block that contributes to the country’s digital health infrastructure transformation. It is a 14-digit randomly generated unique identification number that is vol- untarily generated to standardize an individual’s identifica- tion process between healthcare providers and facilities [22]. ABHA has proved to be instrumental in making paradigm changes in the digital health sector as it is based on the foun- dations of ease of operating, inclusivity, and free consent. An individual can easily create an ABHA for themselves through self-registration or with assistance from participat- ing healthcare facilities. Furthermore, each ABHA number can be linked to multiple ABHA addresses, making it easy for an individual to retrieve his ABHA details. As ABHA works on voluntary consent-based linking and sharing of 139 6 CSIT (April 2023) 11(1):3–9 1 3 personal health records (PHR), it puts full control of data in the hands of patients. A person can access their health records from admission to treatment and discharge online. This helps to create longitudinal digital health records of an individual, giving doctors a better understanding of the disease history and previous treatments [23]. ABHA Application This application enables users to man- age their Personal Health Records, which are an electronic record of a person’s health-related information that conforms to nationally recognized interoperability standards. It can be managed, shared, and controlled by the individual. The most notable feature of the PHR is that the information con- tained within it is under the individual’s control [22]. View- ing a longitudinal record, which includes all health data, lab reports, treatment details, and discharge summaries from one or more health facilities, is possible with this application. A citizen can use the ABHA application to share their records with the healthcare providers as and when required. Health Professional Registry (HPR) It is a systematic and comprehensive database of all healthcare professionals involved in the delivery of healthcare services in both mod- ern and traditional medical systems. This includes all types of doctors, nurses, paramedics, and other healthcare provid- ers. The HPR is currently registering physicians in Modern medicine, Dentistry, Ayurveda, Unani, Siddha, Sowa-rigpa, and Homoeopathy. Other healthcare professionals will soon be able to register as an allied HPR. Signing up for the HPR connects healthcare professionals to a plethora of interoperable, digitally enabled services for the distribution of healthcare activities and service delivery. In accordance with global healthcare standards, the HPR is intended to evolve into a citizen-centric and practitioner-cen- tric platform. Provision of a unique healthcare professional ID will facilitate communication with all stakeholders in the healthcare ecosystem and augment online presence and discoverability of verified professionals who can facilitate telemedicine in India [24]. Health Facility Registry (HFR) This is a comprehensive repository of health facilities across the country in various medical systems. Hospitals, clinics, diagnostic laborato- ries, imaging centers, pharmacies, blood banks, and other health-care facilities, both public and private, are examples of health-care facilities. All health facilities in India, both modern and traditional, are eligible to register with the HFR. It basically ensures that no unauthorized person has access to the health facility’s details, acting as a source of truth. The anticipated benefits of HFR include verified health facilities establishing an online presence by sharing information about available spe- cialties, services offered, contact information, and geoloca- tion, allowing individuals easier access and fostering citizen trust. Mutual access to health facility information by various entities facilitates license registration and renewal, as well as ease of empanelment with insurance agencies. As these facilities would go paperless and encourage creation of elec- tronic medical records, it would lead to seamless retrieval and ease their administrative processes [24]. Drug Registry ABDM is establishing a registry that will serve as a centralized repository for all drugs which are available and approved to be sold in the Indian market. The drug registry will focus on creating a comprehensive reposi- tory of drugs in India, which will act as a primary source of information for all other databases and lists, allowing for the exchange of standardized data across all medical systems, from Allopathy to Ayurveda. As a result, the drug registry will be an updated, single registry of all standardized medicines. Every ecosystem stakeholder is expected to use information from this central- ized pool, helping maintain authenticated drug supply. This in turn will alleviate errors while drug identification and administration, thereby improving patients’ healthcare-seek- ing experiences. By ensuring machine readability of pre- scribed drugs, the drug registry is intended to help smooth inventory flow throughout the drug supply chain over time, improving quality and eventually enabling patient-centric digitization [26]. Unified Health Interface (UHI) In a dispersed healthcare context, service seeking is challenging due to siloed infra- structure. UHI is creating an ecosystem to enable smooth communication among stakeholders on various platforms and the exchange of health data with patients’ consent to address this issue. Similar to how UPI functions in pay- ments, UHI is intended to be an open network that enables the interoperability of digital health services. Patients can find, book, conduct, and pay for services provided by a vari- ety of collaborating providers via any application of their choice through UHI enabled applications. This is in direct contrast to the way digital health services are now delivered, where patients and clinicians must interact through a single platform or application [25]. In UHI, every service transaction comprises five parties: 1. A patient who uses UHI t o get digital health services is a user. 2. An y application that a user selects to access health services is known as an end user application (EUA). Mobile applications, interactive voice response systems, virtual assistants who speak both English and the local language, and other types of technology can all be used as EUAs. 3. Healt h service providers (HSPs) include individual phy- sicians, clinics, medical facilities, testing facilities, phar- macies, and organisations that combine health services. 4. Using Healt h Service Provider Applications (HSPA) that support UHI, they offer digital health services. Any provider-facing application that enables health care pro- 140 7CSIT (April 2023) 11(1):3–9 1 3 viders to respond to EUA requests and provide digital health services is known as a “health service provider application” (HSPA). HSPAs can be independent service providers or service/business aggregators. 5. The UHI Gateway routes initial service provider discov- ery requests and responses in UHI transactions between HSPAs and EUAs [26]. UHI will provide numerous benefits to healthcare pro- viders and citizens. It will facilitate the access of citizens to health services, regardless of their location or socio-eco- nomic status. There will be improved coordination between healthcare providers, aiding to streamline the healthcare system, making it more efficient and reducing the adminis- trative burden on healthcare providers. The use of UHI will facilitate in availing accurate and comprehensive data on healthcare in India, which can be used to inform policy and improve healthcare outcomes [26, 27]. The ABDM is evolving through innovation and introduc- ing new components. One in the making is the Health Claim Exchange (HCX). The number of health insurance claims in India is set to grow exponentially over the next few years due to AB-PMJAY, a public health insurance scheme that covers 50 crore people, as well as growing retail or group health insurance coverage. Currently, much of the claim process- ing interactions between the payer, provider, and beneficiary is manual with cumbersome processes involved. It is time- consuming, expensive, and has operational overheads. The absence of requisite standards makes it fragmented, with each insurance company or their technology provider cre- ating their own standards, preventing interoperability. The current model is not scalable enough to support low-value, low-duration claims, which requires large automation to be in place for processing. This tedious process gives a poor patient experience and can lead to delay in treatment. To overcome the challenges of the health insurance industry and to improve the patient experience in deliver- ing services on time, Health Claim Exchange (HCX) plat- form formulated under the ABDM, provides an interoper- able, machine-readable, auditable, verifiable, explainable, and open standard-based communication protocol between payer, provider, and beneficiary to enable automation of the claims processing workflow for health insurance. It pro- vides an open standard for enabling automation of interac- tion between the parties, enables a high volume of claims processing, facilitates faster and verifiable payment against claims. Heal by India (HBI) is an initiative that aims to posi- tion India as a global resource for health care service pro- viders. It aims to create an online database of all types of healthcare professionals, including doctors, nurses, and pharmacists, as well as the country in which they wish to work. The HBI platform will serve as a “one-stop” portal for those seeking credible information from qualified and reputable Indian medical professionals. Once the portal is operational, recruiters from around the world will be able to search for qualified professionals based on their specialty or medical system, language, and location [28]. This will allow our healthmedical workforce to travel around the world and contribute to a global health. Under the ABDM, NHA is also developing a digital plat- form for National Organ and Tissue Transplant Organisation (NOTTO) that aims to build verified digital registries for organ donors (live and deceased), recipients, automating the organ donation process and making it faster and more trans- parent for those in need. 8 ABDM : Implementation and Adoption efforts Large scale adoption of the mission needs synergistic efforts from all stakeholders in the digital ecosystem. The primary participants who need to be engaged include-. • Citizen/Patient who are the beneficiaries of healthcare services and active users of digital health initiatives. • Healthcare Services Providers. • Direct Providers are Public Sector (Gov- ernment healthcare programs and States) and the pri- vate sector (Players in the private sector - hospitals, professionals, associations). • Indirect providers are the health technology start- ups, social enterprises, non-profits, academic and research institutions, innovators, and all the entities in the digital health entrepreneurial ecosystem. • Health care payers, such as health plan providers and insurance companies, who set service rates, collect pay- ments, process claims, and pay provider claims. • Policy Makers are responsible for establishing frame- works, policy, guidelines, and governance models within which healthcare is provided to the citizens. All of these stakeholders should find value in the offer- ings of the ABDM and be brought under the overarching ecosystem of ABDM for effective and efficient adoption of the scheme across all sectors. Since the responsibility for the delivery of healthcare rests with the states and union territories, they are the front- runners in implementing the different components of the scheme. Through driving IEC campaigns to create ABHA, registrations on HPR, HFR and disseminating massive awareness about the ABDM among people, states are tak- ing ownership of the mission. 141 8 CSIT (April 2023) 11(1):3–9 1 3 9 Scan and share National Health Authority has developed multiple use cases under ABDM. One of them which has scaled up across 450+ government health facilities across country is Scan and Share. Through scanning the hospital’s unique QR Code with their phone camera/scanner/ABHA App/Aarogya Setu App/ or any other ABDM enabled App, patients can share their profile details with the hospital. Post this, a token number (queue number) is generated and shared by the hospitals as notification to the patient’s chosen app. Simultaneously, this token number is displayed on screens placed on the OPD registration counters for patient’s convenience. Based on their token number, the patient can directly collect their outpatient slip (OP Slip) for doctor consultation, as their details were shared with the hospital at the registration desk. This service allows both old and new patients to scan a QR code and share their demographic information with the hospital, such as name, father’s name, age, gender, address, mobile number, and so on. This shortens the time spent at the OPD registration counter from on an average of 50 min to 4–5 min and provides accurate data in the hospital record. Scan and Share is a use case that aims to ease the lives of citizens when accessing healthcare services in facilities, solving for persistent problems of long queues on registra- tion, tests, and payment counters at the hospitals [29]. 10 Repurposing CoWIN and Aaraogya Setu The government intends to repurpose its two applications under its flagship scheme, ABDM, to support the overarch- ing digitization drive to transform the way public health is delivered in the country. Aarogya Setu, which began as a contact tracking app for Covid, is now being repurposed as India’s health and wellness application. CoWIN has been widely used in the implementation of the Covid-19 vaccina- tion and will now be used as a health management informa- tion system for small doctor’s clinics and nursing homes. The goal is to make access to digital health solutions easy and convenient for citizens and health professionals [29]. The NHA has envisioned the expansion of the digital health ecosystem that is being built under ABDM with suc- cessful integrations of both government and private digital health applications. This collaborative approach towards dig- itising healthcare delivery can help India achieve its goal of providing healthcare for all and help in ensuring that the benefits of ABDM reach the last mile. 11 Way forward The future of healthcare in India is digital and India is at a significant stage of implementation of the ABDM mis- sion. In the coming years, digitization would improve India’s healthcare system through -. 1. Creating reliable healthcare By building ABHA, HFR, HPR, HCX and other building blocks, ABDM intro- duces transparency and reliability into the system. Addi- tionally, it will integrate numerous digital identity ser- vices that help healthcare organisations verify patients’ identities while availing health services, thus preventing possible fraud or misuse of identity. 2. Ensuring affordability via integration of telehealth solu- tions ABHA Number helps link electronic health records facilitating access to patient’s medical history, helping doctors to make better diagnosis, reducing overall cost of treatment. Teleconsultations are making healthcare more affordable by increasing accessibility to a larger number of doctors, allowing doctors to consult patients throughout the country, solving demand and supply con- cerns. 3. Driving inclusive healthcare innovation UHI will intro- duce interoperability, and allow healthcare innovations across demographics. Similarly, to the role played by UPI, UHI will act as a market enabler and will provide multiple health services without the need to subscribe to multiple platforms. ABDM is aspiring to drive substantial change in the healthcare ecosystem of the country. With over 35 crore ABHA accounts and nearly 25 crore health records linked, 1.6 lakh HPR and nearly 2 lakh HFR created, it is clear that ABDM is being widely adopted by healthcare professionals and citizens [30]. Despite the mission’s rapid progress, more health technol- ogy players, large public and private hospitals, and laborato- ries must join forces with it. There is also a need to focus on mass publicity, consistent advocacy, and social acceptability of the mission through incentivization of key stakeholders, operationalizing pragmatic use cases that make seeking quality healthcare services convenient for the general public, thereby reducing out-of-pocket expenses. Monitoring, evaluation and impact assessment is a vital part of any government program and all initiatives under the ABDM should be continually tracked for progress and undertake mid-course correction based on evidence and results. The ABDM intends to lay the foundation for the coun- try’s integrated digital health infrastructure. It employs digi- tal highways and open networks to bridge the existing gap 142 9CSIT (April 2023) 11(1):3–9 1 3 between the various stakeholders in the healthcare ecosys- tem. The multiplicity of factors, such as the overall India’s technology revolution, the appropriate government policies and interventions in healthcare, the emergence of health- tech start-ups, the pandemic-induced impetus in digital healthcare, and the awareness among citizens of health and wellness; all create a lucrative opportunity in healthcare. This makes ‘now’ the right time to accelerate digitisation in healthcare and spearhead health equity. Digital health is likely to be the central pillar to influence care models, deliver value-based services throughout the healthcare continuum in India, and have a cascading impact on all stakeholders within the ecosystem. Citizens, health- care providers, innovators, government, and civil society organisations all need to reposition themselves in this digi- tally driven ecosystem and support the Ayushman Bharat Digital Mission in empowering citizens with the information and tools so that they take control of their own health. Acknowledgments National Health Authority, MoHFW, India. Declarations Conflict of interest All authors declare that they have no conflicts of interest. References 1. Best Practice Study IQVIA Deliverable.pdf 2. Burke T (2018) Opt in or opt out of My Health Record at any time in your life. Australian Digital Health Agency Developer Centre. https:// devel oper. digit alhea lth. gov. au/ resou rces/ news/ opt- or- opt- out- my- health- record- any- time- your- life. Accessed 15 Dec 2022 3. Howthe Tamil Nadu Health System was transformed to a paperless health system injust 10 years.https://blogs.worldbank.org/health/ how-tamil-nadu-health-system-was-transformed-paperless- health-system-just-10-years. https:// blogs. world bank. org/ health/ how- tamil- nadu- health- system- was- trans formed- paper less- health- system- just- 10- years.Accessed 22 Jan 2023 4. List of e-Health initiatives in Rajasthan | National Health Portal of India. https:// www. nhp. gov. in/ list- of-e- health- initi atives- in- rajas than-_ pg. Accessed 30 Jan 2023 5 . E-healt h project to make major changes in Kerala’s health sector. OnManorama. https:// www. onman orama. com/ busin ess/ news/e- healt h- proje ct- make- major- chang es- in- kerala- health- sector. html. Accessed 22 Jan 2023 6. ltd R and M. Digital Healthcare Market in India—Research and Markets. https:// www. resea rchan dmark ets. com/ repor ts/ 57234 20/ digit al- healt hcar e- market- in- india. Accessed 30 Jan 2023 7 . Azam ML (2021) N ational Digital Health Mission and the real challenges in the health care sector in India (GS 3, Economics, The Hindu, Indian Express). Plutus IAS. https:// plutu sias. com/ natio nal- digit al- health- missi on- and- the- real- chall enges- in- the- healt h- care- sector- in- india- gs-3- econo mics- the- hindu- indian- e xpre ss/. Accessed 19 Jan 2023 8 . gs4dhdaa2a 9f352b0445bafbc79ca799dce4d.pdf. https:// www. wh o. int/ docs/ defau lt- source/ docum ents/ gs4 dh daa2a 9f352 b0445 bafbc 79ca7 99dce 4d. pdf. Accessed 19 Jan 2023 9. National Digital Health Mission | Make In India. https:// www. makei nindia. com/ natio nal- digit al- health- missi on. Accessed 19 Jan 2023 10. Digital Public Goods. Sattva Consulting. https:// www. sattva. co. in/ ski/ digit al- public- goods/. Accessed 19 Jan 2023 1 1. P erformance Indicators Reports. Telecom Regulatory Authority of India. https:// www. trai. gov. in/ relea se- publi cation/ repor ts/ perfo rmance- indic ators- repor ts. Accessed 19 Jan 2023 12. Aadhaar Dashboard. https:// uidai. gov. in/ aadha ar_ dashb oard/. Accessed 21 Jan 2023 13. admin. Digital India. https:// digit alind ia. gov. in/. Accessed 21 Jan 2023 14. UPI: Unified Payments Interface—Instant Mobile Payments | NPCI. https:// www. npci. org. in/ what- we- do/ upi/ produ ct- overv i ew. Accessed 21 Jan 2023 15. Meskó B, Drobni Z, Bényei É, Gergely B, Győrffy Z (2017) Digital health is a cultural transformation of traditional healthcare. mHealth 14(3):38 16. Aarogya Setu. https:// www. aarog yasetu. gov. in/. Accessed 21 Jan 2023 17. CoWIN Dashboard. https:// dashb oard. cowin. gov. in/. Accessed 21 Jan 2023 18. CoWIN to go global today, 50 countries show interest | Latest News India—Hindustan Times. https:// www. hindu stant imes. com/ india- news/ cowin- to- go- global- today- 50- count ries- show- inter est- 10162 54577 71714. html. Accessed 21 Jan 2023 1 9. H ealth Care’s New Reality Is Dynamic, Digital—and Here to Stay. BCG Global. 2021. https:// www. bcg. com/ publi catio ns/ 2021/ dynam ic- and- digit al- new- reali ty- for- health- care. Accessed 25 Jan 2023 20. national_health_policy_2017.pdf. https:// www. nhp. gov. in/ nhpfi les/ natio nal_ health_ policy_ 2017. pdf. Accessed 25 Jan 2023 21. National_Digital_Health_Blueprint_Report_comments_invited. pdf. https:// www. nhp. gov. in/ NHPfi les/ Natio nal_ Digit al_ Health_ Bluep rint_ Report_ comme nts_ invit ed. pdf. Accessed 25 Jan 2023 22. NDHM Sandbox. https:// sandb ox. abdm. gov. in/ docs/ archi tectu re. Accessed 1 Feb 2023 23. ABHA Number. https:// healt hid. ndhm. gov. in/. Accessed 28 Jan 2023 24. HFR. https:// facil ity. abdm. gov. in/. Accessed 29 Jan 2023 25. NHA | Official website Ayushman Bharat Digital Mission. https:// abdm. gov. in/. Accessed 25 Jan 2023 26. UHI_Consultation_Paper_60a9201c1 d.pdf. https:// abdm. gov. in: 8081/ uploa ds/ UHI_ Consu ltati on_ Paper_ 60a92 01c1d. pdf. Accessed 29 Jan 2023 27. NHA | Official website Ayushman Bharat Digital Mission. https:// uhi. abdm. gov. in/. Accessed 29 Jan 2023 28. “Heal by India” initiative: Govt readying exhaustive online registry of Indian healthcare workers. The Economic Times (2022). https:// econo micti mes. india times. com/ news/ india/ heal- by- india- initi ative- govt- ready ing- exhau stive- online- regis try- of- indian- healt hcare- worke rs/ artic leshow/ 91868 438. cms? from= mdr. Accessed 29 Jan 2023 29. https:// pib. gov. in/ Press Relea sePage. aspx? PRID= 18873 53 30. ABDM-Insights. https:// dashb oard. abdm. gov. in/ abdm/. Accessed 28 Jan 2023 Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. 143 UNIVERSAL ACCESS TO INTERNET BASED INFORMATION The Ayushman Bharat Digital Mission of India: An Assessment Udaya Shankar Mishra a , Suryakant Yadav b , and William Joe c a Department of Epidemiology and Biostatistics, International Institute for Population Sciences, Mumbai, India; b Department of Bio-Statistics and Epidemiology, International Institute for Population Sciences, Mumbai, India; c Population Research Centre, Institute of Economic Growth, Delhi, India ABSTRACT India launched the Ayushman Bharat Digital Mission (ABDM) in 2021 to strengthen the digital health ecosystem by developing and integrating health data records and registries. We apply the health system control knob framework to assess the progress of ABDM by analyzing five indicators. Data from the ABDM dashboard reveal notable progress in beneficiary registration (400 million, as of June 3, 2023) and health records linkage (273 million). The registrations of over 208,000 health facilities and 190,000 health care professionals have been verified by ABDM. However, inter-state variation in progress is significant, particularly in health facility and health professional registration. Going forward, ABDM should expand its strategic framework to ensure that more health facilities and health professionals are registered, as registration is important to influence the payment, organization, and regulation control knobs. These actions are related to the achievement of final health system goals: improved health status, financial risk protection, and beneficiary satisfaction. ARTICLE HISTORY Received 5 March 2024 Revised 7 August 2024 Accepted 9 August 2024 KEYWORDS ABDM; control knob framework; digital health; India; teleconsultations The World Health Organization (WHO) defines digital health as the “field of knowledge and practice associated with the development and use of digital technologies to improve health.” 1 Digital health offers considerable opportunities to support the delivery of organized and efficient health care services. Digital health can also be instrumental in the early detection of and response to epidemics and pandemics. Digital health innovations have additional virtues, including minimizing direct and indirect costs through health-related information. 2 Given the tremendous potential scope of digital health, the Global Strategy for Digital Health (2020–25) endorsed by the 73rd World Health Assembly 2020 calls for sufficient investments in workforce, institu - tional, and governance capacity across countries to allow rapid adoption of digital health technologies. 1 National digital health agendas should be sensitive to specific individual countries’ capacities while also cham - pioning the core principles of accessibility, confidenti- ality, interoperability, privacy, replicability, scalability, security, and transparency. 1 Adoption of digital health technologies by health care providers, health industry professionals, patients, and consumers is governed by the national health sector and health strategies. Several low- and middle-income countries, including India, have adopted a multi-pronged approach to digital trans - formation of health care services. 3 India launched the Ayushman Bharat Digital Mission (ABDM) in 2021 to pursue the digital health agenda with an initial focus on strengthening the digital health eco-system for data, information, and infrastructure services. After provid - ing background on ABDM, this paper presents an assessment of the progress of the mission thus far, focusing on selected parameters of development and impact. Overview of the Health System of India The structure of India’s health system is primarily based on the recommendations of the 1946 Health Survey and Development Committee chaired by Sir Joseph Bhore. The Committee envisioned a predominant role for the government in health care, whereby public health services were organized in a three-tiered system (providing primary, second - ary and tertiary care) and were delivered via a network of doctors and public health workers. However, resource constraints and evolving policy frameworks for efficiency and equity later facilitated the development of the private sector in health, which has gradually transformed into a major source for health care services in India. By the early part of the twenty-first century, the health system in India was characterized by a diverse range of health care CONTACT Udaya Shankar Mishra udayamishra64@gmail.com Department of Epidemiology and Biostatistics, International Institute for Population Sciences, Govandi Station Road, Deonar, Mumbai 400088, India HEALTH SYSTEMS & REFORM 2024, VOL. 10, NO. 2, 2392290 https://doi.org/10.1080/23288604.2024.2392290 © 2024 The Author(s). Published with license by Taylor & Francis Group, LLC. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent. providers, both public and private sectors, that oper- ated with varying capacities while offering general to specialized services. In the Indian health system, 30.1% of medical consultations are conducted in the public sector. Private doctors in clinics and private hospitals account for the remaining 42.5% and 23.3% shares, respectively. 4 Annually, 29 persons per 1,000 popula- tion in India are estimated to be hospitalized, with the majority (55.3%) of these hospitalizations occur- ring in the private sector. The public sector also offers a range of health care services, but its financial constraints and inadequate infrastructure affect the coverage and quality of services in the public health sector. The total health expenditure of India amounts to 3.3% of its GDP. 5 Estimates from the 2019–2020 National Health Accounts show that the central and the state governments together account for 41.4% share of total health expenditure. Thus, public health expenditure is equivalent to 1.35% of the GDP of India. An overwhelming 47.1% of total health expenditure is incurred as direct out-of-pocket payments by households. The private health care sector in India is heteroge- neous in its composition and service delivery models. In particular, the sector is highly skewed. It is partly com- prised of high-end tertiary care facilities catering to economically well-off households and represents private doctors and clinics providing services to a vast majority of patients. The private sector also includes informal and unqualified providers serving patients from rural, disadvantaged, and low-income households. Steering financing and human resources to the health sector has been a priority for health policy and planning. In this regard, the National Health Policy (NHP) of India (most notably in 1983, 2002 and 2017) periodically lays out government health priorities and guides the overall policy approach toward the health sector. The 2017 NHP reviewed overall improvements in maternal and child health outcomes and identified the growing burden of non- communicable diseases and some infectious diseases as priority areas for policymaking. 6 The 2017 NHP specifically noted concerns related to coverage and quality of health care services in India and provided a roadmap for increased public health investments and collaborative actions in the health sector. In this area, the NHP 2017 specifically recognizes the integral role of technology in health care delivery and envi- sions the setting up of a dedicated institutional mechanism to develop, deploy, and regulate digital health across the continuum of care. The Genesis of the ABDM The 2017 NHP mandates linking public and private health care providers through a national health infor- mation architecture. It proposed strengthening health data infrastructure through a health information exchange platform and the development of various registries of providers, patients, provider, diseases, ser- vices, and vital events. The 2017 NHP envisaged digital support both for existing initiatives, such as “Aadhaar” (a unique ID for all residents of India based on bio- metric and demographic data), and for new programs, such as a National Optical Fiber Network (for providing connectivity to rural areas). Further, the 2017 NHP advocates scaling up teleconsultation across secondary and tertiary care institutions in order to facilitate con- sultations with specialists. In 2018, NITI Aayog (a think tank under the Government of India) followed up on the NHP’s recommendation with a consultation paper on a National Health Stack to consolidate health records for digital cloud-based services. 7 Subsequently, the National Digital Health Blueprint (NDHB), building on the NHP, focused on integrating localized and fragmented health data through digital services. 8 NDHB proposes a federated architecture, principles, and a five‐level system of building blocks. These are a) infrastructure to ensure that health data and exchange are secure and adhere to privacy norms; b) data hubs to rationalize the system through unique identification of persons, facilities, and organizations, using unique health identifiers and electronic health records (EHRs); c) technology building blocks for data access management, consent, and privacy; d) applica- tion building blocks that can gather, utilize, and share information from the previous layers for use in a wide range of applications (including emergency care, health care, wellness, medical education, and public health); and, e) access and delivery to various physical or virtual points for use by actors in the health system. Further, the document outlines standards for consent manage- ment, content management, interoperability, privacy, security, patient safety and data quality. Finally, the NDHB proposes setting up a National Digital Health Mission (NDHM) as the entity that will implement the proposed blueprints. The Scope of the ABDM Accordingly, the NDHM was piloted in 2020 and rolled out nationwide in 2021. The NDHM was renamed the Ayushman Bharat Digital Mission (ABDM) and is implemented under the purview of the National Health Authority (NHA), which is an apex body of the 2U. S. MISHRA ET AL. Government of India responsible for planning and inter-sectoral coordination with ministries and line departments of central and state governments, as well as with stakeholders from the private sector and civil society organizations. The main objective of the ABDM is to establish a system to manage digital health data and facilitate its seamless exchange by adhering to the stan- dards and norms prescribed under NDHM. The ABDM’s task is to develop and manage an inte- grated digital health infrastructure in the country using digital solutions to bridge gaps in the health ecosystem. 9 The ABDM is therefore aligning various health-related data records and registries by developing a federated architecture with well-defined norms for data standards and management of EHRs. The ABDM aims to improve citizen and patient services by engaging a wide range of stakeholders, including policy makers (in central and state governments), administrators (regulators and pro- gram managers), providers (hospitals, labs, and phar- macies), health care professionals (doctors and other practitioners), allied private entities (such as insurance providers and health tech companies), and nonprofit organizations (such as civil society and development partners). ABDM is expected to improve health-sector decision-making at the macro-level, as well as to provide patients with access to safe and secure medical records that can be shared across health care providers in the public and private sectors. Since its inception, ABDM has focused on five digi- talization activities: 1) Ayushman Bharat Health Account (ABHA), 2) ABHA Mobile App, 3) Health Facility Registry (HFR), 4) Health Care Professional Registry (HPR), and 5) Unified Health Interface (UHI). The first, ABHA, is a system for identification and authentication of individual patients whereby each patient is assigned a unique 14-digit number to facilitate digital access to personal health records that can be shared with compliant entities. This initiative facilitates sharing and receipt of prescriptions and diagnostic reports with verified doctors and service providers throughout the public and private sectors. The second activity, the ABHA App, facilitates beneficiary registra- tion and links a patient’s ABHA ID across various registered providers. The ABHA App provides a “digital locker” for storing health records and allows them to be shared with registered health care providers for consultation and treatment. The third and fourth activities, HFR and HPR, are the two key registries linked to ABDM. The HFR is the repository of a list of all health facilities in India provid- ing modern or traditional medicine. The HFR includes both public and private sector health facilities, including diagnostic centers and pharmacies. HFR supports geospatial mapping of health services, which adds to their visibility. It also facilitates administrative and reg- ulatory matters related to facilities’ impanelment in national programs, data exchange, and registration and license renewals. The other registry, HPR, includes health care professionals (doctors, nurses, paramedics, etc.) from the modern and traditional systems in both the public and private sectors. It enables health care professionals to connect with the digital health ecosys- tem and benefit from discoverability and teleconsulta- tion opportunities, as well as providing access to digital health records for patient care. HPR also facilitates ease in administrative processes, such as registrations and renewals. Finally, UHI serves as an open protocol for various digital health services between patients and health service providers. It enables booking of appoint- ments, teleconsultations, diagnostic services bookings, and record retrievals—and also facilitates user ratings for quality signaling. Assessing the ABDM This paper uses the control knob framework (described below) to provide an assessment of ABDM by focusing on selected parameters to gauge progress toward its mission. It includes a situation analysis of the manage- ment of the digital environment in terms of its spread and coverage across the states. Based on data from the official dashboard of the ABDM (https://dashboard. abdm.gov.in/abdm/), the assessment focuses on unevenness in coverage of ABHA, HFR, and HPR, as well as associated indicators (such as teleconsultation sessions) that aim at improving efficiency in health services. Although ABDM’s true impact can only be fully ascertained after the program stabilizes, this mid- point assessment sheds light on sub-national variations to draw insights for course corrections. Finally, the paper discusses the results within the broader context of challenges and opportunities in the transfer and exchange of digital health information. The Control Knob Framework The Control Knob Framework (CKF) focuses on “sig- nificant causal determinants of health system perfor- mance” that are amenable to adjustment or changes via government action. 10 The five control knobs that explain health system performance are financing, payment, orga- nization, regulation, and persuasion. As shown in Figure 1, financing refers to the processes (taxation, insurance premiums, direct payments, etc.) for raising financial resources for health-sector activities. Payment describes the methods and means of monetary transfers HEALTH SYSTEMS & REFORM3 to the various health care providers—these means can have a considerable bearing on providers’ behaviors. Organization encompasses the institutional and govern- ance mechanisms that shape health-sector participation and functions—it includes competition and incentives as design components in the framework. Regulation refers to the scope for and implementation of direct state inter- ventions to alter the behaviors of patients, health care providers and insurance companies. The final control knob, persuasion, focuses on activities to influence patients’ and providers’ actions on health and health care. Persuasion can range from mass media campaigns to promote key practices to specific engagements that lead to restrictions on the choice of providers. The various settings of these five control knobs can influence several intermediate outcomes that, in turn, lead to the final outcomes of the health sector: improved health status, financial risk protection, and public satis- faction. The CKF framework offers an analytical lens— this paper applies this lens to understand how various actions under ABDM influence the five control knobs of the health system, and how these contribute to and impact the intermediate and final outcomes. Data systems developed under ABDM relate directly to the payment, organization, and regulation knobs. The HFR and HPR registrations streamline digital connec- tivity for payment transactions for all providers empa- neled under various national health programs. HFR and HPR identification under the flagship public health insurance scheme—called Ayushman Bharat Pradhan Mantri Jan Arogya Yojana (AB-PMJAY)—has improved the efficiency of health services by reducing transaction costs related to time and procedures. Identification of health care providers through HPR and HFR registrations also enables better organization of health care services and supports adherence to reg- ulatory standards. For example, currently several health care facilities in India have not registered under the Clinical Establishments (Registration and Regulation) Act (CEA) of 2010. Yet compliance with CEA can improve the quality of services and thus improve patient satisfaction levels. Regulations to make HFR mandatory can therefore also force health facilities to become com- pliant with the CEA. Moreover, filtering out unqualified practitioners should improve the quality of health care services and have consequential bearing on the health status of the patients. Another example comes from the ABHA ID linkages with health facilities and providers, which can enable greater access to services in remote areas of the country through teleconsultations. This not only contributes to better quality in health care but also offers financial protection to households against unwarranted out-of- pocket payments. These teleconsultations are typically prompted by public health workers, connecting patients to qualified providers and specialists for consultations. However, the problem of information asymmetry among patients is a key concern. Often, patients rely Figure 1. The control knob framework for health sector reforms. Source: Adapted from Roberts et al. (2004) 10 4U. S. MISHRA ET AL. on word of mouth to identify and locate a suitable health care facility. Referral mechanisms among provi- ders are also sometimes inefficient, particularly when reliable institutions within the patients’ vicinity are overlooked because major centers are preferred. The digital health strategy offers a means for streamlining identification of appropriate service providers through registration, verification, and validation of individual providers and institutions. Furthermore, seamless trans- fer of and access to patient information among desig- nated health personnel is expected to minimize procedural requirements, including expenditure- inducing components such as repeat diagnostics. In line with the persuasion control knob, the ABDM can enhance the health and wellness of individuals through educating and empowering them with relevant informa- tion through digital platforms, such as the ABHA App. The UHI component of the ABDM has huge poten- tial in shaping health policymaking. The scope to aggre- gate anonymized data on health ailments and health burden can provide vital inputs for payments and reg- ulations. The variations in the cost of treatment for similar health conditions are often a major problem encountered in pricing of health packages in India. In Figure 2. State-level bivariate associations among ABHA IDs, HPR, HFR and ABHA records Linked. HEALTH SYSTEMS & REFORM5 this regard, evidence from a vast, real-time pool of transactions can provide insights for course- corrections on payment mechanisms, including creating space for piloting potential approaches to inform nego- tiations and regulations. This can directly contribute toward the efficiency of the health system and lead to improved scope for coverage of treatment with financial risk protection. The real-time monitoring can also pro- vide early alerts to prevent or contain potential infec- tious diseases. In this regard, digital health monitoring can also help circumvent future epidemics and pan- demics by fostering effective coordination and informa- tion sharing. Finally, the ABDM envisages building capacity and partnerships for the ongoing development of technology architecture as a critical process in the early phase of the mission. This strengthens the scope for regulation and persuasion by selectively adding or removing incentives and disincentives to the sharing of digital information and by restricting participation as a means to address noncompliance or unreasonable practices. Material and Methods This assessment of the progress of the ABDM is based on a desk review of reports on the ABDM website, including the 2021–22 annual report of NHA. We also reviewed program documents for background on financial and technical progress under ABDM. We then conducted an indicator assessment based on publicly available and anonymized secondary data from the ABDM website (https://dashboard.abdm.gov.in/abdm/). The ABDM dashboard provides information on several mission indi- cators, including health identification numbers created as ABHA accounts; HFR and HPR registrations; status of patient health records linked with ABHA ID; demo- graphic patterns in ABHAs created by gender and age groups; and, a list of verified facilities by sector and system of medicine. The analysis covers progress made as of May 2023. Table 1 presents the indicators selected for the pro- gress assessment of ABDM. Progress was assessed using objective quantitative indicators. The status of linkages across patient records and registration status by age and gender was reviewed by the state. The role of the public and private sectors in registration processes, as well as their respective systems of health care, was also ana- lyzed. Information on progress toward telemedicine consultations was reviewed to examine the use of digital health alternatives for service delivery. The information on selected indicators is presented as the percentage achievement of ABHA ID registra- tions, HFR registrations and HPR registrations. For comparisons across states, count-based information was converted into percentages by normalizing them with respect to state populations from the projection report of the expert group constituted by MoHFW. 11 Similarly, health facility registration status across states is compared using a denominator based on information sourced from facility registries for the respective states. We hypothesized that states performing better in one indicator are also likely to perform better in other indi- cators. To examine this, we undertook state-level bivari- ate correlations of the selected indicators, using scatter plots and Pearson correlation coefficients with stated significance levels. Finally, we also computed the Gini coefficient to examine the inter-state disparities for selected indicators. Results Financial and Technical Performance In the financial year (FY) 2020–21, ABDM had a budget allocation of Rs.30 crore (300 million), out of which 48.1% was utilized or released. In the subsequent FY (2021–22), a total of Rs.75 crore (750 million) was budgeted for the mission, out of which 56.4% was released or utilized. The ABDM’s key activities during these periods consisted of initiating various processes for the development of applications and integration of the data ecosystem through a federated architecture. The inter-operable and scalable building blocks of ABDM (namely, ABHA, HPR, HFR, and ABHA Mobile App) are live for registration with considerable uptake. ABDM conducted stakeholder consultations and capacity-building workshops, providing financial incen- tives for various stakeholders to participate in the pro- cess. State-level teams were constituted to monitor the implementation of ABDM activities. Each team is headed by a State Mission Director, who is supported by nodal officials for IT, Administration, and Coordination. Each team also has a project management unit with consultants for specific roll-out and trouble- shooting tasks. Hardware guidelines for the states were Table 1. Selected indicators for progress assessment of ABDM. IndicatorDefinition ABHA IDPercentage of ABHA ID generated ABHA Records LinkedPercentage of ABHA ID linked with health records HFR Registration Verified Percentage of HFR applications registered and verified HPR Registration Verified Percentage of HPR applications registered and verified TeleconsultationsNumber of eSanjeevani teleconsultations in public sector 6U. S. MISHRA ET AL. created and shared, with scope for modification to suit contextual requirements. As of 2021–22, there were 980 active “integrators” and 58 had received certificates for successfully integrating at least one ABDM application. Approximately 26 capacity-building programs were conducted between August 2021 and December 2022 to promote successful integration and engagement of more entities. Information, Education and Communication (IEC) initiatives were developed in order to promote greater awareness and uptake of digi- tal health initiatives by individuals and institutions. ABHA Registrations and Record Linkages ABHA registrations are open to all; accordingly, it would be considered complete if the entire Indian popu- lation registers and has an ABHA ID. This implies that the ultimate target for ABHA ID is 100% registration of the 1.4 billion population. As of May 15, 2023, a total of 376.2 million ABHA accounts had been created, approximately 48% of which are for females. Based on the overall population of 1.4 billion, ABHA is covering 26.6% of the Indian population. Coverage is better among adults than among younger people. Across age groups, 54.5% of the ABHAs were created for the 19–45- year age group, which comprises 40% of the total popu- lation. Similarly, 20.4% of the ABHAs were created for adults in the 46–59-year age group, who represent about 15% of the population. Elderly people (60+ years) have a share of about 10% in the population, but account for 12.2% of the total ABHAs. Children and adolescents below 18 years represent around 35% of the population, but account for just 12.9% of the total ABHAs created. As of May 15, 2023, 257.0 million individuals had their health records linked with their ABHAs (Table 1). This amounts to 18.2% of the total estimated population of India. Kerala (91.7%) has the highest proportion of population with health records linked, followed by Chandigarh (86.1%) and Uttarakhand (52.9%). The pro- gress in health records linkage is slow in several states and Union Territories (UTs). Table 2 shows the status of other key indicators as of May 15, 2023, disaggregated by state and compared to the projected state population (as the normative target). Table 2. Status of key ABDM indicators (as of May 15, 2023). States% ABHAs % Records Linked% Verified HFR% HPR Verified Andhra Pradesh45.548.430.310.9 Arunachal Pradesh12.910.823.217.8 Assam41.72.527.00.7 Bihar13.913.619.435.3 Chhattisgarh49.845.464.815.6 Goa25.822.017.010.8 Gujarat38.417.427.11.2 Haryana30.625.45.70.8 Himachal Pradesh26.128.453.43.8 Jharkhand16.928.712.77.4 Karnataka31.111.993.916.8 Kerala39.991.711.813.5 Madhya Pradesh47.422.719.10.8 Maharashtra18.010.79.42.6 Manipur15.221.21.0NA Meghalaya6.29.535.8100.0 Mizoram27.634.416.713.2 Nagaland22.314.73.70.6 Odisha52.77.30.00.2 Punjab18.328.212.76.0 Rajasthan21.88.80.00.1 Sikkim47.00.246.933.3 Tamil Nadu7.32.70.00.1 Telangana24.36.317.51.2 Tripura9.227.13.82.9 Uttar Pradesh14.710.718.914.2 Uttarakhand27.252.97.811.7 West Bengal28.76.00.00.1 Union Territories A & N Islands100.057.273.0NA Chandigarh52.186.128.6100.0 Delhi30.729.62.916.5 D&N Haveli/Daman & Diu70.844.888.1NA Jammu & Kashmir46.738.335.926.1 Ladakh98.345.10.0NA Lakshadweep100.01.3100.0NA Puducherry58.119.529.4100.0 India Overall26.618.220.38.2 Source: Author estimates based on ABDM dashboard. Denominators are from various MoHFW reports. HEALTH SYSTEMS & REFORM7 The UTs (including the Andaman and Nicobar Islands (100%), Ladakh (98.3%) and Lakshadweep (100%)) have essentially achieved universal coverage of ABHAs. Among the major states, five display higher coverage than other states: Andhra Pradesh (45.5%), Assam (41.7%), Chhattisgarh (49.8%), Madhya Pradesh (47.4%), and Odisha (52.7%). The lowest estimated coverage of ABHAs is in Meghalaya (6.2%), followed by Tamil Nadu (7.3%) and Tripura (9.2%). Given their vast populations, coverage in Bihar (13.9%) and Uttar Pradesh (14.7%) is also low. HFR and HPR Registrations Registrations of HFR and HPR are also expected to cover all formal health-sector facilities in the public and private sectors (including hospitals, private clinics, diagnostic centers, and pharmacies). Information is col- lated from various sources to provide the normative denominators for estimating coverage (against a target of 100%). As of May 15, 2023, over 206,000 health facilities (20.3%) were verified under HFR. Among the verified health facilities, 25.7% are from the private sector, whereas the bulk (74.3%) are from the public sector. Of these verified facilities, 85.1% provide modern medicine, 7.3% ayurveda, 2.9% dentistry and 2.3% homeopathy. Physiotherapy (1.5%), Unani (1.7%), Siddha (0.1%) and Sowa-Rigpa (0.1%) have small shares. Among major states, 93.9% of the health facil- ities in Karnataka and 64.8% in Chhattisgarh were verified. Progress in verifying providers in the HPR is slow. Just over 8% of professionals had been verified nation- wide. Bihar shows the highest percentage (35.3%) of health professionals verified per HPR. As of June 3, 2023, over 295,000 applications had been submitted by professionals seeking verification, 65% of whom had been verified. Among the verified cases, 89.9% of pro- fessionals adhere to the modern medicine system and 6.2% are from the ayurveda system. Dentists and homeopathy professionals had also been verified, accounting for about 3% of the verified professionals. State-Level Associations of Key Indicators We hypothesized that states with higher coverage in any one of the four indicators should also achieve higher coverage in other indicators. Figure 2 shows the associa- tions among four selected indicators: % of ABHA IDs, % of HPR, % of HFR and % of ABHA records linked. The scatter plots presented in Figure 2, however, suggest that there is little consistency in the associations across all four indicators. Pearson correlation coefficients were then computed to examine the statistical significance of bivariate state-level associations. Table 3 shows that the strength of the state-level correlation is significant in the case of ABHA IDs created and health records linked. The strength of the association is greater (correlation coefficient = 0.520) in the case of ABHAs created and percentage of health facilities verified. Finally, the Gini coefficient was computed to exam- ine the disparities in state-level coverage of the four indicators. A higher value Gini coefficient would reveal higher inter-state variation. The Gini coefficient for inter-state variations in the four selected indicators is: ABHAs creation (Gini = 0.351), health records linkage (Gini = 0.442), HFR verification (Gini = 0.464), and HPR verification (Gini = 0.669). These results show that inter-state disparities in HPR verification are the highest, implying that the progress in some states is much higher than in others. The lower Gini coefficient for ABHA ID creations implies relatively lower inter- state differences, and therefore more similar levels of progress. eSanjeevani Teleconsultations No specific targets have been set by ABDM for teleconsultations. As of June 30, 2022, 92115 Health Sub-Centers (SCs), 22896 Primary Health Centers (PHCs) and 4,726 Urban Primary Health Centers (UPHCs) were connected through the eSanjeevani teleconsultation system. An assessment of teleconsul- tation services being provided across states suggests that the uptake and practice are uneven across states. The total of 100.0 million cases of eSanjeevani Table 3. Correlation between state-level progress across selected indicators. % ABHA IDs% HR Linked% Verified HFR% Verified HPR % ABHA IDs1.000 (N)(36) % HR Linked0.312*1.000 (N)(36)(36) % Verified HFR0.520***0.0601.000 (N)(36)(36)(36) % Verified HPR0.2170.2420.2801.000 (N)(31)(31)(31)(31) *** and * denotes significance at 1% and 10% level, respectively. State/UT numbers in parenthesis (). 8U. S. MISHRA ET AL. consultations is substantial, but represents a tiny fraction of the over 4 billion annual outpatient con- sultations in India. As shown in Table 4, the bulk of these teleconsultation calls were conducted through SCs and PHCs that have been transformed under the Ayushman Bharat Health and Wellness Center (AB- HWC) program. Most teleconsultations took place in the South Indian states of Andhra Pradesh (36.8%), Karnataka (16.4%), Tamil Nadu (14.8%), and Telangana (12.1%). In addition to having no target to compare these numbers to, no disaggregated information is available on the overall magnitude of outpatient consultations across the public and pri- vate sectors by state to facilitate comparisons of progress across states. Discussion Five salient findings emerge from this assessment. First, in a short span of time, ABDM has progressed to cover over 400 million individuals (as of June 3, 2023) with ABHA ID accounts. Second, ABDM has linked the health records of 273 million individuals with their ABHA IDs. Third, over 208,000 HFR and 190,000 HPR registrations have been verified by ABDM. Fourth, there is considerable inter-state variation in progress across key performance indicators, particularly in HFR and HPR registrations. Finally, there is signifi- cant room to boost both budgetary allocations and utilization in order to accelerate progress under ABDM. Thus, the ABDM is steadily progressing toward its basic objectives. This is apparent from the evidence on registrations. Progress in building the capacity of tech- nology integrators, health records linkages, and increas- ing volume of digital transactions by validated facilities are all also evidence of progress. ABDM, however, also needs to overcome the inertia inherent in the federal structure of the health system and the political economy of the health sector. This is appar- ent from inter-state variations in progress toward cover- age of various types of registrations. The inter-state variations in HPR and HFR could be reduced through Table 4. eSanjeevani teleconsultations as a proportion of state population, India. State/UT% Consultations% AB_HWC% OPD Andhra Pradesh36.836.80.04 Arunachal Pradesh--0.03 Assam32.90.08 Bihar2.62.50.05 Chhattisgarh2.92.9- Goa--0.02 Gujarat4.32.91.36 Haryana1.30.70.59 Himachal Pradesh3.83.80.07 Jharkhand1.71.60.03 Karnataka16.411.94.53 Kerala1.90.51.37 Madhya Pradesh4.84.80.01 Maharashtra3.83.70.16 Manipur1.310.25 Meghalaya1.71.7- Mizoram0.40.30.01 Nagaland0-- Odisha1.51.5- Punjab1.21.20.01 Rajasthan0.90.70.13 Sikkim2.42.4- Tamil Nadu14.812.72.09 Telangana12.1120.05 Tripura0.30.3- Uttar Pradesh2.41.60.78 Uttarakhand7.91.46.51 West Bengal12.212.20.01 Union Territories A & N Islands0.100.02 Chandigarh4.131.15 Delhi0.2-0.2 D&N Haveli/Daman & Diu10.210.20.01 Jammu & Kashmir2.61.70.99 Ladakh8.28.10.03 Lakshadweep0.80.8- Puducherry0.10.1- India Overall7.16.40.69 Source: Authors, based on eSanjeevani national telemedicine service (MoHFW) (as of February 16, 2023) HEALTH SYSTEMS & REFORM9 greater engagement by the NHA with states where regis- trations and validations are progressing at slower paces. At the same time, the mission needs to enhance its financial efficiency in terms of budgeting and utilizing earmarked funds. As noted from the annual financial statements, the current levels of utilization under ABDM are low. Incentive schemes for HFR should also be further reviewed to promote broader uptake by stake- holders. A large network of private sector providers remains to be tapped, along with designing a structure to incentivize registration by nodal individuals. Our analysis focused on five selected indicators. Of these, HPR and HFR are expected to have the most direct effects on the payment, organization, and regulation con- trol knobs. Progress on HPR and HFR is varied across states. This implies that achieving ultimate outcomes related to improved health status, financial risk protec- tion, and public satisfaction may be tied to the political economy struggles that affect HPR and HFR registra- tions. These findings call for a review of the procedural bottlenecks that impede registrations across public and private sector. Furthermore, the scope for major and obvious impacts by the digital health mission hinges on addressing con- cerns that are not necessarily within the purview of the mission (such as the infrastructure investments required to enable digital health). For instance, the public sector accounts for a major share in health care service delivery in India (in terms of patients, doctors, and health care facilities). The digital infrastructure capacity in these facilities needs considerable investment. Government spending on health is equivalent to approximately 1.35% of India’s GDP. The central government provides one-third of total government health spending and the state governments contribute the rest. Given past trends and the challenging fiscal environment across Indian states, it seems unlikely we will observe a boost in health care spending by the government. 12 However, prioritiz- ing digital infrastructure investments would be a strategic decision, especially in view of competing investment options, such as insurance schemes or programs provid- ing free medicines and services that are gaining popular- ity across several states. Engaging the private sector in digital health is another important task. ABDM’s initial focus has been on the public sector, but it is critical for the vast, yet fragmented, private sector in the health system to be integrated within the digital health framework. Incentive schemes may need to be redesigned to better motivate the private sector to participate in ABDM registration processes. It would be worthwhile to conduct state-level stakeholder consul- tations focusing on the private health sector’s concerns to promote active participation. The CKF framework emphasizes achieving inter- mediate goals—of access, quality, and efficiency—in order to reach the health system’s ultimate goals. The recognition of digital health as a complementary strat- egy for achieving improved health and health care is an important qualitative impact of ABDM. For example, the increasing number of teleconsultations under eSanjeevani holds huge promise for achieving inter- mediate goals for the vast rural population that remains underserved and deprived of quality health care. The COVID-19 pandemic recently helped shift focus to, and demonstrate the potential of, telemedicine in India, which had previously lacked a legal framework and credibility. Consequently, teleconsultations are now considered a viable and acceptable alternative for out- patient care in remote facilities. Staff nurses and com- munity health officers can connect with medical doctors for teleconsultations on the few more complex patients. While this is now considered a routine activity, the numbers are still nominal. Scaling up the eSanjeevani teleconsultation service in India therefore offers consid- erable potential to expand access to doctors in rural and underserved areas. Expanding the scope of eSanjeevani services is feasible using a hub-and-spoke model, whereby medical college hospitals and large government hospitals could serve as hubs for multiple PHCs. However, with increasing frequency of calls, it is critical for this initiative to be independently evaluated—for its impact, to address access barriers and to enhance the effectiveness of the service. ABDM has been planned with a coherent set of strategies, which in principle are feasible to implement and scale up across the country. However, the strategy could still go further in detailing actions to have more impact on a few critical barriers. As noted in the 2021– 2022 Annual Report of the NHA, there are three critical barriers to adoption of the ABDM. One is its depen- dency on ecosystem players to create ABDM-compliant technologies and solutions. Also, the health system of India currently lacks widespread digitalization and gen- erally operates as a fragmented ecosystem that is neither cost-effective nor user-friendly. The status and func- tioning of existing information management systems is sub-optimal across several contexts. 13 While these issues are being addressed through ABDM’s investments and capacity building for stakeholders, ecosystem inertia is a major concern (and one whose solutions are perhaps beyond the scope of the NHA). Lack of interest on the parts of facilities, professionals, and their representative associations could affect the achievement of the ultimate objective of the mission. Second, and notwithstanding the facility of consent management for data sharing, protecting this vast 10U. S. MISHRA ET AL. amount of clinical information and the computer sys- tem is a contentious concern. These important concerns should be addressed while planning integration of digi- tal records. 14 Similar protocols should also be applied when planning to integrate disease registries (such as the cancer registry) to improve prevention and control efforts under national programs. 15 Finally, capacity building across all critical domains is necessary, includ- ing the digital literacy of the population. ABDM could plan to adopt a broader community health perspective, bringing health and health-related sectors and programs together under the digital health agenda. 16 It is too early to discuss the potential sustainability of ABDM, as several of its strategies and implementation modalities are still being developed. In addition to the supply-side push to pursue the digital health agenda, the initiative is sensitive to demand-side factors, including individuals’ valuation of health (which is guided by their preferences, but also conditioned by the availability of health infrastructure involving institutions, human resources for health and, above all, access in terms of costs and pricing). There are clear benefits of digitaliza- tion, including savings in terms of both patient discom- fort and costs. However, interoperability of systems remains a major challenge worldwide. India can expect to leapfrog on the digital front, as IT is a priority and natural partner in India’s recent developmental performance. 17 Conclusion This assessment of ABDM observes considerable advances in the governance mechanisms and federal collaborations required for the transfer of digital health information. These necessary and immediate tasks are key markers of progress under the mission. Another part of the digital health strategy, engagement of com- munities and health care workers, has been successfully leveraged by ABDM to increase ABHA ID registrations. ABDM has created several digital public goods, forming the building blocks for strengthening the national digital health ecosystem. However, the federal structure of gov- ernance and differential strength of multiple health sys- tems have at times adversely influenced implementation. This is apparent from the slow pace of HPR and HFR registrations across the country. Going forward, training and capacity building for state-level health functionaries and data managers is critical to build upon the early progress of ABDM. We also recommend that ABDM regularly conduct public consultations to allay fears related to consent, privacy, data confidentiality, data security, data sharing norms, grievance redressal, and effective utilization of health services. Acknowledgments The authors are thankful to the Editor and the two anon- ymous reviewers for the helpful comments and suggestions. An earlier version of this paper was presented at the 40th Anniversary Takemi Symposium on “Digital Health: Opportunities and Challenges for Global Health,” held on 20–21 October 2023, in Boston, MA, at Harvard University. The Symposium was organized by the Takemi Program in International Health at the Harvard T.H. Chan School of Public Health, with support from the Japan Medical Association and sponsorship from the Japan Pharmaceutical Manufacturers Association, the Takemi Memorial Trust for Research of Seizon and Life Sciences, and the Pharmaceutical Research and Manufacturers of America. We also thank the participants at the 40th Anniversary Takemi Symposium. Disclosure Statement No potential conflict of interest was reported by the author(s). Funding The author(s) reported that there is no funding associated with the work featured in this article. ORCID Udaya Shankar Mishra http://orcid.org/0000-0003-3900- 0342 Suryakant Yadav http://orcid.org/0000-0003-1579-9524 William Joe http://orcid.org/0000-0003-3282-658X References 1. World Health Organization. Global strategy on digital health 2020-25. Geneva: World Health Organization; 2021. 2. Mitchell M, Kan L. Digital technology and the future of health systems. Health Syst Reform. [2019 Apr 3];5 (2):113–120. doi:10.1080/23288604.2019.1583040 . 3. Labrique AB, Wadhwani C, Williams KA, Lamptey P, Hesp C, Luk R, Aerts A. Best practices in scaling digital health in low and middle income countries. Global Health. 2018 Dec;14(1):1–18. doi:10.1186/s12992-018- 0424-z . 4. NSSO. Key indicators of household consumption on health in India (NSS 75th round). National sample survey office (NSSO). New Delhi: Ministry of Statistics and Program Implementation, Government of India; 2019. 5. NHSRC. National health accounts estimates for India, 2019-20. New Delhi: NHSRC; 2023. 6. MoHFW. National health policy 2017. New Delhi: Ministry of Health and Family Welfare, Government of India; 2017. 7. NITI Aayog. National health stack: strategy and approach. New Delhi: NITI Aayog; 2018 [Accessed HEALTH SYSTEMS & REFORM11 2024 Aug 1]. https://abdm.gov.in:8081/uploads/NHS_ Strategy_and_Approach_1_89e2dd8f87.pdf . 8. MoHFW. National digital health blueprint 2018. New Delhi: Ministry of Health and Family Welfare, Government of India; 2018. 9. NHA. A brief guide on ABDM and its various building blocks. New Delhi: National Health Authority, Government of India; 2022. 10. Roberts MJ, Hsiao WC, Berman P, Reich MR. Getting health reform right: a guide to improving performance and equity. (NY): Oxford University Press; 2004. 11. MoHFW. Population projections for India and states 2011-2036, report of the technical group on population projections. New Delhi: MoHFW, Government of India; 2019. 12. Dilip TR, Pratheeba J, Nandraj S. India’s government health expenditure as the ratio to gdp-is it a fallacy? Econ Political Wkly. [2021 Nov];56(48):21–25. 13. Dehury RK, Chatterjee SC. Assessment of health management information system for monitoring of maternal health in jaleswar block of Balasore District, Odisha, India. Indian J Public Health. [2018 Oct 1];62(4):259–264. doi:10.4103/ijph.IJPH_ 203_17 . 14. Saksena N, Matthan R, Bhan A, Balsari S. Rebooting consent in the digital age: a governance framework for health data exchange. BMJ Global Health. [2021 Jul 1];6(Suppl 5):e005057. doi:10.1136/bmjgh-2021- 005057 . 15. Jena S, Epari V, Sahoo KC. Integration of national cancer registry program with ayushman bharat digital mission in India: a necessity or an option. Public Health Pract. [2022 June 3];3:100263. doi:10.1016/j.puhip. 2022.100263 . 16. Samudyatha UC, Kosambiya JK, Madhukumar S. Community medicine in ayushman bharat digital mis- sion: the hidden cornerstone. Indian J Community Med. [2023 Mar 1];48(2):326–33. doi:10.4103/ijcm. ijcm_343_22 . 17. Nundy S. Digital connections to improve India’s health. BMJ. [2021 Oct 22];375:n2586. doi:10.1136/ bmj.n2586. 12U. S. MISHRA ET AL. Amarakoon et al. BMC Health Services Research (2023) 23:1433 https://doi.org/10.1186/s12913-023-10232-0 RESEARCH Open Access © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http:// creat iveco mmons. org/ licen ses/ by/4. 0/. The Creative Commons Public Domain Dedication waiver (http:// creat iveco mmons . org/ publi cdoma in/ zero/1. 0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data. BMC Health Services Research Exploring health information system resilience during COVID - 19 pandemic: case studies from Norway, Sri Lanka & Rwanda Pamod Madusanka Amarakoon 1* , Ragnhild Bassøe Gundersen 1 , Andrew Muhire 1 , Vetle Alvenes Utvik 1 and Jørn Braa 1 Abstract The study aims at exploring health system resilience by defining the scope on health information systems, one of the six building blocks of the health system. The empirical evidence is derived using qualitative data collec- tion and analysis in the context of Norway, Sri Lanka and Rwanda during the COVID-19 pandemic. The case stud- ies elicit bounce back and bounce forward properties as well as the agility as major attributes of resilience present across the countries. Existing local capacity, networking and collaborations, flexible digital platforms and enabling antecedent conditions are identified as socio-technical determinants of information system resilience based on the case studies across the countries. Keywords Resilience, Sri Lanka, Norway, Rwanda, Information systems, Health system resilience Introduction Drawing on three interpretive longitudinal case stud- ies from Sri Lanka, Rwanda and Norway, this paper de scribes similarities and differences in the countries ́ digitalization processes, in relation to resilience and rapid response. Rapid implementation can be defined as in cor - porating speed and efficiency, while having the ability to ad apt methods and trial design to suit the needs of com- plex studies [1]. We show how the three countries worked t o establish health information systems (HIS) to han- dle the COVID-19 pandemic. HIS is one of six building blo cks World Health Organization (WHO) constitutes as the health system of a country [2]. Destabilization of any of the building blocks could lead to jeopardizing the health system. We are especially motivated by the impact of health information in ensuring the resilience of the health system. A health system of a country is a major source of provi - sion of welfare to its population. ‘Ensuring healthy lives and pr omoting well-being for all at all ages’ is the third goal of the United Nations sustainable development goals, which highlight the prominence provided to health systems across all countries [3]. Numerous catastrophic occurrences or shocks, like the financial crisis or the Ebola outbreak, have recently had an impact on health systems all over the world. Some of the health systems seemed to have been more capable of handling these events and/or better able to anticipate them than others. In other words, some had stronger shock resistance and/ or shock responses. Most recently, the emergence and quick spread of COVID-19, has put the world’s health systems to the test, driven the world economy in jeopardy, and as a result, has caused human costs that far outweigh the disease’s actual effects. Global health systems and economics have been severely damaged by COVID-19, particularly in *Correspondence: Pamod Madusanka Amarakoon pamodm@gmail.com 1 University of Oslo, Oslo, Norway 144 Page 2 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 developing nations. With limited resources, developing nations have been striving to treat the pre-existing dis- ease burden, which was made considerably more difficult dur ing COVID-19. The high cost of treatments, market failures in pluralistic health systems, high out-of-pocket costs, the extra burden of noncommunicable illnesses, missing business opportunities, and social effects includ - ing unemployment and poverty are only a few of the eco- nomic effects of COVID-19 in those nations [4]. While de veloped countries generally have efficient health systems, they were overwhelmed and struggled to provide sufficient care to individuals during the first phase of the COVID-19 pandemic. However, an almost abundance of resources assisted the developed coun - tries to combat the pandemic in a robust way [5]. Thus, C OVID-19 poses an intriguing question on assurance of stability of health systems in affluent nations and their ability to bounce back in unfavourable conditions. Capacity to maintain high quality healthcare services by adapting to changes and challenges at different lev - els can be described as healthcare resilience [6]. Thus, ad aptation and bouncing-back are inherent properties of a system’s resilience. Due to the variability of respon - siveness and of country health systems ́ resilience during advers e circumstances, it would be interesting to explore the determinants of rapid response and resilience at country level. ‘Resilience’ is a trending area in the information sys - tems (IS) domain in recent times. While IS primarily de als with technology, an interesting point to note when referring to ‘implementation of information systems’ is that factors contributing to adaptation and resilience need to be of socio-technical nature. In addition to the core technical dimensions, the researcher needs to focus on organizational and broader social determinants of beneficiaries interacting with the HIS. However, there is a vacuum in literature that explores the socio-technical determinants of resilience of IS. The broader objectives of this paper is to identify key attributes of resilience of information systems and to understand socio-technical determinants involved in the process of building resil - ience in a country context. The empirical evidence for the st udy builds on interpretive case studies of the digital and informational responses to the COVID-19 pandemic in Norway, Sri Lanka, and Rwanda, which captures exam - ples of the unfolding process of building resilience and l aunching a rapid response in shifting circumstances dur- ing a pandemic. T raditionally, in the context of developing countries, the components and workflows in HIS follows a path dependent process in data collection to use. There - fore, when the process is disrupted at a certain point it r equires bouncing back to attain the establishment of information flow [7]. The capacity of HIS to break path dependency and produce multi-scalar effects, reflecting new and systemic thresholds, would also be intriguing to investigate since it suggests a potential for transformability [8]. The rest of the paper is structured as follows. First, we present the existing literature on resilience. Next, in the methods section, we describe the three research approaches from Sri Lanka, Norway and Rwanda. Then, we elaborate the 3 case studies from Sri Lanka, Rwanda and Norway based on the empirical data collection, in the case studies section. Before concluding by summariz - ing the salient takeaways from the three case studies and p otential future research, we discuss attributes for build- ing resilience identified through the case studies, as well a s the determinants which lead to establishing resilience of health information in a country. Theoretical framing Resilience Varied disciplines, including psychology, ecology, man- agement, disaster management, engineering, sociology, and r egional development, have different definitions for resilience. Ecology pioneered the concept of resilience to describe how quickly equilibrium may be restored and how resilient complex natural systems are to change [9]. A "resilience thinking" process framework was conceived by Folke et al. [8],incorporating the concepts of resilience, adaptation, and transformability in complex social-eco - logical systems (SES). Resilience in such systems refers to t he SES’s ability to evolve and adapt continuously while staying within crucial thresholds. From an individual’s perspective resilience has been defined as “...the positive capacity of people to cope with stress and catastrophe” [10]. “Resilient people and com - munities are more inclined to see problems as opportu- nities for growth” (Ibid.). Additionally, resilient people f eel less linkage to a particular place [11], which makes it easier for them to transition into a different role in a new environment. Since the 2014 Ebola outbreaks in West Africa, dis - cussions of resilience have dominated health systems r esearch, and they have become more prominent with the COVID-19 pandemic [12]. The WHO Bulletin noted that "weak health systems cannot be resilient" and that "a strong health system decreases a country’s vulnerability to risks and ensures a high level of pre - paredness to mitigate the impact of crisis," as Ebola de vastated the inadequate systems in Liberia, Sierra Leone, and Guinea [13]. Effective "information sys - tems" and robust epidemiological surveillance were c ited in a WHO brief as essential resilience-building measures [14]. 145 Page 3 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Sochas et al. [15] estimated that the decreased utiliza- tion and provision of routine health services for repro- ductive, maternal, and neonatal health, led to a similar n umber of deaths as those directly from Ebola in their study of "indirect crisis-related deaths in the context of a low-resilience health system" in Sierra Leone. In their analysis, they came to the conclusion that "indirect mor - tality effects of a crisis in a health system lacking resil- ience may be as important as the direct mortality effects of t he crisis itself." The Lancet defines resilient health sys- tems as having the ability to prepare for and respond to di saster, maintain routine functioning when a crisis hits, and reconfigure itself as a result of the lessons learned from the Ebola outbreak [16]. Similar to this, Blanchet et al. [17]expanded on ecology and complexity science to define resilience as the ability of a health system to absorb, adapt, and transform when subjected to stress while maintaining control over its structure and functions. The degree of structural change and crisis intensity are considered as influencing the lev - els of absorptive, adaptive, and transformative capaci- ties. The process of structural change and transformation b ecomes more radical the harsher the crisis, necessitat- ing the health system to adjust organizationally in order t o provide the same level of healthcare services with dif- ferent or less resources. A health system’s transformative p otential is its power to change its operations and organi- zational layout in response to a changing environment by c reating new knowledge systems [17]. Resilience is mostly explored in information systems (IS) research as an extension of engineering studies, sup - ply chains, infrastructure, and risk management. Heeks and Ospina [ 18] note the inadequate response to the question "resilience of what" and criticize the lack of development in the research of resilience in IS. One of the six fundamental components of health systems, along with the health workforce, finances, health services, med - icine, finances, and governance, is the HIS [19]. With the u se of this paradigm, we are urged to abandon the dis- tinction between target and object systems and consider how c losely the health system is integrated with digital resilience. The health system, such as the technologies chosen, impacts the physicality of the digital as well (eg: expanding the scale of data reporting through digital means). Resilience traits are described by several scholars as robustness, redundancy, resourcefulness, and swift - ness [20]. The analytical acuity of the notion is jeopard- ized by an attribute-focused approach’s tendency to be over ly general, and everything ends up being redundantly labelled as "resilience." In addition to the problems men - tioned by Bruneau et al. [20], Klein et al. [21] offer adap- tive capacity as the overarching idea for resilience. They f urther expand it to encompass reduced vulnerability, flexibility, adaptability, agility, and self-organization [18, 22], During the COVID-19 pandemic, Floetgen et al. [23] place special emphasis on the materiality of digital in mobility platforms and how socio-technical elements and digital ecosystems are merged and used to build resil - ience. By combining forward-looking actions with plat- form and ecosystem principles, resilience may be built ine xpensively and transformatively [23]. Drawing on the extant literature on resilience, we describe an information system as resilient when it is able to evolve and adapt continuously while staying within crucial thresholds [8], implying that it is persistent, adap - tive and transformative. Methods In this section, we illustrate the research design, data col- lection method and the analysis approach. Thi s paper employs an interpretive case study tech- nique [24, 25 ] since it enables us to examine the dynam- ics and context of the phenomenon of the rapid creation of p andemic-resistant digital technologies in three dif- ferent nations. In contrast to more realist views, which b elieve in an objective, external reality, we take an inter- pretivist viewpoint, believing that reality is a social crea- tion by human agents [26]. An interpretive case study me thod [24, 27, 28] was used to investigate the actions and perspectives of human stakeholders involved in the introduction of digital technology in the health sec - tor during a pandemic. Such an approach, according to D arke et al. [26], is useful in developing and understudied study fields, similar to the ones examined in this paper. Our approach was an empirical investigation of a con - temporary event in a real-life environment, in accordance w ith [29] Yin’s [30] description definition of a case study, as a detailed examination of one example, enabling the researcher to test different views in relation to phenom - ena as they evolve, by closing in on an authentic situa- tion. The data collection techniques used in this instance, ac cording to Yin, were varied and included socio-techni- cal methodologies [24, 31]. Study setting The main criteria for selecting the study context are the feasibility of access for conducting research during the pandemic. We opted for 3 countries that were utiliz - ing the free and open-source health management infor- mation platform, DHIS2 [32]. The platform is currently b eing implemented in over 80 countries globally [33]. We selected Sri Lanka and Rwanda from LMIC context and Norway from the context of high-income countries. The authors had significant access to the implementa - tion of digital information systems of the three countries 146 Page 4 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 and also had long-term engagement with the health sys- tems of the three countries. For the scope of this study, public he alth digital implementations of the three coun- tries were considered. The engagements for the research pur pose were primarily with the ministries of health, academic institutions, partners supporting the imple - mentation of the information systems and the end users a t health facility level of public health sector. In Norway, there were two suppliers of contact trac - ing systems that shared a user base consisting of almost all t he municipalities, Fiks contact tracing being one of them, and Remin the other. Additionally, three munici - palities developed their own contact tracing systems. For t his research, however, we chose to study the develop- ment of Fiks contact tracing system, which is based on dhi s2, the same platform used by Sri Lanka and Rwanda. By comparing the implementation of the same HIS in three different countries, we were able to describe and discuss the resilience of a HIS in three different contexts. Data collection methods Data collection methods devised in each country are slightly different to each other depending on the context. The primary qualitative data collection methods that were devised in the study includes interviews, observa - tions, analysis of meeting notes and documents. The d ata collection was performed to achieve two overarch- ing objectives. Firstly, to capture how events transpired dur ing the pandemic, and secondly, to reconstruct the historical events around the establishment of background and infrastructure in the health sector. Hence, none of the three studies followed a top-down method where we first developed a conceptual scheme and then conducted a fieldwork to confirm it. Conversely, the theoretical con - cepts described above, are a result of an iterative process of d ata collection and analysis. In all three cases, the choice of selection of interview - ees is a result of a combination of convenience and snow- balling. However, the interviewees had to satisfy some c riteria: knowledge and experience with surveillance and vaccination, involvement in the digitalization of COVID- 19 related data management at some level. We did not require that the interviewees had to have a specific num - ber of years of experience with related work in the health s ector, the experience could be a couple of months or weeks only, because we knew that in some sites individu - als had been employed as contact tracers during the pan- demic. There were no exclusion criteria of participants in Norway and Rwanda. However, in the context of Sri Lanka the participants who were selected were the ones who could converse in either Sinhala or English language. Qualitative data collection methods from Sri Lanka included interviews from stakeholders at the ministry of health, academia and the multi sector organizations. The interviews were complemented by observations and meeting notes to formulate the case studies. Rwanda’s case study was formulated by interviews, meeting notes and observations. The case study in Norway included data collection through interviews with representa - tives from 6 municipalities involved with the digitaliza- tion of Fiks contact tracing, representatives from KS, a s well as the HISP UiO team, and senior advisors from the Norwegian Institute of Public Health (NIPH), and observations and meetings. All interviewees have been anonymized. On some occasions the interviewees were chosen due to easier access than others, primarily due to restrictions that were posed because of the pandemic. We estimated that it would be easier to access locations closer to us, if or when the travel restrictions were lifted. However, through interviews in one area we learned about chal - lenges in different locations, which led us to study these ar eas as well; the choice of a new site “followed logically from the first and so on” [34]. Interview guides were prepared based on findings in extant literature related to information system in health sector. Each interview lasted between 30 min - utes and 1.5 hours. Extensive notes were taken during t he interviews. The interviews were recorded digitally and transcribed in English or local language of the three countries. The transcribed interview notes were trans - lated to English prior to analysis. The initial interview g uide prepared based on HIS literature was refined based on findings from the interviews to be used in subsequent interviews. Interviews with interviewees representing distinct voices in various organizations, followed by an analysis of what the interviewees have said, was an important way towards the point of satura - tion, i.e. when no new insights were “being discovered in t he interviews” [34]. In addition to primary data, we have analyzed publicly available reports, minutes from meetings and research reports that have described and discussed the handling of the pandemic. Updates on public service websites, such as the ministry of health, have been useful, because that has informed us of the continuous changes in rules and restrictions. Summary of data collection methods for each country are illustrated in the Table 1 below. The table has been primarily categorised based on the job profile of the interviewees. In addition it outlines several other charac - teristics of the interviewees such as the location they are c urrently practicing based on the availability of resources (low to high), experience in the type of job role based on number of years, their age, their background expertise and the digital literacy. 147 Page 5 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Table 1 Data collection methods Sri Lanka InterviewsTotal Number: 32 Profile of Interviewees Administrators at MoH (3)Selected administrators had experience working in low and high- resource settings throughout the country. Experience of administrators ranged from 10-20 years – (medium to high). All the participants were in their forties and fifties. All of them started their careers as clinicians and specialised in medi - cal administrators All of them had moderate digital literacy Medical officers of Health Informatics (6)Interviewees had experience working in low to high-resource set- tings throughout the country. Experience of informaticians ranged from 3-12 years – (low to high). All the participants were in their fourth, and fifth decades of their lives. All of them started their careers as clinicians and specialised in health informatics Participants had high level of digital literacy National level implementers (4)Interviewees had experience working in low to high-resource set - tings in several districts and national levl. Experience of implementers ranged from 3-12 years in implement- ing systems – (low to high). All the participants were in their fourth, and fifth decades of their lives. All of them started their careers as clinicians and specialised in health informatics with some experience in public health Participants had high level of digital literacy District level implementers (3)Interviewees had experience working in low to high-resource set - tings in 1-3 districts. Experience of implementers ranged from 2-14 years in implement- ing systems – (low to high). All the participants were in their fourth, and fifth decades of their lives. All of them started their careers as clinicians and specialised in health informatics with some experience in public health Participants had high level of digital literacy Core training team (4)Core team had experience working in low to high-resource settings throughout the country. Experience of core team ranged from 8-11 years in implementing systems – (medium to high) in Sri Lanka and globally. All the participants were in their fourth, and fifth decades of their lives. All of them started their careers as clinicians and specialised in health informatics with public health and administration experi - etise. P articipants had high level of digital literacy. End users of the system at hospital and MOH level (10) End users consisted of medical officers, nurses, public health mid- wives and data entry operators. Most of the participants had experience working in mid to high- resource settings in 1-3 districts of the country. Experience of end users ranged from 2-15 years in health sector. Some data entry operators had work experience in non-health domains. Participants were in their third, fourth, fifth and sixth decades of their lives. All of them started their careers as clinicians and specialised in health informatics with public health and administration experi - etise. P articipants had low - moderate level of digital literacy. 148 Page 6 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Table 1 (continued) Academic staff of University of Colombo (2)Academic staff had experience working in high-resource academic institutes but with field experience in low-high resource settings. Experience of academic 10-15 years in digital systems – (medium to high) in Sri Lanka and globally. All the participants were in the fifth decades of their lives. All of them started their careers as clinicians and specialised in health informatics with public health and medical education experietise. Participants had high level of digital literacy. Meeting NotesPlanning meetings of modules of the system Implementation planning meetings Progress review meetings ObservationsStakeholder meetings held at MoH Trainings conducted at national, district and field level Engagement with information system observed at data entry/analysis Rwanda InterviewsTotal Number: 30 Profile of Interviewees Monitoring and evaluation teams at MOH (3)2 Public health professionals and 1 epidemiologist Interviewees had several years experience from disease surveillance and M&E activities in the Ministry of Health National Level programs teams (3)2 Public health professionals and 1 physician Interviewees had experience from vaccination program (EPI) and disease surveillance program District Hospitals implementers (3)1 hospital manager, 1 statistician, 1 HIS specialist Interviewees had many years experience from working in hospitals Digitalisation teams (4)2 IT professionals and 1 Business analysts, 1 lab technician with very good IT skills. Interviewees had many years of experience from implementing and developing IT solutions in the health sector. The lab technician had experience from computerising the manual lab system Planning teams at Central level (2)Both had background in accounting and project management. Both had many years experience as project managers End users of the systems at Hospitals and Health centers (8)1 Data manager, 1 Manager of the health centre, 3 Nurses, 3 lab technicians, IT staff Interviewees were all direct users of the system at the local level and they all had several years of practice in their jobs Health management information systems teams (3)1 IT professional, 1 data manager, 1 M&E staff Interviewees had many years work in implementing HIS and in train - ing users, getting feedback from users, and in help improving data systems Program level meeting with Hospitals (4)1 Hospital manager, 1 data manager, 2 lab technicians. Interviewees had several years of experience in their jobs and also related to labs and the logistics related to taking samples, analysing results and pro - viding feedback – sending back results M eeting NotesHospital Data Coordination meeting Central lab coordination meeting with participation from other labs Hospital Service level meetings Trainings of end users Supervision at Hospitals ObservationsHealth facility integrated supervision visits 149 Page 7 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Table 1 (continued) Norway InterviewsTotal Number: 45 Profile of Interviewees Municipality contact tracers (9)Diverse background (from pilots to doctors to shopkeepers to stu- dents). Exper ience with contact tracing ranged between none and 20+ years. Age ranged from mid-twenties to mid-sixties. Some were highly digital literate and curious, while others had little experience with the digital but experience from other areas that made them question taken-for-granted practices, influencing change. The six municipalities are resourceful, two are centrally located (close to Oslo), four are in the outskirts. Chief municipal physicians (6)All are medical doctors. Experience with contact tracing and disease surveillance for 10+ years. Age ranged between 40 – 70. They were all highly digital literate, and three contributed to the dig - italization process. M unicipality project managers (15)Diverse backgrounds (Business administration, nurse, IT ). Their experience working in the municipality ranged from 1 year to 20+ years. Age ranged between 40 and 60 years. They were all highly digital literate, some with information technol - ogy education and work. experience and others with a genuine interest in the digitalization process. National Institute of Public Health senior advisors (7)Diverse background (epidemiologist, nurse, medical doctor). Their experience with disease surveillance ranged between 1 and 10 years. Their age ranged between 30 and 40 years. They were highly digital literate. HISP Oslo implementers (3)IT Backgrounds. 10+ years of experience with IT. Ages ranging from 30 – 40. Highly digital literate. KS IT architects (3)IT background. 10+ years of experience with IT. Ages ranging from 40 – 60. Highly digital literate. KS project administrators (2)Backgrounds from business and administration, and IT. 10+ years of experience. Ages ranging from 40 – 60. Medium to highly digital literate. Meeting NotesChief municipal physician meetings User forum meetings Corona clinic administration meetings ObservationsCorona Clinic Document and report studies Laws and regulations concerning infectious disease surveillance Minutes from municipality meetings publicly available on their websites Release notes from Fiks Contact tracing Measures and restrictions published by national health authorities on their websites Reports on the government ́s and the municipalities ́ handling of the COVID-19 pandemic 150 Page 8 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Data analysis Our data analysis draws on a Hermeneutic approach, trying to understand and interpret our interviewees’ thinking, as well as adopt an understanding analysis of published reports and published documents available online [35–38]. This entails that to understand the indi - vidual parts we need to have an understanding of the whole, f ollowing the principle of the hermeneutic cir- cle [38]. The principle of the Hermeneutic circle is the first pr inciple in Klein and Myers’ [38] seven principles for interpretive field research, which are all related to the hermeneutic approach. The principles are meant as ideas and not deemed mandatory, however, interpretive researchers are expected to discuss the principles and together decide which of the principles they will apply in their project [38]. Throughout our iterative collec - tion and analysis of our data, we have been guided by t hese principles. As the digitalization in the three countries has been a continuous change-processes throughout our research, we have collected and analyzed data in a manner to ena - ble an understanding of our interviewees as contributing t o the change-process and not a mere product of history, which concurs with the principle of contextualisation. For instance, during the authors sensed a much broader collaboration and interdisciplinarity than what is com - mon in all three contexts, that the pandemic and needed dig italization process in the three countries forced the actors to think outside the box. During our iterative process of data collection and analysis, we inductively identified resilience as a recur - ring theme. Discussing our findings in relation to the c oncept of resilience adheres to Klein and Myers’ [38] principle of abstraction and generalization. By itera - tively drawing on the concept of resilience and collecting ne w data, we developed a broadened understanding of resilience. Resilience thus became valuable as a sensitiz - ing device during the fieldwork of the three countries. W alsham [24] also states that during a longitudinal case study it is expected that theory evolves in relation to an iterative process of collection and analysis of data. Through interviews, observations and document stud - ies we sought multiple interpretations of the case we st udy, a triangulation of researchers, which is important given that the social context may influence how actors behave. Our data analysis consisted of us carefully read - ing and reflecting on our field notes. We used NVivo to c reate codes and themes, preparing our data by iden- tifying and combining interviewees’ statements that had similar meanings. Further we examined our inter- view transcripts to identify statements or actions that r eflected descriptions of resilience. We used PowerPoint and the digital collaboration platform Miro, to present and discuss findings in smaller groups together with colleagues, co-authors, and supervisors. Then, findings were presented to colleagues at different internal uni - versity workshops and subsequently at conferences. This c oncurs with Klein and Myers’ [38] principle of multiple interpretations and it adheres to Walsham’s [24] descrip - tion of a ‘creative leap’; by filtering our emergent findings t hrough the minds of others, a ‘creative leap’ resulted in the theorisation of resilience. Interviewees representing different voices in various organizations and iterative processes of data collection and analysis, guided the process of deciding when we had reached a point of saturation, hence when there was lack of progression in generating themes. The data from the different sources were closely analyzed to identify con - cepts which then contributed to identify broader the- matic areas for each country using an inductive analysis. The se thematic areas were aggregated further to identify broader dimensions which will be discussed in the dis - cussions chapter comparing and contrasting them across t he countries. Role of authors The Sri Lankan author was engaged in stakeholder dis- cussions as well as implementation of the information s ystem in addition to his role in contributing to data collection, analysis and articulation of the case study. One of the authors from Norway has contributed to the long-term capacity building activities in Sri Lanka in addition to his role in contributing to analysis and formulation of the case study. The author from Rwanda has been instrumental in the implementation of the digital technologies during the COVID pandemic and his lived experience contributed to the case study in addition to the interview and observations. Two authors from Norway were involved with data collec - tion and analysis, formulating the case study section of t his paper. They have both had a relatively neutral role, as outside observers [24] in the case study of Norway. An advantage of being an outside observer is that inter - viewees may have found it easier to respond frankly t o questions [39], as none of the authors have had any personal investment in the project. Case studies Sri Lanka Background Originating in China in December 2019, COVID-19 rapidly spread across Southeast Asia by early 2020. A surge in Chinese tourists threatened Sri Lanka’s tourism sector. Despite lacking the advanced electronic infrastructure common in developed countries, essential for expansive surveillance, Sri Lanka swiftly responded. 151 Page 9 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Leveraging open-source solutions, existing capacities, and governance frameworks, the Ministry of Health, along with other stakeholders, established a digital sur - veillance system to monitor the pandemic. R apid development & implementation of digital solu- tions In January 2020, the Ministry of Health convened a crucial meeting to discuss the technicalities of creat- ing a digital surveillance system for pandemic monitor- ing. Given the limited knowledge at the time, the system’s de sign was to be agile, allowing frequent updates post- deployment. Assessing both the country’s current capa - bilities and training needs, the Ministry chose the DHIS2, a he alth management information platform, as the cen- tral platform. The country had prior experience with this pl atform, enabling them to gather both aggregate and specific health data for various uses. Significantly, medi - cal officers in health informatics played a vital role in im plementing this platform both locally and nationally. In anticipation of COVID-19, a platform was developed to monitor international visitors at airports and other entry points. By the close of January 2020, just before the country’s first confirmed case, this system was ready. The design and execution were spearheaded by health informaticians from the Ministry of Health and the ICT agency of Sri Lanka, collaborating with HISP Sri Lanka, a local entity of the global HISP network responsible for DHIS2 implementation. The platform’s adaptability ena - bled the team to accommodate evolving health needs, inc luding quarantine tracking, contact tracing, commu- nity surveillance, ICU bed monitoring, and lab data col- lection. Within four months, these features were opera- tional. Furthermore, to supplement the platform’s built-in c apabilities, a hackathon was organized in partnership with the ICT agency. This led to the development of addi - tional tools, including a contact mapping visualizer, an I CU bed tracker, and a mobile tower-based contact trac- ing tool. One in terviewee commented, “... it takes weeks or even months to get approval and implement a system within the ministry usually. But during the early days of the pandemic, it was hard to believe how stakeholders outside the ministry and sometimes even outside the country could collabo - rate with ministry officials and get systems designed a nd implemented...” This highlights the level of collaboration which was pre - sent during the pandemic which led to rapid deliverables in s ystem implementation. Despite reduced disease prevalence in Q3 2020, efforts to customize and deploy systems persisted. Anticipating a second wave in Q4, the country bolstered lab monitor - ing and integrated community testing. The team success- fully linked the COVID-19 lab system with the DHIS2 pl atform, forming a comprehensive digital surveillance ecosystem. In 2021, an immunisation module was intro - duced. It was designed to pre-register all Sri Lankan adult s (over 16 million) for vaccination. This module was fully operational by the commencement of Sri Lanka’s COVID vaccination drive. Mid-2021 saw an addition to the module: a feature for creating digitally verifiable vac - cination certificates. Collaborating with the ICT Agency, t he team integrated the DIVOC platform, designated for certificate generation, with the DHIS2 immunisation system. A systems implementer highlighted the level of collabo - ration and how it produced a better experience to the cli- ents of the health system. " ... this was the first time we were able to develop extensions on top of dhis2 and to connect it to another digital public good to produce an entire information system with a seamless integration between systems to provide a better experience to the clients. So it was not just a collaboration of stake - holders, but a collaboration of systems...“ T o monitor the vaccination programme and deliver digital immunisation certificates to citizens for travel, the integrated solution provides a powerful digital sys - tem for capturing and visualising COVID vaccination inf ormation. Leveraging on local capacity & stakeholder engage - ment Using customized DHIS2 components and inte- grated solutions, the COVID-19 surveillance system emer ged as a robust multisectoral information network. Led by the president, the national steering committee for COVID-19 exemplified strong collaboration among health, governmental, corporate, and international enti - ties. Driven by a vision for long-term capacity-building in he alth informatics, the system notably offered real-time dashboards tailored for decision-makers, enhancing their decision-making capabilities. The Sri Lankan approach was bolstered by international collaboration. The swift evolution of their system was facilitated through regular interactions with the open- source DHIS2 community and experts from the Univer - sity of Oslo. Insights and metadata from Sri Lanka were f urther refined at the University and then released as a 152 Page 10 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 generic metadata package. This package has aided over fifty countries in establishing DHIS2-based COVID-19 surveillance. Feedback from the DHIS2 community ena - bled the global adaptation of tools like the contact map- ping visualization app. Historically, IT staff training was c entered at the district level, but COVID-19 restrictions impeded onsite training programs. An information systems implementer stated,’ “...we had never conducted entire training programs remotely specially when collecting individual patient information. But the requirements around the pan - demic was such that this was the best possible strat- egy to conduct training programs rapidly while not r isking spread of disease aming health staff. So many parties contributed and the enthusiasm among health staff was the key to the success...” To assist with training and support, video conferencing platforms and instant messaging groups were rapidly integrated. Healthcare professionals quickly adapted to and accepted this technology. While providing ICT infra - structure in various facilities posed challenges, the core t eam adeptly managed integration with existing and new information systems. One significant hurdle was navigat - ing administrative structures and prioritizing implemen- tation requirements. In general, all t he technological advancements around the information system made the decision-making pro- cess more efficient at all levels in the health hierarchy. An admini strator stated, “..the important thing about developing and imple- menting digital technologies was that we made it p ossible for health staff at all levels to track the progress whether positive or negative.. and to take decisions backed by data in a streamlined manner rather than haphazardly doing it using excel sheets.. this made the system stronger, the entire health sys - tem....” T imeline of events of importance for the case study are depicted in Fig. 1. Rwanda Rwanda is a small country in Central Africa with a population of 13 millions. While being categorised as a Least Developed Country by UN, Rwanda is among the fastest growing economies in the world and the govern - ment has a particular focus on digital transformation in t heir development agenda, which is important in our case. When the COVID-19 reached Rwanda, there were no available digital solutions that could be used to respond to the pandemic by tracing cases and contacts, link with laboratories, facilitate cross-border travels and to provide real-time statistics to help decision making. As in the case of Sri Lanka, Rwanda was already using the DHIS2 platform for their general HIS and had good capacity in developing various IT solution using the platform. Based on templates for COVID-19 data stand - ards distributed through WHO, and learning from the u se of DHIS2 in Sri Lanka, Rwanda was able to rapidly build an integrated set of digital solutions supporting their pandemic responses. A task force with high level government support was leading the digital pandemic response and the national digital strategy combined with good IT infrastructure and Internet provided an important foundation. The speed with which digital solutions had been implemented surprised the participants: "In times of crisis, I was unaware that a system could be tailored and implemented within a week. Never - theless, open-source solutions’ potential to support d uring emergencies has been showcased." Fig. 1 Timeline of events: Sri Lanka 153 Page 11 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 One administrator highlighted, “The presence of a task force has minimized the delayed approval procedures, resulting in acceler - ated implementation.” By e xpanding the existing DHIS2 platform, Rwanda was able to rapidly respond to the need for monitoring of cases and contacts without having to develop new tools. As one member of the task force explained: "Utilizing an existing platform and scaling it for capturing COVID cases proved advantageous for the Government, avoiding additional expenses due to pre-existing in-country capabilities." The collaboration between multiple arms of govern - ment and the private sector, as well as other national instit utions such as the National Identity Agency, has facilitated the deployment of digital solutions for COVID-19, by enabling the health sector to leverage existing data systems. Creation of the National com - mand post played a big role in coordination of COVID- 19 sur veillance. Rwanda’s digital solutions for COVID-19 emphasize patient access, for example, by enabling individuals to directly receive or track their own test results and to get their vaccination and COVID-19 certificates online. Through integration of digital solutions and data from laboratories, testing, vaccination, border control, airport, etc., the entire testing process is now paperless, and users get their test results by sms and certificates online. Trac - ing and monitoring of cases and contacts using digital t ools has reduced the burden on health workers and thus allowed the country to focus their limited capacity on delivering services to the most at-risk individuals, while maintaining consistent monitoring of other patients. Management of all pandemic data from public and private sector into one integrated system enhances both understanding of the pandemic and the ability to coor - dinate and monitor the response interventions. It also sim plifies data management, as all patients, regardless of where they are tested, receive their lab tracking number and results via the same DHIS2 platform. Rwanda decided to leverage existing digital tools and capacity and to bring together expertise from different sectors. During the height of the pandemic, IT staff were pulled from their respective institutions to work together and support the testing and vaccination services. Timeline of deployment of digital technologies during pandemic in Rwanda is highlighted in Fig. 2. Norway Background This case study draws on data collection and data analysis from six municipalities in Norway who implemented the contact tracing system called Fiks con - tact tracing. In Nor way the health care sector has perfected routines and practices for contact tracing for almost 200 years. It is the municipalities ́ responsibility to conduct contact tracing of their citizens infected by a communicable dis - ease. The Infection Control Act [40] instructs munici- palities in what their responsibilities are, such as imple- menting systems, routines and practices for infection c ontrol. However, as the Norwegian municipalities are autonomous, each municipality separately decides how to conduct work related to contact tracing. Due to a high vaccination rate against communicable diseases, munici - palities have been able to handle minor outbreaks of inf ections with phone, pen and paper and spreadsheets. For instance, in a population close to 6 millions, there are between 150 and 200 registered cases of Tuberculosis per year [41]. Click or tap here to enter text.. As a NIPH senior advisor said: “We have not experienced contact tracing at this scale before. When there is an outbreak we have rou - tines for surveillance, outbreak investigation, and Fig. 2 Timeline of events in Rwanda 154 Page 12 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 we have interviewed the infected persons. Today it is a totally different form of contact tracing than before. With measles, we map our the close contacts, but most of the close contats are immunised against measles. The scale of the work is therefore much smaller. There has not been a need for such [digital] tools as [the ones] we have now. For ebola the same contact tracing [as with COVID-19] is relevant but that has not been necessary in western countries.” (NIPH senior advisor). COVID-19, being a novel infection with no vaccination, had the ability to spread everywhere. On 26 February, Norway registered its first case of COVID-19. Seeing how quickly COVID-19 could spread, traditional contact trac - ing tools did not suffice. Health officers in the municipal- ity where the first case was identified, initiated a search f or potential digital contact tracing systems (CTS) that could help them with contact tracing. Rapid development & implementation of digital solu - tions Although the Norwegian municipalities are autonomous, they receive different forms of support from the Norwegian Association of Local and Regional Authorities, also known as the municipal sector organi - zation (KS). This includes information technology (IT) supp ort through a software-as-a-service platform called Fiks. KS became an invaluable contributor to the digitali - zation process. B ased on a recommendation from the World Health Organization (WHO) and Centre for Disease Control and Prevention (CDC), an implementation of DHIS2 was initiated. DHIS2 is a customizable open-source system with Application Programming Interfaces (APIs), with a COVID-19 package, developed by Sri Lanka. The system could be adapted to local workflows with low implemen - tation costs. Finally, HISP Norway had available imple- mentation competence. A s a chief municipal physician said, “I contacted DHIS2 [HISP Oslo] to try and build up something in Norway. To document and report COVID-19. All [health] registers in Norway are top- down, while this is a bottom-up [health register] from the municipalities. That it was an open-source tool was very important.” (Municipal chief physician). Together with KS and HISP Oslo, municipal health offic - ers initiated a bottom-up digitalization process. As the m unicipalities ́ IT service provider, KS implemented the digital CTS, called Fiks contact tracing, on KS digital platform called Fiks. A first pilot was ready in May 2020. KS led a democratic digitalization process, creating a user forum consisting of regular meetings where repre - sentatives from engaged municipalities report errors, de scribe desired new functionality, and share user experi- ences with KS and with other municipalities. A KS admini strator explained it like this, “The resources [participants] in the user council were very active, from both large and small munici- palities. In [some] periods we had weekly meetings w ith the municipalities. It was important to sit close to them. [Together] we lifted tasks up and down. For some municipalities [a task] was not important but it was still relevant when we deployed it. The user needs are governed by the municipalities. KS governs the administration. We involved the municipalities in testing and acceptance testing.” (KS administra - tor). Con trary to other digitalization processes within the healthcare sector, the digitalization of COVID-19 has been labelled the speediest digitalization collaboration in Norwegian history [42]. According to KS ́ project man - ager, all contributors were characterized by a unique de sire to help, in Norwegian labelled as “dugnad”. Leveraging on local capacity & stakeholder engage- ment Initially, there were challenges related to Fiks contact tracing being a stand-alone (SILO) system with no integrations towards other HIS. Contact tracers could spend up to 2 overtime hours per day because they had to register information about positive COVID-19 cases several times in different HIS. By utilizing open bound - ary resources in DHIS2, and with economic support f rom NIPH, KS developed integrations between Fiks contact tracing and the national population register (NPR), NIPH ́s laboratory database for transfer of labo - ratory results, and NIPH ́s clinical report database for a utomatic transfer of clinical reports from Fiks contact tracing. Additionally, a self-registration module was made avail - able for the public, as well as automatic transfer of a reg- istered positive case from one municipality to another. F igure 3 below highlights the timeline of implementation of some important functionalities in Fiks contact tracing. Municipalities in Norway are bureaucratic and hierarchi - cal, and each unit is organized as a silo, where distinct di sciplines work in different departments, thus not facili- tating interdisciplinary work. 155 Page 13 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 A municipal project manager described it like this: “We think differently, work differently, set us up in a different way, we think interdisciplinary and cross sectional.” (Municipal project manager). This was supported by another municipal project man - ager who said: The goal must be extremely clear when you work cross-sectional. [In the municipality] the focus is on prioritization, services and the like. What is impor - tant to me is not important to others. During the p andemic [this was different], what was important was important to all. (Municipal project manager). The COVID-19 pandemic necessitated speedy interdis - ciplinary collaborations. At the onset of the pandemic, a m unicipality project manager established an interdis- ciplinary team with members who had knowledge of for inst ance law, health, IT, project management and eco- nomics. The distance between the one asking a question and t he one answering it was minimized. The municipal project manager described it like this: “Some always worked from home because we were not supposed to be so many together the same time [due to chances of infection] so it was difficult to get an overview of all the stakeholders. Then we got a contact person in the IT department and a devel - oper [only for us] from the start. From then on some- one had the overview of what was important. They got a stron g feeling of ownership to something and attended our meetings. At the most we were twelve people in my team. We had standups every day on zoom, at least for half an hour, and two longer meet - ings during the week. The team was represented [by repre sentatives] across the municipality: digitaliza- tion, ICT operation, analysis, health, and welfare te chnology. People could come to us, we became the hub in the middle.” (Municipal project manager). For instance, a question related to law, if something was allowed to develop or not, could be answered within the team. The interdisciplinary team ́s members from the IT- department created integrations between Fiks contact tracing and the preparedness team, which enabled one- click-production of reports. Thus, immediate access to the different subject expertises helped facilitate a rapid digitalization. Discussion In this chapter, we analyze and discuss the case studies to identify the resilience attributes emerged through the case studies and to derive the socio-technical determi - nants of resilience through inductive data analysis. A r esilient HIS can adapt to continuous change with- out changing its identity [8, 10 ]. An HIS is resilient when it is able to evolve and adapt continuously while staying within crucial thresholds (Ibid.). Resilience is about per - sistence, adaptability and transformability (Ibid). S everal attributes of resilience are highlighted in the literature. However, we identify a few crucial properties of resilience from the empirical data we draw from the study across the three countries. Attributes of IS resilience Bouncing back & bouncing forward Drawing on Folke et al. ́s [8] description of resilience, we argue that an IS is resilient when it adapts to a cri- sis by bouncing forward, which may result in a substan- tial change in use of technology, practices and routines. Fig. 3 Timeline of events: Norway 156 Page 14 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Similar notions have been described in recent IS papers, like Heeks and Ospina [18] who focus on adaptation and transformation to describe resilience of an IS, and Amir and Kant [43] who link socio technical resilience to trans - formability. We continue in this stream of understanding r esilience as bounce-back and bounce-forward. The transformation may take place through several adaptive steps. For the Norwegian case, we describe four of the main steps municipalities bounced forward. The first step entailed municipalities establishing corona clin - ics and manual CTS. Due to a rapid increase in infection ra tes, the manual CTS did not suffice. Thus, a second step forward entailed municipalities adapting by imple - menting the digital CTS Fiks contact tracing, and the em ployment of contact tracers who could register data about infected individuals. Although Fiks contact tracing made it easier to keep an overview of infected individu - als and their close contacts, it was initially implemented a s a SILO system. Thus, contact tracers spent much over- time hours to manually create reports on aggregated con- tact tracing data. A third step forward therefore entailed de veloping different integrations towards other IS within the municipality as well as national IS and HIS. With the COVID-19 Omicron variant, the infection rate rose to new record levels. The municipalities did not have enough resources to register all infected individuals and their close contacts. A fourth step forward thus called for the deployment of a self-registration module, which made it possible for citizens to register positive self-tests. That way, the municipalities were able to keep an over - view of infected citizens without experiencing a high n umber of burned-out employees. Bouncing back is explained as the returning back to what was before the crisis or the shock [18]. Norwegian municipalities have not completely bounced back after the COVID-19 pandemic. They have established new routines, practices, technologies, and knowledge systems for contact tracing. Contact tracing teams have been co-located with vaccination teams. While one munici - pality has been continuously working to create a prepar- edness team during the COVID-19 pandemic that will be r eady to handle a new health crisis, some municipalities have just started this work, and yet others have almost bounced back. Fiks contact tracing is, however, in con - tinuous development and currently it has available func- tionality for contact tracing of infectious diseases such as t uberculosis, monkeypox, meningitis, MRSA and E.coli. Several Norwegian municipalities would like to use Fiks contact tracing as a platform for routine surveillance and embed it to existing surveillance workflows suggesting an approach to combat disease outbreaks in future. We argue this as a bounce-forward aspect of the health sys - tem driven by digital technology. In t he contexts of Sri Lanka and Rwanda, the initial requirement of the countries was to develop a digital system to conduct disease surveillance for COVID-19 in times of crisis to effectively function health systems as during the pre-pandemic era. However, both countries realized the potential of an integrated digital informa - tion system emerged during the pandemic to conduct r outine surveillance, mass vaccination campaigns and management of commodities such as ICU beds. Thus, opportunities were created in both the countries to uti - lize digital systems in an integrated environment linking t he existing systems as well as to innovate components in the existing environment as opposed to building new technologies leading to fragmentations. In the context of Sri Lanka plans were underway to develop a routine digital health management information system based on learnings around use of the platform during the pan - demic. Such measures provide empirical basis to define t he bounce-forward nature of the response of the health system to transition to a status further to the where it existed before the shock of the pandemic. Agility According to researchers, modern firms must be agile in order to prosper [44]. An organization must find a way to balance the demands of its external environment with the speed with which it can reorganize its internal resources in response if it wants to be considered agile. In response to the demands of a volatile, rapidly chang - ing environment, research has looked at how compa- nies might dynamically restructure their resource base t o achieve new capabilities. The degree and speed of this reconfiguration that an organization is capable of closely relates to the idea of its agility [40]. The term "organi - zational agility" (OA) describes a company’s capacity to r ecognise external changes and react to them quickly and effectively [45]. In this paper, we try to focus on a broader country and municipality level than what is available in the literature, which is mostly focused on the organiza - tional level. Dra wing on the three case studies, it was evident that there was increased acceptability for change in the health sector during the times of the pandemic. All three case studies reveal to some extent the general inertia of decision-making and long approval process involved in design and implementation of information systems prior to the pandemic. During the pandemic there was increased presence of stakeholder engagement within the Sri Lankan and Rwandan ministries as well outside expediting the entire process. This is a crucial element of agility and responsiveness which contributed to the rapid development of components of the information system. In addition, the ministries were sensitive and receptive to 157 Page 15 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 the changing requirements arising from the changing dis- ease trajectory as well as feedback received from users. Thi s is vital in establishing the responsiveness element. In the context of Norway, the interdisciplinary teams that were established by actors involved in the digitalization of contact tracing, played an invaluable role. They were responsive to the requirements that arose with the pan - demic and rapidly and responded to the user and domain r equirements. Thus, we believe both the rapidity and responsiveness are crucial components of agility which in turn contrib - uted to the resilience of the information system of the t hree countries during the pandemic. Socio‑technical determinants of process of building resilience Socio-technical resilience has to do with transformabil- ity, and it entails a socio-technical system being able to c hange from one configuration to another due to a dis- ruption or a shock [43]. This includes the ability to scale up and dow n the number of users and the digital system according to new rules and restrictions that influence contact tracing and COVID surveillance practices, due to changes in epidemiology. For instance, increase and decrease in the infection rates due to new variants of virus influenced days in quarantine and isolation, which had to be represented in the digital CTS as well as in the contact tracers ́ learning- and information material. In this chapter, we identify major determinants in the pro - cess of building resilience in information systems based on t he findings from the case study. Existing local capacity Introducing multiple solutions to a country that has a lack of capacity could lead to serious issues related to sus- tainability, based on experience from the Ebola outbreak [ 13]. There are several different types of knowledge and skills enhancement in the domain of IS. The ability to govern the direction, implementation, and coordination of IS through the creation of standard operating proce - dures (SOPs) and high-level coordinating entities like wor king groups or task forces are even more crucial [46]. The contact tracing teams in Norway have consisted of highly interdisciplinary teams, with team members being doctors, nurses, physiotherapists, pilots, flight attendants, police investigators, and shopkeepers, to name some. Their different backgrounds and experi - ences have influenced their view on contact tracing rou- tines and practices, including systems ́ functionalities. Con tact tracers with little or no experience from the health care sector have often questioned comments like “it has always been done like this”, or “it is not possible to digitalize this process” and suggested other solutions or made changes themselves. This corresponds with how Walker and Salt [10] describe resilient people with a positive capacity being more solution-oriented than problem-oriented. In the context of Sri Lanka and Rwanda, both countries had long-standing experience on building digital infor - mation systems in the healthcare sector on the free and op en-source platform, DHIS2. The drive for using open- source solutions may partly be due to the low availability of financial resources to procure and maintain proprie - tary solutions. However, it is understood from the 2 case st udies that both countries possessed experience in using the dhis2 platform for a variety of use cases and local capacity was rooted at all levels in the health hierarchy in design, customization and use of the platform for routine health data requirements. Thus, during the early phase of COVID-19 when global travel was limited due to restric - tions, both countries were still able to not only design but al so establish a digital system for data requirements around COVID-19 by utilizing local resources. While COVID-19 was a shock and draining too much resources from the health system, the countries were still able to devise a digital system and implement it across the coun - try due to the existing local resources. Networking & collaboration The rapid bottom-up innovation in Norwegian munici- palities necessitated an interdisciplinary collaboration ac ross the different units in the municipalities. Hier- archies were flattened and traditional bureaucratic pr ocesses were set aside. The digital CTS with its inte- grations facilitated new communication and collabora- tion processes both within and across municipalities, for inst ance enabling digital transfer of data. This shows how HIS may create new path dependencies as well as facili - tate multi-scalar effects. It corresponds with Folke et al ́s [ 8] view on resilience as a potential for transformability, and Floetgen et al.’ [23] argument about resilience being built transformatively. In the LMIC context, both Sri Lanka and Rwanda demonstrate collaboration within ministries as well as with external entities as a major factor contrib - uting to rapid implementation of digital solutions in t he health sector. The peculiar factor to notice is the level of collaboration observed during the pan - demic under stressful conditions was much greater t han what was generally observed in routine service delivery. The case studies testify that the collabora - tions were crucial for the implementations during t he pandemic amidst stretched resources. Other than in-country collaborations, the open-source network around the dhis2 at regional and global level facili - tated sharing of expertise across the three countries 158 Page 16 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 involved in the study. The learnings of collabora- tions and sharing from LMIC context supported the im plementation in Norway. Technology/platform One major similarity observed in the 3 countries in the study is the core platform around which the digital tech- nologies for COVID-19 was built on. Hsu et al. [47] argue f rom a quantitative survey that openness of technology and support from top level managers catalyses adoption and innovation. While the free and open-source nature was of the DHIS2 platform was a determinant for the his - torical adoption of the platform in resource-limited Sri L anka and Rwanda, it is interesting to observe how this property of the platform contributed to its adoption in Norway during the time of the pandemic. Flexibility is a key component observed in the DHIS2 platform which contributed its use in all three countries when the disease trajectory of the COVID-19 was chang - ing. Ability of developing web applications and creating in tegrations was a salient requirement in Sri Lanka and Rwanda during mid 2020 following the implementa - tion of the solution in early phase of the pandemic. The pl atform essentially was resilient to accommodate such requirements as well as to scale it to manage the entire population data during the COVID vaccination. On the other hand, the ability to create integrations and open - source nature allowing further development on the c odebase was a core requirement for its deployment in Norway, a country which has a complex digital ecosystem with integrated components. Based on the case studies it is evident that the access to the codebase and the flexibil - ity of the platform cleared the path to more stakeholders adopting and c ontributing to the implementation of the digital technology on the DHIS2 platform. Enabling antecedent conditions Sri Lanka had invested in long term capacity building on health informatics and placing the skilled graduates at all levels in the health hierarchy for over a decade. Rwanda had a vision for implementation of digital technologies in the health sector, adopted a flexible open-source plat - form and developed capacity on using and maintain- ing the platform. In the context of Norway, the country alr eady possessed sufficient resources and advanced integrated digital technologies. In addition, Norway was the central hub for design and coordination of the global digital platform which was the common solution implemented across the three countries. All the above conditions were pre-existing in the context in which the digital technologies were implemented during the pandemic. While the local capacity, collaborations and properties of digital platforms contributed to the resil - ience observed during the pandemic, a critical analysis c ould identify the necessity of enabling antecedent con- ditions mentioned above in achieving the resilience. In ot her words, we argue that achieving resilience in infor- mation management using digital technologies would b e challenging if enabling antecedent conditions are not existing in a context. Once we identified the major determinants of the pro - cess of building resilient information systems, we focus on relating how it contributes to the broader health system based on the case studies. We identified mainly through the interviews in Sri Lanka how a digital infor - mation system impacted the health system processes. The he althcare administrators highlighted that avail- ability of information enabled them to arrive at deci- sions based on available data rather than speculating. In addition, t he digital system expanded the evidence- based decision-making to all levels in the health system hierarchy and not just the national level. This was a sig - nificant contribution for management of the health sys- tem in general and thereby contributing to making the r esilience of the broader health system. However, in the case of Norway the information system supported the decision making primarily at health facility level. How - ever, there were challenges in utilizing the initial con- tact tracing system at national and subnational level due t o constraints related to integrations, existing privacy and standardization practices in the health sector. This highlights the long process of maturity required in the context of a more developed country which has existing standards and governance mechanisms in use and man - agement of data. Ther e are several limitations in the study. We try to portray determinants of resilient information systems based on our empirical data in the context of COVID- 19 pandemic. The study does not explore the context of routine information systems other than several infer - ences in the case studies. We also bring about deter- minants based on context of 3 countries. However, we a ttempted to ensure the representation by including two countries in low and middle income setting and one high income country. In the data collection process, we opted to study national system based on access and conveni - ence. This may have led to omission of few other digi- tal systems which were functioning in the country (eg: omi ssion of Remin system of Norway which was also used for contact tracing). Since the study was conducted during the height of the pandemic, the interviews were mostly conducted online in some countries. Due to this, certain important steps in the process of digitalisation may not have been captured. 159 Page 17 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 Conclusion This paper delves into the resilience of health systems, specifically focusing on HIS, a key component among the World Health Organization’s six health system pillars. Our findings emphasize the socio-technical factors influ - encing resilient systems: local capacity, collaboration, ad aptable digital platforms, and favorable antecedent conditions. True resilience is achieved when systems are agile, continuously evolving to address dynamic needs. Drawing from empirical case studies, practical implica - tions in the health sector emerge. A notable suggestion i s refining policy-making processes, necessitating the restructure of both the public sector and its interaction with the private realm. Effective governance embraces all these foundational elements, emphasizing cross-sectoral and interdisciplinary collaboration. Therefore, policy- making, budget allocations, and strategic planning must champion such collaborations. The study outlines key factors nations should consider for crafting resilient information systems, which subse - quently fortify overall health systems. Future research s hould probe deeper into these determinants, offer- ing insights into establishing resilience within specific na tional contexts. A paradigm shift in planning and budgeting is imperative. Instead of individual unit allo - cations, subnational levels must adopt a holistic, citizen- c entric approach, fostering collaboration across units to enhance services for their constituents. Acknowledgements We acknowledge the support and contributions from Ministries of Health, Municipalities, healthcare and multisector staff involved with COVID-19 infor- mation management in Norway, Sri Lanka and Rwanda during the collection of data for the research. Authors’ contributions Pamod Madusanka Amarakoon engaged in data collection in Sri Lanka, analysis of the data, writing the main manuscript. Ragnhild Bassøe Gundersen engaged in data collection in Norway, analysis of the data, writing the main manuscript. Andrew Muhire engaged in data collection in Rwanda, analysis of the data, writ- ing the main manuscript. Vetle Alvenes Utvik engaged in data collection in Nor- way, analysis of the data, writing the main manuscript. Jørn Braa engaged in data analysis and writing the main manuscript. All authors reviewed the manuscript. Funding Open access funding provided by University of Oslo (incl Oslo University Hospital) Norwegian Research Council COVID-19 grant was available for conducting field level data collection in Norway and Sri Lanka. Availability of data and materials The datasets generated and/or analysed during the current study are not publicly available since not being permitted to share interviews due to privacy concerns highlighted in ethics approval. However, analysed categorised data could be shared upon request. Please contact corresponding author, Pamod Amarakoon (pamodm@gmail. com) for any clarification and data requests. Declarations Ethics approval and consent to participate Ethics approval has been granted for the study from both the Ethics Review Committee of Postgraduate Institute of Medicine, University of Colombo Sri Lanka and the Norwegian Centre for Scientific Data. Informed consent has been obtained from all participants of the study. We confirm that all interven- tions including data collection were performed in accordance with relevant guidelines and regulations (such as the Declaration of Helsinki). The Norwegian research project was approved by the Norwegian Centre for Scientific Data, now labeled Sikt (https:// sikt. no/ en/ home) in October 2020. The approval process includes a project description with a start- and end date, the reason behind the project, where it is conducted, type of data collection, type of interviewees, type of personal data that is collected and how these are processed, and who have access to the data. A consent form approved by Sikt has been sent to and signed by all interviewees prior to interview or observa- tion, giving the interviewees the chance to pull out of the project as well as demand that all personal information about them is deleted. Consent for publication Not applicable. Competing interests The authors declare no competing interests. Received: 10 February 2023 Accepted: 27 October 2023 References 1. Quanbeck A, Hennessy RG, Park L. Applying concepts from “rapid” and “agile” implementation to advance implementation research. Implement Sci Commun. 2022;3:1–10. 2. WHO | Monitoring the building blocks of health systems: a handbook of indicators and their measurement strategies. WHO. 2014. 3. The United Nations. Sustainable Development Goals. 2016. https:// susta inabl edeve lopme nt. un. org/? menu= 1300. Accessed 22 Feb 2016. 4. Rodela TT, Tasnim S, Mazumder H, Faizah F, Sultana A, Hossain MM. Economic Impacts of Coronavirus Disease (COVID-19) in Developing Countries. 2020. https:// doi. org/ 10. 31235/ OSF. IO/ WYGPK. 5. Lupu D, Tiganasu R. COVID-19 and the efficiency of health systems in Europe. Health Econ Rev. 2022;12:1–15. 6. Wiig S, Aase K, Billett S, Canfield C, Røise O, Njå O, et al. Defining the boundaries and operational concepts of resilience in the resilience in healthcare research program. BMC Health Serv Res. 2020;20:1–9. 7. Hu X, Hassink R. Overcoming the Dualism between Adaptation and Adaptability in Regional Economic Resilience. Pap Evol Econ Geogr. 2015;15(33):1–40. 8. Folke C, Carpenter SR, Walker B, Scheffer M, Chapin T, Rockström J. Resil- ience Thinking: Integrating Resilience, Adaptability and Transformability. Ecol Soc. 2010;15(4). http:// www. jstor. org/ stable/ 26268 226. 9. Rose A. Defining Resilience Across Disciplines. Defining and Measuring Economic Resilience from a Societal: Environmental and Security Per- spective. Integrated Disaster Risk Management. Springer Singapore; 2017. p. 19–27. 10. Walker B, Salt D. Resilience practice: Building capacity to absorb distur- bance and maintain function. Resil Pract Build Capacit to Absorb Disturb Maint Funct. 2012;1–227. 11. Almedom AM, Glandon D. Resilience is not the absence of PTSD any more than health is the absence of disease. J Loss Trauma. 2007;12:127–43. 12. Haldane V, Ong SE, Chuah FLH, Legido-Quigley H. Health systems resil- ience: meaningful construct or catchphrase? Lancet. 2017;389:1513. 13. K ieny MP, Evans DB, Schmets G, Kadandale S. Health-system resilience: reflections on the Ebola crisis in western Africa. Bull World Health Organ. 2014;92:850–850. 14. T homas S, Sagan A, Larkin J, Cylus J, Figueras J, Karanikolos M. Strength- ening health systems resilience: Key concepts and strategies. 2020. 160 Page 18 of 18 Amarakoon et al. BMC Health Services Research (2023) 23:1433 • fast, convenient online submission • thorough peer review by experienced researchers in your field • rapid publication on acceptance • support for research data, including large and complex data types • gold Open Access which fosters wider collaboration and increased citations maximum visibility for your research: over 100M website views per year • At BMC, research is always in progress. Learn more biomedcentral.com/submissions Ready to submit your researchReady to submit your research ? Choose BMC and benefit from: ? Choose BMC and benefit from: 15. Sochas L, Channon AA, Nam S. Counting indirect crisis-related deaths in the context of a low-resilience health system: The case of maternal and neonatal health during the Ebola epidemic in Sierra Leone. Health Policy Plan. 2017;32(suppl_3):iii32-9. 16. Kruk ME, Myers M, Varpilah ST, Dahn BT. What is a resilient health system? Lessons from Ebola. Lancet. 2015;385:1910–2. 17. Blanchet K, Nam SL, Ramalingam B, Pozo-Martin F. Governance and capacity to manage resilience of health systems: Towards a new concep- tual framework. Int J Heal Policy Manag. 2017;6:431–5. 18. Heeks R, Ospina AV. Conceptualising the link between information systems and resilience: A developing country field study. Inf Syst J. 2019;29:70–96. 19. World Health Organization. MONITORING THE BUILDING BLOCKS OF HEALTH SYSTEMS: A HANDBOOK OF INDICATORS AND THEIR MEASURE- MENT STRATEGIES. 2010. 20. Bruneau M, Chang SE, Eguchi RT, Lee GC, O’Rourke TD, Reinhorn AM, et al. A Framework to Quantitatively Assess and Enhance the Seismic Resilience of Communities. Earthquake Spectra. 2003;19:733–52. 21. Klein RJT, Nicholls RJ, Thomalla F. Resilience to natural hazards: How use- ful is this concept? Environ Hazards. 2003;5:35–45. 22. Erol O, Henry D, Sauser B, Mansouri M. Perspectives on measuring enter- prise resilience. In: 2010 IEEE International Systems Conference Proceed- ings, SysCon 2010. 2010. p. 587–92. 23. F loetgen RJ, Strauss J, Weking J, Hein A, Urmetzer F, Böhm M, et al. Introducing platform ecosystem resilience: leveraging mobility platforms and their ecosystems for the new normal during COVID-19. Eur J Inf Syst. 2021;30:304–21. 24. W alsham G. Interpretive case studies in IS research: nature and method. Eur J Inf Syst. 1995;4:74–81. 25. W alsham G, Sahay S. Research on information systems in developing countries: Current landscape and future prospects. Inf Technol Dev. 2006;12:7–24. 26. Ber ger PL, Luckmann T. The social construction of reality: A treatise in the sociology of knowledge. Anchor; 1967. 27. Z uboff S. In the age of the smart machine : the future of work and power. 1988. p. 468. 28. Or likowski WJ, Baroudi JJ. Studying Information Technology in Organizations: Research Approaches and Assumptions. Inf Syst Res. 1991;2:1–28. 29. F lyvbjerg B. Five misunderstandings about case-study research. Qual Inq. 2006;12:219–45. 30. Y in RK. Case study research : design and methods. 2014. 31. M yers MD, Avison D. Qualitative Research in Information Systems. SAGE Publications, Ltd; 2002. https:// doi. org/ 10. 4135/ 97818 49209 687. 32. Distr ict Health Information System 2. https:// www. dhis2. org/. Accessed 8 Dec 2015. 33. DHIS 2 I n Action. https:// www. dhis2. org/ inact ion. Accessed 14 Jan 2016. 34. M yers MD. (Michael D. Qualitative research in business and management. 2009. p. 284. 35. M ingers J, Willcocks L. Social theory and philosophy for information systems. 2004. p. 455. 36. W alsham G. Doing interpretive research. Eur J Inf Syst. 2006;15:320–30. 37. R itzer G. Sociological theory. 2000. p. 769. 38. K lein HK, Myers MD. A set of principles for conducting and evaluating interpretive field studies in information systems. MIS Q Manag Inf Syst. 1999;23:67–94. 39. W alsham G. Cross-cultural software production and use: A structurational analysis. MIS Quarterly. 2002;26(4):359–80. https:// doi. org/ 10. 2307/ 41323 13 . 40. L ov om vern mot smittsomme sykdommer [smittevernloven] - Lovdata. https:// lovda ta. no/ dokum ent/ NL/ lov/ 1994- 08- 05- 55. Accessed 1 Feb 2023. 41. S chein YL, Madebo T, Andersen HE, Arnesen TM, Dyrhol-Riise AM, Tveiten H, et al. Treatment completion for latent tuberculosis infection in Norway: A prospective cohort study. BMC Infect Dis. 2018;18(1):587. 42. Nor gesrekord i i offentlig digitaliseringssamarbeid – kundeserviceavisen. no. https:// kunde servi ceavi sen. no/ 2022/ 08/ 29/ norge sreko rd-i- i- offen tlig- dig it alise rings samar beid/. Accessed 1 Feb 2023. 43. Amir S, K ant V. Sociotechnical Resilience: A Preliminary Concept. Risk Anal. 2018;38:8–16. 44. Sull D . How to Thrive in Turbulent Markets. 2009. 45. Mao H, Liu S, Zhang J. How the effects of IT and knowledge capability on organizational agility are contingent on environmental uncertainty and information intensity. Inf Dev. 2014;31:358–82. 46. Russpatrick S, Saebø J, Romedenne M, Dubent L. The state of commu- nity health information systems in West and Central Africa. J Glob Heal Reports. 2019;3:e2019047. 47. Hsu HY, Liu FH, Tsou HT, Chen LJ. Openness of technology adoption, top management support and service innovation: a social innovation perspective. J Bus Ind Mark. 2019;34:575–90. Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in pub- lished maps and institutional affiliations. 161 1 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 A tale of ‘politics and stars aligning’: analysing the sustainability of scaled up digital tools for front- line health workers in India Neha S Singh , 1 Kerry Scott , 2 Asha George , 3 Amnesty Elizabeth LeFevre , 4 Rajani Ved 5 Original research To cite: Singh NS, Scott K, George A, et al. A tale of ‘politics and stars aligning’: analysing the sustainability of scaled up digital tools for front- line health workers in India. BMJ Global Health 2021;6:e005041. doi:10.1136/ bmjgh-2021-005041 Handling editor Seye Abimbola Received 18 January 2021 Accepted 27 May 2021 1 Department of Global Health and Development, Faculty of Public Health and Policy, London School of Hygiene and Tropical Medicine, London, UK 2 Department of International Health, Johns Hopkins University Bloomberg School of Public Health, Baltimore, Maryland, USA 3 School of Public Health, University of the Western Cape, Faculty of Community and Health Sciences, Cape Town, Western Province, South Africa 4 School of Public Health and Family Medicine, University of Cape Town, Rondebosch, Western Cape, South Africa 5 National Health Systems Resource Centre, New Delhi, Delhi, India Correspondence to Dr Neha S Singh; neha. singh@ lshtm. ac. uk © Author(s) (or their employer(s)) 2021. Re- use permitted under CC BY. Published by BMJ. ABSTRACT Introduction India has become a lighthouse for large- scale digital innovation in the health sector, particularly for front- line health workers (FLHWs). However, among scaled digital health solutions, ensuring sustainability remains elusive. This study explores the factors underpinning scale- up of digital health solutions for FLHWs in India, and the potential implications of these factors for sustainability. Methods W e assessed five FLHW digital tools scaled at the national and/or state level in India. We conducted in- depth inter views with implementers, technology and technical partners (n=11); senior government stakeholders (n=5); funders (n=1) and evaluators/academics (n=3). Emergent themes were grouped according to a broader framework that considered the (1) digital solution; (2) actors; (3) processes and (4) context. Results The scale- up of digital solutions was facilitated by their perceived value, bounded adaptability, support from government champions, cultivation of networks, sustained leadership and formative research to support fit with the context and population. However, once scaled, embedding digital health solutions into the fabric of the health system was hampered by challenges related to transitioning management and ownership to government partners; overcoming government procurement hurdles; and establishing committed funding streams in government budgets. Strong data governance, continued engagement with FLHWs and building a robust evidence base, while identified in the literature as critical for sustainability, did not feature strongly among respondents. Sustainability may be less elusive once there is more consensus around the roles played between national and state government actors, implementing and technical partners and donors. Conclusion The use of digital tools by FLHWs offers much promise for improving service delivery and health outcomes in India. However, the pathway to sustainability is bespoke to each programme and should be planned from the outset by investing in people, relationships and service delivery adjustments to navigate the challenges involved given the dynamic nature of digital tools in complex health systems. INTRODUCTION Throughout the last decade, over 600 digital health pilot strategies and programmes have been introduced globally. 1 Despite the proliferation of digital health programmes, evidence on their effectiveness is limited. 2–4 Moreover, governments have found it chal- lenging to select, scale- up, and integrate solu- tions into existing national systems. 5 Key questions What is already known? ►Hundreds of digital health interventions have been piloted in low- income and middle- income countries, though few have been successfully scaled. ►Among those that have progressed beyond pilot initiatives to attain scale, efforts to achieve sus- tainability remains elusive, particularly with regard to integration into routine health services delivery, independence from donor funding, interoperability and governance. What are the new findings? ►To successfully sustain a scaled up digital tool, it is imperative for all stakeholders, in particular gov- ernments and donors, to have an entire supportive ecosystem in place that addresses the dynamics be- tween aspects of the digital solution, actor relation- ships, implementation processes and key contextual factors, with strong government leadership to align all these pieces. What do the new findings imply? ►Our findings challenge the notion that digital health programmes progress linearly from pilot to scale to sustainability, and instead explore the elements and tensions between scale and sustainability for digital health. ►With significant resources spent each year on digital health solutions that are never scaled or sustained, it is imperative that we build the evidence base on factors that lead to success in sustaining innovations in the digital health space. BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 162 2 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health Scale- up refers to the increase of a programme’s reach from a pilot population or experimental region to greater numbers of people over wider geographical areas. 6 Studies and frameworks examining scaling up have emerged over time with considerable commonality. 7–10 Sustainability of a programme is the ‘capability of being maintained at a certain rate or level.’ 11 When applied to health programmes and policies, the concept of sustain- ability involves the continuation of inputs (eg, funding or programme activities), outputs (eg, health benefits) and a process of adaption in response to emerging needs of the system. 12 It is an emergent field of enquiry, with numerable frameworks from different disciplines and noted challenges in assessment. 10 12–16 To date, only select digital health programmes for front- line health workers (FLHWs) have scaled, 17 18 including a few in India. 19–21 The successful scale- up of these programmes raises important questions about the micro (eg, negotia- tions between individuals), meso (organisational processes and systems) and macro (national policy and wider context) level factors that underpin decision making on which initia- tives get adopted and with what evidence. Major factors influencing scale- u p have been synthesised to create our conceptual framework (discussed below, figure 1). 10 22–24 The features that influence sustainability overlap consider- ably with those for scale- up, but shift focus from the inter- vention itself to the health system’s ability to plan, organise, adapt and communicate, and the broader fiscal and polit- ical environment. 25 26 To date, very few studies 27 28 have aimed to understand processes underpinning scaled digital health tools in India or elsewhere to reflect on sustainability . Emerging litera- ture, largely from high- income settings, sheds light on the complex and multi- d imensional nature of scaling digital solutions for health, 13 29–31 as well as how the social, political and historical contexts where digital tools are implemented plays a key role in how solutions are embedded, adapted and potentially sustained within a health system. 32 33 This study aims to answer ‘Why have some digital health programmes scaled, and others not, and what are the implications for sustainability in India?’. To under- stand the factors that underpin the scale- up and sustain- ability of different typologies of digital health solutions in India, we examine five FLHW digital tools ranging from direct- to- FLHW programmes to real- time data capture and decision- support tools. This analysis will benefit actors involved in the development of digital tools for FLHWs in India and other settings by illuminating the multifaceted inputs and processes involved in scale- up and by providing a framework for thinking about how the scale- up process can support or hinder the tool’s chances of sustainability. Drawing case studies from India is partic- ularly fruitful because it is the site of several of the world’s largest digital programmes for FLHWs and one of the few low- income or middle- income countries that appear to be sustaining these tools. METHODS Conceptual framework We developed a conceptual framework to study what shapes scale- up and sustainability of digital tools for FLHWs (figure 1), reflecting broader literature on the subject. 6 8 10 13 31 34–37 Our framework was adapted from the following existing conceptual frameworks by taking into account variables relevant to the implementation of digital tools in resource- constrained settings: (1) Greenhalgh et al’s Figure 1 Conceptual framework for evaluating the scale- up and sustainability of digital solutions for front- line health workers. BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 163 Singh NS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 3 BMJ Global Health framework taking into account complexity of scaling- up technology- supported programmes 13 ; (2) Gericke et al’s framework which has been applied to assess the scale- up of mHealth innovations in Malawi and Zambia 31 ; (3) Spicer et al’s framework based on studying scalable health innovations’ attributes in Ethiopia, India and Nigeria 10 and (4) Gilson and Walt’s policy triangle. 38 Doing so enabled us to simplify relevant variables into four themes: (1) digital solution characteristics, (2) actor roles and relationships, (3) implementation processes and (4) context. While drawing from existing frame- works for scaling and sustaining health interventions more generally, our work particularly takes into account specific ‘hardware’(eg, cloud storage) and ‘software’ (eg, technological partnerships) required to scale and sustain digital health solutions. Study setting In 2011, India’s population was 1.2 billion, with nearly three- quarters (74%) being literate. 39 Mobile phone access in India has rapidly increased, with the 2015–2016 National Family Health Survey (NHFS) reporting 90% of households having access to mobile phones. However, less than half of women surveyed (46%) have access to mobile phones. 40 India has a federal health system structure, where health is a state subject but national government defines key strategies and programmes. 41 For example, the Ministry of Health and Family Welfare (MoHFW) is responsible for national programmes for health and family welfare, prevention and control of communi- cable diseases, promotion of traditional and indig- enous systems of medicines, and setting standards and guidelines, which state governments can adapt. Additionally, The Ministry of Women and Child Development (MoWCD) is responsible, among other programmes, for implementing the Integrated Child Development Services (ICDS) programme, in collab- oration with the MoHFW, which provides a package of services including supplementary nutrition, immu- nisation, health check- ups and referral services, and preschool education. The 2015–2016 NHFS reported that utilisation of key maternal and newborn health services are variable and characterised by breaks in the continuity of care. While most women (83%) attend at least one antenatal care visit, only half (51%) receive the recommended four visits. Despite high skilled birth attendance (81%), provision of postnatal care is uneven for mothers and newborns; with only 65% of mothers and 27% of newborns receiving postnatal care within 2 days of birth. 40 Cases In this study, programmes were considered to be suffi- ciently scaled up to serve as case studies if they were reaching a large proportion of eligible FLHWs across at least one state in India. Case studies of varying complexity were selected based on three features. First, our cases showcase a range of technical features such as data capture, decision- support, direct- to- FLHW health information messages. Second, they are at different levels of maturity in terms of scale and sustainability, which enabled us to explore differences in their experiences in scaling and varying levels of success in being sustained. And third, they are geographically diverse, enabling an examination of contrasting Indian governmental state capacities. Our cases and respective digital tools are as follows: (1) TECHO +in Gujarat; (2) Mobile Academy (MA) in Gujarat and Madhya Pradesh; (3) Anmol in Madhya Pradesh and at national level; (4) the non- communicable diseases (NCDs) App at the national level and (5) Common Application Soft- ware (CAS) at the national level. Table 1 compares and contrasts each case study in terms of their components and functions, actors involved and coverage. Data collection We conducted semistructured in- depth inter views with respondents identified using investigator contacts and snowball sampling in person in New Delhi, Bangalore, Bhopal and Ahmedabad from May to October 2019, and remotely using Zoom software from July to October 2020. Respondents were sampled from the following catego- ries: technology partners, implementers and technical partners (n=11); senior government stakeholders who had played key roles in commissioning, scaling and/ sustaining the digital tools (n=5); funders (n=1) and evaluators/academics (n=3) (table 2). Our sample size was limited due to COVID-19 pandemic starting in the middle of our study, which impacted respondents’ avail- ability, as well as our ability to follow up with them in person. However, several respondents (n=7) had in- depth knowledge of multiple cases: MA (n=8); TECHO+ (n=5); ANMOL (n=5); NCD app (n=4); CAS (n=9). Research began by introducing the participant to the study, providing them with an information sheet and consent form for the study, and obtaining and recording verbal consent only after giving them sufficient time to consider whether or not to participate in the research and answering any questions they may have. Interviews were conducted in English using a semistructured interview guide covering domains in the conceptual framework (figure 1). Interviews lasted approximately 1–1.5 hours. At the end of each interview, respondents were asked if they knew anyone with experience relevant to the subject of our research. Researchers took detailed notes and audio recorded each interview, which was transcribed for analysis. Data analysis Analysis involved the following stages: NSS and KS system- atically coded the interview transcripts using Dedoose software, adopting a framework approach whereby a priori and emerging themes were applied. KS prepared a detailed synthesis report that summarised findings by BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 164 4 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health Table 1 Case study overview Case study (inception year) Components/functions Actors Coverage Mobile Academy for India’s Accredited Social Health Activist (ASHA) community health workers*(piloted from 2012, scaled in 2016) 1. Phone- in interactive voice r esponse (IVR) mobile refresher training designed to improve FLHWs interpersonal communication skills on preventative reproductive, maternal, newborn and child health (RMNCH) behaviours. – 44 short (~2.5 minute) pr e- r ecorded audio lessons; total course length 240 minutes. – 44 yes/no, multiple choice quiz questions. 2. MOTECH system which is inter operable with and ingests mobile phone numbers of ASHAs from Maternal and Child Tracking System (MCTS)/Reproductive Child Health (RCH; validation checks help to bolster MCTS/RCH data quality. *Mobile Academy was designed to work together with two ‘sister’ programmes, also developed by BBC Media Action and initially implemented in Bihar. ► Kilkari, a dir ect- to- FLHW health message pr ogramme which delivers prerecorded audio health information messages weekly to pregnant and postpartum women and has been scaled across 13 states nationally. ► Mobile Kunji, an audiovisual job aid to help ASHAs communicate with community members. ASHAs use a deck of 40 colour - coded car ds with illustrations, and access supporting audio by dialling into an IVR service. Mobile Kunji has not been scaled up beyond the state of Bihar, where it has been adopted by the Bihar State Health Society. Technology development: Beehyv, Grameen Foundation, DimagiTechnical development and implementation: BBC Media ActionFunders: BMGF, USAID, the Barr FoundationProgramme support and management: Government of India’s MoHFW; National Informatics Centre (NIC); Price Waterhouse CoopersTelecommunications, IVR, hosting and data centre: Reliance Communications Limited, Railtel, IMI Mobile. ► Implemented in 13 of 29 states. ► Ar ound 267 000 ASHAs, 43% of all ASHAs r egistered in the government’s databases, had started the course (as of March 2019). ► 180 500 (30%) of all ASHAs r egistered, had completed it as of March 2019. ANMOL for auxiliary nurse midwives (ANMs), India’s front- line subnursing cadr e (2017) 1. Andr oid- based tablet application for ANMs that supports data captur e and service delivery planning for health and nutrition services to pregnant women, mothers and children <12 months.a. Pr eloaded audio and video files used to counsel women and couples on subjects like high- risk pr egnancies, immunisation and family planning. b. The tablets maintain an auto- generated list of pending tasks. 2. Inter operability with the RCH database—it feeds data captured by ANMs into the RCH database 3. Compr ehensive dashboards display reports on data captured. Technology development: Dhanush InfotechTechnical development and implementation: Dhanush Infotech with other technology partnersFunders: Unicef and Ministry of Health and Family Welfare (MoHFW)Programme support and management: Government of India’s MoHFW, NIC. Implemented in 9 of 29 states50 000 ANMs of 293 000 in India wer e using the tool as of early 2018 NCD App for ANMs(piloted from 2018, scaled in 2021) 1. A compr ehensive primary healthcare platform (CPHP) that supports technical interoperability with the MoHFW’s MCTS, RCH and other electronic health information systems. 2. An Andr oid application on a tablet that sits on the CPHP and supports ANMs in conducting NCD screening and management for all adults over 30 years of age. Technology and technical development: Dell EMCImplementation: Tata TrustsFunders: Dell EMC, Government of IndiaProgramme support and management: Government of India’s MoHFW. ► Implemented in 26 of 29 states ► Almost 100 000 tablets in the field running the NCD app ► Nearly 20 000 ANMs have logged in over the last 30 days (as of Oct 2019) Continued BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 165 Singh NS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 5 BMJ Global Health Case study (inception year) Components/functions Actors Coverage TECHO+ (Technology Enabled Community Health Operations) for ANMs and ASHAs(piloted from 2013; scaled in 2017) 1. Data captur e, decision- support and scheduling andr oid application for mobile phones used by ASHAs and ANMs to deliver to deliver health and nutrition services to pregnant women, mothers and children <12 months.a. Decision support in form of digital checklist to encourage adher ence to protocols during home visits. b. Scheduling and activity planning in form of r eminder to ANMs to plan for village health and nutrition day. c. Longitudinal, digital tracking of pr egnant women and infants’ health status and services. d. NCDs, nutrition, developmental delays, communicable diseases, and mental health modules ar e being added to achieve comprehensive primary healthcare in alignment of Ayushman Bharat. 2. T argeted client communication using multimedia to transmit targeted health information and improve counselling for behaviour change communication. Technology development: Argusoft India Ltd., GandhinagarImplementation: SEWA Rural, JhagadiaFunders: Government of Gujarat, UNICEF (research funding from Indian Council of Medical Research, WHO and MacArthur Foundation)Programme support and management: GVK EMRI, Government of Gujarat ► 90% of Gujarat’ s population enrolled in TeCHO+ (as of Feb 2019) ► 100% of all pr egnant women and under five children enrolled ► Gujarat Gover nment health department and National Health Mission gave 11 000 smartphones and data plans to all ANMs in 2018 Common Application Softwar e (CAS) for Anganwadi workers (AWWs), India’s community pre- school and nutrition supplementation workers(2018) 1. Data captur e and decision- support andr oid application for mobile phones used by AWW and their supervisors to deliver health and nutrition services to pregnant women, mothers and children <12 months. 2. The CAS A WW app replaces 10 of the 11 paper- based r egisters AWWs used to maintain and consists of 8 modules: household management, home visit scheduler, daily nutrition, growth monitoring, take- home rations, due list, Anganwadi centr e management and monthly progress report. 3. The CAS supervisor app pr oviders supervisors with a checklist which allows them to identify how the AWWs in 10–20 Anganwadi centres are performing, and provides data to inform discussions at monthly sector meetings. 4. CAS web- enabled dashboar d allows real- time monitoring by Integrated Child Development Services (ICDS) of ficials 5. CAS is supported by the CommCar e, an open access technology platform. CommCare is not interoperable with the MoHFW’s RCH or MCTS databases but creates its own database which serves as a data repository for the Ministry of Women and Child Development. Technology development and implementation: DimagiTechnical development and implementation: BMGFFunding: BMGF, MoWCD Implemented in 24 of 29 states.~354 000 Anganwadi Centr es using ICDS- CAS (as of June 2019). FLHW, front- line health workers; MoWCD, Ministry of W omen and Child Development; NCD, non- communicable diseases. Table 1 Continued BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 166 6 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health emerging themes and NSS, KS, AG and AEL participated in an analysis workshop, where emerging findings were reviewed and jointly agreed and the conceptual frame- work for the study was revised to reflect the study’s find- ings. Data were then revisited using the revised concep- tual framework with the paper drafted by NSS with inputs from KS and reviewed by all authors to confirm the find- ings are accurately and coherently presented. We followed Noble and Smith’s recommended steps to enhance the validity and reliability of qualitative data collection and analysis, including accounting for personal biases, frequent communication with all researchers in the study team and ongoing critical reflection of methods to ensure sufficient depth and relevance of data collection and analysis. 42 We operationalised these steps through convening planning and debrief meetings before and after each KI to: revisit the interview guide and focus our interview strategy, discuss the detailed interview notes and high level summary comments, and continually re- evaluate our impressions and interpreta- tions of responses to ensure that personal bias was mini- mised. A preliminary analysis report was also reviewed by the team and discussed at length before proceeding with drafting the manuscript. Patient and public involvement statement Given the nature of our study—a high- level policy analysis— it was not appropriate to involve patients or the public in our research. RESULTS We now apply the framework to our cases, focusing on the potential impact of salient features within the domains (digital solution, actor roles and relationships, implementa- tion processes and context) on the digital health solution’s scale- u p, and the implications of these aspects of scale- u p on the sustainability of these solutions going forward. Digital solution Here, we report characteristics of the digital solution that affected scale and are likely to affect sustainability: their perceived value to all stakeholders, bounded adaptability and data governance. Perceived value Findings suggest that the perceived value of these digital health solutions arose from responding to the needs of various actors. MA was valued as an affordable, standard- ised and logistically simple mechanism to refresh Accred- ited Social Health Activist’s knowledge gained from face to face trainings and fill in knowledge gaps. For the range of digital health solutions focused on FLHW data capture, workflow planning and/or decision support (ANMOL, TECHO+, CAS, NCD app), respondents reported valuing the potential to streamline data collection systems and improve the timeliness, quality, accessibility and use of data. While fulfilling a clear health system need enabled these digital tools to scale, respondents felt that sustain- ability hinged on tools becoming inherent to effective service delivery. Respondents argued that this underlined the success of one state- level solution (KI14, evaluator/ academic), while another speculated that sustainability was not guaranteed because the transformative potential for service delivery was yet to be grasped. I think to some degree, yeah, sustainability is a pipe dream. ... Like, digital is viewed as an IT product, it’s viewed as a data collection mechanism to get you reports. They don't use the reports to do anything useful. So, they're not buy- ing the digital health technology ... because it improves outcomes... (KI16, technology partner) Adaptability Most key informants identified adaptability as a key enabling feature for scaling up, but one that was bounded by certain technical nuances. They distinguished between software that is hardcoded versus configurable. In order to make changes to hardcoded software a senior engineer is needed to manually rewrite the code; a process which can be time consuming and expensive. By comparison, config- urable software allows technology partners to quickly and easily configure different parameters without editing the source code. They specified that configurability was a more scalable approach and seen as essential for accommodating differences in state- level health programmes and priorities. For instance, MA was configurable because new curricu- lums with different numbers of chapters and quizzes could be easily set up using the existing software and infrastruc- ture (KI01, technical partner). However, informants iden- tified that configurability should be carefully managed and permissions based because allowing states to customise data fields would hamper implementation and impede efforts to aggregate and compare data. In addition to adaptability, informants noted the impor- tance of extensibility—defined as the ability of systems to extend to and accommodate new users or geographic areas. Extensibility was driven by infrastructure and Table 2 Key informants Interviewed by respondent type with knowledge of specific case studies CategoryCases represented*N Technology partner/ implementers/technical partner Mobile Academy, TECHO+, Anmol, NCD app, CAS 11† GovernmentMobile Academy, TECHO+, Anmol, NCD app, CAS 5 Funder/donorMobile Academy, CAS1 Evaluator/academicTECHO+, CAS3† Total 19 *Respondents across categories had knowledge of multiple cases: Mobile Academy (n=8); TECHO+ (n=5); ANMOL (n=5); NCD app (n=4); CAS (n=9). †One respondent (KI07) is classified as both a technology partner/ implementer and academic. NCD, non- communicable diseases. BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 167 Singh NS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 7 BMJ Global Health telecommunications connectivity choices. For example, an interactive voice response system is more extensible if it can quickly and easily scale to handle spikes in call traffic and then descale when the spikes have subsided. Data storage and governance Although respondents agreed that data storage and data governance domains (access, privacy and consent) are key considerations for any digital tool, they did not cite them as a key factor contributing to scale or sustainability. Data storage was mentioned as closely tied to scale- up was the use of high- quality cloud- based data storage rather than physical data storage infrastructure. Govern- ment resistance to cloud- based systems, which partially stemmed from concern about data being housed outside the country and ‘exposed’ on the cloud (KI04, techno- logical partner), was reported to be rapidly declining as India- based cloud systems have become available and demonstrated their capacity . Data governance domains including consent, privacy and data protection were not cited as considerations when scaling or sustaining these digital tools. A respon- dent speculated that some stakeholders viewed data protection as ‘a luxury for wealthy consumers and that it’s a barrier to saving lives, and it’s totally unrealistic for illiterate poor people who can’t, who have no idea what data even is’ (KI01, technology partner). Low prioritisa- tion of data governance domains had resulted in poor consent processes at the front lines, wherein FLHWs were ‘not really’ taking proper informed consent when collecting data using digital tools (KI10, government). Another respondent worried that failure to invest in consent processes could someday undermine sustain- ability by undermining public trust: Explaining these [data protection] concepts to poor, illit- erate people is super challenging...[but] if you don't en- gage and take consent to take people’s data, you have a situation of distrust. (KI01, technology partner) Actor roles and relationships In this section, we consider the government champions, networks and sustained leadership, and engagement with FLHWs, including the relationships involved in devel- oping, implementing and scaling these digital tools that are likely to affect sustainability. Government champions Champions in influential government ministerial posi- tions in MoHFW and MoWCD and at state government level were vital to the scale- up of all digital tools studied (KI14, evaluator/academic). For example, CAS was made possible by having ‘the right guy for the job’ in govern- ment (KI06, donor) who was ‘able to push through all the bureaucratic kind of machinery that was required and to make sure that it (CAS) was moving’ (KI17, tech- nology partner). Communication between state government actors was an important enabler for scaling MA and the NCD app. In these cases, the programme was first imple- mented in one state with support from senior actors in that state’s government. These actors went on to praise the programme during interactions with their counter- parts in other states, which created champions for the programmes in other states. Stakeholder networks While a powerful government champion can push a programme forward and approve the decision to scale, sustainability required deeper relationships ‘so it can go all the way down to the people who are actually making things happen’ (KI02, technical partner) and broader buy- in to ensure that the programme continues—espe- cially when individual leaders inevitably move on (KI14, evaluator/academic). Implementing partners, including non- government organisations, technologists and donors invested heavily in building and sustaining relationships, particularly with bureaucrats at different levels of government (KI14, eval- uator/academic). For example, respondents from the technical agency that developed MA described ‘walking the corridors of the National Health Mission’ over several months to build trust (KI02, technical partner). Beyond government, all our cases showcase the impor- tance of committed, sustained teams and strong leaders at donor, technology, technical, and implementing organisations. It’s easy to sort of keep looking externally but even inter- nally, if something had happened and our key, you know, drivers of the project internally had left or were involved in something else and therefore not giving this so much time we wouldn't have had the kind of success we had. (KI02, technical partner) FLHW engagement While digital tools are meant for FLHWs who ultimately determine their use, several respondents noted that FLHWS were not involved in decision making related to scale- up, beyond participating in implementation and research directed by others. As all the tools were required—not optional—for FLHWs, high uptake cannot be considered a proxy for FLHW endorsement. However , a respondent noted that ‘in the end... the true mark of sustainability [of these digital tools] will be that this is something that gets routinised into the day- to- day work of the health worker themselves so they value it, that they demand it, that if it breaks or crashes or does not work that they want it fixed because they find it so valuable’ (KI14, evaluator/academic). Implementation processes In this section, we examine the process underpinning the successful scale- up of these cases, summarised as invest - ments in research evidence, operationalisation consider- ations and balancing actor roles. BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 168 8 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health Investing in evidence Formative work to support fit with context and population The cases underwent diverse development processes with implications for their fit with the context and popula- tion. While some underwent extensive user testing and embedded development (MA, NCD app, TECHO+), others were first developed by technology partners with specifications/data capture features stipulated, and then adjusted when implemented (ANMOL). For instance, the NCD app arose from an embedded development process, wherein app developers spent 1.5 years working in a primary health centre ‘lab’ with a small group of FLHWs to develop a locally appropriate digital tool (KI03, technical partner). In contrast, some of ANMOL’s implementation challenges were linked to what may have been poor initial fit with the population. A respondent felt that although ‘as an application it’s quite good’ it was ultimately made by ‘someone sitting in Delhi’ in order to generate better data for central decision making and analysis, not for the FLHWs who struggled with using smartphones and lower- level health system managers (KI09, government). Evidence from research Both technical partners and government officials suggested that evidence from research studies was less important to informing scale- up than showcasing feasi - bility (KI01, technical partner) or filling a clear need identified by government officials (KI06, donor). It’s like, okay, so they [the government] had some ev- idence... But ultimately, they were interested in the fact that here’s a piece of software that people not only know how to use, but want to use, and are willing to pay for.” (KI01, technical partner) All our cases were scaled and on track to be sustained, so ones with rigorous research showing impact (MA; precursors to CAS and TECHO+) did not appear to be better placed for long- term sustainability compared with cases with only anecdotal insight from implementation experiences (NCD app, ANMOL). Nonetheless, respondents involved in CAS suggested that evidence played two positive roles in achieving scale- up. First, although ‘politics were far outweighing the evidence’ policy- makers did need some evidence of effectiveness in order to meet a requirement before going to scale (KI16, technology partner). Second, the process of evaluating a digital tool can improve it by cultivating a ‘learning culture’ (KI14, evaluator) among policy- makers, technology partners and implementors whereby actors sought data from baseline and process evaluation research to improve the programme. Operationalisation Rolling out use by FLHWs While some tools like TECHO+made an effort to address what users at different levels needed and thus reportedly achieved high FLHW satisfaction, several tools initially struggled with FLHW engagement during implementation—however, these initial hiccups did not seem to affect the tools’ eventual scale- up. These chal - lenges included some states failing to distribute adver- tisements although MA was supposed to be implemented alongside a media campaign explaining the course to FLHWs; and ANMOL being rolled out through trainings for 250–300 Auxiliary Nurse Midwives (ANMs) at a time, which was an unwieldy number of participants (KI05, technology partner/implementor). Respondents had varied perspectives on whether to rapidly switch from paper registers to digital systems, or to have dual systems for a while before the transition to digital systems is complete. ANMs using ANMOL and TECHO+ are expected to continue maintaining their paper registers. The technological partner working on TECHO+ (KI13) explained that paper record keeping should be phased out gradually, and only after it is clear that the new digital system is working. Moreover, FLHWs are answerable to multiple actors beyond the health system, such as the district collector or the national census, who expect to refer to paper registers. I completely don’t think it’s their fault because the de- mands of the health and nutrition programmes of data to be on paper is huge because it’s not just their programme who ask for the data, they have the census guys coming in and say hey show me the register. She can’t say I have ev- erything on the phone I've stopped maintaining a register. (KI06, donor) In contrast, the nutrition system, ICDS, decided to quickly switch Anganwadi workers (AWWs) from paper to digital record keeping through CAS in order to stream- line front- line processes and avoid creating inconsisten- cies between the two data sources. Removing paper- based records was argued to increase CAS’s sustainability pros- pects, since it would be difficult to remove a digital system once the paper- based records were gone: ‘You will meet your goal if you get rid of paper registers’ (KI06, donor). Procurement hurdles Procurement, whether of handsets, maintenance contracts, server capacity, or platform services, emerged as a major challenge during the implementation process with implications for long- term sustainability. Procure- ment was not challenging due to financial shortages, but because government actors feared taking major contracting decisions (KI11, technology partner). Government actors are scrutinised when they issue large contracts and can be questioned about its transparency and appropriateness even years after signing off on procurement (KI11, technology partner). Nonetheless, a respondent (KI16, technology partner) also reflected that the converse of this reluctance was the speed of larg- escale procurement when a government actor identifies an opportunity to ‘get a piece’ of an expensive contract for personal benefit. Programme developers and funders suggested that sustainability could be fostered by ensuring that govern- ment procurement started at the outset, rather than at BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 169 Singh NS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 9 BMJ Global Health the time of transition (KI02, technical partner; KI16, technical partner). This would ensure that procurement processes are developed long before handover and avoid creating an expectation that funders or technical part- ners would handle procurement over the long term. Evolving stakeholder roles and relationships Evolving roles in implementation Once the decision to scale was approved, a tool’s success depended on the implementing organisation’s commitment and capacity in terms of project manage- ment, training and roll- out logistics, ongoing testing and improving of the tool and dedicated relationship building across actors including the government. Despite being used by government, all cases were developed and implemented through extensive non- governmental inputs (table 1). In terms of sustainability, respondents reflected that although the most intense inputs are required early on, ongoing field presence is necessary to troubleshoot, upgrade software and provide sustained support to FLHWs. Planning for this handover to government was not clearly outlined for some digital tools, potentially creating a sustainability challenge. For example, the NCD app implementor (KI11) explained that his organisation did not plan to be involved ‘forever’ but lacked a realistic transition plan agreed by MoHFW. Although the government has developed institutions for managing digital systems and data, for example, National Informatics Centre, respondents diverged in whether they envisioned the government as likely to gain the capacity to effectively manage these solutions over the long- term, in terms of implementation, technological expertise and management, and strategic/technical inputs. Donor and government funding commitments Although donor contributions are not significant in terms of overall development funding in India, for all cases, donor commitment was key to scaling up digital tools for FLHWs because there is an ‘expensive curve’ at the beginning which requires external inputs (KI03, technical partner), and because donors can bring inno- vations in faster than the government, which in turn saves the government time and energy (KI06, donor). Respondents concurred that a digital tool must have a major donor offering to pay for initial phases. In fact, a respondent speculated that many programmes fail to move beyond the pilot phase because they lack sufficient external financial backing to spark government interest (KI03, technical partner). In terms of sustainability, some respondents suggested an ideal transition arc, with donors taking the initial risk, demonstrating proof of concept, and then having the government take over. Furthermore, a few respondents said that in order to be sustainable, programmes needed to no longer be dependent on donor funding due to shifting donor priorities (KI11, implementor; KI03, tech- nical partner; KI06, donor). I think donors get bored... they want to go on to the next project. The Programme Officers are worried about their career, they're worried about the optics. [...] Don't assume because you're doing good work you can get more [from the donor] ... [Donors are] willing to go fund the next random country just because of politics and stars aligned with, you know, what was a priority at the [donor’s], what was the priority for that Minister, and a conversation had happened (KI16, technical partner) However, other respondents did not consider govern- ment funding as a golden bullet to sustaining digital tools for FLHWs, as even with government funding, programmes could still be cancelled (KI01, technical partner). Furthermore, several respondents did not consider sustainability in light of donor versus govern- mental funding (KI09, government; KI02, technical partner). Beyond the source of funding, respondents noted examples of programmatic adaptations made to conserve finite resources. For direct- to- FLHW solutions like MA, to limit the risk of unplanned and unaffordable call costs generated by non- FLHWs, the programme used an approach called ‘white- listing’. Only FLHW numbers registered in government tracking databases were allowed to access MA. Any number that called MA that was not registered would hear an audio message indicating that the programme was for FLHWs and if the number had been changed, they should register the new number to receive access to the service. Context Data from key informants highlighted national- state dynamics and ministry and programme fragmentation leading to interoperability challenges as influential for scaling and sustaining digital tools. National-state dynamics India’s federated structure generates a tension between national- and state- level decision- making, ownership and control. There is no standardised model for national- to state- level scaling up. When the national government decides to scale a digital tool, they offer it to states along- side funding to enable uptake. This federal structure limited scale- up of the NCD app to a certain extent because states with higher capacity and their own state- level systems (eg, T amil Nadu, Kerala) were hesitant to switch to the new national government- supported programme (KI11, technology partner). In contrast, TECHO+ was solely developed in Gujarat state with extremely strong state buy- in, but no national profile. A national government actor (KI12) lamented the missed opportunity of expanding TECHO+, explaining that Gujarat created a ‘beautiful’ application but since it only works within Gujarat’s Reproductive Child Health (RCH) health information system, it cannot be taken to other states. Respondents did not agree on the ideal balance between national authority and state- level control. Some BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 170 10 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health respondents wanted national government to take the lead in selecting tools because state governments ‘are so busy moving from one crisis to another’ (KI09, govern- ment) or because nationally standardised tools enable rapid and efficient implementation (KI06, donor). Others wanted the national government to provide lead- ership on setting standards and definitions for interop- erability (eg, semantic interoperability to standardise the names for drugs) but to allow states to build solutions themselves. A senior national MoHFW official (KI12) felt that ‘innovation has to be everywhere’ and not only a national function; furthermore, national government should ‘create an ecosystem’ and standards within which states can innovate. If this standardisation is in place, each state can have its own system using a common appli- cation programming interface (API) and all the systems can speak to each other and state level data can be fed into a central database (KI01, technical partner). Interoperability The reality of disparate, vertical applications being imple- mented, often in response to government requests for a single- condition solution, was reported to impede sustain- ability and contribute to an environment of multiple solutions being implemented in overlapping geographies and across same FLHW cadres. Respondents noted that limited intersectoral collaboration between government ministries and within the health system resulted in the creation of parallel digital platforms that are not interop- erable and entrench a siloed approach to the delivery of healthcare, nutrition and other social services. The chal- lenge of interoperability between digital tools within the MoHFW is enormous, but even if they all aligned with the underlying RCH platform, there are multiple other ministries building digital tools that are not interoper- able with RCH (KI03, KI04, technology partners). The most striking example of ministry fragmentation can be found with CAS in the MoWCD and multiple tools in the MoHFW. At the village level, AWWs use CAS, and interact regularly with ANMs, who use ANMOL, TECHO+ and/or the NCD app. Notably, CAS operates on Dima- gi’s CommCare platform, which does not integrate with RCH, which is the platform with which the ANM’s digital tools interoperate. If ICDS- CAS was interoperable then you would be able to integrate the data you have collected from ICDS- CAS with [RCH]. W e are talking about probably the same beneficia- ries in two different systems [...] which is not great (KI04, technology partner) While the digital tools serve the same communities and same people, particularly pregnant and postpartum women and children, they require FLHWs from two different programmes (nutrition and health) to sepa- rately enumerate beneficiaries and collect similar data- sets about them. Moreover, malnutrition or health issues identified by FLHWs in one programme and flagged through one digital tool will not integrate on the other tool, thus institutionalising gaps. One respondent (KI14, evaluator) noted that despite this fragmentation arising from the separate government ministries, FLHWs them- selves often collaborated, and several states showcased positive collaboration. Respondents who had participated in efforts to integrate CAS and RCH were pessimistic about resolving national- level fragmentation because of ‘egos’ (KI14) and ‘turf protection’ (KI16). They also explained that in the interest of individual departmental needs and requirements, it appeared that both Ministries wanted to subsume the other’s digital system. DISCUSSION Given that so few digital programmes scale and then sustain, our study examined several scaled digital tools for FLHWs in India to understand both scale and sustain- ability of digital health programmes. While digital programmes are assumed to be amenable to scale due to the promise of technological innovation, we found not only technical complexity of digital tools, but also signif- icant systems or relationship complexity, requiring itera- tive governance approaches to relationship building. Frameworks for scaling up interventions consider the nature of the intervention and its delivery strategy, attri- butes of the actors involved and elements of the socio- political context. 8 Studies of scaling up interventions concur in their conclusions about the unpredictability of the process and the concerted relationship building involved. The technological complexity of digital health programmes further amplifies the importance of such conclusions, particularly because they are not automated solutions, but require significant technological, social service delivery and governance adjustments. 13 32 33 36 Not only do they require ongoing support from stake- holders outside the health system (technology partners) whose motivations or incentives may or may not align with health system actors, but they must overcome imple- mentation challenges that are unique to digital tools (interoperability, data governance, ongoing innovation and technological support). 43 While factors enabling scale and sustainability did overlap, respondents also noted several nuances that distinguished between them (table 3). Respondents emphatically noted the importance of state- level and national- level policy champions for successfully scaling digital tools; however, sustainable innovations also need long- term sustainable support and buy- in across levels and actors, especially in government. These cases also illustrate the importance of committed teams and strong leaders across donor, technology, technical and imple- menting organisations. As policy champions are political actors who are often reappointed to new positions or leave government if there is a change in party leadership, to be sustainable, digital tools need strategies to engage a churning succession of leaders and a mechanism to build and sustain relationships with bureaucrats below the policy champions. 44 45 BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 171 Singh NS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 11 BMJ Global Health Table 3 Factors influencing scale and sustainability of digital tools for front- line health workers (FLHW) in India FactorsScaleSustainability Digital health solution characteristics Perceived value The solution responds to the needs of various actors. Example: ►FLHW data captur e and decision- support solutions streamline data collection systems and improve the timeliness, quality, accessibility and use of data. ►Direct to FLHW solutions affordable, standardised and logistically simple mechanism to refresh face to face training and fill in knowledge gaps. ►Institutionalises support, supervision, and performance monitoring. ►For FLHW data captur e and decision- support tools, the solution should move beyond data capture for report generation to use of data at multiple levels of the health system to improve provider performance and quality of service delivery. Adaptability ►Configurable softwar e is seen as a more scalable approach which can accommodate differences in state- level health programmes and priorities. ►Extensibility is driven by infrastructure and telecommunications connectivity choices. ►Desir ed configurability to allow for changes over time (eg, addition of new curriculum for Mobile Academy; NCD content added to TECHO+). Data storage and governance ►Use of high- quality cloud- based data storage (eg, Mobile Academy). ►Featur es of data governance, including data privacy, access, consent, not considered to be a key enabler of scale. ►Failur e to prioritise data governance features have likely had adverse consequences on consent capture at the front lines. ►Data governance largely not considered, but understood by some as concerning. ►Evolving data pr otection legislation is likely to have impact on data capture, procedural access controls, and consent processes. Actor roles and relationships Government champions ►Champions in influential government ministerial positions were vital to successful scale- up ►Communication between state government actors important – Example: NCD app and Mobile Academy were first implemented in one state with support from senior actors in that state’s government, who praised the programme when interacting with other states, thus creating champions in other states. ►Sustained engagement from influential government actors critical. ►The movement (due to transfer, retirement, other) of these champions is a significant barrier to sustainability. ►NDHM would also be a factor in enabling sustainability—so not an individual champion but a gover nment champion if you will. Stakeholder networks Important to scaling digital tools for FLHWs Example: A government champion pushing CAS forward to approve decision to scale. Argued as key to longevity of digital tools for FLHWs Example: For Mobile Academy, importance of cultivating deeper relationships going down to all implementers/FLHWs and broader buy- in to ensur e the programme continues when there is turnover of key individuals. Or the NCD one that allows for adding other services. FLHW engagementFLHWs are supported to use technologies Continuous FLHW engagement and feedback is integral to the longevity of the digital tool Example: FLHWs value and demand the tool, and want it fixed if it breaks or crashes. Implementation processes Investing in evidence Formative research used to design solutions Example: Some cases underwent extensive user testing and embedded development (MA, NCD app, TECHO+), while others were first developed by technology partners with specifications/data capture features stipulated, and then adjusted when implemented (ANMOL). ►Evidence linking digital solutions to changes in health outcomes (impact) reported to be desirable. ►Routine use of system generated data seen as integral to demand cr eation and learning from evidence. Operationalisation ►Programme roll- out fosters FLHW engagement and ensur es digital tool addresses FLHW needs ►V aried perspectives on whether to discontinue use of paper records immediately, or in phases. ►Procurement processes are initiated at the outset of the programme versus at the point of transition to government. ►Programme roll- out fosters FLHW engagement and ensur es digital tool addresses FLHW needs ►Pr ocurement processes are initiated at the outset of the programme versus at the point of transition to government. Continued BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 172 12 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health For all cases, we found that genuinely productive part- nerships with the potential to sustain digital solutions require working with ministries that ‘put some money on the table’ from the beginning, along with a major donor offering to pay for initial phases (KI06, donor). Once the decision to scale was approved, success depended on the implementing organisation’s commitment and capacity in terms of project management, training and roll- out logistics, ongoing testing and improving of the tool, and dedicated relationship building across actors including the government. Those seeking to develop, scale and sustain digital tools should note the two central themes related to partnership engagement: the importance of investing in relationships and the power of communica- tion between actors within government. These findings are similar to other studies examining national scale- up that found invoking policy champions and building implementer capacity are key ingredients to catalysing scale- up. 10 46 47 Planning for handover to government needs to be clearly outlined. Procurement, whether of handsets, maintenance contracts, server capacity or platform services, emerged as a major challenge during the implementation process with implications for long- term sustainability . Even once a tool is successfully scaled- up, the handover to govern - ment management can stall, not due to cost but because of procurement, which was challenging not due to funding shortages, but because government actors were afraid of taking major contracting decisions. These challenges are not only faced in more resource- constrained settings, as Lennon et al report similar red tape and ‘procure- ment pains’ when evaluating a digital health innovation programme in the UK. 32 Data highlighted the following components of the government health system context as particularly important for sustaining digital tools: government capacity, dynamics between the national and state levels, and inter- sectoral collaboration. Siloed approaches to the roll- out of the studied digital solutions leading to interoperability challenges, among others, echo findings from a system- atic review of mHealth and telehealth interventions in India that reported most of their included interventions were implemented as standalone solutions, often with no health systems integration strategy. 48 It is thus promising to see the recent finalisation of National Digital Health Blue- print (NDHB), which, when implemented, will enforce standards that will allow for seamless interoperability. 49 Furthermore, the NDHB will redress data architecture and governance challenges reported in our study and imple- ment some key recommendations made by Tiffin et al 50 to reduce the risks of health data breach or misuse in digital health programmes in low- income and middle- income countries, by creating a multitier system that ensures the highest levels of data security and ensuring privacy with Indian citizens as the owners of their data. Limitations First, we studied scaled programmes that are in the midst of their implementation, thus our findings, to a certain extent, speculate on what will facilitate or hinder FactorsScaleSustainability Evolving stakeholder roles and relationships ►Initial donor investment integral to enabling scale. ►Programmatic adaptations may be required to conserve finite resources. ►Concerns about government capacity to ensure handovers. ►Government funding is important but not necessarily sufficient for sustainability, as even with government funding, programmes could still be cancelled. Context National- state dynamics ►Standardised model for national- level to state- level scaling up does not exist. ►Several notable examples of state- level solutions which have scaled. ►National government leadership in establishing standards for interoperability. Requires more robust data governance in long term Example: The national government could create an ecosystem and standards within which states can innovate. If this standardisation is in place, each state can have its own system using a common API and all the systems can speak to each other and state level data can be fed into a central database. InteroperabilityIntersectoral collaboration between government ministries required to reach agreement on common architecture and standards for interoperability. ►Intersectoral collaboration between government ministries required to reach agreement on common architecture and standards for interoperability. ►Need to mandate adher ence to standards once agreed on Example: It is important to ensure that all digital platforms built by all Ministries are interoperable with each other to eradi- cate siloed approaches to the delivery of healthcare, nutrition and other social services. NCD, non- communicable diseases; NDHM, National Digital Health Mission. Table 3 Continued BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 173 Singh NS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 13 BMJ Global Health sustainability of these digital tools in the Indian health programming landscape. This means that while the factors that facilitated scale- up (in terms of the digital solution, actor roles and relationships, implementation processes and context) are based on respondent obser- vation of actual practice, their implication on sustain- ability is speculative and requires longitudinal study. This is a noted limitation in many sustainability studies which do not have longitudinal or extensive retrospective designs. 12 15 26 51 52 Second, given our emphasis on under- standing policy design decisions rather than implemen- tation experiences, we did not include FLHWs among respondents. Additional research to capture front- line experiences of the digital tool, the scale- up process and the actors involved, as well as their views on sustainability would enrich the story. Third, due to the nature of quali- tative research and the limited time available from senior government officials, some components of our frame- work were not evenly probed in each interview, which may have hindered the comparability of the digital tools studied. Finally, the COVID-19 pandemic impacted the availability of some identified respondents, including additional donors, to be interviewed, which led to a smaller sample size in our study than we had anticipated, potentially reducing the robustness of the case studies. CONCLUSION Digital innovations, despite their potential for scale, are not scaled or sustained in either an automated or linear manner. Donors, tool developers, implementors and government actors seeking to scale and sustain digital tools must focus not only on technical capacity but also on investing in people, relationships and service delivery adjustments to overcome significant challenges and uncertainties. It is imperative that we learn from the complexities involved to realise the potential promises of digital health. Twitter Neha S Singh @neha_s_singh and Asha George @ashageorge72 Contributors AEL, NSS, AG and RV conceptualised the study and all authors contributed to the final structure and content of the paper. NSS, KS, AG, AEL and RV collaborated on the data collection. NSS and KS led the overall data analysis, and AG, AEL and RV contributed to specific sections. NSS wrote the first draft of the paper with inputs from KS, and all authors contributed to critical interpretation of the results and development of the paper. All authors saw and approved the final version. Funding We received funding from Countdown 2030 supported by the Bill & Melinda Gates Foundation (award number OPP1148933). AG is supported by the South African Research Chair’s Initiative of the Department of Science and Technology and National Research Foundation of South Africa (grant no 82769) and the South African Medical Research Council. Disclaimer None of the funders had any role in study design, data collection, data analysis, data interpretation, or writing of the manuscript. Competing interests None dec lared. Patient consent for publication Not required. Ethics appro val Ethical approval for this study was granted by institutional review boards (IRBs) at Sigma, New Delhi, India, and at the London School of Hygiene and Tropical Medicine, UK. Provenance and peer review Not commissioned; externally peer reviewed. Data av ailability statement Da ta are available on request. Deidentified participant data are available on request from NSS ( neha. singh@ lshtm. ac. uk). Open access This is an open access artic le distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See: https:// creativecommons. org/ licenses/ by/ 4. 0/. ORCID iDs Neha S Singh http:// orcid. org/ 0000- 0003- 0057- 121X Kerry Scott http:// orcid. org/ 0000- 0003- 3597- 9637 Asha George http:// orcid. org/ 0000- 0002- 5968- 1424 Amnesty Elizabeth LeFevre http:// orcid. org/ 0000- 0001- 8437- 7240 REFERENCES 1 Cargo M. South Africa mHealth landscape. GSMA, 2013. 2 Källander K, Tibenderana JK, Akpogheneta OJ, et al. Mobile health (mHealth) approaches and lessons for increased performance and retention of community health workers in low- and middle- income countries: a r eview. J Med Internet Res 2013;15:e17. 3 Free C, Phillips G, Watson L, et al. The effectiveness of mobile- health technologies to impr ove health care service delivery processes: a systematic review and meta- analysis. PLoS Med 2013;10:e1001363. 4 Free C, Phillips G, Galli L, et al. The effectiveness of mobile- health technology- based health behaviour change or disease management interventions for health care consumers: a systematic review. PLoS Med 2013;10:e1001362. 5 WHO. mHealth: use of mobile wireless technologies for public health who: Geneva, 2016. Available: http:// apps. who. int/ gb/ ebwha/ pdf_ files/ EB139/ B139_ 8- en. pdf2016 6 Mangham LJ, Hanson K. Scaling up in inter national health: what are the key issues? Health Policy Plan 2010;25:85–96. 7 Subramanian S, Naimoli J, Matsubayashi T , et al. Do we have the right models for scaling up health services to achieve the millennium development goals? BMC Health Serv Res 2011;11:1–10. 8 Y amey G. Scaling up global health interventions: a proposed framework for success. PLoS Med 2011;8:e1001049. 9 Geor ge A, Rodríguez DC, Rasanathan K, et al. iCCM policy analysis: strategic contributions to understanding its character, design and scale up in sub- Saharan Africa. Health Policy Plan 2015;30 Suppl 2:ii3–11. 10 Spicer N, Bhattacharya D, Dimka R, et al. 'Scaling- up is a craft not a science': catalysing scale- up of health innovations in Ethiopia, India and Nigeria. Soc Sci Med 2014;121:30–8. 11 Gruen RL, Elliott JH, Nolan ML, et al. Sustainability science: an integrated approach for health- programme planning. Lancet 2008;372:1579–89. 12 Lennox L, Maher L, Reed J. Navigating the sustainability landscape: a systematic review of sustainability approaches in healthcare. Implement Sci 2018;13:27. 13 Gr eenhalgh T, Wherton J, Papoutsi C, et al. Analysing the role of complexity in explaining the fortunes of technology programmes: empirical application of the NASSS framework. BMC Med 2018;16:66. 14 Whelan J, Love P , Pettman T, et al. Cochrane update: predicting sustainability of intervention effects in public health evidence: identifying key elements to provide guidance. J Public Health 2014;36:347–51. 15 Shigayeva A, Coker RJ. Communicable disease contr ol programmes and health systems: an analytical approach to sustainability. Health Policy Plan 2015;30:368–85. 16 Shelton RC, Cooper BR, Stirman SW . The sustainability of evidence- based interventions and practices in public health and health car e. Annu Rev Public Health 2018;39:55–76. 17 Long L- A, Pariyo G, Kallander K. Digital technologies for health workfor ce development in low- and middle- income countries: a scoping r eview. Glob Health Sci Pract 2018;6:S41–8. 18 Huang F , Blaschke S, Lucas H. Beyond pilotitis: taking digital health interventions to the National level in China and Uganda. Global Health 2017;13:1–11. 19 Modi D, Dholakia N, Gopalan R, et al. mHealth intervention "ImTeCHO" to improve delivery of maternal, neonatal, and child care services- A cluster - randomized trial in tribal ar eas of Gujarat, India. PLoS Med 2019;16:e1002939. BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 174 14 SinghfiNS, et al. BMJ Global Health 2021;6:e005041. doi:10.1136/bmjgh-2021-005041 BMJ Global Health 20 Agarwal S, Rosenblum L, Goldschmidt T. Mobile technology in support of frontline health workers: a comprehensive overview of the landscape, knowledge gaps and future directions. John Hopkins University Global mHealth Initiative, 2016. 21 Nimmagadda S, Gopalakrishnan L, Avula R, et al. Effects of an mHealth intervention for community health workers on maternal and child nutrition and health service delivery in India: protocol for a quasi- experimental mixed- methods evaluation. BMJ Open 2019;9:e025774. 22 WHO, ExpandNet. Practical guidance for scaling up health service innovations. Geneva: WHO, 2009. 23 Gr eenhalgh T, Robert G, Macfarlane F, et al. Diffusion of innovations in service organizations: systematic review and recommendations. Milbank Q 2004;82:581–629. 24 Bradley EH, Curry LA, Taylor LA, et al. A model for scale up of family health innovations in low- income and middle- income settings: a mixed methods study . BMJ Open 2012;2:e000987. 25 Schell SF, Luke DA, Schooley MW, et al. Public health program capacity for sustainability: a new framework. Implement Sci 2013;8:15. 26 Chilundo BG, Cliff JL, Mariano AR, et al. Relaunch of the official community health worker programme in Mozambique: is there a sustainable basis for iCCM policy? Health Policy Plan 2015;30 Suppl 2:ii54–64. 27 Labrique AB, Wadhwani C, Williams KA, et al. Best practices in scaling digital health in low and middle income countries. Global Health 2018;14:103. 28 Tomlinson M, Rotheram- Borus MJ, Swartz L, et al. Scaling up mHealth: where is the evidence? PLoS Med 2013;10:e1001382. 29 Abimbola S, Patel B, Peiris D, et al. The NASSS framework for ex post theorisation of technology- supported change in healthcar e: worked example of the Torpedo programme. BMC Med 2019;17:233. 30 Leon N, Schneider H, Daviaud E. Applying a framework for assessing the health system challenges to scaling up mHealth in South Africa. BMC Med Inform Decis Mak 2012;12:123. 31 Gericke CA, Kur owski C, Ranson MK, et al. Intervention complexity- -a conceptual framework to inform priority- setting in health. Bull World Health Organ 2005;83:285–93. 32 Lennon MR, Bouamrane M- M, Devlin AM, et al. Readiness for delivering digital health at scale: lessons from a longitudinal qualitative evaluation of a national digital health innovation program in the United Kingdom. J Med Internet Res 2017;19:e42. 33 Huang F , Blaschke S, Lucas H. Beyond pilotitis: taking digital health interventions to the National level in China and Uganda. Global Health 2017;13:49. 34 WHO. Nine steps for developing a scaling- up strategy , 2010. 35 Hanson K, Ranson MK, Oliveira- Cruz V , et al. Expanding access to priority health interventions: a framework for understanding the constraints to scaling- up. J Int Dev 2003;15:1–14. 36 Noor dam AC, George A, Sharkey AB, et al. Assessing scale- up of mHealth innovations based on intervention complexity: two case studies of child health pr ograms in Malawi and Zambia. J Health Commun 2015;20:343–53. 37 Har dee K, Ashford L, Rottach E. The policy dimensions of scaling up health initiatives, 2012. 38 W alt G, Shiffman J, Schneider H, et al. 'Doing' health policy analysis: methodological and conceptual reflections and challenges. Health Policy Plan 2008;23:308–17. 39 Chandramouli C, General R. Census of India 2011. provisional population Totals new Delhi: government of India, 2011. 40 Sciences IIfP, ICF. National family health survey (NFHS-4), 2015–16. India: IIPS Mumbai, 2017. 41 Chokshi M, Patil B, Khanna R, et al. Health systems in India. J Perinatol 2016;36:S9–12. 42 Noble H, Smith J. Issues of validity and reliability in qualitative research. Evid Based Nurs 2015;18:34–5. 43 LeFevre A, Chamberlain S, Singh NS, et al. Avoiding the road to nowhere: policy insights on scaling up and sustaining digital health. Glob Policy 2021. 44 Shea CM, Belden CM. What is the extent of research on the characteristics, behaviors, and impacts of health information technology champions? A scoping review. BMC Med Inform Decis Mak 2016;16:2. 45 Miech EJ, Rattray NA, Flanagan ME, et al. Inside help: an integrative review of champions in healthcare- related implementation. SAGE Open Med 2018;6:205031211877326. 46 Spicer N, Berhanu D, Bhattacharya D, et al. 'The stars seem aligned': a qualitative study to understand the effects of context on scale- up of maternal and newborn health innovations in Ethiopia, India and Nigeria. Global Health 2016;12:75. 47 Spicer N, Hamza YA, Berhanu D, et al. 'The development sector is a graveyard of pilot projects!' six critical actions for externally funded implementers to foster scale- up of maternal and newborn health innovations in low and middle- income countries. Global Health 2018;14:74. 48 Bassi A, John O, Praveen D, et al. Current status and future directions of mHealth interventions for health system strengthening in India: systematic review. JMIR Mhealth Uhealth 2018;6:e11440. 49 John O. A national digital health blueprint for India: the road ahead. Health BG, 2019. https:// blogs. bmj. com/ bmjgh/ 2019/ 10/ 31/ a- national- digital- health- blueprint- for- india- the- road- ahead/ 50 Tif fin N, George A, LeFevre AE. How to use relevant data for maximal benefit with minimal risk: digital health data governance to protect vulnerable populations in low- income and middle- income countries. BMJ Glob Health 2019;4:e001395. 51 Zakumumpa H, Bennett S, Ssengooba F . Accounting for variations in art program sustainability outcomes in health facilities in Uganda: a comparative case study analysis. BMC Health Serv Res 2016;16:584. 52 Flämig K, Decr oo T, van den Borne B, et al. Art adherence clubs in the Western Cape of South Africa: what does the sustainability framework tell us? A scoping literature review. J Int AIDS Soc 2019;22:e25235. BMJ Global Health: first published as 10.1136/bmjgh-2021-005041 on 26 July 2021. Downloaded from https://gh.bmj.com on 6 January 2025 by guest. Protected by copyright. 175 Chapter 4 of James Barlow (2017) Managing Innovation inHealthCare Digital monitoring for data-driven antimicrobial stewardship: a process perspective from resource- constrained contexts in India YogitaThakral 1,2 * 1 The Health Information Systems Programme (HISP) Centre and Department of Informatics, University of Oslo, Oslo, Norway, 2 Society of Health Information Systems Programme, Health Information Systems Programme (HISP) India, New Delhi, India Antimicrobial Resistance (AMR) is one of society’s most urgent global issues, requiring urgent multidisciplinary-based research and practice approaches to engage with these policies. Several global and national policy statements have been released in the last two decades, particularly emphasising the strengthening ofthedigitalsurveillancesystem.However, implementing these initiatives remains patchy, particularly in the context of public health systems in Low- and Middle-Income Countries. This paper argues that one of the significant reasons contributing to this sub-optimal uptake of these systems is that the top- down implementation models do not adequately cater to the needs, aspirations, and capacities of the health facility staff, who, ultimately, are the end users of the system. The paper highlights the importance of digital technology in healthcare facilities with resource constraints to promote the responsible use of antibiotics. It discusses the process of developing an evidence base for action in low- and middle-income countries (LMICs) through digitally mediated data-driven policy. This process is conceptualised as a three-phase process, which involves stabilising data entry, generating outcomes, and taking action at the local level. The paper argues the need for bottom-up implementation models, which emphasise the need to understand the practices users engage with in their everyday work and design the digital system to add value and not work to these everyday practices. The paper emphasises the importance of building local capacities to develop effective and sustainable antimicrobial stewardship (AMS) programs through enabling networking around digital solutions, creating value in networked partnerships, initiating conversations around data, and raising awareness of the digital to develop AMS programs. KEYWORDS antimicrobial resistance, antimicrobial stewardship, digital intervention, information system, resource constrained, microbiology, AST Frontiers inAntibioticsfrontiersin.org01 OPEN ACCESS EDITED BY Santi M. Mandal, Indian Institute of Technology Kharagpur, India REVIEWED BY Robert Terry, World Health Organization, Switzerland Francesca Prestinaci, National Institute of Health (ISS), Italy *CORRESPONDENCE Yogita Thakral yogitat@ifi.uio.no RECEIVED30 April 2023 ACCEPTED11 July 2023 PUBLISHED02 August 2023 CITATION Thakral Y (2023) Digital monitoring for data-driven antimicrobial stewardship: a process perspective from resource- constrained contexts in India. Front. Antibiot.2:1214826. doi: 10.3389/frabi.2023.1214826 COPYRIGHT © 2023 Thakral. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. TYPEOriginal Research PUBLISHED02 August 2023 DOI10.3389/frabi.2023.1214826 176 1 Introduction Antimicrobial Resistance (AMR) is one of the most significant health challenges facing the world today, particularly in low- and middle-income countries (LMICs) already grappling with existing inequities in access to and quality of care across various socioeconomic, geographic, and demographic categories (WHO, 2022). The causes and effects of AMR are interconnected and mutually reinforcing, with AMR being both a cause and a consequence of existing inequities in LMICs. In India, for example, high disease burden, limited resources, and weak health systems result in the inappropriate use of antibiotics, which is the leading driver of AMR, thereby exacerbating the existing inequities (Charani et al., 2021). Several policies and frameworks are defined at the global and national levels. For instance, the Global action plan (GAP) developed by WHO guided the development of National action plans (NAPs) in partner countries. It discusses the key strategies to address AMR at national and global levels. All NAPs emphasise the importance of using antimicrobials 1 carefully and appropriately (Charani et al., 2023). However, they do not take into account the contextual challenges and obstacles hindering progress towards this goal, especially in resource-constrained settings already grappling with challenges (Iskandar et al., 2021). These challenges include inadequate legal and regulatory frameworks, lack of electronic health record systems, difficulties with access to quality-assured medicines, and, over-the-counter (OTC) availability of antibiotics,. The availability of regular data monitoring and analysis is of utmost importance in addressing Antimicrobial Resistance (AMR). By systematically collecting and analysing data on antimicrobial use, resistance patterns, and associated factors, healthcaresystems and policymakers gain critical insights into the magnitude and trends of AMR within their regions. Regular data monitoring allows for the identification of emerging resistance patterns, high-risk areas, and specific populations that may be disproportionately affected. However, the efforts to combat AMR are challenged by the poor availability of reliable data (Van Boeckel et al., 2014; O’Neill, 2016; Murray et al., 2022), particularly from low and middle-income countries (Laxminarayan, 2022), making it very difficult to estimate the burden of disease (de Kraker et al., 2016). Initiating antibiotics policy-making in LMICs is a complex process that requires navigating through various challenges, particularly in the area of AMR surveillance. Addressing these challenges requires building laboratory capacity, strengthening surveillance systems, and developing a comprehensive framework for managing antimicrobial resistance. The availability of information is a critical component to identifying the contextual challenges to address the challenge of over and irrational use of antibiotics. One of the key strategic priorities in NAPs is to strengthentheknowledgeandevidencebasethroughdigital surveillance and monitoring to strengthen policy and practice. Strengthening AMR surveillance is critical for ensuring evidence- based policy-making and supporting effective strategies to promote the responsible use of antibiotics for controlling the spread of antimicrobial resistance. However, owing to the poor digital infrastructure, most LMICs lack the capability to capture routine health information to understand the existing health disparities effectively (Marmot, 2015). For example, in India, the surveillance of AMR is fragmented, with three independent networks 2 collecting surveillance data based on antimicrobial susceptibility test (AST) results mainly from tertiary hospitals, which is not representative of the resistance profile of the entire country. It lacks uniformity and is not scalable geographically and functionally, and faces challenges of uniformity in data, incomplete information with essentialfields like the demographic details and crucial antibiotics missing (Sonal et al., 2023). Addressing these challenges requires a profound contextual understanding of the everyday practices of the staff in the health institution, and how novel digital capabilities can be introduced to support AMR surveillance for evidence-based policy making. For instance, the everyday challenges faced at the microbiology labs of the hospitals in capturing and analysing the information, the challenges in digital management of data and the challenges at the hospitals to use the information for action for patient care and policy making. The availability of information about how and why antibiotics are being used could inform efforts to drive improvements. This contextual understanding can guide the process of development of information systems, shaping new practices and processes that guide patient care and policy-making at local levels with the ability to be scalable to other contexts (Sahay et al., 2020). Antimicrobial stewardship (AMS) programs aim to improve the quality and safety of antimicrobial use, but the effective implementation of these programs requires a two-pronged approach. Firstly, a sociocultural approach is needed to understand the contextual factors that affect the capturing, analysing and using information at the facility level. Secondly, a technical approach to understand the health information challenges that can guide the design and implementation of digital monitoring systems to make the information available about the contextual challenges of antibiotics use, resistance patterns, dosing, duration of treatment etc. Combining both the sociocultural and technical approaches is crucial for the success of AMS programs in promoting the appropriate use of antimicrobials and reducing the development of antimicrobial resistance. Drawing from a sociocultural and technical approach, this paper describes and addresses these two facets of the challenge of AMR data management by discussing;i) what are the novel data management practices to strengthen AMR surveillance at a facility level, and ii) how can these practices be translated to initiate the development of a data-driven policy for AMS?In answering these 1 Antimicrobials are a broad category of drugs used to treat infections caused by microorganisms such as bacteria, viruses, fungi, and parasites. They include antibiotics, antivirals, antifungals, and antiparasitic drugs. 2 The National Centre for Disease Control (NCDC)- 35 laboratories in state medical colleges, Indian Council of Medical Research (ICMR)- 30 tertiary laboratories and WHO Country Office for India with the Indian Association of Medical Microbiologists Delhi (IAMM-DC) to establish the WHO-IAMM Network for Surveillance of AMR. Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org02 177 questions, this paper describes the long path towards the development of AMS programs in resource constrained contexts. This paper develops a granular view of practices and examines them under three interconnected phases of the process to initiate the development of data-driven policy, i) practices to make the “invisible”more visible? ii) practices to enhance the circulation of this visibility across the health institution, and iii) practices to act on this information for changing policy and practice, within and across hospitals. 2 Materials and methods This is an ongoing qualitative longitudinal study started in 2019 in a tertiary hospital in a north Indian state. The hospital under study, typical of most public hospitals, has limited experience with digital systems and suffers from constraints of weak diagnostics, limited capacity, manpower, and infrastructure, with information on antibiotics prescriptions and consumption currently largely invisible. The hospital has a high patient load (of around 2000 patients every day) that while struggling with historically existing constraints of manpower, resources, and digital infrastructure, took the decision to implement a digital ABR reporting system. The process started with two parallel studies, i) a study of the challenges associated with AMR data management at the hospital, ii) the design and development of an AMR surveillance system at the microbiology lab of the hospital based on a free and open-source digital platform called DHIS2 (see dhis2.org) with technical support of a local NGO called HISP (Health Information Systems Programme) India. This study uses a practice lens (Orlikowski, 2010) to understand the everyday work associated with AMR data management, which was identified, documented, and discussed, which provided insights into the system design. The author of this paper holds dual roles as a researcher and a member of the HISP team. As a researcher, the author studied the practices of antibiotics use and exploring how digital systems can effectively intervene in this process. At HISP India, the author is actively involved in the practical processes of designing, developing, and implementing the digital antimicrobial resistance (ABR) monitoring system. The author’s unique position allows her to observe the real-world practices of antibiotic use in context while also analysing them through the lens of research. This enables bringing a critical perspective to the development and implementation of the ABR monitoring system and to identify areas where improvements can be made. The data collection to study the challenges associated with AMR data management and the design and implementation of an AMR monitoring system were parallel activities and hence discussed together. 2.1 Data collection Data collection and the design and development of the digital monitoring application are carried out as ongoing activities. To understand the challenges associated with AMR data management and ongoing design and development of AMR surveillance system, I studied the overall informationflow at the hospital about how AMR data is generated, where it is generated, and how it reaches the treating physician and the patient, and the practices of the stakeholders involved in AMR data handling. The data collection included interviews and discussions with the hospital stakeholders, with a key focus on the microbiology lab, to understand the practices around sample testing, starting from the arrival of the patient at the hospital, the physician ordering for the AST, sample collection, sample transfer, testing at the lab, documentation, dissemination, and data use. This empirical work fed into the design and implementation of the AMR surveillance system. Table 1provides an overview of the data collection tools of AMR data management, and in the next section, I will discuss data collection in detail: 2.1.1 Semi-structured interviews The interviews were important sources of empirical material. In some of these interviews, the interaction between the researcher and informant was a planned event and was structured as an interview. Often, however, the data collection was moread-hoc, which resulted because of observation or a discussion. The microbiologists, lab technicians, and data entry operators werefirst interviewed using a semi-structured interview guide to understand their respective workflow at the billing and registration department, sample collection unit at the hospital, and microbiology lab. Subsequent interviews were scheduled either because of observations or follow- up interviews from discussions. Open discussions were held with the physicians during the designing of the reports for their feedback on the design during the development and also after the development. 2.1.2 Observation of AMR data management practices Along with the interviews, observing the workflow starting from the patient’s arrival at the registration desk at the hospital (Figure 1) was an important source of data collection. The observations were limited to understanding the AMR data handling practices - how patient data was captured and reached the physician through the microbiology lab during treatment at the hospital. The purpose of being physically present in the hospital, rather than relying solely on interviews, was to witness theirorganization and practices, contributing to an in-depth contextual understanding of theflow of information. These dynamics have been important in shaping knowledge from interviews (Mason, 2017). 2.1.3 Annual workshop An annual workshop was held every year at the hospital premises organized by both the hospital and the HISP India team to discuss the progress implementation challenges, and way forward. It was an important data collection tool to both observe and discuss the progress of the implementation over a period of years and to hear the views of both the microbiology team and the hospital management. The annual workshop was especially relevant, as the diversity and number of participants over the years increased as the Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org03 178 microbiology teams from the nearby hospitals and physicians from several departments in the hospital joined. This helped in gaining a deep insight into the relevance and also the change in the ownership of the application and the data at the hospital by the microbiology team and the hospital and a general sense of AMR data from other stakeholders. 2.1.4 Training sessions Training sessions, both onsite and online, were organized every few months as the application design and implementation followed a quick prototyping approach to provide the microbiology team with the essential features they needed. These training sessions were both important for rapport building initially and later to understanding their requirements and observing their changing views of the digital monitoring application as their desired features were incorporated over a period of time. Training sessions were also an important tool to build the capacity of the microbiology team and observe their requirements becoming more refined as they gained experience using digital technology for data capture and report generation over time. 2.1.5 Weekly meetings Weekly meetings were held mostly online and sometimes on- site, depending on thefield visits. The weekly meetings were an essential tool for understanding the challenges the microbiology team and the data entry operator were facing while capturing the data and generating reports. The microbiology team shared their requirements for features and challenges with using the features and data from the application. Technical, operational, and other challenges were shared, and the HISP team presented new features and sequentially implemented them. These meetings were an important tool for assessing the progress at short intervals and building the local capacity of the microbiology team to test the application when new features were added and to generate their own reports regularly. As the application started taking stronger roots and the data entry became increasingly stable, discussions with physicians and hospital staff on aspects of the use of the reports were initiated. 2.2 Data analysis The data analysis followed sequential steps: Data collation and organization:All data collected including interview notes, observations, and study of documents were organized and collated to facilitate analysis.Transcriptions: All TABLE 1 Data collection tools. Stakeholder groupData collection methods NumbersDetails Staff at the registration and billing counterInterviews2Workflow and activities involved during registration, billing, sending the patient for consultation, collecting the sample and getting test results from the lab. Challenges faced with the existing workflow. Staff at the sample collection unit responsible for collection and transfer 2Existing methods of sample collection, transfer to various labs, challenges faced Physicians10Information needed for patient care, if it is readily available, what information is needed, preferable format for reporting, challenges with the existing workflow, suggestions for improvements Microbiologists5Data reporting and details of reporting to physicians and the state/reports dissemination to patients/physicians. Lab technicians3Receiving samples, maintaining records, testing, etc., at the lab. Data entry operator (DEO) at the lab2Data entry andflow of information using the application and challenges in cases the test is delayed, missing information in registers, etc. Registration staff, sample collection staff, Microbiology team, Lab technicians, DEO ObservationAMR data handling in the registers and digital application; Billing and sample collection; Microbiology lab-data entry, reports dissemination, data use Physicians, microbiologists, staff at the microbiology department, and the Principal of the hospital DiscussionDuring the design, development, implementation, and efforts to use the data. Microbiology teams, Physicians, Hospital management, HISP India (technical) team, Microbiology team from other hospitals in the state WorkshopAnnual workshop for requirements analysis, implementation progress, challenges and the way forward. FIGURE 1 Registration and billing counter at the hospital. Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org04 179 primary data was transcribed and translated from Hindi to English wherever needed, and digitized.Thematic analysis to identify the AMR data management challenges: First, responses were grouped, and major practices were identified representing the understanding of the problem. For example, a major theme identified from the analysis of physicians’interviews was the lack of information to decide the antibiotic treatment. The unavailability of information for patient treatment and for preparing local guidelines in the form of antibiotics policy was addressed through a digital reporting system that potentially would make available testing profiles to physicians to guide their prescription decisions. The base for generating these testing profiles was the automation of the testing process (called AST–Antibiotic Susceptibility Tests) which was carried out in the microbiology lab. The process included theinitial requirements construction, followed by continuous ongoing and intertwined processes of design improvements, implementation, and regular evaluations. 3 Results In this section,first the results from the study of challenges associated with AMR data management are described. This is followed by a description of the practices identified subsequently leading to the development of data-driven policy, i) practices to make the“invisible”more visible, ii) practices to enhance the circulation of this visibility across the health institution, and iii) practices to act on this information for changing policy and practice, within and across hospitals. 3.1 AMR data management practices The hospital under study had limited prior experience with digital systems. The process of recording patients’data, testing samples, maintaining records, and sharing reports with patients and physicians was manual and time-consuming. A microbiologist mentioned: Once the test results are ready, they are documented on paper and in the register. Patients or their attendants come to the lab to collect the results, and the rest of the test results are kept on a table once the lab closes every day at 15:00 for patients to come and collect themselves. To carry out the AST test, the microbiologists mentioned that they sometimes lacked the stock of antimicrobial discs to test the samples received at the lab. In the absence of antimicrobial discs, certain antimicrobials could not be tested for some bacteria that were crucial to be tested for certain infections. There were regular stock delays and operational challenges, which prevented microbiologists from generating quality data. One microbiologist explained: We have asked the central store for a stock of cefixime from the last two months, but we have not received the stock yet. In situations when we do not have an antibiotic plate for testing, we usually test other antibiotics from the panel because it anyway takes multiple stock requests and a very long time to get the stock. This challenge of microbiologists to perform the tests for certain antibiotics also affected physicians’prescription practices and supplemented their reasons not to prescribe an AST test. A physician described: A lot of patients come with a complaint of obstructive pulmonary disease, and in such cases, I need the resistance pattern for cefixime to see if I should prescribe it or should I prescribe a higher-generation antibiotic. But I do not see the resistance pattern for cefixime in the results. The test results are received late and incomplete. So, I prescribe based on my own experience. The challenge of delayed test results amplifies by the incomplete information the microbiologists were provided with. The lab technicians at the microbiology lab complained about the quality of the information received in the requisition forms with samples to be tested. These forms were frequently incomplete, with missing patients and sample details. The form had a code of the sample that was mentioned on the vial containing the sample and the name of the patient. However, other details like the department where the patient is treated, his/her diagnosis, and many other relatedfields were often blank. These issues added to the delays in getting test results. The microbiology lab found it difficult to document and sometimes even test such samples with the basic information being unavailable. A lab technician exclaimed: It is really difficult to test because of incomplete information. Sometimes the sample type and the patient’s CR number (unique number) are missing from the form. It is not possible to start the test without these basic details, and the sample is sent back to the collection unit for more information. The hospital did not have existing guidelines for antibiotic use or infection control to guide physicians of how to prepare treatment plans. During the discussions, the head of the microbiology department said: We have all the data lying in registers, and these registers are not digitized. Whenever someone asks for some information on a particular pathogen, we look at the registers and collect information from them, and share. To develop an infection control or an antibiotic policy, a huge amount of analysed data from all pathogens is needed, which is not available right now. The microbiology team was initially unable to generate an aggregate report to be shared with the hospital management and state authorities due to the manual and fragmented nature of data records. A microbiologist at the hospital explained: It is impossible to generate a report with the data in the registers. We can count estimates based on the data for specific pathogens, but a holistic analysis of the test results is impossible to generate with manual analysis. There are three registers each for Blood, Urine, and all other samples, and to prepare an aggregated report, the data from all registers need to compile separately and then aggregated. Another microbiologist at the lab mentioned: Finding relevant data manually from all the registers and then aggregating them together from all registers is a tedious exercise. The team does not have the time to do this task, and there is already a manpower crunch at the lab. We only have two lab technicians who do all the work, and they need to stay overtime to start the culture for the samples received later during the day. Data analysis becomes secondary when there is a huge daily task that needs to be done. Limited capacity and resources added to the existing challenges of delayed test results. Studies of practices of antibiotics use and Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org05 180 AMR data handling guided the identification of the class of problems. 3.2 Practices to make the“invisible” more visible In this case, the term invisible refers to the unavailability of actionable data at both the practice and policy levels for local action at the hospital. The unavailability of data is made worse by the constraints of capacity, resources, and lack of experience with the digital systems accompanied by less awareness about the problem of AMR in the public health system. At the micro level of the hospital, the practice of managing the AMR data at the microbiology lab is largely manual. The lab has manual registers where the technicians record the patients’, samples, and test results daily before being relayed back to the indenting department. Existing data in the manual registers was not subjected to any systematic analysis before the introduction of the digital application and was now captured and analyzed to identify the resistance patterns in the hospital. However, this journey of transformation involved work and transformation of the existing practices of manual data collection and management to enable the digital system to make the problem of AMR visible. The initial focus was mainly on i) recording the AST requisition form sent by hospital physicians to the lab, and ii) recording the test results. Subsequently, other modules have been incrementally added (for example, data analysis, and infection control) based on continuous discussion and interactions with the team in the lab. Several challenges were observed after the introduction of the digital system that required changes in the existing practices to stabilize the use of the digital application. An important initial challenge was to strengthen the practices by which the missing details in the requisition form, such as the patient’sclinicalsymptoms, diagnosis, antibiotics treatment, and sometimes even the sample type and location, could befilled. A microbiologist told during an interview: The requisition form received with each sample from either the sample collection unit for outpatients or wards/in-patient departments is incomplete in many cases or is illegible. There is no information on the diagnosis, proposed antibiotic treatment plan, etc. advised before ordering AST. This missing information needed to befilled in to generate more meaningful reports, such as resistance patterns by departments and sending test results to the treating physicians and ultimately the patients. The software team worked closely with the microbiology team to identify missingfields by creating a report, which was then presented to the microbiologists. The microbiology team used this report as evidence and took it to the medical superintendent of the hospital to drive policy actions, such as requiring trained medical interns to be primarily responsible for sample collection and ensuring all sample details werefilled in the requisition form before they were accepted for testing. The microbiology team also changed the format of the requisition form where they highlighted the mandatory information which was required to befilled before the sample was accepted. The software team then automated the process of report generation and now a monthly report is generated and reviewed monthly to understand what gaps persist. A data quality report generated two months after the workarounds were implemented at the hospital is shown inTable 2,reflecting a significant improvement in completeness, with now less than 20% of thefields being incomplete as compared to 70-80% previously. 3.3 Practices to enhance the circulation of this visibility across the health institution As the data entry processes were increasingly streamlined, the attention shifted to the outputs and the microbiologists started giving requirements for their desired data outputs. These requirements were discussed with the software team, developed, and made available through the customized dashboards offered by the digital platform. The microbiologists could now independently download the automated reports from the application dashboard, which was updated daily with current data, and a stack of reports started to be compiled and emailed to the hospital management, such as the Antibiotics Stewardship Committee, the clinical departments, and also the State Secretariat. Some of the reports on the dashboard are shown inFigure 2, including an aggregation of the sample types received at the lab, organisms identified from the samples, and the antibiotics sensitivity pattern. A microbiologist mentioned the utility of these reports in day- to-day work: TABLE 2 Comparison of data quality over a year. PeriodOut patient countMicrobiology investigations Tests/Out patient count (%)Total investigationsTests/total tests (%) Yearly average641212144622.267180972.01 Monthly average4529112572.78672191.87 Daily average2313522.2528681.81 Comparison to the previous year May 2021159239275.82356852.60 May 20224932418263.70785482.32 Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org06 181 It used to take us weeks to count the numbers from the register and prepare a report. Sometimes, we even skipped developing this report because it was cumbersome and practically impossible to count severalfigures and document them correctly. Butnowwithsupportfromthedigital application, the microbiology lab saw the potential of evolving the existing quarterly susceptibility report into a quarterly organization-wide susceptibility report. After many rounds of discussions, it was decided to develop an aggregate report with department-wise trends of resistance, which could potentially help physicians to decide on the antibiotics to be prescribed based on the sensitivity patterns highlighted by the test reports. The microbiology lab took 4-10 days from the day of sample collection to the generation of the test report. This was too long, and in the meantime, the physician would end up prescribing broad-spectrum, higher-generation antibiotics to provide immediate care to the ailing patients. With this report, the team identified that physicians could make better evidence-based decisions, even in the absence of immediate test results. A sample monthly resistance report sent to all physicians is shown inFigure 3. Another new practice introduced was in the process of displaying the test results. The existing manual registers did not have thefields (and space) to capture details of the department, location by month and year, and to alsofit in one page the long FIGURE 2 A sample dashboard. Percentage susceptibility & Location-wise distribution of LRT (Lower Respiratory Tract) isolate groups Department: ALL Period: January 2023 to June 2023 GPC LRT (Lower Respiratory Tract) % Susceptibility of Isolates to tested antibiotics Susceptible/Tested Isolates Total no. of isolates (1/patient) Location %/N Per Location Staphylococcus aureus (N=55) OPD 36.36 20(12/18)(9/19)(8/18) (1/1)(12/12) (1/1)(4/19)(8/17) (18/18) CCU 3.64 2(1/2)(1/2)(2/2)(2/2)(1/2)(2/2) Unknown 12.73 7(1/5)(1/1)(2/6)(4/5)(2/2)(1/6)(7/7) ICU 14.55 8(1/8)(4/7)(4/4)(2/3)(1/1)(2/2)(3/7)(8/8) Ward 32.73 18(2/14)(12/15) (1/1)(1/18)(1/1)(7/17) (18/18) Enterococcus faecalis (N=38) OPD 78.95 30(13/13)(2/3)(3/3)(29/30) (21/21) (2/2)(25/28)(19/25)(27/27) Ward 18.42 7(5/6)(1/1)(6/6)(7/7)(6/7)(2/5)(6/6) ICU2.63 Ampicillin Cefoxitin CiprofloxacinClindamycinDoxycyclineErythromycinGentamicinGentamicin HL LevofloxacinLinezolidOfloxacinPenicillin Quinupristin Dalfopristin Teicoplanin Tetracycline Trimethoprim/SulfamethoxazoleVancomycin FIGURE 3 A sample department-wise report. Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org07 182 computer registration number. To resolve this issue, the microbiology team decided to design stamps with a predefined list of antibiotics for each sample and organism to be printed in the register to minimize manual data entry by the lab technicians, maintain data quality by standardizing the output, and in saving time to circulate the results. As a future practice modification, the microbiology team has also decided to change the format and reprint the registers to capture the necessary information after finishing their existing printed stock of registers. For example, the existing register does not have thefields for departments (Medicine, Surgery, etc.) and location (Outpatient department, Inpatient department, Intensive care unit etc.) The format of new registers is being defined with the data set to be analyzed in consideration. 3.4 Practices to act on this information for changing policy and practice, within and across hospitals As the microbiology team started generating their reports in their desired formats, the focus shifted to enabling the use of the data to build greater awareness about the problem of AMR within the hospital. As data entry processes improved, the microbiology team identified clinically relevant data to be reported to the physicians and the hospital management. For example, the microbiology team included age and gender-specificdatato identify the age and gender-specific resistance. Another reporting format was developed which identified the top three resistant and sensitive isolates in the hospital. 3.4.1 Dissemination of information to the treating physicians The monthly and quarterly department-wise reports sent to all treating physicians at the hospitals can potentially guide them to prescribe antibiotics therapy. Interviews were conducted with the physicians at various departments in the outpatient departments, wards, and ICUs to understand how these reports can be improved to better meet their needs. A consultant from the Gastroenterology department said: I always wondered if I had such a report available while prescribing, I would have an idea of what antibiotics are susceptible and resistant in the area. Currently, we prescribe a second or third line of antibiotics during thefirst consultation, but it is better to prescribe thefirst-generation antibiotic if it is susceptible in almost 80% of cases as I see in this report. However, I did not think anyone would take an initiative to make such data available at a public hospital. 3.4.2 Dissemination to the antimicrobial stewardship (AMS) committee and state As per the national guidelines, all public hospitals were mandated to form an antimicrobial stewardship committee. The hospital formed a committee in October 2021, which is led by the Head of microbiology and includes members from other departments, such as Medicineand Surgery. The committee meets every month, and the HOD microbiology presents the monthly resistance profiles downloaded from the monitoring application to the members. The committee decided to use one year of resistance profile report data to develop an infection control and antibiotics use policy for the hospital. Additionally, the hospital shares a monthly resistance profile with the AMR coordinating centre in the state. A depiction of theflow of information with these interventions is shown inFigure 4. This process is now ongoing with the research team to have discussions with the different teams, understanding their information needs identified in reference to the current organization-wide report format, and for the technical team to provide the required data support. In an annual workshop organized in July 2022, the new hospital that had adopted the application updated the progress of data entry and AMR data management. This time the physicians from all clinical departments also attended the workshop to discuss the possibility of using the resistance data effectively, particularly for patient care and policy making. All departments in the meeting after the workshop were directed to develop a department-wise guideline based on the reports they received and submit it to the department of Pharmacology. The microbiologists showed their reports from the last three years to all department heads attending the meeting. The chief pharmacist and team were made responsible for developing and presenting a hospital antibiotic policy in consideration of the guidelines shared by all departments. The hospital antimicrobial stewardship committee was thus tasked to develop a local antibiotics policy with guidance from experts from other hospitals who have developed this policy. This stage had its challenges, and further work is required to create the policy and implement it. Additionally, a baseline AMR application with minimum data set for AMR monitoring was maintained by the technical team with basic features to report, monitor, and analyse AMR data. This allowed the implementation of the application in other contexts with minimal development requirements. At the same time, new requirements, like the Android reporting and new reports developed at other sites, have been incorporated for new facilities, and some of them have been made available to the original facility to add greater value to their processes. Having data reported on standard parameters also helped in extending the learnings from this hospital to other medical college hospitals in Himachal Pradesh state to strengthen the state-wide reporting system. 4 Discussion The process of developing an evidence base for action in LMICs is a multi-stage process that is conceptualized through three interconnected phases: input, output, and outcome. This is conceptualised as a process perspective for developing a digitally mediated data driven policy. 4.1 Digitally mediated data driven AMS at local level Thefirst phase, input, involves the stabilization of data entry, ensuring that the data collected is reliable and accurate. A regular monitoring of the data entry and validation of the data collected in Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org08 183 the manual registers and the digital application is essential. The second phase, output, involves the generation of outcomes, where data is analysed and transformed into useful information for decision-making. Finally, the third phase, outcome, involves the use of information to initiate conversations around data and take action at the local level. This process began with digitising and stabilising the data entry practices on the input side and then constructing outputs. These outputs were the foundation for developing outcomes using data to guide policy and practice decisions. This process necessitated continual, interdependent, and iterative cycles that built upon the inputs, fed into the outputs, and ultimately led to the articulation of outcomes. This process is conceptualised analytically as three interconnected stages, and the process, leading to organisational outcomes of a digitally enabled institution for AMR data management relevant to an LMIC context. The importance of digital surveillance in promoting responsible use of antibiotics cannot be overstated. This paper emphasizes the crucial role of digital technology in healthcare facilities with resource constraints to promote responsible use of antibiotics. This information can be used to develop preventative strategies to improve antibiotic stewardship and reduce the emergence of antibiotic-resistant bacteria. However, the process of designing, implementing, and routinizing digital surveillance technologies in resource-constrained settings can be challenging. It goes through a process of building local capacities to initiate conversations around data and building skills to manage and analyse data effectively. It also involves raising awareness about the use of digital technologies and preventative strategies among healthcare professionals and stakeholders. To overcome these challenges, the paper argues for building local capacities to develop effective and sustainable antimicrobial stewardship (AMS) programs. This involves i) enabling networking around digital solutions, ii) creating value in networked partnerships, iii) initiating conversations around data, and iv) raising awareness of the digital to develop AMS programs. 4.2 Enabling networking around digital solutions and data Drawing from the understanding of context-specific challenges, by understanding the processes and mechanisms for building a network of collaboration among multiple stakeholders through digital interventions. This research describes how these networks are slowly and incrementally built and evolved through sharing knowledge and collaborative work. The collaboration between HISP India and the hospital team started as a system development exercise with the microbiologists, which slowly evolved as they participated in the design of the antibiotics stewardship management policy involving the clinicians and hospital administration. Building capabilities of the hospital staff around the digital tools was key in enabling intra-hospital and inter-hospital networking. As they became more confident of the digitally analysed testing data, the microbiologists could speak up strongly in the antibiotics stewardship committee meeting and build the basis for the principal to declare what he wants for the hospital:“a data-driven locally relevant antibiotics stewardship policy”.Inworkshops,which microbiologists from the neighbouring hospitals also attended, the reference hospital could proudly demonstrate their work and encourage the other hospitals to initiate similar processes in their settings. The underlying message conveyed in these interactions was “if we can do it, even you can do it.”. Today, one other hospital has FIGURE 4 Informationflow after the interventions and data use efforts. Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org09 184 established and is routinely running a similar digital system, and two others are ready to start once their lab infrastructure is established. The timeframe to operationalise this scaling was much shorter than in thefirst hospital, as they could benefit from the earlier learning. 4.3 Capacity building through mutual learning The digital intervention goes through cycles of refinements ranging from major to minor design changes after initial implementation based on identifying organisation-specific requirements. This ongoing design and implementation followed ‘learning by doing’, which practically contributed to building the hospital team’s technical and adaptive capacity through mutual learning and knowledge exchange and translation. The mutual learning approach recognises that knowledge has to be always shared both ways: HISP team learnt about the domain of AMR and data handling practices of the hospital; the hospital staff needed to learn about the functioning of the digital tool, what it can and cannot do, and how best it can add value to their work. In the initial design, the microbiology team could not coherently describe their requirements, but as they saw the system and understood its potential, they could slowly start telling their needs, which increasingly became more sophisticated over time. Similarly, as the NGO learned more about the hospital work, they could also make suggestions for features to be incorporated into the application. For example, as the microbiologists described their analysis needs, the NGO pointed out the current registers don’t record the particular data (for example, the patient’s location). The microbiologists then took the proactive step of writing to the principal, requesting permission to reprint the registers incorporating the necessary datafields. Highlighting mutual learning, one microbiologist mentioned,‘The development of the digital system is a process of learning for us as well. We are not only learning about digital management of AST test results and how to use the system but also identifying new ways to improve our processes as we face a challenge with the system,’ 4.4 Initiating conversations around the data The research on health IT in LMIC contexts has forever lamented the problem of“too much data and too little use” (Sahay et al., 2017). Often, a solution to this problem is to build more shiny dashboards and digital tools, and current debates are extolling the virtues of big data and machine learning (Schwalbe and Wahl, 2020). This represents a response based on rational principles that more data will lead to more (and better) action, an assumption that has been discounted by research (Sahay et al., 2017). This paper describes that the focus on digital enhancements on their own, which tend to focus on data as an end product or commodity, is inadequate. It is rather important to understand the processes by which data is collected, quality-assured, analysed, and circulated. Each stage of thisprocessinvolvesdifferent conversations around data concerning different actors. In this research, at the data entry level, it was between the data entry operator, the microbiology lab staff, and HISP India, while at the stewardship management committee, it was between the principal, the clinicians, and microbiologists. This paper highlights how these conversations around data provide the basis for action. For example, when a gynaecologist was presented with an organisation-wide report showing the resistance pattern, she realised that in the future, she would consider prescribing afirst-generation antibiotic to patients with Urinary Tract Infections instead of the previous practice of prescribing a second-generation antibiotic. For the NGO team, regular conversations with the hospital staff provided them with the basis to improve the design and continuously provide the hospital with upgraded functionalities. Identifying actions to be taken often raises the need for new conversations, such as of the principal with the clinical departments, on how the policy can be made more relevant to them. Employing WHO AWARE (Access, Watch, Reserve) scale is an important tool to streamline the use of antibiotics and for the development of antimicrobial stewardship policy. WHO AWARE scale highlights the importance of matching prescriptions to the infectious agent. By doing so, healthcare professionals can ensure targeted treatment, preserve the effectiveness of antibiotics, and promote patient understanding and adherence. These practices are fundamental in combating AMR and preserving the efficacy of antibiotics for future generations. 4.5 Raising awareness of the digital in its mitigation Antibiotics use, and prescriptions represent complex bio-social processes driven by several medical, social, cultural, and economic conditions. In LMICs, with existing challenges of capacity and resources, creating awareness about“new”problems when hospital staff is already preoccupied and overburdened with existing challenges is a complex undertaking. While the global and national levels have developed various guidelines and policies around AMR, these tend to be poorly understood and translated into hospital settings of LMIC contexts (Charani et al., 2023). This translation requires deeply contextualised and intensive institutional work, including building awareness of the problem and potential solutions to address them. The microbiologists were identified as key actors in this process of making AMR data visible and working closely with them, relevant digital solutions were designed and made to work to support different processes of data entry, data quality, analysis, and dissemination of analysed reports. These processes helped raise awareness of the problem incrementally,first among the microbiologists and then others in the hospital. Further, it was demonstrated that it is not all hopeless, as digital technologies supported by collective and collaborative actions can contribute tofinding some local solutions. Through this analysis this paper makes two key contributions toward engaging with the practical challenge of raising awareness. Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org10 185 One, top-down guidelines and directives tend not to work at the micro-level since actors are preoccupied with their local everyday challenges. These directives need to be translated and made relevant to these actors in the context of their everyday work. Two, since there are multiple constituencies involved, a common thread for building awareness needs to be identified and nurtured. This common thread, in this case, related to digitally generated AMR testing data, which was required by the microbiologists, the clinicians, the hospital administration, and the patients. The digital solution thus served asanimportantvehicletobuild awareness and mobilise the intentions of collective action. This initiated a process of building a shared understanding of the“why” of the institutional work. 4.6 Creating value in networked partnerships This research helped to identify that the value proposition for different actors within a heterogenous group varies, and it needs to be approached incrementally and with different means. For the microbiologists, it gave them more control over the testing data by reducing the burden of their everyday manual work and allowing them to focus on data analysis, which was a source of professional pride. Further value came to them as they found more confidence and voice to express theirfindings in the hospital-wide stewardship management meetings. The principal of the hospital, who was responsible for implementing the state mandate of creating effective stewardship management, saw value in how the organization-wise infection analysis could help in building a data- driven policy. Achieving this would no doubt help showcase his hospital in the rest of the state. However, it must be emphasised that building this policy is not a given but will require further and intensive collaborative institutional work. Value for the clinicians came as they could use the analysis reports to do better clinical therapy. This, too, is not a given as there are disagreements between disciplines, such as between paediatricians and surgeons, about the value of data for guiding clinical therapy. These differences must also be negotiated over time, and data must be better customised for different needs. For the NGO, the value came with building unique digital innovations in areas that were to date unchartered. Their experiences in this hospital opened the doors for projects in other states and countries. This analysis resonates with the comment by (Selznick, 2011) that institutions are“infused with value, that is prized not as tools alone but as sources of direct personal gratification and vehicles of group integrity”. The associated stakeholders need to derive value from work, which needs to be developed incrementally and over long periods. The value developed for the microbiologists further yielded value for other constituencies within the hospital (such as the principal and physicians), who then initiated workshops that other hospitals could attend and adopt the digital systems. With time, the aim is to develop a state-wide reporting network, making it pioneering in the country. Also, this paper describes that this value is not a given and will never be static, but would need to be constantly created, maintained, and disrupted. For example, the HISP India needs to continually upgrade and innovate digital solutions to meet the diversity of emerging information needs. The principal needs to constantly negotiate with the different actors in his hospital, for example, the paediatricians and surgeons, to work within the framework of a data-driven policy. Such cumulative value development will necessarily take place over extended periods. 4.7 Regular operational research Regular operational research activities play a crucial role in monitoring the progress of Antimicrobial Resistance (AMR) monitoring efforts. These activities provide valuable insights and data that help assess the effectiveness of interventions, policies, and strategies aimed at combating AMR. By employing rigorous research methodologies, such as data collection, analysis, and evaluation, operational research activities enable the tracking of key indicators related to AMR, including the prevalence and patterns of antimicrobial use, resistance rates, and the impact of interventions on reducing AMR. This information allows policymakers, healthcare professionals, and researchers to make evidence-based decisions, identify areas of concern, and develop targeted interventions to address the challenges posed by AMR effectively. Furthermore, regular operational research activities help identify emerging trends, evaluate the implementation of control measures, and contribute to the global knowledge base on AMR, thereby facilitating continuous improvement and informed decision-making to mitigate the growing threat of antimicrobial resistance 5 Conclusion This paper highlights the multi-stage process of developing an evidence base for action in LMICs, using the example of developing a digitally mediated data-driven policy for AMS. The three interconnected phases of input, output, and outcome, are crucial in ensuring the reliability and accuracy of data collected, generating useful information for decision-making, and taking action at the local level. The paper emphasizes the importance of digital surveillance in promoting responsible use of antibiotics and building local capacities to develop effective and sustainable antimicrobial stewardship programs. Enabling networking around digital solutions and data, building capabilities of hospital staff around digital tools, and initiating conversations around data are crucial in capacity building and mutual learning. Finally, the paper argues that digital interventions must go through cycles of refinements based on identifying organisation-specific Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org11 186 requirements and promote mutual learning to ensure effective implementation and sustainable impact. Data availability statement The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation. Author contributions The author designed the study, performed the research including and data analysis, and wrote the manuscript. Conflict of interest The author declares that the research was conducted in the absence of any commercial orfinancial relationships that could be construed as a potential conflict of interest. Publisher’s note All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher. References Charani, E., Mendelson, M., Ashiru-Oredope, D., Hutchinson, E., Kaur, M., McKee, M., et al. (2021). Navigating sociocultural disparities in relation to infection and antibiotic resistance-the need for an intersectional approach.JAC-Antimicrob Resist.3 (4), dlab123. doi:10.1093/jacamr/dlab123 Charani, E., Mendelson, M., Pallett, S. J. C., Ahmad, R., Mpundu, M., Mbamalu, O., et al. (2023). An analysis of existing national action plans for antimicrobial resistance— gaps and opportunities in strategies optimising antibiotic use in human populations. Lancet Glob Health11 (3), e466–e474. doi:10.1016/S2214-109X(23)00019-0 de Kraker, M. E., Stewardson, A. J., and Harbarth, S. (2016). Will 10 million people die a year due to antimicrobial resistance by 2050?PloS Med.13 (11), e1002184. doi: 10.1371/journal.pmed.1002184 Iskandar, K., Molinier, L., Hallit, S., Sartelli, M., Hardcastle, T. C., Haque, M., et al. (2021). Surveillance of antimicrobial resistance in low- and middle-income countries: a scattered picture.Antimicrob. Resist. Infect. Control10 (1), 1–19. doi: 10.1186/s13756-021-00931-w Laxminarayan, R. (2022). The overlooked pandemic of antimicrobial resistance. Lancet399 (10325), 606–607. doi:10.1016/S0140-6736(22)00087-3 Marmot, M. (2015). The health gap: the challenge of an unequal world.Lancet386 (10011), 2442–2444. doi:10.1016/S0140-6736(15)00150-6 Mason, J. (2017).Qualitative Researching. (Third ed.) Sage Publications Ltd., 289. Murray, C. J., Ikuta, K. S., Sharara, F., Swetschinski, L., Aguilar, G. R., Gray, A., et al. (2022). Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis.Lancet399 (10325), 629–655. doi:10.1016/S0140-6736(21)02724-0 O’Neill, J. (2016). Tackling drug-resistant infections globally:final report and recommendations. In: Ro, A. ed. Resistance. (London, United Kingdom). 1, 84. doi: 10.4103/2045-080x.186181 Orlikowski, W. J. (2010).“Practice in research: phenomenon, perspective and philosophy,”inCambridge Handbook of Strategy as Practice. Eds. D. Golsorkhi, D. Seidl, E. Vaara and L. Rouleau (Cambridge: Cambridge University Press), 23–33. Available at:https://www.cambridge.org/core/books/cambridge-handbook-of- strategy-as-practice/practice-in-research-phenomenon-perspective-and-philosophy/ 94B98C767B58C69DD7435F9CA19B6FCE Sahay, S., Arora, G., Thakral, Y., Rødland, E. K., and Mukherjee, A. S. (2020). “Designing for scale: strengthening surveillance of antimicrobial resistance in low resource settings,”inIFIP Joint Working Conference on the Future of Digital Work: The Challenge of Inequality: IFIP WG 8.2, 9.1, 9.4 Joint Working Conference. (Hyderabad, India: Springer International Publishing). 251–264. Sahay, S., Sundararaman, T., and Braa, J. (2017). Public health informatics: designing for change-a developing country perspective (Oxford University Press). p. 261. Available at:https://scholar.google.com/scholar_lookup?hl=en&publication _year=2017&pages=261&author=S.+Sahay&author=T.+Sundararaman&author= J.+Braa&title=Public+health+informatics%3A+Designing+For+change+%E2%80%93 +A+developing+country+perspective#d=gs_cit&t=1690432442542&u=%2Fscholar% 3Fq%3Dinfo%3A3VZEyCcPUcAJ%3Ascholar.google.com%2F%26output%3Dcite% 26scirp%3D0%26hl%3Den. Schwalbe, N., and Wahl, B. (2020). Artificial intelligence and the future of global health.Lancet395 (10236), 1579–1586. doi:10.1016/S0140-6736(20)30226-9 Selznick, P. (2011).“Leadership in administration: A sociological interpretation,”inQuid Pro Books. Available at:https://scholar.google.com/scholar?q=Selznick,+P.+(2011).+%E2% 80%9CLeadership+in+administration:+A+sociological+interpretation,%E2%80%9D+in +Quid+Pro+Books&hl=en&as_sdt=0,5#d=gs_cit&t=1690464827618&u=%2Fscholar%3Fq %3Dinfo%3APn0VW3KxKuQJ%3Ascholar.google.com%2F%26output%3Dcite%26scirp% 3D0%26hl%3Den. Sonal,S.,Anuj,S.,Amala,A.A.,Pandey,A.,Kochhar,A.,Mittal,A.,etal.(2023).Delhi’s network for surveillance of antimicrobial resistance: The journey, challenges and output from first year.Indian J. Med. Microbiol.41, 19–24. doi:10.1016/j.ijmmb.2022.12.001 VanBoeckel,T.P.,Gandra,S.,Ashok,A.,Caudron,Q.,Grenfell,B.T.,Levin,S.A.,etal. (2014). Global antibiotic consumption 2000 to 2010: an analysis of national pharmaceutical sales data.Lancet Infect. Dis.14 (8), 742–750. doi:10.1016/S1473-3099(14)70780-7 WHO (2022)Global action plan on antimicrobial resistance. Available at:https:// www.who.int/publications-detail-redirect/9789241509763. Thakral10.3389/frabi.2023.1214826 Frontiers inAntibioticsfrontiersin.org12 187 Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : Aadhaar, en Inde/Desafios eticos de las tecnologias digitales para la salud: Aadhaar, India. Authors: Vijayaprasad Gopichandran, Parasuraman Ganeshkumar, Sambit Dash and Aarthy Ramasamy Date: Apr. 2020 From: Bulletin of the World Health Organization(Vol. 98, Issue 4) Publisher: World Health Organization Document Type: Article Length: 2,855 words Lexile Measure: 1650L DOI: http://dx.doi.org.ezproxy.uio.no/10.2471/BLT.19.237123 Abstract: Problem The proliferation of information and communication technologies in India has enabled the emergence of health-related digital applications, from which important ethical issues arise. Approach The Aadhaar identification system provides each resident in India with a 12-digit unique identification number, linked to demographic and biometric data. Identification by Aadhaar in welfare programmes has the important advantage of ensuring targeted benefits reach the intended recipients. Local setting Some of the major issues faced by the public health sector in India are inadequate funding and inefficient utilization of the funds allocated. The enhancement of currently available digital health records will greatly increase the efficiency of the health care services. Relevant changes The Aadhaar identification system has been linked to several health programmes since 2013. Success was achieved in a programme encouraging pregnant women to undergo delivery at a health facility, as use of Aadhaar number ensured that cash incentives reached the correct recipient. However, interruptions in the treatment of patients with tuberculosis and acquired immunodeficiency syndrome have been reported in other health programmes, due to patients fearing a breach of their confidentiality. Lessons learnt Although the proposed merging of the Aadhaar identification system with digital health care records could enable greater efficiency in monitoring public health and welfare programmes, important ethical issues of privacy and data ownership and use must be considered. In joining the digital revolution, low- and middle-income countries must also develop strict legal regulation to protect data and avoid information technology companies exploiting such databases for profit. Probleme La proliferation des technologies de l'information et de la communication en Inde a favorise l'emergence d'applications numeriques liees a la sante, soulevant des questions ethiques. 06/01/2025, 11:53Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=3558d2...1/6 188 Approche Le systeme d'identification Aadhaar fournit a chaque personne residant en Inde un numero d'identification unique a 12 chiffres relie aux donnees demographiques et biometriques. L'identification par Aadhaar dans le cadre de programmes de protection sociale represente un avantage decisif : elle permet de s'assurer que les allocations ciblees sont effectivement attributes aux beneficiaires adequats. Environnement local Le secteur de la sante publique en Inde rencontre plusieurs problemes majeurs, dont un financement insuffisant et une utilisation inefficace des fonds alloues. L'optimisation des dossiers medicaux numeriques actuellement disponibles va considerablement ameliorer les performances des services de soins de sante. Changements significatifs Le systeme d'identification Aadhaar a ete couple a de nombreux programmes de sante depuis 2013. Grace a lui, un programme visant a encourager les femmes enceintes a accoucher dans un etablissement medical a ete couronne de succes: l'utilisation du numero Aadhaar a servi a verifier que les primes d'incitation en especes etaient versees aux bons beneficiaires. Cependant, des interruptions de traitement chez des patients souffrant de tuberculose et du syndrome d'immunodeficience acquise ont ete observees dans d'autres programmes de sante; les patients craignaient une violation de la confidentialite. Lecons tirees Meme si la proposition de fusion entre le systeme d'identification Aadhaar et les dossiers medicaux numeriques pourrait accroitre l'efficacite de la surveillance exercee sur les programmes de sante et de protection sociale, d'importants enjeux ethiques doivent etre pris en compte en matiere de confidentialite, mais aussi de propriety et d'utilisation des donnees. S'ils souhaitent operer une revolution numerique, les pays a faible et moyen revenu doivent egalement adopter des dispositions legates strides afin de proteger les donnees et d'eviter que des entreprises actives dans le sedeur des technologies de l'information n'exploitentde telles bases de donnees a des fins lucratives. Situacion La proliferacion de las tecnologias de la informacion y la comunicacion en la India ha permitido el desarrollo de aplicaciones digitales relacionadas con la salud, de las que se derivan importantes cuestiones eticas. Enfoque El sistema de identificacion de Aadhaar proporciona a cada residente en la India un numero de identificacion unico de 12 digitos, vinculado a datos demograficos y biometricos. La identificacion de Aadhaar en los programas de bienestar social tiene la importante ventaja de garantizar que las prestaciones especificas lleguen a los destinatarios previstos. Marco regional Algunos de los principales problemas a los que se enfrenta el sector de la salud publica en la India son la financiacion inadecuada y la utilizacion ineficiente de los fondos asignados. La mejora de los registros digitales de salud disponibles actualmente aumentara en gran medida la eficiencia de los servicios de atencion sanitaria. Cambios importantes El sistema de identificacion de Aadhaar se ha vinculado a varios programas sanitarios desde 2013. Se logro el exito en un programa que alentaba a las mujeres embarazadas a dar a luz en un centro sanitario, ya que el uso del numero de Aadhaar garantizaba que los incentivos en efectivo llegaran al destinatario correcto. Sin embargo, en otros programas sanitarios se ha informado de interrupciones en el tratamiento de pacientes con tuberculosis y sindrome de inmunodeficiencia adquirida, por temor de los pacientes a que se vulnere su confidencialidad. Lecciones aprendidas Aunque la fusion propuesta del sistema de identificacion de Aadhaar con los registros digitales de atencion sanitaria podria permitir una mayor eficacia en la supervision de los programas sanitarios y de bienestar social, deben considerarse importantes cuestiones eticas de privacidad y propiedad y uso de los datos. Al sumarse a la revolucion digital, los paises de ingresos bajos y medios tambien deben elaborar una reglamentacion juridica estricta para proteger los datos y evitar que las empresas de tecnologia de la informacion exploten esas bases de datos con fines de lucro. 06/01/2025, 11:53Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=3558d2...2/6 189 Full Text: Introduction Low- and middle-income countries have experienced a rapid and massive influx of digital and mobile technologies and their applications. This information and communication revolution has brought great benefits for the practice of public health in these countries. Several studies have shown evidence of effective digital applications in health including electronic health records, digital epidemiology and mobile health applications. (1) With these massive strides in digital health, important ethical issues related to the collection, storage, use and dissemination of patients' digital health information arise. The Aadhaar (Hindi, meaning foundation or base) system of India provides each citizen with a unique identification number, linked to demographic and biometric information about the individual. The National Health Mission established the health management information system across various states of the country, where everyone is also provided with a unique health identification number. Linking this unique health identification number with the Aadhaar system has been proposed; merging the digital identification system with digital health care records could enable greater efficiency in investigating public health, conducting relevant research, ensuring the accuracy of health-related information and monitoring welfare programmes. (2) However, the availability of big data in health care, particularly in low- and middle-income countries, introduces unique challenges. We identify and discuss such challenges in this article. Local setting The delivery of health care in India is characterized by a vast public health infrastructure, which is categorized into primary, secondary and tertiary care services, delivered by the government- funded health system and a private health sector. The public health system is funded by tax revenues and state-sponsored health insurance schemes, such as Ayushman Bharat, and the private health system is largely financed out of pocket and, to a small extent, by private health insurance. In recent years, digital health records have penetrated the public as well as private health systems; most public health data are now recorded in digital format. One of the major issues faced by the public health sector in India is inadequate funding and inefficient utilization of the funds allocated. The enhancement of currently available digital health records will greatly increase the efficiency of planning and budgeting for the health care services. Approach Under the Unique Identification Authority of India, established under the Ministry of Electronics and Information Technology of the Government of India, the Aadhaar system provides a 12-digit unique identification number to every Indian resident who chooses to enrol as per the provision of the Aadhaar (Targeted Delivery of Financial and Other Subsidies, Benefits and Services) Act, 2016. (3) The Aadhaar identification system records demographic data such as name, address, date of birth and sex, but also biometric data including ten fingerprints, two iris scans and a facial photograph. (4) Identification by Aadhaar number yields several important advantages in development and welfare programmes in the country. Targeted interventions, such as subsidies, cash benefits and incentives provided by the state can reach the intended beneficiaries without pilferage or loss. The Aadhaar system has been increasingly linked to bank accounts, income tax accounts, mobile phone numbers, and social welfare programmes, such as disability and elderly pension schemes. Relevant changes Since 2013, Aadhaar has also been linked to several health-related schemes. (2) For example, the Maternal and Child Tracking System is an electronic database that records information about pregnant women in India, including details of antenatal care, delivery and child-related data up to 06/01/2025, 11:53Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=3558d2...3/6 190 immunization. A conditional cash transfer programme (Janani Suraksha Yojna) encourages women to undergo delivery in a health facility by providing a direct benefit transfer; combining this cash transfer programme with the Aadhar identification system ensures that the correct person receives the benefit. Other national health programmes, such as the Revised National Tuberculosis Control Program and the National AIDS Control Program, have recently started linking their databases with Aadhaar. (2) The intended benefit of linking the patient databases to the Aadhaar number is to track the treatment of patients and ensure that any interruptions to treatment schedules or non- compliance is identified and acted upon. However, interruptions in the treatment of patients with tuberculosis were reported due to pressures to link their treatment registration numbers with their Aadhaar identification number. (5) There have also been several reports of HIV-positive patients and patients with AIDS who were undergoing antiretroviral therapy but, fearing a breach of their privacy by allowing their Aadhaar number to be included in the AIDS treatment programme documents, they preferred to drop out of the treatment programme. (6) Lessons learnt The summary of main lessons learnt is presented in Box 1. Linking sensitive private health information with the Aadhaar identification system introduces issues of potential breaches of privacy, data ownership and use, and the autonomy of individuals whose data have become available for analysis. Unlike the United Kingdom of Great Britain and Northern Ireland and the United States of America, who have strong data ownership and protection laws, India has the evolving Electronic Health Record Standards of 2016, which does not have the force of law. Data are owned by the state in a sense of stewardship in the United Kingdom and by the individual in the USA. The Indian Electronic Health Record Standards stipulate that data are owned by individuals, but the state is the custodian of these data. This provision implies that any use of electronic health records requires the authorization of the individual. The exceptions to this rule are situations of emergency and epidemics, in which case the state can collect information without permission. Where data are shared without consent, this is only in a completely anonymized form. (7) The Aadhaar identification system has been the subject of several litigations in various courts in India. In a ruling in 2013, the Supreme Court of India clearly ruled that registering for an Aadhaar identification number is voluntary and that nobody should be denied benefits and services because they do not have an Aadhaar number. Despite this ruling, several national health programmes continue to enforce Aadhaar registration in subtle ways. For example, although including an individual's Aadhaar number is not compulsory in many public health programmes, some health workers continue to insist on this. If patients refuse, the health worker can delay or even prevent the receipt of benefits. In 2017, the Supreme Court ruled that the Right to Privacy is fundamental. This ruling reignited the various debates on the constitutional position of the Aadhaar system and whether it is an infringement of the privacy of individuals. In 2018, the Supreme Court upheld the constitutional position of Aadhaar, but ruled again that it is not mandatory. (8) However, in the absence of strong regulation of electronic health records in low- and middle-income countries, linking sensitive health information to the Aadhaar system results in the privacy of patients being compromised. Other major ethical concerns regarding the linking of digital health data and Aadhaar identification data are the safety and protection of the combined database. Many low- and middle-income countries do not yet have the required data protection laws; even if such laws are present, implementation can be difficult to monitor. Leaks of the Aadhaar data have been reported; a private telecommunication company in India collected the Aadhaar numbers of many of its subscribers and published them on the internet. Over 200 government websites were also found to be inadvertently displaying Aadhaar data of individuals. (9) Although these websites have been taken down, such data can remain in the digital world indefinitely and continue to compromise the privacy of an individual. 06/01/2025, 11:53Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=3558d2...4/6 191 Linking digital health data with the Aadhaar identification system also facilitates the exploitation of the data for profit. Some technologists who were initially involved in the establishment of the Aadhaar system are now working in private for-profit companies. Although security measures are in place to prevent this conflict of interest, there are several loopholes in these regulations. (10) When such profit-motivated, digitally empowered multinational companies gain access to an identification database in low- and middle-income countries, this disproportionately affects the poor and vulnerable. Effective security systems and strong legislation are required to ensure that private companies do not profit from accessing such databases. In this context, the Ministry of Electronics and Information Technology tabled the Draft Personal Data Protection Bill, 2018. When passed, this bill will set up a national Data Protection Authority to supervise and regulate those who collect data, ensuring the autonomy of individuals. (11) Low- and middle-income countries are joining the digital revolution, making big data available for potential health applications. However, weak health data protection laws and evolving data protection capabilities in these countries leave the population vulnerable to serious ethical consequences, such as breaches in privacy and loss of autonomy. In examining the merging of Aadhaar identification data with digital health data in India, we have demonstrated the need for strong health data protection laws to preserve and protect the fundamental human right: that of privacy. Box 1. Summary of main lessons learnt * Use of the Aadhaar identification number in health programmes in India has met with mixed success due to patients' fears of loss of privacy. * The proposed merging of the Aadhaar identification system with other digital health databases in India could enable greater efficiency in monitoring public health, but important ethical issues of data use and protection must be considered. * Low- and middle-income countries must invest in developing strict legal regulations to protect data and avoid its exploitation for profit. [Please note: Some non-Latin characters were omitted from this article.] doi: http://dx.doi.org.ezproxy.uio.no/10.2471/BLT.19.237123 Competing interests: None declared. References (1.) Wyber R, Vaillancourt S, Perry W, Mannava P, Folaranmi T, Celi LA. Big data in global health: improving health in low- and middle-income countries. Bull World Health Organ. 2015 Mar 1;93(3):203-8. doi: http://dx.doi.org.ezproxy.uio.no/10.2471/BLT.14.139022 PMID: 25767300 (2.) Abraham R, Bennett ES, Sen N, Shah NB. State of Aadhaar. Report 2016-17. New Delhi: IDInsight; 2017. Available from: https://stateofaadhaar.in/assets/ downloadZState-of-Aadhaar- Report_2016-2017.pdf [cited 2019 Jan 17]. (3.) What is Aadhar. New Delhi: Unique Identification Authority of India; 2019. Available from: https://uidai.gov.in/your-aadhaar/about-aadhaar.html [cited 2019 Dec 2]. (4.) Ministry of Law and Justice (Legislative Department). The Aadhaar (Targeted Delivery of Financial and Other Subsidies, Benefits and Services) Act. New Delhi: Unique Identification Authority of India; 2016. Available from: https://uidai.gov.in/images/targeted_delivery_of_financial_and_other_subsidies_b enefits_and_services_13072016.pdf [cited 2019 Dec 2]. 06/01/2025, 11:53Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=3558d2...5/6 192 (5.) Rao M. Aadhaar made mandatory for TB patients seeking cash assistance from the government. Scroll.in. 2017 Jun 21. Available from: https://scroll.in/pulse/841250/aadhaar-made- mandatory-for-tb-patients-seeking- treatment [cited 2019 Dec 5]. (6.) Rao M. Why Aadhaar is prompting HIV positive people to drop out of treatment programmes across India. Scroll.in. 2017 Nov 17. Available from: https://scroll.in/pulse/857656/across-india- hiv-positive-people-drop-out-of- treatment-programmes-as-centres-insist-on-aadhaar [cited 2019 December 2]. (7.) Electronic health record (EHR) standards for India. New Delhi: Ministry of Health & Family Welfare; 2016. Available from: https://mohfw.gov.in/basicpage/electronic-health-record-ehr- standards-india-2016 [cited 2019 Dec 2]. (8.) Safi M. Indian court upholds legality of world's largest biometric database. The Guardian. 2018 Sep 26. Available from: https://www.theguardian.com/world/2018/sep/26/indian-court- upholds-legality-of- worlds-largest-biometric-database [cited 2019 Dec 2]. (9.) Press Trust of India. Over 200 govt websites made Aadhaar details public: UIDAI. The Times of India. 2017 Nov 19. Available from: https://timesofindia.indiatimes.com/india/210-govt- websites-made-public-aadhaar- details-uidai/articleshow/61711303.cms [cited 2019 Aug 22]. (10.) Thaker A. The new oil: Aadhaar's mixing of public risk and private profit. The Caravan. 2018 May 1. Available from: https://caravanmagazine.in/reportage/aadhaar-mixing-public-risk-private- profit [cited 2019 Dec 2]. (11.) The Personal Data Protection Bill. New Delhi: Ministry of Electronics and Information Technology; 2018. Available from: https://meity.gov.in/writereaddata/files/Personal_Data_Protection_Bill,2018.pdf [cited 2019 Dec 2]. Vijayaprasad Gopichandran, (a) Parasuraman Ganeshkumar, (b) Sambit Dash (c) & Aarthy Ramasamy (d) (a) Employees State Insurance Corporation Medical College and Post Graduate Institute of Medical Sciences and Research, Chennai, India. (b) Indian Council of Medical Research, National Institute of Epidemiology, Chennai, India. (c) Department of Biochemistry, Melaka-Manipal Medical College, Manipal Academy of Higher Education, Karnataka, India. (d) Madras Diabetes Research Foundation, No. 4, Conran Smith Road, Gopalapuram, Chennai, 600086, India. Correspondence to Aarthy Ramasamy (email: aarthu28@gmail.com). (Submitted: 14 May 2019--Revised version received: 30 September 2019--Accepted: 4 November 2019--Published online: 17 January 2019) Copyright: COPYRIGHT 2020 World Health Organization http://www.who.int.ezproxy.uio.no/bulletin/en/index.html Source Citation (MLA 9th Edition) Gopichandran, Vijayaprasad, et al. "Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : Aadhaar, en Inde/Desafios eticos de las tecnologias digitales para la salud: Aadhaar, India." Bulletin of the World Health Organization, vol. 98, no. 4, Apr. 2020, pp. 277+. Gale Academic OneFile, dx.doi.org.ezproxy.uio.no/10.2471/BLT.19.237123. Accessed 6 Jan. 2025. Gale Document Number: GALE|A625155840 06/01/2025, 11:53Ethical challenges of digital health technologies: Aadhaar, India/Les defis ethiques des technologies numeriques de la sante : ... https://go-gale-com.ezproxy.uio.no/ps/retrieve.do?tabID=T002&resultListType=RESULT_LIST&searchResultsType=SingleTab&retrievalId=3558d2...6/6 193 SPECIAL ARTICLE january 4, 2020 vol lV no 1 EPW Economic & Political Weekly 46 Where Is All Our Health Data Going? Sundeep Sahay, Arunima Mukherjee Sundeep Sahay and Arunima Mukherjee (arunimam@gmail.com) are at the University of Oslo, Norway and Society for Health Information Systems Programmes, India. Multiple initiatives going on in India regarding the collection of digital personal health data are analysed, and the question of how the data is being used is examined. While such data could facilitate healthcare and referral services, a strong and sensitive governance structure is needed to be in place to enable its optimal use and to ensure that the data is not used to further the agendas of surveillance and control. C ontemporary times are characterised by discourses around “big data” and how these can be mined to extract value. The rapid proliferation of new informa- tion and communication technologies (ICT s) are making it pos- sible to collect, store, combine, and share large volumes of data at almost real time levels of speed. We are at an early stage of this “data revolution” and as citizens whose personal data is at stake, it becomes important to understand how this data is collected, by whom, for what purpose, and its implica- tions. As Zuboff’s (2014) digital declaration states: When it comes to “big data” and the digital future, we are at the very beginning. Despite the rapid race of connection and the oceans of data it generates our societies have yet to determine how all this will be used, to what purpose, and who decides. Zuboff (2018) calls data the “new oil” that is fundamentally transforming the economy and how companies interact with citizens, making them the means to further economic inter- ests. While Zuboff’s critique focuses primarily on large western corporations like Amazon and Google, the role of data in public sector settings of the state in low- and middle-income countries (LMIC s) like India is not analysed. Our analytical focus is on the use of personal data for public health settings in India. This increased focus on personal data is justifi ed by the argu- ment that it will help meet the challenges of poor health indi- cators, an endemic challenge. The question of interest then is what kind and volumes of health data are collected, and what remains its purpose. This article primarily focuses on the question of what data is collected, while arguing for the impor- tance of understanding how it is used to improve conditions of health and well-being in India. Increasing Health Data, But for What? Modern health systems are increasingly dependent on good quality health data enabled through ICT s. Decisions on what data is collected, what information is generated from it, who has access to it, and for what purpose has huge implications for health outcomes and health rights. The choice of tech- nology affects how data is collected, analysed, displayed, and to whom and how access is regulated. While ministries of health are primary users of data, there are increasingly major corporate interests involved in the development and management of data systems, for example, in the health insurance sector. A health-rights perspective will view data systems as ena- bling the rights to access and verifi cation of information by civil society, to enhance state accountability and to enable democratic decision-making and citizen engagement. At stake 194 SPECIAL ARTICLE Economic & Political Weekly EPW january 4, 2020 vol lV no 1 47 are issues of privacy, confi dentiality and data security, and how individual rights are challenged by the powers of an intrusive state or by market manipulations. Yet another major concern is how the use of data systems shapes the organisation of health services, and the relationships between providers and patients; this raises the question of whether the state con- tinues to be the primary provider of health services to citizens, or acts only as a broker in the health marketplace. The last decade has seen an explosive growth of the use of data and data systems in the Indian public health sector. But unlike sectors like banking and transport, the benefi ts of data systems are unclear, particularly to the citizens whose data it is. The initiative of strengthening health data systems as a key component of health sector reform was introduced in the 1990 s, however, it is so beset with problems that it is in need of major reforms itself. This study gives an overview of data-re- lated issues under the National Rural Health Mission (NRHM) starting 2008, and then traces current trends in gathering health data in both the public and non-public sectors. The aim is to understand from the perspective of citizens what data related to them is at stake, and how can they engage with it in safeguarding their interests and rights. The Backdrop While national health information systems (HIS) were intro- duced in India in the mid-1980 s and 1990s, driven largely through the World Bank structural adjustment programmes, this article traces the story from 2008 soon after the NRHM was established in 2006. The NRHM’ s agenda was to bolster national public health systems including the health management infor- mation systems (HMIS) through architectural corrections of integration, rationalisation, and strengthening data use to improve health services delivery. The reform process was conceptu alised in three stages. (i) Phase 1 of situation assessment where HMIS data f rom t hree states were systematically examined showing, not unsurpris- ingly, a large amount of data (more than 3,000 elements) being gathered by each health facility, and less than 5% of it used to generate health indicators. (ii) Phase 2 was of system redesign based on the application of the following practical design principles: (a) No data should be collected more than once. For example, data on childhood tuberculosis was collected under HMIS, Inte grated Disease Surveillance Programme (IDSP), and Expan- ded Programme for Immunization (EPI), with clear duplication and adverse impacts on data quality and its use. (b) Only pertinent data that can generate relevant programme i nd ic ator s shou ld be col lec ted. For e x a mple, pr ior to 2008, eac h data element was segregated by caste (Scheduled Castes [SC], Scheduled Tribes [ST] and others), used primarily to safeguard against potential questions in Parliament on issues of equity rather than to improve care. (c) Data fl ows should be governed by a hierarchy of standards, where the lowest level (health clinics) retains the most granular data (for example, names and addresses of pregnant women), while higher levels should receive increasingly aggregated data (for example, data to analyse the percentage of children immunised). (d) Data refl ecting something relatively stable (for example, population estimates of SC and ST groups) should be captured through annual surveys, rather than through routine monthly data, to reduce the data collection load. (iii) Phase 3 was the implementation of the newly designed data collection formats (including 90% reduction in the data to be collected). The states received advice in the form of a letter from G C Chaturvedi, a visionary mission director, quoted below: The Ministry of Health and Family Welfare has been taking steps to establish such a system for national level monitoring and also to help the States in building effective HMIS at the State, district and lower levels ... The department has developed a web based data entry por- tal (http:/nrhm-mis.nic.in) which could provide analysis of data on some specifi c indicators, once the data is entered at the District level ... NHSRC (National Health Systems Resource Centre) has an open source software also capable of handling local level information needs including data entry and analysis ... It is also available to States from NHSRC for free. States willing to make use of it for Blocks/Facilities may avail the services of NHSRC for implementing it. The HMIS formats to be used in this software are compatible with the Ministry’s format. The software has the provision to electronically post the data from the Blocks/Facilities, compiled through it at the district level, directly to the national HMIS portal. (Chatur vedi 2009) This letter touched upon various facets of the centrali sation– decentralisation debate: (i) the centre should only receive data required to generate specifi c indicators (not all data collected); (ii) the centre should only receive aggregate district informa- tion; (iii) the use of free and open source software was encour- aged; (iv) states should have the freedom to use software to collect subdistrict data; and (v) interoper ability mechanisms are needed to enable state specifi c software to report data to the national database. This letter emphasised that health is primarily a state subject, and the centre should only request data to prov ide polic y directions, while states should be f ree to use the software of their choice to report required data. Unfortunately, this policy direction did not last long, for three key reasons. First, the central ministry positioned the national web portal as a “single window of truth” requiring all data to come there, ignoring the multiplicity of systems already existing in states. Second, this portal was designed to “prevent rather than promote interoperability” (for example, by not providing application programming interface [API] access), implying that state systems could not electronically share data with the national web portal. The message implied to states was that they could not use systems other than the national web portal. This lack of interoperability continues till today despite the advancements in technology, and government policy statements that mandate open software and access. The third reason was signifi cant and path-breaking as Ghulam Nabi Azad, the then health minister, said he did not trust reported numbers on immunisation, and data quality would only improve when names were submitted. He is quoted as saying: At present, the chief medical offi cer compiles the vaccine coverage data on the basis of what states tell him, without going into the fi eld. So, we are not sure if the data is actually true. As a pilot project, we are 195 SPECIAL ARTICLE january 4, 2020 vol lV no 1 EPW Economic & Political Weekly 48 starting name-based vaccination with polio which is confi ned to just a few states. Once we have such data, we can simply call up a child’s family and check whether he was actually administered the vaccine or not. (Sinha 2009) This led to the birth of the megalomaniacal system, Mother and Child Tracking System (MCTS), which coll ected the names and details of every woman in the country registered for a pregnancy (about 22 crore annually) and similar numbers of children for immunisation. By design, the system planned to send all data collected to the national portal, despite only fi eld health staff requiring detailed patient data to provide care. Clearly, it was a system based on the logic of strengthening surveillance (of the hapless health workers) rather than on im- proving care. This MCTS ran in parallel to the HMIS (cont raven- ing the principle of “no data should be colle cted more than once”), thus doubling data collection load and making health workers accountable for mismatches between the HMIS and MCTS data. As the entire focus of the government machinery shifted to promoting MCTS, the HMIS was signifi cantly under- mined. Data collected through the MCTS was outsourced to companies to call and follow up with the benefi ciary or health workers to “authenticate” the data reported. There are various other issues regarding the MCTS, including those relating to cost benefi ts, ethics and legality of using personal data, and providing it to third-party vendors. These are larger topics to address that this study fl ags for further discussions. Along with the MCTS, there was the explosion of other data collection systems. Various state-specifi c portals came up to meet the needs of states and donors. At national level also, new systems were introduced (such as the ASHA portal), signifi cantly adding to the data load. Simultaneously, the central ministry moved relentlessly to get more decentralised data down to the individual level, in contravention to the 2008 circular requir- ing only district-level data. Today, about 3,00,000 facilities are reporting data monthly to the national web portal adding about one terabyte of data annually. The data collection load, primarily on the fi eld-level health workers, is exponentially growing and is given minimal consideration in the design of new systems. S Sahay, P Nielsen, and M Latifov (2018) found that the auxi liary nurse midwives (ANM s) need to send (often overlapping) data to nearly 10 different systems and manage their data with 25+ primary registers (each about a metre long), resulting in increased administrative workload. The Existing Situation, 10 Years On Given this brief overview, it is pertinent to assess the volume of data and its use. It is, of course, determined by various factors (for example, governance, politics, infrastructure, capacity, etc [Rao 2017]), but is beyond the scope of discussion here. Data load is constituted by aggregate facility-based and name- or case-based data systems. On an average, states report about 550 data elements through the national HMIS, and addi- tionally have local data sets ranging from 2,500 to 650 data elements. Many data elements are inactive (no values reported). Inactive elements ranged from about 100 to even 2,500+ in different states. There are also programme-specifi c data (mix of aggregate and case-based) for malaria, leprosy, blind- ness control, tuberculosis, and other diseases. Some states like Maharashtra, Odisha, and Uttar Pradesh (UP) have opted to build an integrated state data warehouse to store all their state-specifi c data to enable more integrated analysis. In most other states, these local data are collected in multiple systems, typically on paper or MS Excel fi les, with limited interoperability mechanisms. There are other data sets that this article does not analyse, such as for infrastructure, fi nance, human resour ces, and household surveys. Case-based Data Case-based data refers to individual-level data collected off a patient, including details of their demographics, programme- specifi c parameters, such as haemoglobin for ANC, and CD4 counts for HIV patients. The idea is for data to be captured lon- gitudinally to improve point of care and strengthen referral linkages. This individual data is fi rst compiled in fi eld diaries, then transferred to primary registers, and then reports are compiled on paper, which are sent to the nearest computer location for data entry and reporting to the higher levels. In the past, monthly reports represented aggregates of the case- based data recorded in primary registers, but now, systems like MCTS require the entire patient record from the primary reg- ister to be entered in the computer and transmitted to state- and national-level servers. In most instances, the case-based data does not replace the aggregate reports (even though it is technically possible) and both continue in parallel, resulting in a mbig uit y on whic h data is t he “ t r ut h.” Ver y lit t le feedbac k comes to the fi eldworkers, who are left to wonder about the value and use of their reports. A summary of some programme-specifi c data is given in Table 1. The existing systems are rampant with redundancies and also with important gaps. The health worker faces the brunt of reporting to multiple systems, with limited support and feedback. There is almost no data being made public to citizens. How Is the Data Being Used? Data is collected for different purposes, primarily to serve the bureaucratic function of monthly reporting to higher levels. Missing or “wrong” reports are subject to severe reprimand. More diffi cult to infer is how different functionaries use data to inform action to imp rove health services delivery and health outcomes. This can be inferred through proxies, such as: (i) the number of active data elements implying what they are reported upon; (ii) the number of data elements that are Table 1: Data Elements Collected under Various Programmes Name of Programme Total Data Number Total Data Fields of Cases Fields Per Record Per Month Per Month National Programme for Prevention and Control of Cancers, Diabetes, Cardiovascular Diseases and Stroke 165 270 5,121 Maternal health 143 125 3,849 Eligible couple 91 95 980 Child health 61 250 4,437 Tub erculosis 59 12 227 Source: Compiled by the authors. 196 SPECIAL ARTICLE Economic & Political Weekly EPW january 4, 2020 vol lV no 1 49 systematically reported as zero or left blank; and (iii) the number of data elements used to generate indicators. While the fi rst proxy is indicative of elements currently relevant, the second one refl ects if a health facility is actually providing a particular service. For example, if health facilities are systematically reporting the “number of low birth weight babies” as zero, then it could indicate that there are no low birth weight babies (which is highly unlikely), or that the weighing machines are unavailable, forcing staff to fi ll in “zeroes.” The third proxy refl ects the principle of data for action, which assumes that if the data is converted to an indicator (in reference to a population denominator), it potentially becomes actionable. Whether this actionability potential is realised in practice is another matter, often subject to issues of political will, policy, governance, budgets, capacity, and infrastructure. Another challenge to actionability relates to our focus on numerator- only data, which creates challenges in “comparing to what?” Fredrick Mosteller (2010) illustrated this problem with a joke: Why do the white horses eat more than the black horses? Do not know. Why? Because we have ten times as many white horses and black horses. In public health data, denominators are crucial as all indica- tors are calculated with respect to a target population, such as the percentage of newborn babies immunised. In the absence of this denominator (“number of newborn babies for a period in a particular catchment area”), no meaningful intervention can be designed. In India, denominator fi gures are notoriously ambiguous, with the health and revenue departments having different fi gures and variations across health programmes and administrative levels. Private-sector data, which represents the bulk of healthcare services-provided in the country, is literally non-existent. The data collection load for aggregate data (spanning national HMIS and state specifi c data) in a state varies between 3,000 and 8,000 elements per month. The number of inactive elements tend to be about 20%, while about 50% of the elements are reported as zero or blank on a systematic basis. Furthermore, less than 10% of the data elements reported are used to generate indicators. Overall, this shows that we collect far more data than what is reported on, and an even smaller percentage is actually used for indicators (Table 2). With respect to case-based data, Table 3 summarises all the data fi elds required every month from a peripheral provider (separate from HMIS aggre- gate data). There are excep- tions such as programmes for malaria and leprosy that collect both aggregate and case-based data, as summa- rised in Table 4. They gen- erate a healthy number of indicators, refl ecting potentially an active use of data. To summarise, the HMIS refl ects a high degree of redundancy, with little systematic actual use of data, raising the question of “why is this data being collected?” Is this exercise only to satisfy bureaucratic requirements and to enhance the monitor- ing capacity of the ministry to “see like a state” (Scott 1997). But, the irony is that the state can drown in the sheer volume of data, especially when they receive all subdistrict data with- out abstraction. This, coupled with inadequate analytical and action taking capabilities at the centre, undermines even the bureaucratic function of reporting and contributes to data playing primarily a symbolic and legitimising function (Noir and Walsham 2007). Further, with data quality functions largely centralised, the principle of “data quality corrections are best done closest to the source of data collection” is violated. A large volume of data of suspect quality does not lend itself to effective use while magnifying the workload of fi eld staff, who estimate that 60% of their time is spent on data related work. These are some endu ring data related problems: (i) The steady and huge increase in data collection seriously com- promises the time health workers can spend on care provision. (ii) Despite this huge data collection, there is little reliable actionable information for use at the district level, with limited feedback to data providers other than reprimand. (iii) There is no provision for communities and public repre- sentatives to access data relevant to their participation. (iv) Introduction of case-based reporting has exacerbated problems of data overload and data entry, as this process adds and does not replace existing aggregate data fl ows. The work- fl ow around case-based data is complex, often requiring the movement of cumbersome primary registers to distant offi ces where the computer is located. (v) Case-based data is collected without adequate privacy standards and data regulation frameworks, making it vulner- able to intrusive interventions, such as phone calls from call centres to households (or even their neighbours) to verify a pregnancy. (vi) There are multiple systems functioning with little to no interoperability, each working as an independent silo. Very recently, meta data and data standards (MDDS) were notifi ed but the guidance on implementation is weak. Most applica- tions, like the current HMIS, are expensive, proprietary and Table 2: Data Collected vs Data Used and Analysed Total Elements Percentage Total State Percentage (Some) National HMIS Report- State Specific National Programmes Data ing Specific Data Programmes Data Elements Zeroes Data Elements Data Elements Elements Reporting Elements Reporting Zeroes Zeroes State A 550 273 50 2,536 2,400 95 580 490 State B 550 120 22 1,117 658 59 2,312 16 State C 550 300 55 661 530 80 – – State D 550 350 64 697 200 29 – – Source: HMIS portal. Table 4: Aggregate and Case-based Data Elements Collected Programme Aggregate Case-based Indicators Data Data Elements Elements Malaria 660 178 134 Leprosy 29 168 55 Source: HMIS portal. Table 3: Total Data Fields for Case-based Data Required Every Month Name of Programme Total Data Number Total Data Fields of Cases Fields Per Record Per Month Per Month National Programme for Prevention and Control of Cancers, Diabetes, Cardiovascular Diseases and Stroke 165 270 5,121 Maternal health 143 125 3,849 Eligible couple 91 95 980 Child health 61 250 4,437 Tub erculosis 59 12 227 Source: HMIS portal. 197 SPECIAL ARTICLE january 4, 2020 vol lV no 1 EPW Economic & Political Weekly 50 rigid, and unable to change with changing needs and priorities leading to their early obsolescence. (vii) The large investment in information technology (IT) in healthcare is not matched by outcomes. But despite this, there are little efforts at systematic evaluation and learning from past failures, and similar problems repeat in cycles. (viii) Denominator data continues to be ambiguous or unavail- able, leading to poor action taking potential of the numerator data being collected. (ix) There is no data policy in place with regard to storage, length of time of storage, rights of access, and to ensure privacy. (x) There is a repeated push for centralised electronic health records (EHR s), which is neither feasible nor desirable at a national scale. The standards being mandated (for example, Systematized Nomenclature of Medicine or SNOMED) are pro- prietary and Unites States-based, and have adverse imp lications for long-term and sustainable development of the architecture. (xi) There is a push to develop gigantic systems at the national level, which will incorporate or render redundant all existing systems. Fortunately, while most do not take off, they tend to undermine existing systems in the process. (xii) There are repeated pressures to create a single source of “truth” and outlaw other data and systems. While the acco- mpanying rhetoric is to prevent redundancies, in practice this only adds to the problems and keeps data not transparent to the public. (xiii) A fair number of population-based morbidity and mortality surveys are in use, which are welcome, but only some of the results are in the public domain. Discerning Learnings from the NRHM Experience The NRHM efforts to reform HMIS were only partially success- ful. A discussion on some broader design-related lear nings extracted from this experience follows. (i) Design systems to support the logic of care and not control: Monitoring systems are designed with the aim to control and discipline the performance of individual providers at the periph- eral levels who, from fear of visibility, will tend to self-discipline anyway. The MCTS was a classic example of such a system. (ii) Build governmental procurement systems that encourage the use of free and open source software systems: Governmental systems of procurement typically discriminate against free and open source software, and fail to develop contracts that enable the provision of dynamic and continuous support required to deal with the evolving informational needs. Pro- curement is infl uenced by large IT companies, whose market- ing skills combined with a limited understanding of the health domain lead to inappropriate contracts and vendor lock-ins. (iii) Build systems based on participatory design and a serious commitment to decentralise: Systems catering to what top man- a gers think they need fail to factor in the requirements of providers who collect and enter the data to strengthen care pro- cesses. Quite often, IT reinforces bureaucratic control structures of power, and constrains rather than enables decentralisation. While this discussion has focused primarily on data managed by the state, it is important also to understand data collected by non-state actors like the private sector and international organisations. In India, this arguably is larger than public data. However, almost no published literature discusses this. In its absence, we use proxies to understand this data volume. Health Data with Non-state Actors Whether as a function of access, preference or economics, non-state actors play a critical role in the provision of health-care delivery in low- and middle-income countries. (McCoy and Brikci 2010) The collection and utilisation of health data is an integral aspect of the work of non-state actors, comprising national and international non-governmental organisations (NGO s), civil society organisations, philanthropic and commercial entities, individual medical practitioners, and pharmacies. They provide services in hospitals, nursing and maternity homes, clinics run by doctors, nurses, midwives and paramedical workers, diagnostic facilities, for example, laboratories and pharmacies (Mills et al 2002). There thus is great diversity in healthcare providers, including various non-state actors spanning non-residential and residential care, including hospitals, nursing homes, facil- ities for the elderly, rest homes for the mentally challenged, and those suffering from substance abuse (Kumar 2015). In India, 50% of all hospital beds are in the private sector. The National Sample Survey Offi ce (NSSo) of 2010–11 estimated about 10.4 lakh private healthcare enterprises to be active. This compares with 20% of private sector beds in Latin America, 30% in Asia and more than 34% in Africa (Hanson and Berman 1998). While this trend refl ects efforts to optimise the use of non-state capacity, countries like Bangladesh have progressed slowly (M OHFW 2005), constrained by poor data availability. Building public–private partnerships has been an important strategy to expand healthcare provision capacity; for example, the Chiranjeevi Yojana in India demonstrated an increase in the institutional birth rate from 40.7% (2001) to 89.3% (2010), driven by sharp increases in private sector deliveries (Singh et al 2009). In India, around independence, the public sector was the dominant provider of healthcare services, with the private healthcare sector accounting for only 8% of total patient care (Peters et al 2002). This situation has now dramat- ically changed, and it is estimated that 93% of all hospitals, 64% of beds, 80%–85% of doctors, and 80% of outpatient and 57% of inpatient services are catered to by the pri- vate sector (Tiwari and Nair 2006). The NSSo 2014 estimated that 72% rural and 79% urban spells of ailment were Table 5: Contributions of Public and Private Healthcare Sector in Terms of Service Utilisation, Expenditure, Insurance Coverage and Infrastructure Contributions Public Sector Private Sector Inpatient Outpatient Inpatient Outpatient Services (%) 1986–87 60 22.5 40 77.5 1995–96 43.5 19.5 56.5 80.5 2004–05 40 20.5 60 79.5 2014 (rural) 41.9 28.9 58.1 71.1 2014 (urban) 32 21.2 68 78.8 Contributions Rural Urban Rural Urban Distribution of hospitalised cases (%) 19 95–9 6 4 4 43 56 57 2004–05 42 38 58 62 2014 42 32 58 68 Cost of per hospitalisation case ( `) 1986–87 1,120 1,348 2,566 4,221 1995–96 3,307 3,490 5,091 6,234 2004–05 3,238 3,877 7,408 11,553 2014 5,636 7,670 21,726 32,375 Source: Sembiah et al (2018). 198 SPECIAL ARTICLE Economic & Political Weekly EPW january 4, 2020 vol lV no 1 51 treated in the private sector. The National Family Health Survey (NFHS)-4 report estimated that 56.1% and 49% of members of surveyed urban and rural households respectively, sought private healthcare, while for the public sector, it was only 42% and 46.4% respectively (iips and ICF 2017). Table 5 (p 50) summarises these trends. The estimation of data in the private healthcare sector can be made by the rate of services offered at the facilities. As per the 71st round of the NSSo (2014), the private sector accounted for two-thirds of inpatient and three-fourths of outpatient care treatments nationally. While private sector outpatient care has been nearly constant since 1986–87, inpatient care increased to 68% in urban areas and 58% in rural areas in 2014 from a low of 40% in 1986–87. Table 6 summarises these trends in percentage terms. There is a variation in the distribution of private healthcare enterprises per 1,00,000 people across the states, with the hig hest numbers reported from the relatively high-income states like Delhi and Punjab, follo wed by states like West Bengal and Maharashtra that are higher than the national average. Table 7 summarises this statewide and sector-wide distribution. Using this distribution as a proxy, it can be estimated that 60% of the total volume of health data is generated by non-state actors, which does not fi nd visibility in the national HMIS (Bhattacharya et al 2012). This gap is of concern since the private for-profi t sector represents more than two-thirds of human resources for health, including for maternal and child health services (Raban et al 2009), and in the absence of regulation or incen- tives there is no reporting taking place (Gautham et al 2016). It is arguably erroneously estimated that in 2014 about 75% of the total deliveries reported in national HMIS were from the public sector. 1 UP is the most populous state in India, with one of the high- est maternal mortality rates (258 per 1,00,000 live births) and infant mortality rate (68 per 1,000 live births) in the country (2012–13 data; G oI 2014). The private sector in the state pro- vides nearly 90% of treatment for acute illnesses, 80% for chronic conditions and 18% of institutional deliveries, repre- senting 56.7% of all deliveries in the state. A health facility survey carried out during 2013 in 25 districts of the state re- ported that half of the 731 mapped private facilities providing institutional deliveries did not maintain any relevant records (KHPT and U oM 2013). NGO s play an important role in India, and today, about 31 lakh are active. Multiple other international NGO s are active, supported by donors like the United States Agency for Interna- tional Development. In one of the northern states, an NGO sup- ported by an international donor is collecting health data through a team of about 600 staff, running almost a parallel health information system for the state, and their data is not part of the state repository. Another rich source of health data is collected by medical colleges and research institutes who have designated study areas where they provide healthcare services and run the HIS, but often primarily for research purposes. The Indian Council for Medical Research (ICMR) has 31 institutes spread over the country researching different issues such as communicable diseases, fertility control, maternal and child health. Most of this data is collected in a project mode, and no central repository of this data exists. This is an important opportunity lost for data to be used for informing policy and studying disease trends over time. The ICMR is currently trying to strengthen their digitalisation activities and archive research data nationally. One such example relates to an antimicrobial resistance (AMR) surveillance research network, which includes a software tool to collect AMR data from 25 public and private hospitals and laboratories. There are around 40,000 records entered by two private lab chains in India in the last four to fi ve months. An average volume of around 10,000 records are reported every month, which can become an active tool in the fi ght against AMR. To summarise, huge amounts of health data are collected by the state, and even more by the non-state sector. State systems often focus on surveillance and control, not on care. Despite this huge data collection, there are important gaps, for example, AMR where no data is reported from 800 district hospitals for national surveillance purposes. Collection of Case-based Data The future promises an explosion in the collection of name/ case-based data in India, with limited clarity on how this data would be used. Some planned initiatives are discussed. Table 6: Inpatient and Outpatient Care Treatments by Type of Facilities NSS Rounds Description Inpatient Outpatient Public Private Public Private 42nd 1986–87 Total 60.0 40/0 22.5 77.5 52nd 1995–96 Total 43.5 56.6 19.5 80.5 60th 2004–05 Total 40.0 60.1 20.5 79.5 71st 2014 Rural 41.9 58.1 28.9 71.1 Urban 32.0 68.0 21.2 78.8 Source: Various rounds of NSSO. Table 7: Percentage of Distribution of Hospitalised Treatment across Sectors and States State % Persons Hospitalised Private Hospital Public Hospital Rural Urban Rural Urban Andhra Pradesh 77.5 78.2 22.5 21.8 Assam 10.8 48.5 89.2 51.5 Bihar 57.4 61.2 42.6 38.8 Chhattisgarh 50.6 70.6 49.4 29.4 Gujarat 76.6 76.7 23.4 23.3 Haryana 66.7 81.7 33.3 18.3 Jharkhand 60.4 73.6 39.6 26.4 Karnataka 73.2 81.7 26.8 18.3 Kerala 65.3 66.7 34.7 33.3 Madhya Pradesh 46.5 58.3 53.5 41.7 Maharashtra 80.8 80 19.2 20 Odisha 18.7 42 81.3 58 Punjab 70.7 69.8 29.3 30.2 Rajasthan 45.8 45.6 54.2 54.4 Tamil Nadu 59.6 70.7 4 0.4 29. 3 Telangana 71.4 78.8 28.6 21.2 Uttar Pradesh 69.8 71.7 30.2 28.3 West Bengal 22.8 47.4 77.2 52.6 All 58.1 68.0 41.9 32.0 Source: NSSO 71st round. 199 SPECIAL ARTICLE january 4, 2020 vol lV no 1 EPW Economic & Political Weekly 52 (i) The Integrated Health Information Platform: Planned initially to replace the existing system for IDSP, it is now posi- tioned as a platform to integrate all diseases, such as malaria and tuberculosis, and for one health data from all facility types. In short, Integrated Health Information Platform (IHIP) is positioned a system for everything and everyone, as stated in the website: The primary objective of IHIP is to enable the creation of standards compliant EHR s of the citizens on a pan-India basis along with the integration and interoperability of the EHR s through a comprehen- sive Health Information Exchange (HIE) as part of this centralised accessible platform. With the promise of improved continuity of care, confi dential health records, and better dia gnosis of diseases, the focus is very much on the individual rather than the population. The platform is being developed by two global private providers with expertise in human data science, banking, insurance and fi nancial services, artifi cial intelligence, machine learning, cloud services, identity access, and security. The operationalisation of the platform is delayed, and in the meanwhile, efforts of departments like the National Vector Borne Disease Control Programme (NVBDCP) to develop a malaria surveillance system have been put on hold. (ii) Health and Wellness Centres: The Ministry of Health and Family Welfare proposes to set up 1,50,000 centres as up- graded versions of existing health sub-centres and primary health centres to provide primary, outpatient, and referral care. The late former Finance Minister Arun Jaitley said, will bring health care system closer to the homes of people ... for pro- viding comprehensive health care, including for non-communicable diseases and maternal and child health services ... will also provide free essential drugs and diag nostic services. (Sundararaman 2018) These centres are expected to handle more than 70% of all outpatient care. While nothing much has been written about the supporting HIS, they promise to focus on case-based data to capture the interaction between the patient and the local doctor. Another important issue to consider is the information- al links between the HIS of these wellness centres with other national systems. (iii) The National Health Protection Scheme: This scheme, also called Ayushman Bharat, was launched on 25 September 2018, and is described as being the world’s largest insurance scheme, expected to cover approximately 500 million benefi - ciaries and 1.5 lakh health and wellness centres with coverage of `5 lakh a year per family. The scheme is expected to be cashless and portable across the country, and subsuming earlier schemes like the Rashtriya Swasthya Bima Yojana. The informational requirements to support such a scheme are immense and complex: (i) a functional EMR in every authorised health facility; (ii) a master–patient index with registration details of all citizens in one database; (iii) a family and indi- vidual identifi cation scheme; (iv) interoperability between different systems; and (v) ability to include legacy data from earlier schemes with adequate security mechanisms. Many modern technologies are proposed, such as the cloud, big data analytics, artifi cial intelligence, biometrics and aug- mented reality, 2 but their operationalisation will be complex. (iv) The National Health Stack of the NITI Aayog: NITI Aayog (2018) published the National Health Stack (NHS) as a visionary digital framework usable by centre and state across pub- lic and private sector ... that supports a multitude of health verticals and their disparate branches and is capable of integrating future IT solutions for a sector that is poised for rapid, disruptive changes and unforeseen twists. It is now conceivable to aim for digital health re- cords for all citizens by the year 2022 ... Various layers of the National Health Stack will seamlessly link to support national health electronic registries, a coverage and claims platform, a federated personal health records framework, a national health analytics platform as well as other horizontal components. The Stack’s primary focus is on health insurance with plans to expand across other health programmes, promising analytics on average number of patients treated in a day, commonly occurring diseases, percentage of claims fi led and fraud analysis, average billed amount by medical procedures, and average time of settlement. In addition, there are various other initiatives on patient- level data. For example, states are implementing pilot models for universal health coverage and disease elimination pro- grammes based on case data. The Centre for Development of Advanced Computing is developing personal health record systems, while the National Informatics Centre is rolling out hospital information systems. As citizens, we want to guard against the misuse of our personal data, and limiting its use to improve care services. Conclusions The levels of success starting from the use of HMIS for aggregate data have been limited, and many new complexities emerge for patient-level data. Citizens need to question where all the (individual)-level data is going, who will have access to it, and what they will be doing with it. Existing debates focus on the technology, and the topic of data use is largely margi nalised. Some areas of citizen engagement include the following issues: (i) Data systems should be developed on the guiding principle of reducing fi eld staff’s work burden whilst strengthening care processes. (ii) Data systems must be based on free and open source soft- ware, where the source code remains with the end user with the required capacity. Contracts would allow space for dynamic development of the product with adequate data safeguards. (iii) A policy on health data and its storage, management, and retrieval is required, along with provision for democratic access to data. (iv) The eHR s should typically be maintained at the facility level, and only aggregated data stored in the cloud with supporting guidelines for anonymisation and access. (v) The architecture must be decentralised but accompanied by measures that enable interoperability, incentives to encou rage private sector involvement, and decentralised access to data. (vi) Just as the individual has rights to access their personal data, communities (local, districts, states) would have 200 SPECIAL ARTICLE Economic & Political Weekly EPW january 4, 2020 vol lV no 1 53 rights to access anonymised aggregate data pertaining to their area. (vii) Data collected with public money from large surveys and used for policy purposes must be put up in the public domain for larger access to research. (viii) Data collected through health and biomedical research institutions based on public money should be made available on the public domain. (ix) New initiatives must have clear plans on how they will engage with legacy data systems. (x) Important data gaps, such as on AMR surveillance, need to be identifi ed and plugged in. Without the active engagement of citizens in these areas and more, the answer to the question “Where is all our health data going?” will be as Bob Dylan wrote, “The answer my friend is blowing in the wind.” Notes 1 https://nrhm-mis.nic.in/hmisreports/frm- standard_reports.aspx. 2 https://www.nhp.gov.in. References Bhattacharya, M, R Shahrawat and V Joon (2012): “Understanding Level of Maternal and Child Health Indicators Used in Health Management Information System among Peripheral Level Health Functionaries in Two Districts of India,” Journal of Health Informatics in Developing Countries, Vol 6, pp 385–95. Chaturvedi, G C (2009): “Letter to States,” Do N-20020/2/2008-State (M&E), 9 November. Gautham, M, N Spicer, M Subharwal, S Gupta, A Srivastava, S Bhattacharyya, B I Avan and J Schellenberg (2016): “District Decision-making for Health in Low-income Settings: A Qualita- t ive St udy in Ut tar Pradesh, India, on Engag ing the Private Health Sector in Sharing Health- Related Data,” Health Policy and Planning, Vol 31, No 2, pp ii35–ii46. GoI (2014): “Annual Health Survey Report: A Report on Core and Vital Health Indicators, Part 1,” Offi ce of the Registrar General & Census Commissioner, Ministry of Home Affairs, Gov- ernment of India. Hanson, K and P Berman (1998): “Private Health Care Provision in Developing Countries: A Preliminary Analysis of Levels and Composi- tion,” Health Policy and Planning, Vol 13, No 3, pp 195–211. IIPS and ICF (2017): “National Family Health Survey (NFHS-4),” 2015–16, Mumbai: International Institute for Population Sciences, http://www. rchiips.org/NFHS/NFHS-4Reports/India.pdf. KHPT and UoM (2013): “Facility Mapping in 25 High Priority Districts of Uttar Pradesh: A Presenta- tion Based on the Study,” Karnataka Health Promotion Trust and University of Manitoba. Kumar, S (2015): “Private Sector in Healthcare Delivery Market in India: Structure, Growth and Implications,” http://www.isid.org.in/pdf/ WP1 85.pdf. McCoy, David and Nouria Brikci (2010): “Taskforce on Innovative International Financing for Health Systems,” Bulletin of the World Health Organi- zation, Vol 88, pp 478–80. Mills, A, R Brugha, K Hanson and B McPake (2002): “What Can Be Done about the Private Health Sector in Low-income Countries?” Bulletin of the World Health Organization, Vol 80, No 4, pp 325–30. MoHFW (2005): “Chiranjeevi Yojana an Innovative Partnership with the Private Sector Obstetri- cians to Provide Skilled Care at Birth to the Poor in Gujarat,” Ministry of Health and Family Welfare, https://www.nhp.gov.in/sites/default/ fi les/pdf/chiranjeevi-yojana-details.pdf. Mosteller, F (2010): The Pleasures of Statistics: The Autobiography of Fredrick Mosteller, Stephen E Fienberg, David C Hoaglin and Judith M Tanur (eds), Springer. NITI Aayog (2018): “National Health Stack: Strategy and Approach,” Government of India. Noir, C and G Walsham (2007): “The Great Legiti- mizer: ICT as Myth and Ceremony in the Indi- an Healthcare Sector,” Information Technology and People, Vol 20, No 4, pp 313–33. Peters, David H, A Yazbeck, G Ramana, R Sharma, L Pritchett and A Wagstaff (2002): “Better Health Systems for India’s Poor: Findings, Analysis, and Options,” World Bank Group, Washington, DC. Raban, M, R Dandona and L Dandona (2009): “Essential Health Information Available for India in the Public Domain on the Internet,” BMC Public Health, Vol 9. Rao, S K (2017): Do We Really Care? India’s Health System, New Delhi: Oxford University Press. Sahay, S, P Nielsen and M Latifov (2018): “Grand Challenges of Public Health: How Can Health Information Systems Support Facing Them?” Health Policy and Technology, Vol 7, No 1, pp 81–87. Scott, J (1997): Seeing Like a State: How Certain Schemes to Improve the Human Condition Have Failed, Yale University Press. Sembiah, S, B Paul, A Dasgupta and L Bandyopad- hyay (2018): “Capacity Building of Private Sec- tor Workforce for Public Health Services in India: Scope and Challenges,” Indian Journal of Community Medicine, Vol 43, No 3, pp 144–47. Singh, A, D V Mavalankar, R Bhat, A Desai and S R Patel (2009): “Providing Skilled Birth Attendants and Emergency Obstetric Care to the Poor through Partnership with Private Sector Obstetricians in Gujarat, India,” Bulletin of the World Health Organization, Vol 87, pp 960–64, https://nrhm-mis.nic.in/ hmisre- ports/frmstandard_reports.aspx. Sinha, K (2009): “Azad Doubts Data on Child Vaccination,” Times of India, 15 September, http://timesofi ndia.indiatimes.com/articleshow/ - 5011257.cms?from=mdr&utm_source= con te- ntofi nterest&utm_medium=text&utm_cam- paign=cppst. Su ndararaman, T (2018): “In New Health and Well- ness Centres, India Has a Good Plan for Primary Care—Backed by Little Action,” Scroll.in, https:// scroll.in/pulse/870405/in-new-health-and-well- ness-centres-india-has-a-good-plan-for-primary- care-backed-by-little-action. Taskforce on Innovative International Financing for Health Systems (2009): More Money for Health, and More Health for the Money, World Health Organization. Tiwari, V K and K S Nair (2006): “Private Health Care in India,” Health Millions, Vol 32, pp 36–45. Zuboff, S (2014): “A Digital Declaration,” http:// www.faz.net/aktuell/feuilleton/debatten/the- digital-debate/shoshan-zuboff-on-big-data-as- surveillance-capitalism-13152525.html. — (2018): The Age of Surveillance Capitalism: The Fight for the Human Future at the New Frontier of Power, New York: Public Affairs. EPWRF India Time Series (www.epwrfi ts.in) Agriculture Census Statistics Data sets from Agriculture Census h ave b e e n a d d e d t o t h e A g r ic u lt u r a l St a t i s t ic s m o d u le of the EPWRF India Time Series (ITS) online database. This sub-module contains state-wise data on: ● Number, Area and Average Size of Operational Holdings by Gender, by Social Groups and by Size Groups; and ● Characteristics of Operational Holdings by Tenancy Status, Terms of Leasing, Land Use, Irrigation Status, Sources of Irrigation and Cropping Pattern. These characteristics are also provided in a two-way classification of Social Groups by Size Groups.  Social Groups include Scheduled Castes, Scheduled Tribes, Others and Institutional Holders  Size Groups are: Marginal (Below 1.00 hectare), Small (1.00 < 2.00 hectares), Semi-medium (2.00 < 4.00 hectares), Medium (4.00 < 10.00 hectares) and Large (10.00 hectares and above) These data are available quinquennially from 1970–71. Agricultural Statistics module constitutes one out of 20 modules of EPWRF ITS covering a range of macro-economic, fi nancial sector and social sector indicators for India. For more details, visit www.epwrfi ts.in or e-mail to: its@epwrf.in EXPANSION 201 Smart Cards for All: Digitalisation of Universal Health Coverage in India MARINE AL DAHDAH and RAJIV K. MISHRA In less than ten years, India has launched colossal biometric databases. One among them is related to the first ‘free’ health coverage scheme offered by the government of India: the Rashtriya Swasthya Bima Yojna (RSBY). Based on a public–private partnership between government and private companies, RSBY national scheme was launched in 2008, as a first step towards universal health coverage in a country where households endorse 70% of health expenses. The first phase of RSBY offers to cover `30,000 ($600) of inpatient expenses per year for five members of a below poverty line household and is now piloted in several Indian States to include outpatient expenses and above poverty line families too. RSBY relies exclusively on a centralised digital artefact to function, made visible by the ‘RSBY Smart Card’, a chip enabled plastic card containing personal data of individual and their family counting and conditioning the granting of health services to them; thus, no smart card means no health cover- age. Till date 120 million Indians have been registered in the RSBY database. This article analyses how health accessibility is crafted under the RSBY scheme by questioning two central dimensions of this data-driven digital health scheme: the smart card technology and the public–private partnership, whereas RSBY scheme promises health coverage for all, its digital infrastructures may complicate access to health services, and reveal new patterns of exclusion of individuals. Thus, we will detail how smartcards technologies and private providers condition access to health care in India. Keywords: Digital, biometrics, health coverage, welfare state, India, Jharkhand Marine Al Dahdah (corresponding author) Center for Studies of Social Movements (CEMS), Paris, France. E-mail: marine.aldahdah@ehess.fr Rajiv K. Mishra, Centre for Studies in Science Policy, School of Social Sciences, Jawaharlal Nehru University, New Delhi, India. Science, Technology & Society 25:3 (2020): 426–443 SAGE Publications Los Angeles/London/New Delhi/Singapore/Washington DC/Melbourne DOI: 10.1177/0971721820912920 Introduction Digitally enabled services is becoming a priority of the government of India (Arnold, 2013; Drèze & Sen, 2002) and ‘Multi Application Smart Card’ a new tool to ensure access as well as delivery of public services for various social sector schemes. Among these schemes, universal health coverage (UHC) has 202 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  427 been prioritised in the past decade 1 (Drèze & Khera, 2017; Patel et al. 2015). Thus, the ‘Rashtriya Swasthya Bima Yojana’ (RSBY) was notified under the Ministry of Labour and Employment in 2008 to give access to health insurance for the below poverty line (BPL) families in India 2 and later on to beneficiaries from eleven different categories. 3 Based on a public–private partnership (PPP) between government and private companies, RSBY national scheme was launched with the aim of offering health coverage to the whole population of India. It became the first step towards UHC in a country where households endorse 70% of health expenses (Shahrawat & Rao, 2012). The first phase of RSBY offers to cover `30,000 ($600) of inpatient expenses per year for five members of a BPL household; it is now piloted in several Indian States to include outpatient expenses and above poverty line families too. Till date 120 million Indians have been registered in the RSBY database, which relies exclusively on a centralised digital artefact to function. The scheme is made visible by the ‘RSBY smart card’, a chip enabled plastic card containing personal data of individual and their family counting and conditioning the granting of health services to them; thus, no smart card means no health coverage. As on 2017, there are more than 38 millions of active RSBY smart cards in India. 4 Biometrics based identification systems using chip-enabled smart card are assumed to be efficient tools for ‘faster’ delivery of public services; the most famous and biggest digital project of this kind being the unique identification (UID)/ Aadhaar database started from 2009 by the government of India. 5 These technical artefacts go hand in hand with another growing trend in public service delivery: the use of PPP. Therefore using smart cards for providing health insurance services has occupied the imagination of the state and at the same time driven business opportunities for private players in the past years. RSBY scheme relies both on PPP and smart card. Private providers like insurances companies, technology providers, and private hospitals are major stakeholders of the scheme. The primary purpose of using a smart card is to identify and authenticate the members of the family who are enroled in the database using thumb print scans and facial photographs, and then to count their usage and spending on the scheme; thus, smart card conditions the granting of health services. The smartcard as well as the PPP dimension of RSBY scheme raises many research questions and this article wants to highlight how smart cards and private stakeholders are playing a decisive role in the delivery of health services and access to health care in RSBY. In furtherance of some recent research on RSBY(Ahlin et al., 2016; Dasgupta et al., 2013; Ghosh & Gupta, 2017), our article mobilises Science, Technology & Society studies to understand the nuances of technology used in the name of access to health. Research and data collection for this article is based on qualitative research method. 6 We conducted our fieldwork in Jharkhand in spring 2017. At that time, Health department was advertising the launch of a broader scheme based on RSBY. In fact since late 2015, RSBY was discontinued in Jharkhand after the scheme had been transferred from Labour department to Health department, as per central directives. We conducted 52 semi-structured in-depth interviews (ITWs) and a focus group discussion with various people that included 203 Science, Technology & Society 25:3 (2020): 426–443 428  Marine Al Dahdah and Rajiv K. Mishra doctors and administrative staff from empanelled public and private hospitals, government officials at state and district level, insurance companies, technology service providers (third party administrators [TPA]), community health workers (ASHA/AWW), and families targeted and enroled in the scheme. Interviews with diverse stakeholders provided a broad familiarity with the scheme and how it functioned in Jharkhand. The smartcard as well as the PPP dimension of RSBY scheme raise many research questions. This article highlights how smart cards and private stakeholders are playing a decisive role in the delivery of health services and access to health care. More specifically, it seeks to understand the prevailing ‘social sense’ of smart cards as means of accessing as well as excluding people from health care according to digitally driven criteria. It also tries to de-construct the idea of the PPP model as the only possible way to set UHC in India, 7 knowing the difficulties that such partnership in terms of public versus private responsibilities can hold. To analyse and understand this, the article is divided into two parts, first discussing the materiality of the scheme through smart cards and the complexity it inserts in the process of accessing health care, and second, focusing on the PPP dimension and the specific role of private providers in such a public policy. A Smart Card Based Health Coverage Biometrics cum smartcards based governance policies have increasingly grown all over the world to manage and administer population and to give access to various public services such as health care, education, social security, transpor- tation, and so on (Lyon, 2007, 2013). Similarly, in the wake of globalisation, the imagination of the Indian state became increasingly pre-occupied by using biometric smart card technologies for identification and access to public services (Drèze & Khera, 2017; Lyon, 2008; Ramanathan, 2015; Shukla, 2013). The idea of using identification technologies is to sort, list, filter, include and exclude various categories of beneficiary population (Fluri et al., 2015; Greenleaf, 2010; Lyon, 2002). However the very process of listing, sorting and identifying involves deeply entrenched motives of surveillance, discipline and control of bodies with the creation of infrastructures of biometric identification technologies (Burchell et al., 1993; Monteiro & Hanseth, 1996; Srinivasan & Johri, 2013, pp. 101–112). The material embodiment of this infrastructure in a country like India comes into direct contact with social, cultural and economic heterogeneity of people, their everyday life and their sense of development (Arnold, 2013; Bowker & Star, 2015; Hughes, 2004; Ryan, 1994). In this context, the first national level planning and implementation of chip enabled smart cards infrastructure for health care in India came with RSBY (Government of India, 2007). In this scheme, the biometric database enrolment, the recording of personal, social and demographic details, delivering and accessing the smart card became a central policy focus (Karan et al., 2017; Rajasekhar et al., 2011). However, from the initial phase of implementation of this scheme it showed important limitations, such as enrolment catered with incomplete and faulty 204 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  429 data, difficulties in issuing smart cards, and persistent obstacles in using the cards (Rajasekhar et al., 2011; Selvaraj & Karan, 2012; Seshadri et al., 2012). Whoever was aware about RSBY faced problems in enroling, accessing and using it (Das & Leino, 2011). The following three subsections will discuss these issues: firstly by outlining how public health services in India evolved to smart cards based services like RSBY, secondly by examining the large digital database on which RSBY relies and problems associated with incomplete and obsolete data, thirdly by discussing usages of the smart cards and difficulties in accessing the alleged health services. The analytical discursive aspects of RSBY smart card and the meaning people (beneficiaries) attach to such artefact reflect the prevailing everyday views on technology led development. The infrastructure of smart card based identification of bodies for health care, determined mostly by the dynamics of PPP (public–private partnership) model, is governed through private players (insurance companies, private hospitals) and third party service providers (technology companies) have come to mediate the power relationship between the state and citizens (Abraham & Rajadhyaksha, 2015; Faulkner, 2008; Turner, 2008). Digitalised Public Health Services in India To understand smart cards based universal health care it becomes pertinent to dis- cuss the context of digitalised public health services in India. In recent years health care services have been subjected to large-scale use of biometrics based chip smart cards, considered as a key technological medium for health accessibility (Gold, 2013; Marohn, 2006). With the health policy of 1983, government of India for the first time outlined the role of technology by highlighting the importance of medical information systems for managing health care. 8 However, it took more than fifteen years to implement a prominent project on digital technology and health care, with a first telemedicine network for connecting three hospitals in Chandigarh, Delhi and Lucknow in the year 1998. The health policy of 2002 witnessed a subsequent shift from the policy of 1983 with emphasis on technology associated with an increasing role of the private sector in health care. This policy shift played a major role in extending the use of technology and digital technologies in particular with various projects on health information management systems in the first half of the decade of 2000 (Goldman, 2007; Negaard & Shaaban, 1989). Reflections on strong usage of biometrics and smart card technologies become more visible from the last years of the decade of 2000, as shown by the working group report on ‘Entitlement Reform for the Empowerment of Poor: The Integrated Smart Cards’ submitted on January 2007 as part of the eleventh five-year plan. 9 One of the most striking aspects of this report was the concept of ‘multi-application smart card’ to be used for various social sector schemes among them health care being a crucial one. The policy recommendations of this report became turning point in future construction of technological infrastructure of identification for health care, and also for other public services such as socio-economic welfare entitlements. In this context of increased role of private players in health care and constant policy emphasis on using biometrics based smart cards, the RSBY scheme emerged 205 Science, Technology & Society 25:3 (2020): 426–443 430  Marine Al Dahdah and Rajiv K. Mishra in the year 2008 as a pioneer cashless and paperless scheme. One of the first aspects of RSBY implementation was the creation of a large digital database by enroling beneficiaries into this data driven health care program. This database became a large repository of personal information of people who enroled in the scheme, their photographs, fingerprint scans and address details aggregated for five members of a family. With the help of a software that is connected to this database, empanelled hospitals fetch beneficiaries information when they come for medical treatment. This practically takes place when the beneficiaries are enroled, have received the card and have taken it to an empanelled hospital at time of medical attention. However, from the very beginning this database is catered with incomplete and obsolete data, making it partial and leading to the exclusion of many people. Partial Databases The making of RSBY smart card and the enrolment process is based upon the selection of target BPL families and twelve other categories of beneficiaries. The BPL data list is provided by the district collector’s office to the labour department, which in turn forwards it to the State Nodal Agency (SNA) of RSBY. 10 The SNA locks the data and then forwards to the RSBY central agency, which generates a list of data having a 17 digit encrypted unique relationship number (URN) for each BPL family. The locked data list with URNs is then sent back to the insur- ance company. 11 It contains an identification (ID) and password to access the data list from the central agency’s platform. After getting access, insurance company provides it to the technology provider (TPA). As per the data list, technology providers create a roadmap for enrolment of beneficiaries to RSBY. 12 However, representatives of insurance companies, technology providers and government officials mentioned that this list was fraught with problems of redundancy as well as missing or incorrect data. 13 Indeed, the data relies on a thirteen years old census done in 2003–04 14 . In thirteen years, kids of the census became adults, the elderly died and many families migrated and moved up or down the poverty line. Apart from BPL data, data for other categories were also difficult to access, as mentioned by a government official: ‘taking data was a major challenge, data categories like rickshaw pullers, street vendors, domestic workers, beedi workers, we did not have data on these categories’. 15 On a similar line, an insurance company representative said ‘some woman who came for enrolment, her age was 31 or 32, but the age dur- ing the census was 15 years or 16 years [..], we could not even update the age’ 16 . During the enrolment process, biometrics of five family members were taken and matched with name, age and address details as per the pre-defined URN list. Frequent mismatching of data and biometrics was highlighted by the technology provider who looked over enrolments in several districts of Jharkhand: ‘there are problems with mismatch of biometrics, [...] there is mismatch with URN data [...] people in the villages work and their hands get rough and it becomes difficult to get their biometrics’. 17 Multiple data anomalies could explain the low enrolment of families as explained by the TPA representative ‘there is a lot of problem with data 206 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  431 here; [...] data has hampered the enrolment percentage, so enrolment is 40–50%’. 18 This low percentage of enrolment from the given BPL data list shows that more than 50% of the target population is not covered. According to several testimonies many households are missing from the BPL list used for enrolment, leading to their exclusion from the digital database and the RSBY scheme. This shows that right from the beginning of data acquisition and enrolment of beneficiaries the smart card is riddled with non-existing, fragmented and obsolete data. At the beginning of the scheme in Jharkhand, people came to the enrolment camps to complain about the fact that they were not included in the enrolment list, or that their name or age was wrong in the file, but no mechanism was put in place to update the database and then improve the accuracy of data on site. Being outside the database, rightfully or not, lead to bear one’s own health care expenses. But people who were enroled in the database have also faced this situa- tion. Getting the smart cards made and received did not mean that the beneficiar- ies accessed health services as per the card at time of medical requirement. The politics of (un)use of the smart cards brings into picture some further challenges faced by beneficiaries. Smart Cards’ (Un)Use Enrolment to RSBY was relatively poor in Jharkhand, with less than 50% of the targeted people actually subscribed to the scheme. For this scheme ‘Around 40 lakhs beneficiaries were identified, out of which 18 lakhs people got smart cards, so we had 45% enrolment rate in 2014–15’. 19 People in the villages got the feel- ing that if many people were enroled a few of them only used the scheme, as this community health worker explained: ‘In my knowledge only 2–3 people have used it, but enrolment was done by many people. There were around 70–80 families from my village who were enrolled in the scheme’. 20 Low usage of the scheme was also confirmed by the state officials: ‘Out of 18 lakhs people enrolled, 74.7 thousand people used the cards to get treated in 2014–15’. 21 . The difference between enrolment data and usage data of RSBY is particularly striking, less than 1.8% of families targeted by the scheme actually used it in Jharkhand. The first explanation provided by the insurers and state officials for the low usage of the smart card was lack of awareness of individuals who were supposed to benefit from RSBY: ‘It has been observed that beneficiaries got their smart cards but they are not availing the benefit of that because of lack of awareness’. 22 As explained by a representative from insurance company, some people had a very different understanding of the use of the RSBY smart card: ‘in some places the beneficiaries gave the smart card to the doctors in hospital and asked for `30,000 in cash thinking that it was like an ATM card and they can withdraw money’. 23 For the majority of people who understood the purpose of the scheme, knowing how and where to use the cards was a challenge, as this patient explained: ‘I took it (RSBY smart card) to one hospital in Ranchi but they did not accept it. This hospital was not in the list. I did not read the details in the leaflet that was provided, but also it’s difficult to find the hospitals’. 24 This testimony also 207 Science, Technology & Society 25:3 (2020): 426–443 432  Marine Al Dahdah and Rajiv K. Mishra highlights the low rate of hospitals empanelled in the scheme. Indeed, the number of empanelled hospitals and usage data are correlated; a second explanation for low usage of the card. The low usage of the scheme is also directly associated with the one year validity period of the smart cards, which constitutes the third explanation for low usage of the scheme. Several patients and health workers explained to us that even when people knew about empanelled hospitals and travelled to these specific hospitals to use the smart card, they could not use it because the card was already expired. As told by this health worker: ‘we took the card to the hospital; it was R. hospital since it was in the list. So when we were admitting the patient they said yes the card will be accepted, but when the patient was getting discharged, so we asked whether they used the card and the money in that. They said no, the card cannot be used, the card is not valid, the card has lapsed’. 25 Some hospitals told us that it was the case for the majority of patients that came to their hospitals: ‘This (expired smart cards) happens in 90% of the cases’. 26 If the majority of RSBY smart cards were ‘unused’ in Jharkhand, the several cases of effective usage pointed towards several difficulties during the three important steps of hospitalisation process: registration, blocking and discharge. Registration, blocking and discharge procedures are done through several technologies like smart card readers, biometrics scanner and software where specific treatment packages are selected. 27 When the smart card is accepted at the hospitals’ registration desk, it is punched into the smart card reader along with biometrics verification of the beneficiary family with the thumb readers. 28 At this point, issues of biometrics mismatch can happen. Several interviews revealed that there were frequent biometric mismatch, for almost one person in ten. In that case, another member from the enroled family had to be called, otherwise the registration would not be completed and the smart card will not be used. If registration is completed, the blocking of medical packages has to be done in the first 24 hours. The packages are selected from a list of six different categories: 1/non-surgical (medical) treatment in general ward; 2/admission in intensive care unit (ICU); 3/surgical procedure in general ward (not specified in packages list); 4/surgical procedure in general ward (specified in package); 5/maternity benefit package; 6/ in-patient care (IPD) and day care procedures with list of 1,090 medi- cal conditions. 29 However patients where only asked to provide the smart card and verify their biometrics for match, and did not know anything about packages that were booked. They were never told about the categories of packages and also about the amount taken on their card. This non-communication about the blocking process and the amount retained on the card is further connected with possible manipulations of the card. It came into picture that many private hospitals blocked ‘non-required’ packages, as explained by this technology provider: ‘they booked an appendicitis but the patient was suffering from fever. For the fever the charge should be `500 but they blocked the package for `12,000’, 30 and confirmed by several doctors we met. Another possible manipulation concerned the blockage of packages without any hospitalisation in reality or blockage of several days of hospitalisation, whereas 208 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  433 the patient was discharged earlier. We encounter several cataract patients that spent less than 24 hours in private hospitals where a three days hospitalisation package was blocked indeed. This is done to block the maximum amount on the card, even when beneficiary did not require or use the service in reality. This could be correlated with testimonies provided by several stakeholders, on how in rural areas private hospitals flung rapidly after this scheme started to be implemented. 31 If people are not aware of the blocking process and the money retained on their card, those manipulations are easier to perform. These cases of manipulations also reveal the lack of monitoring of the smart cards usage. Talking about monitoring problems, one of the doctors of an empanelled private hospital mentioned, ‘in the case of private insurance when somebody is admitted, [...], or has swiped the card then some representative of the company within 24 hours visits you to check whether it’s a genuine case or not, but in RSBY there is no monitoring’. 32 Further mentioning about the details, the doctor specified that ‘In the case of RSBY they come after one week or maybe sometime after the patient gets discharged, [...]. Suppose I have done operation of hydrocele, but the booking is done for Hernia, [...] you will come in 1 months or 15 days, the treatment is done and the patient is discharged, when someone comes to monitor, that person will be able to see paper not the manipulation’. All the above-discussed issues highlight that this smart card based health care scheme has unfolded complex social realities, which help to better understand the dynamics of digital technologies. After discussing the social aspects of databases and smart cards, it is crucial to discuss the PPP through which this scheme is being implemented and administered. A Public–Private Partnership Based Health Coverage RSBY is an interesting example of the ever-growing phenomenon of public–private partnerships in the health sector. These partnerships involving the private sector in public health policy are flourishing worldwide (Richter, 2004) and are particularly developed and invasive in India (Kuriyan & Ray, 2009; Medhekar 2014; Raman & Björkman, 2009). These partnerships are often advertised as win-win collabora- tions, offering to lower public expenses and to improve public services efficiency through private management methods. The commercial dimension and attempts to sell products promoted by PPPs in the Global South have already been denounced in the case of partnerships on access to medicines or vaccines (Birn, 2014; Global Justice Now, 2016; McGoey, 2015). Critics of PPPs argue that these partnerships are not obviously benefiting the public partners in the Global South but benefit private partners who set them up (Biehl & Petryna, 2013). These critics also point to the complex entanglement of commercial and public health interests that are coexisting in ventures like RSBY. Jharkhand State selected insurance companies to administer and manage RSBY. Central and state governments paid premiums (between 200 and `700 per year) to insurers for each and every smart card made. The 24 districts of Jharkhand, where 209 Science, Technology & Society 25:3 (2020): 426–443 434  Marine Al Dahdah and Rajiv K. Mishra divided in three clusters of 8 districts, each run by a different insurance company. CholaMandalam administered the two districts of our study. For all technological services, i.e., procurements of smart cards, enrolments, printing of smart cards, operating data servers and providing analytic services insurance companies hired a technology provider known as TPAs. CholaMandalam’s technology provider was Smart Chip Ltd, an Indian subsidiary of a French company named Morpho deal- ing with digital security technologies. Nevertheless, insurers are the visible face of RSBY and insurer employees are often taken for government officials, as this hospital employee explains: ‘So CholaMandalam handles everything of RSBY [...] they are from the government department, now we are not talking about Insurance companies, so they are from RSBY so CholaMandalam’. 33 In the same vein, the technology provider staff in charge of enrolment in the villages and also of setting up the devices in hospitals are most of the time assimilated with the insurance company too. The name CholaMandalam is cited by most of our interviewees, whereas the technology provider Smartchip is relatively invisible. The Double Winners Insurance companies are seen as the main actor of RSBY but also the major ‘winner’ in this partnership: ‘the largest share of benefit is being received by CholaMandalam’. 34 This perception that the partnership is a double win for private players comes from different pieces of evidence. In our study as well as in other research done on RSBY, two kinds of stakeholders were identified as benefiting from the scheme: insurance companies and private hospitals (Dasgupta et al., 2013; Shoree et al., 2014). Indeed, if enrolment to RSBY in Jharkhand was low (around 45%), still 18 lakhs 65 thousands smart cards were made the last year of the scheme, which means that more than 18 lakhs premiums were paid to insurance companies. This constitutes a first obvious win for insurers that collected premiums for so many previously uncovered families. As explained by this district official, enrolment process was the most important part for insurers: ‘Insurance company guys used to be in high spirits when they were doing enrolment and making their cards, since more cards made more money for them’. 35 The validity of the coverage will then play an important role in the ability to use the policy for enroled individuals. One insurance company explained that the card is valid for one year, but that in fact the patient can benefit from it for eight months because the enrolment period can take up to four months: ‘I will tell you this in short and brief, in insurance, a policy is for 12 months, the maximum upper limit is that the last beneficiary who has got the card, that beneficiary should get minimum 8 months policy, this is per IRDA guidelines’. 36 According to both technology provider and district officers in charge of enrolment in the villages, the enrolment period was always more than six months: ‘The government directive is to close the enrolment in 3–4 months but it does not happen like this and the enrolment takes 6–7 months’ 37 ; ‘The CholaMandalam company had a lot of benefit in this scheme, if we see that government is trying to 210 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  435 implement it from April to next year 31st March, and also the money has been paid and also renewal and all has been done. They have become like the middlemen, they are taking money from the government and they are issuing the card in September, and the card has been delivered in October or November’. 38 So according to our interviews in most of the cases, after receiving the card patients had only three to four months to use it before expiration. The second win for insurance companies resides in the fact that empanelment of hospitals and claims settlements were also done by them. Firstly, it was not in their interest to empanel a lot of hospitals, as this state official explains: ‘Most of the time insurance companies are not showing their interests in empanelling the hospitals, because the more hospitals would be empanelled and accordingly they would have to settle more claims. They are discouraging the hospitals, not to create too much RSBY users’. 39 So the less hospitals they would empanel, the less claims they would have to settle. In the next part of the article we will detail the processes of claim settlement that also favours insurers in many ways. The second winners of RSBY scheme are private hospitals. In Jharkhand, 95% of reimbursement of packages (claims) were asked from private hospitals. In our study, as well as in another research conducted in Chhattisgarh, small private hospitals have been identified as central providers of care for RSBY beneficiaries (Dasgupta et al., 2013b) especially in rural districts, as this community worker explains: ‘That card was mainly used in the private hospitals and also more particularly in A. Hospital (a 10 bedded private hospital run by one MBBS doc- tor)’. 40 When RSBY was launched, a hospital to be empanelled had to fill specific criteria—more than 10 bed, 24 hour MBBS doctors on site, lab facilities—but these criteria were considerably altered in states like Jharkhand and Chhattisgarh were few hospitals could meet them, as this state official highlights: ‘Major challenges were to have good hospitals, we didn’t have enough good hospitals to empanel, so we relaxed our criteria to empanel more hospitals, earlier we wanted only 10 bedded hospitals with all facilities. But we relaxed it to 5 bedded, and even to 2 bedded hospitals, so that people in those areas could benefit from the scheme also’. 41 Even in Ranchi the capital of Jharkhand we discovered that activity of small private nursing homes was considerably boosted by RSBY, as the head of this small hospital in Ranchi explains: ‘we use to have many patients from RSBY per month, if there were 30 patients per month in the hospital then 20–22 patients use to be from RSBY [...] we also did this work for our advertisement’. 42 Apparently small private hospitals benefited from the scheme, which brought a lot more customers to them, as this technology provider told us: ‘the private sec- tor has a strong motivation for working for this scheme, they are aware that they can benefit from this scheme. Even to an extent many private hospitals have been opened to make benefits out of this scheme. [...] People have opened hospitals in two rooms, they don’t even have MBBS but yet the registration and license is given to them that’s one of the biggest question mark’. 43 However, all the private hospital managers we met argued that ‘the money never use to come on time’ 44 and that many of their most recent claims are still pending after two years, because 211 Science, Technology & Society 25:3 (2020): 426–443 436  Marine Al Dahdah and Rajiv K. Mishra the insurer refused to clear them: ‘many hospitals have bills pending of up-to 2–3 months, even my hospital has pending bills, I have `21 Lakhs pending’ 45 ; ‘99% of the hospitals have outstanding dues with CholaMandalam, some have 5 Lakhs, some have 2 Lakhs’. 46 So even if private hospitals have benefited from the scheme at the beginning of it, the wind changed for them, several lost the ‘game of claims’ with insurers and some even shut down because of it. The Game of Claims The representatives of insurance companies gave different explanations to the non-settlement of hospitals claims. The late uploading of usage data by hospitals is among the first reason evoked by the different stakeholders. If data were not uploaded within the 24 hours of the discharge of a patient, the claim would be rejected by the insurer as explained by this state official: ‘Connectivity is not there, even in Ranchi district you have those problems. So hospitals couldn’t upload the data within the stipulated time frame of 24h. So very frequently insurers refused their claims with the comment “delayed uploading of data”; they said the hospitals are not respecting the delays’. 47 The process of uploading the data in the servers is crucial for claims recovery. When the patient is discharged, a set of all three slips; registration, blocking and discharge along with all medical records is sent to the insurance company. This has to be matched and verified with upload of hospitalisa- tion data in the server, on this the employee of a private hospital mentioned, ‘if the data is not uploaded in their sever, then there would be a mismatch since if there is blocking and the data of all the procedures is not uploaded then there would be a data mismatch, so the upload has to hit the server’. 48 This was mentioned as a crucial part for claims to be processed, failure of which would lead to pending payment of claims. 49 The second major reason for non-settlement of claims is related to misuse of packages by hospitals or even accusation of fraud. In those cases, the insurer decided that treatment that hospitals are claiming to be reimbursed for were not done properly or even not done at all and these hospitals could be de-empanelled for that reason: ‘One hospital in D. district, was de-empaneled for fraud issue. A patient was coming for diarrhoea and discharged after 3 days, but the hospitals blocked higher package in fact, different from the treatment, like hysterectomy for instance. That hospital was very frequently blocking high packages. That’s why it got de-empanelled’. 50 The insurance company had two systems to identify misuse of the scheme by hospitals, through the data stored on their server or through random checks in suspicious hospitals as explained here: ‘We do checks in the software, if the hospital software is saying that today 10 patients have been admitted (blocking) then we check it. We can generate all that detail, we can take details of the beneficiary, we can take all the treatment documents, OPD paper, X-Ray paper. But we take the documents and then we try to assess using the documents. We can see common things, if the patient is admitted for severe fever, and the fever details is 98 or below 100 and if they have admitted in ICU then that creates a doubt 212 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  437 element’. 51 But insurance staffs are not really qualified to be able to ‘separate the grain from the chaff’ online as well as offline, as they acknowledged themselves: ‘But then we are not doctors, so we cannot justify whether the patient needed ICU treatment or general ward treatment’. 52 However, claims that the insurance companies supposedly found had problems or was suspicious were not reimbursed. The last reason for non-settlement of claims is because insurers did not get their full premiums paid the last year of the scheme, as stated here: ‘If you are giving me the premium then I will cover the risk, if not then we cannot provide the cover. We did not get money from the government so that’s why we could not pay to the hospitals, and this is because there were some political issues’. 53 Central govern- ment that covers 75% of the amount paid its share but the state of Jharkhand that covers the rest refused to pay for the last month of the scheme because of pending vigilance enquiry regarding insurers practices for RSBY, as explained by this state official: ‘As per MOU, they (insurers) had to clear the claims of hospitals within one month. But they didn’t pay those claims; because they said there premiums were not paid by the state. They have not been paid their entire premiums because of the pending enquiry. Earlier they were paid some premium amount, but they said they paid to the hospitals because they had their premiums, but now they have no more money to set the claims’. 54 If the majority of stakeholders we met had the impression that the scheme ben- efited to the insurance companies, they also clearly stated that this partnership was not a win for the government and public services: ‘They (insurers) took the money from the government, the money for the premium amount but they never paid back the claims amount which was suppose to be paid to the concerned hospitals’. 55 The Losing Side When RSBY started in Jharkhand, all the public hospitals from Community health centres to the state referral hospital were automatically empanelled. A strange idea knowing that in government facilities almost everything is free or at a very low cost for all the patients that are using those public facilities. Thus, an incentive mechanism was put in place so that public facilities could block the same packages as private hospitals and get reimbursed as well, as explained by this district official: ‘In the government hospital almost everything is free, so in that case there was some incentive for the government to put government hospitals so that they can get some reimbursements’. 56 The majority of the reim- bursed amount will go to improve infrastructures of the hospital and 25% would benefit directly to the hospital staff, which according to some officials was not enough to motivate the staff to use the card as explained by this official: ‘The public hospitals haven’t used the smart card. Only 25% of the claim amount will go to the hospital staff, individually they were not getting a big amount, the rest is going to the hospital account for the benefit of the hospital. So the staff there was not very eager to use the card’. 57 213 Science, Technology & Society 25:3 (2020): 426–443 438  Marine Al Dahdah and Rajiv K. Mishra In all the government hospitals we visited, managers and medical officers in charge (MOIC) said they used the scheme but did not received any money from RSBY. In one of the studied district, the accountants from the CHC and from the referral hospital with the highest number of claims of the district explained to us that they never ever received any fund from the insurer, even if they used the scheme and sent the data, a fact confirmed by the district accountant: ‘Even when all the paper work was ready and everything was fine, but still the money was not paid back. [...] There is a society called HMS (Hospital Management Society) in which the money was supposed to come, but it never did. HMS is a society in all the CHCs in which government gives money for the betterment of the people/patients’. 58 Even the technology provider working for the insurance company and supervis- ing enrolment as well as claim data for RSBY in Jharkhand highlights the fact that public hospitals never got money out of the scheme: ‘Government focus was to promote and develop the public hospitals, but in this case all the funds were taken by the private hospitals, public hospitals didn’t get anything’. 59 All those different actors highlighted the fact that even if the public hospitals used the scheme and claimed packages from the insurer they never received the claimed amounts for their staff or to improve their infrastructures as promised. Public hospitals did not win anything from the scheme and even lost patients for small private hospitals that were pointed out by several actors as low-performing and of low-quality in many ways. For the government of India and the state of Jharkhand it was then a double loss. Firstly, because public infrastructures in Jharkhand did not benefited at all from the scheme and did not upgrade their facilities or staff thanks to the money injected through RSBY. Secondly, because insurers always kept the hand on data and adapted their premiums to the claim amounts they would have to disburse. Hospitalisation data were used by insurance companies to analyse the use of smart cards but also to evaluate districts performance and claim level. Thus, insurers knew where the treatments were happening and where packages were blocked and could fix premium rates according to this, as explained in detail by this technology provider: ‘using this data they change their premium rates, [...] areas where the usage is high the premium rates would be more and where the usage is less premium would be a bit less, it is easy to know the usage data, the area and locations where it has been used more [...], on this basis insurance company does bidding’. 60 That way, insurers would bid according to the claim ratio of the districts, after carefully analysing the usability of the scheme both from the individuals’ side and the health infrastructures’ side, to ensure that their implication in the scheme will generate sufficient profits. Furthermore, in RSBY policy document, there has been no policy mechanism for stopping insurance companies and technology providers to do data dumping/offloading of RSBY usage data for future purposes. While discussing with private implementers about these issues, we realised that insurance companies can use the data for their own purposes , because the agreement signed with the state has no mention about data regulation and privacy 61 . 214 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  439 Conclusion While evaluating their potential profits and interests in UHC schemes, private entre- preneurs of health like insurers and technology providers are transforming lives of people by conditioning their access to health. While digital infrastructures leave no evident material traces, no physical infrastructure, they nevertheless offer new private players and a new approach to care and health administration. They necessarily pro- duce transformations, which have not yet been sufficiently studied, whereas RSBY scheme promised health coverage for all, its digital infrastructures complicate access to health services and reveal new patterns of exclusion based on digitally constructed criteria. This research shows that both the technological and partnership dimensions of RSBY lead to a commodification of health that is of little benefit for individuals and did not have any proven positive outcomes on accessibility of health care in Jharkhand. Furthermore, we showed that the PPP was a double win for the private sector and was weakening public health infrastructures and the central health care system by diverting public funds toward private infrastructures. Yet it is the chosen model for the upcoming new UHC scheme launched by the government of India DECLARATION Of CONfLICTING INTERESTS The authors declared no potential conflicts of interest with respect to the research, authorship and/or publication of this article. fUNDING We would like to thank the Institut Francilien Recherche Innovation Société (IFRIS) whose funding has been instrumental in bringing about this research. NOTES 1. This has been discussed in the eleventh (2007–2012) and twelfth five-year plan (2012–17). As part of the eleventh FYP a working group report on ‘Entitlement Reform for the Empowerment of Poor: The Integrated Smart Cards’ was submitted on January 2007, for more details please see http://planningcommission.gov.in/plans/planrel/fiveyr/default.html 2. BPL families stood for 30.9% in rural areas and for 26.4% in the urban areas according to the Rangarajan Committee review that was setup in 2014 by planning commission to review the methodology of poverty estimates done by the Tendulkar committee in 2011–12. For details, see http://planningcommission.nic.in/reports/genrep/pov_rep0707.pd 3. These eleven categories include building and other construction workers registered with the welfare boards, licensed railway porters, street vendors, MNREGA workers who have worked for more than fifteen days during the preceding financial year, beedi workers, domestic workers, sanitation workers, mine workers, rickshaw pullers, rag pickers and auto/taxi driver, for details see http:// www.rsby.gov.in/about_rsby.aspx 4. Ibid. 5. For details see https://uidai.gov.in/about-uidai/about-uidai/background.html 6. We collected village and district data from two districts of Jharkhand, and state data from Ranchi. We used contact details of various actors and institutions mentioned in the RSBY website, like 215 Science, Technology & Society 25:3 (2020): 426–443 440  Marine Al Dahdah and Rajiv K. Mishra insurance agents, private hospitals, and government hospitals. The initial round of interviews that we conducted was based on purposive and convenience based sampling, which further helped us to meet the concerned people who were related with the scheme, and from there we did snow balling of our samples. The interviews were conducted in three languages (Hindi, English and local ChotaNagpuri) helping in inclusive data collection. 7. As this is one of the core policies planning part of RSBY within the broader framework of universal health coverage. This could be seen in the policy documents of RSBY here, http://www.rsby.gov. in/Documents.aspx?id=25, and also preceding documents of planning commission’s health sector plans here. For details please see http://planningcommission.gov.in/aboutus/committee/wrkgrp11/ wg11_smtcard.pdf 8 . Government of India, National Health Policy , 1983, see https://www.nhp.gov.in/sites/default/files/ pdf/nhp_1983 9 . For detai ls please see http://planningcommission.gov.in/aboutus/committee/wrkgrp11/wg11_ smtcard.pdf 10. ITW 42, insurance company representative. 11. Ibid. 12. ITW 45, TPA representative. 13. ITW 42, ITW 43, ITW 45, ITW 50. 14. Ibid. 15. ITW 50, state official. 16. ITW 42, insurance company representative. 17. Ibid. 18. ITW 45, TPA representative. 19. ITW 54, state official. 20. ITW 36, community health worker at village level. 21. ITW 54, state employee. 22. ITW 54, state employee. 23. ITW 42 & ITW 43, insurance company employees. 24. ITW 37, patient at village level. 25. ITW 36, community health worker, village level. 26. ITW 11, private hospital employee. 27. ITW 42 & ITW 43, insurance company employees; ITW 45, TPA representative. 28. ITW 42 & ITW 43, insurance company employees; ITW 45, TPA representative; ITW 11, private hospital employee. 29. JASLA WS booklet on RSBY and hospital archives. 30. ITW 45, TPA representative. 31. ITW 45, TPA representative. 32. ITW 13, doctor, empanelled private hospital. 33. ITW 11, private hospital employee. 34. ITW 27, district employee. 35. ITW 50, district official. 36. ITW 42, insurance company employee. 37. ITW 45, technology provider. 38. ITW 27, employee from the district. 39. ITW 55, state official. 40. ITW 35, community health worker, village level. 41. ITW 49, state level official. 42. ITW 51, head of a private hospital. 43. ITW 45, technology provider. 44. ITW 51, head of a private hospital. 45. ITW 13, private hospital employee. 46. ITW 11, private hospital employee. 216 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  441 47. ITW 55, state official. 48. Ibid. 49. Ibid. 50. ITW 55, state official. 51. ITW 43, insurance company employee. 52. ITW 43, insurance company employee. 53. ITW 43, insurance employee. 54. ITW 49, state employee, labour dpt. 55. ITW 27, employee from the district. 56. ITW 27, district employee. 57. ITW 44, state employee. 58. ITW 27, district employee. 59. ITW 45, technology provider. 60. ITW 45, technology provider 61. Draft agreement between State Nodal Agency and insurance company 2012. REfERENCES Abraham, I., & Rajadhyaksha, A. (2015). State power and technological citizenship in India: From the postcolonial to the digital age. East Asian Science, Technology, 9(1), 65–85. http://easts. dukejournals.org/content/9/1/65.short Ahlin, T., Nichter, M., & Pillai, G. (2016). Health insurance in India: What do we know and why is ethnographic research needed. Anthropology & Medicine, 23(1), 102–124. https://doi.org/10.10 80/13648470.2015.1135787 Arnold, D. (2013). Everyday technology: Machines and the making of India’s modernity. University of Chicago Press. https://books.google.co.in/books?hl=en&lr=&id=VZmTedJT2p8C&oi= fnd&pg=PP6&dq=Everyday+Technology+David+Arnold&ots=CCwF1Iuf8j&sig=V37pd5Ag GmFWEFvvtubIuYDOvkQ Biehl, J., & Petryna A. (2013). When people come first: critical studies in global health. Princeton University Press. Bowker, G. C., & Star, S. L. (2015). Science and technology, social study of: Computers and information technology. In J. D. Wright (Ed.), International encyclopedia of the social & behavioral sciences (2nd ed., pp. 186–191). Elsevier. https://doi.org/10.1016/B978-0-08-097086-8.85024-2 Burchell, G., Gordon, C., & Miller, P. (1993). The Foucault effect: Studies in governmentality, with two lectures by and an interview with Michel Foucault. Contemporary Sociology, 22(2), 279–281. https://doi.org/10.2307/2075812 Das, J., & Leino, J. (2011). Evaluating the RSBY: Lessons from an experimental information cam- paign. Economic and Political Weekly, 46(32), 85–93. Dasgupta, R., Nandi, S., Kanungo, K., Nundy, M., Murugan, G., & Neog, R. (2013). What the good doctor said: A critical examination of design issues of the RSBY through provider perspectives in Chhattisgarh, India. Social Change, 43(2), 227–243. https://doi.org/10.1177/0049085713493043 Drèze, J., & Khera, R. (2017). Recent social security initiatives in India. World Development, 98, 555–572. https://doi.org/https://doi.org/10.1016/j.worlddev.2017.05.035 Faulkner, A. (2008). Medical technology into healthcare and society: A sociology of devices, innovation and governance. https://books.google.co.in/books?hl=en&lr=&id=4L2MDAAAQBA J&oi=fnd&pg=PR1&dq=Medical+Technology+into+Healthcare+and+Society&ots=-oAIDHve- G&sig=j9sLQ1tshBcNsr9YLNm3PuuGEf0 Fluri, J. L., Jackson, P. S. B., & Paudel, D. (2015). A new development technology? South Asian biometrics and the promise of state security and economic opportunity. Geography Compass, 9(10), 539–549. https://doi.org/10.1111/gec3.12230 217 Science, Technology & Society 25:3 (2020): 426–443 442  Marine Al Dahdah and Rajiv K. Mishra Ghosh, S., & Gupta, N. D. (2017). Targeting and effects of Rashtriya Swasthya Bima Yojana on access to care and financial protection. Economic & Political Weekly, 52(4), 61–70. Gold, S. (2013). Healthcare biometrics: Solving the staff and patient security governance challenge. Biometric Technology Today, 2013(8), 5–9. https://doi.org/https://doi.org/10.1016/S0969- 4765(13)70143-7 Goldman, M. (2007). How “water for all!” policy became hegemonic: The power of the World Bank and its transnational policy networks. Geoforum, 38(5), 786–800. https://doi.org/https://doi. org/10.1016/j.geoforum.2005.10.008 Greenleaf, G. (2010). India’s national ID system: Danger grows in a privacy vacuum. Computer Law & Security Review, 26(5), 479–491. https://doi.org/https://doi.org/10.1016/j.clsr.2010.07.009 Hughes, T. (2004). Human-built world: How to think about technology and culture. https://books.google. co.in/books?hl=en&lr=&id=G7xmjLN6uXwC&oi=fnd&pg=PR7&dq=Human+Built+World&o ts=nFkIn_QG3_&sig=9uX-RQlaV2HFGrZKHptPnpNmS14 Karan, A., Yip, W., & Mahal, A. (2017). Extending health insurance to the poor in India: An impact evaluation of Rashtriya Swasthya Bima Yojana on out of pocket spending for healthcare. Social Science & Medicine, 181, 83–92. https://doi.org/https://doi.org/10.1016/j.socscimed.2017.03.053 Lyon, D. (2002). Surveillance as social sorting: Privacy, risk and digital discrimination. Routledge. https://doi.org/10.1177/1440783306061355 ———. (2007). National ID cards: Crime-control, citizenship and social sorting. Policing, 1(1), 111–118. https://doi.org/10.1093/police/pam015 ———. (2008). Biometrics, identification and surveillance. Bioethics, 22(9), 499–508. https://doi. org/10.1111/j.1467-8519.2008.00697.x ———. (2013). The border is everywhere: ID cards, surveillance and the other. In E. Zureik & M. Salter (Eds.), Global Surveillance and policing: Borders, security, identity. Willan. https:// doi.org/10.4324/9781843926139 Marohn, D. (2006). Biometrics in healthcare. Biometric Technology Today, 14(9), 9–11. https://doi.org/ https://doi.org/10.1016/S0969-4765(06)70592-6 Monteiro, E., & Hanseth, O. (1996). Social shaping of information infrastructure: On being specific about the technology. In Information technology and changes in organizational work (pp. 325–343). Springer. https://doi.org/10.1007/978-0-387-34872-8_20 Negaard, C., & Shaaban, M. (1989). United nations and other international organizations. Government Publications Review, 16(6), 627–655. https://doi.org/https://doi.org/10.1016/0277-9390(89)90098-8 Planning Commission, Government of India. (2007). Entitlement reform for empowering the poor: The integrated smart card (ISC). http://planningcommission.gov.in/aboutus/committee/wrkgrp11/ wg11_smtcard.pdf Rajasekhar, D., Berg, E., Ghatak, M., Manjula, R., & Roy, S. (2011). Implementing health insurance: The rollout of Rashtriya Swasthya Bima Yojana in Karnataka. Economic & Political Weekly, 46(20), 56–63. Ramanathan, U. (2015). Considering social implications of biometric registration. IEEE Technology and Society Magazine, 34(1), 10–16. https://doi.org/10.1109/MTS.2015.2396113 Richter, J. (2004). Public-private partnerships and international health policy-making: How can public interests be safeguarded? Ministry for Foreign Affairs of Finland, Development Policy Information Unit. Ryan, S. M. (1994). Recent literature on government information. Journal of Government Information, 21(5), 455–485. https://doi.org/https://doi.org/10.1016/1352-0237(94)90021-3 Selvaraj, S., & Karan, A. K. (2012). Why publicly-financed health insurance schemes are ineffective in providing financial risk protection. Economic & Politcal Weekly, 47(11), 61–68. Seshadri, T., Trivedi, M., Saxena, D., Soors, W., Criel, B., & Devadasan, N. (2012). Impact of RSBY on enrolled households: Lessons from Gujarat. BMC Proceedings, 6(Suppl. 5), O9. https://doi. org/10.1186/1753-6561-6-S5-O9 Shukla, R. (2013). Technologies in Aadhaar: A sociotechnical view. In In the wake of Aadhaar, (pp. 1–30). Centre for Studies in Science Policy. http://stasis.in/sites/default/files/CSCS-Aadhaar.pdf 218 Science, Technology & Society 25:3 (2020): 426–443 Smart CardS for all: digitaliSation of UniverSal HealtH Coverage in india  443 Shoree, S., Ruchismita, R., & Desai, K. (2014). Evaluation of RSBY’s key performance indicators: A biennial study | Microfinance gateway—CGAP. ILO’s Impact Insurance Facility. Srinivasan, J., & Johri, A. (2013, December). Creating machine readable men: Legitimizing the ‘Aadhaar’ mega e-infrastructure project in India [Paper presentation]. 6th International Conference on Information and Communication Technologies and Development, Cape Town, South Africa. https://doi.org/10.1145/2516604.2516625 Turner, B. S. (2008). The body and society: Explorations in social theory. SAGE. https://doi. org/10.4135/9781446214329 219 Canadian Anthropology Society "When the Government Changes, the Card Will Also Change": Questioning Identity in Biometrie Smartcards for National Health Insurance (RSBY) in India Author(s): Stefan Ecks Source: Anthropologica, Vol. 60, No. 1, Thematic Section / Section Thématique (2018), pp. 190-200 Published by: Canadian Anthropology Society Stable URL: https://www.jstor.org/stable/44876745 Accessed: 06-01-2025 15:35 UTC JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org. Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at https://about.jstor.org/terms Canadian Anthropology Society is collaborating with JSTOR to digitize, preserve and extend access to Anthropologica This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms220 "When the Government Changes, the Card Will Also Change": Questioning Identity in Biometrie Smartcards for National Health Insurance (RSBY) in India Stefan Ecks Edinburgh University Abstract : Since the mid-2000s, government initiatives in India have been gripped by the idea that biometrie identification is more efficient than any form of paper-based documentation. In this article, I explore how new health care schemes in India have adopted this technocratic promise. On the basis of ethno- graphic research in Karnataka, I describe how enrolments for biometrie smartcards for RSBY insurance proceeds. These enrolments are meant to turn the rural poor into consumer citizens, yet the RSBY cards elicit unexpected responses from the beneficiaries. Instead of reproducing state authority, the new ID cards become a fulcrum for questioning the stability of government. Keywords: biometrie IDs, RSBY, India, health insurance, poverty, consumer citizens Résumé : Depuis la moitié des années 2000, les initiatives du gouvernement indien ont été fascinées par l'idée que l'identifi- cation biométrique est plus efficace que les formes de docu- mentation écrites (sur papier). Dans cet article, j'examine de nouveaux programmes relatifs aux services de santé en Inde qui ont adopté cette promesse technocratique. A partir d'une recherche ethnographique à Karnataka, je décris comment ont lieu les inscriptions pour les cartes biométriques intelligen- tes de l'assurance RSBY. Ces inscriptions visent à changer les pauvres des zones rurales en des citoyens consommateurs ; or les cartes RSBY suscitent des réactions imprévues de la part des bénéficiaires. Au lieu de reproduire l'autorité de l'état, les nouvelles cartes d'identité deviennent l'occasion de contester la stabilité du gouvernement. Mots-clés : Identification biométrique, RSBY, Inde, assurance santé, pauvreté, citoyens consommateurs The Promise of Biometrie Health IDs Identity legal control cards (Das are technologies and Poole 2004, of social, Hull political 2012, Marx and legal control (Das and Poole 2004, Hull 2012, Marx 2015). ID cards enforce asymmetries in how stable the identities of card issuers and card holders are taken to be. Whoever is legitimate to issue an ID card is assumed to be self-same and stable, whereas the identity of the card holder is up for scrutiny. The ID issuer questions and establishes the identity of the card receiver and not vice versa. Yet, as I will argue in the following, the issu- ing of ID cards can also make card receivers question this power asymmetry. Hence, receiving a card does not necessarily mean that the stability of the ID issuer goes unchallenged. The moment a card is issued can occasion doubts in the ID card recipient about the stable identity of the card issuer. My example will be experiences of enrolling for a biometrie smarte ard issued under the Rashtriya Swasthya Bima Yojna (RSBY) program in southern Karnataka, India. RSBY, which translates to "National Health In- surance Program," is the world's largest health scheme that relies on biometrie cards. People "below poverty line" (BPL) are eligible to receive a smartcard, which allows them to claim hospital expenses of up to ^30,000 per family per year. RSBY was first launched by the central govern- ment's Ministry of Labour and Employment in 2008. Policy-makers put all emphasis on RSBY's "smart" tech- nology, which was portrayed as future-oriented and em- blematic of a new, clean and technocratic India. Biometrie smartcards epitomise India's post-reform "aesthetics of arrival" (Kaur & Hansen 2015) in cutting-edge modernity. Between 2008 and 2016, more than 41 million RSBY cards were issued (Government of India 2017). Anthro- pologists have asked why documents are often "invisible" forms of power and have highlighted "the denial of the mediating role of documents" as a technique of main- taining authority (Hull 2012, 253). By foregrounding the futuristic materiality of the smartcards, the RSBY 190 / Stefan Ecks Anthropologica 60 (2018) 190-200 This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms221 scheme does the opposite: it augments the mediating role of the document and makes new power relations visible. There is a range of health insurance programs for poorer people in India, but RSBY is the largest and best known. RSBY uses a combination of photographic and fingerprint technologies to ensure that any one of the people on the card claiming health expenses is entitled to do so. These "paperless" and "smart" ways of storing and processing data are also meant to make sure that the hospitals that provide health services for card holders are not overcharging or making fraudulent claims. When going to hospitals to make claims, claimants have their fingerprints taken and compared to those stored on the card. This aims to make claiming and reim- bursing benefits "safe and foolproof" for all participants. Biometrie identification has become common in in- dustrialised countries, but it is also being introduced in lower- and middle-income countries. Biometrie IDs are used in passports or bank cards. Health is another field of application, with IDs being issued both by governments and by public-private partnerships and non-governmental organisations. Multinational donor organisations, such as the World Bank or the Gates Foundation, are pro- viding financial and technical support to IT systems that extend the reach of biometrie cards in the health field. Biometrie cards seem to be the best way of closing the "identity gap" that people in poor countries are experiencing. The assumption in the development sector is that reliable digital ID systems are the best method of administrating benefits because they provide both iden- tification (who is the beneficiary?) and authentication (is the person claiming the benefit the person entitled to receive the benefit?). Closing identity gaps becomes closing development gaps (Gelb & Clark 2013). Biometrie ID systems look brand new, but they have a long history. One of the oldest recorded moments of using biometrie data for ID purposes was the use of handprints in colonial India. In 1858, Sir William Herschel, of the Indian Civil Service, invented whole- hand printing with ink on the back of employment con- tracts with colonial subjects. Herschel wanted to make contracts more binding, but he also wanted to ensure that only people under contract would receive payments from the civil service (Sengoopta 2004; Komarinski 2005). Biometrie identification technology emerged in a colonial encounter between administrators and largely illiterate locals. The introduction of RSBY cards 150 years later continues a long tradition of administer- ing people who are deemed most reliably identifiable through stable bodily identifiers. ID systems based on writing held sway for most of the colonial and post- colonial period (see Gupta 2012, 204), but biometrics are now established as a superior form of verification. The promise of making the body a stable and incor- ruptible source of unique personal identifiers to sidestep written documents is evident in all the programmatic statements about RSBY. According to Anil Swarup, the civil servant who is credited with designing the scope and shape of RSBY, this biometrie data system is "paperless, cashless, and ageless" (Swarup 2013a). In corruption-prone countries such as India (Srivastava 2012; Roy 2016), services can be delivered transparently and fairly only with a robust personal identification system of beneficiaries and benefits in place. RSBY is superior to other schemes because it minimises the scope for fraud by both individuals and hospitals. The bodies of RSBY beneficiaries may be vulnerable to dis- ease and decay, but their fingerprints and faces are meant to be so incorruptible as to make the administra- tion of benefits incorruptible, too. "Paperless" biometrics work with the "ageless" parts of the body to make the system itself "ageless." In Max Weber's (1978, 957) classic formulation of bureaucracy, documents are handled by "a staff of subaltern officials and scribes of all sorts." In RSBY, all human intermediaries are foregrounded as potential points of corruption and resource leakage, which the smart new system promises to eliminate. RSBY was designed by the Ministry of Labour with assistance from the German international development agency GIZ (Deutsche Gesellschaft für internationale Zusammenarbeit). For complex political reasons, the central Ministry of Health did not want to take up health insurance schemes. The Ministry of Labour took up the development of RSBY under its remit of dealing with informal labour. As Swarup (2013b) points out, 94 per cent of all labour in India is in the informal sector. "The problem is: defining this individual - because without defining him, you can't benefit him - then, locating him, registering him, and benefiting him." This is so difficult because the mąjority of people in India are poor, illiterate and often migratory. If people have no fixed or clearly identifiable address, then the technology has to take this into account. If people are to be reimbursed for health care costs, this has to happen directly in the hospital and not at some later stage through their home address. If people are largely illiterate, a successful scheme also has to be paperless (Swarup 2013b). If people are highly mobile, the smartcard has to be issued on the spot, instead of being printed elsewhere and then being sent to a home address (Swarup 2013b). The RSBY scheme is a key example of how "the software engineer," India's new archetypical citizen-subject, is helping to pull "the farmer," India's old archetype, into Anthropologica 60 (2018) When the Government Changes, the Card Will Also Change / 191 This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms222 the connected world of the twenty-first century (Philip 2016). Initially, hopes were high that RSBY cards could be used for purposes beyond health coverage. Some pilot schemes used the RSBY system for the administration of other social benefits, such as life insurance or food rations, with a plan toward developing RSBY into a plat- form for an integrated social protection system (Swarup 2013a). The excitement about using RSBY-type smart- cards for other services also reached beyond India, and delegations from other countries visited to see how the scheme was working and how it could be adapted elsewhere. For example, in 2012 a German delegation arrived in India to study how RSBY cards could be used to replace paper vouchers to administer free school meals. That Germany, the country with the "world's oldest social security system," would seek "India's help to provide social benefits to needy schoolchildren" was reported with pride in the news ( Economic Times 2012). An additional benefit of RSBY cards was, according to Swarup, the provision of a form of "smart" ID card to poor people. However, since RSBY cards identify groups of household members rather than individuals, the scope for using RSBY cards as proof of individual identity is limited. Moreover, eligibility for enrolling in RSBY is predicated on being identified and documented as the holder of another, non-biometric card, the "below poverty line" card. One of the benefits that comes with holding a BPL card is being entitled to food rations from government shops. BPL cards are issued by state governments to households earning less than ^27,000 a year. By classifying people as BPL, the state "converts the many facts of someone's material deprivations into a category that can be enumerated and measured" to create "a class of people for whom programs are targeted" (Gupta 2012, 156). RSBY could never be a stand-alone ID system, because it has to rely on how Indian state bureaucracies are administering other social benefits. Plans for making RSBY cards proxy IDs for poor people were pushed aside by a much more ambitious national ID card project called Aadhar. The Aadhar system is run by the Unique Identification Authority of India (UIDAI) and has been rolled out since 2009. With now more than 1.133 billion IDs issued, Aadhar is the world's largest biometrie ID system, enrolling up to 99 per cent of the Indian population. Aadhar's mission is to "de-duplicate" (Cohen 2016) the entire population of India so that every individual person has one, and only one, unique identity. The goal is to eliminate all "incomplete, fake, or duplicate identities" (Rao 2013, 72). If any ID system is now in the running to be a platform for social benefits, it is Aadhar and not RSBY. In fact, it is likely that Aadhar is going to become the basis for RSBY enrolments in the future. Whenever someone enrols in Aadhar, they are going to be "pre- seeded" in the database for future RSBY enrolments (Gelb & Raghavan 2014). The central government minis- ter for labour announced plans to move the administra- tion of social benefits to Aadhar (Economic Times 2016). Enrolments into RSBY cost ?30 per card. Enrolments are run by private insurance companies. The companies are selected through a tendering process where the company making the best offer gets the contract from the state government. The insurance companies' incen- tive is to enrol as many people as possible in RSBY, because insurers get a premium for each person that joins. These private companies do not benefit from any- one making claims through RSBY. Hence the incentive structure for the private companies is to achieve high enrolment numbers and low claimant numbers. This design - high investment in getting people to enrol and low investment in explaining how the scheme works - goes some way to making sense of some of the bene- ficiaries' experiences that I will describe here. My main argument, that the issuing of the RSBY biometrie smartcard occasions doubt about the stability and iden- tity of "the state," can be understood only within the context of the political economy of health in India. A Poor and Patchy State of Health India has a poor history of protecting people from exces- sive health expenditures. Most health care expenses continue to be paid out of pocket by rich and poor people alike. Government institutions exist and are in theory supposed to cover all citizens' needs. But the public sector captures only around 30 per cent of all health expenditures, and the bulk of all expenses is in the private sector. Even by the standards of lower- and middle-income countries, national budgets allocated to health are extremely low in India (Organization for Economic Collaboration and Development 2015, 156). The share of the government has been hovering around 1 per cent of GDP since the 1990s (Rao & Choudhury 2012). Even the Ministry of Health and Family Welfare (Government of India 2014, 8) has diagnosed a "failure of public investment in health to cover the entire spec- trum of health care needs" and a "worsening situation in terms of costs of care and impoverishment due to health care costs." People's out-of-pocket (OOP) health expenditures are said to be "more impoverishing than ever," and even hospitalisation in a public hospital does not protect against "catastrophic health expenditures." 192 / Stefan Ecks Anthropologica 60 (2018) This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms223 Indeed, hospitalisation costs almost tripled between 2004 and 2014. The average cost of hospitalisation was ?24,436 in urban areas and ^14,935 in rural areas. The ministry estimates that 63 million people in India fall deeper into poverty every year because of OOP health costs (see Peters et al. 2002; Shahrawat and Rao 2011). In 2011-12, 18 per cent of Indian households faced cata- strophic health expenditures, up from 15 per cent in 2004-05. Rising care costs led to calls for publicly financed health insurance schemes. A range of new schemes have been introduced since the mid-2000s (Devadasan et al. 2006). All these schemes share the idea that cata- strophic household debt caused by health expenditures is bad for both individual households and for the wider economy. All these schemes also assume either that existing public sector health facilities are unable to cope with the demand for affordable care, or that they them- selves can be expensive enough to put people into pov- erty. Everyone, including poor people in both rural and urban areas, consult private practitioners more often than government practitioners (Bhatia and Cleland 2001; Narasimhan et al. 2014). The new policies are designed to allow poorer people to access costly and mostly private health care without having to pay out of pocket. In the language of the policy-makers, "supply-side financing" in the sense of putting money into government infrastructures was unable to reduce household OOP expenditures. Hence a new type of "demand-side financing" was designed, which puts "freedom of choice" about where to spend money into the hands of people. For those who designed RSBY, this freedom of choice was the scheme's "unique selling point" (Swarup 2013a, 2013b): the shifting of decision making about health care spending from the government to the indi- vidual citizen. Instead of the government providing a consistent and reliable public health care infrastructure, citizens are told to seek services in the private sector. Given the costs of private health care, prior to these new schemes, one could opt out of government health care only if one was rich enough to pay for private providers. The "unique selling point" of RSBY is that it empowers people living below the poverty line to choose between public and private hospitals just like the rich. But most other health schemes available in India, even those available to people below the poverty line, work on the same set of demand-driven assumptions. In this way, RSBY is in line with wider neoliberal transforma- tions of health care in India over the past decades. I will return to this gap between neoliberal policy and people's experiences of what these policies mean in my ethnography of RSBY enrolments in Kamataka below. RSBY was meant to be a "national" health care scheme that would transcend the many differences be- tween states and districts. One of the projected benefits of the smartcard technology was that it would allow people to travel to different hospitals within districts and states, and even across different Indian states, and to be able to use the same card in all locations. As a "national" system, the RSBY card should work like a passport that allows movement within India. However, this promise has never been fulfilled because the RSBY scheme has been very unevenly implemented across India. Some federal states in India are providing contin- uous support for RSBY, whereas others, such as Andhra Pradesh, have never participated in RSBY. Some states participated only for limited periods or never committed a lot of resources to it. By 2016, roughly 57 per cent of eligible households across India had been enrolled but with a huge variation across districts, ranging from only 3 per cent enrolment in Kannauj in Uttar Pradesh to nearly 90 per cent in several districts of Chattisgarh and Kerala (Karan, Yip, and Mahal 2017). This checkered implementation is even evident at the highest level of government in terms of which agency should be responsible for RSBY. The scheme was initiated by the Ministry of Labour, but control was shifted to the Ministry of Health in 2015, and its long- term future is not secured. The task of implementing RSBY was conferred to state-level ministries. This resulted in a highly uneven implementation and of RSBY being constantly subjected to the vicissitudes of political conditions. A patchy rollout of RSBY is evident district by district and even village by village (Rajasekhar et al. 2011; Sun 2011; Palacios 2010). In the state of Karnataka, for example, RSBY ground to a halt in 2013. The Karnataka Ministry of Labour stopped organising further enrolments for a host of political reasons, one of them being the uncertain outcomes of the Indian general elections of 2014. In the run-up to the elections, there was fear that promoting RSBY enrolments would be seen as a form of political campaigning on behalf of the ruling Congress Party. In Karnataka, RSBY is associated with Congress politics because it was introduced during the reign of the United Progressive Alliance (UPA), of which Congress is the dominant force, which ruled India from 2004 until 2014. A host of new social welfare schemes were introduced by the UPA, RSBY being an exemplary one among them. The Congress Party maintained its hold on the Karnataka legislative assembly elections in 2013 but in 2014 lost the national elections for the Lok Sabha (the lower Anthropologica 60 (2018) When the Government Changes, the Card Will Also Change / 193 This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms224 house of the Indian parliament in Delhi). A new wave of enrolments in RSBY commenced only in 2014, but the change-over between ministries put another damper on the rollout of the program. Meanwhile the central government has announced that the implementation of RSBY is also going to change in the future, but it is not yet clear how. RSBY card holders can take their card to a hospital that is "empanelled" in RSBY. Both private and public hospitals can become empanelled. Hospitals bill patients at their usual rates but can recover parts of the costs not from patients but from RSBY. Hospitals have an incen- tive to admit BPL patients who might not be able to afford their services out of pocket, and they also have an incentive to charge for services covered by RSBY. Many costs that come with hospitalisation are not covered by RSBY. Also, RSBY reimburses inpatient procedures, but neither outpatient treatments nor medications are covered - the two main sources of household health expen- ditures (Garg and Karan 2009; Shahrawat and Rao 2011). The extent to which hospitals get themselves em- panelled as RSBY providers has been limited and hap- hazard. For example, the largest hospital in Mysore district, the JSS charitable hospital, never became em- panelled in RSBY. With 1,800 beds, the JSS hospital is one of the largest hospitals in India and is by far the biggest in the city of Mysore. Up to one thousand patients are treated every day in the outpatient departments. Around three thousand surgeries are performed in the hospital's 27 operation theatres every month. Every month, more than twenty thousand inpatients and more than sixteen thousand outpatients are treated. JSS is a charitable hospital with a mission to provide "affordable healthcare with human values." JSS explicitly welcomes poorer people and those from the rural areas. RSBY would be expected to be part of the accepted insurance schemes, but it is not. A host of other health care schemes, catering to a wide range of beneficiaries from the poorest to the richest, are administered at JSS. However, RSBY is entirely absent. When I spoke with the hospital's director about health insurance and asked why RSBY is not on its list of approved programs, he said that RSBY was not reliably available in the region and that other schemes were in place and doing a better job at providing access to care than RSBY. The RSBY Enrolment Process Fieldwork for this article was carried out in 2015 at three rural enrolment posts in central Mysore district. The ethnography of RSBY enrolments formed part of a research collaboration called Indian Health Insurance Experiments (2017), which evaluates the uptake of new insurance schemes among poorer people in India (for example, Nandi et al. 2015). The observations and inter- views were conducted with 26 families directly at the enrolment stations. RSBY had been rolled out in Karna- taka since 2008. There were no active RSBY smartcards in southern Karnataka in 2014, and people's memories of earlier phases of RSBY were fuzzy. What I could ob- serve was a new wave of enrolments that began in late 2014. The enrolments took place in public sites, such as primary schools, and it turned out to be easy to contact people and ask them for an interview after they had re- ceived their smartcards. RSBY cards enrol families of up to five people and not individuals. The enrolment identi- fies male household heads as the primary card holder. This patriarchal bias of the bureaucratic process was mirrored in my interviews: the main respondent to my questions was always the male household head, with only occasional interventions from other family members. The field research was carried out by me and my Kannada-speaking research assistant and interpreter, Chanappa Kapli. Interviews were based on a semi- structured questionnaire. Audio recordings of the inter- views were transcribed and translated from Kannada to English. My presence as a European researcher did not have any discernible response effects, neither among the officials carrying out the enrolments nor among the families interviewed. Enrolments into RSBY were done by mobile teams of insurance company employees. The teams consisted of three to four people who travelled from village to village. Prior to their arrival, the companies identified who should enrol in RSBY through a list of BPL card holders provided to them by the state government. The companies liaised with local panchayats (village councils) to let them know when they were coming and what kind of setup was required to carry out the enrolments. The RSBY teams moved into primary schools and village halls for a day or two, depending on the size of the catchment population. The panchayats were active in informing people about the upcoming enrolments and in mobilising them to make the effort to come. In Mysore district, panchayats linked up with local health workers to distribute "tokens" to BPL households, slips of paper containing information about where to go and what to bring. People were also alerted to the need to arrive in person with every household member who should be included on the card. In case of anyone being absent from the enrolment, it was possible to add a name and biometrie data at a later stage through a district office, but this was cumbersome. At all the posts we observed, enrolments in this wave proceeded smoothly. Times spent queuing to be seen ranged from a few minutes to 194 / Stefan Ecks Anthropologica 60 (2018) This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms225 two hours. The full enrolment, from arrival to handover of the card, took about ten minutes per family. To get the card issued, family members gave their names to the enrolment team. A representative from the panchayat confirmed that the family was on the BPL register. In the RSBY database, information about beneficiaries is ordered by unique registration number (URN), name of the "head of family," age, insurance policy number, start and end dates of the policy (one year from day of enrol- ment), the available amount in the account (maximum ?30,000), how much money is "blocked" (spent) from the card, and finally codes for district and state where the registration was done. A photo of all the household members was taken, as well as fingerprints from both hands. The RSBY cards were handed over to the house- hold heads a few minutes later. In Mysore district, most of the time the enrolment teams also gave out leaflets explaining how the RSBY card could be used, with lists of hospitals that were part of the scheme. However, this was not done consistently, and in many cases people walked out with a card but without any information on how to use it. People's negative experiences, such as not understanding what the biometrie card is for, can ex- plain why the issuing of the card undermines rather than builds trust in the state. The following two sections provide a detailed ethnography of these experiences. Experiencing the RSBY Card: What Is It For? Among the 26 families interviewed after their enrol- ments, the most common sources of information about the event were panchayat workers, primary health care nurses, neighbours and family members. The panchayats did an awareness drive, distributing leaflets informing them of the time, place and purpose of the enrolments, as well as making announcements via loudspeakers carried through villages on autorickshaws. Such drives are a com- mon way of spreading information about elections, public health camps and other relevant events. The second source of information was nurses from primary health care centres under the Ministry of Health who went door to door in some areas, trying to mobilise as many potential beneficiaries as possible. Both panchayats and nurses handed out tokens ( chiti ) that people should bring with them to the enrolment station: "Some girl came from a hospital to inform us. She was visiting all houses and giving token. She informed that this is a health card and if there are any problem then the government will give up to 30 thousand, the rest of the amount you have to pay" (family #26). Some families complained that not all relevant people had received tokens for the event in this way. A third and equally important source of information about the enrolment events came from neighbours and extended family members. Several families said that they had not re- ceived any information about the enrolments but were simply following behind neighbours who said that they should come along. All the families that we talked to said that the awareness drives for RSBY had happened only a few days before the actual enrolments and that this was the first time that they had ever heard of RSBY. Since RSBY is meant to be the leading health scheme for people below the poverty line in India and has been running since 2008, to find that most people interviewed had no prior awareness of it was surprising (see Madhukumar et al. 2012; Reshmi et al. 2007; Narasimhan et al. 2014). There were only three families who had prior expe- riences of using RSBY. One household head (#6) had faint memories of having enrolled in RSBY seven years earlier, but said that they did not have any health problems that year and did not use it. After one year the card expired, and they had not heard anything else about renewals until now. Another man (#7) said that RSBY has been around for the past "seven years" but that this was the first time that his family had enrolled. During another enrolment drive some years earlier, he remembered being out of the village and missing the occasion. Srinivas, a lorry driver in his early 40s, had had a kidney operation three years ago at a government hospital and ongoing problems with his kidneys. He remembered enrolling in RSBY for years earlier and of going to the hospital with the card two times, but in each case the card was declined and he was told that RSBY did not cover the particular problem diagnosed. All of the families interviewed said that health care costs were too high. All of them were able to recall previous episodes of a family member being hospitalised with serious consequences for the household's finan- cial situation. For example, Chandru, a 42-year-old day labourer, was trying to find money for his mother's brain tumour operation. The cost was ^100,000; ^10,000 was covered through a central government scheme, but the remaining ?90,000 had to be paid from a loan. They are still repaying to this day. The father of a 35-year-old tailor (#25) had to be taken to hospital eight years ago with liver problems. He was admitted to the JSS hospital and treated there. The total cost was ^45,000, but he had only ^10,000 available, so the rest had to be covered by a loan of ?35,000 at a 5 per cent interest rate. This loan was still being paid off all these years later. His son then got tuberculosis. They took him to the government hospital in Mysore, but when they did Anthropologica 60 (2018) When the Government Changes, the Card Will Also Change /195 This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms226 not receive good treatment there, they shifted to a private clinic where each visit cost ^500, about ?10,000 over six months. TB treatments have a dedicated public infrastructure of clinics that supposedly cover 100 per cent of all treatment needs, yet this is one among many examples that show that OOP expenses can be high even when treatments are, allegedly, free and easily available (Ecks and Harper 2013). OOP health care expenses add to other major expenses. In the case of an elderly couple (#9) who had to find the money for dowries for three daughters, they had to sell their two hectares of land. After selling the land, the husband started working as a cleaner in a private hospital. Some families said that they would rather die than pay too much for health care. It was possible to spend money within limits, but there was no point in ruining an entire household's finances for a single episode of ill health. Devanna (#24), a day labourer with just a small patch of agricultural land, said that for "big problems" they would not seek treatment but "stay at home," because they were unable to repay big loans, even if they could take them out. Nagasundara (#11), a casual worker in his mid-30s who said his family earned less than ^5,000 a month, said that any health problem cost- ing more than ^100,000 to treat would not be taken to a hospital "because we cannot pay that much; just we would like to die, that is the only option." Ravi (#17) and his wife also worked as day labourers. Whatever money they earned, maybe ?200 in a day, was just about sufficient to feed themselves and put their three children through school, but not for other expenses: "If any big problem occurs, we will not go to the hospital for consul- tation. We will try tablets [self-medication]. Otherwise we will commit suicide." Every family said that they "did not know much" or "did not really understand" RSBY. Lacking information about how to use the RSBY card right after it had been issued is striking, because receiving a freshly printed biometrie ID card should be the one moment when people know best what it is good for. Some guessed that the card was "like a ration card" (#12) that could be used to get health services, but the details were fuzzy. Some said the card was for "use in hospitals" (#20), but the difference between empanelled and not- empanelled hospitals seemed mysterious. In all cases, people understood that the card entitled them to ?30,000 per year and that any excess costs had to be paid for out of pocket, even though they did not always grasp if this amount could be spent on several occasions or only on one occasion. Despite having been handed the RSBY card only minutes earlier, some people said that this card was valid "for life" and there was no need for renewal. Indeed, several people pointed out that one of the advantages of the RSBY card was that it did not need annual renewals, as opposed to other health care schemes. One of the people who said that no annual renewal was necessary also said that he was illiterate and unable to read the pamphlet that had been handed to him along with the card: "I am uneducated. I cannot read anything. I just look at pictures" (#26). Sadly, there were no informative pictures on the leaflets. Another said, "We do not know about RSBY, it's just that all people are enrolling, so we also came for enrol- ment" (#11). The most critical voices compared the lack of infor- mation about the uses of RSBY to an act of "cheating" because "they give no clear information to the people" (#11). It was typical that even when benefits were avail- able, the government failed to provide proper infor- mation on how to access them. When approached if it was possible to ask government officials about RSBY, some felt that poor people were routinely treated with disdain. Ravi (#17) said that he did not understand what RSBY was all about, but that there was no point in asking government people about it: "We will not ask anybody about this. If we ask anybody, they will not respond clearly. They will tell us: 'You are uneducated, why do you need this information,' like this they will scold, so I do not want to ask anybody." Experiencing the RSBY Card: "What's the Use?" In our interviews with enrolling families, we asked about their awareness of other "health cards" and that they compare the advantages and disadvantages of RSBY to these other cards. In southern Karnataka, another card is far more widely known and more widely used than RSBY: the Yeshasvini card. This card is available to people in rural areas as well as informal sector workers in urban areas. It is administered through workers' cooperatives across the state of Karnataka, and it covers card-holding families for private health care of up to ^150,000 per year. Enrolment costs for Yeshasvini vary depending on several criteria, but come in on average at ^200 per person. Enrolment in Yeshasvini started at 1.6 million members in 2003 and increased to 3.4 million members in 2013. This represents about 15 per cent of all target beneficiaries and 9 per cent of the rural population of Karnataka (Aggarwal 2010, 6). About a quarter of the families we talked to during RSBY enrolments also had Yeshasvini cards and could compare the benefits of the two cards to each other. Most of the other families had also heard of Yeshasvini 196 / Stefan Ecks Anthropologica 60 (2018) This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms227 even if they were not members of the scheme. The two features that allowed the easiest comparisons between RSBY and Yeshasvini were the enrolment fees and the available annual allowances. At only ?30 per family, RSBY was clearly more affordable and therefore seen as more favourable than Yeshasvini. In fact, a few people pointed out that they had paid for the Yeshasvini annual membership in the past but had not renewed their cards because of the comparatively high cost of enrolment. One household head (#8) who has held a Yeshasvini card for several successive years summed up this opinion: "RSBY is a good scheme, as far as I know. One card contains the whole family and all their informa- tion. And we pay just ^30 for enrolment. Yeshasvini is also good, but we need to pay ?250 a person." Everyone agreed, however, that ?30,000 from RSBY is far too little, not only when it is compared to Yeshas- vini's ^150,000, but by any standard. Almost everyone said that the costs for health care are so high that ^30,000 will not get you anywhere. Perhaps a few minor problems could be covered with this amount, but any actual hospitalisation case could not be financed with the amount provided under RSBY. For this reason, many questioned if RSBY should exist at all: "^30,000? What's the use?" Chandru (#10) asked bitterly. Even if RSBY covered outpatient department (OPD) treatments and medication costs - which it currently does not - the amount was painfully inadequate. Of course, being promised ^30,000 was better than being promised nothing at all. For a small enrolment fee of ?30 per family, there was no visible drawback in taking advantage of a potential source of health care funding: "We are poor people. Thirty thousand rupees is a good amount, if they will give when problems arise. Only if problems occur, that time we will know" (#18). Some said that they were happy that anything at all is given to them to help cover health costs. One said, "I am very happy about this because they [the government] are paying that much money" (#6). However, these expressions of gratefulness were rare, and even those who were grateful for some financial aid did not say that ^30,000 was in any way adequate. Many respondents were quick to offer suggestions about how much RSBY should pay. Ondu lakh , which is ?100,000, was a figure that several people mentioned as the minimum amount any health scheme should offer. This amount was not even to be used in several install- ments for a variety of episodes - in the way that the policy-makers envisaged RSBY should be used - but simply for a single episode of hospitalisation. Another suggestion focused on percentages of total costs to be covered. Several people said that, whatever the amount may be, 50 per cent should be reimbursed; others said that a 70 per cent reimbursement would be adequate (#20). People had many suggestions for how RSBY could be better organised in other ways. One common sugges- tion was that RSBY should not only cover hospitalisation costs, but also OPD treatments and medications. For OPD procedures and drugs, ^30,000 seemed more plau- sible than for large-scale surgeries. Another idea was that RSBY would only succeed if it secured quality care. Some felt that the hospitals treating under RSBY would be bad hospitals and that all the good hospitals must be paid for out of pocket (#26). Another sugges- tion was that government money should be spent to cover whatever procedure is necessary and that the scheme should not work based on a fixed rupee amount. If someone requires a particular surgery and is unable to pay for it out of household resources, the operation should be free: I am giving an important suggestion to the govern- ment: they have to identify the poor people [karag badava ]. Depending on how much they have to spend, if it is ?10,000 they should pay ^10, 000. If it is n00, 000, they should give ^100,000. The full amount. Anyone who is a labourer can earn up to ?300 a day. That goes into food and living - how can he pay any more money? Any big operation that costs more than ?100,000, a poor person will have to die (#10). Other people made proposals for how the money should be allocated, with some people saying that medi- cines should be given directly to poor people when they need them, and others saying that funds should be allocated from the government to private hospitals for them to have a budget to treat poor people in need. The question of social inequality and the fair alloca- tion of limited public resources reappeared when we asked if families who are classified as "APL" (above poverty line) should also be entitled to receive an RSBY card. Most people said that APL households should also get some financial protection because they were almost as poor as households below the poverty line. Given that the RSBY amount of ^30,000 was so low anyway, making it available to others did not seem too prob- lematic. However, several also said that social benefits such as RSBY should be strictly limited to those who needed them most, and those people were the BPL households. This was sometimes coupled with complaints about APL households obtaining BPL cards through bribing panchayat workers to get access to benefits Anthropologica 60 (2018) When the Government Changes, the Card Will Also Change / 197 This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms228 reserved for BPL households (#23). Richer people also managed to get better treatment at government hospi- tals because they were better educated and could harangue hospital staff more effectively than BPL people (#10): "In the government hospital, if you see the educated people, they will question them and get free benefits, but if any uneducated person goes to the hospital, then he must pay the full amount. He will be sent around, from one ward to another, from one hospital to another." Just as there was little disagreement about ^30,000 being insufficient, there was also little disagreement about the government being responsible for providing some level of help to poorer citizens. Yet there were a few people who said that ^30,000 may not be enough money, but that the government should not give away more than that. If the government puts too much into health, then the country suffers in other ways: either funds are deducted from other areas or the government finds ways of extracting funds from elsewhere. A day labourer from a village outside of Mysore was clear about this when asked if ^30,000 was enough. He thought that the government was not able to provide health care to everyone: "If the government pays for all Indian people, how much money would that take? But even if the government pays for everything, people will not be satisfied. But however much money we get, we should get satisfaction" (#7). Health expenditures were just one item among many other areas where govern- ment spending was necessary, and allocating too much for health simply meant that other welfare and develop- ment areas got neglected. Baire Gowda (#26), a man in his mid-50s who had been a deputy member of the local panchayat for 15 years, said that people should not ex- pect more than ^30,000, "because the government should provide all the people, so the government cannot give to a single person too much. The government can help with some amount, but not with the full amount." For the sake of social fairness, people should not expect to get all their costs covered, just some costs (#25). Receiving an RSBY card does not have any imme- diate benefit; the card is only a promise for the future. Many people doubted that this promise would ever be kept. There was a sense that a lot of benefit schemes were first introduced and then never properly imple- mented or maintained. Some people compared the RSBY card to the empty promises of politicians, who vowed anything to get elected but then forgot all about those promises. Several people said that there had been many policies but maintaining them properly was where the difficulties lay: "Maintenance is the big problem in these schemes" (#25). The current government may introduce a scheme, but then another government comes in and throws it all out of the window: "The government is providing this scheme, but the next government has to follow the same rules. If they stop, that means there is no use to this card" (#14). Conclusion Scholars working on welfare, citizenship and the state in India have noticed a shift from a Nehruvian model that wants to smooth social inequalities through targeted handouts to a neoliberal governmentality that stresses self-reliance and individual agency. This ideological shift is meant to make the poor become proactive consumers and wean themselves off government provisions. The RSBY smartcard is a prime example of this shift in its emphasis on citizen empowerment, demand-driven choice, and belief in markets producing optimal care. The question is if these neoliberal imaginations of health citizenship are grounded in real experience. Re- cent scholarship on neoliberal health insurance schemes casts doubts on whether neoliberal reforms have been as thorough as policy-makers imagined they would be. For example, Anjaria and Rao (2014) argue that the RSBY scheme was introduced as a top-down neoliberal policy of mobilising rationally choosing citizens, yet "they have not produced unilateral outcomes of making citizens responsible for their own self-management or promoting a particular unequivocal class politics" (Anjaria and Rao 2014, 424-425). New health care schemes such as RSBY are part of a liberalisation agenda that proposes a demand-driven restructuring of access to health care even for the poor. But the ethnography of RSBY card enrolments engender a different experience of being a citizen. From a policy point of view, RSBY is not meant to create a rationally choosing consumer citizen; rather it assumes that the scheme can find, and work with, consumer citizens who are already there. The smartcards are not making people "smart"; instead they are meant to unleash the smart potentials that consumer citizens already have. This makes sense because the existential burden to choose carefully between different health care options and the weight of having to take on full responsibility for how to spend limited resources have always already been with people, because India had never had a com- prehensive welfare system that could then become neo- liberalised (Gupta 2012). Those who designed RSBY might claim that they have introduced demand-side decision making, but instead they have introduced only another layer of complexity to what was already a com- plex set of decisions that individual households were facing all along. In turn, the lack of proper information 198 / Stefan Ecks Anthropologica 60 (2018) This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms229 about how the scheme is to be used does not produce calculating, self-managing citizen-consumers. Instead de- cision making about spending scarce resources on health care remains as obscure and as risky as it has always been. RSBY does not make the poor take the initiative and mobilise market competition by being canny con- sumers. The scheme appears to people as just another promised state benefit that may, or may not, materialise. And even if the services materialise fully, ?30,000 was clearly seen as insufficient to cover the real costs of a serious illness event. The introduction of biometrie IDs is meant to close the "identity gap" between the disadvantaged and the well-off. The biometrie ID card has thus become a promise of demarginalisation (Ecks 2005). It is supposed to use the individual body as an incorruptible source of stable identi- fiers to give ageless definition to the citizen, who can then become a fully benefit-maximising health care consumer. However, the ethnography of RSBY enrolments does not provide evidence that anyone in Mysore district perceived the card as a moment when their identity as a full health citizen was validated. The common assump- tion in the anthropological literature on bureaucratic procedures is that the issuing of an ID document is a moment when authority becomes reproduced "across time and space" (Sharma and Gupta 2006, 13). Instead, I argue that the issuing of RSBY cards does not seam- lessly reproduce authority and that the card issuing becomes a moment when citizens question the reproduc- tion of authority across time and space. In Mysore dis- trict, nobody seemed to be particularly impressed by the biometrie technologies or by the logistical accom- plishments of receiving a card within a few minutes. Not a single person walked out of the enrolment station proudly waving the newly minted card, declaring them- selves a new kind of person with a new range of exciting opportunities. If anything, they bemoaned that they had not received any paper leaflets that could explain what they should do with the shiny new plastic card. There was no sense that the card receivers were elated by having their identities confirmed by the card issuer. There was no sense that the card-issuing process enacted a power differential between card issuer and card recip- ients. On the contrary, the card recipients questioned the stability and identity of the card issuer: "When the government changes, the card will also change." At stake were not the identities of RSBY card holders, but the identity, across time and space, of the authorities behind RSBY. Stefan Ecks, School of Social and Political Science , University of E dinburgĶ EdinburgĶ UK. Email : stefan.ecks@ed.ajc.uk. References Aggarwal, Aradhna. 2010. "Impact Evaluation of India's Teshasvini' Community-Based Health Insurance Programme." Health Economics (19): 5-35. https://doi.org/ 10.100a^hec.l605. Anjaria, J. S., & Rao, U. (2014). Talking back to the state: citizens' engagement after neoliberal reform in India. Social Anthropology, 22(4), 410-427. Bhatia, Jagdish C., and John Cleland. 2001. "Health-Care Seeking and Expenditure by Young Indian Mothers in the Public and Private Sectors." Health Policy and Planning 16(1): 55-61. https://doi.Org/10.1093/heapol/16.l.55. Cohen, Lawrence. 2016. "Duplicate, Leak, Deity." Limn 6. http://limn.it/duplicate-leak-deity/. Das, Veena, and Deborah Poole, eds. 2004 Anthropology in the Margins of the State. Santa Fe: School of American Research Press. Devadasan, Narayanan, Kent Ranson, Wim Van Damme, Akash Acharya, and Bart Criel. 2006. "The Landscape of Community Health Insurance in India: An Overview Based on 10 Case Studies." Health Policy [Amsterdam] 78(2-3): 224-234. https://doi.org/10.1016Zj.healthpol.2005.10.005. Ecks, Stefan. 2005. "Pharmaceutical Citizenship: Antidepressant Marketing and the Promise of Demarginalization in India." Anthropology & Medicine 12(3): 239-254. https://doi.org/10.1080/13648470500291360. Ecks, Stefan, and Ian Harper. 2013. "Public-Private Mixes: The Market for Anti-tuberculosis Drugs in India." In When People Come First: Critical Studies in Global Health , ed. João Biehl and Adriana Petryna, 252-275. Durham, NC: Duke University Press, https://doi.org/10.1515/ 9781400846801-013. Economic Times. 2012. "German Delegation Coming to India to Take Rashtriya Swasthya Bima Yojana Lessons." 12 August, http://economictimes.indiatimes.com/news/ economy/policy/german-delegation-coming-to-india-to-take- rashtriya-swasthya-bima-yojana-lessons/articleshow/ 15367929.cms?intenttarget = no. Unorganized Workers." 2 May. http:// economictimes.indiatimes.com/news/economy/policy/ government-to-use-aadhaar-to-deliver-benefits-to- unorganised-workers/articleshow/52077509.cms Garg, C. C, and A. K. Karan. 2009. "Reducing Out-of-pocket Expenditures to Reduce Poverty: A Disaggregated Analysis at Rural-urban and State Level in India." Health Policy and Planning 24 (2): 116-128. doi: 10.1093/heapol/ czn046. Gelb, Alan, and Julia Clark. 2013. "Identification for Development: The Biometrics Revolution." Working Paper 315, Center for Global Development, https:// www.cgdev.org/publication/identification-development- biometrics-revolution-working-paper-315. https://doi.org/ 1 0.2 139/ssrn.2226594 . Gelb, Alan, and Sneha Raghavan. 2014. "Rolling Out the Aadhar." Center for Global Development, March 6. https:// www.cgdev.org/blog/rolling-out-aadhaar. Government of India. 2017. Rashtriya Swasthya Bima Yojana. http://www.rsby.gov.in/ Government of India. Ministry of Health & Family Welfare. 2014. National Health Policy 2015 Draft, http:// www.mohfw.nic.in/showfile.php?lid=3014 Anthropologica 60 (2018) When the Government Changes, the Card Will Also Change / 199 This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms230 Gupta, Akhil. 2012. Red Tape: Bureaucracy , Structural Violence , and Poverty in India. Durham, NC: Duke University Press, https://doi.org/10.1215/9780822394709. Hull, Matthew Sģ 2012. "Documents and Bureaucracy." Annual Review of Anthropology 41(1): 251-267. https://doi.org/ 10.1 146/annurev.anthro.012809.104953. Komarinski, Peer. 2005. Automated Fingerprint Identification Systems (AFIS). Amsterdam: Elsevier Academic. Indian Health Insurance Experiments. 2017. Indian Health Insurance Experiments. University of Chicago, https:// indiahie-sites.uchicago.edu/. Karan, Anup, Wnnie Yip, and Ajay Mahal. 2017. "Extending health insurance to the poor in India: An impact evaluation of Rashtriya Swasthya Bima Yojana on Out of Pocket Spending for Healthcare." Social Science & Medicine 181: 83-92. https://doi.Org/10.1016/i.socscimed.2017.03.053. Kaur, Ravinder, and Thomas Blom Hansen. 2015. "Aesthetics of Arrival: Spectacle, Capital, Novelty in Post-reform India." Identities [Yverdon] 23(3): 265-275. https://doi.org/ 10.1080/1070289X.2015.1034135. Madhukumar, Suwarna, D. Sudeepa, and Vaishali Gaikwad. 2012. "Awareness and Perception Regarding Health Insurance in Bangalore Rural Population." International Journal of Medicine and Public Health 22(2): 18-22. https://doi.org/10.4103/2230-8598.108390. Marx, Gary T. 2015. "Technology and Social Control." In International Encyclopedia of the Social & Behavioral Sciences , 2nd ed., vol. 24, 117-124. Nandi, Arindam, E. Phoebe Holtzman, Anup Malani, and Ramanan Laxminarayan. 2015. "The Need for Better Evidence to Evaluate the Health & Economic Benefits of India's Rashtriya Swasthya Bima Yojana." Indian Journal of Medical Research 142(4): 383-390. https://doi.org/ 10.4103/0971-5916.169194. Narasimhan, H., V. Boddu, P.V. Singh, A. Katyal, S. Bergkvist, and M. Rao. 2014. "The Best Laid Plans: Access to the Rajiv Aarogyasri Community Health Insurance Scheme of Andhra Pradesh." HealtĶ Culture and Society [Pittsburgh, PA] 6(1): 85-97. https://doi.org/10.5195/HCS.2014.163. Organization for Economic Collaboration and Development. 2015. Health al a Glance: OECD Indicators. Paris: OECD Publishing. Palacios, R. 2010. "A New Approach to Providing Health Insurance to the Poor in India: The Early Experience of Rashtriya Swasthya Bima Yojna." RSBY Working Paper 1. http://www.rsby.gov.in/documents.aspx7ID = 14. Peters, David H., Abdo S. Yazbeck, Rashmi R. Sharma, G.N.V. Ramana, Lant H. Pritchett, and Adam Wagstaff. 2002. Better Health Systems for India's Poor. Washington, DC: World Bank, https://doi.org/10.1596/0-8213-5029-3. Philip, Kavita. 2016. "Telling Histories of the Future: The Imaginaries of Indian Technoscience." Identities [Yverdon] 23(3): 276-293. https://doi.org/10.1080/ 1070289X.2015.1034129. Rajasekhar, D., Erlend Berg, Maitreesh Ghatak, R. Manjula, and Sanchari Roy. 2011. "Implementing Health Insurance for the Poor: The Rollout of RSBY in Karnataka." Research Paper, Suntory Centre, Suntory and Toyota International Centres for Economics and Related Disciplines, London School of Economics and Political Science, sticerd.lse.ac.uk/ dps/eopp/eopp25.pdf. Rao, Ursula. 2013. "Biometrie Marginality." Economic and Political Weekly 4813: 71-77. Rao, M. Govinda, and Mita Choudhury. 2012. "Health Care Financing Reforms in India." Working Paper 2012-100, National Institute of Public Finance and Policy, http:// www.nipfp.org.in/media/medialibrary/2013/04/ wp_2012_100.pdf. Reshmi, B., N. Sreekumaran Nair, K. M. Sabu, and B. Unnikrishnan. 2007. "Awareness of Health Insurance in a South Indian Population - A Community-based Study." Health and Population : Perspectives and Issues 30 (3):177-188. doi: 10.4103/0970-0218.69288. Roy, S. 2016. "Angry Citizens: Civic Anger and the Politics of Curative Democracy in India." Identities [Yverdon] 23(3): 362-377. https://doi.org/10.1080/1070289X.2015.1034131. Sengoopta, Chandak. 2004. Imprint of the Raj : How Fingerprinting Was Born in Colonial India. London: Pan Books. Shahrawat, Renu, and Krishna D. Rao. 2011. "Insured Yet Vulnerable: Out-of-Pocket Payments and India's Poor." Health Policy and Planning 27(3): 213-221. https://doi.org/ 10.1093/heapol/czr029. Sharma, Aradhana, and Akhil Gupta. 2006. "Introduction: Rethinking Theories of the State in an Age of Globalization." In The Anthropology of the State: A Reader , ed. Aradhana Sharma and Akhil Gupta, 1-42. Oxford: Blackwell. https://doi.Org/10.1385/CBB:44:01. Srivastava, Sanjay. 2012. "Duplicity, Intimacy, Community: An Ethnography of ID cards, Permits and Other Fake Documents in Delhi." Thesis Eleven 1131: 78-93. https:// doi.org/10.1177/0725513612456686. Sun, Changqing. 2011. "An Analysis of RSBY Enrolment Patterns: Preliminary Evidence and Lessons from the Early Experience." In India's Health Insurance Scheme for the Poor : Evidence from the Early Experience of the Rashtriya Siuasthya Bima Yojana , ed. Robert Palacios, Jishnu Das, and Changqing Sun. New Delhi: Centre for Policy Research. Swarup, Anil. 2013a. "Interview with Anil Swarup on India's RSBY scheme." YouTube video, 3:04, posted by Social Protection Floor in Asia, 18 March 2014. https:// www.youtube.com/watch7v = KY 1 k5d6FG2o& t = 9s. Swarup, A. 2013b. "Smart card system of India's RSBY scheme." YouTube video, 6:42, posted by Social Protection Floor in Asia, 18 March 2014. https://www.youtube.com/ watch?v=fm5FmLLKwQo Weber, Max. 1978. Economy and Society: An Outline of Interpretive Sociology. Berkeley: University of California Press. 200 / Stefan Ecks Anthropologica 60 (2018) This content downloaded from 49.37.163.160 on Mon, 06 Jan 2025 15:35:35 UTC All use subject to https://about.jstor.org/terms231b2:T1bd1, C A R E N E S T One platform to manage the complete care journey of your dependents Abhyuday Singh0243/62 Group 5 Mayank Raj Kankas0280/62 Vaibhav Kamble0314/62 Nikhil Yadav0202/62 Siddharth Dewangan0225/62 THE PROBLEM Critical care information is scattered everywhere. Working parents in metro cities increasingly rely on nannies, daycare centers, grandparents, or pet sitters to care for their children or pets. However, daily health updates, prescriptions, vaccinations, appointments, and shopping are managed across multiple disconnected channels, making it difficult to monitor overall wellbeing. Parents switch between 5-6 different platforms to manage one dependent. WhatsAppNotebooksHospital Pharmacy appsReminders Verbal updates Everyone solves one piece. Nobody owns the loop. AppStrengthGap PractoDoctor discovery & bookingNo nutrition, caregiver layer or commerce Apollo 24/7Healthcare services & pharmacyNo preventive care or caregiver layer FirstCryChild products & commerceCommerce only - no health management Supertails / HUFTPet products & healthcarePet-only, no unified family care BabyChakraParenting content & doctor discoveryNo caregiver updates or unified records Google Cal / RemindersScheduling remindersNo records, nutrition or care ecosystem Market Gap: No single platform connects caregivers ↔ tracking ↔ preventive care ↔ appointments ↔ commerce for children & pets. BUSINESS CASE 20M+ urban working parents with daily care-dependency gaps No unified app connecting caregivers ↔ parents ↔ doctors Pet ownership growing 35% YoY with zero care- management app Commission from doctors on bookings & labs App Development maintaining and developing cost of the app Commerce Medicines, supplements, food Marketing and customer acquisition cost Subscription providing advanced insights and data Data Security and compliance cost to maintain privacy Caregiver Collaboration Nannies, grandparents & daycare update via text, voice or image - no app download. AI Preventive Care Tracks nutrition, growth, vaccinations & records; flags deficiencies early. Unified Health Timeline All prescriptions, vaccinations, appointments & care logs in one record. Smart Care Commerce Predicts refills from consumption; one-click ordering for meds & food. The Opportunity Cost Drivers Revenue Drivers Prospective Solution Stakeholders Caregivers Healthcare Providers Pharmacies & Brands Parents Nannies, grandparents, etc. updating the daily activities, meals, medications, etc. Doctors, vaccination clinics, etc. managing appointments and digital prescriptions Medicine suppliers, nutrition brands, baby-care providing products & services on platform Monitor daily care, health records, nutrition, appointments, etc. TARGET PERSONAS Who we're building for. Priya, 34 Product Manager Mumbai GOALS Track child's daily care Never miss vaccinations Store all health records PAIN POINTS No visibility into nanny updates Health records across multiple apps Misses medicine refills OPPORTUNITY A unified platform providing caregiver updates, nutrition tracking, digital medical records, appointment booking and automatic refill reminders gives Priya complete visibility into her child's health while saving time and reducing anxiety. Savita, 50 Full-time Nanny Delhi GOALS Update parents easily Follow care routine accurately Reduce repeated calls PAIN POINTS No structured logging Tracks everything manually Frequent parent follow-ups OPPORTUNITY A simple interface with one-tap logging, voice input, photo uploads and reminders enables caregivers to update parents effortlessly while improving trust and reducing communication gaps. Rahul, 42 Finance Director Bangalore GOALS Keep pet healthy Track treatments & vaccinations Manage pet care easily PAIN POINTS Misses flea/deworming schedules No digital vet records Forgets food & medicine refills OPPORTUNITY A single platform that helps Rahul manage his pet's health through digital records, timely reminders, AI-powered care insights, and hassle-free vet appointments. SCOPE OF MVP CategoriesPain PointsPossible Solutions (MVP) Child Care Management (Phase 1) Lack of visibility into meals, medicines and daily activities when children are looked after by nannies, grandparents or daycare. Caregiver Dashboard enabling caregivers to log meals, medicines, sleep and activities, with real-time updates to parents. Difficulty tracking nutrition, growth milestones and identifying nutritional deficiencies. Smart Nutrition Dashboard that tracks daily intake against recommended nutrition based on age, weight and growth stage, with AI-powered recommendations. Missing vaccination schedules, routine health check-ups and losing physical prescriptions. Healthcare Manager for vaccination reminders, appointment booking and secure digital storage of prescriptions and medical history. Running out of medicines, supplements or baby products due to manual tracking. Smart Refill & Commerce Engine that predicts refill dates, sends reminders and enables one-click purchase of recommended products. Pet Care Management (Phase 2) Pet owners struggle to monitor feeding schedules, medications and daily activities when pets are cared for by pet sitters, house help or boarding facilities. Pet Care Tracker allowing caregivers to update feeding, medicines, walks and activities with live visibility for owners. Difficulty maintaining vaccination records, deworming schedules and veterinary visits. Pet Health Manager with vaccination reminders, vet appointment booking and digital health records. Uncertainty about breed-specific nutrition and timely replenishment of pet food or supplements. AI Nutrition & Refill Assistant that recommends breed- and age-specific nutrition, predicts refill requirements and enables in-app purchases. Delayed detection of health issues due to lack of continuous monitoring. AI Preventive Health Insights that analyze nutrition, weight and medical history to identify potential deficiencies or health risks and recommend timely action. Identifying & Mapping Pain Points to Solutions Embedded in MVP The following table outlines the key challenges faced by working parents (our primary stakeholders) in managing the health and well-being of their children and pets. The proposed MVP focuses on addressing these pain points through a unified care management platform. Daily Care Tracking Daily Active Caregivers (%) Daily Care Update Completion Rate Parent Dashboard Engagement SUCCESS METRICS Healthcare Management Vaccination Reminder Completion Rate Doctor/Veterinarian Appointment Booking Rate Digital Prescription Upload Rate Nutrition & Preventive Care Nutrition Dashboard Adoption Rate AI Recommendation Acceptance Rate Growth Milestone Tracking Completion Commerce & Refill Management Refill Reminder Conversion Rate Repeat Purchase Rate Average Order Value (AOV) Overall Product Success Weekly Active Users (WAU) 30-Day User Retention Rate Net Promoter Score (NPS) North Star - Number of profiles where at least one meaningful care activity is completed each week. T H A N K Y O Ub3:T1f79,I need to put together a strategic advisory document covering the pivot assessment, business model refinement, financial projections, collaboration approach, user acquisition targets, and impact metrics—plus prepare key questions for the professor. The core decision here is whether the ASHA worker pivot is the right direction, and while there's merit to targeting that B2G market segment, I'm sensing this needs more nuance in how I frame it. The ASHA worker angle has real constraints: government procurement timelines are brutal, the market is already saturated with competing apps, and there's minimal willingness to pay from the workers themselves. More critically, pivoting entirely to ASHA workers abandons the original insight about structured caregiver-to-parent coordination—that's not a pivot, that's a complete direction change. The professor's feedback about partnering with daycare centers is actually pointing toward a much stronger wedge: B2B2C through creches where the daycare operator is the payer, the staff are already trained and incentivized to log activities, and parents are already paying ₹8-20k monthly. The real innovation here is building a verified, longitudinal care record linked to the child's health identifier—something that creates defensibility and genuine value across the ecosystem. I'm framing this as a phased approach: private daycare as the immediate MVP with clear revenue potential, while positioning the public health system angle (Anganwadi/ASHA/ABDM integration) as a later horizon that aligns with the course material without overcomplicating the initial go-to-market. Now I'm sizing the organized daycare market in India—looking at the current market value, growth rates, and the landscape of existing players to ground the opportunity. For the bottom-up calculation, I'm targeting 8,000 full-day daycare centres across the top 8 cities with an average of 40 children per centre. The pricing model stacks a SaaS fee of ₹100 per child monthly (or ₹4,000 per centre) plus a parent premium tier at ₹149/month for health records and Care+, with commerce and referrals as later revenue streams. Year 1 projects 150 centres serving 6,000 children, generating roughly ₹85 lakhs in annual revenue from the combination of centre SaaS fees and parent premium attach rates. Scaling forward, Year 2 targets 900 centres with 36,000 children, pushing revenue to around ₹6 crores when factoring in higher premium adoption, provider commissions, and lab/vaccination referrals. By Year 3, I'm modeling 3,000 centres with 120,000 children and revenue approaching ₹28-29 crores, with diversified streams including premium subscriptions, services, commerce, and B2B channels like corporate childcare benefits and insurance partnerships—bringing the per-child annual value to roughly ₹2,400. There's also a corporate employer channel emerging as an additional growth vector. The regulatory angle is compelling: the Maternity Benefit Act amendment mandates crèches for companies with 50+ employees, creating compliance-driven demand and a built-in payer base. This is a strong wedge because employers need both the facility and defensible care records for liability and POSH compliance. Beyond that, daycare centres face a trust crisis from viral abuse incidents, so parents demand transparency and centres need evidence trails—positioning the product as "trust infrastructure" with tamper-evident care logs that protect both sides. The real defensibility comes from building multiple moats: centre-side workflow ownership (staff rosters, attendance, incidents, compliance) creates switching costs; longitudinal, structured daily child data (nutrition, sleep, mood, milestones) that nobody else has enables predictive risk models that improve with scale; and becoming the de-facto compliance format for employer crèches while integrating with ABDM/ABHA standards to create portable health records. ABDM certification itself is a verifiable, defensible milestone that locks in regulatory credibility. The habit loop works through external triggers (6pm day summaries) and internal ones (parental anxiety about what happened), with caregivers logging in under 20 seconds as part of their mandated compliance routine rather than extra work. Parents get variable rewards through photos, milestone cards, and nutrition insights that change based on the child's actual day, while their invested preferences and health data make tomorrow's logs more valuable—creating a growing record that's hard to abandon. The centre-side mandate ensures daily active usage since logging is compliance-driven, not optional. The key metric I'm defining is Weekly Closed Care Loops—a care event that gets logged by a caregiver, viewed by a parent within 24 hours, and triggers at least one downstream action like a reply or task. Targeting 3 per child per week with 60% of active children hitting at least 2 directly addresses the professor's point about repeated coordination rather than isolated app interactions. Now I need to nail down the assumptions with explicit validation methods and kill criteria—the expert judge will want to see where we'd pull the plug. The MVP is stripped down to four core pieces: a caregiver logging app built for tablets with offline capability, a parent digest through WhatsApp plus a lightweight web interface, a centre console for attendance and compliance tracking, and a child health record covering growth charts and vaccination schedules. Everything else—pets, commerce, doctor booking—stays out of scope for now. I'm planning five key experiments to test where the real traction is: testing distribution channels (direct-to-centre versus employer-sponsored versus preschool chains), comparing how caregivers input data (structured taps versus voice notes versus photos), measuring which parent notification channel drives engagement (WhatsApp versus app push), running pricing models (centre-paid, parent-paid, or employer-paid), and testing messaging frames around transparency versus child health records. The big risk is navigating privacy and consent requirements under the DPDP Act for minors—I need verifiable parental consent locked in from the start. Beyond that, there's caregiver pushback on surveillance, centre churn, liability concerns, and low willingness to pay. The Anganwadi and public sector path adds political complexity. But looking at global precedent, Brightwheel in the US validates this model at scale (~$600M+ valuation), which de-risks feasibility and answers the innovation question: the model works abroad, it's unbuilt in India, and the India-specific layer—ABDM-linked portable health records plus compliance—is genuinely novel. For go-to-market, I'm starting with design partners: ten centres across Pune and Bangalore. Starting with free co-builds over eight weeks, then scaling to 150 centres across two cities with founder-led sales and two chain headquarters deals, using a compliance reporting tool as the wedge. From there, moving into chain partnerships through franchise networks like Footprints and Hello Kids, employer benefits via HR aggregators, and pediatrician co-marketing. The longer-term play opens up parent-side monetization, marketplace features, ABDM integration, and public system pilots with state ICDS and Anganwadi systems. The impact metrics I'm tracking are children screened, growth faltering flagged, vaccination timeliness improvements of around 12-18 percentage points, caregiver time saved, parental anxiety reduction on validated scales, and reach into public systems at scale. I need to organize my questions for the professor into buckets: pivot validation, health systems framing, ABDM and data considerations, the public versus private path, metrics, go-to-market, and submission expectations. I should also lead with a clear verdict on whether the ASHA pivot is the right move. Now I'm building out the document using Python and the docx library to structure everything properly.b4:T1c57,I'm starting to build out the generation script with helper functions for formatting different content types like headings, paragraphs, and tables. The document structure will flow from a cover page through an explanation of how to read it, then into Part A analyzing the ASHA pivot decision with decoded feedback and a scoring evaluation, followed by Part B. For Part B, I'm repositioning CareNest as "the operating system for supervised childcare" — keeping the name but clarifying what we're actually building, what we're removing, and the four-layer innovation stack that differentiates us from just cloning Brightwheel for India. Then I'll move through Parts C through I covering defensibility and moats, market sizing with honest filters, refined personas across centre owners, caregivers, parents, and HR buyers, an assumptions register with kill criteria, MVP scope with experiments, the hook framework and JTBD redefinition around weekly closed care loops, and key metrics. Parts J through O lay out the revenue model with pricing locked in, financial projections, impact across child health and public systems, risks including DPDP compliance and surveillance concerns, go-to-market phases, the 15-slide deck skeleton, and questions for the professor. Now I'm locking down the financial model — starting with pricing tiers for centre SaaS at ₹99 per child monthly with a ₹2,999 floor, and a Care+ tier for parents. For Year 1, I'm modeling 180 centres with an average of 42 children each, which gives me 7,560 children. The centre SaaS revenue works out to roughly ₹67L when accounting for a 9-month ramp, though I'll simplify the presentation to focus on exit ARR and recognized revenue rather than getting bogged down in monthly calculations. Now I'm working through the full Year 1 exit ARR picture: the centre SaaS component hits ₹0.90 Cr, Care+ attachment at 12% adds ₹16.2L, employer sites contribute ₹2L, and services bring in ₹5L, putting total exit ARR around ₹1.13 Cr with recognized revenue of approximately ₹0.55 Cr. Moving into Year 2, I'm scaling to 1,100 centres and 46,200 children. The centre SaaS ARR jumps to ₹5.49 Cr, Care+ attachment improves to 18% generating ₹1.49 Cr, employer sites expand to 60 locations for ₹15L, and services continue scaling. By Year 3, I'm projecting 3,200 centres with 134,400 children. Centre SaaS reaches ₹15.96 Cr, Care+ at 22% penetration generates ₹5.91 Cr, employer sites grow to 220 for ₹0.66 Cr, services scale to ₹3.36 Cr, and I'm adding marketplace and commerce revenue of ₹1.6 Cr, bringing total exit ARR to approximately ₹27.5 Cr with recognized revenue around ₹17.5 Cr. Now I'm breaking down the unit economics per centre assuming 42 children, starting with calculating the ARPA from the centre subscription. Looking at the revenue per centre, I'm getting roughly ₹50k annually from the core SaaS, plus another ₹13.5k from parent Care+ adoption at 18%, and ₹5k from services, totaling about ₹68k per centre per year. My CAC varies by channel—founder-led at ₹8k, inside sales at ₹18k, and through chain HQs at ₹4k—blending to ₹15k. With gross margins around 78%, the payback period works out to about 3.4 months, which is strong. Centre churn sits at 2% monthly or roughly 22% annually, giving me a lifetime value of about 4 years. Now I'm calculating LTV/CAC more conservatively. Using a 3-year horizon instead of the optimistic 4.2 years, I get ₹1.59L lifetime value divided by ₹15k CAC, which is roughly 10x—still healthy even after accounting for support costs and net revenue churn, so I'm comfortable saying 6-8x on the conservative end. By year 3, I'm projecting 134,400 children across 3,200 centres with about 215,000 parents and 11,000 staff members, scaling toward a year 5 ambition of 12 million users. For the market sizing, I'm working through TAM, SAM, and SOM with explicit assumptions flagged for validation. The organized daycare and preschool market in India spans roughly 55,000 centres serving 2.5 million children, which at blended ARPU of ₹4,500 per child annually gives me a ₹1,100 crore software and services TAM. My SAM is tighter—just the top 12 cities with branded or franchise centres, about 18,000 facilities and 810,000 children worth ₹365 crore. My 3-year SOM targets 3,200 centres (17.8% of SAM) generating ₹27.5 crore ARR. I need to validate each of these numbers through centre calls, franchise disclosure documents, and market reports like ProEves or Redseer. I'm also building out the funnel explicitly—starting from 20 million working parents and filtering down through the addressable segments. expanding the addressable market to top 20 cities with 60% digital adoption gives me 480k reachable children, and targeting 118k by year 3 across 2,800 centres brings the penetration down to 25%, which feels more realistic for a category entrant. Now I'm recalculating the year 3 financials with this cohort—the SaaS revenue from centre subscriptions, Care+ adoption at 22%, employer partnerships, and per-child service fees stack up to roughly ₹24.1Cr in exit ARR with ₹15.5Cr recognized, which validates the model. For year 2, I'm working through the intermediate milestone of 950 centres serving about 40k children to trace the revenue build. On the impact side, I'm looking at what 118,000 children means in practice—flagging growth faltering cases early, improving vaccination compliance across the network, and the time savings for staff. The real opportunity emerges in Horizon 3 when this integrates with the broader Poshan Tracker ecosystem and ICDS infrastructure, potentially reaching 1.39M Anganwadi centres through district pilots. For positioning, I need to crystallize what we actually own: the ability to design workflows that work for low-literacy frontline staff, the trust and compliance layer we've built, and our health data interoperability capability through ABDM. The unfair advantage comes from our design-partner network across centres, pediatrician advisory board, and the proprietary care-log ontology we've developed. I'm mapping out the competitive landscape—Illumine focuses on billing and ops for preschools, Brightwheel and Procare are US-based, then there's Klay, Footprints, Practo, Apollo, and the reality that many centres still rely on WhatsApp and Poshan Tracker. The key insight is that our primary payer is the institution itself, not consumer insurance or teleconsult adoption, which sidesteps the penetration challenges others face. Now I'm structuring the professor's questions into seven buckets and planning a 10-minute presentation with 15 slides and timing. I want to weave in the frameworks from the course explicitly—JTBD statements, a working-backwards press release, RICE prioritization for MVP features, a 2x2 positioning map, HEART metrics, and the ethical design angle with DPDP principles. I'll also map out a swim lane showing what a care day looks like operationally, which ties back to session 17. I'll save the full script to the public folder so it's downloadable, keeping the formatting clean with proper headings, bullets, and tables styled consistently. Writing the script now...4b:["$","$L93",null,{"params":{"chatId":"lAblOd60G0T"},"promises":{"attributes":"$@9d","externalMeta":"$@9e","latest":"$@9f","messagesRange":"$@a0","messages":"$@a1","template":"$@a2","gitStatus":"$@a3"},"children":["$","$La4",null,{"chatId":"lAblOd60G0T","children":["$","$La5",null,{"seedOnlyKeys":["@\"chat:state\",\"lAblOd60G0T\","],"data":{"block:output:initial":null,"/chat/api/snapshots/proxy?chatId=lAblOd60G0T&messageId=Xbdn8EWDQUJsM0W22gEM5SBOR96sX5jC&v=v2":null,"@\"block:mappings\",\"lAblOd60G0T\",":{"sqlBlockExecutionStates":"$Qa6","blocksForkedFrom":"$Qa7","blocksTemplateIds":"$Qa8","blocksCreatedAt":"$Qa9","blocksShared":"$Qaa","blocksDeployed":"$Qab","blocksSubdomains":"$Qac","brandedBlocks":"$Qad","unlistedBlocks":"$Qae","blockOutputs":"$Qaf"},"@\"chat:state\",\"lAblOd60G0T\",":{"messages":[{"content":{"type":"parts","parts":[{"type":"mdx","content":"for the hight tech product manager, we were awarded with the project where we have to submit \"· Problem (re-)framing (detailing, elaborating) \n· Business Case\n· Target Persona \n· Scope of MVP\n· Success Metrics (target)\" for the interim submission\"\n\nThe idea has to be innovative (something that is not in the market), while also feasible, an industry expert who have made 3 apps successful from 0 is going to judge us and question the feasibility.\n\nFor interim round (holds 15 marks) this"},{"type":"attachment","url":"https://hebbkx1anhila5yf.public.blob.vercel-storage.com/CARENEST-wZOTf8KjChcTwqzKe5oCclzsYqsMqw.pdf","name":"CARENEST.pdf","contentType":"application/pdf","size":4069974},{"type":"mdx","content":"$b0"},{"type":"attachment","url":"https://hebbkx1anhila5yf.public.blob.vercel-storage.com/%5BPasted%20113%20lines%5D-rKnOycG2aMashIXFIPzrqYg7skz7Yg","name":"[Pasted 113 lines]","contentType":"text/plain","size":7512},{"type":"mdx","content":"\"\n\nNow for this we are thinking of meeting with a professor who have worked in the similar domain, and have written this course material"},{"type":"attachment","url":"https://hebbkx1anhila5yf.public.blob.vercel-storage.com/HiDA_2026-2027%20-%20Carolyn%20Tauro%20-%20Course%20Material_2-PIVAAJEvyAVyh5jvRFgee0if8P9OMH.pdf","name":"HiDA_2026-2027 - Carolyn Tauro - Course Material_2.pdf","contentType":"application/pdf","size":19631361},{"type":"mdx","content":"\n\nNow 1st of all how to make our idea innovative such that it is unique, we have a core competency and the competitive advantage in which no one can beat us, what would be our revenue model, how much would be our revenue, what are the steps for the collaboration, what would be the number of users, and what would be the impact without deviating far from original idea.\n\nBased on all this create a microsoft document docx.\n\nalso suggest what questions we can ask to the professor to whom we are meeting."}],"version":1},"role":"user","id":"7WBTxMbZUzyVR6H0f5fosgbnBKRPjgtL","attachments":[{"url":"https://hebbkx1anhila5yf.public.blob.vercel-storage.com/HiDA_2026-2027%20-%20Carolyn%20Tauro%20-%20Course%20Material_2-PIVAAJEvyAVyh5jvRFgee0if8P9OMH.pdf","name":"HiDA_2026-2027 - Carolyn Tauro - Course Material_2.pdf","size":19631361,"content":"$b1","contentType":"application/pdf"},{"url":"https://hebbkx1anhila5yf.public.blob.vercel-storage.com/%5BPasted%20113%20lines%5D-rKnOycG2aMashIXFIPzrqYg7skz7Yg","name":"[Pasted 113 lines]","size":7512,"contentType":"text/plain"},{"url":"https://hebbkx1anhila5yf.public.blob.vercel-storage.com/CARENEST-wZOTf8KjChcTwqzKe5oCclzsYqsMqw.pdf","name":"CARENEST.pdf","size":4069974,"content":"$b2","contentType":"application/pdf"}],"type":"message","authorId":"kuvQF5F3HvZCAJ2vcuu0siKg","createdAt":"$D2026-08-05T06:17:44.152Z"},{"v0ModelId":"v0-opus-5","content":{"type":"message-binary-format","value":[[0,[["AssistantMessageContentPart",{"part":{"createdAt":1785910664684,"finishedAt":1785910664684,"lastPartSentAt":1785910664684,"id":"XzetKfaGEsREk2EX","type":"task-start-v1","parts":[{"type":"launch-tasks"}]}}],["AssistantMessageContentPart",{"part":{"type":"task-grouped-tasks-v1","id":"OcXIxCKj3F98QFVa-1j9BpwvFRaXSwZm4-LURemg6jhzCu68kr","parts":[{"createdAt":1785910664684,"finishedAt":1785910665422,"lastPartSentAt":null,"taskNameActive":"Reading HiDA_2026-2027---Carolyn-Tauro---Course-Material_2.pdf","taskNameComplete":"Read HiDA_2026-2027---Carolyn-Tauro---Course-Material_2.pdf","toolCallId":"tool_Qt1Si65ZpNs0aCv3","agentTurnId":"turn_1DfWvDtR5islFQZ9","filePath":null,"id":"OcXIxCKj3F98QFVa","type":"task-read-file-v1","parts":[]},{"createdAt":1785910664684,"finishedAt":1785910665416,"lastPartSentAt":1785910665392,"taskNameActive":"Reading CARENEST.pdf","taskNameComplete":"Read CARENEST.pdf","toolCallId":"tool_q0yocbA3mZQJwbo6","agentTurnId":"turn_1DfWvDtR5islFQZ9","filePath":null,"id":"1j9BpwvFRaXSwZm4","type":"task-read-file-v1","parts":[{"type":"reading-file","filePath":"user_read_only_context/text_attachments/CARENEST-wZOTf.pdf"}]},{"createdAt":1785910664684,"finishedAt":1785910665411,"lastPartSentAt":1785910665387,"taskNameActive":"Reading [Pasted-113-lines]","taskNameComplete":"Read [Pasted-113-lines]","toolCallId":"tool_VeZPjzu6SD5EFzSl","agentTurnId":"turn_1DfWvDtR5islFQZ9","filePath":null,"id":"LURemg6jhzCu68kr","type":"task-read-file-v1","parts":[{"type":"reading-file","filePath":"user_read_only_context/text_attachments/[Pasted-113-lines]-rKnOy"}]}],"createdAt":0,"finishedAt":1,"lastPartSentAt":1,"taskNameActive":"Explore • 3 Files","taskNameComplete":"Explore • 3 Files"},"id":"OcXIxCKj3F98QFVa-1j9BpwvFRaXSwZm4-LURemg6jhzCu68kr"}],["AssistantMessageContentPart",{"part":{"createdAt":1785910672692,"finishedAt":1785910740054,"lastPartSentAt":1785910740054,"taskNameActive":null,"id":"l81GThhqOOyhzIQs","type":"task-thinking-v1","parts":[{"type":"thinking-end","duration":67,"thought":"$b3"}]}}],["AssistantMessageContentPart",{"part":{"createdAt":1785910740223,"finishedAt":1785910745282,"lastPartSentAt":1785910744472,"taskNameActive":"Checking docx tooling","taskNameComplete":"Checked docx tooling","toolCallId":"toolu_01Xy35Ke3FgoyfCczYRudBKY","agentTurnId":"turn_1DfWvDtR5islFQZ9","filePath":null,"id":"dvzHmEDDPTNaJ70a","type":"task-subtask-v1","parts":[{"type":"subtask-started","data":{"subtaskType":"bash","command":"python3 -c \"import docx; print(docx.__version__ if hasattr(docx,'__version__') else 'ok')\" 2>&1 | head -3; echo \"---\"; python3 --version; echo \"---\"; ls /vercel/share/v0-project | head -30"}},{"type":"subtask-log","data":{"logType":"created-terminal"},"id":"jKG8ZaYecsNRVe6j"},{"type":"subtask-log","data":{"logType":"poll-terminal-output","delta":"Traceback (most recent call last):\n File \"\", line 1, in \n import docx; print(docx.__version__ if hasattr(docx,'__version__') else 'ok')\n---\nPython 3.13.11\n---\napp\ncomponents\ncomponents.json\nlib\nnext-env.d.ts\nnext.config.mjs\nnode_m"},"id":"F2h8utNBw4vm2szw"},{"type":"subtask-log","data":{"logType":"poll-terminal-output","delta":"odules\npackage.json\npnpm-lock.yaml\npostcss.config.mjs\npublic\ntsconfig.json\n"},"id":"4LfyQPvQDXSbk2Ya"}]}}],["AssistantMessageContentPart",{"part":{"createdAt":1785910750619,"finishedAt":1785910752758,"lastPartSentAt":1785910752341,"taskNameActive":"Installing python-docx","taskNameComplete":"Installed python-docx","toolCallId":"toolu_01VJbTi3e5H2jVS9AvctwUTC","agentTurnId":"turn_RUgI9kYFDKV1lQls","filePath":null,"id":"rju1lV4cj8xnxLHn","type":"task-subtask-v1","parts":[{"type":"subtask-started","data":{"subtaskType":"bash","command":"cd /vercel/share/v0-project && (pip3 install python-docx --quiet 2>&1 | tail -3 || pip3 install python-docx --break-system-packages --quiet 2>&1 | tail -3); python3 -c \"import docx; print('docx ready')\""}},{"type":"subtask-log","data":{"logType":"created-terminal"},"id":"FREKXNDktmV9c0Cj"},{"type":"subtask-log","data":{"logType":"poll-terminal-output","delta":"error: No virtual environment found; run `uv venv` to create an environment, or pass `--system` to install into a non-virtual environment\n\nTraceback (most recent call last):\n File \"\", line 1, in \n import docx; print('docx ready')\n ^^^^^^^^^^^\nModuleNotFoundError: No module named 'docx'\n"},"id":"J4kuhdKoLuTYy8Zj"}]}}],["AssistantMessageContentPart",{"part":{"createdAt":1785910756117,"finishedAt":1785910758707,"lastPartSentAt":1785910758217,"taskNameActive":"Installing python-docx","taskNameComplete":"Installed python-docx","toolCallId":"toolu_019Rs8ChCSrpdYSCkoCY6fyD","agentTurnId":"turn_L5vix8wOYM4DSU8a","filePath":null,"id":"ChxXoOf16uwnKBbN","type":"task-subtask-v1","parts":[{"type":"subtask-started","data":{"subtaskType":"bash","command":"cd /vercel/share/v0-project && pip3 install --system python-docx --quiet 2>&1 | tail -3; python3 -c \"import docx; print('docx ready')\""}},{"type":"subtask-log","data":{"logType":"created-terminal"},"id":"IIblibaeECn6WJzf"},{"type":"subtask-log","data":{"logType":"poll-terminal-output","delta":"\nTraceback (most recent call last):\n File \"\", line 1, in \n import docx; print('docx ready')\n ^^^^^^^^^^^\nModuleNotFoundError: No module named 'docx'\n"},"id":"IdoV7NLwPCNqPMdJ"}]}}],["AssistantMessageContentPart",{"part":{"createdAt":1785910763492,"finishedAt":1785910768595,"lastPartSentAt":1785910768030,"taskNameActive":"Setting up venv","taskNameComplete":"Set up venv","toolCallId":"toolu_01HzpLN7pcvffiYZhdJCVhMi","agentTurnId":"turn_m2bThTJMzGNFFWfg","filePath":null,"id":"hfeD6iCoZ6YvTx5w","type":"task-subtask-v1","parts":[{"type":"subtask-started","data":{"subtaskType":"bash","command":"cd /tmp && (uv venv .dv 2>&1 | tail -2) && .dv/bin/python -m ensurepip 2>/dev/null | tail -1; uv pip install --python /tmp/.dv/bin/python python-docx 2>&1 | tail -3; /tmp/.dv/bin/python -c \"import docx; print('docx ready')\""}},{"type":"subtask-log","data":{"logType":"created-terminal"},"id":"PHjNagpUMAYIL0Jp"},{"type":"subtask-log","data":{"logType":"poll-terminal-output","delta":"Creating virtual environment at: .dv\nActivate with: source .dv/bin/activate\n"},"id":"DwKRiRlO2sXGlHu9"},{"type":"subtask-log","data":{"logType":"poll-terminal-output","delta":"Successfully installed pip-25.3\n + lxml==6.1.1\n + python-docx==1.2.0\n + typing-extensions==4.16.0\ndocx ready\n"},"id":"Hn27YamgkDVRsTgp"}]}}],["AssistantMessageContentPart",{"part":{"createdAt":1785910774574,"finishedAt":1785910841294,"lastPartSentAt":1785910841294,"taskNameActive":null,"id":"QW40PAVOdT7knkG3","type":"task-thinking-v1","parts":[{"type":"thinking-end","duration":67,"thought":"$b4"}]}}],["p",{},["text",{},"Now I'll build the strategy document."]],["AssistantMessageContentPart",{"part":{"type":"task-coding-v1","id":"block-b_zONYToqTb6p","parts":[{"type":"code-project","isVersioned":true,"isSourceless":false,"changedFiles":[],"source":"[V0_FILE]py:file=\"/tmp/build_doc.py\" \n...","latestDeploymentInfo":"$ab:0:1","lastDeployedAt":"2026-08-05T06:29:53.495Z","sourceVersionKey":"v_1_s7j1a_s3","needsBlockSource":false,"isAllImages":false,"blockId":"b_zONYToqTb6p","meta":{"taskNameActive":"Making changes","taskNameComplete":"Made some changes","type":"code-project","id":"Code"},"closed":true,"lang":"typescriptreact"}],"createdAt":0,"finishedAt":1,"lastPartSentAt":1,"taskNameActive":"Making changes","taskNameComplete":"Made some changes"},"id":"block-b_zONYToqTb6p"}],["AssistantMessageContentPart",{"part":{"createdAt":1785911387818,"finishedAt":1785911387818,"lastPartSentAt":1785911387818,"id":"hjCzqJhhKDvUGHrW","type":"task-stopped-v1","parts":[{"type":"agent-timeout","willContinueAfterTimeout":true}]}}]]],[1,{}]]},"context":[],"isContentLoading":false,"role":"assistant","id":"Xbdn8EWDQUJsM0W22gEM5SBOR96sX5jC","gitRevision":{"headSha":"981d492b22cedc4a3a38d4652d4136428e21aeb5","readyAt":"2026-08-05T06:29:53.454Z","version":1},"streaming":false,"finishReason":"tool-calls","parentId":"7WBTxMbZUzyVR6H0f5fosgbnBKRPjgtL","type":"message","creditCost":1.585989,"workMetrics":{"diffMap":{},"linesRead":353,"agentActions":8},"createdAt":"$D2026-08-05T06:17:44.153Z","updatedAt":"$D2026-08-05T06:29:53.480Z"}],"lastSyncedAt":1787789771538,"undo":null,"activeForkKey":["7WBTxMbZUzyVR6H0f5fosgbnBKRPjgtL","Xbdn8EWDQUJsM0W22gEM5SBOR96sX5jC"],"lifecycle":{"phase":"idle","persistence":"persisted"},"isAuthor":false,"isRestoring":false,"hashMessageId":null},"@\"active-block\",\"lAblOd60G0T\",":null,"@\"chat:meta\",\"lAblOd60G0T\",":{"title":"ASHA workflow platform","authorId":"kuvQF5F3HvZCAJ2vcuu0siKg","ownerId":"team_brG2lZVpF5zHOKMuTw1oOqqz","storageEntityType":"v0-git-s3-storage","storageEntityId":"v0-1-team_brG2lZVpF5zHOKMuTw1oOqqz-lAblOd60G0T","tailwindV4Default":true,"vercelProjectId":null,"canWriteToChat":false,"nextVersionDefault":16},"@\"chat:vm-mode\",\"lAblOd60G0T\",":true,"@\"chat:vercel-project\",\"lAblOd60G0T\",":"$@b5","@\"team:sensitive-environment-variable-policy\",\"lAblOd60G0T\",":"$@b6","@\"block-view\",\"lAblOd60G0T\",":true,"integrations:figma":"$@b7"},"children":["$Lb8","$Lb9","$Lba","$Lbb"]}]}]}]