This essay is part of the series: World Health Day 2026: Standing with Science in an Age of Shared Risk
The theme for the 2026 World Health Day, “Together for Health, Stand with Science”, highlights the importance of scientific collaboration in protecting the health of people, animals, plants, and ecosystems through the ‘One Health’ approach. In an era defined by zoonotic spillovers, climate-driven disease shifts, and ecological disruption, artificial intelligence (AI) offers powerful tools to advance this agenda by enabling earlier detection of emerging health threats. For countries like India, where dense human populations coexist with large livestock systems and rich biodiversity, operationalising the One Health approach through data-driven systems is particularly critical. By analysing large and diverse datasets, AI can improve predictive epidemiology, strengthen biosurveillance, and support more coordinated public health responses. This piece explores how AI can help operationalise the One Health agenda and assesses India’s evolving efforts to integrate AI into its public health ecosystem.
AI and the One Health Framework
Put simply, One Health is an integrated framework that recognises the interconnectedness of human, animal, and environmental health and calls for coordinated governance across these domains. The approach has gained renewed urgency following the COVID-19 pandemic, which exposed the limitations of fragmented disease surveillance systems. AI is central to advancing this agenda, as its diverse applications enable more integrated and data-driven health surveillance and response systems. In healthcare systems, AI already supports diagnostics, clinical decision-making, patient monitoring, and hospital administration. However, its potential extends beyond traditional healthcare and is particularly relevant to operationalising the One Health agenda.
AI can also strengthen predictive epidemiology by analysing environmental and ecological data, including climate patterns, land-use change, and animal movement, to forecast where zoonotic spillovers are most likely to occur.
AI can enable integrated biosurveillance by analysing data from hospitals, livestock monitoring systems, wildlife surveillance networks, and environmental sensors. By identifying unusual patterns across these datasets, machine learning models can provide early warnings of emerging outbreaks that traditional surveillance systems may miss. AI can also strengthen predictive epidemiology by analysing environmental and ecological data, including climate patterns, land-use change, and animal movement, to forecast where zoonotic spillovers are most likely to occur.
In addition, computer vision systems are increasingly used to detect plant diseases, analyse veterinary imaging, and support clinical diagnostics in human medicine. Such tools could enable more integrated disease monitoring across agriculture, livestock systems, and public health networks. Finally, AI can support policy coordination by enabling integrated data platforms that allow faster information sharing between agencies responsible for health, agriculture, animal husbandry, and environmental protection.
India’s Emerging Efforts
India has begun incorporating the One Health approach into its health governance architecture in recent years. The National One Health Mission (NOHM) seeks to strengthen coordination among agencies responsible for human, animal, and environmental health and improve pandemic preparedness through integrated disease surveillance, cross-sector data sharing, and coordinated outbreak response. AI is increasingly being integrated into this emerging ecosystem. A report from the Office of the Principal Scientific Adviser on the “State and Union Territory Engagement Workshop under the National One Health Mission” identifies data analytics and artificial intelligence as key enablers for improving surveillance precision and operational efficiency within the One Health framework.
Several AI-driven initiatives are already being deployed across India’s public health system. The Ministry of Health and Family Welfare (MoHFW) has introduced AI tools within disease surveillance, telemedicine, and national disease control programmes. These include the Clinical Decision Support System integrated with the eSanjeevani telemedicine platform, the Media Disease Surveillance system under the Integrated Disease Surveillance Programme, and AI-enabled tools supporting tuberculosis screening and prediction of adverse tuberculosis (TB) outcomes. AI-based diagnostic tools such as diabetic retinopathy screening are also being introduced to improve early detection and clinical decision-making. Centres of Excellence for AI in Health have been established at the All India Institute of Medical Sciences (AIIMS), New Delhi, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, and AIIMS Rishikesh to support the development and deployment of such technologies.
A report from the Office of the Principal Scientific Adviser on the “State and Union Territory Engagement Workshop under the National One Health Mission” identifies data analytics and artificial intelligence as key enablers for improving surveillance precision and operational efficiency within the One Health framework.
Parallel efforts are emerging in animal health surveillance. The National Animal Disease Referral Expert System (NADRES v2), developed by the Indian Council of Agricultural Research (ICAR)–National Institute of Veterinary Epidemiology and Disease Informatics, uses artificial intelligence, machine learning, and geospatial analytics to forecast livestock disease outbreaks across India. More recently, the Indian Council of Medical Research (ICMR) has invited an Expression of Interest under the NOHM for AI-enabled tools to support early detection of emerging and novel pathogens across human, animal, and environmental systems.
Taken together, these initiatives indicate the emergence of an AI-enabled biosurveillance ecosystem. If these systems can be effectively integrated, they could form the backbone of a national biosurveillance architecture capable of detecting signals across healthcare systems, livestock monitoring networks, and environmental databases. Yet the gap between ambition and implementation remains significant.
Structural Challenges
The biggest challenge facing AI-enabled One Health systems in India is data fragmentation. Human health records, veterinary surveillance datasets, agricultural information systems, and environmental monitoring platforms are spread across multiple ministries and agencies. These systems often operate under different standards and rarely interoperate. Without integrated datasets, AI systems cannot generate meaningful cross-sector insights. Institutional fragmentation further complicates matters. Effective implementation of the One Health approach requires coordination between ministries responsible for health, agriculture, animal husbandry, environment, and wildlife conservation. While the NOHM provides a coordinating platform, bureaucratic silos remain deeply entrenched.
Effective implementation of the One Health approach requires coordination between ministries responsible for health, agriculture, animal husbandry, environment, and wildlife conservation. While the NOHM provides a coordinating platform, bureaucratic silos remain deeply entrenched.
In addition, uneven public health capacity remains a constraint. Effective biosurveillance depends not only on advanced analytics but also on reliable ground-level reporting systems. Many regions continue to face gaps in disease surveillance infrastructure, veterinary services, and laboratory capacity. These structural limitations mean that AI tools, if deployed in isolation, risk becoming technological overlays on an otherwise fragmented health governance system.
From Vision to System
If India hopes to leverage AI effectively within a One Health framework, the following policy priorities deserve attention:
- Interoperable data systems must connect human, animal, and environmental health databases across ministries and states.
- Biosurveillance infrastructure, including veterinary networks, wildlife monitoring systems, and environmental sensors, must be strengthened to generate reliable data for AI systems.
- Building interdisciplinary expertise across epidemiology, veterinary science, environmental science, and data science will be essential.
- Robust governance frameworks are needed to ensure that AI-enabled surveillance balances public health objectives with privacy, transparency, and accountability.
AI offers powerful tools for operationalising the One Health approach by integrating signals from human health systems, veterinary networks, and environmental monitoring platforms to detect and respond to emerging health threats. For India, the opportunity is considerable given the country’s scale, biodiversity, and dense human–animal interface. However, the real challenge lies not in the sophistication of AI models but in the institutional reforms required to support them. Without interoperable data systems, cross-sector coordination, and sustained investment in public health capacity, AI risks becoming another technological layer applied to an otherwise fragmented system. The success of India’s One Health strategy will therefore depend less on artificial intelligence itself and more on the governance architecture built around it.
Basu Chandola is an Associate Fellow with the Centre for Digital Societies at the Observer Research Foundation.
The views expressed above belong to the author(s). ORF research and analyses now available on Telegram! Click here to access our curated content — blogs, longforms and interviews.
