Evidence for AI in Health (EVAH)

Programme to support locally-led evaluations of AI-enabled clinical decision support tools (CDSTs) within primary and community health care settings in Sub-Saharan Africa, South Asia and Southeast Asia.

The Evidence for AI in Health (EVAH) initiative is supported by the Wellcome Trust, Gates Foundation, and Novo Nordisk Foundation, and delivered in partnership with the Abdul Latif Jameel Poverty Action Lab (J-PAL) and the African Population and Health Research Center (APHRC).

The initiative supports locally-led evaluations of AI-enabled clinical decision support tools (CDSTs) that are ready for real-world use and designed to assist frontline workers with clinical tasks within primary and community health care settings in Sub-Saharan Africa, South Asia and Southeast Asia.

The focus of the programme is on evaluations of AI-enabled CDSTs that:

• Address cross-cutting PHC functions, including but not limited to triage, diagnosis, or referral across multiple conditions or patient populations.
• Demonstrate integration within broader in-country health systems and service delivery pathways rather than stand-alone use cases.
• Show potential for horizontal scalability or adaptation across geographies, disease areas, or cadres of health workers.

Evaluations may include range of methods generating real-world evidence (eg randomised evaluations, Health Technology Assessments, quasi-experimental designs, etc). They should generate evidence on workflow integration, efficiency, safety and cost-effectiveness, equity and inclusion, usability and trust, health impacts as well as mechanisms of impacts.

While the call is open to a range of PHC contexts, evaluations addressing the following topics are particularly encouraged:

• Strengthen integration of service delivery across levels of care (eg, between community health workers and PHC facilities).
• Examine integration of health commodities (eg, medications, rapid tests, where regulation allows).
• Assess system-level fit, including interoperability with digital health tools, data systems, and referral processes.
• Explore multimodal applications (eg, tools using voice, text, or image inputs).
• Focus on reducing inequities by extending reach to vulnerable, underserved, or rural populations.
• Address high-burden conditions with potential for significantly improved outcomes.

Proposals that foster collaboration between technologists, health system actors, researchers, and implementers are strongly encouraged, especially where they engage local health authorities and communities.

Projects are supported via two funding pathways:

• Pathway A: supports real-world evaluation of AI-enabled CDSTs that are early in deployment. The pathway focuses on how the tools perform in practice, including usability, workflow integration, adoption, and safety, and supports research that can inform future impact evaluations.
• Pathway B: supports rigorous impact evaluations of AI-enabled CDSTs that are ready to be deployed at scale. This pathway focuses on measuring the effects of these tools on health outcomes and system performance at scale.