Applying a Climate--Health Foundation Model: Integrating Environmental Data, Health Outcomes, and Workforce Adaptation

This report examines emerging practices in climate–health data integration and introduces Biosurveillance Engine for Adaptive Resilience (BEAR)—a federated, standards-based, and governance-driven framework designed to learn from multimodal data sources to strengthen adaptive governance, predictive surveillance, and workforce resilience. Drawing on case studies, this paper analyzes applications of geospatial, environmental, and clinical data in predictive modeling and identifies systemic evidence gaps. Special attention is given to geo-epidemiological trends and the potential of linking environmental signals with electronic health records to reveal latent disease drivers and support context-sensitive public health responses. The proposed foundation model offers a transformative opportunity to bridge fragmented data ecosystems and support equitable adaptation to climate-related health threats. This paper highlights key research questions for future development, systemic barriers to integration, and strategies and tools to address them. The model’s success depends on open and sustainable infrastructure, inclusive governance, and deliberate workforce investment to integrate climate–health model design and policy to transition toward anticipatory, resilient, and just health systems.