This chapter offers a comprehensive overview of how geographic artificial intelligence (GeoAI) has been employed within health geography to address a wide spectrum of issues. First, it examines how GeoAI techniques have been used to estimate environmental exposures—such as air pollution and green spaces—and to measure human perceptions of the built environment, shedding light on their associations with various health outcomes. Second, it highlights GeoAI’s role in analyzing social and environmental determinants of health, especially when dealing with large, complex datasets that traditional statistical methods find challenging. Third, it covers the integration of GeoAI into disease surveillance and forecasting systems, enabling earlier detection of outbreaks and improved resource allocation. Throughout the chapter, we discuss the theoretical and methodological hurdles facing GeoAI research—such as the “black box” nature of some models, data privacy concerns, and the need for spatially explicit, explainable models. We also identify future directions, including the development of more interpretable GeoAI tools, improved data integration, and stronger interdisciplinary collaborations. Overall, this chapter provides insights into current advancements, challenges, and the potential of GeoAI in health geography.