Asian Journal of Medicine and Health

The integration of Artificial Intelligence (AI) into epidemiological research and practice is reshaping the landscape of public health decision-making, disease surveillance, and predictive modeling. This study provides a comprehensive investigation into how AI technologies are being utilized across five key epidemiological functions: disease surveillance and outbreak prediction, risk factor identification, diagnosis and treatment, data management and analysis, and causal inference. Through an in-depth literature review, the study identifies both the technical and functional benefits of AI, including accuracy enhancement, real-time insights, and resource optimization, while also critically addressing the ethical and operational risks such as data ownership, model transparency, algorithmic bias, and challenges in informed consent. To guide future applications, the study introduces three strategic frameworks: the Loop-Oriented Table of AI Applications, which categorizes AI use cases across epidemiological loops; the AI Overloop Table, which highlights cross-functional synergies of AI implementations; and the AI Risk loop Table, which maps domain-specific risks back to the type of AI deployment. These models provide a systems-level understanding of AI's capabilities and constraints within public health ecosystems. Based on these frameworks, the study offers practical recommendations for integrating AI responsibly and effectively in epidemiological workflows, with an emphasis on transparency, scalability, and equity. Future research should explore the operationalization of these recommendations in real-world settings to validate their feasibility and societal impact.