JMIR Publications

ABSTRACT

Background:

Traditional epidemic intelligence relies heavily on human epidemiologists for data interpretation and reporting, which makes it resource-intensive, slow to respond, and vulnerable to variability in professional expertise.

Objective:

To overcome these limitations, we propose an expanded epidemic intelligence quadripartite framework that extends the classical trinity of surveillance, risk assessment, and early warning with a fourth pillar: decision support and intervention optimization through AI Agents.

Methods:

AI Agents act as “24/7 digital epidemiologists,” integrating heterogeneous signals from multi-source surveillance systems, conducting contextual risk assessment and adaptive forecasting, generating tailored early warnings, and providing actionable recommendations for targeted control. Embedding interpretability and human-in-the-loop oversight enhances trust and accountability.

Results:

The proposed AI-driven framework demonstrates the potential to enable continuous, adaptive, and data-driven epidemic intelligence operations by linking surveillance, assessment, and intervention in real time.

Conclusions:

Nonetheless, real-world deployment requires addressing challenges of data quality, interoperability, robustness, governance, and equity. If designed with transparency, inclusiveness, and resilience, AI Agents have the potential to transform epidemic intelligence into a continuously adaptive and globally connected system.