JMIR Publications

ABSTRACT

Background:

Artificial intelligence is increasingly proposed as a tool to enhance disaster medicine through improved situational awareness, decision support, and resource coordination. However, the extent to which current research has progressed beyond methodological development toward integrated, operationally validated systems remains unclear.

Objective:

This review aims to systematically map the scope, methods, validation strategies, and system integration of artificial intelligence applications in disaster medicine and emergency health systems.

Methods:

A scoping review was conducted in accordance with PRISMA-ScR guidelines. PubMed/MEDLINE, Scopus, IEEE Xplore, and Google Scholar were searched from inception to January 31, 2026. Studies describing artificial intelligence applications in disaster medicine, emergency response, mass-casualty care, or public health emergencies were eligible. Data were charted across emergency domains, scenario types, artificial intelligence functions, study design, and validation level.

Results:

A total of 168 studies were finally included. Research activity was concentrated in Disaster Response and Rescue and Public Health and Pandemics, which together accounted for 64/168 studies (38.1%). Most studies involved algorithm or model development (43/168, 25.6%) or system/tool development (33/168, 19.6%), whereas applied and observational studies were less common. Validation was predominantly internal or simulation-based; external validation was reported in 13/168 studies (7.7%), and prospective real-world validation in 2/168 studies (1.2%). Human-centered, smart city, and mental health domains were consistently underrepresented.

Conclusions:

Artificial intelligence research in disaster medicine is expanding rapidly but remains fragmented and early in translational maturity. Future progress will depend on system-level integration, rigorous real-world validation, and alignment with operational emergency workflows.