AI in Disaster Medicine: Scoping Review of Methods, Validation, and System Integration
JMIR AI · 04.08.2026 · 5 · e90848-e90848
DOI: 10.2196/90848 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift JMIR AI, online erschienen am 04.08.2026. Verfasst von Ruben Peralta und 7 weiteren Autor:innen. Beteiligte Einrichtung: Trauma Surgery, Hamad Medical Corporation, Doha, Baladīyat ad Dawḩah, Qatar. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 173 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
AI 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 aimed to systematically map the scope, methods, validation strategies, and system integration of AI applications in disaster medicine and emergency health care systems.
Methods
This scoping review was conducted in accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. The PubMed (MEDLINE), Scopus, IEEE Xplore, and Google Scholar databases were searched from inception to January 31, 2026. Studies describing AI applications in disaster medicine, emergency response, mass casualty care, or public health emergencies were eligible. Data were charted across the emergency domain, scenario type, AI function, study design, and validation level.
Results
A total of 168 studies were included. Research activity was concentrated in the disaster response and rescue, and public health and pandemics domains, which together accounted for 64 (38.1%) studies. Most studies involved algorithm or model development (43/168, 25.6%) or system or tool development (33/168, 19.6%), whereas applied and observational studies were less common (15/168, 8.9%). Validation was predominantly internal or simulation-based; external validation was reported in 13 (7.7%) studies, and prospective real-world validation was reported in 2 (1.2%) studies. Human-centered, smart city, and mental health domains were consistently underrepresented.
Conclusions
AI research in disaster medicine is expanding rapidly but remains fragmented and is at an early stage of translational maturity. Future progress will depend on system-level integration, rigorous real-world validation, and alignment with operational emergency workflows.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Trauma Surgery, Hamad Medical Corporation, Doha, Baladīyat ad Dawḩah, Qatar.
- Department of Surgery, Universidad Nacional Pedro Henriquez Urena, Santo Domingo, 10100, Dominican Republic.
- Neurological Surgery, Neuroscience Insitute, Hamad Medical Corporation, P.O. Box: 3050, Doha, Baladīyat ad Dawḩah, Qatar, 974 72157731.
- Department is Bioethics and Medical Ethics, Faculty of Medical Sciences, Lebanese University, Beirut, Beyrouth, Lebanon.
- Corporate Department of Emergency Medicine, Hamad Medical Corporation, Doha, Baladīyat ad Dawḩah, Qatar.
- Emergency Medicine, Centre for Neuroscience and Trauma, Blizard Institute, Queen Mary University of London, London, United Kingdom.
Zitieren
APA
Peralta, R., Msheik, A., Al Mokdad, Z., Yigit, Y., Al-Thani, H., Al Rumaihi, G., Al-Sulaiti, G., & Cameron, P. (2026). AI in Disaster Medicine: Scoping Review of Methods, Validation, and System Integration. JMIR AI, 5, e90848-e90848. https://doi.org/10.2196/90848
Vancouver
Peralta R, Msheik A, Al Mokdad Z, Yigit Y, Al-Thani H, Al Rumaihi G, et al. AI in Disaster Medicine: Scoping Review of Methods, Validation, and System Integration. JMIR AI. 2026;5:e90848-e90848. doi:10.2196/90848
BibTeX
@article{Peralta2026,
author = {Peralta, Ruben and Msheik, Ali and Al Mokdad, Zeinab and Yigit, Yavuz and Al-Thani, Hassan and Al Rumaihi, Ghaya and Al-Sulaiti, Ghanem and Cameron, Peter},
title = {AI in Disaster Medicine: Scoping Review of Methods, Validation, and System Integration},
journal = {JMIR AI},
year = {2026},
volume = {5},
pages = {e90848--e90848},
doi = {10.2196/90848}
}
EUVIMED