Linlin Chen^1*, Zhibin Wang^1*, Xiaojing Guo¹ , Zhanheng Chen¹ , Zixin Li¹ , Mi Li¹ , Weiheng Xu² , Zui Zou¹ , Shuo Yang¹

¹School of Anesthesiology, Naval Medical University, Shanghai 200433, China. ²School of Pharmacy, Naval Medical University, Shanghai 200433, China.

^*The authors contribute equally.

Address correspondence to: Shuo Yang, Department of Critical Care Medicine, School of Anesthesiology, Naval Medical University, 168 Changhai Road, Shanghai 200433, China. E-mail: charlotteyang@smmu.edu.cn; Zui Zou, School of Anesthesiology, Naval Medical University, 168 Changhai Road, Shanghai 200433, China. E-mail: zouzui1980@163.com.

Acknowledgement: This work was supported by the Anesthesiology Department Teaching Development Foundation of Naval Medical University (2024MZQN03) and the Teaching Research and Reform Project of Naval Medical University (JYG2024B24).

DOI: https://doi.org/10.61189/793750gpxnge

Received June 23, 2025; Accepted August 28, 2025; Published September 30, 2025

Highlights

● This study introduces an AI-empowered blended teaching model for disaster medicine, integrating generative AI, virtual simulations, and intelligent assessment systems to improve teaching efficiency and student engagement.

● The model employs a “dual-teacher collaboration” approach, combining AI-driven tools with human instructors to foster critical thinking and ethical awareness in disaster response training.

● A multidimensional evaluation system was developed, combining dynamic AI-based assessments, scenario- driven simulations, and long-term tracking to provide personalized feedback and support continuous learning.

● The course emphasizes interdisciplinary integration across engineering, information technology, and psychology, aiming to cultivate comprehensive disaster management competence and strengthen professional responsibility.