DeepSeek-AI-enhanced virtual reality training for mass casualty management: Leveraging machine learning for...

Area of Science:

• Medical Education Technology
• Artificial Intelligence in Healthcare
• Virtual Reality Simulation

Background:

• Traditional medical training faces challenges in providing personalized feedback for complex scenarios.
• Mass casualty management requires continuous skill refinement and adaptive learning strategies.

Purpose of the Study:

• To evaluate an AI-integrated VR system for mass casualty management training.
• To identify performance predictors and optimize VR medical training through AI analysis.
• To generate personalized feedback for medical professionals.

Main Methods:

• 196 medical professionals underwent a 1-hour VR training session.
• AI (DeepSeek framework) analyzed performance using clustering, PCA, and random forest models.
• Trainee data, error rates, and assessment scores were analyzed using R software.

Main Results:

• Three distinct trainee clusters were identified, with high error rates in Clinical Case Analysis (69.4%) and Trauma Assessment (67.3%).
• AI models identified replacing traditional methods and stimulating learning interest as key performance factors.
• AI-driven feedback suggested scenario redesign and usability enhancements.

Conclusions:

• AI-integrated VR training enhances medical education personalization and effectiveness.
• Data-driven, adaptive learning is crucial for high-stakes medical training.
• Future research should explore hybrid models and physiological data integration.