LiZhe202000105/DeepSeek-AI-Enhanced-Virtual-Reality-Training-for-Mass-Casualty-Management: v1.0.0 - Initial Release of VR Training with AI-Based Machine Learning Enhancements
VR Training System for Mass Casualty Management - Initial Release This release includes the first stable version of the VR-based training system designed to train emergency medical responders in mass casualty management. It features: Key VR Scenarios : Training scenarios simulate multi-casualty incidents with realistic triage, injury classification, and transport decisions. AI-Driven Feedback : Machine learning models have been integrated to provide real-time feedback, guiding trainees in optimizing their decision-making skills. Clustering of Trainee Performance : Trainee clustering based on error patterns, providing insights into training ne
Resource information
- Format
- zip
- Original repository
- 15240079
- DOI
- 10.5281/zenodo.15240079
- Credit basis
- Creators in Zenodo record metadata
- Access
- Open files available from the original Zenodo deposit
- Last checked
- Nov 5, 2026
- License
- cc-by-4.0
- Last record update
- Nov 5, 2026
About this resource
VR Training System for Mass Casualty Management - Initial Release This release includes the first stable version of the VR-based training system designed to train emergency medical responders in mass casualty management. It features: Key VR Scenarios : Training scenarios simulate multi-casualty incidents with realistic triage, injury classification, and transport decisions. AI-Driven Feedback : Machine learning models have been integrated to provide real-time feedback, guiding trainees in optimizing their decision-making skills. Clustering of Trainee Performance : Trainee clustering based on error patterns, providing insights into training needs for different learner groups. ROC Curve Analysis : The machine learning model demonstrated strong predictive performance with an AUC of 0.976, aiding in distinguishing competency levels across trainees. Model Features: Random Forest & Linear Regression models to predict the factors influencing training outcomes, such as 'Replaces Traditional Teaching' and 'Stimulates Interest.' PCA-based clustering to categorize trainees' error patterns and performance, leading to more personalized training. Key Findings from Analysis: Clustering Insights : Three trainee groups were identified, with varying performance, offering insights for refining training strategies. Important Factors for Performance : 'Replaces Traditional Teaching,' 'Stimulates Interest,' and 'No Discomfort' were identified as critical factors influencing performance based on machine learning analysis. Known Issues: Minor user interface inconsistencies. Future updates will include further refinements to the feedback system and integration of additional training modules. S1_table1_data.xlsx S2_Fig2_data.xlsx S3_table2_data.xlsx S4_Fig3_data.xlsx S5_Fig4_data.xlsx S6_Fig5_data.xlsx S7_table4_data.xlsx S8_Fig6_data.xlsx