ArticlePloS one2025
DeepSeek-AI-enhanced virtual reality training for mass casualty management: Leveraging machine learning for personalized instructional optimization.
Article in PloS one, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
8 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
objectiveThis study aimed to evaluate the effectiveness of a virtual reality (VR) training system for mass casualty management, integrating artificial intelligence (AI) and machine learning (ML) to analyze trainee performance and error patterns. The goal was to identify key predictors of performance, generate personalized feedback, and provide actionable recommendations for optimizing VR-based medical training. MATERIALS AND
methodsA total of 196 medical professionals participated in a 1-hour VR training session, followed by a 20-question assessment and a post-training evaluation survey. The DeepSeek AI framework was employed to analyze the data, utilizing clustering analysis, principal component analysis (PCA), and random forest models. Descriptive statistics, error rates, and correlation analyses were performed using R software (version 4.1.2). Machine learning models were trained to predict performance outcomes, and feature importance was assessed using the Gini index. Personalized feedback reports were generated based on clustering and error analysis results.
resultsThe study identified three distinct trainee clusters, with the highest-performing group excelling in Trauma Assessment and Clinical Case Analysis. However, high error rates were observed in Clinical Case Analysis (69.4%) and Trauma Assessment (67.3%), indicating areas for targeted improvement. Machine learning models highlighted replacing traditional teaching methods (IncNodePurity = 25.76) and stimulating learning interest (IncNodePurity = 13.08) as the most critical factors influencing learning outcomes. AI-driven feedback provided actionable recommendations, such as redesigning complex scenarios and enhancing system usability.
conclusionsThis study demonstrates the potential of integrating AI with VR training to create a more personalized and effective learning experience for medical professionals. The findings underscore the importance of adaptive, data-driven approaches in medical education, particularly in high-stakes environments such as emergency medicine. Future research should explore hybrid training models and incorporate physiological data to further enhance the efficacy of VR-based training systems.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.