Application of an AI-powered virtual simulation combined with case-based learning in undergraduate emergency medicine education: focusing on advanced clinical competence and clinical transfer ability

Background Emergency medicine is characterized by urgency, criticality, severity, and diversity, which places high demands on undergraduate medical education. Traditional lecture-based teaching has limitations in developing students' advanced clinical competence and clinical transfer ability. Although virtual simulation and case-based learning (CBL) have demonstrated benefits in medical education, their combined application in emergency medicine teaching has not been systematically evaluated, especially based on artificial intelligence (AI). This study primarily aimed to investigate whether the integrated AI-powered virtual simulation combined with CBL could improve students' higher-order clinical competencies and clinical transfer ability, and secondarily to obtain empirical evidence to support the optimization of undergraduate emergency medicine teaching. Methods Third-year undergraduate students majoring in clinical medicine were selected as the research subjects and randomly divided into the control group and the experimental group. The control group adopted the traditional teaching method, while the experimental group adopted the AI-enabled virtual simulation combined with real emergency case teaching method. The learning situation of the virtual simulation platform was automatically recorded by the platform, and the teaching effect was evaluated through theoretical scores, objective structured clinical examination (OSCE) scores, clinical practice tracking evaluation (including advanced clinical ability and clinical transfer effect evaluation), comprehensive evaluation of learning psychology, and teaching satisfaction questionnaire. Results Compared with the control group, the students in the experimental group demonstrated significant advantages in all assessment dimensions, including theoretical test, various practical skills in OSCE, disease assessment, emergency management, clinical decision-making, as well as learning confidence, autonomous learning ability and teaching satisfaction ( P < 0.001). Further analysis indicated that within the experimental group, greater investment in study time was significantly associated with better clinical performance and diagnostic accuracy. Crucially, Cox regression analysis confirmed that diagnostic accuracy was an independent protective factor for the weakness of clinical transfer ability (HR = 0.6469, P < 0.00001), meaning that students with higher diagnostic accuracy had a significantly superior clinical competence. Conclusions In conclusion, this study demonstrates that the teaching model combining AI-powered virtual simulation with real cases can comprehensively and significantly enhance the comprehensive clinical skills and learning experience of medical students. The teaching effect can effectively transfer to the real clinical environment, and the diagnostic accuracy cultivated during the teaching process has important predictive value for the long-term clinical prognosis. This provides empirical evidence for the reform of emergency medicine education and emphasizes the importance of linking educational process evaluation with clinical outcomes.

Authors

Institutions

Publication Details

Journal
Frontiers in Medicine
Published
2026-11-16
DOI
https://doi.org/10.3389/fmed.2026.1905688
Primary Topic
Simulation-Based Education in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Application of an AI-powered virtual simulation combined with case-based learning in undergraduate emergency medicine education: focusing on advanced clinical competence and clinical transfer ability

Yilan Zhang, Rong Zhang, Guo Wei, Zhaohui Zhang et al.
3 links
Frontiers in Medicine
Simulation-Based Education in Healthcare
article

Application of an AI-powered virtual simulation combined with case-based learning in undergraduate emergency medicine education: focusing on advanced clinical competence and clinical transfer ability

Yilan Zhang, Rong Zhang, Guo Wei, Zhaohui Zhang, Li Zhang, Gaosheng Zhou
article en

Abstract

Background Emergency medicine is characterized by urgency, criticality, severity, and diversity, which places high demands on undergraduate medical education. Traditional lecture-based teaching has limitations in developing students' advanced clinical competence and clinical transfer ability. Although virtual simulation and case-based learning (CBL) have demonstrated benefits in medical education, their combined application in emergency medicine teaching has not been systematically evaluated, especially based on artificial intelligence (AI). This study primarily aimed to investigate whether the integrated AI-powered virtual simulation combined with CBL could improve students' higher-order clinical competencies and clinical transfer ability, and secondarily to obtain empirical evidence to support the optimization of undergraduate emergency medicine teaching. Methods Third-year undergraduate students majoring in clinical medicine were selected as the research subjects and randomly divided into the control group and the experimental group. The control group adopted the traditional teaching method, while the experimental group adopted the AI-enabled virtual simulation combined with real emergency case teaching method. The learning situation of the virtual simulation platform was automatically recorded by the platform, and the teaching effect was evaluated through theoretical scores, objective structured clinical examination (OSCE) scores, clinical practice tracking evaluation (including advanced clinical ability and clinical transfer effect evaluation), comprehensive evaluation of learning psychology, and teaching satisfaction questionnaire. Results Compared with the control group, the students in the experimental group demonstrated significant advantages in all assessment dimensions, including theoretical test, various practical skills in OSCE, disease assessment, emergency management, clinical decision-making, as well as learning confidence, autonomous learning ability and teaching satisfaction ( P < 0.001). Further analysis indicated that within the experimental group, greater investment in study time was significantly associated with better clinical performance and diagnostic accuracy. Crucially, Cox regression analysis confirmed that diagnostic accuracy was an independent protective factor for the weakness of clinical transfer ability (HR = 0.6469, P < 0.00001), meaning that students with higher diagnostic accuracy had a significantly superior clinical competence. Conclusions In conclusion, this study demonstrates that the teaching model combining AI-powered virtual simulation with real cases can comprehensively and significantly enhance the comprehensive clinical skills and learning experience of medical students. The teaching effect can effectively transfer to the real clinical environment, and the diagnostic accuracy cultivated during the teaching process has important predictive value for the long-term clinical prognosis. This provides empirical evidence for the reform of emergency medicine education and emphasizes the importance of linking educational process evaluation with clinical outcomes.

Frontiers in MedicineVol. 13
China Three Gorges University (CN), Wuhan University (CN), Zhongnan Hospital of Wuhan University (CN), Yichang Central People's Hospital (CN)
Quality education, Good health and well-being
Simulation-Based Education in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon