Mapping the research landscape of virtual reality and artificial intelligence in medical education evaluation: A bibliometric analysis
Xi Huang, Xingxin Li, Qianwei Lu, Zhengjun Guo, Na Wang, Yifan Zhang, Yanni Hu, Di Li, Yun Luo, Xia WuBackground:
Evaluation of medical education is essential for ensuring the quality of health professional training. However, conventional evaluation approaches often lack objectivity, scalability, and longitudinal assessment capacity. Virtual reality (VR) and artificial intelligence (AI) are increasingly integrated into medical education, yet their application in educational evaluation has not been systematically characterized.
Objective:
To examine research trends, thematic evolution, and emerging directions in VR- and AI-enabled medical education evaluation, a bibliometric analysis was conducted.
Methods:
Publications indexed in the Web of Science Core Collection between January 1, 2015, and December 31, 2025, were retrieved using predefined search terms related to VR, AI, medical education, and evaluation. Eligible English-language articles and reviews were analyzed using CiteSpace (version 6.4.R2). Annual publication and citation trends, country collaboration patterns, and cited journals were assessed. Research themes and frontiers were examined through keyword co-occurrence, clustering, burst detection, and timeline analyses.
Results:
A total of 695 publications were included. Annual publications and citations increased steadily, with accelerated growth after 2020. The United States, Germany, China, England, and Canada produced the highest number of publications, whereas Belgium, Egypt, Sweden, Singapore, and Switzerland demonstrated high collaboration centrality. Influential cited journals were concentrated in medical education and simulation-based training domains. Keyword analyses identified major themes including surgical education, VR simulation, clinical reasoning, decision support, and residency and undergraduate education. Burst and timeline analyses indicated a progression from early simulation-based skill validation toward learner-centered performance evaluation and, more recently, quality-oriented and curriculum-level assessment.
Conclusions:
Research on VR- and AI-enabled medical education evaluation has expanded rapidly and evolved from technical skill assessment toward comprehensive, competency-oriented, and quality-focused evaluation. These findings highlight the growing role of emerging technologies in shaping future global medical education evaluation frameworks.