Exploring the role of generative artificial intelligence in enhancing clinical skills training: A bibliometric analysis

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not applicable — bibliometric study; no clinical effect size reported

• Primary Outcome: 322 publications on GAI in clinical skills training were identified in WoS from 2011 to April 2025; research activity was minimal before 2023 but increased rapidly thereafter, consistent with the emergence of large language models such as ChatGPT

• Nnt Or Sensitivity: Not applicable — dominant contributing country: United States; dominant institutions: National University of Singapore, Gazi University, Nova Southeastern University; dominant journals: JMIR Medical Education, Medical Teacher, BMC Medical Education; dominant thematic clusters: ChatGPT, LLMs, natural language processing, clinical reasoning simulation, personalised learning, virtual patient interaction, ethical governance

• Confidence Interval: Not reported — bibliometric descriptive analysis does not provide confidence intervals

Clinical Application

The bibliometric findings are useful for orienting researchers and educators to the current state of the field, identifying key journals for literature monitoring, and recognising thematic gaps. However, the study does not provide actionable evidence for clinical implementation decisions. Educators should not interpret the rapid growth in publications as evidence of effectiveness. Rigorous empirical evaluation — including randomised controlled trials, controlled before-after studies, and validated competency assessments — is required before GAI tools are integrated into accredited clinical training programmes. Australian medical education operates under AMC accreditation standards, AHPRA registration requirements, and specialty college frameworks (e.g., RACGP, RACP, ANZCA). The RACGP has begun engaging with digital health competency frameworks, and the TGA has issued guidance on software as a medical device (SaMD) that may apply to GAI tools used in clinical decision-making training. Australian institutions are not identified as major contributors in this study, suggesting an opportunity for local research leadership. The Medical Board of Australia's Good Medical Practice standards require that clinical training maintain patient safety primacy — a consideration that must precede any GAI integration. PBS and funding implications are not directly relevant to this bibliometric study but will become critical as GAI tools move toward clinical deployment. Medical educators, clinical training programme directors, health professional education researchers, and institutional leaders considering or implementing GAI tools in undergraduate and postgraduate clinical skills curricula

Abstract

BACKGROUND: Traditional clinical skills training faces challenges such as limited standardized patient resources, high costs of simulation equipment, and restricted opportunities for repeated practice. Generative artificial intelligence (GAI), particularly large language models, has attracted increasing attention as a potential tool for simulation, feedback, and adaptive learning in medical education. However, the research landscape and thematic development of GAI in clinical skills training remain insufficiently mapped. METHODS: A bibliometric analysis was conducted using literature retrieved from the Web of Science Core Collection from January 1, 2011 to April 1, 2025. VOSviewer, the Bibliometrix R package, and CiteSpace were used to analyze publication trends, country and institutional contributions, journal distribution, collaboration networks, keyword co-occurrence, co-cited references, and citation bursts. RESULTS: A total of 322 publications were included. Research activity remained limited before 2023 but increased rapidly thereafter. The United States contributed the largest number of publications, followed by China and India. Major contributing institutions included the National University of Singapore, Gazi University, and Nova Southeastern University. Frequently publishing journals included JMIR Medical Education, Medical Teacher, and BMC Medical Education. Keyword and thematic analyses showed that current research attention is mainly concentrated on ChatGPT, large language models, natural language processing, clinical reasoning simulation, personalized learning, virtual patient interaction, and ethical governance. CONCLUSIONS: Research on GAI in clinical skills training is in an early but rapidly expanding stage, with growing scholarly attention to language-model-driven educational applications and related ethical issues. The bibliometric findings reflect research activity, knowledge structure, and thematic priorities rather than direct evidence of educational effectiveness. Future studies should adopt rigorous empirical designs and standardized evaluation frameworks to assess the effectiveness, safety, and appropriate boundaries of GAI applications in clinical skills training.

References

1. 1.Zhang, J., Liu, Y., & Wang, B. (2026). Exploring the role of generative artificial intelligence in enhancing clinical skills training: A bibliometric analysis. Medicine. https://doi.org/10.1097/MD.0000000000049849