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.
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.
Background While bibliometric analyses have examined the adoption of Artificial Intelligence (AI) in general medical education contexts, the specific knowledge structures, collaborative networks, and evolutionary pathways of AI for medical imaging education remain poorly characterized quantitatively, particularly regarding the transition from technical feasibility to systematic pedagogical integration and cross-institutional partnerships. Methods A structured literature search of English-language original articles and reviews published between 2006 and 2025 was performed in the Web of Science Core Collection (WoS) and Scopus, with the former serving as the primary database and the latter for external validation. Bibliometric analyses covering citation trends, collaboration networks, keyword bursts, and journal distributions were conducted using CiteSpace, VOSviewer, and Bibliometrix. Results This search retrieved 577 articles from WoS, revealing exponential growth since 2019, with 226 articles published in 2025. These publications were contributed by 3,739 authors from 1,479 institutions across 80 countries/regions. Cross-database validation supported the consistency of these findings (Spearman r = 0.97, p < 0.001), with the United States (166 articles, 28.8%) and China (115 articles, 19.9%) as the primary contributors. BMC Medical Education, Insights into Imaging, and Academic Radiology were the most productive journals. Keyword analysis revealed diversification from foundational algorithms toward interactive, generative AI applications in medical imaging education, documenting an expanded scope integrating technical development with pedagogical innovation and ethical governance. Conclusion This study characterizes a dual-polar production structure with the United States and China as dominant contributors, and a journal distribution spanning medical education and imaging technology venues. The post-2022 emergence of generative AI keywords documented a new thematic cluster alongside foundational machine learning research, indicating an evolving methodological repertoire. These findings provide a quantitative baseline for evidence synthesis in this interdisciplinary domain, with implications for curriculum development, algorithmic performance benchmarks, and ethical governance, subject to standard bibliometric data coverage and currency constraints.
Yiman Wu, Wenqi Wu· Frontiers in Medicine· 0 citations
Generative artificial intelligence (GenAI), particularly large language models (LLMs), is poised to fundamentally transform medical education. Based on a structured literature search of PubMed, Scopus, Web of Science, and Google Scholar, this review synthesizes current evidence on the applications, capabilities, and limitations of GenAI across the medical training continuum. Advanced LLMs demonstrate a formidable command of medical knowledge, consistently achieving passing scores on standardized licensing examinations, with GPT-4 and domain-specific models like Ortho GPT showing particular proficiency. As versatile teaching tools, these models can generate high-quality assessment materials, provide personalized on-demand tutoring, and power interactive virtual patients for clinical reasoning practice. However, this potential is tempered by significant challenges, including a propensity for “hallucinations,” embedded biases that can perpetuate health inequities, linguistic performance disparities, and a fundamental gap in flexible, adaptive clinical reasoning. Integration also raises critical concerns regarding academic integrity, potential over-reliance leading to deskilling, and data privacy. Responsible adoption requires a structured approach encompassing the development of tiered AI competency frameworks, blended curricular integration, dedicated faculty development, and a rigorous research agenda focused on longitudinal learning outcomes. Ultimately, GenAI should be viewed as a powerful augmentative tool, not a replacement for human educators. Its successful integration will depend on leveraging its strengths to enhance efficiency and scalability while preserving the essential humanistic elements of medical practice through expert oversight and validation.
R. Xie, Bei-En Zhang, Lifeng Xiao· Frontiers in Medicine· 0 citations
Background and objective Virtual patients have become an integral component of medical education, offering medical students realistic, repeatable, and interactive learning environments that effectively foster the development of clinical competencies. Moreover, the rapid evolution of generative artificial intelligence and large language model technologies has further accelerated the integration of virtual patients into medical education, making it a prominent area of contemporary educational innovation. To provide a comprehensive overview of the research landscape and emerging trends in this domain, we performed a bibliometric and knowledge-mapping analysis of the literature on virtual patients in medical education. Methods Publications published between 2006 and 2025 were retrieved from the Web of Science Core Collection and Scopus databases, including only English articles and review articles. CiteSpace and VOSviewer were used to perform bibliometric and knowledge-mapping analyses of collaboration networks, co-citation patterns, and keyword evolution. Result A total of 2,347 publications showed a consistent upward trend. The United States led contributions, followed by the United Kingdom and Germany, with extensive collaborations between North America and Europe. Medical Education was the most influential journal; Karolinska Institutet was the most productive institution and Cook, DA. was the most prolific author. Frequent keywords included “medical education,” “simulation,” “clinical competence,” “virtual reality,” and “patient simulation.” The most cited article confirmed virtual patients outperform no intervention, providing an evidence base for their adoption in medical education. Conclusions This bibliometric analysis highlights the sustained growth and evolving research landscape of virtual patients in medical education. The findings indicate that recent research has increasingly focused on the integration of generative artificial intelligence and large language models into virtual patient systems. These findings provide a quantitative evidence base for future research priorities and the continued development of virtual patient-based medical education.
Yinglan Ye, H. Tao, Siqi Huang et al.· Frontiers in Medicine· 0 citations
Artificial Intelligence (AI) in medical education is of critical significance for promoting the reform of medical education. The integration of AI technology and medical education has shifted from initial conceptual exploration to technological implementation and educational practice, which helps reduce teachers` workload and improve students` learning efficiency. This study followed the PRISMA guidelines and employed CiteSpace, VOSviewer, and R Bibliometrix to conduct a bibliometric analysis of core literature from the past decade in the Web of Science database. The findings indicated that artificial intelligence medical education research is undergoing rapid development, with core publications emerging in journals such as BMC Medical Education, Journal of Medical Internet Research, and Medical Teacher. Key authors in this field include Friedman, Noseworthy, and Cheungpasitporn, while the United States and China stand as the primary contributing nations. Furthermore, most core research institutions in this domain are located in these regions. This study summarized research hotspots in AI in Medical Education, focusing on three major themes: educational scenarios and core participants, core AI technologies, and educational programs. This has led to the development of a process framework based on scenarios, driven by technology, and implemented through projects. Findings indicate that research in this field has progressed from initial feasibility validation to a stage of deep integration, involving machine learning, deep learning, and large language models. Future research will concentrate on AI in Medical Education, prioritizing three key directions: algorithm optimization, disease diagnosis, and teaching management. This study provided a theoretical and reference foundation for researchers, medical educators, and policymakers in the field of AI in Medical Education.
A conceptual Clinical Co-pilot Framework is proposed to position GenAI as a collaborative partner that supports clinicians rather than replaces them, which provides a conceptual basis for future empirical validation and may help inform the responsible implementation of GenAI in healthcare.
Lina Cheng, Chia-Yu Hung, Te-Nien Chien· International Journal of Adv...· 0 citations
Introduction Problem-based learning (PBL) has been a cornerstone of medical education since its introduction at McMaster University in the 1960s. Since the public release of ChatGPT in November 2022, artificial intelligence (AI) tools have increasingly been applied to PBL and case-based learning (CBL) contexts, yet the research landscape at this intersection remains poorly characterized. This study aimed to map the growth trajectory, thematic structure, and collaboration networks of AI-PBL/CBL research from 2019 to 2026. Methods A comprehensive search of Scopus and Web of Science was conducted on June 2, 2026, combining AI-related terms with PBL/CBL frameworks and medical education contexts. Using a PRISMA-guided bibliometric review workflow, 1,616 records were identified; after deduplication and eligibility screening, 735 unique publications (2019–2026, original articles, reviews, conference papers, and other eligible indexed document types) were included. Bibliometric analyses employed VOSviewer for network visualization (keyword co-occurrence, co-authorship, co-citation), CiteSpace for citation burst detection, and Bibliometrix for thematic mapping, three-field plot, and factorial analysis. Results Publication output grew from 25 papers in 2022 to 254 in 2025, with 206 papers indexed by June 2, 2026. The United States (n = 70) and China (n = 64) led publication volume. Keyword co-occurrence analysis identified four thematic clusters: a central AI-focused cluster, a medical education and clinical reasoning cluster, a nursing and simulation-oriented cluster, and an educational technology cluster. Kung et al.'s 2023 study evaluating ChatGPT's performance on the USMLE was the most frequently co-cited reference (62 co-citations, betweenness centrality = 0.11). Thematic mapping positioned machine learning as a motor theme, while clinical reasoning, medical education, and self-directed learning appeared in the basic themes quadrant. The country/region collaboration network comprised 33 countries/regions and was led by the United States and China, although collaboration patterns remained uneven across regions. Conclusion To our knowledge, this is the first bibliometric study specifically focused on the intersection of AI technologies with PBL/CBL in health professions education. The findings reveal rapid growth after 2023, four distinct but interconnected research clusters, and a collaboration network led by the United States and China, with uneven regional participation. These results may inform curriculum design and research priorities in AI-enhanced medical education.
Qingyuan Tan, Yukui Ma, Jichun Zhao et al.· Frontiers in Medicine· 0 citations