Artificial intelligence in undergraduate medical education clinical skills curricula: a scoping review of implementations since 2022

Purpose To systematically identify and synthesize peer-reviewed literature describing implemented AI innovations within undergraduate medical education clinical skills curricula from January 2022 through January 2026. Method The authors conducted a scoping review querying PubMed and Scopus, supplemented by SciSpace as an AI-assisted citation discovery tool. Eligible studies described utilizing AI to deliver the clinical skills curriculum in innovative ways (e.g., instruction in history-taking, communication, clinical reasoning, clinical documentation, OSCE/simulation assessment). We extracted data into standardized templates and thematically sorted to characterize how AI-assisted instruction was being implemented across educational objectives. Results From 1,130 initial records, 39 studies met inclusion criteria. AI-assisted instruction clustered into eight thematic categories: LLM-Based Virtual Patient and Clinical Simulation Systems ( n = 19), AI-Augmented OSCE and Simulation Assessment Tools ( n = 6), Embodied and Robotic AI Clinical Simulations ( n = 4), AI-Supported Procedural and Technical Skills Training ( n = 3), AI-Assisted Clinical Documentation and EHR-Based Skills Training ( n = 2), Multimodal Analytics for Skills Assessment ( n = 2), Educator-Facing AI Case Authoring and Simulation Design Tools ( n = 2), and AI-Supported Clinical Reasoning and Tutoring Tools ( n = 1). Publication activity concentrated heavily in 2024–2025, with virtual patient applications representing the dominant category. Conclusions AI implementation in clinical skills education has accelerated substantially since 2022, with large language model-powered virtual patient simulations emerging as the predominant application. Current implementations primarily position AI as a supplementary formative tool rather than a replacement for established pedagogical approaches. Robust evidence regarding long-term educational impact remains limited, indicating need for rigorous longitudinal evaluation alongside continued innovation.