Currently submitted to: Interactive Journal of Medical Research
Date Submitted: May 8, 2026
Open Peer Review Period: May 18, 2026 - Jul 13, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Artificial Intelligence in Medical Education: A Narrative Review of Clinical Skills Training, Ethical Integration, and Future Directions
ABSTRACT
Background:
Clinical skills training is central to medical education, yet traditional teaching methods face persistent challenges including inconsistent patient exposure, subjective feedback, and limited faculty and resource availability. Artificial intelligence (AI), encompassing machine learning, deep learning, and expert systems, offers emerging opportunities to address these gaps through adaptive, data-driven educational tools. Despite rapid AI adoption in clinical practice, structured integration into medical curricula remains limited.
Objective:
This structured narrative review synthesizes current evidence on the role of AI in clinical skills training across undergraduate and postgraduate medical education, with a focus on efficacy across skill domains, curricular integration requirements, and ethical considerations for responsible implementation.
Methods:
A structured literature search was conducted across PubMed, Scopus, and Google Scholar for studies published between January 2019 and June 2025. A total of 42 studies were included in the final synthesis: 27 empirical investigations encompassing randomized controlled trials, systematic reviews, scoping reviews, observational studies, and surveys, and 15 non-empirical sources including policy frameworks, governance perspectives, and protocols. Findings were synthesized thematically.
Results:
Evidence across three converging domains was identified. First, AI demonstrates meaningful efficacy signals in procedural and surgical skills training, with one randomized controlled trial demonstrating AI tutoring to be non-inferior to expert instruction, while diagnostic reasoning and non-technical skills show early but more exploratory evidence. Second, a persistent disconnect exists between AI adoption in clinical practice and curricular scaffolding, with over 75% of surveyed students reporting no formal AI training despite high motivation among both students and faculty. Third, algorithmic bias, data privacy, deskilling through over-reliance, and infrastructure disparities represent structural equity and ethics concerns requiring deliberate governance frameworks.
Conclusions:
AI holds meaningful potential for clinical skills training, but it requires system-level investment in pedagogically grounded curricular integration, standardized competency frameworks, and equity-centered ethical governance. Future research should prioritize multi-institutional, longitudinal studies that link AI-enhanced educational outcomes to real-world clinical performance.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.