AI Use for Medical Students: Impact on Clinical Skill Acquisition and Retention. A Systematic Review

Purpose: Artificial Intelligence (AI) is increasingly used in undergraduate medical education but has a potentially negative impact on clinical reasoning development. Specifically, the use of AI in medical student education may lead to deskilling and upskilling inhibition - where automation reduces practice or limits skill development - potentially impairing clinical reasoning. This systematic review aimed to synthesise evidence regarding AI-supported learning effects on acquisition and retention of clinical skills in medical students to assess its potential negative impact in medical education. Methods: A systematic search was conducted on 21 October 2025 across PubMed, Scopus, and Embase using structured Boolean queries restricted to titles and abstracts. Inclusion criteria targeted published studies involving medical students exposed to AI tools in clinical learning, reporting outcomes related to skill acquisition, reasoning, or overreliance on AI. Exclusions included non-AI digital tools, administrative AI applications, and studies without clear educational outcomes. Screening followed PRISMA guidelines. Results: From 420 records, 255 were screened. Four studies met the screening criteria, incorporating a total of 408 medical students. Across included studies, AI exposure was associated with improved efficiency and improved basic knowledge acquisition. When higher-order clinical reasoning and complex decision-making were assessed, findings were mixed: one study reported no overall difference, while others suggested weaker performance or reduced engagement when AI-supported approaches were used. Conclusion: Current evidence suggests that AI-supported learning may be associated with improved efficiency and basic knowledge acquisition in undergraduate medical education. Findings were less consistently supportive of higher-order reasoning outcomes compared with traditional teaching approaches, although the evidence base was limited. Potential risks of deskilling and upskilling inhibition warrant attention as medical schools increasingly integrate AI tools into their curricula. A striking finding of our systematic review was the very low number of existing studies identified in this important field. Further research should explore the long-term impacts of AI on medical students’ independent clinical judgement and consider strategies to mitigate overreliance on AI given the profound potential impact on future patient care. Keywords: clinical reasoning, deskilling, upskilling inhibition