Abstract
INTRODUCTION: Generative artificial intelligence (AI) tools are rapidly transforming case-based learning (CBL) within medical education. Despite growing interest, the literature is heterogeneous, fragmented and inconsistent in terminology and methodology. This scoping review aims to systematically map and synthesise evidence on the integration of generative AI in CBL, identifying key themes, educational outcomes, challenges and research gaps to guide future investigations, curricular innovation and policy development. METHOD AND ANALYSIS: A comprehensive search strategy, developed with a health sciences librarian, will be implemented across multidisciplinary databases, including PubMed/MEDLINE, ERIC, Scopus, Web of Science, EMBASE and CINAHL, covering publications from 2019 to 2025. Two independent reviewers will conduct title/abstract and full-text screening using predefined eligibility criteria. Data extraction will use standardised charting forms capturing study characteristics, AI applications, educational contexts, outcomes and user perceptions. Data synthesis will involve descriptive statistics and inductive thematic analysis to create an evidence map of generative AI-supported CBL in medical education. ETHICS AND DISSEMINATION: No ethics approval is required, as the review synthesises published literature. Findings will be disseminated through peer-reviewed journals, conferences and stakeholder networks to inform educators, researchers and policymakers.