Applications and Outcomes of Large-Language-Model-Generated Cases in Health Professions Education: A Scoping Review

This dataset accompanies the scoping review “Applications and Outcomes of Large-Language-Model-Generated Cases in Health Professions Education: A Scoping Review.” It contains the bibliographic records and screening decisions for all studies identified during the review process, including both included and excluded reports. The dataset documents the full study selection workflow. We searched PubMed, Web of Science, and Scopus using a predefined strategy targeting large language models and case/vignette generation within medical and health professions education. The search yielded 2023 records, which were imported into Rayyan. After removal of 1157 duplicates, 1306 titles/abstracts were screened; 72 full texts were assessed for eligibility, of which 23 studies were included and 49 were excluded with documented reasons. Inclusion criteria required that at least one text-, image-, or sound-based case be generated by an LLM for use in health professions education.