CUI-Curate: A Framework for Automated Clinical Concept Selection from the Unified Medical Language System.

INTRODUCTION: Manual construction of UMLS concept sets is time-consuming and inconsistent across users. METHODS: CUI-Curate, a GPT-5 and graph-based retrieval framework, was developed to automate clinical concept set generation from UMLS source vocabularies. RESULTS: Across five target concepts, CUI-Curate achieved higher recall (mean gain = +0.17) while maintaining high precision (mean 0.94), comparable to manual curation, and substantially reducing manual effort. CONCLUSION: Automated, LLM-assisted curation offers an efficient and reproducible alternative to manual UMLS browsing.