CUI-Curate: a GraphRAG-based framework for automated clinical concept curation for NLP applications.

Abstract

Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs). For many downstream tasks, however, the clinically meaningful unit is not a single CUI but a concept set comprising related synonyms, subtypes, and associated concepts. Constructing these sets is labour-intensive, inconsistently performed, and poorly supported by existing tools. We present CUI-Curate, a graph-based retrieval-augmented-generation (GraphRAG) framework for automated UMLS concept set curation. A UMLS knowledge graph was constructed and embedded for semantic retrieval. Candidate CUIs were retrieved using graph-based expansion and then filtered and classified using large language models (GPT-5 and Qwen3-32B). The framework was evaluated on five lexically heterogeneous clinical concepts against manually curated concept sets and gold-standard concept sets. CUI-Curate produced substantially larger and more complete concept sets than the manual benchmarks. A single retrieval configuration across concepts achieved high recall of definitive concepts with manageable candidate sets. GPT-5 outperformed manual curation for all concepts and retained at least 95% of definitive gold-standard CUIs, while Qwen3-32B achieved comparable but slightly lower performance. Many missed concepts were not observed in 10,000 MIMIC-III notes. CUI-Curate infrastructure and end-to-end processing were inexpensive and stable across runs. CUI-Curate offers a scalable, reproducible, and cost-efficient approach for generating clinician-reviewable UMLS concept sets tailored to clinical natural language processing and phenotyping applications.