biostudies-literatureLopez INCATS NIH HHSU.S. Department of Health & Human Services | NIH | National Institute of Allergy and Infectious Diseases (NIAID)45https://www.ebi.ac.uk/biostudies/studies/S-EPMC11743751biostudies-literatureUnknown8(1)Large language models (LLMs) with retrieval-augmented generation (RAG) have improved information extraction over previous methods, yet their reliance on embeddings often leads to inefficient retrieval. We introduce CLinical Entity Augmented Retrieval (CLEAR), a RAG pipeline that retrieves information using entities. We compared CLEAR to embedding RAG and full-note approaches for extracting 18 variables using six LLMs across 20,000 clinical notes. Average F1 scores were 0.90, 0.86, and 0.79; inference times were 4.95, 17.41, and 20.08 s per note; average model queries were 1.68, 4.94, and 4.18 per note; and average input tokens were 1.1k, 3.8k, and 6.1k per note for CLEAR, embedding RAG, and full-note approaches, respectively. In conclusion, CLEAR utilizes clinical entities for information retrieval and achieves >70% reduction in token usage and inference time with improved performance compared to modern methods.NPJ digital medicineClinical entity augmented retrieval for clinical information extraction.PMC11743751UM1 TR004921UL1 TR0031421R01AI17812101Ma SPVedula KMaddali MGallo RJNarayanan STate SLopez ISwaminathan ANateghi Haredasht FChen JHShah NHLiang ASfalseClinical entity augmented retrieval for clinical information extraction.Large language models (LLMs) with retrieval-augmented generation (RAG) have improved information extraction over previous methods, yet their reliance on embeddings often leads to inefficient retrieval. We introduce CLinical Entity Augmented Retrieval (CLEAR), a RAG pipeline that retrieves information using entities. We compared CLEAR to embedding RAG and full-note approaches for extracting 18 variables using six LLMs across 20,000 clinical notes. Average F1 scores were 0.90, 0.86, and 0.79; inference times were 4.95, 17.41, and 20.08 s per note; average model queries were 1.68, 4.94, and 4.18 per note; and average input tokens were 1.1k, 3.8k, and 6.1k per note for CLEAR, embedding RAG, and full-note approaches, respectively. In conclusion, CLEAR utilizes clinical entities for information retrieval and achieves >70% reduction in token usage and inference time with improved performance compared to modern methods.2025-01-01T00:00:00Z2025 Jan2025-04-22T10:32:29.612Z2025-04-22T10:32:29.612ZS-EPMC117437513982880010.1038/s41746-024-01377-1