Clinical 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…

• GA
  Gordon and Betty Moore Foundation

  Award: 12409
• AH
  American Heart Association
• GC
  Georgia Clinical and Translational Science Alliance

  Award: UL1TR003142
• NI
  National Institutes of Health

  Awards: UG1DA015815, UL1TR003142
• NI
  National Institute of Allergy and Infectious Diseases

  Award: 1R01AI17812101
• NC
  National Center for Advancing Translational Sciences

  Award: UL1TR003142