Large language models for accurate disease detection in electronic health records: the examples of crystal arthropathies.

Journal: RMD open
PMID: 39794274

Abstract

OBJECTIVES: We propose and test a framework to detect disease diagnosis using a recent large language model (LLM), Meta's Llama-3-8B, on French-language electronic health record (EHR) documents. Specifically, it focuses on detecting gout ('goutte' in French), a ubiquitous French term that has multiple meanings beyond the disease. The study compares the performance of the LLM-based framework with traditional natural language processing techniques and tests its dependence on the parameter used.

Authors

  • Nils Bürgisser
    Division of Rheumatology, Geneva University Hospitals, Geneva, Switzerland nburgisser@proton.me.
  • Etienne Chalot
    Information Systems Directorate, Geneva University Hospitals, Geneva, Switzerland.
  • Samia Mehouachi
    Division of Rheumatology, Geneva University Hospitals, Geneva, Switzerland.
  • Clement P Buclin
    Division of Internal Medicine, Geneva University Hospitals, Geneva, Switzerland.
  • Kim Lauper
    Department of medicial specialities, University Hospitals of Geneva, Geneva, Switzerland.
  • Delphine S Courvoisier
    Faculty of Medicine, University of Geneva, Geneva, Switzerland.
  • Denis Mongin
    Division of Rheumatology, Geneva University Hospitals, Geneva, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals