Dynamic few-shot prompting for clinical note section classification using lightweight, open-source large language models.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Jul 1, 2025

Abstract

OBJECTIVE: Unlocking clinical information embedded in clinical notes has been hindered to a significant degree by domain-specific and context-sensitive language. Identification of note sections and structural document elements has been shown to improve information extraction and dependent downstream clinical natural language processing (NLP) tasks and applications. This study investigates the viability of a dynamic example selection prompting method to section classification using lightweight, open-source large language models (LLMs) as a practical solution for real-world healthcare clinical NLP systems.

Authors

  • Kurt Miller
    Department of Urology, Charité, Universitätsmedizin, Berlin, Germany.
  • Steven Bedrick
    Oregon Health & Science University, Portland, OR, USA.
  • Qiuhao Lu
    McWilliams School of Biomedical Informatics, University of Texas Health Science Center, Houston, TX, USA.
  • Andrew Wen
    Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, OR, USA.
  • William Hersh
    Department of Medical Informatics & Clinical Epidemiology, School of Medicine, Oregon Health & Science University, Portland, Oregon, United States of America.
  • Kirk Roberts
    The University of Texas Health Science Center at Houston, USA.
  • Hongfang Liu
    Department of Artificial Intelligence & Informatics, Mayo Clinic, Rochester, MN, United States.

Keywords

External Resources

Popular Topics
Recent Journals