Accuracy of Large Language Models to Identify Stroke Subtypes Within Unstructured Electronic Health Record Data.

Journal: Stroke
Published Date: Jul 25, 2025

Abstract

BACKGROUND: While codes suffice for identifying stroke events in surveillance, accurately classifying stroke types and subtypes using electronic health records remains challenging due to limitations in structured data. This often necessitates manual review of clinical documentation. This study evaluated whether a large language model, GPT-4o, can accurately identify stroke types and subtypes from unstructured clinical notes.

Authors

  • Dylan Owens
    Department of Medicine, UT Southwestern Medical Center, Dallas, TX. (D.O., D.Q.N., E.D.P., A.M.N.).
  • Danh Q Nguyen
    Department of Medicine, UT Southwestern Medical Center, Dallas, TX. (D.O., D.Q.N., E.D.P., A.M.N.).
  • Michael Dohopolski
    Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, TX, United States of America.
  • Justin F Rousseau
    Dell Medical School, University of Texas at Austin, Austin, TX, USA.
  • Eric D Peterson
    Duke Clinical Research Institute, Duke University Medical Center, Durham, NC.
  • Ann Marie Navar
    Division of Cardiology, Department of Internal Medicine, University of Texas Southwestern Medical Center, Dallas, TX, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals