A dataset and benchmark for hospital course summarization with adapted large language models.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 39786555

Abstract

OBJECTIVE: Brief hospital course (BHC) summaries are clinical documents that summarize a patient's hospital stay. While large language models (LLMs) depict remarkable capabilities in automating real-world tasks, their capabilities for healthcare applications such as synthesizing BHCs from clinical notes have not been shown. We introduce a novel preprocessed dataset, the MIMIC-IV-BHC, encapsulating clinical note and BHC pairs to adapt LLMs for BHC synthesis. Furthermore, we introduce a benchmark of the summarization performance of 2 general-purpose LLMs and 3 healthcare-adapted LLMs.

Authors

  • Asad Aali
    Department of Radiology, Stanford University, Stanford, CA 94304, United States.
  • Dave Van Veen
    Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USA.
  • Yamin Ishraq Arefeen
    Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712, United States.
  • Jason Hom
    Stanford University School of Medicine, Stanford, CA, USA.
  • Christian Bluethgen
    Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI), Stanford University, Sheffield, USA.
  • Eduardo Pontes Reis
    Department of Radiology, Stanford University, Stanford, CA, USA. eduardo.reis@einstein.br.
  • Sergios Gatidis
    Department of Radiology, Diagnostic and Interventional Radiology, Eberhard Karls University Tübingen, Germany.
  • Namuun Clifford
    School of Nursing, The University of Texas at Austin, Austin, TX 78712, United States.
  • Joseph Daws
    One Medical, San Francisco, CA 94111, United States.
  • Arash S Tehrani
    One Medical, San Francisco, CA 94111, United States.
  • Jangwon Kim
    Amazon, Seattle, WA 98109, United States.
  • Akshay S Chaudhari
    Department of Radiology, Stanford University, Stanford, California.

Keywords

External Resources

Popular Topics
Recent Journals