Clinical artificial intelligence: teaching a large language model to generate recommendations that align with guidelines for the surgical management of GERD.

Journal: Surgical endoscopy
PMID: 39134725

Abstract

BACKGROUND: Large Language Models (LLMs) provide clinical guidance with inconsistent accuracy due to limitations with their training dataset. LLMs are "teachable" through customization. We compared the ability of the generic ChatGPT-4 model and a customized version of ChatGPT-4 to provide recommendations for the surgical management of gastroesophageal reflux disease (GERD) to both surgeons and patients.

Authors

  • Bright Huo
    Division of General Surgery, Department of Surgery, McMaster University, Hamilton, ON, Canada.
  • Nana Marfo
    Ross University School of Medicine, Miramar, FL, USA.
  • Patricia Sylla
    Division of Colon and Rectal Surgery, Department of Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
  • Elisa Calabrese
    University of California South California, East Bay, Oakland, CA, USA.
  • Sunjay Kumar
    Department of General Surgery, Thomas Jefferson University Hospital, Philadelphia, PA, USA.
  • Bethany J Slater
    Department of Surgery, University of Chicago, Chicago, IL, USA.
  • Danielle S Walsh
    Department of Surgery, University of Kentucky, Lexington, KY, USA.
  • Wesley Vosburg
    Department of Surgery, Harvard Medical School, Mount Auburn Hospital, Cambridge, MA, USA. wesvosburg@gmail.com.

Keywords

External Resources

Popular Topics
Recent Journals