Accuracy of Commercial Large Language Model (ChatGPT) to Predict the Diagnosis for Prehospital Patients Suitable for Ambulance Transport Decisions: Diagnostic Accuracy Study.

Journal: Prehospital emergency care
PMID: 39889232

Abstract

OBJECTIVES: While ambulance transport decisions guided by artificial intelligence (AI) could be useful, little is known of the accuracy of AI in making patient diagnoses based on the pre-hospital patient care report (PCR). The primary objective of this study was to assess the accuracy of ChatGPT (OpenAI, Inc., San Francisco, CA, USA) to predict a patient's diagnosis using the PCR by comparing to a reference standard assigned by experienced paramedics. The secondary objective was to classify cases where the AI diagnosis did not agree with the reference standard as paramedic correct, ChatGPT correct, or equally correct.

Authors

  • Eric D Miller
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Jeffrey Michael Franc
    Department of Emergency Medicine, University of Alberta, Edmonton, AB, Canada. jeffrey.franc@ualberta.ca.
  • Attila J Hertelendy
    Department of Information Systems and Business Analytics, College of Business, Florida International University, Miami, FL 33174, USA; Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Disaster Medicine Fellowship, Boston, MA, USA.
  • Fadi Issa
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Alexander Hart
    Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA.
  • Christina A Woodward
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Bradford Newbury
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Kiera Newbury
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Dana Mathew
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Kimberly Whitten-Chung
    Pikes Peak State College, Colorado Springs, Colorado.
  • Eric Bauer
    FlightbridgeED, Bowling Green, Kentucky.
  • Amalia Voskanyan
    BIDMC Disaster Medicine Fellowship, Department of Emergency Medicine, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts.
  • Gregory R Ciottone
    Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School.

Keywords

External Resources

Popular Topics
Recent Journals