EUVIMEDEUVIMED entdecken
Open Access

ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis

John Michael Hoppe iD, Matthias K Auer iD, Anna Strüven iD, Steffen Massberg iD, Christopher Stremmel iD

Journal of Medical Internet Research · 08.07.2024 · 26 · e56110

DOI: 10.2196/56110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 08.07.2024. Verfasst von John Michael Hoppe und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine IV, LMU University Hospital, Munich, Germany. Hauptthemen laut MEDLINE: Emergency Service, Hospital. Die Arbeit wurde bisher 100-mal zitiert (Crossref) und nennt 11 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

OpenAI’s ChatGPT is a pioneering artificial intelligence (AI) in the field of natural language processing, and it holds significant potential in medicine for providing treatment advice. Additionally, recent studies have demonstrated promising results using ChatGPT for emergency medicine triage. However, its diagnostic accuracy in the emergency department (ED) has not yet been evaluated.

Objective

This study compares the diagnostic accuracy of ChatGPT with GPT-3.5 and GPT-4 and primary treating resident physicians in an ED setting.

Methods

Among 100 adults admitted to our ED in January 2023 with internal medicine issues, the diagnostic accuracy was assessed by comparing the diagnoses made by ED resident physicians and those made by ChatGPT with GPT-3.5 or GPT-4 against the final hospital discharge diagnosis, using a point system for grading accuracy.

Results

The study enrolled 100 patients with a median age of 72 (IQR 58.5-82.0) years who were admitted to our internal medicine ED primarily for cardiovascular, endocrine, gastrointestinal, or infectious diseases. GPT-4 outperformed both GPT-3.5 (P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Emergency Service, HospitalHumansRetrospective StudiesAgedFemaleMiddle AgedMaleAged, 80 and overArtificial IntelligencePhysiciansNatural Language ProcessingTriage

Stichwörter der Autor:innen

AIChatGPTNLPOpenAIaccuracyartificial intelligencediagnosisdiagnostic accuracyemergency departmentemergency medicine triageinternal medicinenatural language processingphysicianphysicianstriage

Autor:innen und Institutionen

  • Department of Medicine IV, LMU University Hospital, Munich, Germany.
  • Department of Medicine I, LMU University Hospital, Munich, Germany.
  • Munich Heart Alliance Partner Site, Deutsches Zentrum für Herz-Kreislaufforschung (German Centre for Cardiovascular Research), LMU University Hospital, Munich, Germany.

ORCID-Profile: John Michael Hoppe, Matthias K Auer, Anna Strüven, Steffen Massberg, Christopher Stremmel

Zitieren

APA

Hoppe, J. M., Auer, M. K., Strüven, A., Massberg, S., & Stremmel, C. (2024). ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis. Journal of Medical Internet Research, 26, e56110. https://doi.org/10.2196/56110

Vancouver

Hoppe JM, Auer MK, Strüven A, Massberg S, Stremmel C. ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis. Journal of Medical Internet Research. 2024;26:e56110. doi:10.2196/56110

BibTeX
@article{Hoppe2024,
  author = {Hoppe, John Michael and Auer, Matthias K and Strüven, Anna and Massberg, Steffen and Stremmel, Christopher},
  title = {ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis},
  journal = {Journal of Medical Internet Research},
  year = {2024},
  volume = {26},
  pages = {e56110},
  doi = {10.2196/56110}
}
Kostenlos starten →