Back to Search
Start Over
ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis
- Source :
- Journal of Medical Internet Research, Vol 26, p e56110 (2024)
- Publication Year :
- 2024
- Publisher :
- JMIR Publications, 2024.
-
Abstract
- BackgroundOpenAI’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. ObjectiveThis study compares the diagnostic accuracy of ChatGPT with GPT-3.5 and GPT-4 and primary treating resident physicians in an ED setting. MethodsAmong 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. ResultsThe 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
Details
- Language :
- English
- ISSN :
- 14388871
- Volume :
- 26
- Database :
- Directory of Open Access Journals
- Journal :
- Journal of Medical Internet Research
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.0eb83f8e064440a6bafea132bca853f8
- Document Type :
- article
- Full Text :
- https://doi.org/10.2196/56110