ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis
GPT-4o's performance in USMLE disciplines, clinical clerkships, and clinical skills indicates substantial improvements over its predecessors, suggesting significant potential for the use of this technology as an educational aid for medical students. These findings underscore the need for careful consideration when integrating LLMs into medical education, emphasizing the importance of structured curricula to guide their appropriate use and the need for ongoing critical analyses to ensure their reliability and effectiveness.
Authors
- Danner Butler
- A Clark (ORCID: https://orcid.org/0000-0001-6677-5560)
- Brenessa M. Lindeman (ORCID: https://orcid.org/0000-0003-0818-6439)
- Lisa Soleymani Lehmann (ORCID: https://orcid.org/0000-0001-8779-1244)
- Adam J. Skelton
- Neel R Edupuganti
- Brenton T. Bicknell (ORCID: https://orcid.org/0009-0000-2101-2543)
- Garrett Dyess (ORCID: https://orcid.org/0009-0006-5774-6614)
- Lance Dzubinski
- Olivia Spaedy
- Hudson Tate (ORCID: https://orcid.org/0000-0003-1204-7415)
- James Ricks (ORCID: https://orcid.org/0000-0002-1789-355X)
- Sydney Whalen
- Cory J Dixon (ORCID: https://orcid.org/0009-0000-7695-8504)
Institutions
- Harvard University (US)
- Illinois College (US)
- Augusta University (US)
- Alabama College of Osteopathic Medicine (US)
- University of Alabama at Birmingham (US)
- University of Illinois Chicago (US)
- Augusta University Health (US)
- Southwestern Medical Center (US)
- Southwestern Medical Center (US)
- Saint Louis University (US)
- Mass General Brigham (US)
- University of Colorado Anschutz Medical Campus (US)
- University of South Alabama (US)
- The University of Texas Southwestern Medical Center (US)
Publication Details
- Journal
- JMIR Medical Education
- Published
- 2024-09-14
- DOI
- https://doi.org/10.2196/63430
- Citations
- 71
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 8.54