EUVIMEDScopri EUVIMED
VergleichsstudieOpen access

ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis

Brenton T Bicknell iD, Danner Butler iD, Sydney Whalen iD, James Ricks iD, Cory J Dixon iD, Abigail B Clark iD, Olivia Spaedy iD, Adam Skelton iD, Neel Edupuganti iD, Lance Dzubinski iD, Hudson Tate iD, Garrett Dyess iD and 2 more

JMIR Medical Education · 2024-11-06 · 10 · e63430-e63430

DOI: 10.2196/63430 ↗

At a glance

Vergleichsstudie in JMIR Medical Education, published online on 2024-11-06. Written by Brenton T Bicknell and 13 co-authors. Institution: UAB Heersink School of Medicine, 1670 University Blvd, Birmingham, AL, 35233, United States, 1 2566539498. Major MEDLINE topics: Clinical Competence, Educational Measurement, Licensure, Medical. Cited 120 times so far (Crossref); 41 references. The full text is freely available in PubMed Central.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Recent studies, including those by the National Board of Medical Examiners, have highlighted the remarkable capabilities of recent large language models (LLMs) such as ChatGPT in passing the United States Medical Licensing Examination (USMLE). However, there is a gap in detailed analysis of LLM performance in specific medical content areas, thus limiting an assessment of their potential utility in medical education.

Objective

This study aimed to assess and compare the accuracy of successive ChatGPT versions (GPT-3.5, GPT-4, and GPT-4 Omni) in USMLE disciplines, clinical clerkships, and the clinical skills of diagnostics and management.

Methods

This study used 750 clinical vignette-based multiple-choice questions to characterize the performance of successive ChatGPT versions (ChatGPT 3.5 [GPT-3.5], ChatGPT 4 [GPT-4], and ChatGPT 4 Omni [GPT-4o]) across USMLE disciplines, clinical clerkships, and in clinical skills (diagnostics and management). Accuracy was assessed using a standardized protocol, with statistical analyses conducted to compare the models’ performances.

Results

GPT-4o achieved the highest accuracy across 750 multiple-choice questions at 90.4%, outperforming GPT-4 and GPT-3.5, which scored 81.1% and 60.0%, respectively. GPT-4o’s highest performances were in social sciences (95.5%), behavioral and neuroscience (94.2%), and pharmacology (93.2%). In clinical skills, GPT-4o’s diagnostic accuracy was 92.7% and management accuracy was 88.8%, significantly higher than its predecessors. Notably, both GPT-4o and GPT-4 significantly outperformed the medical student average accuracy of 59.3% (95% CI 58.3‐60.3).

Conclusions

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.

Subjects

MeSH terms (MEDLINE)

Clinical CompetenceEducational MeasurementLicensure, MedicalHumansUnited StatesClinical Clerkship

Author keywords

AI in medical educationChatGPTChatGPT 3.5ChatGPT 4ChatGPT 4 OmniLLMUSMLEUnited States Medical Licensing Examinationartificial intelligence in medicineclinical skillseducational technologylarge language modelmedical educationmedical licensing examinationmedical student resources

Authors and institutions

  • UAB Heersink School of Medicine, 1670 University Blvd, Birmingham, AL, 35233, United States, 1 2566539498.
  • University of South Alabama Whiddon College of Medicine, Mobile, AL, United States.
  • University of Illinois College of Medicine, Chicago, IL, United States.
  • Harvard Medical School, Boston, MA, United States.
  • Alabama College of Osteopathic Medicine, Dothan, AL, United States.
  • UT Southwestern Medical Center, Dallas, TX, United States.

ORCID profiles: Brenton T Bicknell, Danner Butler, Sydney Whalen, James Ricks, Cory J Dixon, Abigail B Clark, Olivia Spaedy, Adam Skelton, Neel Edupuganti, Lance Dzubinski, Hudson Tate, Garrett Dyess, Brenessa Lindeman, Lisa Soleymani Lehmann

Cite

APA

Bicknell, B. T., Butler, D., Whalen, S., Ricks, J., Dixon, C. J., Clark, A. B., Spaedy, O., Skelton, A., Edupuganti, N., Dzubinski, L., Tate, H., Dyess, G., Lindeman, B., & Lehmann, L. S. (2024). ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis. JMIR Medical Education, 10, e63430-e63430. https://doi.org/10.2196/63430

Vancouver

Bicknell BT, Butler D, Whalen S, Ricks J, Dixon CJ, Clark AB, et al. ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis. JMIR Medical Education. 2024;10:e63430-e63430. doi:10.2196/63430

BibTeX
@article{Bicknell2024,
  author = {Bicknell, Brenton T and Butler, Danner and Whalen, Sydney and Ricks, James and Dixon, Cory J and Clark, Abigail B and Spaedy, Olivia and Skelton, Adam and Edupuganti, Neel and Dzubinski, Lance and Tate, Hudson and Dyess, Garrett and Lindeman, Brenessa and Lehmann, Lisa Soleymani},
  title = {ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis},
  journal = {JMIR Medical Education},
  year = {2024},
  volume = {10},
  pages = {e63430--e63430},
  doi = {10.2196/63430}
}
Start for free →