Abstract
Background
Large language model (LLM)–based artificial intelligence chatbots direct the power of large training data sets toward successive, related tasks as opposed to single-ask tasks, for which artificial intelligence already achieves impressive performance. The capacity of LLMs to assist in the full scope of iterative clinical reasoning via successive prompting, in effect acting as artificial physicians, has not yet been evaluated.


Objective
This study aimed to evaluate ChatGPT’s capacity for ongoing clinical decision support via its performance on standardized clinical vignettes.


Methods
We inputted all 36 published clinical vignettes from the Merck Sharpe & Dohme (MSD) Clinical Manual into ChatGPT and compared its accuracy on differential diagnoses, diagnostic testing, final diagnosis, and management based on patient age, gender, and case acuity. Accuracy was measured by the proportion of correct responses to the questions posed within the clinical vignettes tested, as calculated by human scorers. We further conducted linear regression to assess the contributing factors toward ChatGPT’s performance on clinical tasks.


Results
ChatGPT achieved an overall accuracy of 71.7% (95% CI 69.3%-74.1%) across all 36 clinical vignettes. The LLM demonstrated the highest performance in making a final diagnosis with an accuracy of 76.9% (95% CI 67.8%-86.1%) and the lowest performance in generating an initial differential diagnosis with an accuracy of 60.3% (95% CI 54.2%-66.6%). Compared to answering questions about general medical knowledge, ChatGPT demonstrated inferior performance on differential diagnosis (β=–15.8%; P<.001) and clinical management (β=–7.4%; P=.02) question types.


Conclusions
ChatGPT achieves impressive accuracy in clinical decision-making, with increasing strength as it gains more clinical information at its disposal. In particular, ChatGPT demonstrates the greatest accuracy in tasks of final diagnosis as compared to initial diagnosis. Limitations include possible model hallucinations and the unclear composition of ChatGPT’s training data set.
Topics

No keywords indexed for this article. Browse by subject →

References
29
[1]
Artificial intelligence in healthcare

Kun-Hsing Yu, Andrew L. Beam, Isaac S. Kohane

Nature Biomedical Engineering 10.1038/s41551-018-0305-z
[9]
ChatGPT: optimizing language models for dialogueOpen AI202211302023-02-15https://openai.com/blog/chatgpt/
[14]
TerwieschCWould Chat GPT3 get a Wharton MBA? a prediction based on its performance in the operations management courseMack Institute for Innovation Management at the Wharton School, University of Pennsylvania20232023-08-02https://mackinstitute.wharton.upenn.edu/wp-content/uploads/2023/01/Christian-Terwiesch-Chat-GTP.pdf
[21]
Case studiesMerck Manual, Professional Version2023-02-01https://www.merckmanuals.com/professional/pages-with-widgets/case-studies?mode=list
[24]
Artificial intelligence and algorithmic bias: implications for health systems

Trishan Panch, Heather Mattie, Rifat Atun

Journal of Global Health 10.7189/jogh.09.020318
[25]
Smedley, BD Unequal Treatment: Confronting Racial and Ethnic Disparities in Health Care (2003)
[28]
Survey of Hallucination in Natural Language Generation

Ziwei Ji, Nayeon Lee, Rita Frieske et al.

ACM Computing Surveys 10.1145/3571730
Cited By
282
AI-assisted learning: ChatGPT for anamnesis in women’s health education

Daniela S Espírito Santo, Thiago Lott Bezerra · 2026

Medical Education Online
Journal of Primary Care & Commu...
JAMA Network Open
Oral Surgery, Oral Medicine, Oral P...
JAMA Network Open
Large Language Models in Neurological Practice: Real-World Study

Natale Vincenzo Maiorana, Sara Marceglia · 2025

Journal of Medical Internet Researc...
Journal of Medical Internet Researc...
Metrics
282
Citations
29
References
Details
Published
Aug 22, 2023
Vol/Issue
25
Pages
e48659
Cite This Article
Arya Rao, Michael Pang, John Kim, et al. (2023). Assessing the Utility of ChatGPT Throughout the Entire Clinical Workflow: Development and Usability Study. Journal of Medical Internet Research, 25, e48659. https://doi.org/10.2196/48659