How GPT models perform on the United States medical licensing examination: a systematic review
Discover Applied Sciences · 18.09.2024 · 6 (10)
DOI: 10.1007/s42452-024-06194-5 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Discover Applied Sciences, online erschienen am 18.09.2024. Verfasst von Dana Brin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The United States Medical Licensing Examination (USMLE) assesses physicians' competency. Passing this exam is required to practice medicine in the U.S. With the emergence of large language models (LLMs) like ChatGPT and GPT-4, understanding their performance on these exams illuminates their potential in medical education and healthcare. A PubMed literature search following the 2020 PRISMA guidelines was conducted, focusing on studies using official USMLE questions and GPT models. Six relevant studies were found out of 19 screened, with GPT-4 showcasing the highest accuracy rates of 80–100% on the USMLE. Open-ended prompts typically outperformed multiple-choice ones, with 5-shot prompting slightly edging out zero-shot. LLMs, especially GPT-4, display proficiency in tackling USMLE questions. As AI integrates further into healthcare, ongoing assessments against trusted benchmarks are essential.
Zitieren
APA
Brin, D., Sorin, V., Konen, E., Nadkarni, G., Glicksberg, B. S., & Klang, E. (2024). How GPT models perform on the United States medical licensing examination: a systematic review. Discover Applied Sciences, 6(10). https://doi.org/10.1007/s42452-024-06194-5
Vancouver
Brin D, Sorin V, Konen E, Nadkarni G, Glicksberg BS, Klang E. How GPT models perform on the United States medical licensing examination: a systematic review. Discover Applied Sciences. 2024;6(10). doi:10.1007/s42452-024-06194-5
BibTeX
@article{Brin2024,
author = {Brin, Dana and Sorin, Vera and Konen, Eli and Nadkarni, Girish and Glicksberg, Benjamin S. and Klang, Eyal},
title = {How GPT models perform on the United States medical licensing examination: a systematic review},
journal = {Discover Applied Sciences},
year = {2024},
volume = {6},
number = {10},
doi = {10.1007/s42452-024-06194-5}
}
EUVIMED