Assessing the Ability of a Large Language Model to Score Free-Text Medical Student Clinical Notes: Quantitative Study
JMIR Medical Education · 2024-07-25 · 10 · e56342-e56342
DOI: 10.2196/56342 ↗At a glance
Journal article in JMIR Medical Education, published online on 2024-07-25. Written by Harry B Burke and 6 co-authors. Institution: Uniformed Services University of the Health Sciences, Bethesda, MD, 20814, United States, 1 301-938-2212. Major MEDLINE topics: Students, Medical. Cited 42 times so far (Crossref); 24 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Teaching medical students the skills required to acquire, interpret, apply, and communicate clinical information is an integral part of medical education. A crucial aspect of this process involves providing students with feedback regarding the quality of their free-text clinical notes.
Objective
The goal of this study was to assess the ability of ChatGPT 3.5, a large language model, to score medical students’ free-text history and physical notes.
Methods
This is a single-institution, retrospective study. Standardized patients learned a prespecified clinical case and, acting as the patient, interacted with medical students. Each student wrote a free-text history and physical note of their interaction. The students’ notes were scored independently by the standardized patients and ChatGPT using a prespecified scoring rubric that consisted of 85 case elements. The measure of accuracy was percent correct.
Results
The study population consisted of 168 first-year medical students. There was a total of 14,280 scores. The ChatGPT incorrect scoring rate was 1.0%, and the standardized patient incorrect scoring rate was 7.2%. The ChatGPT error rate was 86%, lower than the standardized patient error rate. The ChatGPT mean incorrect scoring rate of 12 (SD 11) was significantly lower than the standardized patient mean incorrect scoring rate of 85 (SD 74 ; P =.002).
Conclusions
ChatGPT demonstrated a significantly lower error rate compared to standardized patients. This is the first study to assess the ability of a generative pretrained transformer (GPT) program to score medical students’ standardized patient-based free-text clinical notes. It is expected that, in the near future, large language models will provide real-time feedback to practicing physicians regarding their free-text notes. GPT artificial intelligence programs represent an important advance in medical education and medical practice.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Uniformed Services University of the Health Sciences, Bethesda, MD, 20814, United States, 1 301-938-2212.
- Defense Health Agency, Falls Church, VA, United States.
ORCID profiles: Harry B Burke, Albert Hoang, Joseph O Lopreiato, Heidi King, Paul Hemmer, Michael Montgomery, Viktoria Gagarin
Cite
APA
Burke, H. B., Hoang, A., Lopreiato, J. O., King, H., Hemmer, P., Montgomery, M., & Gagarin, V. (2024). Assessing the Ability of a Large Language Model to Score Free-Text Medical Student Clinical Notes: Quantitative Study. JMIR Medical Education, 10, e56342-e56342. https://doi.org/10.2196/56342
Vancouver
Burke HB, Hoang A, Lopreiato JO, King H, Hemmer P, Montgomery M, et al. Assessing the Ability of a Large Language Model to Score Free-Text Medical Student Clinical Notes: Quantitative Study. JMIR Medical Education. 2024;10:e56342-e56342. doi:10.2196/56342
BibTeX
@article{Burke2024,
author = {Burke, Harry B and Hoang, Albert and Lopreiato, Joseph O and King, Heidi and Hemmer, Paul and Montgomery, Michael and Gagarin, Viktoria},
title = {Assessing the Ability of a Large Language Model to Score Free-Text Medical Student Clinical Notes: Quantitative Study},
journal = {JMIR Medical Education},
year = {2024},
volume = {10},
pages = {e56342--e56342},
doi = {10.2196/56342}
}
EUVIMED