Assessing the ability of a large language model to score free text medical student notes (Preprint)

Abstract

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.

The objective of this project is to assess the ability of ChatGPT 3.5 (ChatGPT) to score medical students’ free text history and physical notes.

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. ChatGPT is a large language model (LLM). 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.

The study population consisted of 168 first year medical students. There was a total of 14,280 scores. The standardized patient incorrect scoring rate (error) was 7.2% and the ChatGPT incorrect scoring rate was 1.0%. The ChatGPT error rate was 86% lower than the standardized patient error rate. The standardized patient mean incorrect scoring rate of 85 (SD 74) was significantly higher than the ChatGPT mean incorrect scoring rate of 12 (SD 11), p = 0.002.

ChatGPT had a significantly lower error rate than the standardized patients. This suggests that an LLM can be used to score medical students’ notes. Furthermore, it is expected that, in the near future, LLM programs will provide real time feedback to practicing physicians regarding their free text notes. Generative pretrained transformer artificial intelligence programs represent an important advance in medical education and in the practice of medicine.