Artificial Intelligence Passes U.S. Medical Licensing Exam

ChatGPT

By Staff Reporters

***

***

Two papers show that large language models, including ChatGPT, can pass the USMLE. The papers highlighted different approaches to using large language models to take the USMLE, which is comprised of three exams: Step 1, Step 2 CK, and Step 3. ChatGPT is an artificial intelligence (AI) search tool that mimics long-form writing based on prompts from human users. It was developed by OpenAI, and became popular after several social media posts showed potential uses for the tool in clinical practice, often with mixed results.

According to Victor Tseng, MD, of Ansible Health in Mountain View, California, and colleagues, the results showed “new and surprising evidence” that this AI tool was up to the challenge. Tseng and team noted that ChatGPT was able to perform at >50% accuracy across all of the exams, and even achieved 60% in most of their analyses. While the USMLE passing threshold does vary between years, the authors said that passing is approximately 60% most years.

Source: Michael DePeau-Wilson, Medpage Today [1/19/23]

RELATED: https://medicalexecutivepost.com/2013/06/21/will-future-doctors-need-a-medical-license/

***

***

ORDER: https://www.amazon.com/Dictionary-Health-Information-Technology-Security/dp/0826149952/ref=sr_1_5?ie=UTF8&s=books&qid=1254413315&sr=1-5

COMMENTS APPRECIATED

Thank You

***

%d bloggers like this: