Assessing ChatGPT's Capability as a New Age Standardized Patient: Qualitative Study

By: Joseph Cross, et al
Submitted by: Marsha Harman, Rush Center for Clinical Skills and Simulation

This article offers a snapshot of the advantages and disadvantages of using ChatGPT as a virtual SP and ultimately concludes it can be an effective supplement to, but not a replacement for, working with human SPs.
 
This study aims to assess medical students' perceptions and experiences of using ChatGPT as an SP and to evaluate ChatGPT's effectiveness in performing as a virtual SP in a medical school setting.Students were observed during a live role-play, interacting with ChatGPT as an SP using a predetermined prompt. A structured 15-question survey was administered before and after the interaction. Despite some limitations, students found ChatGPT as a valuable supplement to traditional SPs, enhancing practice flexibility and diagnostic skills. The authors conclude that ChatGPT can effectively augment traditional SPs in medical education, offering accessible, flexible practice opportunities. However, it cannot fully replace human SPs due to limitations in verisimilitude and prompt engineering challenges. Integrating prompt engineering into medical curricula and continuous advancements in AI are recommended to enhance the use of virtual SPs.
 
Read the full article in JMIR Medical Education here.
  
Communications and Connections Committee Mission: “To bring high quality reporting of current research, trends, techniques and information regarding SP methodology and other relevant industry articles to the attention of the membership through the web-based ASPE eNews blog.”
  
Please provide comments, questions or suggestions about the ASPE eNews Blog here.
Share this post:

Comments on "Assessing ChatGPT's Capability as a New Age Standardized Patient: Qualitative Study"

Comments 0-5 of 0

Please login to comment