The Digital Shift: Assessing ChatGPT’s Capability as a New Age Standardized Patient. (Preprint)

Author:

Cross JosephORCID,Kayalackakom Tarron,Robinson Raymond E,Vaughans Andrea,Sebastian Roopa,Hood Ricardo,Lewis CourtneyORCID,Devaraju Sumanth,Honnavar Prasanna,Naik Sheetal,Joseph Jillwin,Anand Nikilish,Mohammed Abdalla,Johnson Asjah,Cohen Eliran,Adeniji Teniola,Nnenna Nnaji Aisling,George Julia

Abstract

BACKGROUND

Standardized patients (SPs) have been crucial in medical education, offering realistic patient interactions to students. Despite their benefits, SP training is resource-intensive, and access can be limited. Advances in artificial intelligence, particularly with large language models like ChatGPT, present new opportunities for virtual SPs, potentially addressing these limitations.

OBJECTIVE

To assess medical students' perceptions and experiences of using ChatGPT as a standardized patient (SP) and to evaluate ChatGPT’s effectiveness in performing as a virtual SP in a medical school setting.

METHODS

This qualitative study, approved by the AUA Institutional Review Board (IRB), involved eleven medical student volunteers (5 females, 6 males, aged 20-32) from the American University of Antigua (AUA) College of Medicine. 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. Thematic analysis was conducted on the transcribed and coded responses, with inductive category formation.

RESULTS

Thematic analysis identified key themes pre-interaction including: technology limitations (e.g., prompt engineering difficulties), learning efficacy (e.g., potential for personalized learning, reduced interview stress), verisimilitude (e.g., absence of visual cues), and trust (e.g., concerns about AI accuracy). Post-interaction, students noted improvements in prompt engineering, some alignment issues (e.g., limited responses on sensitive topics), maintained learning efficacy (e.g., convenience, repetition), and continued verisimilitude challenges (e.g., lack of empathy and non-verbal cues). No significant trust issues were reported post-interaction. Despite some limitations, students found ChatGPT a valuable supplement to traditional SPs, enhancing practice flexibility and diagnostic skills.

CONCLUSIONS

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 artificial intelligence (AI) are recommended to enhance the utility of virtual SPs.

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3