Cross Joseph, Kayalackakom Tarron, Robinson Raymond E, Vaughans Andrea, Sebastian Roopa, Hood Ricardo, Lewis Courtney, Devaraju Sumanth, Honnavar Prasanna, Naik Sheetal, Joseph Jillwin, Anand Nikhilesh, Mohammed Abdalla, Johnson Asjah, Cohen Eliran, Adeniji Teniola, Nnenna Nnaji Aisling, George Julia Elizabeth
Medical University of the Americas, PO Box 701, Charlestown, Saint Kitts and Nevis, 1 9788629500 ext 364.
Department of Education Enhancement, College of Medicine, American University of Antigua, St Johns, Antigua and Barbuda.
JMIR Med Educ. 2025 May 20;11:e63353. doi: 10.2196/63353.
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 (AI), particularly with large language models such as ChatGPT, present new opportunities for virtual SPs, potentially addressing these limitations.
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.
This qualitative study, approved by the American University of Antigua Institutional Review Board, involved 9 students (5 females and 4 males, aged 22-48 years) from the American University of Antigua 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.
Thematic analysis identified key themes preinteraction including technology limitations (eg, prompt engineering difficulties), learning efficacy (eg, potential for personalized learning and reduced interview stress), verisimilitude (eg, absence of visual cues), and trust (eg, concerns about AI accuracy). Postinteraction, students noted improvements in prompt engineering, some alignment issues (eg, limited responses on sensitive topics), maintained learning efficacy (eg, convenience and repetition), and continued verisimilitude challenges (eg, lack of empathy and nonverbal cues). No significant trust issues were reported postinteraction. Despite some limitations, students found ChatGPT as a valuable supplement to traditional SPs, enhancing practice flexibility and diagnostic skills.
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.
标准化病人（SPs）在医学教育中至关重要，为学生提供真实的患者互动体验。尽管有诸多益处，但SP培训资源密集，且参与机会可能有限。人工智能（AI）的进步，尤其是像ChatGPT这样的大语言模型，为虚拟标准化病人带来了新机遇，有可能解决这些限制。
本研究旨在评估医学生对使用ChatGPT作为标准化病人的看法和体验，并评估ChatGPT在医学院环境中作为虚拟标准化病人的有效性。
这项定性研究经安提瓜美国大学机构审查委员会批准，涉及安提瓜美国大学医学院的9名学生（5名女性和4名男性，年龄在22至48岁之间）。在现场角色扮演期间观察学生，他们使用预先设定的提示与作为标准化病人的ChatGPT进行互动。在互动前后进行了一项包含15个问题的结构化调查。对转录和编码后的回答进行主题分析，并形成归纳类别。
主题分析确定了互动前的关键主题，包括技术限制（如提示工程困难）、学习效果（如个性化学习潜力和减轻面试压力）、逼真度（如缺乏视觉线索）和信任（如对人工智能准确性的担忧）。互动后，学生们指出提示工程有所改进，存在一些一致性问题（如对敏感话题的回答有限），学习效果得以维持（如便利性和重复性），逼真度挑战依然存在（如缺乏同理心和非语言线索）。互动后未报告重大信任问题。尽管存在一些限制，学生们发现ChatGPT是传统标准化病人的宝贵补充，增强了实践灵活性和诊断技能。
ChatGPT可以有效地在医学教育中增强传统标准化病人的作用，提供可及、灵活的实践机会。然而，由于逼真度方面的限制和提示工程挑战，它不能完全取代真人标准化病人。建议将提示工程纳入医学课程，并持续推进人工智能技术，以加强虚拟标准化病人的应用。
