• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

探索性评估 ChatGPT 在医学教育中的辅助作用:谨慎使用。

An explorative assessment of ChatGPT as an aid in medical education: Use it with caution.

机构信息

Department of Medical Sciences, Hackensack Meridian School of Medicine, Nutley, NJ, USA.

出版信息

Med Teach. 2024 May;46(5):657-664. doi: 10.1080/0142159X.2023.2271159. Epub 2023 Oct 20.

DOI:10.1080/0142159X.2023.2271159
PMID:37862566
Abstract

OBJECTIVE

To explore the use of ChatGPT by educators and students in a medical school setting.

METHOD

This study used the public version of ChatGPT launched by OpenAI on November 30, 2022 (https://openai.com/blog/chatgpt/). We employed prompts to ask ChatGPT to 1) generate a content outline for a session on the topics of cholesterol, lipoproteins, and hyperlipidemia for medical students; 2) produce a list of learning objectives for the session; and 3) write assessment questions with and without clinical vignettes related to the identified learning objectives. We assessed the responses by ChatGPT for accuracy and reliability to determine the potential of the chatbot as an aid to educators and as a "know-it-all" medical information provider for students.

RESULTS

ChatGPT can function as an aid to educators, but it is not yet suitable as a reliable information resource for educators and medical students.

CONCLUSION

ChatGPT can be a useful tool to assist medical educators in drafting course and session content outlines and create assessment questions. At the same time, caution must be taken as ChatGPT is prone to providing incorrect information; expert oversight and caution are necessary to ensure the information generated is accurate and beneficial to students. Therefore, it is premature for medical students to use the current version of ChatGPT as a "know-it-all" information provider. In the future, medical educators should work with programming experts to explore and grow the full potential of AI in medical education.

摘要

目的

探索医学教育者和学生在医学院环境中使用 ChatGPT。

方法

本研究使用 OpenAI 于 2022 年 11 月 30 日发布的 ChatGPT 公共版本(https://openai.com/blog/chatgpt/)。我们采用提示词要求 ChatGPT 生成以下内容:1)为医学生设计的关于胆固醇、脂蛋白和高血脂课程的内容大纲;2)该课程的学习目标清单;3)与识别出的学习目标相关的无临床案例和有临床案例的评估问题。我们根据 ChatGPT 回答的准确性和可靠性来评估其回复,以确定该聊天机器人作为教育者辅助工具以及学生“万事通”型医学信息提供者的潜力。

结果

ChatGPT 可以作为教育者的辅助工具,但还不能作为教育者和医学生可靠的信息资源。

结论

ChatGPT 可以作为医学教育者起草课程和课程内容大纲以及创建评估问题的有用工具。同时,必须谨慎使用,因为 ChatGPT 容易提供错误信息;为了确保生成的信息准确且对学生有益,需要专家监督和谨慎。因此,医学生目前还不能将当前版本的 ChatGPT 用作“万事通”型信息提供者。未来,医学教育者应与编程专家合作,探索和挖掘人工智能在医学教育中的全部潜力。

相似文献

1
An explorative assessment of ChatGPT as an aid in medical education: Use it with caution.探索性评估 ChatGPT 在医学教育中的辅助作用:谨慎使用。
Med Teach. 2024 May;46(5):657-664. doi: 10.1080/0142159X.2023.2271159. Epub 2023 Oct 20.
2
Integration of ChatGPT Into a Course for Medical Students: Explorative Study on Teaching Scenarios, Students' Perception, and Applications.将 ChatGPT 融入医学生课程:教学场景、学生感知和应用的探索性研究。
JMIR Med Educ. 2024 Aug 22;10:e50545. doi: 10.2196/50545.
3
Using ChatGPT in Psychiatry to Design Script Concordance Tests in Undergraduate Medical Education: Mixed Methods Study.在精神病学中使用 ChatGPT 设计本科医学教育中的脚本一致性测试:混合方法研究。
JMIR Med Educ. 2024 Apr 4;10:e54067. doi: 10.2196/54067.
4
Incorporating ChatGPT in Medical Informatics Education: Mixed Methods Study on Student Perceptions and Experiential Integration Proposals.将 ChatGPT 融入医学信息学教育:学生认知和体验融入建议的混合方法研究。
JMIR Med Educ. 2024 Mar 20;10:e51151. doi: 10.2196/51151.
5
Case-based MCQ generator: A custom ChatGPT based on published prompts in the literature for automatic item generation.基于病例的多项选择题生成器:一种自定义的 ChatGPT,基于文献中发布的提示进行自动项目生成。
Med Teach. 2024 Aug;46(8):1018-1020. doi: 10.1080/0142159X.2024.2314723. Epub 2024 Feb 10.
6
Educational Utility of Clinical Vignettes Generated in Japanese by ChatGPT-4: Mixed Methods Study.ChatGPT-4 生成的日语临床病例对教育的效用:混合方法研究。
JMIR Med Educ. 2024 Aug 13;10:e59133. doi: 10.2196/59133.
7
Capabilities and Limitations of ChatGPT in Anatomy Education: An Interaction With ChatGPT.ChatGPT在解剖学教育中的能力与局限性:与ChatGPT的一次互动
Cureus. 2024 Sep 9;16(9):e69000. doi: 10.7759/cureus.69000. eCollection 2024 Sep.
8
The Revival of Essay-Type Questions in Medical Education: Harnessing Artificial Intelligence and Machine Learning.医学教育中论文型问题的复兴:利用人工智能和机器学习。
J Coll Physicians Surg Pak. 2024 May;34(5):595-599. doi: 10.29271/jcpsp.2024.05.595.
9
The rise of ChatGPT: Exploring its potential in medical education.ChatGPT 的兴起:探索其在医学教育中的潜力。
Anat Sci Educ. 2024 Jul-Aug;17(5):926-931. doi: 10.1002/ase.2270. Epub 2023 Mar 28.
10
Large Language Models in Medical Education: Comparing ChatGPT- to Human-Generated Exam Questions.大语言模型在医学教育中的应用:比较 ChatGPT 与人工生成的考试题目。
Acad Med. 2024 May 1;99(5):508-512. doi: 10.1097/ACM.0000000000005626. Epub 2023 Dec 28.

引用本文的文献

1
Ten tips to harnessing generative AI for high-quality MCQS in medical education assessment.在医学教育评估中利用生成式人工智能生成高质量多项选择题的十条建议。
Med Educ Online. 2025 Dec;30(1):2532682. doi: 10.1080/10872981.2025.2532682. Epub 2025 Jul 17.
2
Student perceptions of GenAI as a virtual tutor to support collaborative research training for health professionals.学生对生成式人工智能作为虚拟导师以支持卫生专业人员协作研究培训的看法。
BMC Med Educ. 2025 Jul 1;25(1):895. doi: 10.1186/s12909-025-07390-6.
3
Large Language Model Architectures in Health Care: Scoping Review of Research Perspectives.
医疗保健中的大语言模型架构:研究视角的范围综述
J Med Internet Res. 2025 Jun 19;27:e70315. doi: 10.2196/70315.
4
Using a Hybrid of AI and Template-Based Method in Automatic Item Generation to Create Multiple-Choice Questions in Medical Education: Hybrid AIG.在医学教育中运用人工智能与基于模板的方法相结合的混合方式进行自动试题生成以创建多项选择题:混合式自动试题生成
JMIR Form Res. 2025 Apr 4;9:e65726. doi: 10.2196/65726.
5
ChatGPT and Other Large Language Models in Medical Education - Scoping Literature Review.医学教育中的ChatGPT及其他大语言模型——文献综述
Med Sci Educ. 2024 Nov 13;35(1):555-567. doi: 10.1007/s40670-024-02206-6. eCollection 2025 Feb.
6
Evaluation of Chat Generative Pre-trained Transformer and Microsoft Copilot Performance on the American Society of Surgery of the Hand Self-Assessment Examinations.关于Chat生成式预训练变换器和微软副驾驶在美国手外科协会自我评估考试中的性能评估。
J Hand Surg Glob Online. 2024 Nov 13;7(1):23-28. doi: 10.1016/j.jhsg.2024.10.001. eCollection 2025 Jan.
7
Application of Generative Artificial Intelligence in Dyslipidemia Care.生成式人工智能在血脂异常护理中的应用。
J Lipid Atheroscler. 2025 Jan;14(1):77-93. doi: 10.12997/jla.2025.14.1.77. Epub 2024 Dec 10.
8
Artificial Intelligence and ChatGPT in Medical Education: A Cross-Sectional Questionnaire on students' Competence.医学教育中的人工智能与ChatGPT:关于学生能力的横断面问卷调查
J CME. 2024 Dec 24;14(1):2437293. doi: 10.1080/28338073.2024.2437293. eCollection 2025.
9
Healthcare professionals and the public sentiment analysis of ChatGPT in clinical practice.医疗保健专业人员与公众对ChatGPT在临床实践中的情感分析。
Sci Rep. 2025 Jan 7;15(1):1223. doi: 10.1038/s41598-024-84512-y.
10
Can ChatGPT generate surgical multiple-choice questions comparable to those written by a surgeon?ChatGPT能否生成与外科医生编写的相媲美的外科选择题?
Proc (Bayl Univ Med Cent). 2024 Oct 22;38(1):48-52. doi: 10.1080/08998280.2024.2418752. eCollection 2025.