Bytes versus brains: A comparative study of AI-generated feedback and human tutor feedback in medical education.

IF 3.3 2区教育学 Q1 EDUCATION, SCIENTIFIC DISCIPLINES

Medical Teacher Pub Date : 2025-06-18 DOI:10.1080/0142159X.2025.2519639

Majid Ali, Ihab Harbieh, Khawaja Husnain Haider

{"title":"Bytes versus brains: A comparative study of AI-generated feedback and human tutor feedback in medical education.","authors":"Majid Ali, Ihab Harbieh, Khawaja Husnain Haider","doi":"10.1080/0142159X.2025.2519639","DOIUrl":null,"url":null,"abstract":"Introduction: Timely, high-quality feedback is vital in medical education but increasingly difficult due to rising student numbers and limited faculty. Artificial intelligence (AI) tools offer scalable solutions, yet limited research compares their effectiveness with traditional tutor feedback. This study examined the comparative effectiveness of AI-generated feedback versus human tutor feedback within the medical curriculum.Methods: Second-year medical students (n = 108) received two sets of feedback on a written assignment, one from their tutor and one unedited response from ChatGPT. Students assessed each feedback using a structured online questionnaire focused on key feedback quality criteria.Results: Eighty-five students (79%) completed the evaluation. Tutor feedback was rated significantly higher in clarity and understandability (p < 0.001), relevance (p < 0.001), actionability (p = 0.009), comprehensiveness (p = 0.001), accuracy and reliability (p = 0.003), and overall usefulness (p < 0.001). However, 62.3% of students indicated that both pieces of feedback complemented each other. Open-ended responses aligned with these quantitative findings. .Conclusion: Human tutors currently provide superior feedback in terms of clarity, relevance, and accuracy. Nonetheless, AI-generated feedback shows promise as a complementary tool. A hybrid feedback model integrating AI and human input could enhance the scalability and richness of feedback in medical education.","PeriodicalId":18643,"journal":{"name":"Medical Teacher","volume":" ","pages":"1-11"},"PeriodicalIF":3.3000,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical Teacher","FirstCategoryId":"95","ListUrlMain":"https://doi.org/10.1080/0142159X.2025.2519639","RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION, SCIENTIFIC DISCIPLINES","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Timely, high-quality feedback is vital in medical education but increasingly difficult due to rising student numbers and limited faculty. Artificial intelligence (AI) tools offer scalable solutions, yet limited research compares their effectiveness with traditional tutor feedback. This study examined the comparative effectiveness of AI-generated feedback versus human tutor feedback within the medical curriculum.

Methods: Second-year medical students (n = 108) received two sets of feedback on a written assignment, one from their tutor and one unedited response from ChatGPT. Students assessed each feedback using a structured online questionnaire focused on key feedback quality criteria.

Results: Eighty-five students (79%) completed the evaluation. Tutor feedback was rated significantly higher in clarity and understandability (p < 0.001), relevance (p < 0.001), actionability (p = 0.009), comprehensiveness (p = 0.001), accuracy and reliability (p = 0.003), and overall usefulness (p < 0.001). However, 62.3% of students indicated that both pieces of feedback complemented each other. Open-ended responses aligned with these quantitative findings. .

Conclusion: Human tutors currently provide superior feedback in terms of clarity, relevance, and accuracy. Nonetheless, AI-generated feedback shows promise as a complementary tool. A hybrid feedback model integrating AI and human input could enhance the scalability and richness of feedback in medical education.

查看原文本刊更多论文

字节与大脑：医学教育中人工智能反馈与人类导师反馈的比较研究。

引言：及时、高质量的反馈在医学教育中至关重要，但由于学生人数的增加和师资力量的有限，反馈越来越困难。人工智能（AI）工具提供了可扩展的解决方案，但很少有研究将其有效性与传统的导师反馈进行比较。本研究考察了在医学课程中人工智能生成的反馈与人类导师反馈的比较有效性。方法：二年级医学生（n = 108）收到两组书面作业反馈，一组来自他们的导师，一组来自ChatGPT的未经编辑的回复。学生们使用结构化的在线问卷来评估每个反馈，重点关注关键反馈的质量标准。结果：85名学生（79%）完成了评估。导师反馈在清晰度和可理解性（p < 0.001）、相关性（p < 0.001）、可操作性（p = 0.009）、全面性（p = 0.001）、准确性和可靠性（p = 0.003）和总体有用性（p < 0.001）方面的评分显著较高。然而，62.3%的学生表示两种反馈是相辅相成的。开放式回答与这些定量调查结果一致。。结论：人类导师目前在清晰性、相关性和准确性方面提供了更好的反馈。尽管如此，人工智能生成的反馈显示出作为一种补充工具的前景。结合人工智能和人工输入的混合反馈模型可以增强医学教育反馈的可扩展性和丰富性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Medical Teacher 医学-卫生保健

CiteScore

7.80

自引率

8.50%

发文量

396

审稿时长

3-6 weeks

期刊介绍： Medical Teacher provides accounts of new teaching methods, guidance on structuring courses and assessing achievement, and serves as a forum for communication between medical teachers and those involved in general education. In particular, the journal recognizes the problems teachers have in keeping up-to-date with the developments in educational methods that lead to more effective teaching and learning at a time when the content of the curriculum—from medical procedures to policy changes in health care provision—is also changing. The journal features reports of innovation and research in medical education, case studies, survey articles, practical guidelines, reviews of current literature and book reviews. All articles are peer reviewed.