通讯作者: 林呈飞, linchengfeidyyy@163.com

DOI：10.12201/bmr.202603.00124

Application of Generative Artificial Intelligence-Assisted Pedagogy in Clinical Ophthalmology Education

• 摘要：目的 研究生成式人工智能辅助教学法在眼科临床教学中的应用。方法 本研究为随机对照研究,通过分层随机数字表法将 27 名住培及实习医师分为试验组(生成式人工智能辅助教学组,n=14)与对照组(传统教学组,n=13)。通过比较理论知识考核、模拟病人临床思维考核成绩及调查问卷结果评价教学效果。结果 试验组学员的临床思维考核总分高于对照组(P<0.05),其中病史归纳总结、初步诊断与鉴别诊断、医学人文三方面考核成绩较对照组明显提升(P<0.05)。试验组学员的理论考核成绩、临床思维中的问诊与沟通、治疗与处置成绩与对照组相比有所提高,但差异不具有统计学显著性(P＞0.05)。在学习兴趣、临床思维能力提升自评和教学方法满意度三个方面,试验组评分均高于对照组(P<0.05),在学习效率、增加学习负担(负向指标)方面,两组自评分无显著差异(P>0.05)。结论 生成式人工智能辅助教学模式相比传统讲授模式在眼科临床教学中具有更好的效果,可在不增加学生学习负担、不降低学习积极性的前提下,提高眼科实习及住培医师临床实践能力。

  关键词： 眼科; 临床教学; 生成式人工智能

   

  Abstract: 【】Objective To investigate the application of generative artificial intelligence-assisted pedagogy in clinical ophthalmology education. Methods This randomized controlled study divided 27 resident and intern physicians into an experimental group (generative AI-assisted teaching group, n=14) and a control group (traditional teaching group, n=13) using stratified random number table method. Teaching effectiveness was evaluated by comparing theoretical knowledge assessment scores, simulated patient clinical reasoning assessment scores, and questionnaire results. Results The total score of the clinical reasoning assessment for the experimental group was significantly higher than that of the control group (P<0.05). Specifically, scores in history summarization, preliminary diagnosis and differential diagnosis, and medical humanities showed significant improvement compared to the control group (P<0.05). The theoretical assessment scores, as well as the scores for history taking communication and treatment management within the clinical reasoning assessment, were higher in the experimental group than in the control group, but the differences were not statistically significant (P>0.05). Regarding learning interest, self-evaluated improvement in clinical reasoning ability, and satisfaction with the teaching method, the experimental groups ratings were significantly higher than those of the control group (P<0.05). There was no significant difference between the two groups in self-rated scores for learning efficiency or increased learning burden (a negative indicator) (P>0.05). Conclusion Compared to the traditional lecture-based model, the generative AI-assisted teaching model demonstrates superior effectiveness in clinical ophthalmology education. It can enhance the clinical competency of ophthalmology interns and resident physicians without increasing their learning burden or diminishing their learning motivation.

  Key words: Ophthalmology; Clinical Education; Generative Artificial Intelligence

  提交时间：2026-03-31

  版权声明：作者本人独立拥有该论文的版权，预印本系统仅拥有论文的永久保存权利。任何人未经允许不得重复使用。
• html

• 图表

• 中国科学技术信息研究所, 北京市海淀区复兴路号. 基于生成式人工智能的医学视频创作路径探究. 2025. doi: 10.12201/bmr.202508.00005

  弓孟春, 李雨杭, 马永慧, 弓凯, 刘超, 欧阳自豪, 戴辉. 生成式医学人工智能(GMAI)的临床伦理治理:三维协同路径与中国实践. 2025. doi: 10.12201/bmr.202511.00057

  孟冬晴, 吕文娟. 生成式人工智能赋能医学图书馆知识服务的路径研究. 2025. doi: 10.12201/bmr.202510.00039

  史森中. 生成式人工智能（GAI）基层医疗应用风险及治理策略分析. 2024. doi: 10.12201/bmr.202408.00053

  向艾宁堃, 田靖雪, 胡德华, 刘海霞. 生成式人工智能对于老年糖尿病应答效能的比较研究. 2025. doi: 10.12201/bmr.202503.00019

  袁由生, 张俊. AI联合PBL-CBL教学模式在医学影像实习教学中的应用效果研究. 2025. doi: 10.12201/bmr.202512.00069

  黄春玲, 韩彤妍, 张娟. 人工智能学习APP结合思维导图对培养儿科实习生临床思维能力的效果研究. 2024. doi: 10.12201/bmr.202412.00023

  王蕾, 刘苗, 王茜, 赵琬清, 胡佳慧, 方安. 生成式人工智能医学语料库:数据风险、合规义务及应对方案. 2025. doi: 10.12201/bmr.202512.00083

  马傲, 葛小玲. 人工智能大模型在医疗健康领域应用的研究. 2024. doi: 10.12201/bmr.202408.00039

  赵锐, 石秀园, 钟雪然, 任平, 田雪晴, 刘春平, 游茂. 基于卫生技术评估构建医学人工智能技术临床应用评估路径的探讨. 2022. doi: 10.12201/bmr.202203.00005

• 序号	提交日期	编号	操作
  1	2026-02-25	10.12201/bmr.202603.00124V1	下载

• 公开评论  匿名评论  仅发给作者 提交评论