基于DeepSeek-R1模型的PBL教学模式构建与应用

doi:10.16352/j.issn.1001-6325.2026.10.1440

基础医学与临床 ›› 2026, Vol. 46 ›› Issue (10): 1440-1446.doi: 10.16352/j.issn.1001-6325.2026.10.1440

• 医学教育 • 上一篇

基于DeepSeek-R1模型的PBL教学模式构建与应用

刘禺汐¹, 徐晓菲¹, 王铭洁², 向萌², 杨达伟³, 尤琳雅^1*, 刘琼^1*

1.复旦大学基础医学院解剖与组织胚胎学系,上海 200032;
2.复旦大学基础医学院生理与病理生理学系,上海 200032;
3.复旦大学附属中山医院呼吸与危重症医学科,上海 200032

收稿日期:2026-05-14 修回日期:2026-06-16 出版日期:2026-10-05 发布日期:2026-09-18
通讯作者: ^*liuqiong@fudan.edu.cn;lyyou@fudan.edu.cn
基金资助:
上海市重点课程“呼吸系统疾病基础”项目(FDSHZD202412)

Construction and application of a problem-based learning teaching model based on the DeepSeek-R1 model

LIU Yuxi¹, XU Xiaofei¹, WANG Mingjie², XIANG Meng², YANG Dawei³, YOU Linya^1*, LIU Qiong^1*

1. Department of Human Anatomy and Histoembryology, School of Basic Medical Sciences, Fudan University, Shanghai 200032;
2. Department of Physiology and Pathophysiology, School of Basic Medical Sciences, Fudan University, Shanghai 200032;
3. Department of Pulmonary and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai 200032, China

Received:2026-05-14 Revised:2026-06-16 Online:2026-10-05 Published:2026-09-18
Contact: ^*liuqiong@fudan.edu.cn;lyyou@fudan.edu.cn

摘要/Abstract

摘要： 目的利用DeepSeek-R1链式推理能力,构建可展示临床思维过程的人工智能(AI)病人,并融入课程PBL教学,评估该DS-PBL教学模式的教学效果。方法以选修“呼吸系统疾病基础”课程的复旦大学临床医学八年制三年级学生127人为研究对象,通过课后问卷收集反馈,采用Likert5量表和多选题评估教学效果,并对开放性问题的主题进行分析。结果学生对DS-PBL模式总体满意度高(“满意”和“非常满意”占79.5%)。92.1%学生认同“AI介入帮助拓宽诊断思路”,90.6%认同“通过对比AI与教师教学更明确AI临床决策局限性”。在多维度能力提升方面,学生对急性呼吸窘迫综合征的理解在“微观结构损伤与宏观功能衰竭联系”(83.5%)和“病理生理机制解释临床表现”(81.9%)上提升显著。开放性反馈揭示AI工具存在“信息矛盾”、“角色混淆”、“思维深度不足”等问题。结论 DeepSeek-R1可有效模拟呼吸临床推理过程,可作为基础医学课程PBL教学的有效辅助工具。

关键词: DeepSeek-R1, 问题导向学习(PBL), 呼吸系统疾病基础, 急性呼吸窘迫综合征, 课后问卷

Abstract: Objective To leverage the chain-of-reasoning capability of DeepSeek-R1 (DS) to construct an AI patient capable of demonstrating the clinical reasoning process,and integrate it into PBL teaching for respiratory diseases,evaluating its effectiveness in improving students′ clinical reasoning skills,pathophysiological understanding,and learning motivation. Methods The study participants were eight-year program medical students enrolled in this course at Fudan University. A total of 127 students,divided into five teaching groups,were participated in DS-PBL teaching practice. Post-class questionnaires were used to evaluate their feedbacks. A 5-point Likert scale and multiple-choice questions were employed to evaluate teaching effectiveness,and open-ended questions were analyzed thematically. Results Students reported a high overall satisfaction with the DS-PBL teaching model(79.5% selected “satisfied” or “very satisfied”). 92.1% of the students agreed that “AI intervention helped broaden my diagnostic thinking,” and 90.6% agreed that “by comparing the AI′s debriefing with that of the instructor,I gained a clearer understanding of the limitations of AI in clinical decision-making.” Regarding multidimensional competency improvement,students showed notable gains in understanding acute respiratory distress syndrome (ARDS) in terms of “linking micro-structural damage to macro-functional failure” (83.5%) and “explaining clinical manifestations through pathophysiological mechanisms” (81.9%). Open-ended feedback revealed issues with the AI tool,including “information contradiction”,“role confusion”,and “insufficient depth of reasoning”. Conclusions The capability of DeepSeek-R1 can effectively simulate the clinical reasoning process in respiratory medicine,making it a useful auxiliary tool in PBL teaching for basic medical courses.

Key words: DeepSeek-R1, problem-based learning (PBL), fundamentals of respiratory diseases, acute respiratory distress syndrome (ARDS), post-class questionnaire

中图分类号:

刘禺汐, 徐晓菲, 王铭洁, 向萌, 杨达伟, 尤琳雅, 刘琼. 基于DeepSeek-R1模型的PBL教学模式构建与应用[J]. 基础医学与临床, 2026, 46(10): 1440-1446.

LIU Yuxi, XU Xiaofei, WANG Mingjie, XIANG Meng, YANG Dawei, YOU Linya, LIU Qiong. Construction and application of a problem-based learning teaching model based on the DeepSeek-R1 model[J]. Basic & Clinical Medicine, 2026, 46(10): 1440-1446.

参考文献

[1] 郑延龙,朱振刚,乔亚珍,等.递进式情景教学在呼吸内科临床带教中的应用[J]. 中国继续医学教育,2021,13:42-45.
[2] 刘少甜,许芳,吴燕娟. CP和PBL教学在呼吸内科护理带教中的联合应用[J]. 中华肺部疾病杂志(电子版),2019,12: 256-258.doi:10.3877/cma.j.issn.1674-6902.2019.02.035.
[3] Jiang J,Yu H,Hu C,et al. Application effect of problem-based learning teaching model in respiratory critical medicine[J]. Front Med,2025,12:1648744. doi:10.3389/fmed.2025.1648744.
[4] Yan X,Zhu Y,Fang L,et al. Enhancing medical education in respiratory diseases: efficacy of a 3D printing,problem-based,and case-based learning approach[J]. BMC Med Educ. 2023,23:512. doi:10.1186/s12909-023-04508-6.
[5] Elnaga HHA,Ahmed MB,Fathi MS,et al. Virtual versus paper-based PBL in a pulmonology course for medical undergraduates[J]. BMC Med Educ. 2023,23:433. doi:10.1186/s12909-023-04421-y.
[6] Arain SA,Akhund SA,Barakzai MA,et al. Transforming medical education: leveraging large language models to enhance PBL-a proof-of-concept study[J]. Adv Physiol Educ,2025,49: 398-404.
[7] Hou J,An F,Qin H,et al. Application of DeepSeek-assisted problem-based learning in hematology residency training[J]. BMC Med Educ,2025,25: 1291. doi:10.1186/s12909-025-07852-x.
[8] Divito CB,Katchikian BM,Gruenwald JE,et al. The tools of the future are the challenges of today: The use of ChatGPT in problem-based learning medical education[J]. Med Teach,2024,46: 320-322.
[9] 杨叶猗,王建文,杨叶蓁. DeepSeek赋能CBL教学在肾内科见习中的应用前景[J]. 中华诊断学电子杂志,2025,13: 289-292.
[10] Abouzeid E,Zakaria I,Alshobaily M,et al. AI-assisted case builder: making PBL more scalable and adaptable[J]. Med Teach,2026: 1-5. doi:10.1080/0142159X.2026.2623964.
[11] Wei H,Dai Y,Yuan K,et al. AI-powered problem- and case-based learning in nedical and dental education: a systematic review and Meta-analysis[J]. Int Dent J,2025,75: 100858. doi:10.1016/j.identj.2025.100858.
[12] Li R,Wu T. Delving into the practical applications and pitfalls of large language models in medical education: narrative review[J]. Adv Med Educ Pract,2025,16: 625-636.
[13] Yi X, Feng W, He Y, et al. How to harness LLMs in project-based learning: empirical evidence for individual autonomy and moderate constraints in engineering education[J]. Systems, 2025, 13:1112. doi:10.3390/systems13121112.
[14] Omeh CB,Ayanwale MA,Mnguni LE,et al. Fostering programming skill and critical thinking through AI-assisted PBL integration[J]. J New Approaches Edu Res,2025,14: 22. doi:10.1007/s44322-024-00022-9.
[15] Thesen T,Park SH. A generative AI teaching assistant for personalized learning in medical education[J]. NPJ Digital Med,2025,8: 627. doi:10.1038/s41746-025-02022-1.

基于DeepSeek-R1模型的PBL教学模式构建与应用

Construction and application of a problem-based learning teaching model based on the DeepSeek-R1 model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	刘婷婷, 郜玲, 李筱妍. 中性粒细胞胞外诱捕网在脓毒症诱导的急性呼吸窘迫综合征中的研究进展[J]. 基础医学与临床, 2026, 46(1): 139-143.
[2]	牛昕妤, 孙志明, 谢旻, 李双玲. 干细胞治疗脓毒症的临床研究进展[J]. 基础医学与临床, 2025, 45(9): 1234-1238.
[3]	杨若彤, 赵国英, 王浩. 新生儿急性肺损伤的发病机制[J]. 基础医学与临床, 2025, 45(1): 135-139.
[4]	盛琪, 童瑾. CXCL10/CXCR3轴在急性呼吸窘迫综合征中的作用[J]. 基础医学与临床, 2024, 44(6): 892-896.
[5]	刘博, 宁雅婵, 张潇然, 王春梅. 电阻抗断层成像在急性呼吸窘迫综合征患者诊疗中的应用[J]. 基础医学与临床, 2024, 44(11): 1487-1491.
[6]	姜振宇, 王小娜, 汤克功, 陈明锐, 蒋澄宇. 炙甘草来源的sRNA可能通过靶向TNF-α缓解轻度ADRS模型小鼠的肺损伤[J]. 基础医学与临床, 2023, 43(7): 1030-1039.
[7]	王行行, 王导新. NETs与急性呼吸窘迫综合征的研究进展[J]. 基础医学与临床, 2021, 41(7): 1047-1051.