Taking the national first-class undergraduate online course intelligent upgrading of "doctor-patient communication" as the practical carrier, this study proposes and implements an overall framework of "knowledge graph-based and AI dual-wheel driven", and systematically promotes the construction of three core pathways: knowledge graph construction, AI learning support, and AI teaching assistant management. The course team has successfully built a structured knowledge network covering 4 major modules, including "introduction to doctor-patient communication", and 67 knowledge points. The course has been selected by more than 20,000 students from over 40 colleges and universities, with a total of 43,000 teaching interactions. A small-sample student satisfaction survey reveals a high overall satisfaction with the course, with a comprehensive score of (8.68 ± 1.18) (full score: 10 points), and 88.0% of students expressed willingness to recommend the course. The deep empowerment of knowledge graph and AI technology serves as an effective approach to improving the quality of online medical humanities courses and realizing the integration of large-scale education and personalized training, which can provide a practical paradigm for the teaching reform in similar courses.

1. HanC, WuQ, LiuC, et al. Patient's perceived empathy can predict doctor-patient relationship in medical interaction[J]. BMC Med Educ, 2025, 25(1): 741. doi：10.1186/s12909-025-07117-7

2. BardenA, KalmanJ, GierlingerS, et al. From monologue to dialogue: the pursuit of relationship centered communication across a large, integrated healthcare system[J]. J Patient Exp, 2024, 11: 23743735241226507. doi：10.1177/23743735241226507

3. CoxC, FritzZ. What is in the toolkit (and what are the tools)? How to approach the study of doctor-patient communication[J]. Postgrad Med J, 2023, 99(1172): 631-638. doi：10.1136/postgradmedj-2021-140663

4. 国家卫生健康委办公厅, 教育部办公厅, 国家中医药局综合司, 国家疾控局综合司. 关于印发医学人文关怀提升行动方案 (2024-2027年) 的通知[EB/OL]. (2024-09-29)[2026-02-27]. https://www.gov.cn/zhengce/zhengceku/202410/content_6979036.htm.

5. 胡逸菲, 黄涔, 朱丹, 等. 面向数智时代的医学教育:现代教育技术的发展路径、应用现状与未来趋势[J]. 中华医学教育探索杂志, 2023, 22(9): 1281-1286.HuYF, HuangC, ZhuD, et al. Medical education in the digital intelligence era: development paths, application status and future trends of modern educational technology[J]. Chinese Journal of Medical Education Research, 2023, 22(9): 1281-1286.

6. QianJ, DuMY, YangY, et al. Promoting educational equity and facilitating effective use of high-quality resources: an empirical study on improving massive open online courses completions[J]. Eng Educ Rev, 2024, 2(1): 37-43. doi：10.54844/eer.2024.0512

7. 王婧方, 张彦. 慕课赋能医学伦理教育: 人文素养培育现状与优化路径[J]. 中国医学伦理学, 2025, 38(11): 1483-1491.WangJF, ZhangY. MOOCs empowering medical ethics education: current status and optimization paths of humanistic literacy cultivation[J]. Chinese Medical Ethics, 2025, 38(11): 1483-1491.

8. 李儒婷, 许宽勤, 施慧, 等. 慕课在我国高等医学教育中应用的文献计量分析[J]. 中华医学教育探索杂志, 2022, 21(8): 971-975.LiRT, XuKQ, ShiH, et al. Bibliometric analysis of the application of MOOCs in higher medical education in China[J]. Chinese Journal of Medical Education Research, 2022, 21(8): 971-975.

9. 高一飞, 郭璐怡, 王珏, 等. 医学人文慕课中“教”与“学”的分歧——一项质性研究[J]. 中华医学教育探索杂志, 2020, 19(6): 731-736.GaoYF, GuoLY, WangJ, et al. Divergences between "teaching" and "learning" in medical humanities MOOCs: a qualitative study[J]. Chinese Journal of Medical Education Research, 2020, 19(6): 731-736.

10. da Silva MenezesA, Gomes Moreira FarinhaAK, Machado DinizPS. Online medical education during the pandemic in different countries[EB/OL]. (2023)[2026-01-15]. https://www.semanticscholar.org/paper/Online-medical-education-during-the-pandemic-in-J%C3%BAnior-Farinha/1ebf8c437d1110e5d3713b9688f3f7da8d5f6f30. doi：10.1590/1981-5271v47.2-2022-0394.ing

11. ZhuB, ChauKT, MokminNAM. Optimizing cognitive load and learning adaptability with adaptive microlearning for in-service personnel[J]. Sci Rep, 2024, 14(1): 25960. doi：10.1038/s41598-024-77122-1

12. RaineP. Using GPT-3 as a more knowledgeable other to provide feedback on English language learners' spoken transcripts[J]. TESL-EJ, 2025, 29(2): 1. doi：10.55593/ej.29114a7

13. Pamukçu KarasuB. New approaches in educational sciences[M]. Lyon: Livre De Lyon, 2025: 36-37.

14. 张倍思, 陈烨, 齐艺, 等. 多源过程性数据驱动的学习者综合评价模型研究[J]. 情报科学, 2022, 40(5): 104-110.ZhangBS, ChenY, QiY, et al. Research on a comprehensive learner evaluation model driven by multi-source process data[J]. Information Science, 2022, 40(5): 104-110.

15. ActonR. Doing knowledge work differently: problem-based projects as encounters in coming-to-know[J]. Higher Educ, 2023, 86: 225-242. doi：10.1007/s10734-022-00910-z

16. 李惠乾, 钟柏昌. 教育知识图谱: 研究进展与未来发展——基于2013-2023年中文核心期刊载文的分析[J]. 计算机工程, 2024, 50(7): 1-12.LiHQ, ZhongBC. Educational knowledge graph: Research progress and future development—an analysis based on Chinese core journal publications from 2013 to 2023[J]. Computer Engineering, 2024, 50(7): 1-12.

17. LiangW, TadesseGA, HoD, et al. Advances, challenges and opportunities in creating data for trustworthy AI[J]. Nat Mach Intell, 2022, 4: 669-677. doi：10.1038/s42256-022-00516-1