AI赋能病理学课程思政教学改革：三段式教学模式的构建与准实验研究

AI-Empowered Curriculum-Based Ideological and Political Education Reform in Pathology: Construction and Quasi-Experimental Evaluation of a Three-Phase Teaching Model

摘要: 目的：构建以“知识–能力–价值”(KCV)螺旋递进模型为理论基础的AI赋能病理学课程思政三段式教学模式，并通过准实验研究评价其对医学生共情能力及职业价值观内化的干预效果。方法：采用准实验前后测对照设计，以安徽中医药大学中西医结合学院2023级中医临床专业两个平行班(实验组约40人，对照组约40人)为研究对象。实验组实施“课前预热–课中情境–课后反思”三段式AI辅助课程思政教学模式，借助DeepSeek大语言模型构建含20个以上案例的标准化思政案例库；对照组采用传统教学方式。采用中文版杰弗逊医学共情量表学生版(JSPE-S, Cronbach’s alpha = 0.861)评估共情能力，结合DeepSeek语义分析反思日志及学习平台行为数据进行多维度评价。统计分析采用独立样本t检验及Mann-Whitney U检验(SPSS 26.0，P < 0.05为差异有统计学意义)。结果(预期)：实验组JSPE-S总分提升幅度显著大于对照组(P < 0.05)，反思日志中思政主题词频率及学习平台互动频次均高于对照组，且专业知识测评成绩不低于对照组。结论：AI赋能三段式课程思政教学模式理论基础扎实、操作路径清晰，多维度评价工具包为医学人文素养的量化评估提供了低成本、可推广的解决方案，具有在中医药院校基础医学课程中推广应用的价值。

Abstract: Objective: To construct an AI-empowered three-phase curriculum-based ideological and political education (IPE) teaching model grounded in the Knowledge-Competency-Value (KCV) spiral progression framework, and to evaluate its effects on medical students’ empathy and professional value internalization through a quasi-experimental study. Methods: A quasi-experimental pre-test/post-test controlled design was employed with two parallel cohorts of 2023-grade clinical traditional Chinese medicine students at Anhui University of Chinese Medicine (experimental group n ~= 40; control group n ~= 40). The experimental group received a three-phase AI-assisted IPE teaching model (pre-class preparation, in-class contextual learning, post-class structured reflection), with a standardized IPE case library (>=20 cases) constructed using the DeepSeek large language model API. The control group received conventional instruction. Empathy was assessed using the Chinese version of the Jefferson Scale of Physician Empathy-Student version (JSPE-S; Cronbach’s alpha = 0.861), supplemented by DeepSeek semantic analysis of reflection journals and learning-platform behavioral data. Independent-samples t-tests and Mann-Whitney U tests were used (SPSS 26.0; P < 0.05). Expected (Results): The experimental group is expected to show significantly greater improvements in JSPE-S scores, higher IPE-related thematic language frequencies in reflection journals, and greater platform engagement than the control group, with comparable or superior knowledge assessment performance. Conclusion: The AI-empowered three-phase IPE teaching model is theoretically grounded and practically feasible. The multi-dimensional assessment toolkit provides a low-cost, scalable approach to quantifying humanistic competency outcomes in medical education at TCM universities.