ChatGPT联合ASSURE评估在临床医学本科教学中的探索与实践

Exploration and Practice of ChatGPT Combined with ASSURE Evaluation in Clinical Medicine Undergraduate Teaching

摘要: 目的：探索ChatGPT联合ASSURE评估模式在临床医学本科教学中的应用效果，为培养具有主动学习能力、临床思维能力和创新能力的医学人才提供实践依据。方法：选取2024年在我院进行临床培训的60名临床医学本科生作为研究对象，随机分为教改实验组(n = 30)和传统教学组(n = 30)。传统教学组采用基于PPT的LBL教学模式，教改实验组采用ChatGPT联合ASSURE评估的“师–生-ChatGPT”三主体教学模式，以呼吸衰竭为教学病种开展教学。比较两组学生的理论考核成绩、体格检查技能、胸部CT判读能力、入院记录书写质量、人文沟通能力及教学满意度，并分析教改模式的优缺点。结果：教改实验组学生的理论考核成绩、体格检查技能评分、胸部CT判读评分、入院记录书写质量评分、人文沟通能力评分及教学满意度均显著高于传统教学组，差异均有统计学意义(P < 0.05)。结论：ChatGPT联合ASSURE评估模式能有效提升临床医学本科生的理论知识水平、临床实践技能和综合素养，激发学生主动学习热情，是一种值得推广的临床医学本科教学创新模式。

Abstract: Objective: To explore the application effect of the ChatGPT combined with ASSURE evaluation model in undergraduate clinical medicine teaching, and to provide practical evidence for cultivating medical talents with autonomous learning ability, clinical thinking ability, and innovation ability. Methods: Sixty clinical medicine undergraduates undergoing clinical training in our hospital in 2024 were selected as the study subjects and randomly divided into a teaching reform experimental group (n = 30) and a traditional teaching group (n = 30). The traditional teaching group adopted a PPT-based LBL teaching model, while the teaching reform experimental group used a three-subject “teacher-student-ChatGPT” teaching model integrating ChatGPT combined with ASSURE evaluation, focusing on respiratory failure as the teaching disease. Theoretical exam scores, physical examination skills, chest CT interpretation ability, inpatient record writing quality, humanistic communication ability, and teaching satisfaction were compared between the two groups, and the advantages and disadvantages of the teaching reform model were analyzed. Results: The teaching reform experimental group scored significantly higher than the traditional teaching group in theoretical exam scores, physical examination skill scores, chest CT interpretation scores, inpatient record writing quality scores, humanistic communication ability scores and teaching satisfaction, with all differences being statistically significant (P < 0.05). Conclusion: The ChatGPT combined with ASSURE evaluation model can effectively improve the theoretical knowledge, clinical practice skills, and overall quality of clinical medicine undergraduates, stimulate students’ enthusiasm for autonomous learning, and is an innovative clinical medicine undergraduate teaching model worth promoting.