Evaluation of the Teaching Effectiveness of Generative Artificial Intelligence-Assisted Surgical Clerkship

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Background: Clinical clerkship is a critical stage linking preclinical theory with clinical practice in medical education. However, traditional surgical clerkship faces limitations in case resources, teaching staff capacity, and opportunities for skill training. This study developed a four-step generative artificial intelligence (GenAI)-assisted surgical clerkship teaching model and evaluated its effects on medical students’ theoretical knowledge, operational skills, and clinical thinking. Methods: A randomized controlled design was adopted. A total of 47 undergraduate clinical medicine students who underwent surgical clerkship in the Department of General Surgery of Qinghai University Affiliated Hospital between July 2025 and February 2026 were enrolled and randomly assigned to an experimental group (n = 24) and a control group (n = 23). The experimental group adopted a four-step GenAI (DeepSeek)-assisted teaching model consisting of AI scenario introduction, AI case deduction, AI skill analysis, and AI immediate feedback, whereas the control group received traditional teaching. Theoretical examination, objective structured clinical examination (OSCE), clinical case analysis, and a learning satisfaction questionnaire were compared between the two groups after the clerkship. Results: Baseline data were comparable between the two groups (all P > 0.05). Scores of theoretical knowledge, OSCE, clinical case analysis, and learning satisfaction in the experimental group were significantly higher than those in the control group (all P < 0.05). Conclusions: The four-step GenAI-assisted surgical clerkship teaching model can effectively improve students’ theoretical knowledge, operational skills, clinical thinking, and their learning experience. This model provides empirical evidence for the standardized application of GenAI in surgical clerkship teaching.