Background To investigate the application effectiveness of an artificial intelligence (AI)-assisted World Café teaching model in graduate-level clinical pharmacology course and to evaluate its impact on facilitating students’ acquisition and integration of professional knowledge, developing clinical decision-making competencies, and enriching the teaching-learning experience. Methods A pilot study was conducted involving 56 first-year master’s students enrolled in a clinical pharmacology course at Kunming Medical University. Instruction was organized around a complex comprehensive clinical case of depression. Students participated in a structured five-stage seminar using the World Café format, supported by AI tools to facilitate group discussions and learning. A multi-method assessment strategy was employed, integrating a teaching effectiveness perception questionnaire, a specialized knowledge test, and a comparative analysis of AI-generated versus instructor-generated scores on case discussion records. Results Student evaluations of the teaching model were favorable, with agreement rates exceeding 90% across all items assessing the learning experience. Mean self-rated scores for clinical decision-making abilities each exceeded 4.0 points. Following the intervention, post-test accuracy on depression etiology knowledge improved significantly (median increase from 60.71 to 78.43%; p 0.01). AI-based scoring of case discussion records demonstrated balanced distributions across five assessment dimensions, and total scores showed high concordance with instructor ratings ( p 0.05). Conclusion The AI-assisted World Café model effectively promotes the assimilation of complex knowledge and fosters higher-order clinical decision-making abilities among clinical pharmacology graduate students. It facilitates a pedagogical shift from passive knowledge transmission toward active capacity building. Furthermore, AI demonstrated reliability and promising utility as a tool for formative assessment, offering empirical support for innovative human-computer collaborative teaching approaches.
Guo et al. (Fri,) studied this question.