Enhancing cardiopulmonary physiotherapy education with an AI-driven Smart Learning Platform: a quasi-experimental study

Abstract Objective This study aims to evaluate student acceptance of a Smart Learning Platform (SLP) (based on the Chaoxing Learning System™) to deliver a cardiopulmonary physiotherapy curriculum. The SLP leverages AI-enabled knowledge graphs to facilitate adaptive learning, case-based simulations, and the development of clinical reasoning skills. Methods A quasi-experimental design was adopted. The SLP was implemented for 89 students in the 2022 cohort (post-reform group), while 90 students in the 2021 cohort (pre-reform group) received conventional teaching. Both groups completed the Student Evaluation of Educational Quality (SEEQ) questionnaire. Data were analyzed using the Mann-Whitney U test. Results The median scores across all SEEQ domains were similar between the pre- and post-reform groups, indicating comparable student perceptions of core teaching quality. However, the post-reform group reported statistically significant improvements in mean scores in the domains of Learning Value, Group Interaction, and Knowledge Breadth (all P < 0.05). No significant differences were found in the areas of Course Organization and Workload. Conclusion The SLP demonstrated comparable teaching effectiveness to traditional training while ostensibly enhancing student engagement, perceived learning value, and breadth of knowledge. The SLP represents an acceptable and scalable model for delivering physiotherapy education, particularly when teaching resources are limited.