Application of AI ‐Enhanced Teaching Combined With Traditional Instruction in Cardiac and Great Vessel Surgery
ABSTRACT Objective To investigate the feasibility and effectiveness of combining AI‐enhanced teaching with traditional instruction for clinical skills training of resident physicians undergoing standardized training in cardiac and great vessel surgery. Methods Forty resident physicians were randomly divided into two groups. The AI‐combined teaching group ( n = 20) received an 8‐week AI‐enhanced teaching program (including intelligent learning planning, an intelligent surgical video library, and an intelligent case analysis library) combined with traditional instruction; the traditional teaching group ( n = 20) received only conventional teaching. Before and after the training, Objective Structured Clinical Examinations (OSCE) and porcine heart model assessments for mitral valve replacement and coronary artery bypass grafting were conducted, and satisfaction was surveyed. Results After training, the total OSCE score of the AI‐combined teaching group was significantly higher than that of the traditional teaching group (85.6 ± 4.2 vs. 78.3 ± 5.1, p < 0.01), with notable advantages in image interpretation and skill operation. Surgical skill scores were also significantly better (92.4 ± 3.7 vs. 86.1 ± 4.9, p < 0.001). All members of the AI‐combined teaching group expressed satisfaction, and their surgical confidence scores increased significantly ( p < 0.001). Conclusion AI‐enhanced teaching combined with traditional instruction significantly improves the clinical and surgical skills of resident physicians in cardiac and great vessel surgery and represents a feasible and efficient human–computer collaborative teaching model.
Authors
- Jinguo Xu
- Chengxin Zhang (ORCID: https://orcid.org/0000-0001-5535-9190)
Institutions
- Anhui Medical University (CN)
- First Affiliated Hospital of Anhui Medical University (CN)
Publication Details
- Journal
- ANZ Journal of Surgery
- Published
- 2026-09-11
- DOI
- https://doi.org/10.1111/ans.70972
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00