Artificial Intelligence in Cardiac Rehabilitation: Assessing ChatGPT's Knowledge and Clinical Scenario Responses

OBJECTIVE
Cardiac rehabilitation (CR) improves survival, reduces hospital readmissions, and enhances quality of life, yet participation remains low due to access, awareness, and socioeconomic barriers. This study explores the potential of AI, particularly ChatGPT, to support CR by providing guideline-based recommendations and fostering patient motivation.


METHODS
In this cross-sectional study, 40 questions developed by two cardiologists based on current cardiology guidelines were presented to ChatGPT-4. The questions covered the fundamental principles of CR, clinical applications, and real-life scenarios. Responses were categorized based on their guideline adherence as "fully compliant," "partially compliant," "compliant but insufficient," or "non-compliant." Evaluations were conducted by two experts, and inter-rater reliability was analyzed using Cohen’s kappa coefficient.


RESULTS
ChatGPT provided responses to all 40 questions. Among the 20 general open-ended questions, 14 were rated as fully compliant, while 6 were compliant but insufficient. Of the 20 clinical scenario-based questions, 16 were fully compliant, and 4 were compliant but insufficient. ChatGPT demonstrated strengths in areas such as risk stratification and patient safety strategies, but limitations were identified in topics such as managing elderly patients and high-intensity interval training. Inter-rater reliability was calculated as 90% using Cohen’s kappa coefficient.


CONCLUSION
ChatGPT shows potential as a complementary decision support tool in CR by providing guideline-compliant information. However, limitations in contextual understanding and real-world validation restrict its independent clinical use. Future improvements should focus on personalization, clinical validation, and integration with healthcare professionals.