⚡ Quick Summary
This study evaluated the potential of ChatGPT as a decision-support tool in cardiac rehabilitation (CR), finding that it provided guideline-compliant responses to 80% of clinical scenario questions. While promising, limitations in contextual understanding highlight the need for further development before independent clinical use.
🔍 Key Details
- 📊 Study Type: Cross-sectional study
- 🤖 AI Tool: ChatGPT-4
- 📝 Questions Evaluated: 40 questions based on cardiology guidelines
- 👨⚕️ Evaluators: Two cardiologists
- 📈 Inter-rater Reliability: 90% (Cohen’s kappa coefficient)
🔑 Key Takeaways
- 💡 ChatGPT demonstrated strengths in risk stratification and patient safety strategies.
- 📉 Limitations were noted in managing elderly patients and high-intensity interval training.
- 🔍 14 out of 20 general questions were rated as fully compliant.
- 🏥 16 out of 20 clinical scenario questions were rated as fully compliant.
- ⚠️ Contextual understanding remains a challenge for AI in clinical settings.
- 🔄 Future improvements should focus on personalization and clinical validation.
- 🌐 Study published in Turk Kardiyol Dern Ars.
- 🆔 PMID: 40152733
📚 Background
Cardiac rehabilitation (CR) is a vital component of cardiovascular care, known to improve survival rates, reduce hospital readmissions, and enhance the quality of life for patients. Despite its benefits, participation in CR programs remains low due to various barriers, including access, awareness, and socioeconomic factors. The integration of artificial intelligence (AI) into CR could potentially address these challenges by providing tailored recommendations and fostering patient engagement.
🗒️ Study
This study aimed to assess the knowledge and clinical scenario responses of ChatGPT-4 in the context of cardiac rehabilitation. A total of 40 questions were developed by two cardiologists, covering essential principles of CR and real-life clinical applications. The responses were evaluated for adherence to current cardiology guidelines, allowing for a comprehensive analysis of the AI’s capabilities.
📈 Results
ChatGPT successfully answered all 40 questions, with a notable performance in the clinical scenario-based questions. Specifically, 16 out of 20 clinical questions were rated as fully compliant, while 14 out of 20 general questions achieved the same rating. The inter-rater reliability was impressively high at 90%, indicating a strong agreement between the evaluators on the quality of the responses.
🌍 Impact and Implications
The findings of this study suggest that ChatGPT could serve as a valuable complementary tool in cardiac rehabilitation, providing guideline-compliant information that could enhance patient care. However, the limitations in contextual understanding and the need for real-world validation underscore the importance of integrating AI with healthcare professionals to ensure safe and effective use in clinical settings.
🔮 Conclusion
This study highlights the potential of AI in supporting cardiac rehabilitation efforts. While ChatGPT shows promise in delivering guideline-compliant information, further advancements are necessary to improve its contextual understanding and clinical validation. The future of AI in healthcare looks bright, and ongoing research will be crucial in unlocking its full potential.
💬 Your comments
What are your thoughts on the integration of AI in cardiac rehabilitation? We would love to hear your insights! 💬 Leave your comments below or connect with us on social media:
Artificial Intelligence in Cardiac Rehabilitation: Assessing ChatGPT’s Knowledge and Clinical Scenario Responses.
Abstract
OBJECTIVE: Cardiac rehabilitation (CR) improves survival, reduces hospital readmissions, and enhances quality of life; however, participation remains low due to barriers related to access, awareness, and socioeconomic factors. This study explores the potential of artificial intelligence (AI), specifically ChatGPT, in supporting CR by providing guideline-aligned recommendations and fostering patient motivation.
METHOD: This cross-sectional study evaluated ChatGPT-4’s responses to 40 questions developed by two cardiologists based on current cardiology guidelines. The questions covered fundamental principles of CR, clinical applications, and real-life scenarios. Responses were categorized based on guideline adherence as fully compliant, partially compliant, compliant but insufficient, or non-compliant. Two expert evaluators assessed the responses, 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 six were compliant but insufficient. Of the 20 clinical scenario-based questions, 16 were fully compliant, and four were compliant but insufficient. ChatGPT demonstrated strengths in areas such as risk stratification and patient safety strategies, but limitations were noted in managing elderly patients and high-intensity interval training. Inter-rater reliability was calculated as 90% using Cohen’s kappa coefficient.
CONCLUSION: ChatGPT shows promise as a complementary decision-support tool in CR by providing guideline-compliant information. However, limitations in contextual understanding and lack of real-world validation restrict its independent clinical use. Future improvements should focus on personalization, clinical validation, and integration with healthcare professionals.
Author: [‘Geneş M’, ‘Yaşar S’, ‘Fırtına S’, ‘Yağcı AF’, ‘Yıldırım E’, ‘Barçın C’, ‘Yüksel UÇ’]
Journal: Turk Kardiyol Dern Ars
Citation: Geneş M, et al. Artificial Intelligence in Cardiac Rehabilitation: Assessing ChatGPT’s Knowledge and Clinical Scenario Responses. Artificial Intelligence in Cardiac Rehabilitation: Assessing ChatGPT’s Knowledge and Clinical Scenario Responses. 2025; 53:173-177. doi: 10.5543/tkda.2025.57195