Artificial intelligence applications for enhancing patient self-care education following sternotomy: Development and...

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Patient Education

Background:

• High rates of 30-day rehospitalization exist for patients undergoing coronary artery bypass grafting (12%) and surgical aortic valve replacement (14%).
• Many of these re-admissions are preventable through improved post-discharge self-care and education.
• Artificial intelligence (AI) offers a novel approach to deliver personalized patient recommendations and enhance adherence to recovery protocols.

Purpose of the Study:

• To design an AI application to address common patient self-care questions post-sternotomy discharge.
• To provide patients with crucial information to reduce the risk of postoperative complications and subsequent readmission.

Main Methods:

• Development of a beta version AI application for sternotomy patients.
• Input of 75 common patient inquiries into the AI, with responses generated from 50 scholarly articles.
• Evaluation of AI-generated responses by the research team for accuracy and completeness.

Main Results:

• The AI application successfully answered all 75 questions posed.
• 86.7% (65/75) of AI responses were rated as comprehensive and accurate.
• 13.3% (10/75) of responses were deemed incomplete or convoluted, requiring further refinement.

Conclusions:

• Personalized patient education is vital for minimizing postoperative complications after discharge.
• AI applications show promise as effective tools for delivering tailored patient education.
• Pre-implementation evaluation by cardiac surgery teams and subsequent patient trials are recommended to ensure AI accuracy and usability.