Deep Learning for Predicting Cardiac Procedure Outcomes: a Scoping Review of Recent Advance

Accurate prediction of outcomes after cardiac procedures is critical for personalized decision-making and risk stratification. While machine learning (ML) has shown promise in this domain, most prior studies rely on traditional ML methods that require structured data and manual feature engineering, limiting scalability. Deep learning (DL) offers an alternative by enabling automatic feature extraction and integration of unstructured data such as text, images, and signals. This scoping review summarizes recent advances in DL-based prediction of outcomes for four major cardiovascular procedures: percutaneous coronary intervention (PCI), coronary artery bypass grafting (CABG), aortic valve replacement (AVR), and mitral valvuloplasty. Following PRISMA-ScR guidelines, we searched PubMed and IEEE Xplore for studies published between 2020 and March 2025. Finally, 457 studies were retrieved and nine eligible studies were included after screening. DL models demonstrated varying performance across data types, with particularly strong results for text and imaging tasks. Multimodal approaches combining clinical, imaging, and signal data showed added predictive value. Compared with traditional ML, DL models required minimal preprocessing, highlighting efficiency advantages. These findings suggest DL has potential to enhance preoperative risk stratification and provide useful information for clinical decisions. However, all included studies lacked external validation, and challenges remain regarding generalizability, explainability, and integration into clinical workflows. Future research should prioritize large, diverse cohorts, multimodal data fusion, and interpretable DL models to enable safe and effective clinical implementation.