Applications Of Artificial Intelligence For Prediction, Diagnosis And Treatment Selection In Cardiovascular Diseases: A Narrative Review

This review, examines the applications of artificial intelligence (AI) in cardiovascular diseases (CVDs), with particular focus on risk prediction, diagnostic evaluation, treatment selection, and patient education. Literature published between ۲۰۱۹ and ۲۰۲۵ was systematically retrieved from PubMed, ScienceDirect, SID, Magiran, and Google Scholar using relevant keywords, with inclusion restricted to full-text Persian or English articles directly addressing the topic. Excluded were theoretical analyses, letters to the editor, and inaccessible full texts. The evidence indicates that AI-driven approaches, particularly those leveraging machine learning and deep learning, enhance clinical decision-making by improving predictive accuracy, facilitating precise diagnostic interpretation, and supporting personalized therapeutic strategies. Predictive models integrating electronic health records, imaging data, and genomic information consistently outperform traditional statistical methods in forecasting cardiovascular events. In parallel, AI-enabled diagnostic tools, including automated electrocardiography systems and stethoscopes, allow rapid and reliable detection of structural and functional cardiac abnormalities. Furthermore, adaptive AI platforms contribute to patient education, promoting adherence, lifestyle modification, and long-term health outcomes. Despite these advances, challenges remain regarding data quality, algorithm transparency, ethical governance, and prospective clinical validation. Overall, AI is poised to transform cardiovascular care by enabling precision medicine, optimizing resource allocation, and improving patient-centered outcomes. Continued research and rigorous implementation studies are essential to fully integrate these technologies into routine clinical practice, ultimately reducing the global burden of cardiovascular diseases.

Keywords:

Artificial Intelligence , Machine Learning , Clinical Decision Support , Cardiovascular Diseases , Diagnosis and Treatment