[Artificial intelligence in cardiovascular prevention: a strategic opportunity for risk prediction and early...

Cardiovascular diseases remain the leading cause of mortality and morbidity worldwide, with substantial impact in Italy. Cardiovascular prevention is a strategic priority, yet a significant gap persists between evidence-based guideline recommendations and their actual implementation in clinical practice. Artificial intelligence (AI), through machine learning and deep learning models, is emerging as a potentially transformative technology to bridge this gap, enabling more precise, dynamic, and personalized cardiovascular risk stratification compared with traditional risk scores. This review examines the most recent evidence on the application of AI in cardiovascular prevention, with a specific focus on risk stratification, early detection of subclinical disease, and identification of patients most likely to benefit from targeted interventions. It addresses the limitations of conventional risk scores and the contribution of emerging risk determinants, including digital biomarkers, genetic data, and wearable devices. It discusses the role of AI-enabled electrocardiography in the early detection of subclinical atrial fibrillation, left ventricular dysfunction, and coronary artery disease; the potential of opportunistic imaging (chest radiography, chest and coronary computed tomography, mammography) for subclinical atherosclerosis; and the integration of AI into clinical care pathways, electronic health records, clinical decision support systems, and telemonitoring networks. Overall, AI outlines the transition from a reactive cardiology model toward a predictive, proactive, and precision-based approach. Translation into routine clinical practice requires robust prospective evidence, randomized controlled trials, validation in heterogeneous populations, improved model interpretability, and adequate digital and regulatory infrastructures.