Conventional and Non‑conventional Risk Factors: A Need for an Innovative Integration in Cardiovascular Disease

Cardiovascular disease (CVD) remains the most important cause of morbidity and mortality worldwide, despite major advances in prevention and treatment strategies. Traditional risk scores based on conventional risk factors have improved cardiovascular prevention but are insufficient for residual risk, particularly that driven by inflammation, endothelial dysfunction, thrombosis, metabolic alterations, and chronic comorbidities such as chronic kidney disease. In this narrative review, we discuss the limitations of current cardiovascular risk assessment models and explore the added value of non-conventional biomarkers, including inflammatory, endothelial, thrombotic, and metabolic markers, as well as emerging diagnostic technologies. We analyze the growing role of point-of-care testing (POCT) in enabling rapid, decentralized, and dynamic biomarker assessment, and we examine how artificial intelligence (AI)-based approaches can integrate heterogeneous clinical, biological, and technological data. Evidence suggests that multimodal, AI-driven models outperform traditional algorithms in identifying high-risk individuals and refining personalized prevention strategies. We propose an innovative framework for cardiovascular prevention based on the integration of clinical data, biomarkers, POCT, and AI, aiming to move from static risk estimation toward a dynamic and personalized cardiovascular risk assessment paradigm.