Skip to Content
  • Review
  • Open Access

16 September 2026

25 Pages

Beyond Traditional Risk Scores: Artificial Intelligence in Coronary Plaque Characterization and Personalized Atherosclerosis Management

,
,
,
,
and
1
School of Pediatrics, S.D. Asfendiyarov Kazakh National Medical University, Tole Bi Street 94, Almaty 050000, Kazakhstan
2
Institute for Fundamental and Applied Medical Research, S.D. Asfendiyarov Kazakh National Medical University, Tole Bi Street 94, Almaty 050000, Kazakhstan
3
Department of Cardiology, S.D. Asfendiyarov Kazakh National Medical University, Tole Bi Street 94, Almaty 050000, Kazakhstan
4
College of Medicine, Korea University, Seoul 02841, Republic of Korea

Abstract

Atherosclerosis remains a leading global cause of cardiovascular morbidity and mortality, yet its insidious progression and multifaceted etiology, spanning genetic, metabolic, and environmental determinants, often delay clinical recognition until adverse events occur. Traditional risk stratification tools, while foundational in preventive cardiology, are constrained by their reliance on limited variables and static linear assumptions, frequently misclassifying individuals at the extremes of risk. This review critically examines the transformative role of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in redefining atherosclerosis management across three interconnected domains. First, we explore how AI-driven predictive models integrate high-dimensional data, from genomics and imaging to real-time wearable metrics, to achieve superior cardiovascular risk stratification compared with conventional scores. Second, we detail AI’s capacity to automate and enhance plaque characterization through advanced imaging analysis, enabling reproducible quantification of burden, composition, and vulnerability markers that are imperceptible to human readers. Third, we investigate AI-powered clinical decision support systems, digital twins, and reinforcement learning approaches that facilitate dynamic, personalized treatment planning tailored to each patient’s evolving profile. We also critically address the ethical imperatives, algorithmic fairness, data privacy, transparency, and accountability, alongside practical challenges of clinical integration, regulatory validation, and health equity.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.