Influence of Subclinical Atherosclerosis Burden and Progression on Mortality

Clinically Accessible Liver Fibrosis Association with CT Scan Coronary Artery Disease Beyond Other Validated Risk Predictors: The ICAP Experience

Background/objectives: Cardiovascular risk (CVR) stratification in clinical settings remains limited. This study aims to evaluate clinical parameters that could improve the identification of higher-than-expected coronary artery disease (CAD) in CT scan coronarography. Methods: In a cross-sectional study of asymptomatic patients from the Integrated Cardiovascular Assessment Program (ICAP), volunteers aged 40-80 without diagnosed cardiovascular disease were assessed. CVR factors like obesity, lipid and glucose profiles, liver fibrosis risk (FIB-4 ≥ 1.3), C-reactive protein, and family history of CVD were evaluated. Patients were stratified by CVR following ESC guidelines. "CVR excess" was defined as CAD-RADS ≥ 2 in low-to-moderate-risk (LMR), CAD-RADS ≥ 3 in high-risk (HR), and CAD-RADS ≥ 4 in very-high-risk (VHR) groups. Results: Among 219 patients (mean age 57.9 ± 1.15 years, 14% female), 43.4% were classified as LMR, 49.3% as HR, and 7.3% as VHR. "CVR excess" was observed in 18% of LMR, 15% of HR, and 19% of VHR patients. LMR patients with prior statin use and HR patients with obesity were more likely to have "CVR excess" (p < 0.01 and p < 0.05, respectively). FIB-4 modified the effect of statin use and obesity on "CVR excess" prediction (p for interactions < 0.05). Models including age, sex, and both interactions showed a strong discrimination for "CVR excess" in LMR and HR groups (AUROC 0.84 (95% CI 0.73-0.95) and 0.82 (95% CI 0.70-0.93), respectively). Conclusions: Suspected liver fibrosis combined with statin use in LMR patients and obesity in HR patients is associated with CVR excess, providing potential indications for image CAD assessment in asymptomatic patients.

Artificial Intelligence in Ischemic Heart Disease Prevention

PURPOSE OF REVIEW

This review discusses the transformative potential of artificial intelligence (AI) in ischemic heart disease (IHD) prevention. It explores advancements of AI in predictive modeling, biomarker discovery, and cardiovascular imaging. Finally, considerations for clinical integration of AI into preventive cardiology workflows are reviewed.

RECENT FINDINGS

AI-driven tools, including machine learning (ML) models, have greatly enhanced IHD risk prediction by integrating multimodal data from clinical sources, patient-generated inputs, biomarkers, and imaging. Applications in these various data sources have demonstrated superior diagnostic accuracy compared to traditional methods. However, ensuring algorithm fairness, mitigating biases, enhancing explainability, and addressing ethical concerns remain critical for successful deployment. Emerging technologies like federated learning and explainable AI are fostering more robust, scalable, and equitable adoption. AI holds promise in reshaping preventive cardiology workflows, offering more precise risk assessment and personalized care. Addressing barriers related to equity, transparency, and stakeholder engagement is key for seamless clinical integration and sustainable, lasting improvements in cardiovascular care.