AI-CCTA for Predicting Cardiovascular Events in CAD

This multicenter, retrospective registry study aims to evaluate the value of artificial intelligence (AI)-derived coronary CT angiography (CCTA) parameters in predicting long-term cardiovascular events in patients with coronary artery disease (CAD). We plan to enroll 3,000 patients from five tertiary hospitals who underwent both CCTA and invasive coronary angiography (ICA) within 90 days. Using ICA and quantitative flow ratio (QFR) as reference standards, we will compare the diagnostic performance of different commercial AI software platforms. Furthermore, we will investigate the association between AI-extracted CCTA multidimensional parameters-including high-risk plaque features, CT-derived fractional flow reserve (CT-FFR), and pericoronary fat attenuation index (FAI)-and major adverse cardiac events (MACE) during over one year of follow-up. We will also explore how lipid-lowering therapies, antiplatelet regimens, and inflammatory biomarkers modify these predictive relationships. This study is expected to provide imaging evidence for personalized risk stratification and optimized clinical decision-making in CAD management.