The primary design of this study is an ambispective cohort study. We plan to integrate coronary imaging features (including parameters derived from Coronary Computed Tomography Angiography(CCTA) and coronary angiography(CAG)), coronary functional indices (e.g., FFR, QFR), and metabolic biomarkers (e.g., LDL-C, Lp(a), hs-CRP). First, we will develop a multimodal risk prediction model for coronary artery disease using a retrospective cohort; subsequently, we will validate the model in a prospective cohort to assess its performance in discriminating high- versus low-risk individuals and to explore its potential clinical utility for risk stratification and decision-making.