Wang Y, Chen H, Sun T, et al. - This study attempted to explore the risk predicting for acute coronary syndrome based on a machine learning model with kinetic plaque features from serial coronary computed tomography angiography. In this study, 101 out of 452 patients with documented acute coronary syndrome (ACS) event and received more than once coronary computed tomography angiography (CCTA) during the past 12 years were included. Moreover, other 101 patients without ACS events were compared as case control. Via independent CCTA measurement core laboratories, baseline, follow-up, and changes of anatomical, compositional, and haemodynamic parameters [e.g. luminal stenosis, plaque volume, necrotic core, calcification, and CCTA-derived fractional flow reserve (CT-FFR)] were examined. The results demonstrate that the dynamic changes of plaque features are highly relative with subsequent ACS events. The outcomes reveal that machine learning model of integrating these lesion characteristics (e.g. CT-FFR, necrotic core, remodelling index, plaque volume, and calcium) can improve the ability for predicting risks of ACS events.