Risk predicting for acute coronary syndrome based on machine learning model with kinetic plaque features from serial coronary computed tomography angiography

More patients with suspected coronary artery disease underwent coronary computed tomography angiography (CCTA) as gatekeeper. However, the prospective relation of plaque features to acute coronary syndrome (ACS) events has not been previously explored.

One hundred and one out of 452 patients with documented ACS event and received more than once CCTA during the past 12 years were recruited. Other 101 patients without ACS event were matched as case control. 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 analysed by independent CCTA measurement core laboratories. Baseline anatomical, compositional, and haemodynamic parameters of lesions showed no significant difference between the two cohorts (P > 0.05). While the culprit lesions exhibited significant increase of luminal stenosis (10.18 ± 2.26% vs. 3.62 ± 1.41%, P = 0.018), remodelling index (0.15 ± 0.14 vs. 0.09 ± 0.01, P < 0.01), and necrotic core (4.79 ± 1.84% vs. 0.43 ± 1.09%, P = 0.019) while decrease of CT-FFR (−0.05 ± 0.005 vs. −0.01 ± 0.003, P < 0.01) and calcium ratio (−4.28 ± 2.48% vs. 4.48 ± 1.46%, P = 0.004) between follow-up CCTA and baseline scans in comparison to that of non-culprit lesion. The XGBoost model comprising the top five important plaque features revealed higher predictive ability (area under the curve 0.918, 95% confidence interval 0.861–0.968).

Dynamic changes of plaque features are highly relative with subsequent ACS events. The 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.