Predicting Midterm Risk of Coronary Plaque Progression in Subclinical Nonobstructive Coronary Atherosclerosis Using...

Coronary atherosclerosis (CAS) is a leading cause of cardiovascular morbidity and mortality. Subclinical nonobstructive CAS, often under-recognized in practice, carries substantial risk. We developed a clinically interpretable machine learning model that integrated traditional risk factors with quantitative plaque features derived from coronary computed tomography angiography to predict midterm plaque progression.

We retrospectively studied 664 adults with subclinical nonobstructive CAS from a community screening program who underwent serial coronary computed tomography angiography (median follow-up: 56 months). Candidate variables were filtered using Spearman correlation and a bootstrap-enhanced least absolute shrinkage and selection operator. Seven algorithms were compared; the optimal model was explained using SHapley Additive exPlanations (SHAP; https://github.com/shap/shap).

Participants had a mean age of 62 years; 53.6% were men. The random forest model performed best. The final 8-feature random forest achieved an area under the receiver operating characteristic curve of 0.875 (95% confidence interval, 0.827-0.920), with precision 0.863, accuracy 0.779, recall 0.726, F1 score 0.788, specificity 0.849, and negative predictive value 0.702. SHAP analysis identified fibrofatty plaque volume and coronary artery calcium category as the principal drivers of plaque progression.

The proposed machine learning SHAP framework integrates imaging and clinical features to enable individualized risk stratification for subclinical nonobstructive CAS. Incorporating quantitative imaging biomarkers into longitudinal follow-up might facilitate the early identification of high-risk individuals and support the timely implementation of intensive lipid-lowering, anti-inflammatory therapy, and lifestyle modification, thereby maximizing plaque stabilization or regression and ultimately reducing the risk of future cardiovascular events.