Key result
Machine learning using non-contrast CT calcium and epicardial fat-omics predicts obstructive CAD with ~90% AUC.
Why the study?
Non-contrast CT calcium scoring provides direct evidence of coronary atherosclerosis, prompting the development of a machine learning model using CTCS features to predict obstructive CAD defined by CAD-RADS.
Can a machine learning model using clinical, Agatston-score-derived, and epicardial fat-omics features from non-contrast CT calcium scoring scans accurately predict obstructive coronary artery disease?
Observational (n=3,640)
Can a machine learning model using clinical, Agatston-score-derived, and epicardial fat-omics features from non-contrast CT calcium scoring scans accurately predict obstructive coronary artery disease?
A novel machine learning model using non-contrast CT calcium scoring and epicardial fat-omics can accurately predict obstructive CAD, potentially identifying patients who would benefit from advanced imaging.
May refine CAD risk stratification on routine calcium scoring CT; leaves open prospective validation before clinical adoption.
BACKGROUND: Low-cost/no-cost non-contrast CT calcium scoring (CTCS) exams can provide direct evidence of coronary atherosclerosis. In this study, using features from CTCS images, we developed a novel machine learning model to predict obstructive coronary artery disease (CAD), as defined by the coronary artery disease-reporting and data system (CAD-RADS). METHODS: This study analyzed 1324 patients from the SCOT-HEART trial who underwent both CTCS and CT angiography. Obstructive CAD was defined as CAD-RADS 4A-5, while CAD-RADS 0-3 were considered non-obstructive CAD. We analyzed clinical, Agatston-score-derived, and epicardial fat-omics features to predict obstructive CAD. The most predictive features were selected using elastic net logistic regression and used to train a CatBoost model. Model performance was evaluated using 1000 repeated five-fold cross-validation and survival analyses to predict major adverse cardiovascular event (MACE) and revascularization. Generalizability was assessed using an external validation set of 2316 patients for survival predictions. RESULTS: Among the 1324 patients, obstructive CAD was identified in 334 patients (25.2 %). Elastic net regression identified the top 14 features (5 clinical, 2 Agatston-score-derived, and 7 fat-omics). The proposed method achieved excellent performance for classifying obstructive CAD, with an AUC of 90.1 ± 0.9 % and sensitivity/specificity/accuracy of 83.5 ± 5.5 %/93.7 ± 1.9 %/82.4 ± 2.0 %. The inclusion of Agatston-score-derived and fat-omics features significantly improved classification performance. Survival analyses showed that both actual and predicted obstructive CAD significantly differentiated patients who experienced MACE and revascularization. CONCLUSIONS: We developed a novel machine learning model to predict obstructive CAD from non-contrast CTCS scans. Our findings highlight the potential clinical benefits of CTCS imaging in identifying patients likely to benefit from advanced imaging.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2025) conducted an observational in Obstructive coronary artery disease (n=3,640). Machine learning model (CatBoost) using clinical, Agatston-score, and epicardial fat-omics features was evaluated on Prediction of obstructive CAD (CAD-RADS 4A-5) (AUC 90.1%). A machine learning model incorporating clinical, Agatston-score, and epicardial fat-omics features from non-contrast CT calcium scoring scans predicted obstructive CAD with an AUC of 90.1%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: