Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring

2026-05-20

AI Summary

This study aims to enhance the accessibility and accuracy of myocardial ischemia prediction by leveraging routine non-contrast CT-based coronary calcium scoring. The authors propose a machine learning model built on XGBoost that integrates clinical variables, Agatston scores, and novel radiomic features derived from coronary calcifications—termed "calcium radiomics." Model interpretability and feature selection are achieved through SHAP (SHapley Additive exPlanations) analysis, and performance is rigorously evaluated using five-fold cross-validation. The model achieves an accuracy of 98.9 ± 3.0%, sensitivity of 79.2 ± 8.4%, and F1 score of 87.7 ± 5.3%. Calcium radiomics features significantly outperform conventional approaches (p < 0.05), with the number of calcified arteries emerging as a key predictor strongly associated with myocardial ischemia, offering a promising new direction for cardiovascular risk stratification.

Abstract

Non-contrast computed tomography calcium scoring (CTCS) is widely recognized as an effective tool for cardiovascular risk stratification. This study aimed to develop a novel machine learning framework for predicting myocardial ischemia from routine non-contrast CTCS scans using quantitative coronary calcium assessment. This study analyzed 1,375 patients who underwent both non-contrast CTCS and regadenoson stress cardiac positron emission tomography myocardial perfusion imaging within one year at University Hospitals Cleveland Medical Center. A total of 74 variables, including clinical variables, Agatston score, and calcium-omics features, were evaluated. Relevant features were identified using XGBoost with Shapley Additive exPlanations (SHAP). Predictive models were trained and evaluated using 5-fold cross-validation. Among 987 patients, 89 (9%) were positive for myocardial ischemia. The final model incorporated the Agatston score, eight calcium-omics features, and age. The proposed model achieved a precision of 98.9+/-3.0%, sensitivity of 79.2+/-8.4, and F1 score of 87.7+/-5.3%. The addition of calcium-omics features significantly improved predictive performance compared with models using clinical variables alone or clinical variables with the Agatston score (p<0.05). Interestingly, the number of calcified arteries, despite being the lowest-ranked feature based on SHAP analysis, showed the strongest association with myocardial ischemia in logistic regression analysis (odds ratio: 3.63, 95% confidence interval: 2.80-4.77, p<0.00001). We developed a machine learning approach for predicting myocardial ischemia using routinely acquired non-contrast CTCS scans. Calcium-omics features provided incremental predictive value beyond conventional risk factors and Agatston scoring and may support more accessible cardiovascular risk stratification.

Problem

• myocardial ischemia
• coronary calcification
• non-contrast CT
• calcium scoring
• cardiovascular risk stratification

Innovation

• calcium-omics
• machine learning
• myocardial ischemia prediction
• non-contrast CT calcium scoring
• SHAP