Interpretable and reproducible machine learning model for coronary calcification and segment-level stenoses stratification on computed tomography angiography.
Authors
Affiliations (17)
Affiliations (17)
- Department of Radiology, School of Clinical Medicine, University of Cambridge, Cambridge, UK.
- Department of Systems Hub, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China.
- School of Biomedical Engineering & Imaging Science, King's College London, London, UK.
- British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK.
- Cambridge Baker Systems Genomics Initiative, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK.
- Department of Engineering, University of Cambridge, Cambridge, UK.
- Department of Clinical Neuroscience, School of Clinical Medicine, University of Cambridge, Cambridge, UK.
- Department of Oncology, University of Cambridge, Cambridge, UK.
- Department of Cardiac Surgery, Xiangya Hospital, Central South University, Changsha, China.
- School of Life and Health Sciences, Fujian Fuyao University of Science and Technology, Fuzhou, China.
- Nanjing Jingsan Medical Science and Technology, Ltd., Jiangsu, China.
- Department of Medicine, University of Cambridge, Cambridge, UK.
- Department of Radiology, School of Clinical Medicine, University of Cambridge, Cambridge, UK. [email protected].
- BHF Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK.
- Department of Radiology, School of Clinical Medicine, University of Cambridge, Cambridge, UK. [email protected].
- School of Biomedical Engineering & Imaging Science, King's College London, London, UK. [email protected].
- Department of Radiology, Royal Papworth Hospital, Cambridge, UK. [email protected].
Abstract
Coronary computed tomography angiography (CCTA) is widely used as a first-line tool for diagnosing and managing coronary artery disease (CAD), and machine learning (ML)-based analysis shows promise for quantitative CAD assessment. In this post hoc analysis of 909 participants from the SCOT-HEART trial (median follow-up, 5.8 years), we first evaluated the distribution of CCTA-derived imaging features in a cohort (n = 221) with a zero calcium score, stenoses < 10%, and no evidence of CAD on CCTA, across 21 image processing settings. Interpretable ML models were then developed and validated to quantify coronary calcification and stenoses in major coronary segments (LMA, LCX, LAD, pRCA, mRCA). Calcified plaques, stenoses, and myocardial infarction outcomes were comprehensively assessed. A total of 549 stable imaging features was identified across processing settings. Six ML algorithms (SVM, KNN, MLP, Naïve Bayes, gradient boosting, LightGBM) were evaluated for predicting coronary calcification and stenoses. The best model achieved an accuracy of 84.2% and an AUC of 0.973. Stenosis stratification accuracy exceeded 84.8% across all segments, with minimal (< 0.05) differences between models using all versus stable features. SHAP analysis indicated heterogeneous contributions of imaging phenotypes and clinical risk factors. Stable imaging features provide a reference for future ML-based coronary quantitatively assessments. Interpretable ML models demonstrated promising performance in quantifying coronary calcification and segment-level stenoses.