Radiomic Carotid Plaque Features Integrated into Machine Learning Models for Cardiovascular Risk Prediction.
Authors
Affiliations (8)
Affiliations (8)
- Department of Medicine, University of British Columbia, Vancouver, Canada.
- School of Computing, Queen's University, Kingston, Canada.
- Department of Medicine, Cardiovascular Imaging Network at Queen's, Queen's University, Kingston, Canada.
- Department of Internal Medicine, University of Toronto. Toronto, Canada.
- School of Computing, Queen's University, Kingston, Canada; Department of Biomedical and Molecular Sciences, Queen's University, Kingston, Canada.
- School of Medicine, Johns Hopkins University, Baltimore, USA.
- Stroke Diagnosis & Monitoring Division, AtheroPoint™, Roseville, CA, USA.
- Department of Medicine, Division of Cardiology, CINQ, Queen's University, Kingston, Canada. Electronic address: [email protected].
Abstract
Carotid plaque detected by ultrasound is associated with major adverse cardiovascular events (MACE) and can be characterized using manual or automated radiomic analysis. The generated plaque characteristics may have complex interdependencies for which machine learning (ML) may provide predictive modeling. The objective of the study was to develop a ML model to predict MACEs from clinical variables, manual focused vascular ultrasound (FOVUS) measurements, and semi-automated radiomic ultrasound features. Carotid ultrasound scans were performed on 493 patients and MACE outcomes were collected over 5 y by medical chart review. ML-based models were compared that incorporated clinical characteristics, manual FOVUS measurements, and quantitative radiomic features. Feature selection was performed via ReliefF, with a sample:feature ratio of 10:1 yielding 11 top features for training the ML model. Four ML classifiers were developed using 10 K-fold cross-validation. Over 5 years, 144 patients (29%) experienced a MACE outcome (death, unstable angina, myocardial infarction, stroke, transient ischemic attack, carotid endarterectomy, coronary artery bypass graft, or percutaneous coronary intervention). The best model (x-gradient boost) performed significantly better than chance alone (p = 2 × 10<sup>-7</sup>), with the highest average prediction accuracies (clinical data only: 0.849 ± 0.039, FOVUS only: 0.875 ± 0.029, radiomics only: 0.705 ± 0.036, clinical and FOVUS data: 0.885 ± 0.023, clinical and radiomics data: 0.804 ± 0.053, FOVUS and radiomic data: 0.935 ± 0.043, all data: 0.958 ± 0.023). The combination of clinical, FOVUS and radiomics data provides strong predictive power for distinguishing MACE from non-MACE. Moreover, both automated and manual plaque quantification can generate predictive features.