Long-term Major Adverse Cardiac Event Prediction by Computed Tomography-derived Plaque Measures and Clinical Parameters Using Machine Learning

Abstract

Objective The present study evaluated the usefulness of machine learning (ML) models with the coronary computed tomography imaging and clinical parameters for predicting major adverse cardiac events (MACEs). Methods The Nationwide Gender-specific Atherosclerosis Determinants Estimation and Ischemic Cardiovascular Disease Prospective Cohort study (NADESICO) of 1,187 patients with suspected coronary artery disease 50-74 years old was used to build a MACE prediction model. The ML random forest (RF) model was compared with a logistic regression analysis. The performance of the ML model was evaluated using the area under the curve (AUC) with the 95% confidence interval (CI). Results Among 1,178 patients from the NADESICO dataset, MACEs occurred in 103 (8.7%) patients during a median follow-up of 4.4 years. The AUC of the RF model for MACE prediction was 0.781 (95% CI: 0.670-0.870), which was significantly higher than that of the conventional logistic regression model [AUC, 0.750 (95% CI: 0.651-0.839)]. The important features in the RF model were coronary artery stenosis (CAS) at any site, CAS in the left anterior descending branch, HbA1c level, CAS in the right coronary artery, and sex. In the external validation cohort, the model accuracy of ensemble ML-RF models that were trained on and tuned using the NADESICO dataset was not similar [AUC: 0.635 (95% CI: 0.599-0.672)]. Conclusion The ML-RF model improved the long-term prediction of MACEs compared to the logistic regression model. However, the selected variables in the internal dataset were not highly predictive of the external dataset. Further investigations are required to validate the usefulness of this model.

Keywords: coronary artery calcification; coronary artery disease; coronary computed tomography; machine learning analysis; major adverse cardiac events; validation study.

Figure 1.

The receiver operating characteristic curve for internal validation. A comparison of the best cross-validation folder performance of the ML model, LR model, and score methods. AUC: area under the curve, ML: machine learning, LR: random forest

Figure 2.

Permutation feature importance in the entire population. CAS: coronary artery stenosis, DM: diabetes mellitus, LAD: left anterior descending artery, LCX: left circumflex artery, RCA: right coronary artery, TC: total cholesterol

Figure 3.

Permutation feature importance: (a) in the men; (b) in the women. BP: blood pressure, CAS: coronary artery stenosis, DM: diabetes mellitus, eGFR: estimated glomerular filtration rate, HDL-C: high density lipoprotein cholesterol, LAD: left anterior descending artery, RCA: right coronary artery, TC: total cholesterol