Figure 3.

ROC Curves of the Risk Models for the Validation Cohort

(A) Practical ML models using 7 variables. (B) Framingham HF risk model. The 7 variables include age, pre-existing HF, creatinine clearance, cardiothoracic ratio on x-ray, LV ejection fraction, LV end-systolic diameter, and LV asynergy. AUC = area under the curve; GBM = gradient boosting machine; HF = heart failure; LV = left ventricular; ML = machine learning; ROC = receiver operating characteristic; SVM = support vector machine.