From:  Prediction of low cardiac output syndrome in patients following non-isolated coronary artery bypass grafting surgery using machine learning

 Prediction and calibration performance of the five algorithms in the training cohort of the model.

AlgorithmAUC (95% CI)SensitivitySpecificityAccuracyPrecisionBrier score
LR0.854 (0.808–0.900)0.8260.730.7610.5970.145
XGB0.933 (0.903–0.962)0.8490.8650.860.7530.107
RFC0.918 (0.884–0.952)0.8720.8310.8450.7140.131
SVM0.850 (0.803–0.898)0.7670.7980.7880.6470.146
LGBM0.936 (0.907–0.964)0.9420.7640.8220.6590.12

AUC: area under the curve; CI: confidence interval; LR: logistic regression; XGB: extreme gradient boosting; RFC: random forest classifier; SVM: support vector machine; LGBM: light gradient boosting machine.