Table 4.

Metrics of machine learning.

Classifier	AUCa	Accuracy	Sensitivity	Specificity	Precision	PPVb	F1-score	NPVc
LRd	0.946	0.817	0.808	0.953	0.818	0.818	0.809	0.954
SVMe	0.980	0.858	0.857	0.965	0.861	0.861	0.854	0.964
RFf	0.976	0.858	0.860	0.965	0.856	0.856	0.854	0.964
KNNg	0.930	0.767	0.772	0.942	0.787	0.787	0.768	0.941
MLPh	0.973	0.825	0.823	0.957	0.830	0.830	0.819	0.956
LightGBMi	0.963	0.900	0.908	0.975	0.895	0.895	0.899	0.974
AdaBoostj	0.962	0.858	0.859	0.964	0.855	0.855	0.856	0.964
XGBoostk	0.961	0.908	0.905	0.978	0.901	0.901	0.901	0.977
CatBoostl	0.970	0.892	0.892	0.974	0.885	0.885	0.885	0.973

^aAUC: area under the curve.

^bPPV: positive predictive value.

^cNPV: negative predictive value.

^dLR: Logistic Regression.

^eSVM: Support Vector Machine.

^fRF: Random Forest.

^gKNN: k-nearest neighbor.

^hMLP: Multilayer Perceptron.

ⁱLightGBM: Light Gradient-Boosting Machine.

^jAdaBoost: Adaptive Boosting.

^kXGBoost: Extreme Gradient Boosting.

^lCatBoost: Categorical Boosting.