Table 2.

The result of machine learning model.

Model name	Accuracy	Prevalence	Recall	F1-Score	MCC	AUROC	Precision	Specificity	FNR	FPR
KNNC Test	0.779	0.623	0.896	0.835	0.517	0.846	0.782	0.586	0.104	0.414
GBDT Test	0.797	0.623	0.882	0.844	0.558	0.799	0.809	0.655	0.118	0.345
AdaBoost Test	0.810	0.623	0.882	0.852	0.588	0.786	0.825	0.690	0.118	0.310
LGBM Test	0.866	0.623	0.931	0.896	0.711	0.918	0.865	0.759	0.069	0.241
Logistic Test	0.680	0.623	0.778	0.752	0.303	0.780	0.727	0.517	0.222	0.483
RF Test	0.762	0.623	0.951	0.833	0.485	0.832	0.741	0.448	0.049	0.552
MLP Test	0.797	0.623	0.924	0.850	0.557	0.846	0.787	0.586	0.076	0.414
NB Test	0.658	0.623	0.715	0.723	0.277	0.731	0.730	0.563	0.285	0.437
CatBoost Test	0.797	0.623	0.931	0.851	0.558	0.915	0.784	0.575	0.069	0.425
XGB Test	0.853	0.623	0.917	0.886	0.682	0.923	0.857	0.747	0.083	0.253
SVM Test	0.714	0.623	0.938	0.804	0.365	0.769	0.703	0.345	0.063	0.655
DecisionTree Test	0.766	0.623	0.958	0.836	0.497	0.775	0.742	0.448	0.042	0.552
Mean_scores	0.773	0.623	0.892	0.830	0.508	0.827	0.779	0.577	0.108	0.423

F1-Score, Harmonic Mean of Precision and Recall; MCC, Matthews Correlation Coefficient; AUROC, Area Under the Receiver Operating Characteristic Curve; FNR, False Negative Rate; FPF, False Positive Rate; KNNC Test, k-Nearest Neighbors; GBDT Test, Gradient Boosting Decision Tree; AdaBoost Test, Adaptive Boosting; LGBM Test, Light Gradient-Boosting Machine; Logistic Test, Logistic Regression; RF Test, Random Forest; MLP Test, Multi-Layer Perceptron; NB Test, Naive Bayes; CatBoost Test, Categorical Boosting; XGB Test, Extreme Gradient Boosting; SVM Test, Support Vector Machine; DesicionTree Test, Decision Tree.