Table 3.

Performance metrics of classifiers using random oversampling preprocessing and no preprocessing without feature selection.

	Classifier	ROC	Sensitivity	Specificity	F1 Score	Accuracy	NPV
Without RandomOversample	LR	0.577	0	1	0	0.791	0.791
	SVM	0.535	0	1	0	0.791	0.791
	AdaBoost	0.5	0	1	0	0.791	0.791
	RF	0.502	0.051	0.978	0.09	0.784	0.796
	XGBoost	0.514	0.102	0.897	0.136	0.73	0.791
	CatBoost	0.539	0.051	0.978	0.09	0.784	0.796
	LightGBM	0.53	0.119	0.901	0.159	0.738	0.794
	MLP	0.571	0	0.991	0	0.784	0.789
After RandomOversample	LR	0.577	0.538	0.571	0.552	0.554	0.542
	SVM	0.743	0.684	0.680	0.687	0.682	0.673
	RF	0.951	0.882	0.906	0.895	0.894	0.880
	MLP	0.797	0.741	0.700	0.730	0.720	0.721
	LightGBM	0.942	0.892	0.833	0.869	0.863	0.880
	AdaBoost	0.686	0.660	0.581	0.641	0.622	0.621
	XGBoost	0.943	0.901	0.818	0.868	0.860	0.888
	CatBoost	0.936	0.877	0.818	0.855	0.848	0.865