Table 2. Model comparison.

AUC, area under the curve

	Model	Accuracy	c-statistics (AUC)	Recall	Precision	F1 value	Kappa	Matthews Correlation Coefficient	Training time
et	Extra Trees Classifier	0.967	0.9944	0.9518	0.9307	0.939	0.9164	0.9185	0.546
rf	Random Forest Classifier	0.9638	0.9922	0.946	0.9229	0.9329	0.9082	0.9096	0.532
xgboost	Extreme Gradient Boosting	0.9575	0.9898	0.9224	0.9205	0.9193	0.8906	0.8925	0.212
lightgbm	Light Gradient Boosting Machine	0.956	0.9911	0.9342	0.9074	0.9191	0.8889	0.8904	0.149
dt	Decision Tree Classifier	0.9387	0.9213	0.8853	0.8847	0.8826	0.8412	0.8433	0.207
gbc	Gradient Boosting Classifier	0.9387	0.9849	0.9099	0.8693	0.8868	0.8449	0.8474	0.294
lr	Logistic Regression	0.8789	0.9383	0.7243	0.8044	0.7583	0.678	0.6825	0.601
ridge	Ridge Classifier	0.8774	0	0.7243	0.8008	0.756	0.6747	0.6796	0.141
lda	Linear Discriminant Analysis	0.8773	0.9422	0.736	0.7938	0.7598	0.6778	0.6817	0.177
svm	SVM - Linear Kernel	0.8663	0	0.6761	0.8009	0.7251	0.6382	0.6483	0.104
ada	Ada Boost Classifier	0.8663	0.9329	0.6651	0.8051	0.7247	0.6375	0.6452	0.274
knn	K Neighbors Classifier	0.8649	0.9379	0.5772	0.8675	0.6877	0.6073	0.6307	0.259
dummy	Dummy Classifier	0.7375	0.5	0	0	0	0	0	0.114
qda	Quadratic Discriminant Analysis	0.5694	0.5852	0.5143	0.3733	0.3391	0.0825	0.1196	0.115
nb	Naive Bayes	0.5233	0.9067	0.9941	0.3593	0.5268	0.227	0.3231	0.192