Table 4.

Performance evaluation of ML models in terms of accuracy, precision, recall and AUC metrics.

	Accuracy		Precision (CAD class)		Recall (CAD Class)		AUC
	No SMOTE	SMOTE	No SMOTE	SMOTE	No SMOTE	SMOTE	No SMOTE	SMOTE
NB	0.700	0.906	0.336	0.973	0.318	0.835	0.700	0.941
LR	0.754	0.779	0.645	0.710	0.088	0.762	0.729	0.793
MLP	0.730	0.798	0.355	0.742	0.146	0.801	0.661	0.833
3-NN	0.722	0.796	0.311	0.760	0.140	0.867	0.585	0.854
RF	0.748	0.855	0.493	0.844	0.063	0.871	0.693	0.931
RotF	0.751	0.845	0.625	0.827	0.054	0.872	0.713	0.925
J48	0.714	0.787	0.268	0.777	0.205	0.804	0.636	0.857
Stacking	0.747	0.909	0.482	0.967	0.059	0.876	0.698	0.961
Bagging	0.748	0.843	0.500	0.827	0.045	0.866	0.702	0.926
Voting	0.787	0.908	0.367	0.960	0.187	0.852	0.702	0.958