Table 2.

Hospitalization case: Hyperparameter best tunning for each model for F1-score

	All the variables			Age & gender			Top-12 features
	None	ADASYN	SMOTE	None	ADASYN	SMOTE	None	ADASYN	SMOTE
DeepNetwork	[256,128,64]	[256,128,64,32,16]	[256,128,64,32]	[512,256]	[128,64]	[128,64,32,16]	[512,256,128]	[128,64,32,16,8]	[128,64,32,16]
LR	1000	0.001	0.001	1	0.01	0.1	10	10	0.001
MLR	10	0.001	0.001	1	0.01	0.1	1	1	10
Knn	3	21	21	7	21	21	3	21	21
SVM lin.	100	0.001	0.001	0.001	0.001	0.01	10	100	10
SVM RBF	1000	1	1	1000	1000	1000	1000	1000	1000
AdaBoost	[10,2]	[10,2]	[10,2]	[10,1]	[10,2]	[10,2]	[20,2]	[10,2]	[10,2]
Bagging	[30,1000]	[20,1]	[80,1]	[60,1000]	[30,1000]	[50,1000]	[10,1000]	[30,1000]	[40,1000]
RF	[10,10]	[80,10]	[40,9]	[20,4]	[60,3]	[90,4]	[40,10]	[40,6]	[50,7]
MLP	40	80	10	80	20	30	50	10	10