The use of class imbalanced learning methods on ULSAM data to predict the case–control status in genome-wide association studies

Journal of Big Data

Table 4 The performances of multi-layer perceptron with imbalanced learning methods

Imbalanced learning methods number of SNP 399935		Prediction class		PPV*	NPV**	Sensitivity	Specificity	F1 Score	Accuracy
MLP		Controls	Cases
Reel class	Controls	277	1	0.00	0.82	0.00	0.99	0.00	0.82
Reel class	Cases	57	0	0.00	0.82	0.00	0.99	0.00	0.82
SMOTE		Controls	Cases
Reel class	Controls	282	5	0.98	0.96	0.96	0.98	0.97	0.97
Reel class	Cases	9	275	0.98	0.96	0.96	0.98	0.97	0.97
SVM SMOTE		Controls	Cases
Reel class	Controls	290	3	0.97	0.89	0.80	0.98	0.88	0.92
Reel class	Cases	33	140	0.97	0.89	0.80	0.98	0.88	0.92
ADASYN		Controls	Cases
Reel class	Controls	285	0	1.00	0.89	0.88	1.00	0.93	0.84
Reel class	Cases	32	245	1.00	0.89	0.88	1.00	0.93	0.84
RUS		Controls	Cases
Reel class	Controls	45	2	0.50	0.46	0.03	0.95	0.07	0.47
Reel class	Cases	51	2	0.50	0.46	0.03	0.95	0.07	0.47