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 8 The performances of multi-layer perceptron with imbalanced learning methods with using clumped SNPs

Imbalanced Learning Methods Number of SNP 29		Prediction Class		PPV*	NPV**	Sensitivity	Specificity	F1 Score	Accuracy
MLP		Controls	Cases
Reel Class	Controls	251	27	0.46	0.88	0.40	0.90	0.43	0.82
Reel Class	Cases	34	23	0.46	0.88	0.40	0.90	0.43	0.82
SMOTE		Controls	Cases
Reel Class	Controls	210	64	0.79	0.80	0.82	0.77	0.81	0.80
Reel Class	Cases	52	245	0.79	0.80	0.82	0.77	0.81	0.80
SVM SMOTE		Controls	Cases
Reel Class	Controls	221	57	0.81	0.81	0.82	0.79	0.81	0.81
Reel Class	Cases	53	240	0.81	0.81	0.82	0.79	0.81	0.81
ADASYN		Controls	Cases
Reel Class	Controls	213	71	0.78	0.86	0.88	0.75	0.83	0.81
Reel Class	Cases	36	255	0.78	0.86	0.88	0.75	0.83	0.81
RUS		Controls	Cases
Reel Class	Controls	42	14	0.65	0.71	0.60	0.75	0.63	0.69
Reel Class	Cases	17	26	0.65	0.71	0.60	0.75	0.63	0.69