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 9 The performances of logistic regression with imbalanced learning methods with using clumped SNPs

Imbalanced learning methods number of SNP 29		Prediction class		PPV*	NPV**	Sensitivity	Specificity	F1 score	Accuracy
LR		Controls	Cases
Reel class	Controls	272	6	0.82	0.90	0.47	0.98	0.60	0.89
Reel class	Cases	30	27	0.82	0.90	0.47	0.98	0.60	0.89
SMOTE		Controls	Cases
Reel class	Controls	210	64	0.79	0.76	0.79	0.77	0.79	0.78
Reel class	Cases	67	245	0.79	0.76	0.79	0.77	0.79	0.78
SVM SMOTE		Controls	Cases
Reel class	Controls	213	65	0.77	0.74	0.75	0.77	0.76	0.76
Reel class	Cases	73	220	0.77	0.74	0.75	0.77	0.76	0.76
ADASYN		Controls	Cases
Reel class	Controls	208	76	0.75	0.76	0.77	0.73	0.76	0.75
Reel class	Cases	67	224	0.75	0.76	0.77	0.73	0.76	0.75
RUS		Controls	Cases
Reel class	Controls	48	8	0.79	0.79	0.70	0.86	0.74	0.79
Reel class	Cases	13	30	0.79	0.79	0.70	0.86	0.74	0.79