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 3 The performances of random forest with imbalanced learning methods

Imbalanced learning methods number of SNP 399935		Prediction class		PPV*	NPV**	Sensitivity	Specificity	F1 Score	Accuracy
RF		Controls	Cases
Reel class	Controls	278	0	0.00	0.82	0.00	1.00	0.00	0.82
Reel class	Cases	57	0	0.00	0.82	0.00	1.00	0.00	0.82
SMOTE		Controls	Cases
Reel class	Controls	286	1	0.99	0.87	0.85	0.99	0.92	0.92
Reel class	Cases	40	244	0.99	0.87	0.85	0.99	0.92	0.92
SVM SMOTE		Controls	Cases
Reel class	Controls	290	3	0.97	0.84	0.68	0.98	0.80	0.87
Reel class	Cases	54	119	0.97	0.84	0.68	0.98	0.80	0.87
ADASYN		Controls	Cases
Reel class	Controls	285	0	1.00	0.86	0.84	1.00	0.91	0.92
Reel class	Cases	43	234	1.00	0.86	0.84	1.00	0.91	0.92
RUS		Controls	Cases
Reel class	Controls	26	21	0.47	0.43	0.35	0.55	0.40	0.45
Reel class	Cases	34	19	0.47	0.43	0.35	0.55	0.40	0.45