BMC Medical Informatics and Decision Making

Table 4 Sensitivity, precision and F scores by virus, balancing method and feature selection

From: Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines

HBV mean (95% CI)	SMOTE	SMOTE RF	Downsize	Downsize RF	MDS	MDS RF
Fscore	0.056 (0.054, 0.057)	0.052 (0.050, 0.053)	0.056 (0.054, 0.057)	0.052 (0.050, 0.053)	0.065 (0.061 0.068)	0.059 (0.055, 0.063)
Precision	0.034 (0.032, 0.036)	0.026 (0.025, 0.027)	0.029 (0.028, 0.030)	0.027 (0.026, 0.028)	0.034 (0.032, 0.036)	0.031 (0.029 0.032)
Sensitivity	0.625 (0.605, 0.645)	0.611 (0.587, 0.634)	0.625 (0.605, 0.645)	0.611 (0.587, 0.634)	0.246 (0.231, 0.260)	0.675 (0.654, 0.680)
HCV mean (95% CI)	SMOTE	SMOTE RF	Downsize	Downsize RF	MDS	MDS RF
Fscore	0.187 (0.179, 0.196)	0.200 (0.196, 0.202)	0.174 (0.170, 0.178)	0.208 (0.200, 0.215)	0.192 (0.190, 0.195)	0.225 (0.220, 0.229)
Precision	0.134 (0.128, 0.140)	0.117 (0.115, 0.119)	0.103 (0.100, 0.105)	0.124 (0.20, 0.129)	0.115 (0.113, 0.117)	0.138 (0.134, 0.141)
Sensitivity	0.311 (0.296, 0.326)	0.668 (0.654, 0.682)	0.567 (0.545, 0.590)	0.625 (0.600, 0.650)	0.589 (0.579, 0.598)	0.610 (0.596, 0.623)

Downsize simple downsizing, Downsize RF Simple downsizing with random forest variable selection, MDS Multiple downsizing, MDS RF MDS with random forest variable selection, SMOTE Synthetic Minority Oversampling Technique, SMOTE RF SMOTE with random forest variable selection, HBV Hepatitis B virus, HCV Hepatitis C virus

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com