Skip to main content

Table 2 Comparison of classification performance with three types of markers in the uterine leiomyoma cancer dataset

From: Mining pathway associations for disease-related pathway activity analysis based on gene expression and methylation data

Classifiers

Markers

Sensitivity

Specificity

Accuracy

kNN

genes

93.75

92.97 (2.21)

93.36 (1.1)

pathways

92.97 (2.21)

93.75

93.36 (1.1)

pathway-sets

93.75

93.75

93.75

RF

genes

90.62 (3.34)

93.75

93.36 (1.1)

pathways

92.97 (2.21)

92.97 (2.21)

92.19 (1.45)

pathway-sets

93.75

92.97 (2.21)

93.36 (1.1)

SVM

genes

93.75

92.19 (2.89)

92.97 (1.45)

pathways

92.97 (2.21)

93.75

93.75

pathway-sets

93.75

93.75

93.75

Naïve Bayes

genes

93.75

92.19 (2.89)

92.97 (1.45)

pathways

93.75

93.75

93.75

pathway-sets

93.75

93.75

93.75