Skip to main content

Table 3 Performance of prediction models by standard statistical evaluation parameters for independent testing dataset.

From: Classification models for clear cell renal carcinoma stage progression, based on tumor RNAseq expression trained supervised machine learning algorithms

Classifier

Accuracy

Sensitivity

Specificity

F-value

auROC#

J48

62.11

79.63%

39.02%

0.704918

0.563

Naïve Bayes

72.63

93.56%

48.78%

0.790323

0.749

Random Forest

76.84

88.89%

60.98%

0.813559

0.778

SMO

73.68

87.04%

56.10%

0.789916

0.716

  1. # auROC denotes area under Receivers Operating Characteristic curve. Highest numerical value in each column is highlighted as bold letters.
Back to article page

BMC Proceedings

ISSN: 1753-6561

Contact us