Skip to main content

Table 5 Comparison of the weighted accuracy on the test set of the best result from our voting method versus some well known cancer treatment guidelines

From: A voting approach to identify a small number of highly predictive genes using multiple classifiers

Classifier

Weighted accuracy on Test set

C4.5 with boosting

91.67%

St. Gallen 1998*

68%

NIH 2000*

79%

NPI*

58%

70-genes*

74%

BPIM*

68%

BDIM*

58%

  1. *Results obtained from Gevaert et al. [43], where results were provided as number of true positives and true negatives.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us