Skip to main content

Table 1 Estimated classifier performance for breast cancer, pathological complete response

From: Win percentage: a novel measure for assessing the suitability of machine classifiers for biological problems

Gene 1

Gene 2

NC

DLDA

LDA

SDA

UDA

QDA

217764_s_at

215127_s_at

0.812*

0.774

0.771

0.752

0.743

0.748

219233_s_at

205225_at

0.787

0.818*

0.770

0.781

0.799

0.775

216092_s_at

220040_x_at

0.785

0.787

0.796*

0.782

0.782

0.776

219438_at

218663_at

0.761

0.763

0.762

0.806*

0.777

0.771

203928_x_at

217297_s_at

0.739

0.744

0.759

0.793

0.810*

0.802

213228_at

212956_at

0.764

0.761

0.761

0.765

0.799

0.809*

  1. * Top performing classifier and any classifiers that do not have a significantly lower mean using a paired t-test with α = 0.05.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us