Skip to main content

Table 1 Average balanced accuracy (BACC) of the three variable selection methods

From: Knowledge-based variable selection for learning rules from proteomic data

Variable selection method

BACC (± std. dev)

(Sensitivity, Specificity)

P-Value

(randomization test)

None

66.40% (± 19.66)

(53.3%, 79.5%)

-

DSVS

71.84% (± 17.49)

(50.58%, 93.1%)

0.068

BSVS

78.24% (± 18.48)

(66.78%, 89.7%)

0.003

  1. None indicates no variable selection, DSVS is disease-specific variable selection and BSVS is biofluid-specific variable selection.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us