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.