Skip to main content

Table 2 Average classification accuracy and associated standard deviations (in parentheses) of prostate cancer subtypes in the test group using SBGG, BBGDE, SVM and Random Forest models for 50 marker genes

From: A Bayesian approach for inducing sparsity in generalized linear models with multi-category response

Sample Type

SBGG

SBGDE

SVM

Random Forest

Benign

95.4 (3.07)

99.6 (1.9)

90.1 (1.7)

96.8 (1.3)

PIN

80.6 (0.08)

53.4 (1.4)

38.2 (8.2)

52 (1.1)

PCA

98.9 (1.9)

65.4 (7.2)

45.8 (6.2)

84.8 (5.4)

MET

96.8 (4.6)

95.4 (6.3)

81.8 (1.6)

83.6 (7.09)