Skip to main content

Table 3 Classification performance of marker profile based on random-forest classifiers for different pairs of groups

From: Serum protein signature of coronary artery disease in type 2 diabetes mellitus

 

Optimal markers giving the separation more than > 1 VIS

Classification accuracy (%)

Sensitivity (%)

Specificity (%)

AUC (Median)

p value

Control vs T2DM

Total 9 markers i.e., IL-1beta, GM-CSF, glucagon, PAI-I, rantes, IP-10, resistin, GIP, Apo-B.

76

72

81

0.72

< 0.0009

Control vs CAD

Total 14 markers i.e., resistin, PDGF-BB, PAI-1, lipocalin-2, leptin, IL-13, eotaxin, GM-CSF, Apo-E, ghrelin, adipsin, GIP, Apo-CII, IP-10.

86

85

87.5

0.84

3.5e−6

Control vs T2DM_CAD

Total 12 markers i.e., insulin, resistin, PAI-1, adiponectin, lipocalin-2 GM-CSF, adipsin, leptin, apo-AII, rantes, IL-6, Ghrelin.

92

92.3

90

0.92

4.2e−10

T2DM vs T2DM_CAD

Total 9 markers i.e., adiponectin, C-peptide, resistin, IL-1beta, Ghrelin, lipocalin-2, Apo-AII, IP-10, Apo-B

85.7

86.9

78.5

0.76

4.3e−6

  1. For each pair of groups, the Random Forest classifications were obtained with 10-fold cross validation (there were 1000 iterations where in each iteration the classifiers were trained on 90% of the subjects, while the rest 10% were used for prediction). Top discriminatory marker features for each pair wise classification. Fisher’s exact test were then performed on the confusion matrix, in order to judge the significance of the prediction profile
  2. VIS variable importance score, AUC area under curve, AUC is mentioned as median