Skip to main content

Table 1 Overview of individual classifier performance and definition of ensembles

From: A computational pipeline for the development of multi-marker bio-signature panels and ensemble classifiers

Classifier

Method

Features

Sensitivity

Specificity

AUC

Ensemble 1

Ensemble 2

Ensemble 3

Ensemble 4

Ensemble 5

Genomics 1

LDA

24

0.73

0.90

0.73

X

X

X

 

X

Genomics 2

SVM

50

0.82

0.95

0.96

 

X

  

X

Genomics 3

RF

50

0.64

0.95

0.92

  

X

X

X

Genomics 4

EN

43

0.73

1.00

0.93

 

X

  

X

Genomics 5

EN

174

0.73

1.00

0.95

   

X

X

Proteomics 1

SVM

12

0.64

0.95

0.94

X

X

X

 

X

Proteomics 2

EN

10

0.64

0.81

0.90

  

X

 

X

Proteomics 3

SVM

33

0.55

0.81

0.83

   

X

X

Proteomics 4

EN

13

0.55

0.86

0.85

 

X

  

X

Proteomics 5

SVM

13

0.64

0.95

0.94

  

X

 

X

  1. Shown is a list of 5 genomic and 5 proteomic classifiers, their individual classification performance and their inclusion into 5 ensembles that are explored in this paper. LDA stands for linear discriminant analysis; EN for Elastic Net (Generalized Linear Model); SVM for Support Vector Machine, and RF for Random Forest. Sensitivity, specificity and area under the ROC [receiver operator characteristics] Curve (AUC) for the individual classifiers were estimated using cross-validation.