Skip to main content

Table 1 Classification performance test with the independent dataset

From: Stable feature selection based on the ensemble L 1 -norm support vector machine for biomarker discovery

Classifier

Performance measure

FCBF

Random forest

(766)

Random forest

(180)

Ensemble SVM-RFE

Our method

AdaBoost

Accuracy

0.789

0.845

0.859

0.887

0.901

F1-score

0.545

0.593

0.667

0.75

0.774

MCC

0.408

0.532

0.588

0.68

0.717

AUC

0.7

0.717

0.766

0.825

0.834

Logistic regression

Accuracy

0.789

0.789

0.817

0.845

0.845

F1-score

0.651

0.595

0.667

0.718

0.732

MCC

0.533

0.456

0.552

0.623

0.646

AUC

0.801

0.74

0.799

0.838

0.858

Random forest

Accuracy

0.817

0.817

0.803

0.831

0.845

F1-score

0.48

0.48

0.462

0.5

0.56

MCC

0.426

0.426

0.381

0.479

0.531

AUC

0.658

0.658

0.649

0.667

0.697

SVM

Accuracy

0.803

0.831

0.859

0.831

0.901

F1-score

0.632

0.571

0.583

0.684

0.811

MCC

0.504

0.489

0.589

0.577

0.749

AUC

0.77

0.708

0.706

0.808

0.895

  1. The performance score is calculated on the independent dataset. The items that obtained the best score are highlighted in bold text. The numbers below the random forest classifier denote the number of genes selected for the performance test