Table 2 Description of the traditional feature selection methods and the mean AUROC score in each setting
From: miRDM-rfGA: Genetic algorithm-based identification of a miRNA set for detecting type 2 diabetes
Traditional feature selection methods | Setting 7 | Setting 8 | Setting 9 |
|---|---|---|---|
Feature selection models | Univariate feature selection (f_classif) | Lasso (Logistic regression using L1 regularization) | Lasso (Logistic regression using L1 regularization) |
Selection methods | SelectKBest (top 3) | SelectFromModel (top 3) | SelectFromModel (top 3) |
T2DM classification model | Random forest | Lasso | Random forest |
Selected miRNAs | hsa-miR-6820–5p, hsa-miR-29b-2-5p, and hsa-miR-1307-3p | hsa-miR-22-3p, hsa-miR-92a-3p, and hsa-miR-181a-5p | hsa-miR-22-3p, hsa-miR-92a-3p, and hsa-miR-181a-5p |
Fold for cross-validation of test data | 3 | 3 | 3 |
Mean AUROC score by threefold cross-validation in test set and standard deviation | 0.72 ± 0.08 | 0.64 ± 0.05 | 0.52 ± 0.02 |