Table 6 Comparison of the proposed method with other feature selection methods in the test cohort in terms of classifier performance. The bold values indicate the highest score in each performance metric.

From: Machine learning-based automated classification of headache disorders using patient-reported questionnaires

Feature selection method

Accuracy

Minimum sensitivity

Minimum specificity

LASSO

0.8071

0.5273

0.4561

SVM-RFE

0.8014

0.4468

0.3443

mRMR-MIQ

0.7180

0.1600

0.0877

mRMR-MID

0.7055

0.0833

0.0597

  1. LASSO least absolute shrinkage and selection operator, SVM-RFE support vector machine recursive feature elimination, mRMR-MIQ minimum-redundancy maximum-relevancy mutual information quotient, mRMR-MID minimum-redundancy maximum-relevancy mutual information difference.
Back to article page