Table 13 Performance of model-based and model-free methods (using top 10 selected features).

From: Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease

Method

acc

sens

spec

ppv

npv

lor

auc

Logistic Regression

0.728

0.537

0.855

0.710

0.736

1.920

0.774

Random Forests

0.796

0.683

0.871

0.778

0.806

2.677

0.821

AdaBoost

0.689

0.610

0.742

0.610

0.742

1.502

0.793

XGBoost

0.699

0.707

0.694

0.604

0.782

1.699

0.787

SVM

0.709

0.561

0.806

0.657

0.735

1.672

0.822

Neural Network

0.699

0.610

0.758

0.625

0.746

1.588

 

Super Learner

0.738

0.683

0.774

0.667

0.787

1.999

 
Back to article page