Table 12 Performance of model-based and model-free methods (using all 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

0.505

0.390

0.581

0.381

0.590

−0.121

0.603

Random Forests

0.689

0.537

0.790

0.629

0.721

1.473

0.702

AdaBoost

0.718

0.610

0.790

0.658

0.754

1.773

0.719

XGBoost

0.670

0.610

0.710

0.581

0.733

1.340

0.711

SVM

0.757

0.512

0.919

0.808

0.740

2.482

0.767

Neural Network

0.680

0.659

0.694

0.587

0.754

1.474

 

Super Learner

0.670

0.512

0.774

0.600

0.706

1.281

 
Back to article page