Skip to main content

Table 3 Performance metrics of the machine learning models

From: Machine learning for predicting diabetes risk in western China adults

Models

Accuracy

Sensitivity

Specificity

PPV

NPV

AUC

CART

0.7870

0.8181

0.7845

0.2322

0.9819

0.8839

LightGBM

0.7799

0.8237

0.7764

0.2269

0.9822

0.8808

RF

0.7663

0.8217

0.7619

0.2156

0.9817

0.8730

XGBoost

0.8314

0.8180

0.8324

0.2800

0.9829

0.9122

MLP

0.8008

0.7803

0.8025

0.2394

0.9787

0.8754

TabNet

0.8068

0.7728

0.8095

0.2443

0.9781

0.8759

LR

0.9260

0.07522

0.9938

0.4918

0.93097

0.8161

  1. PPV positive predictive value, NPV negative predictive value, AUC area under the receiver operating characteristic curve
Back to article page

Diabetology & Metabolic Syndrome

ISSN: 1758-5996

Contact us