Skip to main content

Table3 Optimal cutpoints and youden index for each model

From: Predictive value of CAC score combined with clinical features for obstructive coronary heart disease on coronary computed tomography angiography: a machine learning method

 

Cutpoint

SE

SP

PPV

NPV

Accuracy

Youden index

RF model

0.229

0.749

0.806

0.436

0.941

0.778

0.555

CACS model

0.136

0.655

0.789

0.384

0.919

0.722

0.444

Clinical model

0.129

0.825

0.644

0.317

0.948

0.734

0.468

  1. SE, sensitivity; SP, specificity; PPV, positive predictive value; NPV, negative predictive value; RF, random forest; CACS model, CAC score only; clinical model, atherosclerotic cardiovascular disease risk factors and CAC score