Skip to main content

Table 3 The predictive value and optimal cutoff in the different models

From: Predictive value of machine learning algorithm of coronary artery calcium score and clinical factors for obstructive coronary artery disease in hypertensive patients

 

Cutpoint

Sensitivity

Specificity

PPV

NPV

accuracy

LR

0.121

0.726

0.702

0.319

0.930

0.706

RF

0.184

0.768

0.722

0.347

0.942

0.730

SVM

0.134

0.713

0.681

0.301

0.925

0.687

NNET

0.323

0.511

0.726

0.447

0.875

0.618

XGBoost

0.254

0.837

0.786

0.389

0.950

0.767

  1. PPV, positive predict value; NPV, negative predict value. LR, Logistic Regression; XGBoost, Extreme Gradient Boosting; RF, Random Forest; SVM, Support Vector Machine; NNET, Neural Network; PPV, positive predictive value; NPV, negative predictive value
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us