Skip to main content

Table 4 High-risk population identification compared using three machine learning algorithms

From: Identification of associated risk factors for serological distribution of hepatitis B virus via machine learning models

Algorithm

Training dataset

 

Testing dataset

AUC

Sensitivity

Specificity

 

Sensitivity

Specificity

Accuracy

Kappa

F-measure

RFa

0.730

0.633

0.765

 

0.761

0.674

0.717

0.435

0.728

SVMb

0.741

0.686

0.718

 

0.728

0.725

0.727

0.453

0.725

SGBc

0.746

0.637

0.783

 

0.776

0.674

0.725

0.450

0.736

  1. Note: a RF, random forest; b SVM, support vector machine; c SGB, stochastic gradient boosting;