Table 5 Prediction performances of four machine learning models incorporating SD-V-LY, RBC count, and LY%.

From: Evaluation of disease activity in systemic lupus erythematosus using standard deviation of lymphocyte volume combined with red blood cell count and lymphocyte percentage

Models

AUC

95% CI

Sensitivity

Specificity

Accuracy

NPV

PPV

F1

Decision tree

0.678

0.428–0.928

0.757

0.600

0.738

0.250

0.933

0.836

SVM

0.832

0.709–0.956

0.730

1.000

0.762

0.333

1.000

0.844

Linear SVC

0.903

0.788–1.000

0.811

0.600

0.786

0.300

0.938

0.870

Logistic regression

0.908

0.799–1.000

0.811

0.600

0.786

0.300

0.938

0.870

  1. AUC area under the curve; CI confidence interval; NPV negative predictive value; PPV positive predictive value; F1 F1-score; SVM support vector machine; SVC support vector classification.
Back to article page