Table 4 Performance summary of four machine learning models.

From: Serum growth differentiation factor 15 associates with extra-glandular manifestations and disease activity of primary Sjögren’s syndrome

Models

AUC

95% CI

Sensitivity

Specificity

Accuracy

NPV

PPV

F1

Decision Tree model

0.88

0.81–0.94

0.72

0.77

0.76

0.91

0.46

0.56

AdaBoost model

0.91

0.86–0.96

0.66

0.94

0.88

0.91

0.75

0.70

Random Forest model

0.89

0.84–0.94

0.47

0.92

0.82

0.87

0.60

0.53

Logistic Regression model

0.89

0.83–0.94

0.88

0.74

0.77

0.96

0.48

0.62

  1. AUC, area under the curve; CI, confidence interval; NPV, negative predictive value; PPV, positive predictive value; F1, F1-score; Adaboost, adaptive boosting.
Back to article page