Table 2 Performance of the six models for the three datasets
Models | GBM | XGBoost | GLM | DNN | RF | SE | |
|---|---|---|---|---|---|---|---|
Training set | AUC | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
sensitivity | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | |
specificity | 1.000 | 1.000 | 1.000 | 0.994 | 1.000 | 1.000 | |
PPV | 1.000 | 1.000 | 1.000 | 0.994 | 1.000 | 1.000 | |
NPV | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | |
accuracy | 1.000 | 1.000 | 1.000 | 0.997 | 1.000 | 1.000 | |
F1-score | 1.000 | 1.000 | 1.000 | 0.997 | 1.000 | 1.000 | |
Validation set | AUC | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
sensitivity | 0.895 | 0.993 | 0.993 | 1.000 | 1.000 | 1.000 | |
specificity | 1.000 | 0.994 | 1.000 | 0.987 | 0.987 | 1.000 | |
PPV | 1.000 | 0.993 | 1.000 | 0.987 | 0.987 | 1.000 | |
NPV | 0.906 | 0.994 | 0.994 | 1.000 | 1.000 | 1.000 | |
accuracy | 0.948 | 0.993 | 0.997 | 0.993 | 0.993 | 1.000 | |
F1-score | 0.944 | 0.993 | 0.997 | 0.993 | 0.993 | 1.000 | |
Test set | AUC | 0.822 | 0.800 | 0.867 | 0.898* | 0.807 | 0.866 |
sensitivity | 0.348 | 0.742 | 0.719 | 0.820 | 0.809 | 0.787 | |
specificity | 1.000 | 0.820 | 0.978 | 0.854 | 0.539 | 0.910 | |
PPV | 1.000 | 0.805 | 0.970 | 0.849 | 0.637 | 0.897 | |
NPV | 0.605 | 0.760 | 0.777 | 0.826 | 0.738 | 0.810 | |
accuracy | 0.674 | 0.781 | 0.848 | 0.837 | 0.674 | 0.848 | |
F1-score | 0.517 | 0.772 | 0.826 | 0.834 | 0.713 | 0.838 | |