Table 2 Predictive model based on machine learning algorithms.
Model_name | Accuracy | AUC | 95% CI | Sensitivity | Specificity | PPV | NPV | Task |
|---|---|---|---|---|---|---|---|---|
LR | 0.972 | 1.000 | 1.000–1.000 | 0.944 | 1.000 | 1.000 | 0.947 | train |
LR | 0.900 | 1.000 | 1.000–1.000 | 0.800 | 1.000 | 1.000 | 0.833 | test |
SVM | 0.972 | 1.000 | 1.000–1.000 | 0.944 | 1.000 | 1.000 | 0.947 | train |
SVM | 0.900 | 1.000 | 1.000–1.000 | 0.800 | 1.000 | 1.000 | 0.833 | test |
KNN | 0.861 | 0.965 | 0.916–1.000 | 0.833 | 0.889 | 0.882 | 0.842 | train |
KNN | 0.800 | 0.940 | 0.799–1.000 | 0.800 | 0.800 | 0.800 | 0.800 | test |
RandomForest | 0.944 | 0.985 | 0.952–1.000 | 0.944 | 0.944 | 0.944 | 0.944 | train |
RandomForest | 0.900 | 1.000 | 1.000–1.000 | 0.800 | 1.000 | 1.000 | 0.833 | test |
ExtraTrees | 0.944 | 0.997 | 0.988–1.000 | 0.889 | 1.000 | 1.000 | 0.900 | train |
ExtraTrees | 0.900 | 1.000 | 1.000–1.000 | 0.800 | 1.000 | 1.000 | 0.833 | test |
XGBoost | 0.917 | 0.998 | 0.994–1.000 | 0.833 | 1.000 | 1.000 | 0.857 | train |
XGBoost | 0.900 | 1.000 | 1.000–1.000 | 0.800 | 1.000 | 1.000 | 0.833 | test |
LightGBM | 0.500 | 0.500 | 1.000–1.000 | 0.000 | 1.000 | 0.000 | 0.500 | train |
LightGBM | 0.500 | 0.500 | 1.000–1.000 | 0.000 | 1.000 | 0.000 | 0.500 | test |
MLP | 0.944 | 0.988 | 0.961–1.000 | 0.889 | 1.000 | 1.000 | 0.900 | train |
MLP | 0.900 | 1.000 | 1.000–1.000 | 0.800 | 1.000 | 1.000 | 0.833 | test |
