Table 2.
Model prediction performance in the training set.
| Algorithm | AUC (95%CI) | Accuracy | Sensitivity | Specificity | PPV | NPV | F1 Score |
|---|---|---|---|---|---|---|---|
| SVM | 0.963 (0.930–0.996) | 0.924 | 0.872 | 1.000 | 1.000 | 0.841 | 0.932 |
| Adaboost | 0.989 (0.978–1.000) | 0.947 | 0.910 | 1.000 | 1.000 | 0.833 | 0.953 |
| XGBoost | 0.984 (0.968–0.999) | 0.931 | 0.897 | 0.981 | 0.986 | 0.867 | 0.940 |
| RF | 0.990 (0.959–1.000) | 0.947 | 0.910 | 1.000 | 1.000 | 0.883 | 0.953 |
| KNN | 0.982 (0.964–0.9993) | 0.924 | 0.897 | 0.962 | 0.972 | 0.864 | 0.933 |
| LR | 0.969 (0.939–0.999) | 0.664 | 0.987 | 0.189 | 0.642 | 0.909 | 0.778 |
AUC = Area Under Curve, SVM = Support Vector Machine, AdaBoost = Adaptive Boosting, XGBoost = eXtreme Gradient Boosting, RF = Random Forest, KNN = K-Nearest Neighbors, LR = Logistic Regression, PPV=Positive Predictive Value, NPV=Negative Predictive Value.