Table 2 Performance evaluation of twelve prediction models.
Model | AUC | Accuracy | Sensitivity | Specificity | F1 | |
|---|---|---|---|---|---|---|
RF | Random Forest | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
ADA | Ada Boost Classifier | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
GBM | Gradient Boosting Machine | 1.000 | 0.994 | 0.975 | 1.000 | 0.987 |
SVM | Support Vector Machine | 0.999 | 0.971 | 0.888 | 1.000 | 0.940 |
KNN | K-Nearest Neighbor | 0.999 | 0.961 | 0.863 | 0.996 | 0.920 |
XGBoost | eXtreme Gradient Boosting | 0.983 | 0.933 | 0.775 | 0.987 | 0.855 |
MLP | Multi-Layer Perception | 0.884 | 0.881 | 0.725 | 0.935 | 0.758 |
C5.0 | C5.0 | 0.872 | 0.837 | 0.500 | 0.953 | 0.611 |
NB | Naive Bayes | 0.861 | 0.821 | 0.388 | 0.970 | 0.525 |
NN | Neural Network | 0.807 | 0.776 | 0.250 | 0.957 | 0.364 |
LR | Logistic Regression | 0.805 | 0.763 | 0.313 | 0.918 | 0.403 |
GP | Gaussian Processes | 0.804 | 0.776 | 0.200 | 0.974 | 0.314 |
