Table 3.
Screening Evaluation Metrics for Machine Learning Algorithms Using 10-fold cross-validation.
| Classifier | LSTM | CNN | SVM | KNN | LDA | LR | NB | RF | MLP | XGB |
|---|---|---|---|---|---|---|---|---|---|---|
| Average-AUC | 0.910 | 0.864 | 0.880 | 0.871 | 0.886 | 0.891 | 0.874 | 0.881 | 0.883 | 0.952 |
| Average-Kappa | 0.717 | 0.652 | 0.672 | 0.656 | 0.691 | 0.702 | 0.624 | 0.706 | 0.698 | 0.763 |
| Average- Accuracy | 0.877 | 0.833 | 0.794 | 0.811 | 0.852 | 0.823 | 0.857 | 0.744 | 0.779 | 0.891 |
AUC, area under curve; SVM, support vector machine; XGBoost, extreme gradient boosting; RF, random forest; LDA, linear discriminant analysis; LR, logistic regression; NB, naive bayesian model; KNN, k-nearest neighbors; MLP, multilayer perceptron; LSTM, long short-term memory; CNN, convolutional neural network.