Model performance obtained from 5-fold CV with random-splitting
| SVM | LR | XGB | RF | DNN | |
|---|---|---|---|---|---|
| Accuracy | 0.903 ± 0.003 | 0.898 ± 0.004 | 0.9 ± 0.005 | 0.908 ± 0.004 | 0.877 ± 0.015 |
| Precision | 0.907 ± 0.003 | 0.908 ± 0.004 | 0.907 ± 0.005 | 0.912 ± 0.004 | 0.889 ± 0.02 |
| Recall | 0.923 ± 0.004 | 0.913 ± 0.005 | 0.918 ± 0.006 | 0.927 ± 0.005 | 0.889 ± 0.025 |
| F1 score | 0.915 ± 0.003 | 0.91 ± 0.003 | 0.912 ± 0.005 | 0.919 ± 0.003 | 0.891 ± 0.014 |
| AUROC | 0.959 ± 0.001 | 0.955 ± 0.002 | 0.955 ± 0.003 | 0.968 ± 0.002 | 0.945 ± 0.012 |
Performance metrics were obtained across 100 iterations of 5-fold CV with random-splitting (average ± standard deviation). CV, cross-validation; SVM, Support Vector Machine; LR, Logistic Regression; XGB, XGBoost; RF, Random Forest; DNN, Deep Neural Network, AUROC, area under the receiver operating characteristic curve.