Table 3.
Model prediction performance comparison results in terms of ROC-AUC and AUPR
| Model | Algorithm | ROC-AUC | AUPR |
|---|---|---|---|
| 32 | XGBOOST | 0.883 ± 0.005 | 0.357 ± 0.008 |
| 33 | XGBOOST | 0.891 ± 0.004 | 0.370 ± 0.014 |
| 35 | ERT | 0.849 ± 0.007 | 0.244 ± 0.013 |
| 37 | Logistic Regression | 0.846 ± 0.008 | 0.188 ± 0.007 |
| 39 | Feed-forward neural network | 0.913 ± 0.005 | 0.396 ± 0.015 |
| 40 | Feed-forward neural network | 0.915 ± 0.004 | 0.429 ± 0.019 |
| 44 | Autoencoder | 0.891 ± 0.005 | 0.356 ± 0.018 |
| 45 | End-to-end neural network | 0.913 ± 0.005 | 0.423 ± 0.021 |
‘Model’ column indicates the reference number of the model in the main text. The results in ‘ROC-AUC’ and ‘AUPR’ are in the form of mean ± SD from five repeated experiments. Highlighted rows are top-performing methods.