Table 2 Mean (standard deviation) of performance metrics using 18 features selected in [5] via SHAP
From: An interpretable neural network for outcome prediction in traumatic brain injury
Method | Accuracy | Recall | Precision | F1 | AUC |
|---|---|---|---|---|---|
TFNN | 0.719 (0.040) | 0.657 (0.094) | 0.671 (0.054) | 0.614 (0.057) | 0.794 (0.039) |
XGB | 0.693 (0.028) | 0.591 (0.075) | 0.646 (0.033) | 0.569 (0.048) | 0.743 (0.039) |
RF | 0.744 (0.035) | 0.579 (0.055) | 0.754 (0.057) | 0.608 (0.049) | 0.802 (0.036) |
SVM | 0.728 (0.019) | 0.551 (0.106) | 0.745 (0.056) | 0.579 (0.059) | 0.795 (0.048) |