Fig 1.
Patient demographics and injury characteristics.
Fig 2.
Illustration of the DT model for predicting mortality in patients with isolated moderate and severe TBI.
Boxes denote the percentage of patients analyzed with discriminating variables; survivors and non-survivors are indicated by green and red colors, respectively.
Fig 3.
Architecture of the three-layered feed-forward ANN.
Table 1.
Mortality prediction performance (i.e., accuracy, sensitivity, and specificity) for the LR, SVM, DT, NB, and ANN models on training and test sets.
Fig 4.
ROC curves for the LR, SVM, DT, NB, and ANN models in predicting the mortality of patients with isolated moderate and severe TBI.
Fig 5.
Calibration curves by the LR, SVM, DT, NB, and ANN models in predicting the mortality of patients with isolated moderate and severe TBI.