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.
| Methods | Train | Test | ||||
|---|---|---|---|---|---|---|
| Accuracy | Sensitivity | Specificity | Accuracy | Sensitivity | Specificity | |
| LR | 93.66% | 53.89% | 98.08% | 93.54% | 59.38% | 93.54% |
| SVM | 92.96% | 64.12% | 96.10% | 92.50% | 65.63% | 95.22% |
| DT | 94.69% | 62.35% | 98.21% | 92.92% | 43.75% | 98.29% |
| NB | 89.56% | 73.53% | 91.30% | 86.15% | 59.38% | 89.08% |
| ANN | 93.94% | 80.59% | 95.40% | 92.00% | 84.38% | 92.83% |
LR, logistic regression; SVM, support vector machine; DT, decision trees; NB, Naive Bayes; and ANN, artificial neural networks.