Table 2.
Performance metrics of SIS prediction models.
| Model | Accuracy (%) | Precision | Recall | F1 scores | AUC-ROC |
|---|---|---|---|---|---|
| SIS main scale | |||||
| RF | 85 | 0.88 | 0.85 | 0.85 | 0.86 |
| KNN | 75 | 0.76 | 0.75 | 0.75 | 0.8 |
| ANN | 75 | 0.77 | 0.75 | 0.74 | 0.87 |
| SVM | 72 | 0.73 | 0.73 | 0.73 | 0.71 |
| LG | 72.82 | 0.73 | 0.73 | 0.72 | 0.77 |
| SIS global rating scale | |||||
| RF | 80 | 0.78 | 0.8 | 0.78 | 0.75 |
| KNN | 82.5 | 0.82 | 0.83 | 0.81 | 0.76 |
| ANN | 77.5 | 0.77 | 0.78 | 0.77 | 0.75 |
| SVM | 77.5 | 0.77 | 0.78 | 0.77 | 0.68 |
| LG | 77.5 | 0.78 | 0.78 | 0.78 | 0.75 |
SIS Stroke Impact Scale, RF random forest, KNN k-nearest neighbors, ANN artificial neural network, SVM support vector machine, LG logistic regression, AUC-ROC area under the receiver operating characteristic curve.