Table 2 Predictive performance of the nine-feature, multi-factorial models.
From: Machine learning models identify predictive features of patient mortality across dementia types
Survival-time threshold | Internal test set | External test set | ||||
|---|---|---|---|---|---|---|
Accuracy (95% CI) | AUC-ROC (95% CI) | AUC-PR (95% CI) | Accuracy | AUC-ROC | AUC-PR | |
One-year | 0.780 (0.770–0.788) | 0.824 (0.820–0.850) | 0.259 (0.257–0.301) | 0.817 | 0.870 | 0.300 |
Three-year | 0.750 (0.743–0.758) | 0.825 (0.817–0.830) | 0.566 (0.545–0.588) | 0.752 | 0.837 | 0.539 |
Five-year | 0.744 (0.735–0.749) | 0.823 (0.813–0.826) | 0.722 (0.702–0.730) | 0.710 | 0.817 | 0.667 |
Ten-year | 0.748 (0.733–0.755) | 0.829 (0.814–0.832) | 0.905 (0.896–0.911) | 0.693 | 0.789 | 0.741 |
