Table 5 Prediction accuracy performance at different EDSS milestones
From: Predicting multiple sclerosis severity with multimodal deep neural networks
| Â | AUROC | AUPRC | Sensitivity | Specificity | Accuracy |
|---|---|---|---|---|---|
MRI & Notes & EHR (EDSS > 4) | 0.8380 ± 0.0438 | 0.7963 ± 0.0520 | 0.7489 ± 0.0502 | 0.7936 ± 0.0488 | 0.7960 ± 0.0312 |
MRI & Notes & EHR (EDSS > 6) | 0.8032 ± 0.0556 | 0.7012 ± 0.0501 | 0.8043 ± 0.0454 | 0.7121 ± 0.0755 | 0.6720 ± 0.0555 |
MRI & Notes & EHR (EDSS > 7) | 0.8543 ± 0.0572 | 0.7678 ± 0.0588 | 0.6777 ± 0.0453 | 0.7534 ± 0.225 | 0.7248 ± 0.0377 |