Table 4.
Performance measurements generated by DL models and radiomics models trained on four combined sequences (T1WI/T2WI/FLAIR/DWI) and clinical model trained on clinical variables in the external test dataset.
| Models | AUC (95% CI) | P-value | Accuracy | Specificity | Sensitivity |
|---|---|---|---|---|---|
| Clinical Variables | 0.837 (0.639-0.955) | 0.017* | 0.840 | 0.818 | 1.000 |
| Radiomics_Combined | 0.807 (0.549-0.906) | 0.024* | 0.760 | 0.889 | 0.429 |
| DL_Combined | 0.754 (0.639-0.955) | 0.007* | 0.840 | 0.900 | 0.600 |
| Fusion | 0.927 (0.688-0.975) | Na | 0.880 | 0.947 | 0.667 |
*P < 0.05. The paired Student t-test was used to compare the predictive performance of the prognosis in patients with anti-NMDAR encephalitis between the fusion model and the other three models (The fusion model is the reference).
AUC, area under the receiver operating characteristic curve; CI, confidence interval; DL, deep learning; anti-NMDAR, anti-N-methyl-D-aspartate receptor; Na, Not available.