TABLE 3.
Diagnostic performance of the multimodality fusion model.
| Model | Dataset | AUC (95% CI) | ACC | SEN | SPE | NPV | PPV |
|---|---|---|---|---|---|---|---|
| Multimodality fusion model | Training set | 0.987 (0.975–1.000) | 0.932 | 0.910 | 0.974 | 0.844 | 0.986 |
| Test set | 0.889 (0.798–0.980) | 0.848 | 0.750 | 1.000 | 0.720 | 1.000 |
ACC, accuracy; AUC, area under the curve; CI, confidence interval; NPV, negative predictive value; PPV, positive predictive value; SEN, sensitivity; SPE, specificity.