TABLE 6.
Comparison of diagnosis efficiency between clinical model and radiomics model.
AUC | Sensitivity | Specificity | PPV | NPV | Accuracy | |
---|---|---|---|---|---|---|
Training set | ||||||
Clinical | 0.83 | 0.76 | 0.83 | 0.87 | 0.70 | 0.79 |
Radiomics | 0.82 | 0.77 | 0.75 | 0.82 | 0.69 | 0.76 |
Combined | 0.86 | 0.81 | 0.77 | 0.84 | 0.73 | 0.79 |
Test set | ||||||
Clinical | 0.78 | 0.72 | 0.79 | 0.80 | 0.71 | 0.75 |
Radiomics | 0.79 | 0.64 | 0.88 | 0.86 | 0.68 | 0.75 |
Combined | 0.80 | 0.68 | 0.84 | 0.83 | 0.69 | 0.75 |
AUC, area under the curve; PPV, positive predictive value; NPV, negative predictive value.