Skip to main content

Table 4 Predictive performance of clinical model, the optimal machine learning model, and DLRN.

From: CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study

Model

Training cohort

External test cohort

AUC (95% CI)

Accuracy

AUC (95% CI)

Accuracy

Clinical model

0.752(0.707–0.797)

0.723

0.745(0.678–0.813)

0.708

Optimal ML model

0.953(0.931–0.974)

0.902

0.943(0.916–0.970)

0.840

DLRN

0.961(0.944–0.979)

0.919

0.947(0.921–0.973)

0.854

  1. AUC, area under the curve; CI, confidence interval; ML, machine learning; DLRN, deep learning radiomics nomogram
Back to article page

Cancer Imaging

ISSN: 1470-7330

Contact us