Skip to main content

Table 4 The performances of the models in the training and validation cohort

From: Prediction of prognosis of immune checkpoint inhibitors combined with anti-angiogenic agents for unresectable hepatocellular carcinoma by machine learning-based radiomics

Cohort

Rad-Score C-Index (95% CI)

Clinical Nomogram C-Index (95% CI)

Combined Nomogram C-Index (95% CI)

% Improvement Over Clinical Nomogram

Training cohort

0.837 (0.796, 0.878)

0.752 (0.692, 0.789)

0.846 (0.804, 0.879)

12.8%

Validation cohort

0.830 (0.744, 0.912)

0.709 (0.586, 0.772)

0.845 (0.767, 0.893)

19.1%