Skip to main content

Table 3 Predictive performance of the two models in the training and validation cohorts

From: Combination of computed tomography imaging-based radiomics and clinicopathological characteristics for predicting the clinical benefits of immune checkpoint inhibitors in lung cancer

  Radiomics model1 Radiomics nomogram model1
Training cohort Validation cohort Training cohort Validation cohort
AUC (95%CI) 0.848 (0.743–0.952) 0.795 (0.581–1.000) 0.902 (0.811–0.994) 0.877 (0.735–1.000)
Accuracy (%) 0.766 0.714 0.875 0.893
Sensitivity (%) 0.625 1.000 0.857 0.800
Specificity (%) 0.906 0.704 0.884 0.944
Positive predictive value (%) 0.870 0.111 0.783 0.889
Negative predictive value (%) 0.707 1.000 0.927 0.895