Skip to main content

Table 4 Predictive performance of the PDPM models in predicting the disease progression in the cohorts

From: Baseline MRI-based radiomics model assisted predicting disease progression in nasopharyngeal carcinoma patients with complete response after treatment

Model Training cohort (n = 119) Validation cohort (n = 52)
AUC 95% CI SEN SPE AUC 95% CI SEN SPE
Low High Low High
L1 0.85 0.78 0.92 0.80 0.77 0.66 0.51 0.81 0.88 0.41
L2 0.69 0.59 0.78 0.75 0.54 0.66 0.50 0.81 0.44 0.89
L3 0.66 0.57 0.76 0.96 0.32 0.69 0.54 0.84 0.44 0.93
L4 0.75 0.66 0.83 0.67 0.75 0.77 0.64 0.90 0.92 0.52
S1 0.97 0.94 1.00 0.98 0.88 0.72 0.58 0.86 0.52 0.89
S2 0.84 0.76 0.91 0.84 0.72 0.61 0.45 0.77 0.80 0.44
S3 0.85 0.78 0.92 0.71 0.75 0.61 0.45 0.77 0.44 0.89
S4 0.95 0.91 0.98 0.96 0.78 0.67 0.52 0.82 0.64 0.63
  1. AUC, area under the curve; CI, confidence interval; SEN, sensitivity; SPE, specificity