Milea Timbergen

134 Table 3. Performance of the radiomics models for the DTF differential diagnosis based on: model 1: volume only; model 2: age and sex only; model 3: T1w imaging features, including volume; model 4: the combination of T1w imaging features and age and sex; model 5: the combination of T1w and T2w imaging features; and model 6: the combination of T1w and T1w post-contrast imaging features. Outcomes are presented with the 95% confidence interval. Model 1 Volume Model 2 Age + Sex Model 3 T1w Model 4 T1w + Age + Sex Model 5 T1w + T2w Model 6 T1w + T1w post-contrast AUC 0.69 [0.61, 0.76] 0.86 [0.79, 0.92] 0.79 [0.73, 0.85] 0.88 [0.82, 0.93] 0.84 [0.78, 0.89] 0.84 [0.78, 0.90] BCA 0.59 [0.53, 0.65] 0.78 [0.71, 0.86] 0.71 [0.65, 0.77] 0.79 [0.72, 0.86] 0.68 [0.62, 0.75] 0.75 [0.69, 0.81] Sensitivity 0.80 [0.70, 0.91] 0.78 [0.66, 0.90] 0.61 [0.49, 0.72] 0.70 [0.57, 0.83] 0.43 [0.31, 0.55] 0.62 [0.52, 0.73] Specificity 0.39 [0.28, 0.49] 0.79 [0.71, 0.87] 0.81 [0.73, 0.89] 0.88 [0.82, 0.94] 0.94 [0.88, 0.99] 0.88 [0.82, 0.95] NPV 0.50 [0.71, 0.89] 0.88 [0.81, 0.94] 0.80 [0.76, 0.75] 0.85 [0.80, 0.91] 0.76 [0.72, 0.80] 0.81 [0.76, 0.85] PPV 0.41 [0.36, 0.46] 0.72 [0.57, 0.76] 0.64 [0.53, 0.75] 0.76 [0.67, 0.86] 0.80 [0.66, 0.94] 0.76 [0.65, 0.88] T1w, T1-weighted; T2w, T2-weighted; AUC, area under the receiver operator characteristic curve; BCA, balanced classification accuracy; NPV, negative predictive value; PPV, positive predictive value 5