Skip to main content
. 2026 May 20;10:70. doi: 10.1186/s41747-026-00736-9

Table 3.

Performance obtained on the test set for the best model selected for each of the three conducted analyses (CE-T1-weighted, T2-weighted, CE-T1-weighted + T2-weighted)

Test set performance
CE-T1-weighted T2-weighted CE-T1-weighted + T2-weighted
ML model Logistic regression AdaBoost XGBoost
AUC 0.80 0.78 0.85
Accuracy 0.74 0.66 0.76
Sensitivity 0.81 0.69 0.81
Specificity 0.67 0.62 0.71