SOCR logoBPAD

Model Evaluation Dashboard

Move a single decision threshold and watch it reshape the ROC curve, the calibration plot, the probability distribution and the decision curve at once.

  • ROC
  • calibration
  • net benefit
  • threshold
  • external validation
AUC
0.000
Sensitivity
0.000
Specificity
0.987
Net benefit @ pt
-0.037

ROC curve

00.10.20.30.40.50.60.70.80.9100.20.40.60.811 - specificitysensitivity

Precision-recall curve

prevalence00.10.20.30.40.50.60.70.80.9100.20.40.60.81recallprecision

Calibration plot

pt00.10.20.30.40.50.60.70.80.9100.20.40.60.81mean predicted probabilityobserved proportion

Decision curve

treat none0.10.20.30.40.50.60.70.80.9-8-7-6-5-4-3-2-10threshold probability ptnet benefit
ModelTreat allTreat none
Reading the dashboard
Discrimination, calibration and utility are separate questions answered by separate plots. A model can have AUC below 0.5 on one cohort and still, at an extreme threshold, edge out treat-none — but that does not make it clinically useful. Compare the model curve against both defaults, not just against zero.