Clinical Risk Model Calibration Simulator

AI risk scores and clinical-decision-support alerts are only as trustworthy as their calibration — the match between the probability a model reports and how often the event actually happens. This simulator generates a synthetic patient cohort with a hidden true risk for every patient, runs it through an adjustable model with a confidence-gain and systematic-offset dial, and renders a live 3D reliability diagram: bars show the model's predicted-vs-observed rate in each probability bin against a perfect-calibration diagonal, while a scatter of individual patients shows the outcomes those predictions were built from. Brier score, Expected Calibration Error and AUC update in real time as you push the model toward overconfidence, underconfidence, or a systematic bias.