UC MRE Activity Risk Stratifier
Abstract
A Streamlit research prototype that converts segment-level UC MR enterography features and a patient-level fecal calprotectin into a marginal new-patient probability of clinically active disease (Mayo endoscopic subscore >= 2) using a Bayesian ordinal logistic regression model. Reports a posterior median with a 95% credible interval and a three-tier triage output. Model parameters are loaded from a versioned artifact produced by the analysis notebook.
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 15 June 2026