WITNESS DATA Factory provides synthetic, regulatory‑grade medical text datasets so clinical AI teams can develop and validate models without touching real patient data. Each corpus is generated by a m
Reported area under the receiver operating characteristic (AUROC) and 95% CIs for each deterioration index for identifying high-risk patients within the first five days of admission.
Supporting datasets (iid and ood) used in the evaluation experiments of the paper "Why did AI get this one wrong? - tree-based explanations of machine learning model predictions" by Parimbelli, Buonoc
