External Validation of the FedHist Dynamic Early Warning Model for Mortality Risk in Critically Ill Patients: A Prospective Multicenter Study

The purpose of this study is to assess how accurately FedHist, an artificial intelligence model, predicts the risk of death in critically ill patients. Patients in intensive care units (ICUs) can become worse quickly. Updating risk estimates as new clinical information becomes available may help identify patients at higher risk. FedHist uses routinely collected clinical information to estimate a patient's risk of dying in the ICU within the next 24 hours. These estimates are updated every 6 hours. This study will evaluate FedHist prospectively across several hospitals. The model will be integrated into hospital clinical information systems, and its predictions will be compared with observed patient outcomes. The study aims to determine whether FedHist provides accurate predictions across hospitals with different patient populations and clinical practices.

Inclusion Criteria: * Admission to a participating ICU Exclusion Criteria: * Age younger than 18 years. * Expected ICU length of stay shorter than 24 hours. * Refusal to provide written informed consent.