MOFNet: Network-Based Early Warning System for Multi-Organ Failure in Intensive Care Units
Abstract
MOFNet is an open-source physiological network analysis framework that predicts multi-organ failure (MOF) in ICU patients using graph theory and transfer entropy. Key Features: • Provides 11.3-hour median early warning before MOF onset • Achieves 84.6% sensitivity and 81.3% specificity for 12-hour prediction • Superior accuracy (AUC 0.893) compared to SOFA score (AUC 0.794) • Real-time monitoring with
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 6 January 2026
- Language
- EN