Assessing AI-Based Decision Support in Early Sepsis and AKI Recognition

Sepsis and acute kidney injury (AKI) remain among the most critical conditions in acute care, associated with high morbidity and mortality. Early risk recognition is essential but often hampered by nonspecific symptoms. Recent studies have demonstrated that AI- and ML-based Clinical Decision Support Systems (CDSS) can enhance the early detection of sepsis and AKI and support clinical decision-making [1-3]. In May 2025, the University Hospital Augsburg (UKA) integrated an externally developed AI-based CDSS to provide real-time risk predictions for sepsis and AKI. This study evaluates the effectiveness of the system in routine clinical practice using retrospective data from periods before and after its implementation. Primary endpoints include diagnostic accuracy. The results will indicate whether the CDSS contributes to improved early risk recognition and enhanced patient safety in a real-world hospital environment.