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

Area of Science:

• Critical care medicine
• Medical informatics
• Artificial intelligence in healthcare

Background:

• Sepsis and acute kidney injury (AKI) are critical conditions with high mortality.
• Early detection is vital but challenging due to nonspecific symptoms.
• AI and ML-based Clinical Decision Support Systems (CDSS) offer potential for enhanced early recognition.

Purpose of the Study:

• To evaluate the effectiveness of an AI-based CDSS for real-time sepsis and AKI risk prediction in routine clinical practice.
• To assess the impact of CDSS integration on diagnostic accuracy and patient safety.
• To determine the contribution of CDSS to improved early risk recognition in a hospital setting.

Main Methods:

• Retrospective analysis of data from before and after AI CDSS implementation at University Hospital Augsburg.
• Evaluation of diagnostic accuracy as a primary endpoint.
• Assessment of real-world clinical utility and patient safety impact.

Main Results:

• The study is ongoing; results are pending.
• Data analysis will focus on diagnostic accuracy and clinical decision support effectiveness.
• Findings will elucidate the system's performance in a real-world hospital environment.

Conclusions:

• The integration of AI CDSS at UKA aims to improve early detection of sepsis and AKI.
• Evaluating the system's real-world effectiveness is crucial for enhancing patient safety.
• Results will inform the broader adoption of AI in critical care settings.