Medical News Observer

Key Points:

• COMPOSER AI model analyzes 150+ patient variables in real-time, predicting high-risk sepsis cases early in emergency departments.
• A study of 6,217 patients shows a 1.9% absolute reduction in sepsis mortality and a 5.0% increase in compliance with sepsis treatment protocols.
• Results indicate AI’s significant role in enhancing critical care, marked by a 4% decrease in SOFA score changes post-sepsis onset.

Overview

Sepsis, a life-threatening blood infection, is associated with significant morbidity and mortality. In a study aimed at combating sepsis, researchers assessed the impact of a deep-learning model called COMPOSER on patient outcomes. UC San Diego Health System conducted this study. This model was used in emergency departments to predict sepsis before clinical symptoms became apparent.

COMPOSER AI Model

The COMPOSER AI model operates in real-time, analyzing over 150 patient variables, such as lab results, vital signs, and medical history, to identify high-risk sepsis patients. It then alerts the nursing staff for further action.

Results

The study revealed notable findings by analyzing data from 6,217 adult septic patients. Findings include a 1.9% absolute reduction in in-hospital sepsis mortality, translating to a 17% relative decrease. Additionally, there was a 5.0% absolute increase in sepsis bundle compliance and a 4% reduction in the 72-hour Sequential Organ Failure Assessment (SOFA) score change after sepsis onset.

Implications

These results highlight the potential of AI models in early sepsis prediction and improving patient outcomes in critical care settings.

References

• Boussina, Aaron, Supreeth P. Shashikumar, Atul Malhotra, Robert L. Owens, Robert El-Kareh, Christopher A. Longhurst, Kimberly Quintero, et al. 2024. “Impact of a Deep Learning Sepsis Prediction Model on Quality of Care and Survival.” Npj Digital Medicine 7 (1): 1–9. https://doi.org/10.1038/s41746-023-00986-6.
• “Study: AI Surveillance Tool Successfully Helps to Predict Sepsis, Saves Lives.” n.d. Accessed January 25, 2024. https://today.ucsd.edu/story/study-ai-surveillance-tool-successfully-helps-to-predict-sepsis-saves-lives.