Photo Credit: Dr Microbe
Benefits include significant reduction in mortality and significant increase in sepsis bundle compliance, researchers noted.
Deploying deep learning models for early prediction of sepsis is associated with significant improvements in outcomes, including mortality, according to a study published online in NPJ Digital Medicine. Aaron Boussina and colleagues assessed the impact of a deep learning model (COMPOSER) for the early prediction of sepsis on patient outcomes. The analysis included a before-and-after quasi-experimental study design at two emergency departments that saw 6,217 adult patients with sepsis from January 1, 2021, through April 30, 2023. The researchers found that deploying COMPOSER was significantly associated with a 1.9% absolute reduction (17% relative decrease) among in-hospital sepsis mortality. Additionally, there was a 5.0% absolute increase (10% relative increase) in sepsis bundle compliance and a 4% reduction in 72-hour sequential organ failure assessment score change after sepsis onset in a causal inference analysis.
