Skip to main content

AI Model for Early Prediction of Sepsis Improves Outcomes

Medically reviewed by Judith Stewart, BPharm. Last updated on Jan 31, 2024.

By Lori Solomon HealthDay Reporter

WEDNESDAY, Jan. 31, 2024 -- Deployment of COMPOSER for early prediction of sepsis is associated with significant improvements in outcomes, including mortality, according to a study published online Jan. 23 in npj Digital Medicine.

Aaron Boussina, from University of California in San Diego (UCSD), 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 septic patients from Jan. 1, 2021, through April 30, 2023.

The researchers found that the deployment of COMPOSER was significantly associated with a 1.9 percent absolute reduction (17 percent relative decrease) in in-hospital sepsis mortality. Additionally, there was a 5.0 percent absolute increase (10 percent relative increase) in sepsis bundle compliance and a 4 percent reduction in 72-hour sequential organ failure assessment score change after sepsis onset in a causal inference analysis.

"Our COMPOSER model uses real-time data in order to predict sepsis before obvious clinical manifestations," coauthor Gabriel Wardi, M.D., also from UCSD, said in a statement. "It works silently and safely behind the scenes, continuously surveilling every patient for signs of possible sepsis."

Several authors are co-founders of Healcisio Inc., a UCSD start-up focused on commercialization of advanced analytical decision support tools.

Abstract/Full Text

Disclaimer: Statistical data in medical articles provide general trends and do not pertain to individuals. Individual factors can vary greatly. Always seek personalized medical advice for individual healthcare decisions.

© 2024 HealthDay. All rights reserved.

Read this next

Novel Criteria Validated for Pediatric Sepsis, Septic Shock

MONDAY, Jan. 29, 2024 -- The Phoenix Criteria are valid for identifying sepsis and septic shock in children, according to two studies published online Jan. 21 in the Journal of...

Limited English Proficiency Not Linked to Sepsis Mortality Overall

FRIDAY, Jan. 5, 2024 -- Limited English proficiency (LEP) is not associated with overall sepsis mortality, but in a subgroup analysis, it was associated with mortality among those...

Placental Swabs Yield Highest Number of Potential Pathogens

WEDNESDAY, Jan. 3, 2024 -- Among microbial specimen types examined in a maternity hospital, placental swabs yield the highest number of potential pathogens, according to a study...

More news resources

Subscribe to our newsletter

Whatever your topic of interest, subscribe to our newsletters to get the best of Drugs.com in your inbox.