HMN 2025: How AI models predict sepsis in children to allow preemptive care

Sepsis, or infection causing life-threatening organ dysfunction, is a leading cause of death in children worldwide. In efforts to prevent this rare but critical condition, researchers developed and validated AI models that accurately identify children at high risk for sepsis within 48 hours, so that early preemptive care can be provided.

These predictive models used routine electronic health record (EHR) data from the first four hours the child spent in the Emergency Department (ED), before organ dysfunction was present.

The multi-center study, led by Elizabeth Alpern, MD, MSCE, from Ann & Robert H. Lurie Children’s Hospital of Chicago, is the first to use AI models to predict sepsis in children based on the new Phoenix Sepsis Criteria. Findings were published in JAMA Pediatrics.

“The predictive models we developed are a huge step toward precision medicine for sepsis in children,” said Dr. Alpern, lead author and Division Head of Emergency Medicine at Lurie Children’s, as well as Professor of Pediatrics at Northwestern University Feinberg School of Medicine.

“These models showed robust balance in identifying children in the ED who will later develop sepsis, without over-identifying those who are not at risk. This is very important because we want to avoid aggressive treatment for children who don’t need it.”

The study included five health systems contributing to the Pediatric Emergency Care Applied Research Network (PECARN), which provided Dr. Alpern and colleagues access to a large dataset and diverse population.

Children with sepsis already at arrival or within the first hours of ED care were excluded, focusing the goal of the study on predicting sepsis, to allow for early initiation of therapies that have been proven as lifesaving.

“We evaluated our models to ensure that there were no biases,” said Dr. Alpern. “Future research will need to combine EHR-based AI models with clinician judgment to make even better predictions.”

The content is provided for information purposes only.