Sign in Subscribe
Pediatrics

AI-Powered Sepsis Prediction in Children Showcases Progress in Precision Medicine

Strategic Insights

— 2 min read

Researchers have successfully developed and validated artificial intelligence (AI) models that can accurately identify children at high risk for sepsis within 48 hours. This breakthrough has the potential to save lives by enabling early preemptive care. The study, led by Elizabeth Alpern, MD, MSCE, from Ann & Robert H. Lurie Children's Hospital of Chicago, utilized routine electronic health record (EHR) data from the first four hours a child spent in the Emergency Department (ED) to develop the predictive models. The models used the new Phoenix Sepsis Criteria, which is a key factor in this study.

Key Takeaways:

  • The AI models showed robust balance in identifying children in the ED who will later develop sepsis without overidentifying those who are not at risk.
  • The study focused on predicting sepsis to allow for early initiation of therapies proven to be lifesaving.
  • The research used a large dataset from the Pediatric Emergency Care Applied Research Network (PECARN), which consisted of five health systems.
  • The models excluded children with sepsis already at arrival or within the first hours of ED care to focus on predicting sepsis.
  • The study cited no biases in the evaluation of the models, and future research aims to combine EHR-based AI models with clinician judgment.
  • The project received support from the National Institute of Child Health and Human Development (NICHD) grant R01HD087363.
  • Dr. Alpern holds the George M. Eisenberg Professorship in Pediatrics at Northwestern University Feinberg School of Medicine.
  • Ann & Robert H. Lurie Children's Hospital of Chicago is a nonprofit organization committed to providing access to exceptional care for every child.

Statistics:

  • The study included data from five health systems contributing to the Pediatric Emergency Care Applied Research Network (PECARN).
  • The models were developed and validated using EHR data from the first four hours a child spent in the ED.
  • The predictive models used the new Phoenix Sepsis Criteria to identify children at high risk for sepsis.
  • The study showed robust balance in identifying children at risk without overidentifying those not at risk.
  • The research received support from the National Institute of Child Health and Human Development (NICHD) grant R01HD087363.

Sources:

  • NewsRx, "Nov. 1, 2025": No source date provided in the original text for the publication date.
  • JAMA Pediatrics: "No source date provided in the original text for the publication date."
  • Ann & Robert H. Lurie Children's Hospital of Chicago: "No source date provided in the original text for the publication date."
  • National Institute of Child Health and Human Development (NICHD): "No source date provided in the original text for the publication date."

Read more