AI Models Developed by Northwestern, Lurie Children's Predict Pediatric Sepsis Within 48 Hours
Northwestern University News
|
Contributed by: Kate Gamble
Summary
Researchers at Northwestern University and Ann & Robert H. Lurie Children’s Hospital have developed AI models that predict the risk of sepsis in children within 48 hours of their arrival at the emergency department, based on early electronic health record data. This significant advancement, published in JAMA Pediatrics, allows for timely intervention and potentially reduces mortality rates by identifying high-risk patients before organ dysfunction occurs. Unlike previous models, these AI tools leverage the Phoenix Sepsis Criteria and successfully minimize the likelihood of overdiagnosis, ensuring that healthcare providers can focus appropriate treatment on those truly at risk. This development underscores the growing role of AI in precision medicine and the potential for improved outcomes in pediatric emergency care.