(Children’s Hospital of Philadelphia) Automated programs can identify which sick infants in a neonatal intensive care unit (NICU) have sepsis hours before clinicians recognize the life-threatening condition. A research team of data scientists and physicians tested machine-learning models in a NICU population, drawing on routine collected electronic health information.

Original source: https://www.eurekalert.org/pub_releases/2019-02/chop-ruh022819.php