STAT+: Serving as a ‘clinical colleague,’ AI shows potential to reduce sepsis deaths in real-world studies

Three studies published Thursday found that an AI platform developed by Bayesian Health and Johns Hopkins University reduced deaths from sepsis by 18.2% in real-world use when physicians responded promptly to its alerts, a finding that suggests AI has potential to become an important tool in battling a leading cause of deaths in hospitals.

The company and Hopkins researchers tested the platform at five hospitals in the Northeast — both academic and community-based — with more than 4,000 clinicians. The software, which was integrated into the hospitals’ electronic health records, monitors patient data and alerts clinicians when it spots early signs of potential sepsis. It identified over 17,500 cases of sepsis from over 750,000 patient encounters among all adults who presented to the emergency department or were admitted to a medical or surgical unit over the course of one to two years.

Continue to STAT+ to read the full story…