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.
The researchers analyzed 6,877 patients that the technology flagged for sepsis prior to treatment with antibiotics. When a provider responded to the alert within three hours — effectively adopting and confirming the AI’s intuition — there were reductions in mortality, organ failure, and length of stay when compared to patients whose alerts were not addressed within that window.
This article is exclusive to STAT+ subscribers
Unlock this article — and get additional analysis of the technologies disrupting health care — by subscribing to STAT+.
Already have an account? Log in
Already have an account? Log in
To submit a correction request, please visit our Contact Us page.
STAT encourages you to share your voice. We welcome your commentary, criticism, and expertise on our subscriber-only platform, STAT+ Connect