Bayesian Health and Johns Hopkins University announce results that associate lives saved with a clinically deployed artificial intelligence platform
Bayesian Health announced release of three large, prospective multisite cohort studies offering a comprehensive and rigorous evaluation of the efficacy of their adaptive AI approach and showing patient lives saved.
The three studies, which appear in Nature Medicine and npj Digital Medicine, were conducted in collaboration with researchers from Johns Hopkins University.
Using data from 764,707 patient encounters (17,538 with sepsis) across five hospitals in both academic and community-based hospital settings with 2,000+ providers using the software, this research shows accurate early detection (1 in 3 cases were physician confirmed) at high sensitivity (82%) and significant lead time (5.7 hours earlier), high provider adoption (89%), and associated significant reductions in mortality, morbidity and length of stay.
Most significantly, the studies show timely use of Bayesian’s AI platform is associated with a relative reduction in mortality of 18.2%.
Sepsis is one of several conditions that Bayesian’s AI technology can help identify earlier in a hospital stay, preventing mortality and morbidity. When Bayesian’s adaptive AI suspects a patient is at risk of developing sepsis, it immediately alerts doctors and nurses through the patient’s electronic medical records (EMR) system, and then cues the provider to take specific actions, such as requesting blood cultures or prescribing antibiotics.
Bayesian’s adaptive AI is designed to integrate with a hospital’s EMR where it provides early detection flags and key insights that are actionable, shown on the patient list and/or linked with paging, phone, or other escalation pathways to alert the appropriate clinician. The flags that are generated drive prescriptive workflows for the healthcare provider and are paired with explanations and clinical history.
