An algorithm from Dascena, Oakland, Calif, demonstrated a nearly 40% reduction in mortality due to severe sepsis, according to a recent study involving 75,147 patient encounters.1
“Sepsis is notoriously difficult to diagnose and treat, resulting in significant mortality and a high cost of treatment,” says Ritankar Das, chief executive officer of Dascena. “Our algorithm helps clinicians identify sepsis at an earlier stage, thereby allowing for earlier intervention to improve patient outcomes and, in turn, reducing the costs associated with treatment.”
The study prospectively evaluated multiyear, multicenter, real-world clinical data from 75,147 patient encounters that were monitored by the InSight machine-learning algorithm for sepsis prediction at facilities ranging from community hospitals to large academic centers. Hospitalized patients, including those in intensive care units, and emergency department visits were included.
Data were evaluated to determine the algorithm’s effect on outcomes, including in-hospital mortality, hospital length of stay, and 30-day readmission. During operation of the InSight algorithm, patient data were captured from the hospitals’ electronic health records in real-time, and hospital staff were informed when a patient was determined to be at high risk for sepsis.
Of the 75,147 patient encounters monitored by the InSight algorithm, 17,758 patient hospital stays met two or more criteria for systemic inflammatory response syndrome criteria and were therefore included in the analysis. The InSight algorithm implementation resulted in a 39.50% reduction in in-hospital mortality (p p p Dascena.
Reference
1. Burdick H, Pino E, Gabel-Comeau D, et al. Effect of a sepsis prediction algorithm on patient mortality, length of stay, and readmission: a prospective multicenter clinical outcomes evaluation of real-world patient data from US hospitals. BMJ Health Care Inform. 2020;27(1); doi: 10.1136/bmjhci-2019-100109.
