BeaconPredict receives FDA breakthrough status for stroke swelling risk tool

Beacon-Neuro.AI Inc., a Washington University in St. Louis startup, has received FDA Breakthrough Device designation for BeaconPredict, an AI-enabled software tool that predicts malignant cerebral edema after acute stroke. Developed from technology created by WashU Medicine researchers, the platform is described as the first device designed to predict the dangerous brain swelling complication.

Malignant cerebral edema affects up to 70,000 stroke patients in the U.S. each year and has a mortality rate of 80% if untreated. The condition is the leading cause of death in the first week after stroke, while surgery and other interventions are most effective within 48 hours of the stroke. BeaconPredict analyzes brain scans taken in the first 24 hours after hospital admission and combines them with blood pressure readings, age, neurological exam results and other clinical data to generate a risk assessment.

Rajat Dhar, MD, a WashU Medicine professor of neurology and co-founder of Beacon-Neuro.AI, said standard approaches are about 70% accurate in identifying patients needing intervention. In a recent study using data from 598 stroke patients at three medical centers, BeaconPredict was 99% accurate in identifying patients who needed surgery to relieve brain pressure 24 hours after stroke and achieved a precision rate of 87%, compared with 50% for current methods on the same measure.