Johns Hopkins AI tool TREWS gets FDA clearance for early sepsis detection

The US Food and Drug Administration (FDA) has approved a new artificial intelligence-powered early warning system developed by Johns Hopkins University that can detect sepsis significantly earlier than conventional clinical methods, potentially improving survival outcomes for patients.

The system, called the Targeted Real-Time Early Warning System (TREWS), analyzes patients’ electronic health records in real time and can identify warning signs of sepsis up to 48 hours before standard diagnosis techniques, according to researchers.

Sepsis is a life-threatening condition triggered by the body’s extreme response to infection and is responsible for more than 350,000 deaths annually in the United States, according to the Centers for Disease Control and Prevention (CDC).

Medical experts say that every hour of delay in treatment reduces survival chances, making early detection critical.

TREWS was developed by researcher Suchi Saria and her team at Johns Hopkins, who were motivated in part by a personal loss after Saria’s nephew died from sepsis in 2017.

The AI system has already been deployed in several healthcare institutions, including the Cleveland Clinic and the University of Rochester School of Medicine, where early results indicate reductions in in-hospital deaths and shorter patient stays.

Scientists involved in the project say FDA clearance represents a major milestone for the use of clinical AI in healthcare.

Hospitals using the system may also become eligible for Medicare and Medicaid reimbursement under programs that support advanced medical technologies.