FDA clears Johns Hopkins AI system that predicts sepsis early, boosting survival rates
The FDA approved Johns Hopkins University’s AI-powered TREWS system, developed by Suchi Saria, to detect sepsis up to 48 hours earlier than traditional methods, potentially saving lives by enabling faster treatment. The tool, already tested at hospitals like the Cleveland Clinic and University of Rochester, may qualify for Medicare and Medicaid reimbursement under advanced medical technology programs.
The U.S. Food and Drug Administration (FDA) has cleared the Targeted Real-Time Early Warning System (TREWS), an AI-driven tool created by Johns Hopkins University researcher Suchi Saria and her team. The system predicts sepsis—a life-threatening immune response to infection that kills over 350,000 Americans annually—up to 48 hours earlier than standard clinical methods, allowing hospitals to intervene sooner and improve survival rates. TREWS analyzes electronic health records in real time, identifying warning signs before they become critical. Saria developed the technology after her nephew died from sepsis in 2017. Early detection is crucial, as delayed treatment reduces survival chances by the hour. The AI system has already been deployed at major hospitals, including the Cleveland Clinic and the University of Rochester School of Medicine. Studies show it has reduced in-hospital deaths and shortened patient stays. The FDA approval marks a major milestone for AI in healthcare, with potential Medicare and Medicaid reimbursement for hospitals adopting the technology. Sepsis remains a leading cause of death in the U.S., with the CDC reporting over 350,000 fatalities annually. TREWS’ ability to detect the condition earlier could significantly lower mortality rates by enabling faster medical responses. The system’s success highlights the growing role of AI in improving patient outcomes. Hospitals using TREWS may now qualify for financial support under programs promoting advanced medical technologies, further incentivizing its adoption.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.