AI Early Warning System: Earlier Detection Saves Lives
Sepsis is one of the deadliest infections for hospital patients, claiming over 250,000 lives annually in the United States. Its symptoms, such as fever and confusion, are common in other conditions, making it easily missed. Every hour of delay in detection significantly decreases a patient's chance of survival.
To address this, researchers at Johns Hopkins University developed the Targeted Real-Time Early Warning System (TREWS). By integrating electronic health records with advanced clinical AI, the system can detect sepsis 2 to 48 hours before clinician suspicion, providing precious lead time.
Proven Results: 18% Reduction in Mortality
TREWS has been deployed in dozens of hospitals across the United States, reducing sepsis mortality rates by 18%. In 2023, the technology received the FDA's Breakthrough Device designation and was implemented at several health systems, including the Cleveland Clinic, MemorialCare in California, and the University of Rochester School of Medicine, where it significantly reduced in-hospital mortality, morbidity, and length of stay for sepsis patients.
Expert Voices
Lead researcher Suchi Saria, a Johns Hopkins professor and director of the AI & Healthcare Lab, stated: "Few clinical AI systems can reason across the full breadth of messy, real-world hospital data and deliver guidance clinicians can reliably act on. FDA approval is a regulatory first that shifts what the standard of care can be for a condition associated with roughly one in three in-hospital deaths." She emphasized that this represents decades of clinical AI research translated into practice – not just models built in the lab, but technology delivered at the bedside.
Johns Hopkins patient safety expert Albert Wu commented: "It gives physicians an additional set of eyes and ears and could genuinely help save lives. This is a significant milestone for Johns Hopkins and Dr. Saria's team."
FDA clearance also allows hospitals using the system to receive Medicare and Medicaid reimbursement under the New Technology Add-on Payment (NTAP) program, further incentivizing its adoption.