FRIDAY, May 15, 2026 (HealthDay News) — The U.S. Food and Drug Administration (FDA) has approved an AI-powered early warning system to detect sepsis, one of the deadliest infections for hospital patients.
The tool, developed at Johns Hopkins University (JHU), detects sepsis hours faster than doctors. It has already reduced deaths by nearly 20% in dozens of hospitals across the United States, JHU reports.
“Pre-suspicion screening is what creates lead time, and lead time is what changes outcomes in sepsis,” said Suchi Saria, director of JHU’s AI & Healthcare Lab. “Once a clinician already suspects sepsis, the clock has been running — often for hours or even days.”
After losing her nephew to sepsis in 2017, Saria and her lab created the Targeted Real-Time Early Warning System for real-world use.
“No other cleared test or device monitors for sepsis prior to clinician suspicion,” she said in a news release.
With the help of advanced clinical AI, the tool integrates patients’ electronic health records. The federally funded tool has helped doctors detect sepsis cases two to 48 hours earlier than traditional methods.
Sepsis is an infection where time is of the essence when it comes to treatment. Every hour that detection is delayed significantly reduces a patient’s survival odds. The deadly immune response claims more than 350,000 lives a year, according to the U.S. Centers for Disease Control and Prevention (CDC).
Up until now, providers have had to depend solely on symptoms like fever and confusion, which can easily be attributed to other medical conditions.
“It gives physicians an additional set of eyes and ears and could genuinely help save lives,” said researcher Dr. Albert Wu, a patient safety expert who was a co-investigator on the project. “This is a significant milestone for Johns Hopkins and Dr. Saria’s team.”
Under an FDA program that fast-tracks emerging technologies that improve care for life-threatening conditions, the technology was first deployed in 2023 at several health systems, including the Cleveland Clinic and University of Rochester School of Medicine, where it significantly reduced in-hospital death rates and lengths of stays for patients with sepsis.
“Few clinical AI systems can reason across the full breadth of messy, real-world hospital data and deliver guidance clinicians can reliably act on,” Saria said.
The tool’s clearance from the FDA also paves the way for hospitals using the system to receive Medicare and Medicaid reimbursement under a program that compensates hospitals for use of new technologies, according to the release.
“FDA approval is a regulatory first that shifts what the standard of care can be for a condition associated with roughly 1 in 3 in-hospital deaths,” Saria said. “This represents decades of clinical AI research at Johns Hopkins translated into practice — not just models built in the lab, but technology delivered where it matters: at the bedside.”
More information
There’s more about sepsis symptoms and causes at the Mayo Clinic.
SOURCE: Johns Hopkins Institute for Clinical and Translational Research, news release, May 12, 2026
