Bayesian Health co-founder and CEO Suchi Saria (left) began working on sepsis technology after her nephew died of sepsis in 2017. [Photo courtesy of Johns Hopkins University]
The software as a medical device (SaMD) is the first continuous artificial intelligence/machine learning-based sepsis monitoring system to earn FDA clearance. The system detects sepsis hours faster than doctors and has reduced deaths by nearly 20%, according to a research study published in Nature Medicine.
“Pre-suspicion screening is what creates lead time, and lead time is what changes outcomes in sepsis. Once a clinician already suspects sepsis, the clock has been running — often for hours or even days,” lead researcher and Bayesian Health co-founder and CEO Suchi Saria said in a news release. “No other cleared test or device monitors for sepsis prior to clinician suspicion.”
She and her team designed the Bayesian Health Sepsis Flagging Device to assist clinicians in early sepsis detection and/or risk prediction of a patient developing sepsis within 24-hours by analyzing patient data from electronic health records, according to their FDA submission.
The 2026 MDO Medtech Startups Special Report: Technical tips and actionable advice for device startups
The system uses a machine learning algorithm to analyze patient data from health records, such as comorbidities, chief complaint, lab measurements, vital signs, procedures, medications and consult orders. If the patient is at risk of developing sepsis within 24 hours, it displays a “Sepsis Risk High” flag in the patient’s electronic health record.
The software provides a summary of clinical factors potentially contributing to the patient being flagged for sepsis risk for a healthcare provider to incorporate into their clinical decision-making.
Other FDA-cleared sepsis technologies require a clinician to suspect sepsis first before using biomarker-based diagnostic blood tests or calculating sepsis risk using software and the blood test results.
“Catching sepsis before a clinician suspects it is a needle-in-a-haystack problem. Sepsis prevalence in acute care is just 2 to 4 percent, while traditional diagnostic tests run at 20 to 40 percent on patients already suspected of having it. Missing a single case is catastrophic, and that demands a level of precision most AI can’t meet, even tools that look promising in preliminary studies,” Bayesian Health Head of Clinical Enterprise Dr. Neri Cohen said in a news release.
“Few companies have done the rigorous data science and independent validation required to meet that bar,” he continued. “Fewer still have done the equally rigorous work that has to follow: building it into clinical workflows, earning clinician adoption at the bedside, and measuring outcomes long enough to know it’s still working.”
MDO Contribution: Designing SaMD for safety and rethinking risk management through system architecture
Saria began working on sepsis technology after her nephew died of sepsis in 2017. Soon, Saria and her team at Johns Hopkins created a version of the sepsis monitoring tool (then called the Targeted Real-Time Early Warning system), which integrated electronic health records with advanced clinical AI to help clinicians detect sepsis cases nearly two to 48 hours earlier than traditional methods, the university said.
The system earned FDA Breakthrough Device designation in 2013 and was integrated in select U.S. hospitals, “where it significantly reduced in-hospital mortality, morbidity, and length of stays for patients with sepsis,” Johns Hopkins said.
With FDA clearance, Bayesian Health can begin commercialization, and hospitals using the system could receive Medicare and Medicaid reimbursement under the New Technology Add-on Payment program starting in October 2026.
“FDA [clearance] 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,” 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.”
