Rapid Bedside Test Predicts Sepsis with Over 90% Accuracy

Sepsis is a severe response to an infection that causes the immune system to attack the body's own organs and tissues, potentially leading to organ failure and death if not addressed promptly. It is responsible for approximately 20% of all global deaths. Predicting sepsis remains challenging, as its early symptoms are vague and current diagnostic tests can take up to 18 hours, often requiring specialized labs. This delay in treatment increases the risk of death by nearly 8% per hour. Now, researchers have developed a new blood test and portable device that can detect the onset of sepsis more quickly and accurately than existing methods.

The test, developed by scientists at the University of British Columbia (UBC, Vancouver, BC, Canada) and Sepset Biosciences (Victoria, BC, Canada), has demonstrated over 90% accuracy in identifying individuals at high risk of developing sepsis, marking a significant advancement in how doctors will diagnose and treat this condition. The study, published in Nature Communications, involved analyzing blood samples from more than 3,000 hospital patients with suspected sepsis. Using machine learning, the researchers identified a six-gene expression signature, dubbed "Sepset," which successfully predicted sepsis nine times out of ten, even before a formal diagnosis was made. When tested with an additional 248 blood samples using RT-PCR (Reverse Transcription Polymerase Chain Reaction), a common hospital laboratory technique, the test showed 94% accuracy in detecting early-stage sepsis in patients whose condition was likely to worsen.

Image: PowerBlade is a portable device that uses a drop of blood and an automated sequence of steps to efficiently detect sepsis (Photo courtesy of NRC)

This success highlights the powerful role of AI in handling complex data, pinpointing the critical genes necessary for predicting sepsis, and developing a highly accurate algorithm for assessing sepsis risk. To make this test more accessible in clinical settings, the National Research Council of Canada (NRC) has developed a portable device, PowerBlade, which uses a drop of blood and an automated sequence of steps to detect sepsis efficiently. In trials with 30 patients, PowerBlade demonstrated 92% accuracy in identifying patients at high risk of sepsis and 89% accuracy in ruling out those not at risk. The device provided results in under three hours, making it suitable for use in various environments, including emergency rooms and remote healthcare settings.

“Sepsis accounts for roughly 20% of all global deaths,” said lead author Dr. Claudia dos Santos, a critical care physician and scientist at St. Michael’s Hospital. “Our test could be a powerful game changer, allowing physicians to quickly identify and treat patients before they begin to rapidly deteriorate.”

Related Links:
UBC
Sepset Biosciences