Healthcare (Commonwealth Union) – Sepsis is a life-threatening medical emergency that occurs when the body’s response to an infection spirals out of control, leading to widespread inflammation, organ failure, and even death. Sepsis requires immediate medical attention to prevent severe complications.
Researchers based in Canada have created a groundbreaking blood test and portable device that can detect early signs of sepsis more quickly and precisely than current diagnostic tools.
Detailed in a recent edition of Nature Communications, the new test boasts over 90 per cent accuracy in pinpointing individuals at high risk of developing sepsis, marking a significant advancement in how the condition may soon be diagnosed and managed.
Dr. Claudia dos Santos, who is the lead researcher and critical care physician at St. Michael’s Hospital stated that sepsis is responsible for approximately one in five deaths worldwide. She further indicated that this new tool has the potential to revolutionize care by enabling doctors to identify and treat vulnerable patients before their condition rapidly worsens.
Researchers of the study pointed out that early detection is particularly challenging because initial symptoms are vague, and existing diagnostic tests can take as long as 18 hours and must be conducted in specialized laboratories. Every hour of delay in starting treatment raises the risk of death by nearly eight percent.
By analyzing blood samples from over 3,000 hospitalized individuals suspected of having sepsis, scientists from the University of British Columbia (UBC) and Sepset, a UBC-affiliated biotech firm, applied machine learning to uncover a six-gene expression pattern—dubbed “Sepset”—that was able to forecast sepsis in 90% of cases, even before a formal diagnosis was made. In a further validation study using 248 blood samples and a standard hospital method known as RT-PCR (Reverse Transcription Polymerase Chain Reaction), the test achieved a 94% accuracy rate in identifying early-stage sepsis in patients whose condition was on the verge of worsening.
Dr. Bob Hancock, co-author of the study, UBC microbiology and immunology professor, and Sepset’s CEO indicated that this highlights the powerful role of AI in making sense of highly complex genetic data to pinpoint key genes linked to sepsis risk, and in developing an algorithm capable of predicting the condition with remarkable precision.
To make the test more accessible for use at the point of care, the National Research Council of Canada (NRC) created a compact device named PowerBlade. Using just a single drop of blood, the device performs an automated series of steps to quickly identify signs of sepsis. In trials involving 30 patients, PowerBlade demonstrated 92 per cent accuracy in detecting individuals at high risk for sepsis and 89 per cent accuracy in confirming those who were not.
“PowerBlade delivered results in under three hours. Such a device can make treatment possible wherever a patient may be, including in the emergency room or remote health care units,” explained Dr. Hancock.
“By combining cutting-edge microfluidic research with interdisciplinary collaboration across engineering, biology, and medicine, the Centre for Research and Applications in Fluidic Technologies (CRAFT) enables rapid, portable, and accessible testing solutions,” added the co-author Dr. Teodor Veres, who is from the NRC’s Medical Devices Research Centre and CRAFT co-director. CRAFT, a joint venture between the University of Toronto, Unity Health Toronto and the NRC, which is responsible for the rapid production of innovative devices that have the ability to bring high-quality diagnostics to the point of care.
Dr. Hancock’s team, alongside UBC research associate and co-author Dr. Evan Haney, has begun the commercial rollout of the Sepset gene signature. Dr. Haney pointed out that these tests identify the earliest signs of sepsis, enabling doctors to intervene promptly rather than waiting for the condition to cause serious harm.
