Doctors say a combination of simple blood tests and artificial intelligence could help diagnose sepsis more quickly and identify patients most at risk of serious complications.
Sepsis is a serious condition in which the body is unable to respond properly to infection. It can progress to septic shock, which can damage the lungs, kidneys, liver, and other organs. Severe damage can be fatal, with an estimated 11 million sepsis-related deaths worldwide.
A new dual approach using blood tests and AI can detect symptoms early and save lives, say experts who combine sepsis' unique molecular signatures with AI tools to predict risk of organ failure and death. It is said that there is a possibility.
Their findings will be presented at the European Congress of Clinical Microbiology and Infectious Diseases in Barcelona next month.
Dr Lisa Melhammar from Lund University in Sweden said: “It is important to identify patients with suspected sepsis before organ failure sets in. Given the challenges associated with timely diagnosis and the fact that sepsis kills millions of people worldwide each year. Alternative approaches are urgently needed.”
She says that blood tests combined with personalized risk models have the potential to “provide more accurate sepsis diagnosis and save lives by identifying those who are likely to develop more severe clinical symptoms.” There is a gender,” he said.
The researchers studied 1,364 plasma samples from adults admitted to the emergency department of Skåne University Hospital with suspected sepsis between September 2016 and March 2023. Of the 1,073 patients with infectious diseases, 913 had sepsis.
The team then analyzed proteins associated with the body's immune response to sepsis to see if there was a pattern. They created a molecular signature from their analysis and used it to train an AI model that predicts who is likely to go into septic shock.
Patients were categorized as having low, medium, or high risk of developing septic shock, and the technique was able to show how increased risk was associated with increased mortality.
The researchers also identified a panel of proteins that predicted dysfunction in six different organs, including the heart, liver, and kidneys. The researchers then classified patients into five risk categories based on their likelihood of developing organ failure, infection, and death.
Melhammar added: “Rapid tests that can provide a more accurate sepsis diagnosis and predict who is at higher risk of poor outcome now seem truly achievable.” Such studies require clinical validation, and many hurdles must be cleared before these biomarkers can be used in the clinic. But we envision this as a tool that can be deployed around the world as the future of sepsis early detection. ”
Dr Ron Daniels, Founder and Co-Chief Executive Officer of the UK Sepsis Trust, said: “We will accelerate sepsis recognition, identify patients who need the most urgent attention sooner and increase the number of antibiotics available while using antibiotics. It is extremely important to ensure that lives are saved.” Be smarter.
“This study has great potential to further our understanding of sepsis, and may eventually help redesign clinical systems. As the authors acknowledge, sepsis is a complex syndrome; Although this technology is not yet commercially available, it is an important step in the right direction.”
It comes as NHS England prepares to introduce the first phase of 'Martha's Rule' from next month. The initiative, which was first rolled out nationally in April and has been adopted by 100 hospitals in the UK, gives patients and their loved ones in deteriorating health conditions an urgent second opinion on their care. be given the right to receive it.
The development comes as The Guardian's senior editor Merope Mills and her husband Paul Ratey put pressure on politicians, NHS bosses and doctors to tell how their 13-year-old daughter Martha died. This is the direct result of multiplying by . Sepsis cases at King's College Hospital, London in 2021.