Doctors say combining a simple blood test with artificial intelligence could help diagnose sepsis more quickly and identify patients most at risk of serious complications.
Sepsis is a serious illness in which the body does not respond properly to infection. It can progress to septic shock, which can damage the lungs, kidneys, liver and other organs. When the damage is severe, it can lead to death, with an estimated 11 million sepsis-related deaths worldwide each year.
A new dual approach using a blood test and AI could detect the disease earlier and save lives, according to experts who combined the unique molecular signature of sepsis with AI tools to predict the risk of failure of a organ and death.
Their results will be presented at the European Congress of Clinical Microbiology and Infectious Diseases in Barcelona next month.
Dr Lisa Mellhammar, from Lund University in Sweden, said: “It is essential that patients with suspected sepsis are identified before organ failure develops. Given the challenges associated with rapid diagnosis and the fact that sepsis kills millions of people worldwide each year, there is an urgent demand for an alternative approach.
She said a blood test combined with a personalized risk model “has the potential to save lives by providing a more accurate sepsis diagnosis and determining who might develop more serious clinical manifestations.”
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 infected patients, 913 had sepsis.
The team then analyzed proteins associated with the body’s immune response to sepsis to see if there was a trend. They created molecular signatures from their analysis, which were used to train an AI model to predict who was likely to experience septic shock.
Patients were classified as having low, medium and high risk of developing septic shock, with the technology able to show how increasing risk was associated with a higher mortality rate.
The researchers also identified panels of proteins that predicted dysfunction in six different organ types, including the heart, liver and kidneys. They then classified patients into five risk categories based on their likelihood of experiencing organ dysfunction and infection, as well as their risk of dying.
Mellhammar added: “A rapid test that provides a more accurate sepsis diagnosis and could also predict who is most at risk of poorer outcomes now seems a real possibility. Any research like this requires clinical validation and many obstacles must be overcome before these biomarkers are used in the clinic. But we envision this as a tool that could be deployed globally as the future of early detection of sepsis.
Dr Ron Daniels, founder and co-chief executive of the UK Sepsis Trust, said: “It is extremely important to accelerate the recognition of sepsis and identify patients who need immediate attention earlier, to ensure that we can save more lives using antimicrobials. more wisely.
“This research has enormous potential to refine our understanding of sepsis and could ultimately help us rethink clinical systems. As the authors acknowledge, sepsis is a complex syndrome and this technology is not yet ready for street use, but 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. Patients in failing health and their loved ones will have the right to an urgent second opinion on their care, as the initiative was initially adopted in 100 English hospitals from April, before being introduced at national.
The rollout is a direct result of pressure put on politicians, NHS bosses and doctors by Guardian editor Merope Mills and her husband, Paul Laity, telling the story of the death of their 13-year-old daughter. years old, Martha. of sepsis at King’s College Hospital, London in 2021.