Researchers out of the University of British Columbia have found that artificial intelligence can detect sepsis quicker.
According to a UBC news release Tuesday, sepsis is responsible for at least one in five deaths worldwide, including those from severe cases of COVID-19.
But experts warn, the life-threatening condition is difficult to detect early.
UBC researchers say because sepsis is defined as the body’s dysfunctional response to an infection and has a variety of symptoms – including fever, fatigue, hyperventilation and a fast heart rate – it can often appear at first to be from other diseases.
“This new technique dissects the dysfunctional immune responses involved in sepsis like never before, providing new insights into the biological processes involved in sepsis of any type, including that from COVID-19,” says Arjun Baghela, a UBC graduate student who led the analysis.
“People don’t know much about sepsis, but in 2020, the number of deaths from life-threatening sepsis is likely much higher than one in five, since pretty much everyone who had died from COVID-19 has actually died from sepsis.”
According to the Centers for Disease Control, infections that can lead to sepsis typically start in the skin, lungs, urinary tract or gastrointestinal tract.
It can take anywhere between 24 to 48 hours before health-care providers can confirm a patient has sepsis. But for every hour delay in providing treatment, the risk of death increases by as much as 7.6 per cent, hightlighting the need for rapid detection, UBC researchers say.
“Typically, a patient arrives in the emergency room feeling profoundly ill, with a bunch of symptoms that are faily non-specific,” says Dr. Bob Hancock, UBC professor.
“The physician looks at that patient if they have an aggregate of symptoms and says, ‘This is a patient that might have sepsis,’ but only if they have some certainty can they start to treat them immediately. They’re in a bit of a ‘look-and-see’ game for the first 24 to 48 hours.”
Hancock adds that it’s imperative to learn if the patient has sepsis as early as possible, given that it’s so common and rampant antimicrobial resistance is a risk if antibiotics are used more than necessary.
For the study, published in the EBioMedicine journal, researchers examined a total of 348 patients across four continents. Scientists say they were able to confirm their findings by re-examining two other large studies, for a total of 1,062 patients.
The research found that severe sepsis can be detected when a patient first arrives for medical care.
“Using machine learning, also known as articificial intelligence, the researchers were able to identify sets of genes that predict whether a patient will acquire severe sepsis, and could make sense of the five distinct ways (subtypes/endotypes) in which sepsis manifessts itself,” the study reads.
Researchers say this discovery will eventually lead to testing that will allow health-care providers to identify the body’s dysfunctional response to an infection more rapidly and determine the appropriate treatment.
“This is important because two subtypes are associated with a much higher risk of severe sepsis and death,” the study reads. “These biomarkers also worked in the ICU, where it was shown that one endotype was particularly deadly, with a mortality rate of 26 per cent.”
Researchers add that the technique for measuring gene expression is already present in hospitals, and it can be performed within just two hours of being admitted to the emergency room.
View original article here Source