A blood test taken while people have COVID could predict whether they are likely to develop long-term health problems, a new study has found.
If the experimental test is validated by further research, it may result in people at high risk of long-COVID receive antiviral treatments in hopes of preventing debilitating symptoms.
Researchers from University College London compared the levels of more than 90 blood proteins in 54 healthcare workers with covid and a control group of healthy personnel.
They found that several proteins were significantly disrupted for up to six weeks, even in people with mild symptoms, according to findings published in the Lancet journal eBioMedicine.
Twenty of these were predictive of persisting symptoms a year later. Most were related to anti-coagulant and anti-inflammatory processes.
The researchers then used an artificial intelligence (AI) algorithm to analyze proteins in the blood samples – and successfully identified all 11 infected health workers who developed long COVID.
Dr Wendy Heywood, one of the principal investigators at UCL’s Great Ormond Street Institute of Child Health, said: “If we can identify people who are at risk of developing long COVID, that opens the door to trials of treatments. such as antivirals at this earlier stage, initial stage of infection, to see if it can reduce the risk of later long-COVID.
Kevin McConway, professor emeritus of applied statistics at the Open University, said the blood test would need to be validated in a larger study to make sure the AI algorithm was working properly.
“While their prediction tool certainly looks quite promising, this research cannot provide enough evidence that it can work in a broader context,” he said.
“All of the data in this study comes from the first wave of the COVID pandemic, before new virus variants emerged and before vaccines were developed – and when the participants, who were all healthcare workers, were subjected to a fairly specific set of conditions in their work and in the country in general.”
A blood test taken while people have COVID could predict whether they are likely to develop long-term health problems, a new study has found.
If the experimental test is validated by further research, it may result in people at high risk of long-COVID receive antiviral treatments in hopes of preventing debilitating symptoms.
Researchers from University College London compared the levels of more than 90 blood proteins in 54 healthcare workers with covid and a control group of healthy personnel.
They found that several proteins were significantly disrupted for up to six weeks, even in people with mild symptoms, according to findings published in the Lancet journal eBioMedicine.
Twenty of these were predictive of persisting symptoms a year later. Most were related to anti-coagulant and anti-inflammatory processes.
The researchers then used an artificial intelligence (AI) algorithm to analyze proteins in the blood samples – and successfully identified all 11 infected health workers who developed long COVID.
Dr Wendy Heywood, one of the principal investigators at UCL’s Great Ormond Street Institute of Child Health, said: “If we can identify people who are at risk of developing long COVID, that opens the door to trials of treatments. such as antivirals at this earlier stage, initial stage of infection, to see if it can reduce the risk of later long-COVID.
Kevin McConway, professor emeritus of applied statistics at the Open University, said the blood test would need to be validated in a larger study to make sure the AI algorithm was working properly.
“While their prediction tool certainly looks quite promising, this research cannot provide enough evidence that it can work in a broader context,” he said.
“All of the data in this study comes from the first wave of the COVID pandemic, before new virus variants emerged and before vaccines were developed – and when the participants, who were all healthcare workers, were subjected to a fairly specific set of conditions in their work and in the country in general.”