Pavilion Publishing and Media Ltd
Blue Sky Offices Shoreham, 25 Cecil Pashley Way, Shoreham-by-Sea, West Sussex, BN43 5FF, UNITED KINGDOM
Tel: +44 (0)1273 434 943
Email: [email protected]
Researchers from University College London (UCL) have developed a blood test which may be able to predict people’s likelihood of developing Long Covid.
However, the researchers warn that the study’s results need to be validated in a larger group of patients before the test is rolled out on a national level.
AI algorithm predicted all 11 healthcare workers who went onto develop Long Covid symptoms
To carry out the study, researchers analysed blood plasma samples from 54 healthcare workers who had PCR- or antibody-confirmed infection, taken every week for six weeks in spring 2020, comparing them to samples taken over the same period from 102 healthcare workers who were not infected.
Using these blood samples, the researchers were able to analyse proteins in the blood. Usually, protein levels in the body are stable, but the researchers found abnormally high levels of 12 proteins out of the 91 studied among those infected with the virus. They also found that the degree of abnormality correlated with the severity of symptoms.
The research team found that at the time of first infection, abnormal levels of 20 proteins (which were mostly linked to linked to anti-coagulant and anti-inflammatory processes) were predictive of persistent symptoms after one year.
An artificial intelligence (AI) algorithm was then able to identify a “signature” in the abundance of different proteins, meaning the researchers were able to successfully predict all of the 11 healthcare workers who reported at least one persistent symptom at one year following infection.
Another machine learning tool was used to estimate the likelihood of error and suggested a possible error rate of 6% for this method.
The test could be rolled out “quickly and in a cost-effective way”
Lead author Dr Gaby Captur (MRC Unit for Lifelong Health and Ageing at UCL) said: “Our study shows that even mild or asymptomatic Covid-19 disrupts the profile of proteins in our blood plasma. This means that even mild Covid-19 affects normal biological processes in a dramatic way, up to at least six weeks after infection.
“Our tool predicting long Covid still needs to be validated in an independent, larger group of patients. However, using our approach, a test that predicts long Covid at the time of initial infection could be rolled out quickly and in a cost-effective way.
“The method of analysis we used is readily available in hospitals and is high-throughput, meaning it can analyse thousands of samples in an afternoon.