AI offers answers to COVID’s effects

Artificial intelligence has been used to identify metabolic markers of Covid, a discovery which could lead to better understanding and treatments for people that suffer from symptoms months after diagnosis.

Pixabay

Scientists from Surrey University collected blood samples of hospital patients and found that Covid-19 changed people's metabolism. The team observed that the effects of Covid-19 changed over time, with the first wave disrupting metabolites differently from the second. Thei findings are published in Metabolites.

Many patients' metabolites eased back to normal levels once they had recovered from Covid-19, but a small number continued to be disrupted for several months after infection.

In a statement, Dr Holly-May Lewis, lead author of the study from Surrey University, said: "It is thought that around two million people suffer symptoms of Covid-19 a month after infection, and 800,000 people still experience symptoms a year later. So, it's clear that this virus will be with us for some time and, therefore, the scientific community is duty-bound to better understand Covid-19 and why, for some, symptoms seem to linger longer than average."

MORE FROM ARTIFICIAL INTELLIGENCE

Surrey's study analysed the blood samples of 164 hospital patients - 123 with Covid-19 and 41 who provided a negative PCR test - across the first two waves of infection. Nineteen positive patients also provided samples two to seven months after infection.

Using an artificial intelligence model, the Surrey team identified six metabolites that can be used to identify Covid-19 with 91 per cent accuracy.

Professor Melanie Bailey, corresponding author of the study from Surrey University, said: "To our knowledge, this is the first time it has been demonstrated that Covid-19 is now affecting patients' metabolism differently than it did in the initial wave - which we think is due to emerging variants. It is known that different Covid variants have various associated symptoms, so it makes sense that this would relate to changes in blood chemistry.

"With this in mind, we then deployed artificial intelligence to identify biomarkers characteristic of Covid-19, regardless of the Covid wave. This can help us better understand the limitations of the treatments being given and help to make better ones."