Loughborough Echo

AI could help beat Covid-19 by calculatin­g the virus risk


- News Reporter By DAVID OWEN

PATIENTS treated for coronaviru­s in Leicester’s hospitals are helping researcher­s find out if artificial intelligen­ce (AI) can calculate someone’s risk of dying from the disease.

Researcher­s at the University of Oxford believe they have identified a “disease signature” using machine learning and CT chest scans taken at city hospitals.

They suggest the technology could be used to tailor treatment and give people the best chance of recovery, following research funded by the British Heart Foundation (BHF).

Severe cases of Covid-19 have been associated with something called a cytokine storm. This is where the spike protein of the virus causes the immune system to go into overdrive and produces a surge of damaging molecules called cytokines.

By using routine chest CT scans, Oxford researcher­s have developed a Covid-19 signature.

It works by detecting biological red flags in the fat surroundin­g blood vessels in the chest to measure the level of inflammati­on driven by cytokines in people infected with the virus.

Charalambo­s Antoniades, professor of cardiovasc­ular medicine and BHF senior clinical research fellow at the university, said: “We have built an incredibly adaptable AI platform that tracks vascular disease by decoding informatio­n from blood vessel images obtained routinely during hospital admission, and integratin­g it with a large RNA bioresourc­e from human tissue biopsies.”

RNA is ribonuclei­c acid, something that is present in all living cells. Its principal role is to act as a “messenger”, carrying instructio­ns from DNA for controllin­g proteins.

“By simply adding in one extra step to the routine care of people admitted to hospital with Covid-19 who already have a CT scan, we can now detect patients at high risk of life-threatenin­g complicati­ons and could potentiall­y tailor their treatment to aid long-term recovery,” said Prof Antoniades.

“But the benefits don’t stop there - we know that this exaggerate­d immune response to the virus can also cause abnormal blood clotting, and so we are developing this AI platform to specifical­ly identify Cov id -19 patients who are most at risk of having a future heart attack or stroke.

“We can also pivot our platform with ease to develop a new scanning ‘signature’ to better understand future viruses and diseases that take hold of our population.”

Researcher­s applied the Covid-19 signature to CT chest scans of 435 people admitted to hospitals in Oxford, Leicester and Bath, and compared the degree of inflammati­on and risk of death in people with and without Covid.

They found that for patients admitted to hospital, the level of cytokine- driven inflammati­on in the blood vessels was much higher in those with Covid-19, and even greater in patients infected by the Kent variant. Researcher­s found that those with a high level of vascular inflammati­on were up to eight times more likely to die, and were most likely to respond to the anti-inflammato­ry drug Dexamethas­one. Covid-19 patients with high vascular inflammati­on treated with

Dexamethas­one had a six-fold reduction in risk of dying compared to Covid-19 patients who were not given the drug.

Researcher­s say that by using this tool to obtain an inflammati­on score, patients found to have a lot of inflammati­on in their blood vessels - and therefore increased risk of death - could potentiall­y be given anti-inflammato­ry drugs to reduce the risk and aid long-term recovery.

Clinical trials are now looking into the effectiven­ess of this approach, which was presented at the British Cardiovasc­ular Society conference.

Professor James Leiper, associate medical director at the BHF, said: “We have supported our scientists to direct their expertise to help the global effort in understand­ing Covid-19. This research clearly demonstrat­es that Covid-19 is a virus that can wreak havoc on our circulator­y system, and different variants are associated with different risk levels.

“There are still a lot of unknowns relating to how the virus can impact our health in the long term, but this AI tool could ultimately help to save lives.”

There are still a lot of unknowns... but this AI tool could ultimately help to save lives

Professor James Leiper

Newspapers in English

Newspapers from United Kingdom