The research, conducted by a team at the University of the West of Scotland (UWS), sees a specially-designed Artificial Intelligence (AI) algorithm compare a patient’s X-ray scans with up to 3,000 images belonging to those suffering with Covid, healthy individuals and patients with viral pneumonia.
From there, the technology is able to advise if a patient is in fact suffering from coronavirus – with reported 98 per cent accuracy.
Compared to PCRs, which take around two hours to return a result, this new method comes back with a diagnosis in a few minutes – potentially easing pressure on health systems around the world, if it is rolled out.
Professor Naeem Ramzan, who led the three-person team developing the project at UWS, said: “There has long been a need for a quick and reliable tool that can detect Covid-19, and this has become even more true with the upswing of the Omicron variant.
“Several countries are unable to carry out large numbers of Covid tests because of limited diagnosis tools, but this technique utilises easily accessible technology to quickly detect the virus.”
But Prof Ramzan, who is director of the Affective and Human Computing for SMART Environments Research Centre at UWS, stressed the need for PCR tests is unlikely to disappear.
“Covid-19 symptoms are not visible in X-rays during the early stages of infection, so it is important to note that the technology cannot fully replace PCR tests,” he said.
“However, it can still play an important role in curtailing the viruses spread especially when PCR tests are not readily available. It could prove to be crucial, and potentially life-saving.”
The researchers now plan to expand the study of their new testing technique by comparing a larger number of X-ray images, to see if the technology can be rolled out in hospitals and clinics.
PCRs – or polymerase chain reaction – are molecular tests that require scientists in labs to amplify small amounts of RNA from the sample provided into deoxyribonucleic acid (DNA) through a machine called a thermal cycler.
This DNA is then replicated until the Covid virus is detectable, if it is present. One of the chemicals in the machine produces a fluorescent light if Sars-CoV-2 is detected.
While still considered the most effective form of testing, it can be slow, with wait times for results in the UK lasting as long as five days during the Delta and Omicron waves.
If scientists can swap to X-rays and computer analysis, they could become far more efficient at recognising the virus.
Prof Milan Radosavljevic, UWS’ vice-principal of research, innovation and engagement, described the new findings as “potentially game-changing”.
“I am incredibly proud of the drive and innovation demonstrated by our internationally renowned academics, as they strive to find solutions to urgent global problems,” he said.
The news comes after testing requirements were changed in England earlier this month, to mean that from 11 January asymptomatic people testing positive for Covid via a lateral flow device were no longer required to take a confirmatory PCR test.