This technology can help ease the strain on difficult hospitals, especially in countries where PCR testing is available.
The technique, using X-ray technology, compares the scan with a database of about 3,000 images of patients with COVID-19, healthy people, and people with viral pneumonia.
It uses an AI process known as deep complex neural networks; an algorithm commonly used to analyze visual images to make a diagnosis.
According to research published in the journal Sensorthe technique proved to be more than 98% accurate during extensive testing.
Professor Naeem Ramzan from UWS, who led the study, said: “There has long been a need for a quick and reliable tool that can detect COVID-19, and this is becoming increasingly true for evolution of the Omicron variant”.
“Some countries are unable to perform large numbers of COVID-19 tests because of limited diagnostic tools, but the technique uses easily accessible technology to detect the virus reliably,” said Ramzan. fast”.
The researchers note that COVID-19 symptoms cannot be seen in X-rays in the early stages of infection, so the technology cannot completely replace PCR tests.
However, it can still play an important role in limiting the spread of the virus, especially when PCR tests are not available.
“It could prove to be very important and potentially life-saving, when diagnosing severe cases of the virus, helping to determine what treatments may be required,” Ramzan said.
The team now plans to expand the study, incorporating a larger database of X-ray images obtained by different X-ray machine models to assess the suitability of the approach. in the clinical setting.