Scientists in Scotland have developed an artificial intelligence (AI) based test that uses X-rays to accurately diagnose COVID in minutes.
The testing platform, developed by researchers at the University of the West of Scotland (UWS), is capable of detecting the SARS-CoV-2 virus much faster than the PCR test, which usually takes about two hours.
The technology could eventually be used to help relieve the strain on hard-pressed hospitals, especially in countries where PCR tests are not readily available, he said.
The technology uses X-ray technology, comparing the scans to a database of nearly 3000 images belonging to COVID patients, healthy individuals and people with viral pneumonia.
It then uses an AI process known as a Deep Convolutional Neural Network, an algorithm commonly used to analyze visual imagery, to make diagnoses.
Read | Cheaper version of Merck Kovid pill to be made for poor countries
The technology proved to be more than 98 percent accurate during the extensive testing phase, according to research published in the journal Sensors.
“There has long been a need for a quick and reliable tool that can detect COVID, and this has become even more true with the rise of the Omicron version,” said UWS Professor Naeem Ramzan, who led the research.
“Many countries are unable to conduct large numbers of COVID tests due to limited diagnostic equipment, but this technology uses easily accessible technology for early detection of the virus,” Ramzan said.
The researchers noted that X-rays may not show signs of Covid during the early stages of infection, so the technique cannot completely replace PCR tests.
However, it can still play an important role in containing the virus from spreading, especially when PCR tests are not readily available, he said.
“This could prove to be important and potentially life-saving when diagnosing severe cases of the virus, helping to determine what treatment may be needed,” Ramzan said.
The team now plans to expand the study to include a larger database of X-ray images obtained by different models of X-ray machines to evaluate the suitability of the approach in a clinical setting.
Read also | Novavax becomes Australia’s 5th approved COVID-19 vaccine
Read also | WHO counts 18 million Covid-19 cases last week as omicron slows spread