Drug Regulatory Authority of Pakistan (Drap) Chief Executive Officer Asim Rauf on Saturday said the body has granted approval to a locally invented software that can "detect the coronavirus infection in a person's lungs within a minute".

According to the certificate of registration granted by Drap, a copy of which is available with Dawn.com, the Cov-Raid — which has been developed by the National Electronics Complex of Pakistan — "shall employ Convolutional Neural Networks to predict [presence of] Covid-19 in suspected individuals" by using X-rays and it has been approved for "secondary detection" of the virus.

The Cov-raid website says the artificial intelligence (AI) technology was developed by "creating a data repository of chest X-rays (CXR) for Covid-19 or non-Covid-19 detection", adding that the software "requires a chest X-ray image as an input for the detection of Covid-19 positive or negative patients in less than one minute".

"The algorithm has been trained on more than 35,000 CXRs (data authentication done through multiple certified radiologists and PCR reports)," it said.

According to the description posted on the website, the technology "can be path-breaking to conduct screening of a large number of patients in a limited time".

The Drap CEO also said that the device would "greatly help" in the treatment of virus patients.

"This [technology] is available in only a few countries in the world. Pakistan will supply the Cov-raid technology to various countries," he disclosed.

The software will soon be available across the country, he added.

A similar algorithm was developed by a team of researchers at the University of Minnesota in the United States last month "that can evaluate chest X-rays to diagnose possible cases of Covid-19 within seconds".

"[The] model learns from thousands of X-rays and detects Covid-19 in seconds, then immediately shows the risk score to providers who are caring for patients," Ju Sun, who led the team, said.

Another such software was developed in China earlier this year by Axial AI which analysed Computed Tomography (CT) imagery in seconds.