Oxford test employs AI to detect virus in five minutes

OXFORD UNIVERSITY has unveiled a new Covid test capable of detecting the virus in less than five minutes through artificial intelligence analysis of throat swabs.

Its creators said the technology could be used to provide rapid tests at public venues such as airports. They say the test is able to distinguish between SarsCOV-2 – the virus responsible for Covid19 – and negative clinical samples.

It is also able to tell it apart from other viruses such as flu and seasonal human coronaviruses, according to the study.

The design team hope to begin manufacture of the test at the start of 2021 and to make it widely available by the summer.

Working directly on throat swabs from Covid-19 patients, without the need for genome extraction, purification or amplification of the viruses, the method starts with the rapid labelling of virus particles in the sample with short fluorescent DNA strands.

A microscope is used to collect images of the sample, with each image containing hundreds of fluorescently-labelled viruses. Machine-learning software quickly and automatically identifies the virus present in the sample.

Researchers say this approach exploits the fact that distinct virus types have differences in their fluorescence labelling due to differences in their surface chemistry, size, and shape.

The scientists worked with collaborators at the John Radcliffe Hospital in Oxford to validate the test on Covid-19 patient samples which were confirmed by conventional RT-PCR methods.

Prof Achillefs Kapanidis, at Oxford’s department of physics, said: “Unlike other technologies that detect a delayed antibody response or that require expensive, tedious and time-consuming sample preparation, our method quickly detects intact virus particles, meaning the assay is simple, extremely rapid, and cost-effective.”

The research, which is yet to be peerreviewed, is published on medrxiv.com.