A team of scientists from Oxford University’s Department of Physics are using machine learning technology as part of a diagnostic test, said to identify viruses in less than five minutes.
The University is currently working with external advisors to set-up a spinout company and are seeking investment. Their aim is to roll-out the device from the middle of next year, following a testing phase in early 2021.
The test works using throat swabs, with a microscope used to collect images of the sample. Machine learning software is then used to automatically scan and identify if the virus is present in the sample.
The scientists have worked with John Radcliffe Hospital in Oxford to validate the assay on COVID-19 patient samples which were confirmed by conventional RT-PCR methods.
Professor Achilles 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.”
DPhil student Nicolas Shiaelis, at the University of Oxford, said: “Our test is much faster than other existing diagnostic technologies; viral diagnosis in less than 5 minutes can make mass testing a reality, providing a proactive means to control viral outbreaks.”
The researchers aim to develop a device that will eventually be used for testing in sites such as businesses, music venues, airports etc., to establish and safeguard COVID-19-free spaces.
They hope to incorporate the company by the end of the year, start product development in early 2021, and have an approved device available within 6 months of that time.
