Here’s an example of how AI is going to change all things medical. We now have a world-first diagnostic test, powered by artificial intelligence, which can identify a virus such as Covid in less than five minutes from just one nasal or throat swab.
This test could replace the current ones that can only test for one infection – such as a lateral flow test for Covid-19 – and are time-consuming, or fast but less accurate.
The technology for this virus detection springs from a collaboration between student Nicolas Shiaelis and Professor Achillefs Kapanidis of Oxford University, and Dr Nicole Robb of Warwick University, who is also a visiting lecturer at Oxford.
Their report demonstrates how AI learning can vastly improve the efficiency, accuracy and time taken to identify viruses, and to even differentiate between variants.
The method is much like facial recognition software, but for germs.
Nicolas Shiaelis and Dr Robb collaborated with the John Radcliffe Hospital, Oxford, to validate the method. This groundbreaking technology creates a universal platform that looks directly at a patient sample and can identify which virus is present in a matter of seconds.
After demonstrating the test could identify the Covid-19 virus in patient samples, further work showed it could diagnose many respiratory infections, all within five minutes and with better than 97% accuracy. The colleagues formed a company called Pictura Bio to licence the technology on behalf of Oxford University.
Their aim is to turn the method into a one-off diagnostic test that can be used directly on patients, needing little expertise from the operator. Pictura Bio will start expanding the number of viruses that can be identified and will eventually start looking at bacteria and fungi in respiratory samples, blood and urine.
Dr Robb says: “Cases of respiratory infections this winter have hit record-breaking highs, increasing the number of people seeking medical help.
“This, combined with the Covid-19 backlog, staff shortages, tighter budgets and an ageing population puts the NHS under immense pressure.
“Our simplified method of diagnostic testing is quicker and more cost-effective, accurate and future-proof than any other tests available.
“If we want to detect a new virus, all we need to do is retrain the software to recognise it, rather than develop a whole new test. Our findings demonstrate the potential for this method to revolutionise viral diagnostics and our ability to control the spread of respiratory illnesses.”
This test would rapidly identify the infectious agent so treatment can be started faster than ever before.
