Oxford researchers create test to diagnose respiratory viruses in just five minutes
The novel diagnostic test may replace existing procedures that can only detect a single infection, such a COVID-19 lateral flow test, or that are either lab-based and labor-intensive or quick and less precise.
- Feb 13, 2023,
- Updated Feb 13, 2023 8:31 PM IST
Oxford scientists have created a world-first artificial intelligence-powered diagnostic tool that can identify known respiratory viruses in five minutes from a single nasal or throat sample.
The novel diagnostic test may replace existing procedures that can only detect a single infection, such a COVID-19 lateral flow test, or that are either lab-based and labor-intensive or quick and less precise.
In a paper published in ACS Nano, DPhil student Nicolas Shiaelis, Professor Achillefs Kapanidis from the Department of Physics, and Dr. Nicole Robb from the University of Warwick, who serves as a visiting lecturer at Oxford's Department of Physics, describe the new virus detection and identification methodology.
The study shows how machine learning may greatly increase the speed, precision, and effectiveness of not only classifying viruses but also differentiating between strains.
The John Radcliffe Hospital worked with Nicolas Shiaelis and Dr. Robb to validate the novel approach. The innovative testing method combines molecular labelling, computer vision, and machine learning to produce a universal diagnostic imaging platform that can quickly detect the pathogen present in a patient sample by looking straight at it — similar to facial recognition software, but for germs.
Initial studies showed that the test could recognise the COVID-19 virus in patient samples, and subsequent studies showed that the test could detect various respiratory illnesses in five minutes with an accuracy rate of over 97 per cent.
Pictura Bio, an Oxford University spinout company formed by Dr. Robb and Nicolas Shiaelis, now licences the technology. They are currently seeking additional funding to speed up research and bring it to the forefront of healthcare.
Dr Robb said, “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 and its workforce under immense and unsustainable pressure.”
“Our simplified method of diagnostic testing is quicker and more cost-effective, accurate and future proof than any other tests currently 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.” Robb added.
Oxford scientists have created a world-first artificial intelligence-powered diagnostic tool that can identify known respiratory viruses in five minutes from a single nasal or throat sample.
The novel diagnostic test may replace existing procedures that can only detect a single infection, such a COVID-19 lateral flow test, or that are either lab-based and labor-intensive or quick and less precise.
In a paper published in ACS Nano, DPhil student Nicolas Shiaelis, Professor Achillefs Kapanidis from the Department of Physics, and Dr. Nicole Robb from the University of Warwick, who serves as a visiting lecturer at Oxford's Department of Physics, describe the new virus detection and identification methodology.
The study shows how machine learning may greatly increase the speed, precision, and effectiveness of not only classifying viruses but also differentiating between strains.
The John Radcliffe Hospital worked with Nicolas Shiaelis and Dr. Robb to validate the novel approach. The innovative testing method combines molecular labelling, computer vision, and machine learning to produce a universal diagnostic imaging platform that can quickly detect the pathogen present in a patient sample by looking straight at it — similar to facial recognition software, but for germs.
Initial studies showed that the test could recognise the COVID-19 virus in patient samples, and subsequent studies showed that the test could detect various respiratory illnesses in five minutes with an accuracy rate of over 97 per cent.
Pictura Bio, an Oxford University spinout company formed by Dr. Robb and Nicolas Shiaelis, now licences the technology. They are currently seeking additional funding to speed up research and bring it to the forefront of healthcare.
Dr Robb said, “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 and its workforce under immense and unsustainable pressure.”
“Our simplified method of diagnostic testing is quicker and more cost-effective, accurate and future proof than any other tests currently 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.” Robb added.