They say current tests are ‘either lab-based and time-consuming’, or ‘fast and less accurate’, adding: “They are also limited; for instance, a lateral flow test only tests for one infection, which means illnesses are spread as infected people wait for results, or because they are unaware they are infected.” The team says its findings on harnessing AI in such testing, set out in an article in peer-reviewed scientific journal, ACS Nano, titled ‘Virus detection and identification in minutes using single-particle imaging and deep learning’, ‘demonstrate how machine learning can significantly improve the efficiency, accuracy, and time taken to not only identify different types of viruses, but also differentiate between strains’. They say this could help better control the spread of respiratory infections, and alleviate pressure on the NHS and healthcare staff while reducing medical waste.
Nicola Shiaelis and Dr Nicole Robb collaborated with Oxford’s John Radcliffe Hospital to evaluate a new method that uses AI software to identify viruses. The testing technology combines molecular labelling, ‘computer vision’, and machine learning, ‘to create a universal diagnostic imaging platform that looks directly at a patient sample, and can identify which pathogen is present in a matter of seconds’. As they put it, ‘this is much like facial recognition software, but for germs’.
Preliminary research demonstrated that the test could identify the COVID-19 virus in patient samples. However, the scientists were keen to determine if the test could be used to diagnose multiple respiratory infections. In the study, researchers began by labelling viruses in over 200 clinical samples from the John Radcliffe Hospital. Images of labelled samples were captured and processed by custom machine-learning software trained to recognise specific viruses by analysing their fluorescence labels, which show up differently for every virus because their surface size, shape, and chemistry, vary. The scientists say that results show the technology can rapidly identify different types and strains of respiratory viruses, including flu and COVID-19, ‘within five minutes, and with >97% accuracy’.
The scientists formed Pictura Bio to further develop this technology, and are now looking for further investment to accelerate development.
Dr Nicole Robb, co-founder of Pictura Bio, said: “Cases of respiratory infections in winter 2022/23 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, put the NHS and its workforce under immense and unsustainable pressure.
“Pictura Bio’s 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 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.”
The technology is now licensed by Pictura Bio, which aims to turn the method into a diagnostic test by creating a dedicated imager and single-use cartridge for use in point-of-care testing, with limited user input. The team will also expand the number of viruses that the models are trained on, and will eventually start looking at other pathogens, such as bacteria and fungi, in respiratory samples, blood, and urine.
The Pictura Bio team is focusing on ‘packaging’ its PIC-ID technology into a simple desktop ‘lab in a box’ (see photo), named IRIS (Instant Recognition Identification System), ‘around the size of a domestic microwave’, comprising a single-purpose high-powered fluorescent microscope and image capture and processing technology. The patented technology has reached proof of concept, and the team is now building the technology ‘to scale this product for wider availability and adoption in the medical community’.