AI diagnostic test accurately identifies respiratory viruses in minutes
Scientists have developed a groundbreaking diagnostic test using artificial intelligence (AI) to identify respiratory viruses within five minutes from a single nasal or throat swab. The diagnostic test can identify multiple viruses and differentiate between strains, making it more accurate than current methods.
The paper published in ACS Nano describes the new virus detection and identification methodology.
Facial recognition for germs
The technology combines molecular labeling, 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—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. To do so, researchers collaborated with the John Radcliffe Hospital to validate the new method.
They labeled viruses with single-stranded DNA in over 200 clinical samples from the hospital. Images of labeled samples were captured using a commercial fluorescence microscope and processed by custom machine-learning software trained to recognize specific viruses by analyzing their fluorescence labels, which show up differently for every virus.
Results showed that the technology could rapidly identify different types and strains of respiratory viruses, including flu virus and COVID-19, within five minutes and with >97% accuracy.
Point-of-care testing
In 2021, Nicolas Shiaelis and Dr. Nicole Robb, authors of the study, founded the University of Oxford spin-out Pictura Bio to license the technology. The team 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 input from the user. The company is also expanding the number of viruses the models are trained on and plans to look at other pathogens, such as bacteria and fungi, in respiratory samples, blood, and urine.
The technology is quicker, more cost-effective, accurate, and future-proof than any other available tests. If researchers want to detect a new virus, they only need to retrain the software to recognize it rather than develop a whole new test. The team's findings demonstrate the potential for this method to revolutionize viral diagnostics and control the spread of respiratory illnesses.
The team believes that this technology is essential as it is inevitable that new viruses like COVID-19 will emerge. Therefore, more advanced diagnostic technologies are needed to reduce the impact of new viruses on public health and the healthcare system.
The study was published in the journal ACS Nano.
Abstract:
The increasing frequency and magnitude of viral outbreaks in recent decades, epitomized by the COVID-19 pandemic, has resulted in an urgent need for rapid and sensitive diagnostic methods. Here, we present a methodology for virus detection and identification that uses a convolutional neural network to distinguish between microscopy images of fluorescently labeled intact particles of different viruses. Our assay achieves labeling, imaging, and virus identification in less than 5 min and does not require any lysis, purification, or amplification steps. The trained neural network was able to differentiate SARS-CoV-2 from negative clinical samples, as well as from other common respiratory pathogens such as influenza and seasonal human coronaviruses. We were also able to differentiate closely related strains of influenza, as well as SARS-CoV-2 variants. Additional and novel pathogens can easily be incorporated into the test through software updates, offering the potential to rapidly utilize the technology in future infectious disease outbreaks or pandemics. Single-particle imaging combined with deep learning therefore offers a promising alternative to traditional viral diagnostic and genomic sequencing methods and has the potential for significant impact.