The test uses a convolutional neural network to classify microscopy images of...
The test uses a convolutional neural network to classify microscopy images of single intact particles of different viruses.
Source: University of Oxford

AI-enabled rapid diagnostic test for COVID-19

Scientists from Oxford University’s Department of Physics have developed an extremely rapid diagnostic test that detects and identifies viruses in less than five minutes.

The method, published on the preprint server MedRxiv, is able to differentiate with high accuracy SARS-CoV-2 from negative clinical samples, as well as from other common respiratory pathogens such as influenza and seasonal human coronaviruses.

Working directly on throat swabs from COVID-19 patients, without the need for genome extraction, purification or amplification of the viruses, the method starts with the rapid labelling of virus particles in the sample with short fluorescent DNA strands. A microscope is then used to collect images of the sample, with each image containing hundreds of fluorescently-labelled viruses.

Machine learning software quickly and automatically identifies the virus present in the sample. This approach exploits the fact that distinct virus types have differences in their fluorescence labeling due to differences in their surface chemistry, size, and shape.

The scientists have worked with clinical collaborators at the 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, says: ‘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.’

Recommended article

DPhil student Nicolas Shiaelis, at the University of Oxford, says: ‘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.’

Dr Nicole Robb, formerly a Royal Society Fellow at the University of Oxford and now at Warwick Medical School, says: ‘A significant concern for the upcoming winter months is the unpredictable effects of co-circulation of SARS-CoV-2 with other seasonal respiratory viruses; we have shown that our assay can reliably distinguish between different viruses in clinical samples, a development that offers a crucial advantage in the next phase of the pandemic.’

The researchers aim to develop an integrated 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 are currently working with Oxford University Innovation (OUI) and two external business/finance advisors to set up a spinout, and are seeking investment to accelerate the translation of the test into a fully integrated device to be deployed as a real-time diagnostic platform capable of detecting multiple virus threats. 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.

Subscribe to our newsletter

Related articles

Biosensors quickly spot coronavirus proteins, antibodies

Biosensors quickly spot coronavirus proteins, antibodies

Scientists have created a new way to detect the proteins that make up the pandemic coronavirus, as well as antibodies against it.

Quantum nanodiamonds help detect disease earlier

Quantum nanodiamonds help detect disease earlier

The quantum sensing abilities of nanodiamonds can be used to improve the sensitivity of paper-based diagnostic tests, potentially allowing for earlier detection of diseases such as HIV.

Holographic imaging to detect viruses

Holographic imaging to detect viruses

A new approach using holographic imaging to detect both viruses and antibodies has the potential to aid in medical diagnoses and, specifically, those related to the COVID-19 pandemic.

Using machine learning to detect COVID-19 in X-rays

Using machine learning to detect COVID-19 in X-rays

Students at Cranfield University have designed computer models that can identify COVID-19 in X-rays.

Nanotechnology provides rapid visual detection of COVID-19

Nanotechnology provides rapid visual detection of COVID-19

Scientists have developed an experimental diagnostic test for COVID-19 that can visually detect the presence of the virus in 10 minutes.

mhealth: A smartphone-based COVID-19 test

mhealth: A smartphone-based COVID-19 test

Researchers are developing a COVID-19 testing method that uses a smartphone microscope to analyze saliva samples and deliver results in about 10 minutes.

A bifunctional biosensor detects COVID-19

A bifunctional biosensor detects COVID-19

How fast could SARS-CoV-2 be detected? Researchers have developed an accurate, high-speed, and portable detector for COVID-19.

'Liquid' machine learning system adapts to changing conditions

'Liquid' machine learning system adapts to changing conditions

A machine learning system learns on the job. By continuously adapting to new data inputs, this “liquid network” could aid decision-making in medical diagnosis.

Biomedical research: deep learning outperforms machine learning

Biomedical research: deep learning outperforms machine learning

Deep-learning methods have the potential to offer substantially better results, generating superior representations for characterizing the human brain.

Popular articles