University working on rapid coronavirus testing app

CT scans could be used to rapidly diagnose Covid-19 Credit: University of Essex

Researchers at the University of Essex believe they have found a rapid diagnostic tool for Covid-19.

Scientists from the university's School of Computer Science and Electronics Engineering have created an app which examines images taken from medical scans. It then gives an indication of the likelihood of the patient having the disease.

Early results from the App - which uses an algorithm to analyse Computed Tomography images (CT) - are said to be encouraging, despite wortk being at a very early stage.

Researchers hope that if it's successful it could return results in under an hour, compared with the 24 hours it takes to get the results of swab tests.

Scientists are using AI to identify a specific coronavirus cough Credit: ITV News Anglia

The University has already started work on a method of using artificial intelligence to detect coronavirus by listen to recordings of people coughing.

The trial is similar to one being carried out in Cambridge, which is also aiming to collect recordings of people breathing and coughing.

But researchers on the CT scan app - MSc student Suraj Ghuwalewala and Dr Haider Raza, an expert in AI for decision making - say they need more CT images to test.

They are hoping to partner with an NHS Trust to enrich the CT image dataset as including more images in training the AI model may improve the accuracy of the app.

“Although this research is at a very early stage, we have seen some very impressive results on its accuracy. If the virus reappears, our algorithm has great potential to be applied in clinical applications for accurate and rapid COVID-19 diagnosis, which would be a great help for frontline medical staff.”

Dr Haider Raza

It is hoped that the work might also eventually be expanded to other respiratory diseases.