Coronavirus particles

AI test ‘can identify Covid-19 within one hour’, researchers say

Image credit: Science Photo Library

A new test powered by artificial intelligence (AI) could be capable of identifying coronavirus within one hour, according to new research.

Its developers say it can rapidly screen people arriving at hospitals for Covid-19 and accurately predict whether or not they have the disease.

The Curial AI test has been developed by a team at the University of Oxford and assesses data typically gathered from patients within the first hour of arriving in an emergency department – such as blood tests and vital signs – to determine the chance of a patient testing positive for Covid-19.

Testing for the virus currently involves the molecular analysis of a nose and throat swab, with results having a typical turnaround time of between 12 and 48 hours. However, the Oxford team said their tool could deliver near real-time predictions for a patient’s Covid-19 status.

In an ongoing study, running since March, the researchers have tested the AI tool on data from 115,000 visits to A&E at Oxford University Hospitals (OUH).

Study lead Dr Andrew Soltan said: “When we tested the Curial AI on data for all patients coming to OUH’s emergency departments in the last week of April and the first week of May, it correctly predicted patients’ Covid status more than 90 per cent of the time.

“Until we have confirmation that patients are negative, we must take additional precautions for patients with coronavirus symptoms, which are very common.

“The Curial AI is optimised to quickly give negative results with high confidence, safely excluding Covid-19 at the front door and maintaining flow through the hospital.

Soltan suggested the AI test could be a useful tool for the NHS. He added that the researchers now hope to carry out real-world trials of the technology.

“The next steps are to deploy our AI in to the clinical workflow and assess its role in practice,” he said.

“A strength of our AI is that it fits within the existing clinical care pathway and works with existing lab equipment. This means scaling it up may be relatively fast and cheap.

“I hope that our AI may help keep patients and staff safer while waiting for results of the swab test.”

Meanwhile, the effects of the coronavirus pandemic on businesses continues to be sharply felt. UK bank TSB announced today that it had taken a £111m "impairment" across the six months as the economic outlook weakened. The bank attributed the loss to the hit it has taken from loans which it expects to go bad as the pandemic wreaks havoc with the economy.

TSB's pre-tax loss of £65.5m for the half year comes after making a £21.1m profit in the same period in 2019.

Many rival banks have similarly been writing off billions of pounds-worth of loans which they suspect will turn bad, citing the economic conditions brought on by coronavirus.

TSB highlighted the slow housing market and rising unemployment as two major threats to economic stability and recovery.

However, the lockdown has also seen a huge growth in users for TSB's mobile banking app, as more customers conduct almost all aspects of their lives online and from home. Nearly three times as many customers have been signing up for its mobile bank app every day since lockdown began.

Around nine out of 10 transactions were processed through digital or automated channels in June, with more than 70 per cent of sales online.

Debbie Crosbie, TSB chief executive, said: “We had a strong start to the year, but the external environment changed significantly when Covid-19 struck.

“Despite the challenging context, our balance sheet and capital position remain strong, we have improved efficiency in our operations, and our purpose to help people increase their money confidence has never been more relevant.”

Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.

Recent articles