This article is based on research findings that are yet to be peer-reviewed. Results are therefore regarded as preliminary and should be interpreted as such. Find out about the role of the peer review process in research here. For further information, please contact the cited source. As society transitions to "living with COVID-19", having access to both efficient and accurate screening tools is integral.
Researchers at the University of Oxford are seeking NHSX funding for an artificial intelligence (AI) COVID screening test. Results of a three-month evaluation study at John Radcliffe Hospital found the CURIAL-Rapide test could screen emergency department (ED) patients at the bedside within 10 minutes, without needing a laboratory. Results were available 45 minutes after patients arrived at the ED – 26% faster than with lateral flow tests (LFTs). When compared against PCR testing, the AI test was more likely to identify COVID patients than LFTs and corrected ruled out the infection 99.7% of the time. Collaborating with University Hospitals Birmingham NHS Foundation Trust, Portsmouth University Hospitals NHS Trust, and Bedfordshire Hospitals NHS Foundation trust, the study found CURIAL-Rapide performed consistently across 72,000 admissions to five UK hospitals. Another AI model named CURIAL-Lab, which uses routine blood tests performed in a laboratory alongside vital signs, was at least as effective as CURIAL-Rapide when tested at hospitals.
Artificial intelligence can enable busy NHS emergency departments to perform bedside checks for Covid-19 in just 10 minutes without the need for a laboratory, a study led by Oxford University shows. During a three-month evaluation at John Radcliffe Hospital, Oxford's main accident and emergency centre, the study found that AI test results were available 45 minutes after a patient arrived, 26% faster those for a lateral flow test. The AI screening test, known as CURIAL-Rapide, uses routine healthcare data (blood tests and vital signs) to screen patients for Covid-19. Compared to lateral flow tests, the AI test was more likely to identify Covid-19 in patients and correctly ruled out the infection 99.7% of the time, the research found. In addition, a collaboration with five NHS trusts between December 2020 and March 2021 – University Hospitals Birmingham, Portsmouth University and Bedfordshire Hospitals – the study found that the AI test performed consistently in 72,000 admissions. It provided reliable negative results for uninfected patients up to 98.8% of the time and was 21% more effective at identifying Covid-19 positive patients than lateral flow tests.
Results of the CURIAL study show that the AI test correctly predicted the Covid-19 status of 92.3 per cent of patients coming to A&E departments at the John Radcliffe Hospital in Oxford and the Horton General Hospital in Banbury during a two-week test period. The screening test was developed by infectious disease and clinical machine learning experts at the University of Oxford. Compared against results of laboratory swab testing, the CURIAL AI screening test correctly ruled-out COVID-19 97.6 per cent of the time. However, whereas swab testing typically takes 24 hours, the AI screening test offers rapid results using data that is already routinely available within one hour. The research team is led by Dr Andrew Soltan, an NIHR Academic Clinical Fellow (Cardiology) at the John Radcliffe Hospital, joining with the AI for Healthcare lab of Professor David Clifton, within Oxford's Institute of Biomedical Engineering, and with Professor David Eyre of the Oxford Big Data Institute. Dr Soltan, also a researcher at Oxford University's Radcliffe Department of Medicine, said: "Every day around 350 people come to our Emergency Departments in the John Radcliffe Hospital in Oxford and the Horton General Hospital in Banbury, yet only a small number will be ill with Covid-19.
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. What does the test involve? Currently, testing for the virus 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. How long has the study been running since?