AI test screens for COVID-19

New AI test identifies COVID-19 within one hour of a patient arriving at an emergency department

Infectious disease and clinical machine learning experts at the University of Oxford have developed an Artificial Intelligence test that can rapidly screen for COVID-19 in patients arriving in emergency departments.

The new ‘CURIAL’ AI test assesses standard data that is routinely collected during patient’s first hour in the emergency department, such as temperature, heart rate and standard blood tests, and then uses these to determine if a patient has a high chance of testing positive for coronavirus.

Currently, to test for COVID-19, patients require a nose and throat swab which usually has a turnaround of 12 to 48 hours and requires an array of specialised equipment, testing materials and staff.

Dr Andrew Soltan, an NIHR Academic Clinical Fellow at the John Radcliffe Hospital, said that identifying Covid-19 early in a hospital admission is essential for maintaining infection control and delivering timely care to patients.

“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”

This new system is said to give a near ‘real time’ prediction of a patient’s covid-19 status, all with equipment and staff already available in emergency departments.

The research team developed two early-detection models to identify COVID-19 using routinely collected data typically available within one hour of arrival to an emergency department, including laboratory tests, blood gas and vital signs and checked those against 115,394 emergency presentations and 72,310 admissions to hospital.

They hen trained relevant AI algorithms and continually assessed those for their accuracy.  Once the algorithms had been sufficiently tested, the two early-detection models were put to the test in a real hospital setting.

Results from these tests showed that the Emergency Department Model correctly predicted the COVID-19 status of patients 92.3% of the time, across the 3,326 patients coming to A&E in the two week test period, and the Admissions Model was correct 92.5% of the time for the 1,715 patients admitted.

Due to the positive results in the preprint, researchers are working hard to rapidly trial the CURIAL AI as a clinically useful tool for the NHS.

Contact Gi National
Email us: