An AI created by Bering Limited and a study conducted by iCAIRD, Scotland’s Industrial Centre for AI Research in Digital Diagnostics, have yielded promising results from chest x-rays in a simulated clinical test setting to speed up COVID-19 diagnosis in patients who presented to emergency departments with respiratory symptoms.
The iCAIRD study was in partnership with NHS Greater Glasgow and Clyde using Canon Medical Research Europe’s Safe Haven Artificial Intelligence Platform (SHAIP) as well as datasets from the Glasgow Safe Haven service. It used the AI algorithm, giving an accurate COVID-19 result in under three minutes, with performance on a par with four certified radiologists.
Joint clinical lead of the West of Scotland Innovation Hub and emergency medicine consultant at Queen Elizabeth University Hospital Professor David Lowe said: “Through testing in a safe environment we have been able to see that this algorithm can identify COVID-19 on chest x-rays that were routinely taken during initial clinical assessment. This could not just help with the treatment of patients but may also speed up the process of isolating infected patients.”
The Canon Medical Research Europe AI Centre of Excellence includes a team of data scientists, clinical analysts and software engineers based in Edinburgh collaborating with universities and hospitals. The team is developing tools to help clinicians create novel AI solutions using UK patient data for machine learning, together with infrastructure for data scientists to develop, train and validate algorithms without patient data leaving the hospital environment.
Picture: An AI imaging collaboration could speed up emergency department triage of suspected COVID-19 cases.
Published on page 9 of the April 2022 issue of RAD Magazine.