Future Covid-19 patients may be identified by AI

NHS is using a national database of anonymous scans to develop the algorithm

Published: 16 February 2021 Learning

AI is to be used to help identify Covid-19 patients who present at hospital without a confirmed test.

Addenbrooke’s Hospital in Cambridge is developing an algorithm based on the National Covid-19 Chest Imaging Database (NCCID) images, a database of over 40,000 CT scans, MRIs and X-rays from more than 10,000 patients across the UK.

The algorithm is to be designed to identify visual signatures of the virus by comparing the patient’s scan with those from the NCCID for a more accurate diagnosis and prognosis.

It is hoped the ‘database can speed up diagnosis of Covid-19, leading to a quick treatment plan and greater understanding of whether the patient may end up in a critical condition,’ said a government statement.

The anonymised data is being collected from 20 trusts throughout the pandemic. It is held by The NHS AI Lab at NHSX. NHSX is a unit tasked with driving the digital transformation of care in the NHS, and NHS AI Lab aims to overcome challenges faced by using AI in healthcare from health and care providers, government, companies and academia.

Using AI to improve treatment for Covid-19 patients, is being developed by universities in London and Bradford, which are using the NCCID, as well as other conditions such as cancer.