A machine learning model based on visualising data could help medical professionals identify coronavirus cases, differentiate them from other lung conditions and help to predict potential outcomes for patients.
The platform has been developed by Oxford-based Zegami and uses X-rays of Covid-19-infected lungs, applying artificial intelligence and data visualisation to analyse the images. Zegami says it can help to identify coronavirus cases and differentiate them from other lung conditions such as “bacterial pneumonia” and “viral pneumonia”.
As well as spotting Covid-19 cases more easily, it could help predict potential outcomes for patients by comparing their Covid-19 lung X-rays with previous patients with similar conditions and what eventually happened to them, based on different treatment options. However for the model to reach its potential, Zegami requires more images and data, and has called on the NHS to provide these.
Zegami is also offering its services for free in the fight against coronavirus. CEO Roger Noble said Zegami “is more than happy to work with them if the NHS finds it valuable,” reporting that they have already received a response to its open letter from NHSX, the organisation driving digital transformation in the NHS.
On how many images would be sufficient for the model, Noble says “a great starting point would be at least 1,000, and ideally with metadata such as patient age, gender, outcome, and so on. Similarly, 1,000 images each of other categories for ‘bacterial pneumonia’, ‘viral pneumonia’ and ‘healthy’. That way we can get a set of diverse and representative examples of all cases in order to make the machine learning model more robust.”
The firm believes it would only take a matter of weeks to have enough images of Covid-19 X-rays for the platform to become usable as a diagnostic tool.
Zegami is also keen to support researchers working in medical imaging to use its platform, especially those working in Covid- 19 research and similar global issues, and has launched Zegami Grants as a way of obtaining free access to the platform.
Noble added: “Covid-19 is a huge challenge, and technology should play a key role in defeating it. The model we develop could not only help our amazing NHS staff to make more informed decisions and potentially save lives, it could be shared around the world and play a role in helping to defeat Covid-19 on a global scale.”
The OxVent ventilator for Covid-19 patients, developed in just two weeks in March by engineers and medics in Oxford and London, is being tested for safety and usability at the Smith+Nephew medical manufacturing facility in Hull.
Matthew Cobb’s book charts the history of efforts to understand the brain and brings us up to date with the latest developments in neuroscience.