AI research in Cambridge to help guide Covid-19 diagnosis and prognosis for Addenbrooke’s patients
Artificial intelligence is to be used to help diagnose patients with Covid-19 before they have had a confirmed test - and provide a better understanding of their prognosis to guide treatment.
Scientists and clinicians in Cambridge are developing an algorithm based on a massive dataset from the National COVID-19 Chest Imaging Database (NCCID).
This database features 40,000 CT scans, MRIs and X-rays from more than 10,000 patients across the UK, brought together during the pandemic by NHSX, the unit tasked with the digital transformation of NHS care.
Access to it has been given to hospitals and universities to help them track patterns and markers of illness.
At Cambridge University Hospitals, the aim is to enable a more accurate diagnosis of patients when they present at Addenbrooke’s with Covid-19 symptoms but have yet to have confirmed test results back.
Comparing patterns in the patient’s imaging with visual signatures of the virus seen in chest scans in the database allows a diagnosis to be made and the prognosis predicted.
Carola-Bibiane Schönlieb, professor of applied mathematics and head of the Cambridge Image Analysis group at the University of Cambridge, said: “The NCCID has been invaluable in accelerating our research and provided us with a diverse, well-curated, dataset of UK patients to use in our algorithm development.
“The ability to access the data for 18 different trusts centrally has increased our efficiency and ensures we can focus most of our time on designing and implementing the algorithms for use in the clinic for the benefit of patients.
“By understanding in the early stages of disease, whether a patient is likely to deteriorate, we can intervene earlier to change the course of their disease and potentially save lives as a result.”
Implementing appropriate, early interventions can reduce the chances of complications later. It could involve giving patients oxygen and medication before they reach a critical stage.
The technology can also help hospital trusts predict the need for additional ICU capacity, enabling better management of beds and staff resources.
Evis Sala, professor of oncological imaging at the University of Cambridge, said: “The NCCID team have been extremely knowledgeable, helpful and responsive to our questions throughout the process. This is precisely the initiative we need to ensure we are better prepared and more responsive for future pandemics.”
Meanwhile, the NCCID is also helping researchers at University College London and Bradford to develop AI tools to help doctors improve treatments for Covid-19 patients.
Its creation will also inform the development of a potential national AI imaging platform, from data would be safely shared to help tackle conditions from heart disease to cancer.
Dominic Cushnan, head of AI imaging at NHSX, said: “We are applying the power of artificial intelligence to quickly detect disease patterns and develop new treatments for patients. “There is huge potential for patient care, whether through quicker analysis of chest images or better identification of abnormalities.
“The industrial scale collaboration of the NHS, research and innovators on this project alone has demonstrated the huge potential and benefits of technology in transforming care.”
Led by NHSX, the NCCID is a collaboration with the British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and London-based AI specialist Faculty. Identifying details of patients are stripped by hospitals before scans are submitted to the collection. Among the trusts submitting data to the NCCID are Cambridge University Hospitals and West Suffolk NHS Foundation Trust.
Health secretary Matt Hancock said: “The use of artificial intelligence is already beginning to transform patient care by making the NHS a more predictive, preventive and personalised health and care service.
“It is vital we always search for new ways to improve care, especially as we fight the pandemic with the recovery beyond. This excellent work is testament to how technology can help to save lives in the UK.”
The NHS AI Lab at NHSX has also launched a £140million AI award in collaboration with the Accelerated Access Collaborative and National Institute for Health Research. Initial bids were awarded to 42 organisations last September, with a further round of bids closing last month.
Sign up for our weekly newsletter for a digest of the latest Cambridge science direct to your inbox every Friday