The latest artificial intelligence technology brings together data from thousands of patients to better inform COVID-19 diagnostic and treatment pathways
Patients with COVID-19 are set to benefit from faster treatment, improved outcomes, and shorter hospital stays thanks to the use of the latest artificial intelligence (AI) technology.
NHSX, a unit tasked with driving the digital transformation of care in the NHS, has brought together more than 40,000 CT scans, MRIs, and X-rays from 10,000 patients across the UK during the course of the pandemic.
And access to this National COVID-19 Chest Imaging Database (NCCID) has now been extended to hospitals and universities across the country who are using the images to track patterns and markers of illness.
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.
Matt Hancock, Secretary of State for Health and Social Care, 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.
We are applying the power of artificial intelligence to quickly detect disease patterns and develop new treatments for patients
“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.”
Clinicians at Addenbrooke’s Hospital in Cambridge are developing an algorithm based on the NCCID images to help inform a more-accurate diagnosis of patients when they present to hospital with potential COVID-19 symptoms and have not yet had a confirmed test.
Using visual signatures of the virus, as they appear in chest scans, they are able to compare the patterns in the patient’s imaging with those seen previously in the NCCID to get a more-accurate diagnosis and prognosis.
Understanding the earlier stages of disease means that clinicians are more easily able to implement appropriate, early medical interventions, reducing the potential for later complications.
This includes giving patients oxygen and medication before they reach a critical stage, and predicting the need for additional ICU capacity, enabling the management of beds and staff resource in those settings.
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
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 has 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.”
The NCCID is also helping researchers from University College London and the University of Bradford, to develop AI tools that could help doctors improve the treatment for patients with COVID-19.
The database is helping to inform the development of a potential national AI imaging platform to safely collect and share data, developing AI technologies to address a number of other conditions such as heart disease and cancers.
The NCCID is one workstream taken forward by the NHS AI Lab at NHSX.
The lab has also set up and launched a £140m AI Award this year in collaboration with the Accelerated Access Collaborative (AAC) and National Institute for Health Research (NIHR), which aims to bring the benefits of AI technologies to patients and staff across health and care.
This is precisely the initiative we need to ensure we are better prepared and more responsive for future pandemics
Initial bids were awarded to 42 organisations in September, with a further round of bids closing last month.
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.”
Evis Sala, Professor of Oncological Imaging at the University of Cambridge, added: “This is precisely the initiative we need to ensure we are better prepared and more responsive for future pandemics.”
And Dr Joe Jacob, consultant radiologist and research lead at BSTI, said: “The National COVID-19 Chest Imaging Database was developed with the support and enthusiasm of chest radiologists and healthcare professionals from around the United Kingdom.
“Their efforts have helped to provide a resource that will help the NHS in the management of the healthcare emergency engendered by COVID-19.”
NHSX was able to quickly establish the project during the spring by working closely with Royal Surrey NHS Foundation Trust to scale up an existing data collection process.
Dr Mark Halling-Brown, head of scientific computing at Royal Surrey County Hospital, said: “We have led the way in creating and sharing research imaging databases that have enabled the development of AI tools, and have, more recently, specialised in the evaluation and validation of AI radiology products within a range of specialties supporting their safe deployment into the clinic.
“Our expertise allowed us to help build the National COVID-19 Chest Imaging Database and we are excited by the potential of the AI solutions being developed and the research underway that will use this dataset.”