IMC Newsdesk

NHS tests AI for detecting breast cancer

  • September 15, 2020
  • Steve Rogerson

Patients of the UK National Health Service (NHS) could benefit from artificial intelligence (AI) technologies for detecting breast cancer thanks to a £50m boost announced this month.

AI-powered innovations that can rapidly and accurately analyse breast cancer screening scans and assess emergency stroke patients will be tested and scaled, helping clinicians deliver the right treatment faster.

Take-home technology could also see patients given devices and software that can turn their smartphones into clinical grade medical devices for monitoring kidney disease, or a wearable patch to detect irregular heartbeats, one of the leading causes of strokes and heart attacks.

The creation of the NHS AI Lab provided tools and products as part of the £140m AI in Health and Care Award programme, each receiving a share of over £50m. The award is managed by the Accelerated Access Collaborative in partnership with NHSX and the National Institute for Health Research.

The package also includes funding to support the research, development and testing of promising ideas that could be used in the NHS in future to help speed up diagnosis or improve care for a range of conditions including sepsis, cancer and Parkinson’s.

Sir Simon Stevens, NHS chief executive, said: “The NHS has and always will rely first and foremost on the clinical expertise of our staff, but the innovations we’re funding have the potential to save lives by improving screening, cancer treatment and stroke care for NHS patients across the country.”

The announcement supports a range of technologies at different stages of development, from initial concepts to real-world tests. AI products will be trialled in several NHS organisations before potentially being adopted across the health service. Each product will undergo robust testing and independent evaluation to ensure they are effective, accurate, safe and value for money.

“Throughout the pandemic, the NHS has shown how digital technology can transform the service it provides, quickly and safely, but we have a long way to go,” said Matthew Gould, chief executive of NHSX. “The NHS AI Lab was set up to drive the adoption of data-driven technologies, with the goal of enhancing the care our staff can give their patients, and these awards should give that effort a serious boost.”

Subject to contracting, successful products to be spread include:

  • Healthy IO will spread its AI powered app that turns a smartphone into a clinical grade medical device capable of detecting albuminuria, an early warning sign of chronic kidney disease that could help patients with diabetes.
  • Irhythm Technologies will spread its wearable ECG monitoring patch and service that uses AI-led processing and analysis to help diagnose atrial fibrillation.
  • Brainomix will share its digital tools, used to assess emergency stroke patients, to a number of NHS sites following recent successful deployment at Royal Berkshire NHS Trust.

The NHS will also support the first real-world tests of technologies including a system that can detect prostate cancer in biopsy tissue slides, and a device that uses an algorithm to immediately diagnose heart failure.

An AI platform that can predict heart disease will be implemented in NHS hospitals. The platform, called EchoGo from Ultromics, uses machine learning algorithms to analyse ultrasound scans of the heart. This enables doctors to diagnose heart disease more efficiently and prevent heart attacks.

Ultromics is a cardiac health-tech company based in Oxford. The company was co-founded by CEO Ross Upton during his PhD studies at the University of Oxford, and Paul Leeson, Ultromics’ CMO, professor of cardiovascular medicine at the University of Oxford. Ultromics was spun out of the university in 2017.

The company is one of the first winners of the AI in Health & Care Award and will receive a share of the funding totalling over £50m.

“AI can both help protect and transform the NHS,” said Upton. “Post Covid-19, it has become even more evident that the NHS needs to find new ways of working. This initiative embraces the potential offered by AI to ease current difficulties in healthcare delivery with more accurate and faster diagnosis, and to significantly improve patient care and outcomes.”

The NHS has identified 42 technologies to test in four phases of development, with EchoGo selected in both phases three and four, which are focused on technologies closest to market and scaling-up for full adoption by health providers.

Phase one supports the demonstration of the technical and clinical feasibility of the proposed concept, product or service. Phase two supports the development and evaluation of prototypes and generates early clinical safety and efficacy data. Phase three supports the first real-world tests in health and social care settings of AI products or tools to develop evidence of efficacy and preliminary proof of effectiveness, including evidence for routes to implementation to enable rapid adoption.

Phase four supports the spread of AI products or tools that have market authorisation but insufficient evidence to merit large-scale commissioning or deployment. Successful products will be adopted in a number of NHS sites to stress test and evaluate the AI technology within routine clinical or operational pathways to determine efficacy or accuracy, and clinical and economic impact.