Posted Monday 25 October 2021
Kingston University researchers will examine whether artificial intelligence (AI) can be safely and effectively used to detect diabetic eye disease in an international project that could lead to the first widespread use of AI within the NHS.
Academics from the University's Faculty of Science, Engineering and Computing will be working with several partner institutions on the £500,000 project, funded by NHSX – an organisation that leads on digital transformation in the NHS – and the Health Foundation, and enabled by the National Institute for Health Research (NIHR).
Led by St George's, University of London and Moorfields Eye Hospital NHS Foundation Trust, the study will test AI technology trained to analyse retinal images from diabetic patients to detect diabetic retinopathy – a potentially sight-threatening diabetic eye disease – more efficiently and more quickly than human specialists.
As part of the project, the research teams will develop safeguarding systems to ensure AI performance does not vary across population sub-groups, such as ethnicity or gender. The study will also provide evidence to support the commissioning and deployment of the first potential widespread use of AI within the NHS.
Alongside St George's and Moorfields, the University will also be working with The Homerton University Hospital and the University of Washington in the United States on the project, which could provide major benefits for the NHS Diabetic Eye Screening Programme (DESP). The DESP generates millions of retinal images every year for early detection of diabetic eye disease - the leading causes of blindness in the working age population. Introducing AI to support healthcare professionals in screening work could potentially save the NHS more than £10m annually.
"There is huge potential for the rollout of artificial intelligence in healthcare applications," Kingston University's Professor Sarah Barman, who has been working with colleagues at St George's on AI development projects for a number of years, said. "However, we need to ensure that, as with any AI image analysis technologies, there is consistent performance across gender and ethnicity and through this project we will be providing a robust analysis of these AI algorithms to ensure they work across all populations.
"The really exciting part for me is that we will also be developing a framework for the continuous monitoring of the technology once in use that will ensure it is working equally well for everyone in practice."
The study will see the research teams create a data set of retinal images from different ethnic groups, genders and ages to ensure continued safety and confirm that anyone affected by diabetes in the UK will benefit. They will convene a group from North East London DESP including diabetic patients, a screening specialist, a consultant endocrinologist and a public health physician, informing the best way to use these systems within the NHS DESP.
Professor Paolo Remagnino, from Kingston University's Robot Vision team (RoViT), will be working with Professor Barman and a postgraduate researcher recruited for the project – building on a wide range of previous research into the potential applications of AI. "We are now at the point where artificial intelligence can be deployed in everything from smart farming to assisted living and security systems," he said. "With this project, we will be testing artificial intelligence systems that have been trained to spot the early signs of eye disease to ensure their trustworthiness for all patients, hopefully leading to the one of the first applications of AI in healthcare in the UK."
The NHSX and Health Foundation funding is part of a £1.4m award to a total of four projects that will help address racial and ethnic health inequalities using artificial intelligence.
Dr Indra Joshi, director of the NHS AI Lab at NHSX, said: "As we strive to ensure NHS patients are among the first in the world to benefit from leading AI, we also have a responsibility to ensure those technologies don't exacerbate existing health inequalities. These projects will ensure the NHS can deploy safe and ethical artificial intelligence tools that meet the needs of minority communities and help our workforce deliver patient-centred and inclusive care to all."