St. George’s, University of London and Moorfields Eye Hospital NHS Foundation Trust are leading a half a million pound artificial intelligence (AI) project funded by the NHSX and the Health Foundation and supported by the National Institute for Health Research (NIHR). The research project will use AI technology to analyze retinal images of diabetics in order to identify visually impaired diabetic eye diseases more efficiently and faster than human specialists. It is critical that the project develop safety systems to ensure that it works for everyone and that AI performance does not vary between population sub-groups such as ethnicity or gender. The project will also provide evidence to support the start-up and deployment of the first potential widespread use of AI within the NHS.
Researchers at St. George’s and Moorfields have already shown that automated retinal image analysis systems using AI can indeed be a safe and inexpensive alternative. This could be of great benefit to the NHS Diabetic Eye Screening Program (DESP), which takes millions of retinal images every year for the early detection of diabetic eye disease – the leading causes of blindness in the working-age population. Given the cost and number of screening episodes, the savings could be more than £ 10 million each year in England alone.
Concerns have been raised about AI image recognition technologies such as: B. Face recognition, which varies in performance depending on gender and ethnicity. Researchers from St. George’s and Moorfields will create a database of retinal images of various races, genders and ages to ensure continued safety and confirm that everyone with diabetes in the UK will benefit. They will convene a group from North East London’s DESP, including diabetics, a screening specialist, a consulting endocrinologist and a public health doctor, to provide information on how best to use these systems within the NHS DESP.
It is vital that the first large-scale deployment of AI in the NHS is safe and high performing across the board. This project will develop the essential security tools and monitoring systems necessary to verify the post-deployment performance of the AI to ensure trustworthy AI for the benefit of all patients. “
Professor Adnan Tufail, Consultant Ophthalmologist at the NIHR Biomedical Research Center at Moorfields Eye Hospital and the UCL Institute of Ophthalmology
“The important thing is that this project will also be independent of commercial interests,” said Professor Alicja Rudnicka, Professor of Statistical Epidemiology at St. George’s University of London. “We will also assess the perception, acceptance and expectations of health professionals and people with diabetes regarding the implementation of AI technology within DESP in North East London. In addition, the methods and standards we develop will be transferable to other healthcare areas to build trust. “Advance in AI technology in healthcare.”
This project will begin in 2021 in collaboration with Homerton University Hospital, Kingston University and the University of Washington, USA.
Source:
St. George’s, University of London
