Google DeepMind AI partners with NHS to help tackle eye disease
Google DeepMind has announced a brand new research project in partnership with the NHS. The collaboration will see Google’s artificial intelligence division working with London’s Moorfields Eye Hospital to develop a machine learning system that will detect the early signs of degenerative eye conditions which humans might miss.
Though this is the second project DeepMind is embarking on with the NHS, it’s the first time the company has used machine learning in purely medical research and DeepMind co-founder Mustafa Suleyman says he thinks “one day this work will be a great benefit to patients across the NHS.”
Moorfields says that analysing complex eye scans is a time consuming process and traditional analysis tools have been unable to explore them fully. It hopes the research with DeepMind will lead to earlier detection and more effective treatment for patients and ultimately help to avoid cases of preventable eye disease.
Professor Sir Peng Tee Khaw, Director of the Ophthalmology Research Centre at Moorfields said: “Our research with DeepMind has the potential to revolutionise the way professionals carry out eye tests and could lead to earlier detection and treatment of common eye diseases such as age-related macular degeneration. With sight loss predicted to double by the year 2050 it is vital we explore the use of cutting-edge technology to prevent eye disease.”
To help get the project going, Moorfields has shared around one million anonymised digital eye scans with DeepMind as well as anonymous information about eye condition and disease management that the hospital has gathered over time through routine care.
The last time DeepMind collaborated with the NHS, it and the Royal Free Trust were accused of not having the proper authority to share patient records, going against patients’ best interests and breaching their trust. At the time of the controversy the Royal Free said that encryption ensured that “absolutely no patient-identifiable data is shared with DeepMind.”
This time, though, there are less privacy hurdles as the scans are completely anonymous. Moorfields and Google have stated that though the scans are from real patients it would be impossible to identify any individual patient’s identity and as the scans are historical their use won’t affect the care any current patients are receiving.
Instead, the hope is that the DeepMind researchers will be able to use the scans to train an algorithm to spot the early signs of two common diseases in particular: wet age-related macular degeneration and diabetic retinopathy, the latter of which Mustafa Suleyman says is the fastest growing cause of blindness worldwide.