Moorfields Eye Hospital is sharing one million people's eye scan data with Google Deepmind in an attempt to detect common eye diseases much earlier.
DeepMind will apply its AI algorithms to the anonymised scans to see if it can help research into detecting wet age-related macular degeneration and diabetic retinopathy.
Together, these conditions affect 625,000 people in the UK, while two million people in the UK have sight loss, 360,000 of whom are registered as blind or partially sighted. Diabetic retinopathy affects around 350 million people worldwide.
Doctors rely on digital scans to diagnose these common eye conditions, and also use them to decide what form of treatment best suits the patient. However, the scans are complex and existing analysis tools have not been able to fully explore the data they contain.
Meanwhile, the length of time needed to properly analyse the scans means patients must wait longer to discuss the diagnosis and proposed treatments with their doctors.
DeepMind and Moorfields are working on a research project that aims to solve this problem by seeing whether artificial intelligence can act as a better analysis tool for eye scans, in the hope it will speed up diagnoses and treatment decisions.
Professor Sir Peng Tee Khaw, director of the National Institute for Health Research Biomedical Research Centre in Ophthalmology at Moorfields Eye Hospital, 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."
Moorfields is sharing one million anonymised scans that have been collected over time with DeepMind, as well as anonymous clinical diagnoses and demographic data.
DeepMind will feed this data into a machine learning algorithm, along with information on the treatment of eye diseases and a model of the machine that took the images, to see whether it can improve on the hospital's own methods of analysis.
Mustafa Suleyman, co-founder of DeepMind, said: "We set up DeepMind because we wanted to use AI to help solve some of society's biggest challenges, and diabetic retinopathy is the fastest growing cause of blindness worldwide. I'm really excited to announce this collaboration with leading researchers at Moorfields.
"Detecting eye diseases as early as possible gives patients the best possible chance of getting the right treatments. I really believe that one day this work will be a great benefit to patients across the NHS."
The NHS previously caused controversy when it emerged in May that the Royal Free NHS Trust had signed a deal with DeepMind to share 1.6 million records of patients attending its hospitals.
The data was fuelling the design of an app called Streams, meant to help staff monitor patients with kidney disease.
This time around, Moorfields was clear the data is anonymised, saying: "This [data] has been collected over time through routine care, which means it's not possible to identify any individual patients from the scans. And they're also historic scans, meaning that while the results of our research may be used to improve future care, they won't affect the care any of our patients receive today."
