JUL 06, 2016
Comprehensive Ophthalmology, Retina/Vitreous
Moorfields Eye Hospital is working with Google’s artificial intelligence division to develop an algorithm to better screen for early AMD and diabetic retinopathy.
Under the 5-year agreement, Moorfields will share 1 million fundus images and OCT scans with Google’s DeepMind, along with information about eye condition and disease management collected over time through routine care.
Google's DeepMind Health will use the anonymous scan results to search through and discover ways it could speed up and improve the detection process.
"Our research with DeepMind has the potential to revolutionize the way professionals carry out eye tests and could lead to earlier detection and treatment of common eye diseases. 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," said Professor Sir Peng Tee Khaw, Director at Moorfields Eye Hospital and University College of London Institute of Ophthalmology.
The partnership has sparked some criticism over the sharing of patient data with Google. But the companies have stressed that the huge number of scans involved means it will not be possible to pick out individuals from the records. The terms of the agreement state that the records can be shared as long as they are encrypted and cannot be read by Google employees.
“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,” said Mustafa Suleyman, co-founder of DeepMind. “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 National Health Service.”