Google DeepMind and Moorfields Eye Hospital develop artificial intelligence to assist with diagnosis of eye disease

Posted: 06/02/2018

Google has developed artificial intelligence (AI) which, following collaborative research between its sister company ‘DeepMind’ and Moorfields Eye Hospital, has shown “promising signs” of being able to provide early diagnosis of eye disease.

At the moment diagnosis of eye disease is a complicated process that often requires specialists to examine and interpret various scans, each taking a considerable amount of time. Any delays could lead to deferred diagnosis and treatment.

The newly developed AI technology works by training an algorithm that uses thousands of anonymised 3D retinal scans to identify signs of three of the most common eye diseases, glaucoma, age-related macular degeneration and diabetic retinopathy, so that it is able to detect patterns and reach a diagnosis. The algorithm is reportedly able to spot signs of these diseases faster and more efficiently than a human specialist.

Explaining the idea behind the technology, Professor Sir Peng Tee Khaw, director of research and development at Moorfields, said: “An ageing and growing world population could lead to a threefold increase in blindness by 2050, so it is vital we explore the use of cutting-edge technology to… diagnose and treat eye conditions early.” He goes on to say that he is ‘optimistic’ that the research could prevent people around the world from suffering avoidable sight loss.

The findings of the two year project have been submitted to a medical journal, and it is hoped that they will be published by the end of 2018. The technology could enter clinical trials in a few years if results pass a peer review by academics.

Arran Macleod, an associate in the clinical negligence team at Penningtons Manches, comments: “There are a number of types of eye disease that cause loss of vision and with many of these, the damage is irrecoverable so it is vital to diagnose and treat the condition as early as possible.

“We act for many patients who have suffered damage to their vision because of a delay in their diagnosis or in receiving treatment. They often find it difficult to accept when their lost vision has been caused by an avoidable and negligent delay. We therefore fully support the safe introduction of AI into healthcare to assist with earlier diagnosis of eye disease. If the technology is successful, it will be a giant leap forward for patients to have their eyes routinely tested for difficult eye conditions, and to receive treatment earlier than they would otherwise have done under traditional diagnostic methods. We await the safe development of this technology with interest.” 

Return to news headlines