AI eye screening 'did not miss a single urgent case'

Published on 15th August 2018

A study by Moorfields Eye Hospital in London and the Google company DeepMind found that a machine could learn to read complex eye scans and detect more than 50 eye conditions.

The machine was trained by 'learning' from thousands of eye scans and was able to find the patterns and key characteristics of different eye conditions. It was then pitted against humans, and didn't miss a single urgent case. 

Dr. Pearse Keane, who published the information in the scientific journal 'Nature Medicine', is excited where this technology could go and how it could help eye screenings. "Every eye doctor has seen patients go blind due to delays in referral; AI should help us to flag those urgent cases and get them treated early."

"We really want to get this into clinical use within two to three years but cannot until we have done a major real-time trial to confirm these exciting findings."

Dr. Keane has proposed that this new technology will alleviate some the pressure and burden on clinicians and allow them to focus on the more urgent cases. 

For more information about the programme, click here.

Back to latest news