Artificial Intelligence helping diabetic patients keep their sight

Pilot project has 96 per cent success rate in helping doctors diagnose eye disease at Dubai Diabetes Centre

Artificial intelligence is helping doctors accurately diagnose eye disease in 96 per cent of cases at Dubai Diabetes Centre.

Thousands of routine eye scans have been fed into an AI programme to identify retinal damage caused by diabetes in a trial during February — UAE Innovation Month.

The programme’s success could now lead to it being permanently adopted at the centre in 2nd of December Street, as it is helping doctors treat more patients at an earlier stage.

“To diagnose diabetic retinopathy, regular retinal imaging is required and in some cases optical coherence tomography is also used,” said Dr M Hamed Farooqi, director of Dubai Diabetes Centre.

“This imaging test provides cross-sectional images of the retina that show the thickness of the retina, which will help determine whether fluid has leaked into retinal tissue.”


Read more:

The machines are taking over: how AI will change life in the UAE over the next 50 years

Governments must control the rise of artificial intelligence, experts say 


Diabetic retinopathy is a diabetes complication that affects eyes and is caused by damage to the blood vessels of light-sensitive tissue at the back of the eye.

At first, diabetic retinopathy may cause no symptoms or only mild vision problems, but can develop into blindness.

This initiative aims to utilise an AI programme to identify retinal damage from the thousands of eye scans fed into it, hence aiding doctors in diagnosing and treating patients who are suffering from retinal damage effectively and quickly.

The second phase of the Dubai Diabetes Survey 2017 revealed that the total prevalence of diabetes among Emiratis in Dubai is 19 per cent, while the total number of undiagnosed diabetes cases of Emiratis is 11 per cent and the rate of pre-diabetic Emiratis is 18.6 per cent.

Usually, seven pictures of each eye are needed to diagnose retinal damage — that means doctors must go through thousands of scans to diagnose patients.

The AI programme makes that process faster, and more accurate.

Dubai Diabetes Center provided images that were fed into an AI programme developed by local firm Artelus LLC.

These images were already diagnosed by the retina experts at Dubai Hospital and were compared with the diagnosis of the AI programme.

The accuracy of the programme’s diagnosis of retinal damage reached 96 per cent of all referable cases in comparison. The more scans are fed to the programme the more accurate the diagnosis will be.

“These positive results will be considered in possibly adopting this programme at the centre,” Dr Farooqi said.