Artificial intelligence may diagnose the leading cause of blindness much earlier

Artificial intelligence is able to analyze vast amounts of information very quickly and efficiently. And, therefore, unsurprisingly it is very useful in medicine. Scientists from UCL and the Western Eye Hospital have now developed a new eye test, which takes advantage of AI technology to predict wet age-related macular degeneration three years before symptoms develop.

Age-related macular degeneration is the leading cause of blindness in the Western world. Image credit: BruceBlaus via Wikimedia (CC BY-SA 4.0)

Wet age-related macular degeneration (AMD) is the leading cause of severe sight loss. It can be diagnosed rather well, but diagnosis relies on a person developing symptoms, which then leads them to seek advice from a clinician. In other words, AMD is diagnosed only when the vision loss has already started. Wet AMD involves  abnormal growth of blood vessels leaking fluid into the retina. It can be treated, but only if it is diagnosed early. And that's where the new test, called Detection of Apoptosing Retinal Cells (DARC) comes in.

DARC involves injecting a fluorescent dye into the bloodstream of the patient. This dye latches onto the retinal cells, illuminating those that are under stress or affected by apoptosis. Cells damaged in this way are illuminated in a bright white colour, which can be seen in a normal eye examination. A specialist can then count those damaged cells, reaching some sort of a DARC count, which is then a good predictor of the age-related macular degeneration. This process is actually very difficult and t specialists often disagree when viewing the same scans, which is why scientists incorporated AI into this method. It simply creates a more objective result, which can then be analysed and attached to diagnosis.

While testing DARC scientists  assessed 19 of the study participants who had already shown signs of AMD, but not necessarily in both eyes. These tests showed that DARC is an effective way to diagnose wet AMD early. 

Professor Francesca Cordeiro, lead researcher of the study, said: “Our new test was able to predict new wet AMD lesions up to 36 months in advance of them occurring and that is huge – it means that DARC activity can guide a clinician into treating more intensively those patients who are at high risk of new lesions of wet AMD and also be used as a screening tool.” The next step for this study is a clinical trial with more participants. DARC is already being commercialised, but more extensive trials could help dialing the quality of the test much closer to what it needs to be.

Hopefully, DARC will become that necessary push towards tackling the leading cause of blindness in our societies. It is a relatively easy test, which could spread across hospitals very quickly. In the future it could help prevent many cases of blindness, improving chances of elderly to take care of themselves.


Source: UCL