Need help? Call us 0800 032 9366
New eye test uses AI to predict AMD

New eye test uses AI to predict AMD

Monday 18 January 2021

Scientists at University College London (UCL) have collaborated with the Western Eye Hospital, London, to develop a pioneering new eye test that may predict wet age-related macular degeneration (AMD) three years before symptoms begin to develop.

The first part of the test is called Detection of Apoptosing Retinal Cells (DARC) and involves injecting a fluorescent dye into the bloodstream (via the arm) that attaches to retinal cells and illuminates those that are undergoing stress or in the process of apoptosis, making them appear bright white when examined under a fluorescent camera. These stressed retinal cells could lead to abnormal growth of blood vessels which then leak fluid into the retina. The more damaged cells detected, the higher the DARC count.

The second part of the test uses an Artificial Intelligence (AI) algorithm, which detects whether the highlighted white spots are located around the macula, indicating a high AMD risk. Specialists often disagree when viewing the same scans, so incorporating AI into the method ensures objectivity and consistency, as well as enabling analysis of thousands of images of the retina. AMD doesn't cause total blindness but it can make everyday activities like reading and recognising faces difficult. Wet AMD is the most common cause of permanent and severe sight loss in the UK, but current diagnosis of the disease relies upon a person seeking advice from a clinician once symptoms have already developed. Once the initial symptoms of visual distortion have presented themselves, this can progress very quickly to complete central vision loss.

Over 20 years ago, the disease was deemed to be untreatable, but scientific advances and new treatments have already led to greatly improved results for patients. However, patient outcomes could be better still if treatment was started in the very earliest stages of the disease.

Lead researcher Professor Francesca Cordeiro (UCL Institute of Ophthalmology, Imperial College London, and Western Eye Hospital Imperial College Healthcare NHS Trust) said, “Our results are very promising as they show DARC could be used as a biomarker for wet AMD when combined with the AI-aided algorithm. 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.”

Researchers say that this testing could be used to identify the disease early enough so that treatment can effectively prevent any vision loss and hope to continue their research with a clinical trial including more participants so that it can be used in medical settings in the future.


  1. UCL.
  2. Imperial.
  3. iNews.



◄ Blog Home

Subscribe to our email newsletter and claim your FREE copy of our popular guide '9 Top Tips to Save Your Sight'


  • Sharon Atkins
    03 Feb 2021

    My mother-in-law (who is 90 today 3/2/31) has wet AMD. She first became aware of this at aged 73, by which time it was too late and believe she had been suffering from it for years without knowing. My husband (her second son) is aged 64 and is already developing cataracts, albeit minimal, so I am wondering if he could assist in your research into AMD. Please let us know if we can help.

    Serious Readers reply:

    Hi Sharon Thanks for your comment and sorry to hear that your husband is developing cataracts. Serious Readers is a curator of this information and did not carry out the research noted in the article. You can find the contact details of the lead researcher at the following link:- Thanks

Post a comment…