A new artificial intelligence (AI) eye test can predict a condition that can progress to blindness, a recent study has determined.
Researchers from Imperial College London and University College London (UCL) conducted a clinical trial using a retinal imaging technology known as Detection of Apoptosis in Retinal Cells ( DARC). When tested on 113 patients in the trial, the technology was able to identify areas of the eye that showed signs of geographic atrophy (GA) – a common condition that causes reduced vision and blindness.
The results of the study have been published in Advances in research on the retinal eye.
Currently, early detectable symptoms and predictors of GA are limited, making it difficult to identify the disease early enough to avoid vision loss. The researchers behind the study hope the technology can be used as a screening test for knee OA and aid in the development of new treatments for the disease.
Age-related macular degeneration and geographic atrophy
Age-related macular degeneration (AMD) is the most common blindness in people over 55 and AG is an advanced form of AMD. GA affects 700,000 people in the UK and the incidence is expected to double over the next 25 years. AG develops over several years and can lead to progressive and irreversible vision loss. Although there is no cure, early detection is critically important as there are potential treatments that could prevent severe vision loss or slow disease progression, such as eye injections and tablets. .
Professor Francesca Cordeiro, lead author of the study and chair and professor of ophthalmology at Imperial College London, said: “Geographic atrophy is one of the main causes of reduced vision, and in some cases blindness in the developed world. This can have a significant impact on patients’ quality of life, as tasks such as reading, driving and even recognizing familiar faces become more difficult as the disease progresses.
“As life expectancy in developed countries continues to increase, the incidence of knee OA has increased.
“Early detection is a key defense against this disease but, as symptoms develop over several years, the condition is often detected once the disease has progressed to a more advanced stage.
“Our study is the first to show that DARC technology can be used to predict whether a patient is at risk of developing GA. These results will help clinicians intervene with treatments to slow vision loss and manage the disease at an early stage. We also hope this technology can be rolled out to street opticians and used as a screening test in primary care settings.
The DARC method visualizes diseased and dying cells on the retina – a thin layer of tissue that lines the inside of the back of the eye and sends visual information to the brain. Rather than providing an estimate of healthy cells, DARC highlights unhealthy and diseased cells, to give an indication of disease activity.
The test involves injecting a fluorescent dye into the bloodstream (via the arm) that attaches to retinal cells and illuminates those that are under stress or cell death. Damaged cells appear bright white when observed during eye examinations – the more damaged cells detected, the higher the number of DARCs. The researchers also incorporated an AI algorithm developed by Professor Cordeiro to rigorously count and evaluate DARC spots, as specialists often disagree when viewing the same scans. Previous clinical trials have shown that the test can predict the progression of glaucoma and new areas of wet AMD.
For the new study, researchers recruited 113 patients at Western Eye Hospital, part of Imperial College Healthcare NHS Trust, in 2017. 19 patients had early signs of wet AMD and 13 patients had early signs of AG . To assess various conditions, the team also recruited from three different groups: healthy volunteers, patients with progressive glaucoma, optic neuritis (as a model of multiple sclerosis) and Down syndrome, where the pathology would be similar to Alzheimer’s disease.
All patients were screened using the DARC method and then followed up with optical coherence computed tomography (OCT) scans, to visualize eye health, every six months for a period of three years. The researchers then compared the DARC scans with the baseline OCT scans to assess the ability of DARC to predict GA expansion.
The researchers found that the level of DARC was predictive of GA. Patients with DARC count greater than 10 were found to have increased GA expansion three years later.
Now the team plans to further validate their findings in larger clinical trials starting in the UK later this year.
Recommended related articles