The death of the retina cells at the back of the eye causes glaucoma. It is the leading global cause irreversible blindness affecting more than 60 million people. Experts predict that its number will double by 2040 as the global population ages.

Researchers have developed a quick test using artificial intelligence (AI) to identify which people with glaucoma are at risk of rapid progression to blindness. This new test can detect glaucoma progression 18months earlier than the current gold standard method.

DARC (Detection of Apoptosing Retinal Cells)

Results from a UCL-sponsored clinical trial are used to develop the new technology, supported by an artificial intelligence algorithm. According to the Wellcome-fund study published in Expert Review of Molecular Diagnostics, this technology can help accelerate clinical trials and may be used in detection and diagnostics.

"We have developed a quick, automated and highly sensitive way to identify which people with glaucoma are at risk of rapid progression to blindness," said Professor Francesca Cordeiro, the lead researcher from UCL Institute of Ophthalmology, Imperial College London and Western Eye Hospital Imperial College Healthcare NHS Trust.

They call the test Detection of Apoptosing Retinal Cells (DARC) which involves injecting a fluorescent dye into the bloodstream that will attach to retinal cells and illuminates those that are in the process of apoptosis or a form of programmed cell death.

When viewed in eye examinations, the damaged cells appear bright white. The more damaged cells detected, the higher will be the DARC count.

There were 20 participants with glaucoma and 40 healthy control subjects who participated in Phase II of the clinical trial where the AI was used. Initially trained by analyzing the retinal scans after injection of the dye on healthy control subjects, the AI was then tested on glaucoma patients.

Participants were followed up 18 months after the main trial period to check if their eye health condition had deteriorated. Every patient with an above the threshold of DARC was found to have progressive glaucoma at the follow-up.

This means that the researchers correctly predict progressive glaucomatous damage 18 months earlier compared with the current gold standard OCT retinal imaging technology.

Implications of their study

Professor Cordeiro said that the results of the study are very promising as they show DARC can be used as a biomarker when combined with the AI algorithm. Biomarkers are indicators of disease or state or severity, which are urgently needed for glaucoma, to speed up trials as it progresses slowly and can take years for the symptoms to change.

First author, Dr Eduardo Normando from the Imperial College London and Western Eye Hospital Imperial College Healthcare NHS Trust added that detecting glaucoma on its early stage and predicting its course of progression could help people maintain their eyesight. This is because the treatment provided at an early stage is most successful.

The researchers are also applying the test to rapidly detect cell damage caused by many conditions other than glaucoma like the neurodegenerative conditions that involve the loss of nerve cells in the age-related macular degeneration, multiple sclerosis, and dementia.

The UK's Medicines and Healthcare products Regulatory Agency and the USA's Food and Drug Administration recently approved the AI-supported technology as an exploratory endpoint for testing a new glaucoma drug in a clinical trial.

They also hope to utilize the technology in people with lung disease and hope that it may help assess people with breathing difficulties from COVID-19 by the end of the year.