Early detection of glaucoma thanks to artificial intelligence

The technology, backed by an artificial intelligence (AI) algorithm, could help speed up clinical trials and, over time, could be used in detection and diagnosis, according to the Wellcome-funded study published in the Expert Review of Molecular Diagnostics.

Lead researcher Professor Francesca Cordeiro (UCL Institute of Ophthalmology, Imperial College London and Western Eye Hospital Imperial College Healthcare NHS Trust) commented: ‘We have developed a fast, automated and highly sensitive way to identify which people with glaucoma are at risk of suffer a rapid progression to blindness’.

Glaucoma, the world’s leading cause of irreversible blindness, affects more than 60 million people, which is projected to double by 2040 as the world’s population ages. Vision loss in glaucoma is caused by the death of cells in the retina, at the back of the eye.

More information: Glaucoma: what it is, causes, symptoms, dangers and its treatment

The test, called DARC (Detection of Apoptosing Retinal Cells), consists of injecting into the bloodstream (through the arm) a fluorescent dye that attaches to retinal cells and illuminates those that are in the process of apoptosis, a form of death. programmed cell phone. Damaged cells appear bright white when seen on eye exams – the more damaged cells detected, the higher the DARC count.

One challenge in evaluating eye disease is that specialists often disagree when viewing the same retinal images, so the researchers have incorporated an AI algorithm into their method.

In the DARC phase II clinical trial, AI was used to evaluate 60 of the study participants (20 with glaucoma and 40 healthy control patients). The AI ​​was initially trained by analyzing the retinal scans (after injection of the dye) of healthy control subjects and then the AI ​​was tested in glaucoma patients.

Study participants were monitored 18 months after the main test period to see if their eye health had deteriorated.

The researchers were able to accurately predict progressive glaucomatous damage 18 months earlier than seen with current standard OCT retinal imaging technology, as every patient with a DARC count above a certain threshold was found to have progressive glaucoma at follow-up.

‘These results are very promising as they show that DARC could be used as a biomarker when combined with the AI-assisted algorithm,’ comments Professor Cordeiro, and biomarkers (measurable biological indicators of disease status or severity), They are urgently needed to be printed to analyze glaucoma and thus accelerate clinical trials, since we are facing a disease that progresses slowly, so it can take years for symptoms to change.

“What’s really exciting, and really unusual when looking at biomarkers, is that there was a clear DARC count threshold above which all eyes with glaucoma confirmed progression of the disease,” he added.

First author Dr Eduardo Normando (Imperial College London and Western Eye Hospital Imperial College Healthcare NHS Trust) said: “Being able to diagnose glaucoma at an earlier stage and predict its course of progression could help people preserve your eyesight, as treatment is most successful if it is provided early in the disease. ‘

The team is also applying the test to rapidly detect cell damage caused by numerous conditions other than glaucoma, such as other neurodegenerative conditions that involve nerve cell loss, including age-related macular degeneration, multiple sclerosis and dementia.

The AI-backed technology has recently been approved by the UK Medicines and Healthcare Products Regulatory Agency and the US Food and Drug Administration, allowing them to begin testing a new glaucoma drug in a trial. clinical.

Researchers are also evaluating the DARC test in people with lung disease, and they hope that, by the end of this year, the test can help evaluate people with breathing difficulties for Covid-19.

DARC is being commercialized by Novai, a newly formed company of which Professor Cordeiro is Scientific Director.

Link to the study: A CNN-aided method to predict glaucoma progression using DARC (Detection of Apoptosing Retinal Cells)