Optical coherence tomography (OCT) is a type of retinal imaging technology that’s commonly used for detecting damage by glaucoma. A new test that uses artificial intelligence (AI) can detect damage one and a half years sooner than OCT.*

The Detection of Apoptosing Retinal Cells (DARC) test, used by researchers in a study in the Expert Review of Molecular Diagnostics, injects fluorescent dye into the bloodstream. The role of the dye is to attach to retinal cells and illuminate cells in the process of apoptosis, or cell death. This enables clinicians to visually detect disease progression during eye examinations. A higher number of damaged cells indicates a higher DARC count.

Since glaucoma is notorious for being a leading cause of irreversible blindness, AI-enabled technology could be a tool to reduce the occurrence of such damage.

What they did

Researchers evaluated 20 individuals with progressing glaucoma and 40 healthy control subjects via DARC and the new algorithm. The researchers looked at baseline infrared images before administering fluorescent liquid. After injecting with the dye, images were taken after 15 minutes, two (2) hours, and four (4) hours. They were then fed into the AI-based algorithm.

The researchers analyzed 58,730 apoptotic cells taken from baseline images and fed the majority into the algorithm.

What they found

After 18 months, the researchers followed up with participants to determine if their health had deteriorated and whether the algorithm accurately predicted glaucoma progression. According to the authors, the algorithm found “DARC count was…significantly higher in patients who were later found to be progressing at 18 months compared to those who were stable.”

The DARC count acts as a reliable biomarker that indicates the risk of progressive glaucoma. For example, after 18 months, stable eyes did not have a CNN DARC count above 30. The hope is that the technology aids in accelerating clinical trials for glaucoma treatments and may eventually be used in diagnostic methods.

In recognizing the promising results, the AI-supported technology has been approved by the United Kingdom’s Medicines and Healthcare products Regulatory Agency (MHRA), as well as the United States’ Federal Drug Administration (FDA) as an “exploratory endpoint for testing a new glaucoma drug in a clinical trial.”

What it means

Future longitudinal studies are needed to further validate the findings and to understand the viability of the test in rapidly detecting damage from other conditions, like age-related macular degeneration, multiple sclerosis, and dementia. It’s even being used for detecting lung disease and assessing patients with breathing problems who have been diagnosed with the coronavirus (COVID-19).

*Melillo, G. (2020, May 5). Can Artificial Intelligence Predict Glaucoma Progression? American Journal of Managed Care. https://www.ajmc.com/view/can-artificial-intelligence-predict-glaucoma-progression-