- Age-related macular degeneration (AMD) often results in permanent loss of central vision.
- A team of researchers in the UK developed an AI-based eye test to predict wet AMD in patients before the onset of symptoms.
- They published their findings in the journal Expert Review of Molecular Diagnostics
Researchers at University College London (UCL), in collaboration with Western Eye Hospital, trained a newly developed artificial intelligence (AI) algorithm to analyze retinal scans. Using the AI-based eye test, the researchers aimed to predict wet AMD in patients years before the development of symptoms.
Age-related macular degeneration (AMD) is the leading cause of severe, permanent vision loss in adults aged over 60 years. Symptoms such as blurry vision or loss of central vision occur as a result of damage to the macula of the retina. The medical condition has two main types: wet and dry. Although dry is more common, it can often progress to the wet form.
In wet AMD, abnormal blood vessels grow underneath the macula. These newly formed vessels are fragile and cause fluid and blood to leak. Thus, resulting in scarring and eventually permanent loss of central vision.
The AI-Based ‘Pioneering’ Eye Test
The first part of the ‘pioneering’ test involves DARC, a test initially developed for glaucoma patients. DARC (Detection of Apoptosing Retinal Cells) involves injecting a fluorescent dye into the bloodstream of patients. The dye attaches to retinal cells and illuminates areas where cells are undergoing stress or death. The more the illuminated area, the higher number of stressed retinal cells. Thus, highlighting the possibility of progression to wet AMD.
However, often at times, different specialists analyze the scan differently. Thus, resulting in varying conclusions and diagnoses. Therefore, the researchers included an AI algorithm to compare thousands of these scans and detect disease-related abnormalities. Using their newly trained AI, the researchers assessed 19 patients with early signs of AMD.
A 3-Year Head Start
Results showed that DARC particularly highlighted endothelial cells that line blood vessels. Under stress, these cells generally result in the formation of leaky blood vessels, characteristic of wet AMD. Using conventional eye scans with Optical Coherence Tomography (OCT), doctors detected these leaky vessels in patients three years later.
Next, the researchers aim to conduct further clinical trials and develop the test for other eye diseases.
Reference:
UCL. AI-Supported Test Predicts Eye Disease Three Years before Symptoms. 18 Dec. 2020, www.ucl.ac.uk/news/2020/dec/ai-supported-test-predicts-eye-disease-three-years-symptoms.