New technology developed at Monash University could be used to prevent vision loss and blindness and help predicting the risk of heart attack and stroke.
Create a free account to read this article
$0/
(min cost $0)
or signup to continue reading
The retinal deep learning model uses artificial intelligence (AI) technology to detect subtle changes in the retina.
Developed over the course of a three-year study, the model can detect and predict the risk of retinal vein occlusion, which is caused by blockage of a vein in the retina due to a blood clot.
The technology also has the potential to predict stroke and heart attack due to the connection between the retina and other parts of the body through the central nervous system.
Study author Zongyuan Ge said retinal vein occlusion affects 16 million people worldwide, making it the second most common retinal vascular disease.
Associate Professor Ge said if diagnosed too late or left untreated, it could lead to vision loss, or even blindness, in some cases. It can occur if the veins of the eyes are too narrow, and is more likely in people with diabetes, high blood pressure or high cholesterol.
During the study, researchers used an AI model to examine more than 10,500 photographs of the rear of the eye - known as fundus images. The photos were collected from Sichuan University's West China Hospital. Hundreds of thousands of pieces of data were used to enable the model's predictions.
Associate Professor Ge said artificial intelligence research had previously focused on eye diseases such as diabetic retinopathy, glaucoma or cataracts.
"We believe our study enhances our understanding of what AI can really do in disease diagnosis and management," he said.
"The ability of artificial intelligence to perform massive calculations and capture unknown and seemingly unrelated factors for classification is far beyond human thinking and capabilities."
He said researchers believed the tool could be used as a predictive tool by doctors and clinicians using "smart" fundus cameras and computer technology which had been integrated with the algorithm.
"We also hope the algorithm will make it much cheaper and more accessible for patients to check the health of their vessels," he said.
The study was published in medical journal Eye. To read it in full click HERE.