New artificial intelligence (AI) technology that detects subtle changes in the retina could prove a game-changer in helping millions of people avoid vision loss or blindness.
The retinal deep learning model has been developed during a three-year study by Monash University.
While the technology will help detect and predict the risk of retinal vein occlusion (RVO), it also has the potential to predict the risk of heart attack and stroke.
RVO occurs when a blood clot blocks a vein in the retina.
The study, published in the prestigious journal Eye, was carried out by Monash Medical AI Group, which sits within the university’s Monash eResearch Centre.
Study author Associate Professor Zongyuan Ge said RVO is the second most common retinal vascular disease in the world, affecting an estimated 16 million people. If diagnosed too late or left untreated, it can lead to vision loss, or in serious cases, blindness.
During the study, researchers trained an AI model to distinguish between more than 10,500 fundus images collected from the West China Hospital of Sichuan University.
Assoc Prof Ge said AI had previously focussed on eye diseases such as diabetic retinopathy, glaucoma or cataracts.
“However, it’s rare that a study links fundus images to neurological and systemic disease risk factors,” he said.
“We believe our study enhances our understanding of what AI can really do in disease diagnosis and management.
“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,” Assoc Prof Ge noted in a media release issued by Monash University.
It is hoped the algorithm tool will help doctors and clinicians predict the risk of RVO and other cardiovascular and cerebrovascular diseases – even if they are not specialists.
All they will need is a ‘smart’ fundus camera, which are now widely available, even in developing countries, and a cloud computing platform integrated with the AI algorithm.
Assoc Prof Ge said he hoped the algorithm will make it much cheaper and more accessible for patients to check their eye health – perhaps AU$20–40, compared to cost of an MRI scan, which could cost thousands in some countries.
It is hoped the study will lead to clinical trials in China, Australia, the United Kingdom and the United States.
