A new high-tech screening program could save thousands from blindness.
Scientists have developed an AI scan for single-gene conditions known as IRDs (inherited retinal diseases).
It will enable more widespread provision of testing and improved efficiency, say the international team.
Project leader Dr. Nikolas Pontikos expects Eye2Gene to lead to personalized treatments.
The retina is a small membrane at the back of the eye that contains light-sensitive cells.
Dr. Pontikos, of Moorfields Eye Hospital in London, said the device reveals the genetic cause of a host of disorders.
He said: “Identifying the causative gene from a retinal scan is considered extremely challenging, even by experts.
“However, the AI is able to achieve this to a higher level of accuracy than most human experts.”
It could enable drugs and lifestyle changes to be prescribed years before symptoms emerge.
The main IRD is retinitis pigmentosa. Passed down through families, symptoms include difficulty reading and seeing in poor light.
The British and German researchers utilized Moorfields’ vast database of information on IRDs, covering more than three decades.
More than 4,000 patients have received a genetic diagnosis as well as detailed retinal imaging, making it the largest center of its kind.
Current methods are based on a patient’s individual expression of genes, defined by the Human Phenotype Ontology, or HPO.
It involves the use of standardized and structured descriptions of observable characteristics.
Dr. Pontikos said: “However, HPO terms are often imperfect descriptions of retinal imaging phenotypes, and the promise of Eye2Gene is that it can provide a much richer source of information than HPO terms alone by working directly from the retinal imaging.”
In tests, Eye2Gene performed better or as well on 130 IRD cases with a known gene diagnosis. In the future, it could be easily incorporated into routine eye examinations.
Dr. Pontikos said: “Ideally, Eye2Gene software would be embedded into the retinal imaging device.”
For widespread use, it will need to go through regulatory approvals to demonstrate safety and efficacy.
Dr. Pontikos said: “We need further evaluation of Eye2Gene in order to assess its performance for different types of IRD patients from different ethnicities, different types of imaging devices, and in different types of settings, for example, primary vs. secondary care.
“Clinical trials will be required before our system can be deployed in clinics as medical device software.”
He added: “We all know a picture is worth a thousand words, so we had some expectation that retinal scans interpreted by AI could out-perform HPO terms only.
“But we were still pleasantly surprised to see that, even when quite specific HPO terms were used, Eye2Gene could still do as well or better than an HPO-only approach. We hope that AI will help patients and their families by making specialist care more efficient, accessible, and equitable.”
Each IRD is caused by at least one gene that is not working as it should.
Others include Leber congenital amaurosis, Achromatopsia, Stargardt disease, Cone-rod dystrophy, Choroideremia. X-linked retinoschisis and Congenital stationary blindness.
They can affect individuals of all ages, can progress at different rates, and are rare. However, many are degenerative, which means that the symptoms of the disease will get worse over time.
The study will be presented on June 10 at a European Society of Human Genetics meeting in Glasgow, Scotland.
Conference chair Professor Alexandre Reymond said: “While real life experts are essential, the use of AI will help in mitigating biases and will allow diagnoses for all in the future.”
Produced in association with SWNS Talker
Edited by Saba Fatima and Newsdesk Manager
Get news, handpicked just for you, in your box.
