AI improves diagnosis of retina disease

Artificial intelligence could be used to help diagnose inherited retinal diseases, according to research presented at the European Society of Human Genetics conference.

Eye2Gene, an AI system capable of identifying the genetic cause of IRDs from retinal scan, has been developed by researchers in the UK and Germany.

Dr Nikolas Pontikos, a group leader at the UCL Institute of Ophthalmology and Moorfields Eye Hospital, London, will tell delegates at the conference in Glasgow, Scotland, that the system could make specialist care for IRDs “more efficient, accessible, and equitable”.

“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,” says Dr Pontikos.

The researchers used Moorfields Hospital’s database of information on IRDs, which covered more than 30 years’ research. More than 4,000 patients have received a genetic diagnosis and detailed retinal imaging at Moorfields, making it the largest single centre dataset of patients with both retinal and genetic data.

Identifying the gene involved in a retinal disease is often guided by using the patient’s phenotype defined using the Human Phenotype Ontology (HPO). However, HPO terms are often imperfect descriptions of retinal imaging phenotypes, said Dr Pontikos.

The team benchmarked Eye2Gene on 130 IRD cases with a known gene diagnosis for which whole exome/genome, retinal scans, and detailed HPO descriptions were available, and compared their HPO gene scores with the Eye2Gene gene scores.

They found Eye2Gene provided a rank for the correct gene higher or equal to the HPO-only score in more than 70% of cases.

Dr Pontikos hopes Eye2Gene could be incorporated into standard retinal examination, first as an assistant in specialist hospitals to get a second opinion, and eventually as a “synthetic expert”.

Before then, the system will go through regulatory approvals to demonstrate safety and efficacy.

“We all know that a picture is worth a thousand words, so we had some expectation that retinal scans interpreted by AI could out-perform HPO terms only,” said Dr Pontikos.

“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.”

Abstract no. PL3.6 Eye2Gene: a novel AI algorithm enables phenotype-driven gene prioritisation directly from retinal scans in inherited retinal diseases

, ,

Leave a Reply

Your email address will not be published. Required fields are marked *



Monthly Posts

Our Clients

Practice Index