The latest Artificial Intelligence tools are just ‘as good as experts’ at detecting eye problems, according to the latest research published in the journal Nature this week.
A new machine-learning system can identify over 50 different eye diseases and could considerably speed up diagnosis and treatment, according to experts.
The new AI system developed by Google’s DeepMind and Moorfields eye hospital and University College London can refer patients with 94% accuracy, with the machine-learning system said to be just as good as human experts at detecting eye problems and referring patients for treatment.
Deepmind’s revolutionary AI optician system was developed in conjunction with the NHS foundation trust and University College London.
“The results of this pioneering research with DeepMind are very exciting and demonstrate the potential sight-saving impact an AI optician could have for patients,” said Prof Sir Peng Tee Khaw, the director of the NIHR Biomedical Research Centre at Moorfields eye hospital and the UCL Institute of Ophthalmology.
The two-stage AI system is comprised of five separate machine-learning systems, trained using 877 clinical OCT scans, to create detailed maps of the patient’s OCT scans.
The AI optician will see you now
These initial five maps are then analysed by a second phase made up of five machine-learning systems, trained on maps created from 14,884 OCT scans from 7,621 patients. To date!
The referral decisions combined into one result, are then delivered with a confidence rating expressed as a percentage. A human clinician can then analyse the results, if there is any question over what the patient needs.
“The number of eye scans we’re performing is growing at a pace much faster than human experts are able to interpret them,” said Dr Pearse Keane, a consultant ophthalmologist at Moorfields eye hospital. “The AI technology we’re developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional. If we can diagnose and treat eye conditions early, it gives us the best chance of saving people’s sight.”
If the Artificial Intelligence system passes the testing and approval stage then it will then be available for use across all of Moorfields’ sites for five years.
Robert Dufton, the chief executive at Moorfields Eye Charity, said: “The need for treatment for eye diseases is forecast to grow, in part because people are living longer, far beyond our ability to meet the demand using current practice.
“Artificial intelligence is showing the potential to transform the speed at which diseases can be diagnosed and treatments suggested, making the best use of the limited time of clinicians.”
The research is published in the journal Nature Medicine.
Via The Guardian