For the treatment of eye illness, early detection is essential. AI-enhanced eye scan analysis could identify danger indications more quickly and reach more people.
Since 2017, OPHTHALMOLOGY has had the highest volume of clinical appointments out of all the medical disciplines in the UK's National Health Service. Almost 10% of all NHS outpatient sessions are for eye-related issues. That amounts to around 10 million appointments annually, and during the last five years, the number has increased by more than a third.
Diabetic eye disease is the leading cause of blindness in people between the ages of 18 and 65. But as the population ages, age-related disorders including age-related macular degeneration (AMD) are becoming more common. The most frequent reason for blindness is that. According to a recent study published in the British Journal of Ophthalmology, over 60s in Europe make up 25.3% of those who have AMD. A severe type of AMD termed wet AMD, which results in blindness as a result of hemorrhage at the back of the eye, is also emerging in the UK at a rate of roughly 200 people each day.
It is difficult for ophthalmologists to examine and treat all of these patients. Unfortunately, this means that many people are losing their vision as a result of inadequate diagnosis and treatment. All the data point to early detection and treatment as being equivalent to safe sight.
These difficulties can be lessened through technology. Every optometrist office, like your neighbourhood Specsavers or Vision Express, is implementing new optical coherence tomography (OCT) eye scanners. These cutting-edge scanners have the ability to take non-invasive, extremely high-resolution retinal scans.
This holds promise but also poses a difficulty. Community optometrists frequently refer patients to eye hospitals because they lack the skills to analyse OCT scans, which adds to the load.
AI has the power to disseminate cutting-edge knowledge from institutions like Moorfields Eye Hospital. In 2018, we co-authored a proof-of-concept article with DeepMind that demonstrated how an AI system could analyze OCT scans and evaluate them for more than 50 retinal illnesses, performing on par with skilled ophthalmologists.
Since then, we have worked to confirm that the system is clinically viable by training the algorithm on a variety of data sets that will guarantee that it is applicable to all patients, regardless of ethnicity and clinical context.
Once we accomplish that, the AI system can be widely implemented throughout the neighbourhood. In order to treat them first in hospitals, the algorithm will be able to identify and prioritise those patients in local practises who have the worst prognosis. Chronic illnesses like AMD will be less of a burden as a result.
Similar to Thomas Edison's discovery of the electric light bulb, medical AI represents an innovation. A powered electricity generator, a grid distribution system to deliver electricity to people's homes, and a metre reader to track how much electricity was being used were among the network of innovations Edison believed were necessary to usher in the electrical age. With regard to ophthalmology AI, we have reached that stage. We are beginning to connect OCT devices used in optometry practices to the cloud.
We're launching national transformation programs for eye disorders in the NHS, which will set up payment mechanisms and channels that make it easier to move people from the community to the hospital. This network of inventions will enable the eventual deployment of AI once they all begin to mesh together.
The WIRED UK magazine's July/August 2023 issue includes a version of this story.
Comments
Post a Comment