News, NHS trust

Moorfields Eye Hospital and UCL develop AI tool to predict eye damage from autoimmune drug

Teams from Moorfields Eye Hospital NHS Foundation Trust and the University College London Institute of Ophthalmology have developed an AI tool capable of predicting patients at risk of developing retinopathy, following use of a common autoimmune medication, said to be widely prescribed to treat rheumatoid arthritis, lupus, and other autoimmune conditions.

Moorfields shares that hydroxychloroquine retinopathy can affect up to 7.5 percent of hydroxychloroquine users, causing irreversible damage to the retina. “The challenge is that significant harm may have already occurred by the time doctors can reliably spot the damage using current screening methods, which involve an annual ophthalmic check-up for anyone who has taken the drug for five years. Currently, the only way to prevent damage is to stop taking the medication, which can mean worsening the symptoms of arthritis.”

Trained using more than 8,000 eye scans from 409 patients in the US and UK, the HCQuery algorithm works by analysing retinal images captured using optical coherence tomography, a standard part of screening for hydroxychloroquine patients. It correctly identified 100 percent of patients with retinopathy up to 2.74 years earlier than doctors, according to Moorfields, also achieving 91 percent accuracy in ruling out patients without the condition.

The algorithm’s development was supported by data infrastructure from Moorfields’ INSIGHT Health Data Research Hub, and the code has been made publicly available on GitHub in order to accelerate its development and encourage further testing. Teams will now look at how the algorithm performs in a real-world setting, including an exploration of how current care pathways can be optimised to support earlier detection of hydroxychloroquine retinopathy.

Lead author, PhD researcher and research fellow Peter Woodward-Court, highlighted how the approach “could significantly improve care for the millions of people who depend on hydroxychloroquine”, adding: “Early detection would prevent irreversible vision loss while allowing patients to continue benefiting from this important medication for longer.”

Late last year, Moorfields and the UCL Institute of Ophthalmology also collaborated with Google, Topcon, and the INSIGHT Health Data Research Hub, in support of the rollout of a mobile AI service for diabetic retinopathy in outback Australia, aiming to tackle inequalities in eye health for rural and Indigenous Australians. Following a successful one-year pilot and a $5 million AUD grant from the West Australian government, the AI model said to offer “instant point-of-care diagnosis” is set to be rolled out in Pilbara, a region of Western Australia with a population of just 45,000 in an area almost twice the size of the UK where access to health services is “extremely limited”.

Wider trend: AI 

For a recent HTN Now webinar, we were joined by Neill Crump, digital strategy director at Dudley Group NHS Foundation Trust; Anil Mistry, AI safety lead and senior clinical scientist in AI at Guy’s and St Thomas’​ NHS Foundation Trust; and Matea Deliu, GP clinical lead and clinical lead for primary care digital delivery, South East London ICB. Our panellists discussed AI in healthcare, sharing their own learnings from recent AI strategies and projects as well as their thoughts on regulations, tackling data bias, through to safety and evaluations.

Google has announced an AI-powered personal health coach to Fitbit tracking services, with plans to roll out a preview of the new functionality in October to premium subscribers who are using the latest Fitbit trackers, Fitbit smart watches and Pixel watches. Built with Google’s AI tool, Gemini, the new personal health coach works as a fitness trainer, sleep coach and health and wellness advisor that can create a bespoke health plan based on goals set by the user. Additional functionality includes custom routines, where detailed workout suggestions and metrics help with weekly progression; real-time check-ins and adjustments to a workout based on lifestyle changes and daily insights; and personalised advice depending on how you’re feeling.

Health Education and Improvement  Wales has launched a free foundational course in AI for healthcare professionals, with plans to introduce a chatbot interface to the online course. It follows an AI education and skills landscape review earlier this year, which highlighted the need for AI education, particularly on understanding ethical, safe and effective use of AI, and that professionals are keen to learn about AI but lack structured programmes.