a computer in a dark room, its screen displaying a large amount of binary code

Researchers at Moorfields have been investigating how artificial intelligence (AI) might help them discover new ways of improving eye healthcare.

For years, researchers at Moorfields Eye Hospital and the UCL Institute of Ophthalmology have been working to use their world-leading expertise in artificial intelligence (AI) to improve eye care.

In 2019, a team led by Dr Pearse Keane and working with international collaborators set out to see if they could diagnose common eye diseases like age-related macular degeneration (AMD) and glaucoma using a branch of AI called machine learning’.

Machine learning is based on the idea that computer systems can learn from data, identify patterns and make decisions themselves - and in doing so speed up many of the processes that take time for humans to complete.

Using AI to improve eye healthcare

Recent advances in AI research across the world have made it possible to analyse and interpret data in new ways which can greatly improve the quality of patient care.

However, doing this takes time, specialised computers and advanced technical skills. 

Moorfields Eye Hospital is the largest eye hospital in Europe and generates a huge amount of data on patients’ eyes. 

If AI could be made more accessible - in particular to healthcare professionals without computer programming expertise - this data could be used to open up a whole new avenue of AI research in healthcare.

Importantly, this would mean that any advances could be created, tested and developed by eye experts themselves, hopefully producing new systems that hold potential for significant patient benefits.

AI built by AI - results and applications

Together with a team from Moorfields, and supported by a Moorfields Eye Charity Springboard Award, Dr Keane successfully developed a new algorithm for analysing medical images to diagnose eye diseases using the automated machine learning platform Google AutoML.

This AI built by AI’ can classify eye images just as well as established deep learning algorithms – at least for simple tasks.

This new approach makes creating and using AI easier, and opens up the possibility for more clinicians to make use of it to provide patients with a faster diagnosis. 

However, there is more work to be done before this process can be applied in the clinic, and making sure that AI is used correctly in practice will require AI experts and clinicians to work closely together to develop good regulation and guidelines around it.

These results are the first to come out from Moorfields Eye Charity’s new Springboard Award programme, which is designed to support researchers looking to test a new idea which they hope will open up new avenues of research. 

It’s still early days but these results are really encouraging when we consider their potential to bring clinical benefits to a wider range of patients. We’re excited to see what our continued funding of ground-breaking AI research at Moorfields will lead to next.

Ailish Murray, director of Grants and Research at Moorfields Eye Charity