Putting the ‘Eye’ in AI

face
main_img

The new AI tech from Google’s DeepMind can diagnose over 50 retinal diseases with more accuracy than your optometrist.

Research conducted by Nature Medicine found that a ground-breaking artificial intelligence system developed by Moorfields eye hospital, University College London and Google’s DeepMind can identify over 50 eye diseases with 94% accuracy.

Among the diseases that this revolutionary tech can detect are the three most common: glaucoma, diabetic retinopathy and age-related macular degeneration. Eye doctors are understandably delighted as they see the potential for this new tech to save time, money and most importantly – the sight of their patients.

Dr Pearse Keane, a consultant ophthalmologist at Moorfields eye hospital, notes that “The number of eye scans we’re performing is growing at a pace much faster than human experts are able to interpret them. 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.”

In the case of AI, quantity does not degrade quality.

 “The algorithm is on a par with expert performance at diagnosing OCT scans.” Keane continues, “It’s as good, or maybe even a little bit better, than world-leading consultant ophthalmologists at Moorfields in saying what is wrong in these OCT scans.” Unlike other AI systems, this algorithm can demonstrate how it reached a certain diagnosis and can be used on multiple types of OCT machine.

The next stage is for the AI system to be put through clinical trials and regulatory approval; necessary steps before it can be used in hospitals for patient referrals. DeepMind co-founder Mustafa Suleyman asserts that “What we do hope is that when this is ready for deployment, which will be several years away, it will end up impacting 300,000 patients per year.”

Looking forward, the researchers have posited that the intelligible AI system could also be used to help train clinicians, as well as allowing more patients to be treated thus relieving some of the burden on the NHS. Robert Dufton, chief executive of the Moorfields Eye Charity, concludes, “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.”

Latest Report