Artificial intelligence increasingly valuable

Ophthalmology is well suited to take advantage of advances in machine learning and AI

Dermot McGrath

Posted: Sunday, September 8, 2019

Ursula Schmidt-Erfurth MD, PhD
AS an image-intensive field of medicine, ophthalmology in general, and retinal practice in particular, is particularly well suited to take advantage of advances in machine learning and artificial intelligence, according to Ursula Schmidt-Erfurth MD, PhD, speaking at the session on The Diabetic Retina at the 19th EURETINA Congress.
“AI-based image analysis offers a rapid, cost-effective, precise and reliable screening and monitoring of diabetic retinopathy and diabetic macular oedema. This technology is not here to replace doctors but to assist them in managing their diabetic patients more efficiently,” she said.
Prof Schmidt-Erfurth told delegates that machine learning and AI applications will become increasingly necessary to help tackle the impending global epidemic of diabetes-related ocular disease.
“It is important to realise that diabetic retinal and macular disease represents a global pandemic with many millions of individuals being affected by systemic disease. On the other hand, there are only 210,000 retinologists working in the world to try to keep this under control. This clear disproportion highlights the need for AI support to manage such a major disease,” she said.
The first FDA clearance for an autonomous AI-diagnostic system to automatically detect more than mild DR in previously undiagnosed adults with diabetes was granted in 2018, noted Prof Schmidt-Erfurth.
“Several studies have already shown that AI is as accurate or better than the human eye in the analysis of digital fundus images,” she said.