AI algorithm improves glaucoma diagnosis – ICT and health

Glaucoma itself is a fairly treatable condition. That is why it is important that eye disease is detected at an early stage. This is still a problem, and not only in developing countries. In the Netherlands, too, the correct diagnosis is made and appropriate treatment is started in only half of the cases. Failure to diagnose this eye disease in time can lead to irreversible vision loss and even blindness.

Better diagnosis of glaucoma thanks to artificial intelligence

to me Development An AI algorithm first populates a database with base images of more than 110,000 people. The project, ‘glaucoma picturesIt started in 2020 and its main goal was to explore the possibility of using artificial intelligence (AI) in the evaluation of eye images and the early diagnosis of glaucoma.

These images were evaluated by 20 optometrists/ophthalmologists from different countries. All images were categorized as ‘glaucoma’ or ‘no glaucoma’. This database was then used to “train” the developed AI algorithm to diagnose this eye disease.

AI Challenge

At the beginning of this year, the so-called AI Challenge was organized, in which, in cooperation with the Department of Artificial Intelligence at the University of Amsterdam, developers were challenged to build an algorithm that could diagnose glaucoma at least as well, and preferably better. , as specialists. The ‘winning’ algorithm ultimately achieved an 85% diagnostic rate for identification of glaucoma, regardless of race and regardless of fundus camera used. This is just as good as a specialist does.

Research has now shown that the algorithm can be used in a broad and easily accessible way. With the help of artificial intelligence, the chance of widespread screening for this eye disease is greatly increased. The goal is to prevent and reduce blindness and visual impairment worldwide as much as possible thanks to early diagnosis and treatment.