Researchers have developed deep learning (AI) models to assist ophthalmologists in diagnosing corneal diseases, such as keratitis (IK). This inflammation of the cornea affects millions of people around the world, especially in developing countries where there is little access to specialized eye care. Keratitis is therefore an important cause of corneal blindness worldwide.
The study, which analyzed 35 studies on the use of AI models to diagnose infectious keratitis, reports positive results. These are published in eClinicalMedicine, part of the Lancet.
AI performs slightly better
The research concludes that the AI models perform as well, or actually better, than ophthalmologists. For the study, more than 136,000 images of the corn were analyzed by the different AI models. The AI models matched the diagnostic accuracy of ophthalmologists with a sensitivity of 89.2 percent and a specificity of 93.2 percent. The ophthalmologists achieved 82.2 percent sensitivity and 89.6 percent specificity, respectively, during diagnosis.
“Our research shows that AI has the potential to provide fast, reliable diagnosis, which could transform the way we treat corneal diseases around the world. This is particularly promising for regions where access to specialized eye care is limited, and could help reduce the burden of avoidable blindness worldwide,” said Dr. Ting, lead author of the study, Birmingham Health Partner (BHP) and consultant in ophthalmology at the University of Birmingham.
Differentiate the underlying causes
The AI models were also effective in differentiating between healthy eyes, infected corneas and the various underlying causes of IK, such as bacterial or fungal infections.
While these results demonstrate the potential of deep learning models and AI in eye care, researchers also stressed that, in addition to external validation of the findings, more data is needed -varied also to increase the reliability of these models for clinical use. As AI technology continues to grow and play a central role in medicine, it may soon become an important tool in preventing forest blindness worldwide.
Glaucoma in pictures
Research has also been carried out in the Netherlands for several years on the use of AI models for better (and faster) diagnosis of eye disorders. A good example is the AI project ‘Glaucoma in pictures‘. More than 100,000 fundus images were provided for this purpose in 2020. These images were used to ‘train’ the computers to recognize glaucoma using AI. For this purpose, all fundus photographs were first evaluated by two experts. That data, along with the pictures, was entered into the computer system.
It was then checked whether the computer made the same judgment as the experts. Due to the large number of pictures and reviews, the computer will learn, with the help of AI (artificial intelligence), to find out from a fundus picture if that eye has glaucoma.
2024-10-22 20:17:00
#detect #corneal #diseases #ophthalmologists #ICT #health
