Winning competition algorithms outperform ophthalmologists

An international competition has resulted in the development of artificial intelligence models (AI) capable of outperforming ophthalmologists in the diagnosis of myopic maculopathy.

The Myopic Maculopathy Analysis Challenge (MMAC), which was described in JAMA Ophthalmology, saw 15 AI models developed for the classification and segmentation of myopic maculopathy.

The participants built deep learning (DL) algorithms using public datasets before the AI models were validated and evaluated, with model performance compared to a group of five ophthalmologists.

The researchers found that some AI models achieved better diagnostic performance than the ophthalmologists.

“Algorithms submitted to the MMAC competition showed promising diagnostic performance compared with ophthalmologists, with some DL algorithms outperforming ophthalmologists,” the authors shared.

Study co-author, Professor Yalin Wang, of Arizona State University, highlighted that innovations in technology can help to provide important healthcare solutions.

“AI is ushering in a revolution that leverages global knowledge to improve diagnostic accuracy, especially in its earliest stage of the disease,” he said.

“These advancements will reduce medical costs and improve the quality of life for entire societies,” Wang shared.