Researchers May Have Found a Way to Predict Blindness Later in Life

Sight loss is a phenomenon that affects millions around the world each year, especially among older folks whose eyes begin to develop problems. For many years, this slow slide into blindness was inevitable with few options for elderly people looking to improve their vision and reverse their ocular deterioration. 

New research out of Japan's Tokyo Medical and Dental University might have some promising news for those looking to slow the process of sight loss. The study, published in JAMA Ophthamology, used machine-learning models to predict visual acuity in patients with high myopia, or severe shortsightedness, one of the top three causes of irreversible blindness in the world.

In the end, a regression model showed that it can accurately predict visual acuity at three and five years, while a binary classification model can predict and visualize the risk at five years. "Using artificial intelligence to estimate future visual acuity could help clinicians to identify and monitor patients with a high risk of vision reduction in advance," the scientists said in the research.

The purpose in conducting this study was to determine just how good machine learning can be at making long-term predictions, specifically when it comes to predicting the rate of vision decline. 

"We know that machine-learning algorithms work well on tasks such as identifying changes and complications in myopia, but in this study, we wanted to investigate something different, namely how good these algorithms are at long-term predictions," study lead author Yining Wang said. 

With so much criticism around artificial intelligence and machine learning these days, it's reassuring to hear of some good the technology is bringing.