Researchers have developed a new artificial intelligence (AI) model that can predict the risk of long-term visual impairment in patients with high myopia, one of the top three causes of irreversible blindness in many regions of the world. The team at the Tokyo Medical and Dental University (TMDU) said its machine-learning model works well for predicting and visualizing the risk of visual impairment over the long term.
Machine learning is a type of AI focused on building computer systems that learn from data, enabling software to improve its performance over time.
People with extreme shortsightedness (called high myopia) can see objects that are near to them but cannot focus on objects at a distance.
Contacts, glasses, or surgery can be used to correct their vision, but having high myopia can lead to a condition called pathologic myopia, a leading cause of blindness.
“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,” said Yining Wang, lead author of the study.
The study, recently published in the journal JAMA Ophthalmology, looked at the visual acuity of 967 Japanese patients at TDMU’s Advanced Clinical Center for Myopia after 3 and 5 years had passed.
The researchers formed a dataset from 34 variables that are commonly collected during ophthalmic examinations, such as age, current visual acuity, and the diameter of the cornea.
They then tested several popular machine-learning models such as random forests and support vector machines. Of these models, the logistic regression-based model performed the best at predicting visual impairment at 5 years.
However, predicting outcomes is only part of the story, the researchers said.
“It is also important to present the model’s output in a way that is easy for patients to understand and convenient for making clinical decisions,” said Kyoko Ohno-Matsui, senior author of the study.
The researchers used a nomogram to visualize the classification model. Each variable is assigned a line with a length that indicates how important it is for predicting visual acuity.
These lengths can be converted into points that can be added up to obtain a final score explaining the risk of visual impairment in the future, they said.
Although the model still has to be evaluated on a wider population, this study has shown that machine-learning models have good potential to help address this increasingly important public health concern, which will benefit both individuals and society as a whole.