Accurate prediction of myopic progression and high myopia by machine learning

Abstract

Myopia is a leading cause of visual impairment in Asia and worldwide. However, accurately predicting the progression of myopia and the high risk of myopia remains a challenge. This study aims to develop a predictive model for the development of myopia. We first retrospectively gathered 612 530 medical records from five independent cohorts, encompassing 227 543 patients ranging from infants to young adults. Subsequently, we developed a multivariate linear regression algorithm model to predict the progression of myopia and the risk of high myopia. The model to predict the progression of myopia achieved an R-squared (R2) value of 0.964 vs a mean absolute error (MAE) of 0.119D (95% CI: 0.119, 1.146) in the internal validation set. It demonstrated strong generalizability, maintaining consistent performance across external validation sets: R2 of 0.950 vs MAE of 0.119D (95% CI: 0.119, 1.136) in validation Study 1, R2 of 0.950 vs MAE of 0.121D (95% CI: 0.121, 1.144) in validation Study 2, and R2 of 0.806 vs MAE of −0.066D (95% CI: −0.066, 0.569) in Shanghai Children Myopia Study. Beijing Children Eye Study, the model sustained R2 of 0.749 vs MAE of 0.178D (95% CI: 0.178, 1.557). The model to predict the risk of high myopia achieved and an area under the curve (AUC) of 0.99 in the internal validation set and consistently high AUC values of 0.99, 0.99,0.96 and 0.99 in the respective external validation sets. Our study demonstrates accurate prediction of myopia progression and risk of high myopia providing valuable insights for tailoring strategies to personalize and optimize the clinical management of myopia in children.