Li Y, Feng W, Zhao X, et al. - In this cross-sectional, prospective study, researchers sought to apply deep learning technology to develop an artificial intelligence (AI) system that can identify vision-threatening conditions in high myopia patients based on optical coherence tomography (OCT) macular images. In total, 5,505 qualified OCT macular images obtained from 1,048 high myopia patients admitted to Zhongshan Ophthalmic Centre from 2012 to 2017 were chosen for the development of the AI system. The areas under the receiver operating characteristic curves were high for all conditions (0.961 to 0.999) in the independent test dataset. OCT macular images were used for the development of convolutional neural network models to identify vision-threatening conditions in high myopia patients. Reliable sensitivities and high specificities were obtained by the models, comparable to those of retina specialists, and can be used for large-scale screening for high myopia and patient follow-up.