Xie Y, Zhao L, Yang X, et al. - Researchers conducted a diagnostic, cross-sectional study to investigate the use of a deep learning model in the screening of candidates for refractive surgery. This investigation was performed at the Zhongshan Ophthalmic Center, Guangzhou, China, with examination dates extending from July 18, 2016, to March 29, 2019. Participants in the study were 1,385 patients. On the validation data set, a deep learning model achieved an overall detection accuracy of 94.7%. The model achieved a discrimination rate (95.0%) on the independent test data set, equivalent to that of senior ophthalmologists who conduct refractive surgery (92.8%). Pentacam InceptionResNetV2 Screening System (PIRSS) seems to be useful in classifying images for providing corneal information and for the preliminary identification  of at-risk corneas. PIRSS may provide guidance to refractive surgeons in screening participants for refractive surgery and for generalized clinical application for Asian patients, but its use needs to be verified in other populations.