To assess the accuracy of deep learning models to predict glaucoma development from fundus photographs several years before disease onset. Algorithm development for predicting glaucoma using data from a prospective longitudinal study. A total of 66 721 fundus photographs from 3272 eyes of 1636 subjects who participated in the Ocular Hypertension Treatment Study (OHTS) were included. Accuracy and area under the curve (AUC). Fundus photographs and visual fields were carefully examined by 2 independent readers from the optic disc and visual field reading centers of the OHTS. When an abnormality was detected by the readers, the subject was recalled for retesting to confirm the abnormality and for further confirmation by an end point committee. By using 66 721 fundus photographs, deep learning models were trained and validated using 85% of the fundus photographs and further retested (validated) on the remaining (held-out) 15% of the fundus photographs. The AUC of the deep learning model in predicting glaucoma development 4 to 7 years before disease onset was 0.77 (95% confidence interval CI, 0.75-0.79). The accuracy of the model in predicting glaucoma development approximately 1 to 3 years before disease onset was 0.88 (95% CI, 0.86-0.91). The accuracy of the model in detecting glaucoma after onset was 0.95 (95% CI, 0.94-0.96). Deep learning models can predict glaucoma development before disease onset with reasonable accuracy. Eyes with visual field abnormality but not glaucomatous optic neuropathy had a higher tendency to be missed by deep learning algorithms.