Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder

Purpose To develop a novel deep learning algorithm to improve estimation of rates of progression and prediction of future patterns of visual field loss in glaucoma. Design Prospective observational cohort. Methods A variational auto-encoder (VAE) was trained to learn a low-dimensional feature representation of standard automated perimetry (SAP) visual fields using 29,161 fields from 3,832 patients. The VAE was trained on a 90% sample of the data, with randomization at the patient level. Using the remaining 10%, rates of progression and predictions were generated, with comparisons to SAP mean deviation (MD) rates and point-wise (PW) regression predictions, respectively. From the VAE, rates were calculated using the average of slopes across latent features from ordinary least squares (OLS) regression and trajectories of the features were used to generate predictions. Results The longitudinal rate of change through the VAE latent space (e.g., with eight dimensions) detected a significantly higher proportion of progression than MD at two (19% vs. 6%) and four (40% vs 14%) years from baseline. Early on, VAE improved prediction over PW, with significantly smaller mean absolute error in predicting the 4th, 6th and 8th visits from the first three (e.g., visit eight: VAE8: 4.06 dB vs. PW: 6.06 dB; P<0.001). Conclusion A deep VAE can be used for assessing both rates and trajectories of progression in glaucoma, with the additional benefit of being a generative technique capable of predicting future patterns of visual field damage in the disease.