Abstract

In this manuscript we develop a deep learning algorithm to improve estimation of rates of progression and prediction of future patterns of visual field loss in glaucoma. A generalized variational auto-encoder (VAE) was trained to learn a low-dimensional 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. 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 (25% vs. 9%) and four (35% vs 15%) 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: 5.14 dB vs. PW: 8.07 dB; P < 0.001). 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.

Details

Title
Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder
Author
Berchuck, Samuel I 1 ; Mukherjee, Sayan 2 ; Medeiros, Felipe A 3 

 Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA; Department of Statistical Science and Forge, Duke University, Durham, North Carolina, USA 
 Departments of Statistical Science, Mathematics, Computer Science, Biostatistics & Bioinformatics, Duke University, Durham, North Carolina, USA 
 Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA 
Pages
1-12
Publication year
2019
Publication date
Dec 2019
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2321203092
Copyright
© 2019. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.