%0 Journal Article
%A Lin, Andrew
%A Fenyo, David
%A Schuman, Joel S
%A Wollstein, Gadi
%A Ishikawa, Hiroshi
%T Using Deep Learning Methods to Develop a Novel Predictive Glaucoma Progression Model
%B Investigative Ophthalmology & Visual Science
%D 2020
%J Investigative Ophthalmology & Visual Science
%V 61
%N 7
%P 872-872
%@ 1552-5783
%X To develop a novel glaucoma progression model with deep learning methods incorporating four major glaucoma biomarkers: VFI, MD, cRNFL and GCIPL. 1023 eyes from 596 glaucoma/glaucoma-suspect patients were included from clinic. Two types of deep learning (DL) models were developed using Keras: an artificial neural network (ANN) and a recurrent neural network (RNN). The ANN contained five fully-connected (FC) layers, with a leaky rectified linear unit activation function and a dropout layer with a rate of 0.2. The RNN contained two long short-term memory layers, followed by a FC layer and a dropout layer with a rate of 0.2. Both models were trained to predict four major clinical biomarkers for glaucoma: visual field index (VFI), mean deviation (MD), circumpapillary retinal nerve fiber layer (cRNFL) thickness, and ganglion cell inner plexiform layer (GCIPL) thickness. The models were trained using the first three visits to predict the fourth one year later. Train/validation/test splits were 65/15/20. A linear regression (LR) model was trained and evaluated on the same data for baseline comparison. Evaluation of the actual and predicted values were measured by mean absolute error (MAE). Statistical testing of each biomarker was performed between the DL models and LR model by paired Wilcoxon rank sum test. The mean patient age was 62.4 ± 12.9 years. The baseline mean cRNFL: 76.9 ± 13.4 μm, GCIPL: 70.3 ± 9.9 μm, VFI: 90.3 ± 17.8%, and MD: -3.76 ± 6.13 dB. Table shows the MAE between the actual and predicted values of each of the four biomarkers across all three models. The ANN and RNN models showed statistically significantly smaller MAE compared to the LR model. In particular, the ANN model had the lowest MAE and was able to predict all four biomarkers significantly better than the LR model. By harnessing the power of deep learning, we were able to accurately predict future values of both structural and functional measures of glaucomatous change one year later. This is possible as neural networks are able to recognize the intricate interplay between structural and functional changes in glaucoma that otherwise cannot be well captured in a conventional linear regression model. This is a 2020 ARVO Annual Meeting abstract. Biomarker Prediction Results of Models (Mean Absolute Error)
%[ 1/28/2021