Improving visual field trend analysis with OCT and deeply regularized latent-space linear regression

Abstract

Purpose: To investigate whether OCT measurements can improve visual field (VF) trend analyses in glaucoma patients using the deeply regularized latent-space linear regression (DLLR) model. Design: Retrospective cohort study. Participants: Training and testing datasets included 7984 VF results from 998 eyes of 592 patients and 1184 VF results from 148 eyes of 84 patients with open-angle glaucoma, respectively. Each eye underwent a series of 8 VF tests with the Humphrey Field Analyzer OCT series obtained within the same observation period. Methods: Using pointwise linear regression (PLR), the threshold values of a patient’s eighth VF results were predicted using values from shorter VF series (first to second VF tests [VF1–2], first to third VF tests, . . . , to first to seventh VF tests [VF1–7]), and the root mean square error (RMSE) was calculated. With DLLR, OCT measurements (macular retinal nerve fiber layer thickness, the thickness of macular ganglion cell layer and inner plexiform layer, and the thickness of the outer segment and retinal pigment epithelium) that were obtained within the period of shorter VF series were incorporated into the model to predict the eighth VF. Main Outcome Measures: Prediction accuracy of VF trend analyses. Results: The mean ± standard deviation RMSE resulting from PLR averaged 27.48 ± 16.14 dB for VF1–2 and 3.98 ± 2.25 dB for VF1–7. Significantly (P < 0.001) smaller RMSEs were obtained from DLLR: 4.57 ± 2.71 dB (VF1–2) and 3.65 ± 2.27 dB (VF1–7). Conclusions: It is useful to include OCT measurements when predicting future VF progression in glaucoma patients, especially with short VF series.