Detecting glaucoma worsening using optical coherence tomography derived visual field estimates

Multiple glaucoma studies have attempted to generate visual field (VF) mean deviation (MD) estimates using cross-sectional optical coherence tomography (OCT) data. However, whether such models offer any value in detecting longitudinal VF progression is unclear. We address this by developing a machine learning (ML) model to convert OCT data to MD and assessing its ability to detect longitudinal worsening. In this study, we created a model dataset of 70,575 paired OCT/VFs to train an ML model to convert OCT to VF-MD. We created a separate progression dataset of 4,044 eyes with ≥ 5 paired OCT/VFs to assess the ability of OCT-derived MD to detect worsening. The progression dataset eyes had 2 additional unpaired VFs (≥ 7 total) to establish a "ground truth" rate of progression defined by MD slope. We used the ML model to generate longitudinal OCT-MD estimates for each OCT scan for progression dataset eyes. We calculated MD slopes after substituting/supplementing VF-MD with OCT-MD and measured the ability to detect progression. We labeled true progressors using a ground truth MD slope < 0.5 dB/year calculated from ≥ 7 VF-MD measurements. We compared the area under the curve (AUC) of MD slopes calculated using both VF-MD (with < 7 measurements) and OCT-MD. Because we found OCT-MD substitution had a statistically inferior AUC to VF-MD, we simulated the effect of reducing OCT-MD mean absolute error (MAE) on the ability to detect worsening. Our model's OCT-MD estimates had an MAE of 1.62 dB (better than that of any previously published models). However, we found the AUC of MD slopes with partial OCT-MD substitution was significantly worse than the VF-MD slope. Supplementing VF-MD with OCT-MD also did not improve AUC, regardless of MAE. We found that OCT-MD estimates needed an MAE ≤ 1.00 dB before AUC was statistically similar to VF-MD alone. Overall, our ML model converting OCT data to VF-MD had error levels lower than those published in prior work and was inferior to VF-MD data for detecting trend-based VF progression. Our data suggest that future models converting OCT data to VF-MD must achieve better prediction errors (MAE ≤ 1 dB) to be clinically valuable at detecting VF worsening.