Logo image
Back
Predicting Visual Field Worsening with Longitudinal Optical Coherence Tomography Data Using a Gated Transformer Network (OPHTHA-D-22-01964)s
Journal article   Open access   Peer reviewed

Predicting Visual Field Worsening with Longitudinal Optical Coherence Tomography Data Using a Gated Transformer Network (OPHTHA-D-22-01964)s

Kaihua Hou, Chris Bradley, Patrick Herbert, Chris Johnson, Michael Wall, Pradeep Y Ramulu, Mathias Unberath and Jithin Yohannan
Ophthalmology (Rochester, Minn.), Vol.130(8), pp.854-862
08/2023
DOI: 10.1016/j.ophtha.2023.03.019
PMCID: PMC10524436
PMID: 37003520
url
https://doi.org/10.1016/j.ophtha.2023.03.019View
Published (Version of record) Open Access

Abstract

To identify visual field (VF) worsening from longitudinal optical coherence tomography (OCT) data using a Gated Transformer Network (GTN), and to examine how GTN performance varies for different definitions of visual field worsening and different stages of glaucoma severity at baseline. A total of 4,211 eyes (2,666 patients) followed at the Johns Hopkins Wilmer Eye Institute with at least five reliable VFs and one reliable OCT within one year of each reliable VF. Retrospective longitudinal cohort study. For each eye, we used three trend-based methods (MD, VFI, and PLR slope) and three event-based methods (GPA, CIGTS, and AGIS) to define VF worsening. Additionally, we created an algorithm, called M6, that classifies an eye as worsening if 4 or more of the 6 aforementioned methods classifies the eye as worsening. Using these 7 reference standards for VF worsening, we trained 7 GTNs that accepts a series of at least 5 as input OCT scans and provides as output a probability of VF worsening. GTN performance was compared to non-deep learning models with the same serial OCT input from previous studies - linear mixed effects models (MEM) and naïve Bayes classifiers (NBC) - using the same training sets and reference standards as for the GTN. The effect of glaucoma severity at baseline VF on GTN performance was also investigated through stratified analysis. Area under the receiver operating characteristic curve (AUC) and F1 score. The M6 algorithm labeled 63 eyes (1.50%) as worsening. The GTN achieved an AUC (95% CI) of 0.97 (0.88, 1.00) when trained with M6. GTNs trained and optimized with the other 6 reference standards had AUC ranging from 0.78 (MD slope) to 0.89 (AGIS). The 7 GTNs outperformed all 7 MEMs and all 7 NBCs accordingly. GTN performance was worse for eyes with more severe glaucoma at baseline. GTN models trained with OCT data may be used to identify VF worsening. After further validation, implementing such models in clinical practice may allow us to track functional worsening of glaucoma with less onerous structural testing.

Details

Metrics

20 Record Views
Logo image