Skip to content
Open access

Longitudinal Pointwise Visual Field Prediction in Early‐Stage Glaucoma Using Regression Models and Long Short‐Term Memory: A Simulation Study

Jan 2026 · BioMed Research International · Vol 2026 · 0 citations · 45 references
Medicine

TL;DR

The performance of the models shows dependence on the number of examinations in the present study, which highlights the importance of temporal information in longitudinal VF prediction.

Abstract

Background Glaucoma is a progressive optic neuropathy in which longitudinal visual field (VF) prediction is essential for timely clinical decision‐making and preventing irreversible VF loss. However, accurate prediction remains challenging due to the noisy, high‐dimensional nature of VF data and their complex longitudinal patterns. Capturing these patterns may require increasingly sophisticated prediction models, but greater model complexity can reduce interpretability. Therefore, prediction models need to capture temporal patterns while balancing interpretability and computational feasibility. This study is aimed at evaluating and comparing the performance of four methods, including personalized models (first‐order autoregressive [AR(1)] and ordinary linear regression (OLR)), a population‐level long short‐term memory (LSTM), and a naive baseline (BL) forecast for glaucoma VF prediction. Materials and Methods Data were simulated for patients with early‐stage glaucoma using a linear mixed effects model (LMM) to account for noise in VF measurements and the impact of individual effects on glaucoma progression. Future VFs were predicted from examinations 6–11 based on previous examinations. Prediction accuracy was assessed using root mean squared error (RMSE) and pointwise mean absolute error (PMAE). Results Evaluation of the four approaches showed that OLR and naive BL forecast achieved higher errors than AR(1) and LSTM models. LSTM performed best when the number of examinations was small (in the initial examinations, indeed) in slow, moderate, and fast progression rate scenarios. However, with a larger number of examinations, prediction errors increased for LSTM compared with AR(1), resulting in higher accuracy for AR(1), particularly under moderate and fast progression rate scenarios. Conclusion The performance of the models shows dependence on the number of examinations in the present study. These findings highlight the importance of temporal information in longitudinal VF prediction.

Read PDF

Similar papers

Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors

GLAM (Glaucoma Longitudinal Analysis Model), a deep learning framework that ingests longitudinal Humphrey 24-2 total deviation sequences with five clinical features and predicts MD and visual field index progression rates using attention-based fusion and aleatoric uncertainty, is presented.

Taiabur Rahman, Siddiqur Rahman, M. Moniruzzaman et al. · 0 citations
Open access Sep 2026

Improved Estimation of Rates of Glaucoma Progression Using Spatial Two-Fold Linear Mixed Models

Visual field testing is essential for detecting glaucomatous damage. Traditional approaches such as pointwise linear regression often fail to account for the spatial correlations and hierarchical structure among test locations. We propose a two-fold linear mixed model that incorporates both eye-level and within-eye clu...

Chen Zhao, S. Swaminathan, J. S. Rao · 0 citations
Open access Oct 2026

Deep learning classification of longitudinally defined 24-2 central- and peripheral-onset visual field phenotypes in glaucoma using baseline fundus photographs

In conclusion, DL applied to baseline fundus photographs identified longitudinally defined patterns of central versus peripheral VF vulnerability in glaucoma, as defined by longitudinal VF follow-up.

Eun Jung Lee, Jeong Won Im, Yeeun Choi et al. · 0 citations
Open access Oct 2026

Deep learning-based prediction of one-year functional and structural outcomes in treatment-naïve DMO after anti-VEGF therapy.

Deep learning analysis of baseline OCT can predict one-year outcomes in DMO, and responder identification suggests the potential utility of this approach for prognostic assessment and risk stratification, warranting further validation before clinical implementation.

Lorena Ulla, Jonathan D. Oakley, Riccardo Fasana et al. · 0 citations
Oct 2026

Naturalistic Driving Engineered Trajectories Forecast Future Cognitive Decline.

OBJECTIVES Early population-based screening for Alzheimer's disease remains limited by the scalability and accessibility of conventional biomarker testing. We tested whether passive naturalistic driving changes predict progression from cognitively normal status to sustained mild cognitive impairment. METHODS Season-a...

Subrata Pal, David C. Brown, Chen Chen et al. · 0 citations
Preprint Oct 2026

Longitudinal retinal imaging and auxiliary tasks for discrete-time survival prediction of referable diabetic retinopathy and maculopathy: a retrospective cohort study

Deep learning can predict progression to referable diabetic retinopathy (rDR) and referable maculopathy (rM) from screening photographs, but existing models ignore the prior images that screening programmes hold. We assessed whether multi-visit (MV) images and auxiliary objectives that model the future visit improve pr...

Paul Nderitu, L. Webster, Samantha S. Mann et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.