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

Taiabur Rahman; Siddiqur Rahman; Muhammad Moniruzzaman; Ummay Kawsar; Sayedatunnessa Ratna; Shadman Siddique; Rafsan Siddique; Tausif Ahmad

cs.CVSep 24, 2026

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

Authors: Taiabur Rahman, Siddiqur Rahman, Muhammad Moniruzzaman, Ummay Kawsar, Sayedatunnessa Ratna, Shadman Siddique, Rafsan Siddique, Tausif Ahmad, +2 more

Organizations: AI-MIQA, www.ai-miqa.eu. · Vision Eye Institute and Hospital, Dhaka, 1205, Bangladesh. · China West Normal University, Nanchong, Sichuan, China.

Abstract

Glaucoma is the leading cause of irreversible blindness, and timely identification of fast progressors is essential to prevent disability. Current practice estimates progression by ordinary least-squares regression of mean deviation (MD) on time, requiring 6--10 visual field (VF) tests over several years to obtain a reliable slope. We present 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. On the open-access University of Washington Humphrey Visual Field dataset (4,276 patient-eyes), GLAM achieved an MD-rate mean absolute error of 0.139 dB yr $^{-1}$ ( $R^2 = 0.927$ ; 73.5% reduction over a ridge baseline) and an AUC of 0.990 for fast-progressor detection. VF-only deep learning can match multimodal pipelines for progression prognostication using routinely collected perimetry alone.

Figures & tables

Characteristic	All	Train	Val.	Test
	( $n=4{,}276$ )	( $n=2{,}992$ )	( $n=640$ )	( $n=644$ )
Visits per eye, mean $\pm$ s.d.	$5.2\pm 2.8$	$5.2\pm 2.8$	$5.2\pm 2.8$	$5.2\pm 2.8$
Follow-up, years (median, IQR)	4.3 (2.5–7.7)	4.3 (2.5–7.7)	4.3 (2.5–7.7)	4.2 (2.5–7.7)
MD rate, dB yr -1 (mean $\pm$ s.d.)	$-0.126\pm 0.956$	$-0.127\pm 0.957$	$-0.122\pm 0.950$	$-0.126\pm 0.964$
Fast progressors (MD $<-1$ dB yr -1 )	394 (9.2%)	276 (9.2%)	62 (9.7%)	56 (8.7%)
Baseline MD proxy, dB (mean $\pm$ s.d.)	$-6.1\pm 6.1$	$-6.1\pm 6.1$	$-6.0\pm 6.1$	$-6.2\pm 6.2$

Table 1: Cohort characteristics of the analysis population (UWHVF,

n=4{,}276

patient-eyes). 0 0 footnotetext: IQR, interquartile range; MD, mean deviation; s.d., standard deviation; UWHVF, University of Washington Humphrey Visual Field dataset.

Figure 1: GLAM model architecture. Longitudinal VF total deviation sequences ( $T$ visits $\times$ 54 points) are encoded by a VisualFieldEncoder and processed by a two-layer bidirectional LSTM to produce a 512-dimensional functional representation. A five-feature clinical branch produces a 128-dimensional embedding. An attention-fusion module combines all modality representations with learned soft weights. A dual regression head predicts MD and VFI progression rates with aleatoric uncertainty. The structural branch (dashed) is inactive in this study because UWHVF contains no fundus images and outputs zeros. BiLSTM, bidirectional long short-term memory; MD, mean deviation; MLP, multilayer perceptron; VFI, visual field index; UWHVF, University of Washington Humphrey Visual Field dataset.

Model	MAE	RMSE	$R^{2}$	AUC (95% CI)	Sens.	Spec.	F1
Naive (global mean)	0.524	0.797	—	0.500 (0.500–0.500)	—	—	—
Ridge (baseline MD)	0.527	0.802	—	0.367 (0.293–0.444)	—	—	—
GLAM (this work)	0.139	0.238	0.927	0.990 (0.982–0.996)	98.2	90.6	0.663

Table 2: Test-set performance of GLAM and clinical baselines (

n=644

patient-eyes). 0 0 footnotetext: MAE and RMSE are MD rate in dB yr -1 . Sensitivity, specificity (%), and F1 for GLAM are reported at the Youden-optimal threshold of

-0.58

dB yr -1 . Ridge regression AUC was computed using the negated predicted MD as the discrimination score. AUC, area under the receiver operating characteristic curve; CI, confidence interval (stratified bootstrap, 1,000 resamples); MAE, mean absolute error; MD, mean deviation; RMSE, root mean squared error.

Figure 2: Predicted versus true MD progression rate on the held-out test set ( $n=644$ patient-eyes). Each point represents one patient-eye. The red dashed line indicates the line of identity. $R^{2}=0.927$ ; mean absolute error $=0.139$ dB yr -1 ; signed bias $=0.001$ dB yr -1 . Point colour encodes prediction error magnitude (darker $=$ larger absolute error). MD, mean deviation.

Figure 3: Receiver operating characteristic curve for fast-progressor detection (MD $<-1$ dB yr -1 ) on the held-out test set. AUC $=0.990$ (95% confidence interval by stratified bootstrap: 0.982–0.996). The Youden-optimal operating point (predicted MD threshold $=-0.58$ dB yr -1 ; sensitivity 98.2%, specificity 90.6%) is marked. AUC, area under the receiver operating characteristic curve; MD, mean deviation.

Figure 4: Aleatoric uncertainty calibration plot. Predicted standard deviation $\sigma=\exp(0.5\times\log\mathrm{var})$ plotted against absolute prediction error $|\mathrm{MD}_{\mathrm{pred}}-\mathrm{MD}_{\mathrm{true}}|$ for each patient-eye in the held-out test set. The red dashed line denotes ideal calibration ( $\sigma=|\mathrm{error}|$ ). Empirical coverage of nominal 90% prediction intervals is 99.8%, indicating conservative over-coverage; Spearman $\rho$ between predicted standard deviation and absolute error is 0.41 ( $P<0.001$ ). MD, mean deviation.

Modality	All ( $n=644$ )	Fast ( $n=56$ )	Slow ( $n=588$ )
Structural (placeholder)	0.321	0.329	0.317
Functional (BiLSTM)	0.410	0.396	0.413
Clinical (MLP)	0.271	0.275	0.270

Table 3: Mean modality attention weights by progression subgroup (held-out test set). 0 0 footnotetext: The structural branch carries only zeros and therefore cannot influence predictions; non-zero weights reflect the architectural softmax constraint

\alpha_{s}+\alpha_{f}+\alpha_{c}=1

. Fast/slow columns are progressor subgroups. BiLSTM, bidirectional long short-term memory network; MLP, multilayer perceptron.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 5: Test-set MAE by MD-rate quintile. Bars show MAE within each quintile of true MD rate (Q1: $\geq 0$ dB yr -1 , $n=129$ ; Q2: $-0.09$ to $0$ dB yr -1 , $n=129$ ; Q3: $-0.35$ to $-0.09$ dB yr -1 , $n=129$ ; Q4: $-0.82$ to $-0.35$ dB yr -1 , $n=129$ ; Q5: $<-0.82$ dB yr -1 , $n=128$ ). Error increases monotonically with progression severity from 0.092 dB yr -1 (Q1) to 0.205 dB yr -1 (Q5). MAE, mean absolute error; MD, mean deviation.

Explore similar work

DiffSight-Former: Modeling Structural Differences and Temporal Dynamics for Glaucoma Progression Prediction
Jun 8, 2026Yi Huang, Lei Bi, Jinman KimGlaucoma Detection Fundus Images
School of Computer Science, The University of Sydney · Institute of Translational Medicine, Shanghai Jiao Tong University
Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion Models
Jun 29, 2026Marta Colmenar Herrera, Pablo Márquez Neila, Şerife Seda Kucur Ergünay +2Glaucoma Detection Pixel-Level Prediction
ARTORG Center for Biomedical Engineering Research, UniBe, Switzerland · PeriVision SA, Epalinges, Switzerland · Department of Ophthalmology, Inselspital, Bern, Switzerland
Detecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study
Sep 24, 2026Raghavan Lavanya, Yangqin Feng, Ten Cheer Quek +36Glaucoma Detection Fundus Images
Singapore Eye Research Institute, Singapore National Eye Centre, Singapore · Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore · Institute of Advanced Intelligence and Computing, Agency for Science, Technology and Research, Singapore +14

Jun 8, 2026, cs.CVJ/K move · Enter open · S save

DiffSight-Former: Modeling Structural Differences and Temporal Dynamics for Glaucoma Progression Prediction

Yi Huang, Lei Bi, Jinman Kim

School of Computer Science, The University of Sydney · Institute of Translational Medicine, Shanghai Jiao Tong University

Glaucoma Detection Fundus Images Temporal Dynamics Longitudinal Data

Open paper AskPDF arXiv

Glaucoma is a leading cause of irreversible blindness worldwide, and early detection from fundus images is critical for effective disease management. While deep learning has achieved promising performance in fundus image analysis, most existing methods rely on single time-point images and fail to capture longitudinal structural and vascular changes associated with disease progression. Sequential fundus images acquired during clinical follow-up provide valuable temporal information; however, current sequential models often struggle to detect subtle early progression signals and commonly depend on fixed-length inputs or diagnostic cues from already glaucomatous images, limiting their clinical utility for early prediction. To address these limitations, we propose DiffSight-Former, a framework for glaucoma progression prediction from sequential fundus images. It incorporates a time-variant feature extraction module based on a fundus-specific foundation model to obtain robust anatomical representations. A multi-structure difference modeling module is introduced to quantify progression-related changes in the optic disc/cup region and retinal vasculature. These representations are integrated with temporal interval embeddings and processed by a time-aware Transformer to model disease progression and estimate the probability of future glaucoma onset. Experiments were conducted on two longitudinal datasets, SIGF (405 sequences) and GRAPE (263 sequences). On SIGF, DiffSight-Former achieved an AUC of 91.54% and a sensitivity of 92.16% for progression prediction. On GRAPE, it achieved an average accuracy of 87.48% across three clinical visual-field progression criteria. Compared with existing approaches, DiffSight-Former demonstrates strong performance and robustness across different temporal settings, highlighting its potential for longitudinal glaucoma monitoring and early risk prediction.

Abstract

Explore similar work

DiffSight-Former: Modeling Structural Differences and Temporal Dynamics for Glaucoma Progression Prediction

Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion Models

Detecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study