Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion Models
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors studied how to predict future vision test results for glaucoma patients more reliably. Instead of giving just one guess, they used a method that shows a range of possible outcomes to capture uncertainty in disease progression and measurement errors. Their new approach uses advanced models called conditioned denoising diffusion models, which provide better-calibrated predictions. Tests on real patient data showed their method not only gives more informative predictions but also matches or beats current techniques in accuracy. This work suggests moving toward prediction methods that account for uncertainty to help doctors better assess risks in glaucoma care.
glaucomavisual fieldsforecastingprobabilistic predictiondenoising diffusion modelslongitudinal datauncertainty quantificationcalibrationpoint-estimate predictionrisk assessment
Authors
Marta Colmenar Herrera, Pablo Márquez Neila, Şerife Seda Kucur Ergünay, Martin S. Zinkernagel, Raphael Sznitman
Abstract
Forecasting visual fields (VFs) is critical for personalized monitoring and treatment planning in glaucoma. This is inherently uncertain due to heterogeneous disease progression and measurement variability, yet most existing methods produce single deterministic predictions that fail to represent this uncertainty. We formulate VF forecasting as a probabilistic prediction problem and the use of conditioned denoising diffusion models to generate distributions of plausible future VFs from longitudinal observations with irregular follow-up intervals. Experiments on two independent VF cohorts show that diffusion-based predictions produce well-calibrated distributions for clinically relevant VF measures. When reduced to a standard point-estimate, the proposed approach achieves state-of-the-art accuracy compared to clinical baselines and prior learning-based methods. Our results highlight the advantages of distributional modeling for VF forecasting and support a shift from point-estimate prediction toward uncertainty-aware, clinically interpretable risk assessment in glaucoma.