Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion Models

2026-06-29

AI Summary

Glaucomatous visual field progression prediction is challenged by high uncertainty arising from disease dynamics and measurement variability, yet existing approaches are largely limited to deterministic point estimates. This work introduces, for the first time, a conditional denoising diffusion model to this task, learning the probabilistic distribution of future visual fields from irregularly sampled longitudinal data and thereby enabling uncertainty-aware forecasting. Evaluated on two independent cohorts, the proposed method demonstrates well-calibrated predictive uncertainty and, when reduced to point estimates, achieves state-of-the-art accuracy surpassing both clinical baselines and current learning-based approaches. These advances pave the way toward probabilistic and interpretable risk assessment in glaucoma management.

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.

Problem

• glaucoma
• visual field forecasting
• uncertainty quantification
• probabilistic prediction
• point estimates

Innovation

• diffusion models
• visual field forecasting
• probabilistic prediction
• uncertainty quantification
• glaucoma progression