Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bui, Phuoc-Nguyen, Vo, Van-Vi, Le, Duc-Tai, Pham, Van-Nguyen, Kim, Ki-Young, Yu, Seung-Young, Choo, Hyunseung
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2606.00588
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916070466519040
author Bui, Phuoc-Nguyen
Vo, Van-Vi
Le, Duc-Tai
Pham, Van-Nguyen
Kim, Ki-Young
Yu, Seung-Young
Choo, Hyunseung
author_facet Bui, Phuoc-Nguyen
Vo, Van-Vi
Le, Duc-Tai
Pham, Van-Nguyen
Kim, Ki-Young
Yu, Seung-Young
Choo, Hyunseung
contents Long-term visual acuity (VA) outcomes after anti-VEGF therapy are central to patient counseling, expectation setting, and follow-up planning in diabetic macular edema (DME). However, in clinical practice, physicians must often estimate long-term visual trajectories based only on early post-treatment findings, making reliable prognostication difficult. Although prior OCT-based learning approaches have largely focused on short-term response or single-endpoint prediction, modeling VA trajectories across multiple future time points from early longitudinal observations remains insufficiently explored. In this study, we assembled a real-world cohort of 188 anti-VEGF-treated DME patients with paired baseline and month-1 OCT scans, along with tabular OCT-derived biomarkers and non-imaging clinical variables. Using only these early data, we formulate a multi-horizon VA forecasting problem aimed at predicting visual outcomes at 3, 6, 12, 18, and 24 months, reflecting clinically meaningful follow-up intervals. We propose ReVA, a response-aware multimodal framework that integrates structural features from baseline and month-1 OCT with the tabular variables to capture baseline disease status and early treatment response. ReVA uses spatial attention to preserve localized prognostic imaging features and a dependency-aware tabular encoder to model interactions among clinical variables. These multimodal representations are fused to predict patient-specific long-term visual acuity trajectories. The proposed framework achieves MAE=0.1246, RMSE=0.1621, and R^2=0.6064 for 24-month VA prediction, with consistent performance across all forecast horizons. Our findings show that incorporating early treatment-response signals enables clinically meaningful long-term visual acuity forecasting, supporting data-driven decision support for routine anti-VEGF management.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00588
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Response-Aware Multimodal Learning for Post-Treatment Visual Acuity Forecasting
Bui, Phuoc-Nguyen
Vo, Van-Vi
Le, Duc-Tai
Pham, Van-Nguyen
Kim, Ki-Young
Yu, Seung-Young
Choo, Hyunseung
Computer Vision and Pattern Recognition
Long-term visual acuity (VA) outcomes after anti-VEGF therapy are central to patient counseling, expectation setting, and follow-up planning in diabetic macular edema (DME). However, in clinical practice, physicians must often estimate long-term visual trajectories based only on early post-treatment findings, making reliable prognostication difficult. Although prior OCT-based learning approaches have largely focused on short-term response or single-endpoint prediction, modeling VA trajectories across multiple future time points from early longitudinal observations remains insufficiently explored. In this study, we assembled a real-world cohort of 188 anti-VEGF-treated DME patients with paired baseline and month-1 OCT scans, along with tabular OCT-derived biomarkers and non-imaging clinical variables. Using only these early data, we formulate a multi-horizon VA forecasting problem aimed at predicting visual outcomes at 3, 6, 12, 18, and 24 months, reflecting clinically meaningful follow-up intervals. We propose ReVA, a response-aware multimodal framework that integrates structural features from baseline and month-1 OCT with the tabular variables to capture baseline disease status and early treatment response. ReVA uses spatial attention to preserve localized prognostic imaging features and a dependency-aware tabular encoder to model interactions among clinical variables. These multimodal representations are fused to predict patient-specific long-term visual acuity trajectories. The proposed framework achieves MAE=0.1246, RMSE=0.1621, and R^2=0.6064 for 24-month VA prediction, with consistent performance across all forecast horizons. Our findings show that incorporating early treatment-response signals enables clinically meaningful long-term visual acuity forecasting, supporting data-driven decision support for routine anti-VEGF management.
title Response-Aware Multimodal Learning for Post-Treatment Visual Acuity Forecasting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.00588