Predicting Visual Acuity after Retinal Vein Occlusion Anti-VEGF Treatment: Development and Validation of an Interpretable Machine Learning Model.

Abstract

Accurate prediction of post-treatment visual acuity in macular edema secondary to retinal vein occlusion (RVO-ME) is critical for optimizing anti-VEGF therapy and improving clinical outcomes. While machine learning (ML) has shown promise in ophthalmic prognostication, existing models often lack interpretability and clinical applicability for RVO management. This study developed and validated an interpretable ML model to predict visual acuity changes in RVO patients following anti-VEGF treatment. Using retrospective data from 259 RVO patients at the First Affiliated Hospital of Jinan University, we identified key predictive features through the Boruta algorithm and evaluated eight ML algorithms. The Extreme Gradient Boosting (XGBoost) model emerged as optimal, achieving an AUC of 0.91 (95% CI: 0.85-0.96) in the testing cohort with 0.83 accuracy, 0.88 sensitivity, 0.73 specificity, 0.87 F1 score, and 0.14 Brier score. Critical predictors included baseline visual acuity, systolic blood pressure (SBP), age, diabetic retinal inner layer dysfunction (DRIL), and disease subtype. Shapley Additive exPlanations (SHAP) analysis revealed baseline visual acuity as the most influential prognostic factor, followed by SBP and age. Our model seeks to bridge the critical gaps in current research: (1) systematically comparing the applicability and effects of different ML algorithms in RVO-ME visual acuity prediction, and (2) inherent interpretability through SHAP value visualization. The combination of high predictive performance (AUC > 0.9) with inherent clinical transparency may enable the practical implementation of this tool in guiding anti-VEGF treatment decisions. Future validation in multicenter cohorts could further strengthen its generalizability for personalized RVO management.