Interpretable Machine Learning Predictions of Bruch’s Membrane Opening-Minimum Rim Width Using Retinal Nerve Fiber Layer Values and Visual Field Global Indexes

Abstract

The aim of this study was to predict Bruch’s membrane opening-minimum rim Width (BMO-MRW), a relatively new parameter using conventional optical coherence tomography (OCT) parameter, using retinal nerve fibre layer (RNFL) thickness and visual field (VF) global indexes (MD, PSD, and VFI). We developed an interpretable machine learning model that integrates structural and functional parameters to predict BMO-MRW. The model achieved the highest predictive accuracy in the inferotemporal sector (R2 = 0.68), followed by the global region (R2 = 0.67) and the superotemporal sector (R2 = 0.64). Through SHAP (SHapley Additive exPlanations) analysis, we demonstrated that RNFL parameters were significant contributing parameters to the prediction of various BMO-MRW parameters, with age and PSD also identified as critical factors. Our machine learning model could provide useful clinical information about the management of glaucoma when BMO-MRW is not available. Our machine learning model has the potential to be highly beneficial in clinical practice for glaucoma diagnosis and the monitoring of disease progression.

Keywords

• BMO-MRW
• Bruch’s membrane opening-minimum rim width
• optical coherence tomography
• visual field
• VF global index
• machine learning