Which Explanatory Variables Contribute to the Classification of Good Visual Acuity over Time in Patients with Branch Retinal Vein Occlusion with Macular Edema Using Machine Learning?

Abstract

This study’s goal is to determine the accuracy of a linear classifier that predicts the prognosis of patients with macular edema (ME) due to a branch retinal vein occlusion during the maintenance phase of antivascular endothelial growth factor (anti-VEGF) therapy. The classifier was created using the clinical information and optical coherence tomographic (OCT) findings obtained up to the time of the first resolution of ME. In total, 66 eyes of 66 patients received an initial intravitreal injection of anti-VEGF followed by repeated injections with the pro re nata (PRN) regimen for 12 months. The patients were divided into two groups: those with and those without good vision during the PRN phase. The mean AUC of the classifier was 0.93, and the coefficients of the explanatory variables were: best-corrected visual acuity (BCVA) at baseline was 0.66, BCVA at first resolution of ME was 0.51, age was 0.21, the average brightness of the ellipsoid zone (EZ) was −0.12, the intactness of the external limiting membrane (ELM) was −0.14, the average brightness of the ELM was −0.17, the brightness value of EZ was −0.17, the area of the outer segments of the photoreceptors was −0.20, and the intactness of the EZ was −0.24. This algorithm predicted the prognosis over time for individual patients during the PRN phase.

Keywords

• optical coherence tomography
• branch retinal vein occlusion
• fovea
• macular
• logistic regression
• machine learning