Machine Learning to Predict Outcomes and Dosing Frequency With Aflibercept for Macular Edema Following Central Retinal Vein Occlusion

Background and Objective: This study aimed to develop machine learning algorithms to predict visual and anatomic outcomes and treatment frequency in patients with macular edema following central retinal vein occlusion (MEfCRVO) after intravitreal aflibercept injections (IAI). Patients and Methods: Data from patients from the COPERNICUS ( n = 107) and GALILEO ( n = 91) trials treated with monthly IAI 2 mg for 24 weeks then pro re nata (PRN) through week 52 were used to develop machine learning algorithms. Results: Machine learning algorithms predicted actual values at week 52 with strong correlation for absolute best-corrected visual acuity (BCVA) ( r = 0.87), BCVA change from baseline ( r = 0.76), ≥ 15-letter gain (area under the curve [AUC] = 0.81), and change in central subfield thickness from baseline ( r = 0.76). PRN injection frequency from week 24 to 52 was predicted with high accuracy (AUC = 0.83). Univariate analyses confirmed all predictive factors. Conclusion: Machine learning algorithms predicted outcomes and dosing frequency with high accuracy and may help inform patients' and clinicians' expectations during MEfCRVO management.