Fellow-eye retinal age gap and high injection burden over four years in neovascular age-related macular degeneration.

PURPOSE: To evaluate whether fellow-eye retinal age gap (RAG), estimated using a deep learning model, is associated with long-term intravitreal injection burden in treatment-naive neovascular age-related macular degeneration (nAMD). METHODS: This retrospective cohort study included 80 patients with treatment-naive nAMD followed for ≥ 4 years after initiating anti-vascular endothelial growth factor therapy. Retinal age was estimated from fellow-eye fundus photographs using the publicly available Japan Ocular Imaging Registry model, and raw RAG was calculated as retinal age minus chronological age. Univariable analyses assessed associations of retinal age metrics with baseline ocular parameters, whereas univariable and multivariable analyses assessed their associations with 4-year injection burden. RESULTS: Median chronological age, retinal age, and raw RAG were 67.6, 68.9, and 1.33 years, respectively. Retinal age correlated with baseline best-corrected visual acuity and central retinal thickness, while raw RAG correlated with central choroidal thickness. Neither raw nor age-corrected RAG was associated with total injection number in the count analysis. In an exploratory threshold-based analysis, the ≥ 24-injection group had higher raw RAG than the < 24-injection group (4.19 vs. 0.66 years, P = 0.039), and higher raw RAG was associated with requiring ≥ 24 injections (OR 1.11 per 1-year increase; 95% CI, 1.01-1.22; P = 0.029). However, this association was attenuated after age correction and was not replicated at alternative thresholds. CONCLUSION: Higher raw fellow-eye RAG was associated with the ≥ 24-injection threshold; the association was attenuated after age correction and nonsignificant in alternative-threshold and count analyses. Further studies should evaluate RAG as a fundus-based candidate marker of sustained high treatment burden.