Article
Author(s):
The ERF and ERF-free groups had similar best visual acuity gains from baseline to week 52.
In contrast to previous post-hoc findings, new findings suggest there was no significant difference in long-term best visual acuity (BVA) gains between early residual fluid (ERF) and ERF-free cohorts with neovascular age-related macular degeneration (nAMD).
The study investigators led by Rishi Singh, MD, President Martin Health, Cleveland Clinic Florida additionally suggest there was no significant difference between the week 12 fluid subgroups.
Treatment for nAMD can often require intensive therapy with anti-vascular endothelial growth factor (VEGF) injections. As alluded to above, the investigators note prior post hoc studies have reported an association between ERF after the loading phase and poorer treatment outcomes.
The retrospective cohort included treatment-naive patients with nAMD who were initiated on anti-VEGF between 2012 and 2018, with at least 1-year of follow-up. An overall population of 286 patients with nAMD was included in the study.
A machine learning algorithm quantified intraretinal fluid (IRF), subretinal fluid (SRF), and total retinal fluid from OCTs. The ERF-group included individuals with fluid at week 12 and was further stratified by fluid subtype. Investigators used paired t-tests and analysis of variance to compare best visual acuity and fluid among subgroups, as well as a quartile analysis to correlate fluid volumes to week 52 best visual acuity.
The risk of ERF was predicted from baseline factors using 3 machine learning methods, including ridge logistic regression, k nearest neighbors classification, and support vector classification. The main outcome measures were the mean change in best visual acuity from baseline to week 52 according to week 12 fluid status.
At week 12, the findings indicate 58.4% of patients had ERF. When breaking down the population, those in the ERF group included SRF only (45.5%), IRF-only (21.6%), and IRF and SRF (32.9%). The ERF and ERF-free groups had similar best visual acuity gains from baseline to week 52 (+5.7 ± 15.4 vs. +4.9 ± 18; P = .69), according to the data.
Then, in examining specific ERF subgroups, investigators observed no significant differences among the IRF-only (+4.6 ± 16.4), SRF-only (+5.6 ± 12.5), and IRF and SRF (+6.6 ± 18.5; P = .93) groups.
Moreover, quartile analysis of week 12 fluid revealed no predictive pattern for best visual acuity gains. Investigators developed three machine learning methods to predict those at risk for ERF and found that they achieved equivalent performances, with F1 scores of 0.73 to 0.76.
The abstract, “Characterizing Early Residual Fluid in Neovascular Age-Related Macular Degeneration Using Machine Learning in Routine Clinical Practice,” was published in Ophthalmology.