Search

Purpose: To investigate the association between rim area focal hyperautofluorescence (RAFH) signals and geographic atrophy (GA) growth rates, as well as the impact of oral metformin on the longitudinal change of RAFH., Design: Secondary analysis of a randomized controlled trial., Participants: Seventy-one eyes from 44 participants with GA and ≥6 months of follow-up in the METformin for the MINimization of geographic atrophy progression study., Methods: Fundus autofluorescence images were captured using a 488 nm excitation wavelength. Two masked graders identified and measured RAFH lesions using proprietary semiautomatic segmentation software and ImageJ. We calculated RAFH by dividing the areas of hyperautofluorescence within a 450-μm rim circumscribing the GA by the total area enclosed within this rim., Main Outcome Measures: Longitudinal changes in RAFH and GA area., Results: Baseline RAFH was positively associated with the baseline square root of GA area 0.065/year ( P < 0.001). In the entire study cohort, higher baseline RAFH was associated with a faster GA area growth rate in mm 2 /year (Spearman's ρ = 0.53; P < 0.001). The association became weaker in square root-transformed GA area growth (ρ = 0.19, P  = 0.11) and perimeter-adjusted GA growth rate (ρ = 0.28, P  = 0.02), achieving statistical significance only in the latter. When this analysis was stratified into 3 baseline GA tertiles, the first and second tertiles showed weak to moderate association with statistical significance in all 3 modes of GA growth rates. Rim area focal hyperautofluorescence increased slightly but significantly over time at 0.020/year ( P < 0.01). Rim area focal hyperautofluorescence increased slightly but significantly over time at 0.020/year ( P < 0.01). The use of oral metformin was not significantly associated with the change in RAFH over time compared with the observation group (0.023/year vs. 0.016/year; P  = 0.29)., Conclusions: Increased baseline RAFH is associated with faster GA area progression. However, the effect size of this association may depend on the baseline GA lesion size such that small to medium-sized GA lesions display this relationship regardless of the mode of the calculation of GA growth rate., Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article., (© 2024 by the American Academy of Ophthalmology.)

Importance: The identification of patients at risk of progressing from intermediate age-related macular degeneration (iAMD) to geographic atrophy (GA) is essential for clinical trials aimed at preventing disease progression. DeepGAze is a fully automated and accurate convolutional neural network-based deep learning algorithm for predicting progression from iAMD to GA within 1 year from spectral-domain optical coherence tomography (SD-OCT) scans., Objective: To develop a deep-learning algorithm based on volumetric SD-OCT scans to predict the progression from iAMD to GA during the year following the scan., Design, Setting, and Participants: This retrospective cohort study included participants with iAMD at baseline and who either progressed or did not progress to GA within the subsequent 13 months. Participants were included from centers in 4 US states. Data set 1 included patients from the Age-Related Eye Disease Study 2 AREDS2 (Ancillary Spectral-Domain Optical Coherence Tomography) A2A study (July 2008 to August 2015). Data sets 2 and 3 included patients with imaging taken in routine clinical care at a tertiary referral center and associated satellites between January 2013 and January 2023. The stored imaging data were retrieved for the purpose of this study from July 1, 2022, to February 1, 2023. Data were analyzed from May 2021 to July 2023., Exposure: A position-aware convolutional neural network with proactive pseudointervention was trained and cross-validated on Bioptigen SD-OCT volumes (data set 1) and validated on 2 external data sets comprising Heidelberg Spectralis SD-OCT scans (data sets 2 and 3)., Main Outcomes and Measures: Prediction of progression to GA within 13 months was evaluated with area under the receiver-operator characteristic curves (AUROC) as well as area under the precision-recall curve (AUPRC), sensitivity, specificity, positive predictive value, negative predictive value, and accuracy., Results: The study included a total of 417 patients: 316 in data set 1 (mean [SD] age, 74 [8]; 185 [59%] female), 53 in data set 2, (mean [SD] age, 83 [8]; 32 [60%] female), and 48 in data set 3 (mean [SD] age, 81 [8]; 32 [67%] female). The AUROC for prediction of progression from iAMD to GA within 1 year was 0.94 (95% CI, 0.92-0.95; AUPRC, 0.90 [95% CI, 0.85-0.95]; sensitivity, 0.88 [95% CI, 0.84-0.92]; specificity, 0.90 [95% CI, 0.87-0.92]) for data set 1. The addition of expert-annotated SD-OCT features to the model resulted in no improvement compared to the fully autonomous model (AUROC, 0.95; 95% CI, 0.92-0.95; P = .19). On an independent validation data set (data set 2), the model predicted progression to GA with an AUROC of 0.94 (95% CI, 0.91-0.96; AUPRC, 0.92 [0.89-0.94]; sensitivity, 0.91 [95% CI, 0.74-0.98]; specificity, 0.80 [95% CI, 0.63-0.91]). At a high-specificity operating point, simulated clinical trial recruitment was enriched for patients progressing to GA within 1 year by 8.3- to 20.7-fold (data sets 2 and 3)., Conclusions and Relevance: The fully automated, position-aware deep-learning algorithm assessed in this study successfully predicted progression from iAMD to GA over a clinically meaningful time frame. The ability to predict imminent GA progression could facilitate clinical trials aimed at preventing the condition and could guide clinical decision-making regarding screening frequency or treatment initiation.