Dataset Information

Drusen and pigment abnormality predict the development of neovascular age-related macular degeneration in Japanese patients.

ABSTRACT: Drusen are known to be the important hallmark to predict the development of age-related macular degeneration (AMD). The prevalence of drusen is lower in Asians compared with Caucasians so that the role of signs constituting early AMD is not well established in Asian populations as in Western countries. In this study, we retrospectively investigated clinical characteristics and 5-year incidence of neovascular AMD (nAMD) in the fellow eye of unilateral nAMD patients. Of 296 consecutive unilateral nAMD patients who had been followed up more than 5 years, 170 typical AMD, 119 polypoidal choroidal vasculopathy, and 7 retinal angiomatous proliferation were included. To examine factors associated with nAMD occurrence in the fellow eye, drusen and pigmentary abnormality in the fellow eye were classified into 4 categories; Category 1: no or small drusen < 63 μm (37.2%), Category 2: 63-125 μm medium drusen or pigmentary abnormality (22.2%), Category 3: large drusen > 125 μm (25.0%), Category P: pachydrusen (15.5%). The mean sub-foveal choroidal thickness (SFCT) was Category 1: 276 μm, Category 2: 308 μm, Category 3: 246 μm, and Category P: 302 μm, respectively. Of note, SFCT in Category 2 and Category P was significantly larger than those of Category 3. Finally, the 5-year incidence of nAMD in the fellow eye was 32/296 (10.8%); Category 1: 0/110 (0%), Category 2: 12/66 (18.2%), Category 3: 20/74 (27.0%), and Category P: 0/46 (0%). Thus, signs of intermediate AMD (large drusen) as well as those of early AMD, especially the pigmentary abnormality, may contribute to development of bilateral nAMD in Japanese patients.

SUBMITTER: Notomi S

PROVIDER: S-EPMC8315508 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeNeovascular age-related macular degeneration (nAMD) shows variable treatment response to intravitreal anti-VEGF. This analysis compared the potential of different artificial intelligence (AI)-based machine learning models using OCT and clinical variables to accurately predict at baseline the best-corrected visual acuity (BCVA) at 9 months in response to ranibizumab in patients with nAMD.DesignRetrospective analysis.ParticipantsBaseline and imaging data from patients with subfoveal choroidal neovascularization secondary to age-related macular dengeration.MethodsBaseline data from 502 study eyes from the HARBOR (NCT00891735) prospective clinical trial (monthly ranibizumab 0.5 and 2.0 mg arms) were pooled; 432 baseline OCT volume scans were included in the analysis. Seven models, based on baseline quantitative OCT features (Least absolute shrinkage and selection operator [Lasso] OCT minimum [min], Lasso OCT 1 standard error [SE]); on quantitative OCT features and clinical variables at baseline (Lasso min, Lasso 1SE, CatBoost, RF [random forest]); or on baseline OCT images only (deep learning [DL] model), were systematically compared with a benchmark linear model of baseline age and BCVA. Quantitative OCT features were derived by a DL segmentation model on the volume images, including retinal layer volumes and thicknesses, and retinal fluid biomarkers, including statistics on fluid volume and distribution.Main outcome measuresPrognostic ability of the models was evaluated using coefficient of determination (R2) and median absolute error (MAE; letters).ResultsIn the first cross-validation split, mean R2 (MAE) of the Lasso min, Lasso 1SE, CatBoost, and RF models was 0.46 (7.87), 0.42 (8.43), 0.45 (7.75), and 0.43 (7.60), respectively. These models ranked higher than or similar to the benchmark model (mean R2, 0.41; mean MAE, 8.20 letters) and better than OCT-only models (mean R2: Lasso OCT min, 0.20; Lasso OCT 1SE, 0.16; DL, 0.34). The Lasso min model was selected for detailed analysis; mean R2 (MAE) of the Lasso min and benchmark models for 1000 repeated cross-validation splits were 0.46 (7.7) and 0.42 (8.0), respectively.ConclusionsMachine learning models based on AI-segmented OCT features and clinical variables at baseline may predict future response to ranibizumab treatment in patients with nAMD. However, further developments will be needed to realize the clinical utility of such AI-based tools.Financial disclosuresProprietary or commercial disclosure may be found after the references.

Dataset Information

Drusen and pigment abnormality predict the development of neovascular age-related macular degeneration in Japanese patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets