A progressive loss of central vision characterizes age-related macular degeneration (AMD). It is the commonest cause of blindness in the elderly. Intermediate AMD is a risk factor for progression to advanced stages categorized as geographic atrophy (GA) and neovascular AMD. However, rates of progression to advanced stages vary between individuals. Recent advances in imaging and computing technologies have enabled deep phenotyping of intermediate AMD. Researchers have developed a multivariable prediction model that utilizes machine learning (ML) and advanced statistical modeling as an innovative approach to discover novel features and accurately quantify markers of pathological retinal aging that can individualize progression to advanced AMD.
The study consists of both retrospective and prospective parts. More than 400,000 optical coherent tomography (OCT) images are being pooled, centrally stored, and pre-processed in the retrospective part. With this large dataset featuring eyes with AMD at various stages and healthy controls, the researchers aim to identify imaging biomarkers for disease progression for intermediate AMD via supervised and unsupervised ML.
The prospective multivariable prediction model study part will first characterize the progression of intermediate AMD in patients between one and three years; secondly, it will validate the utility of biomarkers identified in the retrospective cohort as predictors of progression towards late AMD.