Retinal texture biomarkers may help to discriminate between Alzheimer's, Parkinson's, and healthy controls

Abstract

A top priority in biomarker development for Alzheimer's disease (AD) and Parkinson's disease (PD) is the focus on early diagnosis, where the use of the retina is a promising avenue of research. We computed fundus images from optical coherence tomography (OCT) data and analysed the structural arrangement of the retinal tissue using texture metrics. We built clinical class classification models to distinguish between healthy controls (HC), AD, and PD, using machine learning (support vector machines). Median sensitivity is 88.7%, 79.5% and 77.8%, for HC, AD, and PD eyes, respectively. When the same subject has the same classification for both eyes, 94.4% (median) of the classifications are correct. A significant amount of information discriminating between multiple neurodegenerative states is conveyed by OCT imaging of the human retina, even when differences in thickness are not yet present. This technique may allow for simultaneously diagnosing Alzheimer's and Parkinson's diseases.