Meeting Banner
Abstract #1514

Data-driven model of Parkinson’s disease progression performs precision staging with magnetic resonance imaging biomarkers

Neil P Oxtoby1, Leon M Aksman2, Louise-Ann Leyland3, Rimona S Weil3, and Daniel C Alexander1
1Department of Computer Science, University College London, London, United Kingdom, 2Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom, 3Department of Neurodegenerative Diseases, University College London, London, United Kingdom

We estimate a data-driven signature of de novo Parkinson's disease progression as a sequence of disease events. We show that clinical decline in classic markers precedes grey-matter and white-matter neurodegeneration estimated from T1-weighted MRI and diffusion-weighted MRI. Using only cross-sectional data from the PPMI data set, we show model utility for fine-grained staging/stratification of patients, which holds promise for future clinical applications.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here