B0193
Title: A disease progression model for exponential family outcomes with application to neurodegenerative diseases
Authors: Aaron Scheffler - University of California, San Francisco (United States) [presenting]
Abstract: Disease progression can be tracked via a cascade of changes in biomarkers andclinical measurements over the disease time course. For example, in progressiveneurodegenerative diseases (ND), such as Alzheimers Disease, changes in biomarkers(neuroanatomical images, cerebrospinal fluid) may precede clinical measurements (cognitivebatteries) by months or years. Viewing repeated measurements of biomarkers and clinicalmeasurements as a multivariate time series composed of both continuous and discretevalues, successful modeling of disease progression balances capturing stereotypic patterns indisease progression across subjects with subject-level variability in timing, acceleration, andshape of disease progression trajectories. We propose a generalized nonlinear mixed-effectmodeling framework that models trajectories of exponential family outcomes across thedisease time course allowing for characterization of typical disease progression as well asheterogeneity in the timing, speed, ordering, and shape of disease progression at the subject-level via random effects structure that partitions phase and amplitude variance. Ourframework will accommodate continuous and count outcomes allowing for incorporation ofmeasurements ranging from neuroimaging features to sensitive sub-scales of cognitivebatteries. A working example is provided from patients experiencing progressive ND.