Title: Predicting disease progression in neurodegenerative diseases with high phenotypic variability
Authors: Frank Dondelinger - Lancaster University (United Kingdom) [presenting]
Abstract: Identifying factors that influence the clinical progression of neurodegenerative diseases is of critical importance to both experimentalists trying to understand the disease mechanisms, and clinical researchers trying to develop improved therapies. While much effort has gone into the detection of risk factors for a given disease, most of these approaches ignore the inherent variability in the clinical phenotypes. We have developed a high-dimensional mixture model approach for jointly solving the problem of data-driven estimation of clinical phenotypes and prediction of disease progression. Longitudinal dynamics are captured via a mixed model approach, and we take into account both the distribution of the response and the distribution of the covariates for estimating the disease phenotypes. We demonstrate the performance of our method by applying it to data from the PROACT database on amytrophic lateral sclerosis, as well as data from the Alzheimers Disease Neuroimaging Initiative (ADNI). We show that in both cases joint inference of the subtypes and predictors improves the prediction performance, and hence the clinical usefulness of our results.