|
Abstract:
|
Alzheimer’s disease (AD) is a neurological disorder with substantial deleterious effects on cognitive processing, and currently available medications for AD do not clearly alter disease progression. As such, our research focuses on ways in which the progression of AD can be characterized, thereby providing a means for clinicians and public health authorities to hopefully delay or prevent the onset of AD in patients. Specifically, we focus on characterizing how at-risk patients with a precursor to AD, called mild cognitive impairment (MCI), transition from MCI to AD via novel variants of space-time mixture (STM) models we developed in a Bayesian hierarchical model framework. In particular, we make use of a non-parametric quantification of the dependence between two variables called the maximal information coefficient (MIC). The MIC then allows us to conditionally share latent temporal disease risk components identified by our model variants based on the estimated dependence between the magnitude of MCI and AD risk over time at the geographic-level. Preliminary results suggest that these novel STM model variants outperform the original STM model in terms of goodness of fit to AD data.
This research was supported by the South Carolina Clinical & Translational Research (SCTR) Institute, with an academic home at the Medical University of South Carolina, NIH/NCATS Grant Numbers TL1 TR001451 & UL1 TR001450.
The authors have no conflicts of interest to declare.
|
