Identification of Pre-Clinical Alzheimer's Disease in a Population of Elderly Cognitively Normal Participants.

Alzheimer's disease (AD) has a long pathological process, with an approximate lead-time of 20 years. During the early stages of the disease process, little evidence of the building pathology is identifiable without cerebrospinal fluid and/or imaging analyses. Clinical manifestations of AD do not present until irreversible pathological changes have occurred. Given an opportunity to provide treatment prior to irreversible pathological change, this study aims to identify a subgroup of cognitively normal (CN) participants from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL), where subtle changes in cognition are indicative of early AD-related pathology. Using a Bayesian method for unsupervised clustering via mixture models, we define an aggregate measure of posterior probabilities (AMPP score) establishing the likelihood of pre-clinical AD. From Baseline through to 54 months, visuo-spatial function had the greatest contribution to the AMPP score, followed by attention and processing speed and visual memory. Participants with the highest AMPP scores had both increasing neo-cortical amyloid burden and decreasing hippocampus volume over 54 months, compared to those in the lowest category with stable amyloid burden and hippocampus volume. The identification of a possible pre-clinical stage in CN participants via this method, without the aid of disease specific biomarkers, represents an important step in utilizing the strength of cognitive composite scores for the early detection of AD pathology.

Overfitting Bayesian Mixture Models with an Unknown Number of Components.

This paper proposes solutions to three issues pertaining to the estimation of finite mixture models with an unknown number of components: the non-identifiability induced by overfitting the number of components, the mixing limitations of standard Markov Chain Monte Carlo (MCMC) sampling techniques, and the related label switching problem. An overfitting approach is used to estimate the number of components in a finite mixture model via a Zmix algorithm. Zmix provides a bridge between multidimensional samplers and test based estimation methods, whereby priors are chosen to encourage extra groups to have weights approaching zero. MCMC sampling is made possible by the implementation of prior parallel tempering, an extension of parallel tempering. Zmix can accurately estimate the number of components, posterior parameter estimates and allocation probabilities given a sufficiently large sample size. The results will reflect uncertainty in the final model and will report the range of possible candidate models and their respective estimated probabilities from a single run. Label switching is resolved with a computationally light-weight method, Zswitch, developed for overfitted mixtures by exploiting the intuitiveness of allocation-based relabelling algorithms and the precision of label-invariant loss functions. Four simulation studies are included to illustrate Zmix and Zswitch, as well as three case studies from the literature. All methods are available as part of the R package Zmix, which can currently be applied to univariate Gaussian mixture models.