3265 Analysis of High-Dimensional Patient Data in Characterizing Alzheimer’s Disease Progression

Abstract

OBJECTIVES/SPECIFIC AIMS: Our research hypothesis is that resting state fMRI (rsfMRI) data can be used to identify regions of the brain which are associated with cognitive decline in patients – thereby providing a tool by which to characterize AD progression in patients. METHODS/STUDY POPULATION: We used data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) to analyze Mini-Mental State Examination (MMSE) questionnaire scores from 14 patients diagnosed with AD at two measurement occasions. RsfMRI data was available at the first of these occasions for these patients. These rsfMRI data were summarized into 264 node-based graph theory measures of clustering coefficient and eigenvector centrality. To address our research hypothesis, we modeled changes in patient MMSE scores over time as a function of these rsfMRI data, controlling for relevant confounding factors. This model accounted for the high-dimensionality of our predictor data, the longitudinal nature of the outcome, and our desire to identify a subset of regions in the brain most associated with the MMSE outcome. RESULTS/ANTICIPATED RESULTS: The use of either the clustering coefficient or eigenvector centrality rsfMRI predictors in modeling MMSE scores for patients over time resulted in the identification of different subsets of brain regions associated with cognitive decline. This suggests that these predictors capture different information on patient propensity for cognitive decline. Further work is warranted to validate these results on a larger sample of ADNI patients. DISCUSSION/SIGNIFICANCE OF IMPACT: We conclude that different rsfMRI graph theory measures capture different aspects of cognitive function and decline in patients, which could be a future consideration in clinical practice.