This supplement is to a funded R01 called ADNI Psychometrics. This Supplement builds on the Second Specific Aim of the funded parent grant.
That Aim focused on characterizing brain structure and functioning for people with different cognitively- defined subgroups of Alzheimer's disease. The Supplement adds one technique for analyzing the structural data we are already analyzing, and adds analyses of functional data we had not previously been planning to analyze. The new technique for structural data is machine learning. We have the opportunity to collaborate with a talented faculty member in Biomedical Informatics who has specific expertise in machine learning approaches to anatomical data (J Gennari). Dr. Genarri will supervise machine learning approaches to complement the various analytical approaches we already have underway for Aim 2. The new functional data analyses incorporate measurements of blood oxygen level dependent (BOLD) data from resting state functional connectivity MRI (fcMRI) data collected by ADNI. Those data enable the characterization of functional connectivity. There are many levels of correlation in the analyses of longitudinal fcMRI data, and another talented faculty member in Radiology has specific expertise in analyzing these data (T Madhyastha). Dr. Madhyastha will supervise analyses of longitudinal fcMRI data from the cognitively-defined subgroups of Aim 2, which will provide important additional information regarding whether the functional connectivity patterns of people in these subgroups are similar to or different from each other.
This Supplement proposal builds on the second aim of R01 AG 029672, 'ADNI Psychometrics (P Crane, PI) , which is to use ADNI's rich neuroimaging data to compare metabolism and brain structure correlates of cognitively defined Alzheimer's disease subgroups. This proposal would add analyses of functional connectivity, and would add machine learning approaches to the analytic strategies already being pursued by the investigators. This Supplement Proposal would substantially augment the scientific value of the overall study.
Showing the most recent 10 out of 44 publications
