There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Linglong Kong |
| Institution: | University of Alberta |
| Department: | Math & Stat |
| Country: | |
| Proposed Analysis: | The aims of our study is to investigate the relationship between the Alzheimer's disease (AD) and diffusion tensor imaging measures, say, Fractional Anisotropy (FA), along corpus callosum while adjusting demographic and other variables. The FA values are to be obtained by applying the package TBSS in FSL with a masking procedure and they will be treated as functional data of locations along corpus callosum. First, we will look at how AD status (AD, aMCI - amnestic mild cognitive impairment, and HC - healthy controls) are affected by the FA values along corpus callosum at screening (SC). The method we propose to use is a joint modeling approach borrowing from jointly analyzing survival and longitudinal data while assume an underlying latent process using Bayesian methods. Second, we investigate how the FA values affect the Alzheimer's disease assessment scores (ADAS) using partial functional linear model by Reproducing Kernel Hilbert Spacing method (RKHS). Third, we then extend the RKHS to quantile partial functional linear model, not only look at how FA values affect the center part of ADAS but also the tail parts while accounting the possible outliers for ADAS. Forth, we treat FA values along corpus callosum as functional responses to see how they are affected by AD status using varying coefficient models under both mean regression and quantile regression frameworks. The method we will focus on is RKHS. Last but not least, we will check the possible scenarios at the longitudinal case instead of just SC. |
| Additional Investigators |
