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: | Daniel Baer |
Institution: | Medical University of South Carolina |
Department: | Public Health Sciences |
Country: | |
Proposed Analysis: | I am a biostatistics PhD candidate at the Medical University of South Carolina. My dissertation research concerns the development of statistical models at the intersection of longitudinal data analysis and covariate selection as motivated by the study of Alzheimer's disease. One model I am developing is relevant to the data scenario where we observe multiple longitudinal outcomes for a given patient. For instance, this data scenario may arise when a battery of neuropsychological assessments are given to a patient over time. In this scenario, a research may desire a statistical model which can achieve the following: -Account for temporal correlation in each longitudinal outcome. -Account for between-outcome correlation amongst the multiple longitudinal outcomes. -Handle irregularly-spaced patient measurement occasions. -Select patient covariates most associated with the multiple longitudinal outcomes. My statistical model aims to address these data complexities using a fully-Bayesian framework, where I have derived a Markov chain Monte Carlo Gibbs sampler to fit my model. In order to evaluate my model using real-world data, I would like to request from the ADNI any available data relevant to the aforementioned data scenario; that is any data arising from a patient sample where multiple longitudinal outcomes (of cognition) are collected for each patient, along with any corresponding patient covariate data (e.g. patient demographic factors). By facilitating the evaluation of my model using real world data, I can submit my manuscript relating to this work for publication. Ultimately, this manuscript will detail a statistical method which will be of great use to researchers encountering the aforementioned data scenario in the study of Alzheimer's disease and related dementias. |
Additional Investigators |