ADNI data is made available to researchers around the world. As such, there are many active research projects accessing and applying the shared ADNI data. To further encourage Alzheimer’s disease research collaboration, and to help prevent duplicate efforts, the list below shows the specific research focus of the active ADNI investigations. This information is requested annually as a requirement for data access.
|Principal Investigator's Name:||Pawel Markiewicz|
|Institution:||University of Konstanz|
|Department:||Department of Computer and Information Science|
|Proposed Analysis:||Development of new methods to probabilistic diagnosis and prognosis of neurodegeneration using high dimensional imaging datasets and other relevant biological variables. 1. The aims of the new method(s) a. Primary use of FDG and Amyloid PET datasets. b. Use of other biological variables such as: genetics (ApoE, CSF, clinical diagnosis, etc.) c. Optimal signal extraction in the presence of measurement and biological variability. d. Separation the signal defining the current neurodegenerative state from the signal corresponding to the rate and path of neurodegeneration. e. Accounting for uncertainties and variabilities introduced by limited accuracy of clinical diagnosis. f. Investigation of the effects of spatial and intensity normalisations of brain images. 2. Statistical Tools a. Use of probabilistic approach (Bayesian statistics) b. Reinforcement learning where limited accuracy of the label data and data itself exists. c. Investigation of the structure of the highly-dimensional datasets by the use of unsupervised methods (PCA, etc.). 3. Application a. Diagnosis of AD and its subtypes. b. Prognosis: Prediction of progression rates based on a given longitudinal image datasets. c. Identification of possible dementia subtypes and their corresponding stages of progression. d. Reliable estimation of the rate of neurodegeneration.|