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: | Shan Yu |
| Institution: | Iowa State University |
| Department: | Department of Statistics |
| Country: | |
| Proposed Analysis: | Early diagnosis of Alzheimer's disease (AD), while still at the stage known as mild cognitive impairment (MCI), is important for the study of AD and the development of new treatments. However, brain degeneration in MCI evolves with time and differs from patient to patient, making the early diagnosis a very challenging task. Motived by the above challenge, we consider a functional linear Cox regression model for characterizing the association between time-to-event data and a set of clinical and imaging predictors. The functional linear Cox regression model incorporates functional data analysis for modeling the functional predictors and a high-dimensional Cox regression model to characterize the joint effects of both imaging and clinical predictors on the time-to-event data. We propose flexible multivariate splines over triangulations to estimate the slope function and develop an efficient algorithm to obtain the proposed estimates of unknown linear coefficients and slope functions. We demonstrate our proposed method by using simulations and the analysis of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data. The time of conversion from MCI to AD can be treated as time-to-event data. Patient-level features, such as age, gender, and education length are included as the scalar predictors. FDG-PET images are treated as 2D or 3D functional predictors. To create a large and diverse inference sample for our proposed research, we need to access to the ADNI database. |
| Additional Investigators |
