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: | Yushu Shi |
Institution: | University of Missouri Columbia |
Department: | Statistics |
Country: | |
Proposed Analysis: | Alzheimer’s disease (AD) is a progressive disease that destroys memory and other important mental functions. Multiple risk factors have been associated to poor outcomes, including advanced age, family history and head injury. However, the predictive value of many prognostic factors has not been robustly evaluated and remains unclear and inconsistent across studies. There are many implications of having unreliable predictors in AD, as these prognostic factors are used in medical decisions. We propose a novel statistical method based on knockoff feature selection technique and Bayesian modeling. It can incorporate both continuous and categorical covariates for a heterogeneous population. The method guarantees good false discovery control while significantly improves the power of detecting true predicting variables compared with existing methods. We plan to use the clinical and demographical variables at the first screen as predictors and time till mild AD as the outcome of interest. The proposed method will help to identify prognostic factors that are truly predictive of the AD conversion time with false discovery rate under control. |
Additional Investigators |