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: | Jiachen Cai |
| Institution: | University of Cambridge |
| Department: | MRC Biostatistics Unit |
| Country: | |
| Proposed Analysis: | The increasing availability of high-dimensional biomarker measurements taken longitudinally can facilitate analysis of the biological mechanisms underlying disease and clustering of patients, as required for precision medicine. Existing approaches can only deal with part of the data structure but fail to jointly model all of them: specifically, Bayesian Latent Factor Analysis (BLFA) [Carvalho et al, 2008] can be used to uncover the latent structure, drastically reducing the dimension; whereas, treating the longitudinal factors as functional data, Dependent Gaussian Processes (DGP) constructed through kernel convolutions [Shi & Choi, 2011] may be appropriate for modeling time-dependent factor trajectories and correlation between factors simultaneously. We proposed an integrative model combining BLFA and DGP to address this gap, and developed an Empirical Bayes/Gibbs Sampler [Casella, 2001] for estimation and inference. We would like to apply this new methodology to ANDI data. |
| Additional Investigators |
