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: | Benjamin Goudey |
Institution: | University of Melbourne |
Department: | Computing and Information Systems |
Country: | |
Proposed Analysis: | We will be making use of the datasets within ADNI to construct predictive models of AD-related outcomes using machine learning models. There are three streams of work we are considering: 1) how to adapt machine learning models to the characteristics of AD-related longitudinal datasets (small sample size, noisy measurements, longitudinal but with missing data)? 2) How can polygenic risk score development be improved for AD-related traits and how might such genetic risk scores be integrated? 3) How can we use cognitive data to predict AD-related outcomes? This work is being conducted as part of a joint initiative between IBM Research and The University of Melbourne (led by Prof. Colin Masters) and we are working with our collaborators in AIBL. |
Additional Investigators | |
Investigator's Name: | Victor Fedyashov |
Proposed Analysis: | Victor Fedyashov is guiding the research across all domains of this project. Specifically, he will be looking at 1) the ability to identify latent variables from across multiple biomarkers which may provide insight into the biological basis of AD; 2) The impact of interval-censored informed survival analysis compared to standard right-censored models on common AD survival analyses 3) The ability of blood biomarkers to predict AD outcomes, with a particular focus on Bayesian methodologies |
Investigator's Name: | Xiyuan Zhang |
Proposed Analysis: | Xiyuan will be looking at the construction and utility of polygenic risk scores for AD-related traits. |
Investigator's Name: | Shu Liu |
Proposed Analysis: | Shu will be looking at the prediction of AD-related traits (such as levels of PET/CSF amyloid) from cognitive tests and visa-versa using machine learning techniques. |
Investigator's Name: | Martin Saint-Jalmes |
Proposed Analysis: | Martin will be looking at the adaptation of Bayesian methodologies, primarily Gaussian processes, for predicting AD-related outcomes both cross-sectionally and longitudinally. His work will integrate all modalities of data. |
Investigator's Name: | Adam Kowalczyk |
Proposed Analysis: | Adam Kowalczyk will be exploring the association and utility of multi-gene/SNP combinations with AD outcomes. |
Investigator's Name: | Uditi Shah |
Proposed Analysis: | Looking at the predictive utility of family history combined with other types of variables for the purposes of GWAS. |