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: | Richard Everson |
| Institution: | University of Exeter |
| Department: | Institute for Data Science and AI |
| Country: | |
| Proposed Analysis: | The Early Detection of Neurodegenerative diseases initiative (https://edon-initiative.org) is a global initiative working to develop digital fingerprints for the early detection of diseases that cause dementia. EDoN is working with the BU ADC and other cohorts and centres to gather prospective digital biomarker data. This specific project will examine the use of machine learning for retrospective existing data, particularly in relation to modelling early dementia-related changes and in combining data from multiple datasets. This project will develop robust models of cognitive decline, neuroimaging changes and incident dementia in order to identify which biomarkers and combinations of features may be most useful. In addition it will examine ways in which data from different modalities and multiple cohorts may be used to increase statistical power in machine learning and multivariate statistical models. A combination of advanced multivariate statistical and machine learning techniques will be employed, such as ensemble methods, transfer learning, multi-task learning and Bayesian modelling. Neuropathological data and cerebrospinal fluid biomarkers will be used in subsamples to evaluate the validity and disease specificity of the models. The specific objectives of the project are: • To develop and validate multivariate predictive models of cognitive decline, neuroimaging abnormalities and dementia. * To develop and validate transfer learning and multi-task learning methods for combining data across cohorts (incorporating overlapping features and dementia-related outcomes). In summary, this project aims to advance our understanding of early indicators of early dementia- related changes and thus the ‘high risk’ groups that should be prioritised for disease modifying trials and prevention interventions. This project will also inform future clinical guidelines regarding the early signs and symptoms that should trigger further dementia investigations. |
| Additional Investigators |
