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: | Bruno Hebling Vieira |
| Institution: | University of Zurich |
| Department: | Psychologisches Institut |
| Country: | |
| Proposed Analysis: | We plan to develop and test models for the diagnosis and modelling of cognitive alterations in the context of AD. We plan to develop probabilistic models (e.g. semi supervised VAEs) that jointly capture imaging, clinical and cognitive trajectories. We also plan to train deep learning models with built-in interpretability, for the prediction of cognitive decline based on imaging data, which warrants large datasets. |
| Additional Investigators | |
| Investigator's Name: | Roya Hüppi |
| Proposed Analysis: | This proposed analysis aimed to replicate the findings of a previous study by Vieira et al. (2022) on the prediction of future continuous cognitive decline in Alzheimer's disease (AD) using both OASIS-3 and ADNI data to test the generalizability of a machine-learning-based model that combined non-brain data with structural magnetic resonance imaging (MRI) data. |
| Investigator's Name: | Camille Elleaume |
| Proposed Analysis: | For this proposed analysis, normative models derived from a large scale cohort of UK Biobank anatomical magnetic resonance images will be validated using ADNI data. This includes quantifying deviations from the norm in subjects in ADNI and performing transfer learning to adjust the models to ADNI norms. Additionally, machine learning models will be studied in this context to predict cognitive decline in healthy and pathological aging. This is part of Camille's PhD Thesis. |
