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: | Kaustubh Patil |
Institution: | Research Center Juelich |
Department: | Institute oif Neuroscience and Medicine |
Country: | |
Proposed Analysis: | The ADNI data will be used to to test ageing and Alzheimer's biomarkers derived using structural and functional MRI data. Specifically, we will use machine learning methods to (1) directly predict AD and/or MCI status, (2) derive proxy measures such as BrainAGE (difference between chronological and predicted age) and assess if their sensitivity to AD/MCI. The biomarkers will be derived at different spatial resolutions, from voxel-level, whole-brain parcellations as well as comparison with simulation models. The ADNI data may be used in combination with other sources, e.g. Human Connectome Project and UK biobank. |
Additional Investigators | |
Investigator's Name: | Georgios Antonopoulos |
Proposed Analysis: | We will use the ADNI data to evaluate the variance due to difference preprocessing pipelines applies to structural (e.g. sMRIPrep and CAT) as well as functional (e.g. fMRIPrep and CONN) data and their effect on individual-level predictive analyses. The pipelines will be used to assess predictivity of VBM-derived features as well as whole brain and network-based connectivity features for (1) AD/MCI status, and (2) prediction of the chronological age as a proxy for neurodegeneration. |
Investigator's Name: | Shammi More |
Proposed Analysis: | We will use the ADNI data to evaluate the variance due to difference preprocessing pipelines applies to structural (e.g. sMRIPrep and CAT) as well as functional (e.g. fMRIPrep and CONN) data and their effect on individual-level predictive analyses. The pipelines will be used to assess predictive power of VBM-derived features as well as whole brain and network-based connectivity features for (1) AD/MCI status, and (2) prediction of the chronological age as a proxy for neurodegeneration. The focus will be on identification of machine learning pipelines, i.e. preprocessing+feature extraction+learning algorithms, that are suitable for the prediction tasks. |