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: | Charmake Moussa Abdi |
| Institution: | Université de Mohamed 6 de Science et de la santé |
| Department: | 'Ecole Supérieure de Génie Biomédical |
| Country: | |
| Proposed Analysis: | Multimodal Neuroimaging Analysis for Early Detection of Alzheimer's Disease Dear ADNI Review Committee, We propose to conduct a multimodal neuroimaging study using data from the ADNI database. Our primary goal is to identify the earliest possible neuroimaging biomarkers of Alzheimer's disease (AD), focusing on both structural (MRI) and functional (FDG-PET, Amyloid PET) brain changes. Specifically, our proposed analysis includes the following steps: Data Preprocessing: We will apply standard preprocessing techniques to the neuroimaging data, including motion correction, spatial normalization, and smoothing for MRI data, and standard uptake value ratio (SUVR) normalization for PET data. Feature Extraction: We will extract features from the preprocessed neuroimaging data using voxel-based morphometry for MRI data and voxel-based analysis for PET data. Additionally, we plan to calculate cortical thickness and subcortical volume measures using surface-based morphometry. Machine Learning Model Training: We plan to train machine learning models, such as support vector machines and deep learning networks, using the extracted features. The aim is to classify individuals into AD, mild cognitive impairment (MCI), and healthy control (HC) groups. Model Validation: We will validate our models using cross-validation methods and by assessing their performance on a separate test set. We will use accuracy, sensitivity, specificity, and area under the ROC curve as our main performance metrics. Interpretation of Results: We will interpret the features that are most important for classification. This could provide insights into the brain regions most affected in the early stages of AD. We plan to adhere to all conditions of use of the ADNI database, including data privacy and security measures, and providing appropriate citation in any publications resulting from this work. Thank you for considering our request. Sincerely, Charmake Moussa Abdi Ecole Supérieure de Génie Biomédical |
| Additional Investigators |
