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: | Usama Pervaiz |
| Institution: | 3 Billion Pairs Genetic |
| Department: | Computational Genomics |
| Country: | |
| Proposed Analysis: | We are proposing data integration across multiple modalities (e.g., imaging, genetics, clinical data) to bridge the gap in our understanding of Alzheimer’s disease diagnosis using advanced machine-learning algorithms. Specifically, we will use machine learning to integrally analyze MRI brain images, genetic (SNPs), and clinical test data to classify and understand patients with Alzheimer’s disease and mild cognitive impairment. In terms of analysis, we will use variational auto-encoders and convolutional neural networks to extract interpretable features from genetics and imaging data respectively. We will then use these multi-modality features to distinguish the control group from Alzheimer's subjects. Our proposed approach is comprehensive and unique as it plans to use multi-model data and a suite of advanced machine learning techniques to jointly identify brain areas, SNPs, and other clinical features that is predictive of Alzheimer's disease. |
| Additional Investigators | |
| Investigator's Name: | Gabor Soter |
| Proposed Analysis: | We are proposing data integration across multiple modalities (e.g., imaging, genetics, clinical data) to bridge the gap in our understanding of Alzheimer’s disease diagnosis using advanced machine-learning algorithms. Specifically, we will use machine learning to integrally analyze MRI brain images, genetic (SNPs), and clinical test data to classify and understand patients with Alzheimer’s disease and mild cognitive impairment. In terms of analysis, we will use variational auto-encoders and convolutional neural networks to extract interpretable features from genetics and imaging data respectively. We will then use these multi-modality features to distinguish the control group from Alzheimer's subjects. Our proposed approach is comprehensive and unique as it plans to use multi-model data and a suite of advanced machine learning techniques to jointly identify brain areas, SNPs, and other clinical features that is predictive of Alzheimer's disease. |
