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: | Niklas Eisl |
| Institution: | Technical University of Munich |
| Department: | AI for Medicine and Healthcare |
| Country: | |
| Proposed Analysis: | Much deep learning research focuses on creating the best possible model with only one source of data, often leaving a lot of useful information unnecessarily on the table. With so much information from many different sources available in ADNI, we are interested in investigating how best to combine these pools of information to achieve the best possible classification of Alzheimer's disease state. Focus will be on how to optimally combine different modalities, taking care not to encode the same information multiple times while allowing correlations and interactions between data sources to be learned. |
| Additional Investigators | |
| Investigator's Name: | Lisa Schmierer |
| Proposed Analysis: | Much deep learning research focuses on creating the best possible model with only one source of data, often leaving a lot of useful information unnecessarily on the table. With so much information from many different sources available in ADNI, we are interested in investigating how best to combine these pools of information to achieve the best possible classification of Alzheimer's disease state. Focus will be on how to optimally combine different modalities, taking care not to encode the same information multiple times while allowing correlations and interactions between data sources to be learned. |
| Investigator's Name: | Simon Koch |
| Proposed Analysis: | Much deep learning research focuses on creating the best possible model with only one source of data, often leaving a lot of useful information unnecessarily on the table. With so much information from many different sources available in ADNI, we are interested in investigating how best to combine these pools of information to achieve the best possible classification of Alzheimer's disease state. Focus will be on how to optimally combine different modalities, taking care not to encode the same information multiple times while allowing correlations and interactions between data sources to be learned. |
