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: | Yikuan Li |
| Institution: | Northwestern University |
| Department: | Preventive Medicine |
| Country: | |
| Proposed Analysis: | Heterogeneous data, including genetics, image data, clinical variables, are all essential to predict Alzheimer's disease. Learning the multimodal representation from multiple data formats is the bedrock for the predictive models. Current research in this area usually modals different data sources separately and add merging function to integrate them together. However, this genre of methods ignore the interaction of datasets. Our preliminary research on thoracic disorder identification shows that the joint learning strategy using transformer-based model can significant improve the performance of multimodal representation learning. We would like to transfer our success to the prediction of AD. |
| Additional Investigators | |
| Investigator's Name: | Hanyin Wang |
| Proposed Analysis: | Heterogeneous data, including genetics, image data, clinical variables, are all essential to predict Alzheimer's disease. Learning the multimodal representation from multiple data formats is the bedrock for the predictive models. Current research in this area usually modals different data sources separately and add merging function to integrate them together. However, this genre of methods ignore the interaction of datasets. Our preliminary research on thoracic disorder identification shows that the joint learning strategy using transformer-based model can significant improve the performance of multimodal representation learning. We would like to transfer our success to the prediction of AD. I am the co-author of the main applicant. |
