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: | Ali Abedi |
Institution: | Toronto Rehabilitation Institute |
Department: | KITE |
Country: | |
Proposed Analysis: | There is a large volume of healthcare-related data generated by hospitals and institutions all over the world. This valuable data can be used to train machine-learning and deep-learning models. In conventional machine-learning methods, all institutions send their data to a centralized server, and model training is performed centrally on the server. However, medical data is private in nature, and sharing this data with the server causes different legal, privacy, and data-ownership problems, especially between international institutions. In our project, we try to develop a new federated-learning framework for training our machine-learning models in a decentralized manner. In our scenario, institutions do not send their raw private data to the server. Each institution trains a model locally using its raw data. Then, all institutions send their locally-trained models to the server. Finally, the curator server aggregates all received models and create a global model that can be utilized by all institutions. Since the ADNI dataset is multi-institutional, it is ideal to be used in our experiments about developing a federated-learning algorithm. |
Additional Investigators |