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: | Florence Leony |
| Institution: | Yuan Ze University |
| Department: | Industrial Engineering and Management |
| Country: | |
| Proposed Analysis: | We plan to propose a data fusion framework to combine multiple heterogeneous data for classification, specializing in Alzheimer’s disease. The proposed data fusion framework is designed to handle heterogeneous data in terms of size, format, or processing method, which is also well-known as multimodal data. The proposed data fusion framework explores data uncertainty, including outliers and conflicts, and considers data heterogeneity in terms of importance level for each modality. The objective of the research is to correctly classify data by integrating data obtained from different channels. Especially, the implementation for classifying Alzheimer’s Dementia (AD), Mild Cognitive Impairment (MCI), and Cognitive Normal (CN). By exploring the underlying structure of data, better discrimination between each class can be obtained. Numerous studies have been conducted in the field and researchers tried to incorporate more data to recognize patterns associated with the disease. However, a few studies tried to understand the relationship between test results, biomarkers, and structural changes in the brain, while it is critical for diagnosis validation. This raises an opportunity for us to implement our proposed data fusion framework that explores the underlying structure of the multiple datasets to get better discrimination of different status/ stage of Alzheimer’s disease. |
| Additional Investigators | |
| Investigator's Name: | Chen-ju Lin |
| Proposed Analysis: | We plan to propose a data fusion framework to combine multiple heterogeneous data for classification, specializing in Alzheimer’s disease. The proposed data fusion framework is designed to handle heterogeneous data in terms of size, format, or processing method, which is also well-known as multimodal data. The proposed data fusion framework explores data uncertainty, including outliers and conflicts, and considers data heterogeneity in terms of importance level for each modality. The objective of the research is to correctly classify data by integrating data obtained from different channels. Especially, the implementation for classifying Alzheimer’s Dementia (AD), Mild Cognitive Impairment (MCI), and Cognitive Normal (CN). By exploring the underlying structure of data, better discrimination between each class can be obtained. Numerous studies have been conducted in the field and researchers tried to incorporate more data to recognize patterns associated with the disease. However, a few studies tried to understand the relationship between test results, biomarkers, and structural changes in the brain, while it is critical for diagnosis validation. This raises an opportunity for us to implement our proposed data fusion framework that explores the underlying structure of the multiple datasets to get better discrimination of different status/ stage of Alzheimer’s disease. |
