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: | Lining Pan |
| Institution: | Manifest Technologies Inc |
| Department: | N/A |
| Country: | |
| Proposed Analysis: | We plan to process and analyze the de-identified neural data (including structural, functional, diffusion MRI and PET), as well as demographic and clinical/cognitive behavioral data from the ADNI and related datasets including patients with Alzheimer’s disease (AD) and healthy individuals. Specifically, we plan to perform feature extraction and statistical analyses (including via data reduction methods such as Principal Component Analysis and multivariate approaches such as Canonical Correlation Analysis) on the neural and behavioral data to map the relationships between multi-modal functional and receptor imaging neural features with behavioral symptoms, with cognitive performance measures being of primary interest. We further plan to use these relationships to investigate computational methods for patient stratification using these datasets. The goal of the analyses is to develop a framework for identifying patterns of covarying clinical and neural features in patients with AD. Lastly, we plan to use available longitudinal data to study how the neural-behavioral relationships identified in the cross-sectional studies may or may not change over disease progression. |
| Additional Investigators | |
| Investigator's Name: | Jie (Lisa) Ji |
| Proposed Analysis: | We plan to process and analyze the de-identified neural data (including structural, functional, diffusion MRI and PET), as well as demographic and clinical/cognitive behavioral data from the ADNI and related datasets including patients with Alzheimer’s disease (AD) and healthy individuals. Specifically, we plan to perform feature extraction and statistical analyses (including via data reduction methods such as Principal Component Analysis and multivariate approaches such as Canonical Correlation Analysis) on the neural and behavioral data to map the relationships between multi-modal functional and receptor imaging neural features with behavioral symptoms, with cognitive performance measures being of primary interest. We further plan to use these relationships to investigate computational methods for patient stratification using these datasets. The goal of the analyses is to develop a framework for identifying patterns of covarying clinical and neural features in patients with AD. Lastly, we plan to use available longitudinal data to study how the neural-behavioral relationships identified in the cross-sectional studies may or may not change over disease progression. |
| Investigator's Name: | Markus Helmer |
| Proposed Analysis: | We plan to process and analyze the de-identified neural data (including structural, functional, diffusion MRI and PET), as well as demographic and clinical/cognitive behavioral data from the ADNI and related datasets including patients with Alzheimer’s disease (AD) and healthy individuals. Specifically, we plan to perform feature extraction and statistical analyses (including via data reduction methods such as Principal Component Analysis and multivariate approaches such as Canonical Correlation Analysis) on the neural and behavioral data to map the relationships between multi-modal functional and receptor imaging neural features with behavioral symptoms, with cognitive performance measures being of primary interest. We further plan to use these relationships to investigate computational methods for patient stratification using these datasets. The goal of the analyses is to develop a framework for identifying patterns of covarying clinical and neural features in patients with AD. Lastly, we plan to use available longitudinal data to study how the neural-behavioral relationships identified in the cross-sectional studies may or may not change over disease progression. |
| Investigator's Name: | Alan Anticevic |
| Proposed Analysis: | We plan to process and analyze the de-identified neural data (including structural, functional, diffusion MRI and PET), as well as demographic and clinical/cognitive behavioral data from the ADNI and related datasets including patients with Alzheimer’s disease (AD) and healthy individuals. Specifically, we plan to perform feature extraction and statistical analyses (including via data reduction methods such as Principal Component Analysis and multivariate approaches such as Canonical Correlation Analysis) on the neural and behavioral data to map the relationships between multi-modal functional and receptor imaging neural features with behavioral symptoms, with cognitive performance measures being of primary interest. We further plan to use these relationships to investigate computational methods for patient stratification using these datasets. The goal of the analyses is to develop a framework for identifying patterns of covarying clinical and neural features in patients with AD. Lastly, we plan to use available longitudinal data to study how the neural-behavioral relationships identified in the cross-sectional studies may or may not change over disease progression. |
