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: | Giorgia Tosi |
| Institution: | University of Salento |
| Department: | Psychology |
| Country: | |
| Proposed Analysis: | We are interested in studying the complexity of cognitive impairment through Network Analysis (NA). A network is formed by a set of nodes (i.e., the cognitive performances and clinical symptoms) and the edges connecting those nodes (i.e., the relationships between variables). We plan to use ADNI data to estimate clinical networks and to evaluate how the cognitive and clinical symptoms are related and organized in Alzheimer's Disease. In particular, we will use Exploratory Graph Analysis (EGA) to estimate a Gaussian Graphical Model (GGM) with LASSO regularization, in which edges correspond to partial correlation coefficients. After the GGM estimation, EGA applies a communities detection algorithm (i.e., the walktrap algorithm) to estimate the number of dimensions underlying the specific set of nodes in the given sample. This approach allows for studying the reorganization of cognitive and clinical symptoms in Alzheimer's Disease. In the case panel data are available, we also plan to estimate temporal networks to evaluate which variables can predict cognitive and clinical outcomes in the specific population. In particular, we will use the Dynamic Exploratory Graph Analysis approach, which estimates the number of latent variables and their short-term temporal dynamics. |
| Additional Investigators | |
| Investigator's Name: | Daniele Romano |
| Proposed Analysis: | We are interested in studying the complexity of cognitive impairment through Network Analysis (NA). A network is formed by a set of nodes (i.e., the cognitive performances and clinical symptoms) and the edges connecting those nodes (i.e., the relationships between variables). We plan to use ADNI data to estimate clinical networks and to evaluate how the cognitive and clinical symptoms are related and organized in Alzheimer's Disease. In particular, we will use Exploratory Graph Analysis (EGA) to estimate a Gaussian Graphical Model (GGM) with LASSO regularization, in which edges correspond to partial correlation coefficients. After the GGM estimation, EGA applies a communities detection algorithm (i.e., the walktrap algorithm) to estimate the number of dimensions underlying the specific set of nodes in the given sample. This approach allows for studying the reorganization of cognitive and clinical symptoms in Alzheimer's Disease. In the case panel data are available, we also plan to estimate temporal networks to evaluate which variables can predict cognitive and clinical outcomes in the specific population. In particular, we will use the Dynamic Exploratory Graph Analysis approach, which estimates the number of latent variables and their short-term temporal dynamics. |
