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: | Yuxiao Li |
| Institution: | West China Hospital of Sichuan University |
| Department: | Department of Geriatrics |
| Country: | |
| Proposed Analysis: | To effectively evaluate the short-term effects of healthy lifestyle interventions (diet, exercise, and sleep) on participants with mild cognitive impairment, we aim to develop a brain age model based on machine learning algorithm. Interpretable machine learning methods are used to estimate features (regions, voxels, or vertices) that contribute to the prediction of the model. The established model will be applied to our study to evaluate the between-group variance in predicted brain age before and after intervention. And we will further explore how individual differences in neuroanatomy and behavior drive brain age changes under health lifestyle intervention with model explanation. Regarding the purpose of data using, variations in regional heterogeneous patterns and differences in cortical and subcortical regions for T1 and T2 weighted anatomical data, graph metrics for rest-fMRI data, and white matter integrity (e.g. Fractional anisotropy, mean diffusivity)) for DWI data will be estimated as optional features for machine learning. The demographic data, clinical assessment and cognitive assessment will be used as confounding variables in variance partition analysis. We sincerely hope to be approved. Thank you. |
| Additional Investigators | |
| Investigator's Name: | Sigen A |
| Proposed Analysis: | To effectively evaluate the short-term effects of healthy lifestyle interventions (diet, exercise, and sleep) on participants with mild cognitive impairment, we aim to develop a brain age model based on machine learning algorithm. Interpretable machine learning methods are used to estimate features (regions, voxels, or vertices) that contribute to the prediction of the model. The established model will be applied to our study to evaluate the between-group variance in predicted brain age before and after intervention. And we will further explore how individual differences in neuroanatomy and behavior drive brain age changes under health lifestyle intervention with model explanation. Regarding the purpose of data using, variations in regional heterogeneous patterns and differences in cortical and subcortical regions for T1 and T2 weighted anatomical data, graph metrics for rest-fMRI data, and white matter integrity (e.g. Fractional anisotropy, mean diffusivity)) for DWI data will be estimated as optional features for machine learning. The demographic data, clinical assessment and cognitive assessment data will be used as confounding variables in variance partition analysis. We sincerely hope to be approved. Thank you. |
| Investigator's Name: | Sigen A |
| Proposed Analysis: | To effectively evaluate the short-term effects of healthy lifestyle interventions (diet, exercise, and sleep) on participants with mild cognitive impairment, we aim to develop a brain age model based on machine learning algorithm. Interpretable machine learning methods are used to estimate features (regions, voxels, or vertices) that contribute to the prediction of the model. The established model will be applied to our study to evaluate the between-group variance in predicted brain age before and after intervention. And we will further explore how individual differences in neuroanatomy and behavior drive brain age changes under health lifestyle intervention with model explanation. Regarding the purpose of data using, variations in regional heterogeneous patterns and differences in cortical and subcortical regions for T1 and T2 weighted anatomical data, graph metrics for rest-fMRI data, and white matter integrity (e.g. Fractional anisotropy, mean diffusivity)) for DWI data will be estimated as optional features for machine learning. The demographic data, clinical assessment and cognitive assessment data will be used as confounding variables in variance partition analysis. We sincerely hope to be approved. Thank you. |
