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: | Leonard Wesley |
| Institution: | San Jose State University |
| Department: | Computer Science |
| Country: | |
| Proposed Analysis: | ABSTRACT: Evidential reasoning (ER) is like to conventional machine learning (ML) approaches in that the method enables integration and analysis of heterogeneous data types, but is distinct in that it predicts what is possible rather than what is probable. Essentially ER predictions identify candidate variables that are promising, but lack sufficient information to correctly classify then, as well as the quantity and type of information needed to reduce classification errors. The calculus is a sound and mathematically proven approach that is ideally suited to represent and reason from heterogeneous data that are to varying degrees incomplete, imprecise, and inaccurate. The aim of this proposal is to apply this approach to outcomes of critical importance for Alzheimer’s disease in the ADNI dataset. One outcome is conversion from healthy aging to eMCI or MCI. A second outcome will be functional disability in MCI for which we will generate an aggregate score of the Pfeffer Functional Activities Questionnaire (FAQ), Everyday Cognition (Study Partner Report), and the Financial Capacity Instrument in patients with MCI. A third outcome will be depressive symptoms on the Geriatric Depression Scale. Initial analyses will include text based data from the family and medical history, neuropsychological battery, biospecimen results, physical/neurological examinations, and MR Image Analysis (Freesurfer ROI analysis, baseline and longitudinal). We will subsequently integrate these text based data with imaging results such as amyloid positivity and resting state fMRI to relate these functional changes to brain substrates. We anticipate that prediction results will advance the state-of-the-art and accuracy in recruiting AD and dementia study participants. |
| Additional Investigators |
