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: | Long Xie |
| Institution: | Siemens Healthineers |
| Department: | Digital Technology Innovation |
| Country: | |
| Proposed Analysis: | Curing Alzheimer’s disease (AD) and related dementias (ADRD) is one of the great challenges of our generation. New drugs for Alzheimer's will lead to increased demand for differential diagnosis, staging to identify suitable patients, quantifying disease progression and monitoring to ensure there are no adverse drug reactions. Artificial intelligence (AI) has the potential to support clinicians in these tasks, but like the clinician needs to consider multimodal information, i.e. neuroimaging, cognitive measures, biofluid biomarkers, or the combination of them. We will develop machine learning based data latent representations that encode multimodal information and demonstrate their value in clinical tasks. (1) Dementia results from multiple underlying diseases, including AD, fronto-temporal dementia, vascular dementia and so on. Due to conflicting treatment options, accurately differentiating between different diseases and different disease stages has been identified as crucial task for dementia care and related clinical trials. Combining data from ADNI with datasets targeting other types of dementia, we will build a model to achieve high accuracy in differential diagnosis. (2) We will develop machine learning algorithm to process the multimodal data, i.e. neuroimaging, cognitive measures, biofluid biomarkers from ADNI to derive measurements that are related to disease severity. Such measurements can serve as biomarkers for early detection, tracking disease progression and evaluate treatment effectiveness. (3) In addition, there is a pressing need for monitoring adverse side effects of potential treatments, such as ARIA, with FDA approval of the first treatments for AD. We will use data from ADNI to build generative deep learning models of image appearance of the normal aging brain. Such models can help to identify deviations from normal aging brain, which can be used to detect abnormalities, such as adverse side effects, when combined with other datasets. We anticipate publishing results of the research in academic conferences, journals and/or arxiv. |
| Additional Investigators |
