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: | Liang Zhu |
| Institution: | University of Texas Health Science Center at Houston |
| Department: | Internal Medicine, Biostatistics & Epidemiology Re |
| Country: | |
| Proposed Analysis: | This project aims to investigate how to predict the Alzheimer’s Disease (AD) progression for a patient’s next medical visit through using information from previous visits in ADNI data. Data from baseline and follow-ups in different phases will be combined as a longitudinal data. Long short-term memory recurrent neural networks (RNN) will be adopted, which will use an enhanced “many-to-one” RNN architecture to support the shift of time steps. The information used for prediction of progression include magnetic resonance imaging (MRI), positron emission tomography (PET), other biological markers, and clinical and neuropsychological assessment. Considering the high-dimensional imaging data, we will try dimension-reduced voxel-level features, region-of-interest (ROI) level features, or landmark-based features and select the one with the best result. Cross-validation will be used. Results will be compared to deep learning methods (i.e., deep convolutional neural network) using only the baseline data or only the last visit data. The learned model will be used as a pre-trained model on prediction of AD progression in the AIBL data. |
| Additional Investigators |
