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: | Haiping Zhang |
Institution: | Capital Medical University |
Department: | Epidemiology and Health Statistics |
Country: | |
Proposed Analysis: | Aiming at big data with heterogeneous characteristics among multi-category data such as imagingomics, proteomics, genomics data and scales, based on the elastic network method, we study the adaptive group elastic network (AGEN) method , Assign weights to different groups, improve the penalty items through the weighting mechanism and reduce the dimensionality, which can solve the difficulties in the ultra-high dimensional and multi-omics heterogeneous analysis of different omics markers; for the lack of early diagnosis of some Alzheimer's disease (AD) Gold standard, low degree of distinction between data classes, difficult classification, quasi-integrated Transfer Learning (TL) and Generating Adversarial Networks (GANs) combined method to build based on brain multi-modal PET/MRI images Transfer Learning-Generating Adversarial Networks (TL-GAN). In the process of model migration learning, the first to use the pre-training network to train the target layer on the target data set. For the target with some labels during the sample migration process, part of the label of the source and target domain can be repeated in the target domain after reweighting. Training, and then build a classification diagnosis model to classify Alzheimer’s disease (AD), mild cognitive impairment (MCI), and healthy people; then simulate and verify the optimization parameters, in order to improve the diagnosis rate of AD and significantly improve the patient’s health The 5-year survival rate lays a scientific basis. |
Additional Investigators |