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: | Qing Lu |
| Institution: | University of Florida |
| Department: | Department of Biostatistics |
| Country: | |
| Proposed Analysis: | Artificial intelligence (AI) is a thriving research field with many successful applications in areas such as computer vision and speech recognition. Machine learning methods, such as deep neural networks (DNN), play a central role in modern AI technology. While DNN also holds great promise for human genetic research, the high-dimensional genetic data and complex genetic structure bring tremendous challenges to use DNN in current genetic research. The vast majority of genetic variants on the genome have small or no effects on diseases and fitting DNN on a large number of these genetic variants without considering the underlying genetic structure (e.g., linkage disequilibrium) could bring a serious overfitting issue. Furthermore, while a single disease phenotype is often studied in the classic genetic research, in emerging research fields (e.g., imaging genetics), researchers need to deal with different types of output data (e.g., vectors and matrices). To address these challenges, we will develop a set of new neural network methods for high-dimensional genetic data analysis. Through simulations, we demonstrate the advantages of new methods for high-dimensional genetic data analysis. By applying these new methods to the Alzheimer’s Disease Neuroimaging Initiative (ADNI), we will also evaluate the role of genetic variants in APOE in predicting hippocampus volume change over time. |
| Additional Investigators |
