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: | Jiajie Peng |
| Institution: | Northwestern Polytechnical University |
| Department: | Computer Science |
| Country: | |
| Proposed Analysis: | Currently, the incidence Alzheimer disease (AD) is increasing around the world but it is still difficult to predict the disease risk level for individuals. Although there is some existing evidence to suggest that some genetic variants can increase the AD risk, there is no reliable method for AD risk prediction. Therefore, further research is required. A key public health need is to identify individuals at high risk for AD to enable enhanced screening or preventive therapies. Recent research shows that genome-wide polygenic score based on common variations can identify individuals at high risk for several diseases (like Type 2 diabetes, breast cancer). However, people do not know whether common variations can identify individuals at high risk for AD. In this study, we will develop a tool to identify individuals at high risk for AD based on the genome-wide polygenic scores. Our research includes several steps: first, we will double check the power of PRS score for disease risk prediction on several diseases including CAD Atrial fibrillation, Type 2 diabetes, Breast cancer. Second, we will develop a novel method considering genome-wide polygenic score for AD risk prediction. The proposed project will use machine learning models to analyze existing data collected by ADNI Data Project. This is the first research to use genome-wide polygenic scores for the disease risk prediction of AD. Our research will provide a powerful tool for AD risk prediction for individuals. The tool could also be applied to other diseases. The public, especially AD high-risk individuals, could be supported to enhance screening or preventive therapies and to improve the quality of later life and save on future healthcare costs. |
| Additional Investigators | |
| Investigator's Name: | Jingyi Li |
| Proposed Analysis: | Currently, the incidence Alzheimer disease (AD) is increasing around the world but it is still difficult to predict the disease risk level for individuals. Although there is some existing evidence to suggest that some genetic variants can increase the AD risk, there is no reliable method for AD risk prediction. Therefore, further research is required. A key public health need is to identify individuals at high risk for AD to enable enhanced screening or preventive therapies. Recent research shows that genome-wide polygenic score based on common variations can identify individuals at high risk for several diseases (like Type 2 diabetes, breast cancer). However, people do not know whether common variations can identify individuals at high risk for AD. In this study, we will develop a tool to identify individuals at high risk for AD based on the genome-wide polygenic scores. Our research includes several steps: first, we will double check the power of PRS score for disease risk prediction on several diseases including CAD Atrial fibrillation, Type 2 diabetes, Breast cancer. Second, we will develop a novel method considering genome-wide polygenic score for AD risk prediction. The proposed project will use machine learning models to analyze existing data collected by ADNI Data Project. This is the first research to use genome-wide polygenic scores for the disease risk prediction of AD. Our research will provide a powerful tool for AD risk prediction for individuals. The tool could also be applied to other diseases. The public, especially AD high-risk individuals, could be supported to enhance screening or preventive therapies and to improve the quality of later life and save on future healthcare costs. |
