| Title: | Statistical and Machine-Learning Methods for Genetic and Health-Record Data |
| Lead Institution: | Colorado State University |
| Principal investigator: |
Application 207159
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
Scientific rationale: Individual-level genetic profile variations have different impacts on diseases. Numerous genes have been identified to be associated with complex diseases, including breast cancer, Alzheimer's disease, schizophrenia, etc. Due to the limited understanding of genetic structures, it is beneficial to integrate genetic data with other information from the UK Biobank, such as electronic health records, so that we are able to model unseen underlying genetic effects through the time-varying phenotypes. Aims: the aims of this project include (1) developing novel statistical methods for identifying genes associated with Alzheimer's disease in a single tissue or cell type; (2) integrating genetic data with electronic health records to analyze the complex time-varying genetic regulation. Project duration: three years Public health impact: According to the World Alzheimer Report 2021, over 55 million people have dementia worldwide, and it is now the 7th leading cause of mortality. Dementia becomes a burden to both society and families. Also, this increasing number of people seeking a diagnosis owing to dementia will become a challenge in the future. By investigating the genetic association varying over time, we will contribute to the prevention of dementia or a call of attention before first diagnosis.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 19166 | A Powerful Transformation of Quantitative Responses for Biobank-Scale Association Studies | Yaowu Liu (+1) | 2025 | Journal of the American Statistical Association |
Enabling scientific discoveries that improve human health