| Title: | Investigation of Genetic and Lifestyle Determinants in Chronic Non-Communicable Diseases |
| Lead Institution: | Fujian Provincial Hospital |
| Principal investigator: |
Application 230583
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
Our research project aims to comprehensively explore the roles of genetic and lifestyle factors in chronic non-communicable diseases (such as diabetes,heart disease, and cancer). By employing statistical analysis and machine learning techniques, we hope to uncover how these factors collectively impact health. Firstly, we will use statistical models to investigate the relationships between genetic and lifestyle factors and these diseases. These models will help us identify which factors significantly increase or decrease the risk of developing these conditions. Next, we will conduct stratified and interaction analyses to uncover the combined effects of different factors. For example, we will group samples by genetic type or lifestyle and evaluate the independent effects of each factor within these groups. We will also use interaction analysis to understand the interplay between genetic and lifestyle factors. Additionally, we will employ machine learning techniques to handle large-scale data. This will include the use of random forests, support vector machines, and neural networks. Machine learning will help us accurately predict individual disease risk and identify high-risk feature combinations and complex gene-environment interaction patterns. Mendelian randomization will serve as a robust tool to help us determine the causal relationships of genetic factors and their impact on lifestyle factors. This method allows us to avoid confounding variables, providing a clearer understanding of the connections between genes and diseases. The entire project is expected to last three years. Through this research, we aim to gain a deep understanding of the roles of genetic and lifestyle factors in chronic non-communicable diseases, providing scientific evidence for personalised prevention and treatment strategies and optimising public health policies. Incorporating machine learning techniques enhances the flexibility and precision of our analysis, making our research more forward-looking and applicable. The ultimate goal of this research is to improve our understanding of chronic non-communicable diseases, thereby enhancing early prevention and treatment outcomes and contributing to public health.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 18771 | Association between physical activity and all-cause mortality in rheumatoid arthritis: evidence from NHANES and UK Biobank cohort studies | Haodong Zheng (+6) | 2026 | Arthritis Research & Therapy |
Enabling scientific discoveries that improve human health