| Title: | Neuroimaging and WGS to identify variant loci and foci of neurological and pan-vascular disease, modeling multiple co-morbidity risk prediction models. |
| Lead Institution: | Hunan University of Chinese Medicine |
| Principal investigator: |
Application 592923
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
Research Questions: 1. What are the causal associations between mental illness and common population risk factors, including vanity, cardiometabolic metrics, and their stratification by age and sex? Association of mental illness with various common risk factors in the primary study cohort. 2. How do metabolomic and proteomic profiles intersect between neurological and whole-vessel diseases? 3. Can deep learning and advanced geometric diffusion network algorithms elucidate structural brain changes associated with disease etiology? Objectives: 1. Establish Risk Correlations: Conduct cohort studies integrating neuroimaging and whole-genome sequencing (WGS) to identify genetic loci and foci associated with psychiatric disorders and whole-vessel diseases. 2. Develop Predictive Models: Employ machine learning techniques to develop robust comorbidity risk prediction models based on large-scale population datasets. 3. Explore Metabolic Pathways: Utilize genome-wide association studies (GWAS), WGS, proteomics, and metabolomics to identify shared metabolic signatures and aging-related biomarkers between neurological and whole-vessel diseases. 4. Advance Neuroimaging Analysis: Analyze large-scale neuroimaging datasets with deep learning and geometric diffusion network algorithms to uncover correlations between brain structural changes and disease progression. Scientific Rationale: Neurological and whole-vessel diseases are linked by overlapping risk factors such as genetic susceptibility, metabolic dysregulation, and structural brain alterations. This project integrates multi-omics data with advanced computational frameworks to investigate these relationships, addressing critical gaps in understanding comorbidities and advancing biomarker development for early diagnosis and precision interventions.Deep learning models, combined with neuroimaging, provide novel opportunities to untangle the complex associations between brain structure and systemic diseases.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 16080 | Association between physical activity patterns and the risk of stroke phenotypes: an accelerometer-based prospective cohort study from the UK Biobank | Yiming Shi (+9) | 2025 | BMC Public Health |
Enabling scientific discoveries that improve human health