| Title: | Modeling complexity of brain diseases by integrating multimodal data |
| Lead Institution: | Fudan University |
| Principal investigator: |
Application 99876
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
Brain diseases, especially psychiatric diseases and neurodegenerative diseases, have complex biological mechanisms and are usually affected by both genetic and environmental factors. At present, the therapeutic effect of brain diseases is not ideal, which usually varies from person to person. To achieve better therapeutic effect, it is urgent to understand the complexity of many aspects of these diseases. Therefore, this project intends to integrate multimodal data to model the complexity of brain diseases, thus helping the development of precise medicine for brain diseases. The project will model disease's complexity in three aspects: 1) Modeling the interactions between environmental and genetic factors in the dynamic development of brain diseases; 2) Modeling the complexity of comorbidity patterns among brain diseases based on both phenotypic and genotypic data; 3) Modeling the mediated relationships between brain image abnormalities and brain diseases by integrating longitudinal Magnetic resonance imaging (MRI) data. Our proposal meets the purpose of the UK Biobank by two ways: 1) Identification of environmental, phenotypic and genetic factors associated with brain diseases is expected to help early diagnosis, prevention and treatment of these diseases; 2) Modeling the complexity of brain diseases is expected to stratify patients more precisely that can help maximize the treatment efficacy. As we will model disease's complexity by integration of environmental, phenotypic as well as genomic data, we would apply for the whole cohort data, including data now being available and future data when available. The project duration is expected to be three years.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 21455 | EIGNN: An Explainable Imaging-Genetic Neural Network for Robust Alzheimer's Disease Risk Prediction | Zi-Chao Zhang (+8) | 2026 | IEEE Transactions on Medical Imaging |
Enabling scientific discoveries that improve human health