| Title: | Integrating Multimodal Data of Lifestyle, Biomarkers, Imaging and Genetics for Predictive Modeling of Cancer Risk and Outcomes. |
| Lead Institution: | Sun Yat-sen University Cancer Center |
| Principal investigator: |
Application 1049648
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: Cancer etiology and progression involve complex interactions between genetic, environmental, and lifestyle factors. While individual elements have been studied, their synergistic effects and mechanisms-especially in contexts like comorbidities (e.g., obesity)-remain unclear. Advances in genomics (e.g., TfR/GPX4 biomarkers) and imaging enable holistic risk assessment, but integrating these data into clinically actionable insights requires large-scale integrative approaches. This study employs a prospective cohort design, leveraging retrospective data for model development and validation. Objectives: This research aims to investigate interrelationships between lifestyle factors, biomarkers, genetics, and imaging features in cancer development and outcomes. It seeks to develop integrated predictive models for early high-risk identification, elucidate biological mechanisms (e.g., tumor microenvironment interactions), and inform personalized interventions to improve prognosis and survival rates. Scientific Rationale: Multi-faceted data will be collected: lifestyle/comorbidity information via questionnaires/medical records, blood samples for biomarker/genetic analysis, and serial imaging for quantitative features. Advanced statistical methods (Cox regression, mediation analysis) and machine learning will integrate data to build robust predictive models. A large-scale cohort of 50,000-100,000 participants (aligning with biobanks like UK Biobank) is targeted, including substantial cancer cases and a sub-cohort with multi-omics/imaging data. This study will uncover novel pathways, enable early risk stratification, and inform public health strategies, ultimately reducing cancer burden and providing a paradigm for predictive oncology.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 20823 | Dietary inflammatory index and lung cancer risk: multi-cohort evidence and plasma proteomic profiles | Lingli Chen (+11) | 2026 | Lung Cancer |
Enabling scientific discoveries that improve human health