This project aims to develop an AI-driven framework for predicting and modeling the development and progression of chronic diseases and aging by integrating diverse multimodal data, including questionnaire data, physical measurements, biomarkers and omics data, healthcare records, environmental exposures, wearable data, and imaging data to construct individualized health trajectories.
In addition to chronic disease progression, the project will examine how multimodal risk profiles influence susceptibility to infectious diseases, infection severity, recovery patterns, and long-term health burden, particularly among aging populations and individuals with pre-existing chronic conditions.
The primary research questions include:
1) How can we predict the onset and progression of aging and chronic diseases such as cardiovascular diseases, cancer, diabetes, dementia, depression, and anxiety?
2) What are the most significant risk factors influencing aging, chronic disease progression, and infectious disease severity and outcomes across different populations?
3) What mechanisms drive aging, chronic disease progression, and differential responses to infectious exposures, and how can these insights help predict health outcomes?
4) How can AI and multimodal data be utilized to identify personalized intervention strategies for prevention and treatment?
The integration of lifestyle factors, omics data, and clinical records will enhance disease prediction models, supporting early detection and proactive disease management.
