Aims: This study aims to explore the relationships between chronic diseases such as cardiovascular conditions, metabolic disorders, respiratory illnesses, cancers, autoimmune diseases, chronic kidney disease, liver diseases, neurological disorders, and mood disorders with demographic, sociological, lifestyle, metabolic biomarkers, and genetic markers. Additionally, it seeks to identify factors affecting the efficacy and safety of treatments for these diseases and to develop AI algorithms that integrate imaging and genetic data to enhance the accuracy of disease diagnosis and prognosis.
Scientific Rationale: Chronic diseases pose a significant global health challenge, increasing the burden on healthcare systems and affecting patients’ quality of life. Personalized medicine is crucial for improving treatment outcomes, necessitating a deeper understanding of diseases’ risk factors and mechanisms. This project employs deep learning, machine learning, statistical learning, and genomic analysis to integrate multimodal data, aiming to precisely identify disease biomarkers and genetic variants to guide diagnosis, treatment, and prognosis.
Project Duration: 3 years.
Public Health Impact: By improving the early diagnosis rates and treatment outcomes for chronic diseases, this research could reduce the risk of late-stage diagnoses, optimize the allocation of medical resources, and promote the development of personalized medicine. Furthermore, the outcomes of this project may help reduce healthcare costs and increase public awareness of diseases, positively impacting public health.