Background
Metabolic dysfunction-associated steatotic liver disease (MASLD) is a chronic condition linked to obesity, type 2 diabetes, and dyslipidemia, affecting over 1.2 billion people globally. MASLD progresses from simple steatosis to steatohepatitis (MASH) and fibrosis, with 30% of MASL patients progressing to MASH and 40% of MASH patients developing advanced fibrosis within a decade. The rising prevalence mirrors obesity rates, and MASLD often coexists with diabetes, accelerating liver fibrosis. Current diagnostic tools have limited accuracy, and there are no FDA-approved treatments, underscoring the need for improved biomarkers and personalized therapies.
Aim
This study aims to create a comprehensive biomarker atlas for Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) by integrating clinical, imaging, proteomic, and genetic data. Despite affecting 25% of the global population, MASLD is often underdiagnosed due to reliance on invasive biopsies and varied progression patterns. We hypothesize that combining cross-modal data can uncover the mechanistic links between metabolic dysregulation, genetic factors, and liver injury, leading to the identification of stage-specific biomarkers for precision management.
research questions
1.Which dynamic clinical markers and novel biomarkers can optimize risk stratification and disease progression monitoring in MASLD?
2.How can deep learning integrate radiomics, clinical data, and multi-omics features to develop early diagnostic models and personalized prognostic prediction systems for MASLD?
3.What are the bidirectional mechanistic links between MASLD and chronic diseases!
Scientific rational
Existing biomarkers have suboptimal diagnostic performance, hindering accurate differentiation between steatosis and MASH. This highlights the need for more precise biomarkers to better distinguish stages of liver disease progression.
