Multi-Modal Data Integration for Inflammatory Bowel Disease
Inflammatory Bowel Disease (IBD) is a relapsing and remitting immune-mediated disease characterized by chronic inflammation and damage of the gastrointestinal tract. In the USA alone, it is estimated that at least 58,000 children and 1.2 million adults suffer from IBD, with both incidence and prevalence rising. The main disease entities are Crohn’s Disease (CD) and ulcerative colitis (UC) which present with different clinical and pathological phenotypes but share genetic risk factors and treatment options. Currently, treatment strategies are based on assessment of disease activity and phenotyping of the disease severity including history of complications and disease location. To improve on the clinical classification of IBD and enable precision medicine approaches, we need to go beyond clinical phenotyping, and integrate molecular data with clinical data to better define molecular and cellular subphenotypes that are associated with disease complications and treatment response.
The history of IBD research at the Mount Sinai Health System in New York goes back to 1932 with the first description of Crohn’s Disease by Dr. Burrill B. Crohn and is up until today a major research focus at Mount Sinai (MS). In collaboration with clinician researchers at MS, we aim to develop clinically meaningful machine learning models to potentially forecast the progression of disease and enable clinical sub-phenotyping of the disease. Data of interest includes electronic health records, clinical notes and reports from Radiology and Pathology as well as EHR-linked Omics data.
Please reach out in case you are interested in a research internship or master thesis in context of the described project, and have a look at our project page.