Computational Foundations for Biomedical Data Science

Catalog description

This course provides a hands-on introduction to essential computational tools and workflows required for biomedical data science. Material covers foundational approaches in both Biomedical Informatics and Computational Statistics. Informatics topics emphasize working with Electronic Health Records (EHRs), including deriving clinical phenotypes, utilizing clinical ontologies, and extracting data from relational databases to build analytic datasets. The course also explores rigorous statistical computing methods, such as bootstrapping, permutation testing, and MCMC. Throughout the term, we emphasize the proper implementation and interpretation of these approaches using real-world biomedical and clinical data. Students should possess proficiency in a data science programming language (such as R or Python), including experience with data manipulation and basic functional programming. Prerequisite(s): Enrollment in the Master of Biostatistics Program Health AI track, prior graduate training in computing (BIOSTAT 721 or equivalent), or permission of the Director of Graduate Studies. Credits 3