Students will be exposed to scientific methods and processes to extract knowledge and insights from structured and unstructured data in this course. This course will leverage advanced statistics, data analysis, machine learning, and related data methodologies to analyze, understand, model, and gain novel knowledge from data. I shall present an introduction to clinical epidemiology, predictive analytics, comparative effectiveness and health services research, clinical prediction rules, and patient-centered outcomes research. Students will learn to apply health care analytics, including using methodologies to extract, transform, and load data while maintaining data quality, performance improvement, and innovation projects. An introduction to research informatics tools such as REDCap, i2b2, and TriNetX will be presented during the course. The OMOP Common Data Model will be introduced. Students will learn database design and modeling using a hands-on experience with a specific focus on the conceptual model: the logical structure of the entire database. The course will address conceptual schemas, database design, entity-relationship diagram (ERD), external and internal models, normalization, and data independence (logical and physical). This course will have a heavily applied aspect, with students utilizing Python, JavaScript, HTML5/CSS, API Interactions, SQL, Tableau, R, and Git/GitHub.
Upon completing the course, students will know how to describe and utilize the basic and essential tools of fused data analysis, epidemiology, and statistics.