Using R to derive robust insights from real-world health care data

Real-world data (RWD) and real-world evidence (RWE) are playing an increasing role in health care decisions. Real-world data can come from a variety of sources, including electronic health records (EHR), claims, and registries, and captured in a variety of data formats. Because of their diversity in source and format, real-world data are rarely ‘analysis-ready’ for specific use-cases. In this workshop, we describe a framework and techniques for using R tools, such as the tidyverse and pointblank package, to assess and derive robust, repeatable insights from real-world data. We cover topics such as, assessing data for use-case suitability, transforming data into 'tidy' analysis ready data (ARD), and surfacing data provenance so collaborators can understand, for example, when patients are included in the final analysis and why.