Concept Set Distributions

Concept Set Distribution (CSD) checks provide distributions of concepts that form or represent a particular variable in a dataset. The purpose of the checks is to understand how concept sets drive the prevalence or clinical composition of variables for a particular study. For example, to identify “asthma” in a primary care cohort, wheezing or uncomplicated asthma may be the most common concept represented, but concepts related to asthma exacerbation or severe asthma may be most common in a more specialized respiratory cohort.

Access technical code and implementation requirements for this module on GitHub.