Synthetic data generation (SDG) is one approach for creating non-identifiable information. This means that the information is deemed de-identified (or anonymized) and therefore can be used and disclosed for secondary purposes without having to go back and obtain additional consent from the data subjects. Typical use cases including providing data for advanced machine learning projects, software testing, as well as training and education.

The purpose of this webinar is to provide a general introduction to synthetic data generation, explaining what it means and how it works, what technologies are used for synthetic data generation, and provide an overview of the use cases where synthetic data can provide value in the context of real world data and clinical trial data. This presentation will also examine other methods for deriving non-identifiable data and compare them to SDG.

Examples from some of the projects that we have worked on will be presented to illustrate the various points and show SDG being applied in practice.