Internship project: Exploring use cases for synthetic data in health

Project Participants

Status: Completed


The use of synthetic data can provide opportunities to conduct lower-risk research projects, train students and early to mid-career researchers, test code and analysis capabilities before completing ethics applications, and trial new technology before implementation. This project would review several key use cases for synthetic data, and provide an analysis/recommendation on what kind of synthetic data would be needed for each, and any other considerations (i.e. access/ethics requirements, amount of data and infrastructure). In addition, this analysis could include a review on associated markets – which organisations (and how many) would benefit in these use cases, and what their current appetite is for using synthetic data.

Project Objectives

  • Identify and describe how users want to apply synthetic data.
  • Environmental scan of the research around synthetic data generation and available software; and
  • Investigate the possible techniques/algorithms for generating synthetic data.

Integrity, Excellence,
Teamwork and Authenticity