Synthetic Data

Health City and its partners identified synthetic data generation as one approach to leverage the region’s capacity and partnerships in data, artificial intelligence, and machine learning to fuel health system innovation. Synthetic data accurately simulates patient-derived datasets and, although generated from real world data, is not linked to the individuals from whom the data were derived. Because synthetic data contains no real patient health information, the datasets have the potential to be shared freely among investigators or those in industry without raising patient privacy concerns or contravening the Alberta Health Information Act. The project engaged the Office of the Information and Privacy Commissioner of Alberta to ensure synthetic data can be used in a way that respects the privacy of citizens.

The first phase of the project, which took place in October 2020, validated the first synthetic health dataset in Alberta. The success of Phase I informed the current phase, which aims to establish use cases for the synthetic datasets. Validating synthetic datasets and establishing use cases creates further opportunities for innovators to work alongside the health system while preserving patient privacy. Creating opportunities for innovators and researchers is a vital step in attracting investment to the province.

Health City and the Institute of Health Economics (IHE) are welcomed Merck Canada as a new partner to an innovative Alberta collaboration aimed at exploring the potential uses for synthetic health data. Merck Canada will be joining existing partners Alberta Innovates and the University of Alberta, and will support the acceleration of research in the field of synthetic data use with the ultimate goal of helping improve health outcomes for Canadians.