Practical Experiences with Synthetic Health Data

The application of synthetic data generation (SDG) has been increasing over the recent part. With SDG a machine learning model is trained on existing real data, and it learns the patterns in that data. The model is then used to generate new data that preserve the learned patterns. There are multiple use cases for SDG: privacy, de-biasing, and augmentation.

In this presentation, Dr. El Emam provides an overview of SDG, how to evaluate the privacy vulnerabilities in synthetic data, methods for assessing the utility of synthetic data, as well as applications for de-biasing real-world datasets (RWD) and augmentation in clinical trials and RWD. He reviews specific examples and a summary of evidence.

Bio:

Dr. Khaled El Emam,

Professor, School of Epidemiology and Public Health, University of Ottawa;

Senior Scientist, Electronic Health Information Laboratory, CHEO Research Institute

Dr. Khaled El Emam is a leading Canadian expert in medical AI and health data privacy. He is a Tier 1 Canada Research Chair at the University of Ottawa, directs a major health information lab, advises privacy regulators, and contributes to international committees. He has founded multiple data-focused companies, previously worked at the NRC and Fraunhofer Institute, and holds a PhD in electrical and electronic engineering.