Synthetic data as an enabler for machine learning applications in medicine

Jean-Francois Rajotte; Robert Bergen; David L Buckeridge; Khaled El Emam; Raymond Ng; Elissa Strome

doi:10.1016/j.isci.2022.105331

Synthetic data as an enabler for machine learning applications in medicine

iScience. 2022 Oct 13;25(11):105331. doi: 10.1016/j.isci.2022.105331. eCollection 2022 Nov 18.

Authors

Jean-Francois Rajotte¹, Robert Bergen¹, David L Buckeridge², Khaled El Emam³, Raymond Ng¹, Elissa Strome⁴

Affiliations

¹ Data Science Institute, University of British Columbia, Vancouver, BC, Canada.
² McGill University and McGill University Health Centre, Montreal, QC, Canada.
³ School of Epidemiology and Public Health, University of Ottawa and Replica Analytics, Ottawa, ON, Canada.
⁴ CIFAR, Toronto, ON, Canada.

Abstract

Synthetic data generation is the process of using machine learning methods to train a model that captures the patterns in a real dataset. Then new or synthetic data can be generated from that trained model. The synthetic data does not have a one-to-one mapping to the original data or to real patients, and therefore has the potential of privacy preserving properties. There is a growing interest in the application of synthetic data across health and life sciences, but to fully realize the benefits, further education, research, and policy innovation is required. This article summarizes the opportunities and challenges of SDG for health data, and provides directions for how this technology can be leveraged to accelerate data access for secondary purposes.

Keywords: Artificial intelligence; Artificial intelligence applications; Health sciences; Medical science.

Publication types

Review