Synthetic data
The WA Department of Health is leading the way in data innovation with the creation of synthetic health datasets. These datasets are a cutting-edge, privacy-safe alternative to real world data.
Using advanced artificial intelligence (AI) and machine learning (ML) models, our data scientists have generated artificial datasets that mimic the patterns, relationships, and structure of real health information. These models are trained on real source data however the resulting synthetic data is entirely artificial and does not contain any real or identifiable personal data. This means researchers, developers, analysts and health professionals can explore realistic data while maintaining privacy protection.
With rapid advancements in AI and ML, synthetic data is transforming how we manage and share health information - providing a secure and ethical option for approved use cases.
Benefits
Synthetic data offers several advantages over real health data, particularly in terms of privacy, security, and accessibility.
Timely access
Synthetic datasets can be shared more quickly, as they are subject to fewer governance requirements than real data. This means users can access representative healthcare data with reduced wait times.
Privacy and security
Synthetic data replicates the statistical properties of real health information without exposing actual patient details, minimising risks of data breaches or re-identification.
Collaboration and innovation
By providing a privacy-safe alternative, synthetic data enables researchers, analysts, and developers to collaborate and innovate without barriers related to data privacy.
Support for research and training
Synthetic data mirrors the structure and trends of real data, allowing researchers to test methods and develop analytical tools, and educators to provide hands-on training, all without compromising sensitive information.
How to apply for Synthethic Data
All applicants are encouraged to read the Synthetic Data Information Pack prior to submitting a request. This document outlines the benefits, limitations, and appropriate use of synthetic data, and will help you determine whether synthetic data is suitable for your needs.
If you have any questions or require assistance during the application process, please contact the Data Linkage Strategy team at DataLinkageStrategy@health.wa.gov.au.
1. Apply and Submit
All applicants - both internal and external - must complete and submit the online Synthetic Data Application Form.
Once submitted, your application will be reviewed by the relevant internal teams and data custodians - The review process is typically completed within 10 business days.
This is an iterative process, you may be asked to revise or clarify aspects of your application during the review.
2. Access
Once your application has been reviewed and approved by the relevant data custodians, you will be notified of the outcome via email.
External applicants will receive an email containing a secure link to access the approved synthetic datasets through MyFT. This platform provides a user-friendly interface for downloading and interacting with the data.
Internal applicants will be notified that access has been granted to the relevant SQL database, enabling direct querying of the synthetic datasets within the WA Health network environment.
Resources
- Synthetic Data Information Pack (PDF, XX MB)
- Data Dictionary (Excel, XX MB)
Last reviewed: 11-11-2025