Framework and Pathfinder for Advanced Analytics in Healthcare

Read a national infrastructure framework and a federated learning pathfinder for advanced analytics in healthcare research, developed through the ARDC People Research Data Commons for health research and translation.

  • Senior researchers
  • Infrastructure providers (including research facilities)
  • Data custodians/managers
  • Digital skills trainers
  • Government
  • Industry

By the end of reading this resource, you should understand:

  • researchers’ need for infrastructure for advanced health analytics, as identified through the ARDC and the Australian Data Science Network’s consultation
  • the ARDC’s key recommendations to address identified gaps and needs in Australia’s advanced health analytics infrastructure through an Australian Harmonized Approach (AHA)
  • the requirements for, current experiences with and recommendations on federated learning in the context of sensitive health-related data.

The ARDC’s People Research Data Commons is involving all parts of the health system in national-scale activities, including co-designing frameworks and implementing solutions, to address some of Australia’s core digital health research challenges.

One such challenge is applying advanced analytics techniques like machine learning to national sensitive data collections across multiple secure data repositories, which raises data challenges that require innovative solutions.

As a first step to addressing this challenge, the ARDC has worked with the Australian Data Science Network (ADSN) and Australian Cancer Data Network (ACDN) through our Advanced Analytics in Healthcare activity to develop a: 

  • Framework for Advanced Analytics for National Healthcare Research Infrastructure
  • Pathfinder for exploring federated learning tools, opportunities and resource requirements in the context of sensitive health-related data. 

The National Infrastructure Framework was designed to understand the breadth of issues, and the Pathfinder project was designed to dig deeper around the specific but cardinal issue of making use of sensitivity of data through AI and advanced analytics in healthcare research. The Pathfinder explores federated learning as a potential solution to learning from sensitive data that is prohibited from being transferred across the organisational and jurisdictional boundaries.

We welcome your feedback on the reports. Your input will help us understand the views of research, policy and research infrastructure communities relating to advanced analytics in healthcare. Complete the feedback form.

Advanced analytics framework cover thumbnail

Framework for Advanced Analytics for National Healthcare Research Infrastructure

Through surveys, workshops and interviews, the ARDC and the ADSN consulted a wide range of stakeholders in research, government and research infrastructure to identify the needs, aspirations and challenges of advanced analytics in healthcare.

Based on our findings, we have developed an infrastructure framework to create a comprehensive and coordinated approach to health analytics infrastructure, leveraging national and international collaborations to enhance research capabilities, data governance and technological advancements. We have made the following key recommendations, which are aimed at creating an Australian Harmonized Approach (AHA) to health data analytics research infrastructure:

  • enhance computation resources and data environments
  • standardise data governance and curation
  • promote collaborative and ethical research initiatives
  • support workforce development and practical implementation.

Citation

Armstrong NJ, Bharathy GK, Buchhorn K, Mehta D, Mengersen K, Papaioannou A, Perrin D, Tanaka E, (2024). People RDC Framework for Advanced Analytics for National Healthcare Research Infrastructure. Australian Data Science Network (ADSN). Report to ARDC, Australian Research Data Commons. DOI: 10.5281/zenodo.13831385

Also watch a recording of our launch event for the framework, where we delved into the framework’s development, discussed its key recommendations and explored how it can support advanced health analytics in the coming years.

Advanced analytics pathfinder cover thumbnail

Pathfinder: Exploring Federated Learning Tools, Opportunities and Resource Requirements

In the fourth quarter of 2023, the ARDC reached out to the ACDN, who had previously collaborated on a federated learning project with the ARDC, to jointly develop a pathfinder project. It sought to: 

  • explore the uses, needs and challenges of federated learning in the context of sensitive health-related data, while ensuring the maintenance of privacy and confidentiality
  • identify and establish a collaborative network among similar research groups
  • develop suitable demonstrator artefacts to centre the dialogues around them. 

This report presents the findings of this project, providing an overview of requirements and current experiences with federated learning. It covers:

  • a comparison of key federated learning tools available and infrastructure requirements to support federated learning with the goal of establishing a suitable blueprint for a federated learning architecture that can be effectively implemented
  • consideration of use cases that could become cardinal edge cases for the development of a national infrastructure, including discussion of case study of designs and deployments that are available to or informing national infrastructure
  • healthcare-focused conclusions and recommendations to the ARDC on infrastructure and other support required to enable and encourage use of federated learning by Australian research groups.

Citation

Holloway L, Anees A, Al Mouiee D, Uddin A, Vafaee F, Haidar A, Gorse D, Sullivan R, Wang D, Bharathy G (2024). People RDC National Pathfinder Project: Exploring Federated Learning Tools, Opportunities and Resource Requirements. Report to ARDC, Australian Research Data Commons. DOI: 10.5281/zenodo.13831453

Also watch a recording of our launch event for the pathfinder.

Next Steps

Based on the 2 projects, we are developing a reference architecture and roadmap for the next 4 years for future research infrastructure in analytics in the healthcare area. The roadmap will allow us to start infrastructure development on multiple fronts simultaneously, affording flexibility and minimising critical paths.

Learn more about the infrastructure development on our Advanced Analytics in Healthcare activity page, and stay tuned as details are released by registering your interest in our People Research Data Commons and subscribing to the ARDC Connect newsletter.