A new project led by the University of Queensland seeks to create a national data network that will support the development of novel solutions for managing chronic diseases.

Recently, the National Infrastructure for Federated Learning in Digital Health (NINA) project secured A$6 million ($3.9 million) funding from the federal government's Medical Research Future Fund. It also received an additional A$7.7 million ($5 million) in contributions from UQ, Monash and Macquarie universities, and the Queensland Cyber Infrastructure Foundation.

WHAT IT'S ABOUT

According to a media release, the five-year project will enable researchers to use machine learning to access siloed information on debilitating chronic diseases, such as diabetes, rheumatoid arthritis and osteoarthritis. It will prepare and harmonise the data to global standards while protecting individual privacy. Analyses will also be generated and shared across health organisations and states.

UQ will collaborate with 23 Australian and global partners to co-design the conceptual framework for NINA and speed up the translation and adoption of the data model at a national scale. 

WHY IT MATTERS

Researchers across Australia find it difficult to access health databases and move their research forward on digital health. 

"Australia has excellent digital health records, but data is siloed across health systems, preventing talented researchers from accessing millions of records about treatments and trends in crippling chronic conditions," noted Clair Sullivan, associate professor at UQ’s Queensland Digital Health Centre.

Chris Bain, Professor of Practice in Digital Health at Monash University Faculty of IT, said various privacy and data sharing restrictions hinder the meaningful use of such databases. 

"This has ultimately led to an almost insurmountable divide across healthcare sectors, including a lack of data connectivity across primary, secondary and tertiary care," he said in a separate statement.

The NINA project intends to "put data to work" to find solutions for better managing chronic conditions. "Rather than attempting to merge different data sets to enable machine learning centrally, the project will bring machine learning to the data," Sullivan added.

THE LARGER TREND

Despite having the will to pursue digital transformation using data and analytics, most healthcare organisations across Australia and New Zealand lack the ability to share real-time data and integrate disparate systems, according to a recent study commissioned by InterSystems. They are also analysing a limited number of data despite having tons of it as multiple datasets are not interoperable.

Nevertheless, most providers wanted a standardisation of data exchange. The Australian Digital Health Agency is helping fulfil this through its National Healthcare Interoperability Plan, which envisions a more connected Australian health system by 2027. 

As part of this endeavour, the agency recently partnered with Health Level Seven Australia to promote the consistent adoption of FHIR standards in the country. It also tied up with CSIRO's Australian e-Health Research Centre to create the National Clinical Terminology Service, which will provide terminology services and tools that will enable connectivity across the health system.