People Research Data Commons

Health research has a rich data ecosystem with national data assets distributed across the government, research and health service sectors. The challenge for potential users of these national data assets, like researchers or industry members, is identifying what data is available, where it is located and how it can be accessed. Additionally, there is a need for national research infrastructure to play a role in the strategy, provision and continuity of access of national scale data assets for health and medical research.

For example, to dynamically update dietary guidelines on stroke management, we want to be sure we have the data we need, that it is governed and standardised for re-use, and that we can find it and request permission to use it.

Data custodians and their organisations typically operate bespoke secure environments that enable researchers, collaborators and data requesters to analyse data, but they also lead to data silos that constrain national scale cross-sector, cross-jurisdiction multidisciplinary data collaborations. To ensure that data remains protected and under the full control of the data custodian at all times, it is vital to improve interoperability across secure data analysis platforms and incorporate privacy-preserving technical interoperability and seamless data governance.

For example, to transform our understanding of ageing by bringing together scores of longitudinal studies of brain ageing and dementia, we want to know how to give researchers secure access, and what systems and processes need to be in place to respect the privacy of the study participants.

Australia has world-leading, NCRIS-funded data linkage capabilities which enable a wide range of health data to be linked within and across jurisdictions. To meet research demand, it is essential to accelerate and scale up data integration capabilities nationally while ensuring the highest standards of privacy and security.

For example, to improve outcomes for people who suffer traumatic injuries in car accidents, we want to integrate data from the trauma registry, car accident insurance claims, accident and emergency hospital records, ambulance records, research studies and the deaths registry. We need to consider any existing standardisation of data structures across these sources, whether common medical concept definitions are in place, and whether there are common identifiers.

Facilitating the application of advanced analytics techniques like machine learning – in the context of national sensitive data collections managed across disparate institutional secure data repositories – raises challenges around data heterogeneity, quality and integration which will require frontier solutions.

For example, to support diagnostics and improve survival of cancer patients, we want to consider how nationally distributed machine learning over cancer data and imagery can be established. We want the images to remain securely within clinics and yet provide parameters to a model that is supported by data and coding standards and a well curated reference dataset.