The Centre for Big Data Research in Health (CBDRH) is a leading Australian and international hub for health research using big data. Our experts are recognised leaders in research using routinely collected and linked data. They have a breadth and depth of experience in health data analytics across the areas of epidemiology, biostatistics, machine learning, visualisation, health policy, health economics, ethics and the governance of health data.
Our expertise covers the sourcing of state and national datasets, longstanding relationships with data custodians and applying for linked data via state and Commonwealth agencies.
We have health committee memberships with the NHMRC Australian Health Ethics Committee, Australian Academy of Science, National Committee for Data in Science and the NSW Population and Health Services Research Ethics Committee.
Our researchers help shape national policy regarding access to publicly funded health data for research and ethics in relation to ‘big data’. And we co-create research with end-users to shape policy and future research.
There are almost 110,000 hip, knee and shoulder replacements undertaken each year. The incidence of these procedures has increased rapidly in recent years and that increase is expected to continue.
This study involves the analysis of a new and unique national dataset with the purpose of further enhancing the outcome of hip, knee and shoulder replacement surgery. It builds on the recognised success of the Australian Orthopaedic Association National Joint Replacement Registry (AOANJRR).
Although the AOANJRR has been very successful at improving the outcome of joint replacement surgery in this country it is currently only able to report on two outcomes: revision and mortality. There is a much wider range of complications that can occur, contributing to significant ongoing morbidity and cost.
This new data set of more than one million patients combines the entire AOANJRR data set (1999–2015) through case level linkage to MBS, PBS and state hospital databases. This data linkage enhances the capacity of the AOANJRR to report on an expanded range of outcomes.
The analysis of these data will be able to identify national, regional and hospital incidence trends and variations for a wide range of previously unreported complications. In addition, it is planned to identify the effects of patient, surgical, implant, surgeon, hospital, pharmacological and disease related factors on a range of specific local and systemic complications.
Understanding the relative importance and interaction of these factors and how the effects can be modified in patient populations is critically important to identifying and implementing best practice. In addition, this study will define and describe the use of rehabilitation, as well as the frequency of rehospitalisation and emergency room encounters post-surgery to more completely assess the extent of health resource utilisation associated with joint replacement surgery.
Patient segmentation, which divides a patient population into distinct groups with specific needs and characteristics, underpins patient-centric approaches to tailoring care delivery.
We propose new methods to create longitudinal, patient-centric and data-driven representations of patient experience. We will use chronologically ordered hospital records for the population of New South Wales (~15 million individuals, ~90 million hospital events).
Using deep learning, we will compute patient ‘representations’ for trajectories of hospital use events and use these to identify clusters of individuals who share patterns of hospital use (patient segments). We will characterise and visualise the segments and explore how they change over time and the impacts of policy changes and population shocks. We will make our methods available via open-source code and an end-user app.
Our novel approach to patient segmentation uses sequences of health service use events—not diagnosis codes—as the primary way to represent patients. To do this, we employ Transformer deep learning architecture to make optimal use of longitudinal patient sequence data.
Our approach is ‘patient-journey-centric’—thereby aligned with the key preoccupations of policymakers—and ‘diagnosis-agnostic’—thereby flexibly supporting exploration of hospital trajectories in patient subgroups defined by any diagnosis, combinations of diagnoses or demographic features such as geography and ethnicity.
Our methods will inform health service planning, delivery and evaluation by allowing identification of patient subgroups who are most likely to be high users of hospital services. They will form the foundation for deep learning methods that can be applied to large multimodal datasets that integrate primary and secondary care e.g., MyHealth Record.
Our team includes senior, mid- and early-career researchers with outstanding expertise in data analytics, machine learning, biostatistics, health economics and research translation.
Although Australia has a high performing health system, it faces widening inequities, large variation in quality of care, and unbridled growth in health care spending; now exceeding 10% of gross domestic product. This poses major challenges for health system sustainability and the prosperity of the nation more broadly. This project establishes a partnership between the New South Wales Ministry of Health (NSW Health), an initial three Local Hospital Districts (LHDs) and two Primary Health Networks (PHNs), the Consumers Health Forum (CHF) and leading health service researchers. We will develop, implement and evaluate Patient Centred Co-Commissioning Groups (PCCGs) which are new regional alliances between LHDs and PHNs. PCCGs will commission novel care pathways for a target patient population with the goal of improving health care access and quality, patient experience, and reductions in total health care spending.
In 2020, two initial PCCGs will be established in diverse regions. Western Sydney will create a multi-faceted, community-based, rapid access service for patients with urgent care needs. Western NSW will develop a coordinated care model for people with diabetes at high risk of complications. Each year an additional 4 PCCGs will be added until all ten NSW PHN regions have PCCGs in place. Each PCCG will receive new funding from NSW Health for developing the care pathway, commissioning new services according to local priorities. Outcome payments will be provided if total health care spending is reduced and quality of care is improved compared to baseline.
Health and medical research in Australia significantly improve the health of the population. But a major research challenge remaining is the timely identification of eligible research participants.
The development of the Join Us register—Australia’s first disease agnostic research participant register—is a response to current health emergencies such as the COVID-19 pandemic. It also delivers longterm benefits for medical research and health outcomes. This is achieved through an online consent registration process and reaching out to participants about relevant opportunities to participate in health and medical research.
The register is open to all Australian adults. As part of registration, participants are asked to provide informed consent to be contacted for future research. They complete a brief questionnaire consisting of a few items about sociodemographic characteristics and health conditions or diagnoses. The participants are also invited to provide consent for linkages and extraction of their health records from databases managed by relevant government agencies and other care providers.
All research studies seeking support through the Join Us register for participant recruitment are required to have approval from a relevant human research ethics committee before using the register. The Join Us register will then forward research invitations to participants with the characteristics matching the study inclusion and exclusion criteria.
In the first year of operation, more than fifty research, health and non-government and consumer organisations joined the Register as Partners. The register assisted about 20 clinical trials with their recruitment. Further leveraging on the routinely collected data of the Join Us register will become a versatile resource for supporting diverse health research in Australia—strengthening Australia’s research capacity, productivity and sustainability.