Research in health

Bottom Padding

Our approach

CMCRC's Market Quality – Health program covers the application of advanced data sciences to all public and private healthcare settings. The program has been running since 2013, with the objective of improving market integrity and efficiency.

We do this by:

  • Developing advanced analytical and performance management solutions.
  • Maximising use of the administrative and transactional data of healthcare funders and providers, enhanced by the relevant findings and metrics from Australian and international research.

The program combines elements of health policy, health economics, epidemiology, public health, data mining, predictive analytics and simulation modelling. It is divided into five streams:

  1. Low- and high-value care
  2. Consumer empowerment
  3. Predictive modelling and risk stratification
  4. NLP and unstructured data
  5. Spatio-temporal variation.

Partnering in this work are the private and public health organisations that account for 60 percent of Australia’s $150 billion annual health spend, together with 10 leading Australian universities.

Top Padding

Program goals

  • Address the challenges and opportunities facing healthcare funders, providers and consumers.
  • Overcome data fragmentation across the health market.
  • Reduce fraud, abuse, waste and errors.
  • Empower consumers to play an active, fully-informed role in the choice, cost and quality of their healthcare.
  • Improved health outcomes for consumers.
  • Realise the commercial benefits from innovation.

Top Padding

The research program is divided into five streams:

  1. Low and High Value Care
    [Partners: NSW Health, HAMBS]
    • Identify/ measure low value care
    • Measure cost-effectiveness cardiovascular procedures
  2. Consumer Empowerment
    [Partners: HAMBS / AHSA, AIHW]
    • Provide personalised information
    • Provide Analysis of provider choice
    • Improve patient centric care
    • Promote Equity and Fairness
  3. Predictive Modelling and Risk Stratification
    [Partners: NSW Health, TAC, Medibank, Health Roundtable, HAMBS]
    • Design Risk stratification tools (re-admission, chronic disease, return to work)
    • Simulate Policy (prevention / new treatments)
    • Evaluate DRG design
  4. NLP and Unstructured Data
    [Partners: CMCRC, TAC, Sintelix]
    • Design tools for analysis of clinical notes/ guidelines
    • Analyse phone calls for predictive purposes
  5. Spatio -Temporal Variation
    [Partners: AIHW / DoH]
    • Design customisable geographies
    • Clustering and analysing health trajectories

Top Padding

Latest health research

 Chronic conditions can be costly but also preventable as well as predictable. We develop a model to predict in the short term (2-3 years) the onset of one or more chronic conditions.
The study illustrates a framework to predict the progression of chronic diseases from a new perspective using graph theory and social network analysis methods.
Previous studies have documented the application of electronic health insurance claim data for health services research purposes.