Skip to main content

Predicting short- and long-term outcomes of pregnancy to optimise maternal health care (PhD)

Primary supervisor

Lan Du

Co-supervisors

  • Joanne Enticott

As a pregnancy approaches term (the point at which the foetus is considered fully developed), decisions are made about the timing of birth and the way babies are born. These decisions are incredibly challenging for clinicians and pregnant women. Digital health records, advances in big data, machine learning and artificial intelligence methodologies, and novel data visualisation capabilities have opened up opportunities for a dynamic, ‘Learning Health System’ – where data can be harnessed to inform real-time and personalised decision-making. Existing linked administrative databases already capture Australian women and children's observed birth events and their actual health and well-being outcomes. The latest machine learning and artificial intelligence advancements can mine these datasets to create prediction models that can forecast the likely outcomes of current practices.

The project aims to

  • develop cutting-edge machine learning and statistical risk prediction techniques to predict each short-term, long-term and cost outcomes, which include but are not limited to 
    • Statistical (risk) modelling, 
    • Model calibration and uncertainty estimation, 
    • Causal learning for explainable machine learning
    • Transparent, comprehensible and explainable machine learning
  • explore the use of near-time data from healthcare providers to update these models over time.

Required knowledge

  • the candidate should have gained knowledge of statistics, statistical machine learning and deep learning. A publication or two in related areas will be a plus.
  • the candidate should have strong Python/R programming skills.

The candidate will work closely with experts in both machine learning and public health.

 

Project funding

Project based scholarship

Learn more about minimum entry requirements.