Skip to main content

Ambulance Clinical Record Information Complexity

Primary supervisor

David Dowe


  • Samuel Campbell

Turning Point’s National Ambulance Surveillance System is a surveillance database comprising enriched ambulance clinical data relating to alcohol and other substance use, suicidal and self-injurious thoughts and behaviours, and mental health-related harms in the Australian population. These data are used to inform policy and intervention design and are the subject of ever-increasing demand from academic professionals and units, government departments, and non-government organisations.


Student cohort

Double Semester


With the support of a Google AI Impact Challenge grant, Turning Point has begun to develop and deploy machine learning models to automate a subset of the clinical coding of these records. To prevent information loss in the event of a complex attendance, the emergence of novel substances, etc., we will develop a complexity criterion - using, e.g., the Bayesian information-theoretic minimum message length (MML) principle - that will determine the appropriateness of automated or manual clinical coding.

Required knowledge

Strong mathematics

Strong programming

Strong theoretic understanding of ML/Deep Learning

Experience with ML frameworks, e.g., Keras/TensorFlow, PyTorch

Good communication skills

Interest in health data

WAM > 75