Probabilistic graphical models for detecting outbreaks. This project will create a novel class of probabilistic graphical model algorithms for learning and inference in problems involving unfrequent events such as anomaly detection. The outcome will be a methodology for seamlessly integrating space-time correlated data that will enable the early prediction of outbreaks in a principled statistical manner.
Active and interactive analysis of prescription data for harm minimisation. Active and interactive analysis of prescription data for harm minimisation. This project aims to enhance prescription monitoring to reduce and prevent dangers to the public from inappropriate drug use. The project will develop a framework integrating active machine learning, interactive data mining, and data visualization into analysis of prescription data. The expected outcomes include online interactive analysis of lar ....Active and interactive analysis of prescription data for harm minimisation. Active and interactive analysis of prescription data for harm minimisation. This project aims to enhance prescription monitoring to reduce and prevent dangers to the public from inappropriate drug use. The project will develop a framework integrating active machine learning, interactive data mining, and data visualization into analysis of prescription data. The expected outcomes include online interactive analysis of large scale prescription data and a system that can interact with health professionals to provide high quality real time prescription monitoring, thereby improving patient outcomes and the efficiency of the healthcare system.Read moreRead less
The development of automated advanced data analysis techniques for the detection of aberrant patterns of prescribing controlled drugs. The state of the art in ICT for healthcare monitoring is rapidly advancing, however, the value of data depends on effective tools and techniques. This project will develop novel techniques for the detection of emerging patterns in the prescribing of controlled drugs, supporting Queensland Health’s role in patient harm minimisation.
Evaluating and developing the evidence-base and data mining approaches to strengthen the consumer product safety system in Australia. Consumer product-related injuries cause over 173,000 injuries per year though there is limited evidence about the causes and risks to enable early identification and warnings for consumers. This project will evaluate the evidence-base and develop new methods to support an early identification and surveillance system for product-related injuries.