Expanding Data Sets to Allow Improved Critical Care for Children – Outpatient Risk Prediction

About the Project

The traditional hospital-focused model of care neglects monitoring and treating diseases at home. A number of intelligent monitoring systems exist for clinical abnormalities prediction for patients who are confined to hospital beds, but few attempts have been made to develop such a predictive system for home care that could prevent and minimize health-related risk at an early stage. As a result, recovering patients who leave the hospital after treatments are known to have adverse outcomes due to lack of efficient alert systems. In particular, children at risk of serious infection and sepsis are often discharged home with ‘safety-netting’ advice for parents and carers to subjectively observe signs of deterioration.

This project, in collaboration with Queensland Health, aims to develop a probabilistic cloud-based health monitoring and risk prediction system that can predict clinical abnormalities based on streaming data of vitals of children with possible serious infection at home. 


About the Candidate

This is an opportunity for a highly motivated student to join the CIRES project team, collaborating closely with leading experts in Queensland Health on investigating machine learning techniques for designing risk predictive models in outpatient settings. This scholarship is one of three CIRES projects with Queensland Health related to pediatric sepsis management. The successful candidate will collaborate with Queensland Health to develop a probabilistic based risk prediction system that identifies the future clinical abnormalities of children at risk of infection and sepsis.

This project seeks to develop a strong and capable future leader who can undertake medical analysis in a data-sparse environment, with the proposed model and research tasks able to be adapted and applied to other medical predictive tasks.

For this position, CIRES is seeking a candidate with an understanding of concepts from applied statistics/probability, numerical linear algebra, machine learning, algorithms and complexity. This project also requires proficiency in Python programming language, and machine learning software packages such as Pytorch. CIRES particularly encourages applicants with a medical background and relevant knowledge in the research domain.

project researchers
Prof Andrew Burton-Jones
Prof Shazia Sadiq
Dr Sen Wang (Principal Advisor)
partner investigator
Queensland Health