Congratulations CBDRH Researchers

Congratulations to three CBDRH staff who were recently awarded grants.

A/Professor Blanca Gallego-Luxan was awarded an NHMRC Ideas grant over 4 years

Title: Learning what works and for which patients: efficient framework and novel technologies for precision comparative effectiveness research 

Summary: A new comparative effectiveness system that will harness existing big medical data, deep learning technologies and novel causal inference algorithms to provide a nimbler more efficient approach to address evidence needs. This system will be used to answer important questions on needed real-world evidence regarding two interventional procedures: electroconvulsive therapy for patients with severe psychiatric conditions (in collaboration with Professor Loo from the Black Dog Institute), and percutaneous ablation for patients with atrial fibrillation (in collaboration with Professor Brieger from the University of Sydney).

Dr Michael Falster was awarded an NHMRC Ideas Grant over 3 years

Title: Same patient, same care: is our funding of hospitals promoting inequities in care and outcomes?

Summary: Funding shortfalls have led to a surge of patients in public hospitals being funded through their private health insurance (PHI), but the consequences of this shift in patient care are unknown. Using linked administrative data for three states, this project will quantify and characterise variation and changes in PHI use, and whether similar patients with public or private funding receive similar care (e.g. quality or low value services) and have similar outcomes (e.g. complications, mortality).

Dr Sebastiano Barbieri

Title: The Health Gym: An Open Platform with Health-Related Benchmark Problems for the Development of Reinforcement Learning Algorithms

Description: Reinforcement learning (RL) algorithms hold tremendous promise for personalising healthcare but their development has been hampered by lack of openly available data with sufficient clinical detail. We will create The Health Gym, a set of publicly accessible healthcare-related “benchmark problems” (tasks with patient record examples) for developing, testing and comparing RL algorithms. The first two RL problems distributed as part of The Health Gym will concern the management of sepsis patients in the intensive care unit and the optimisation of antiretroviral therapy in HIV patients. At the end of the project, we will hold a two-day DataThon for teams of clinicians and data scientists, to help popularise The Health Gym platform and accelerate the development of robust and reproducible RL algorithms for application in healthcare.

Date Published
Wednesday, 5 February 2020
Back to Top