The Australian stillbirth rate has remained unchanged for 20 year. Current approaches to identify fetuses at risk of stillbirth is unsuccessful. Women who had stillborn commonly reported on abnormal baby movements prior to the loss. Unfortunately, there are no robust way to assess fetal movements. This project aims to develop a low-cost, lightweight, soft, conformal and non-intrusive wearable fetal movement monitor AI system to understand and reduce stillbirth nationally and globally.
Biosensor Based Clinical-decision Support For Patients With Heart Failure
Funder
National Health and Medical Research Council
Funding Amount
$691,933.00
Summary
Heart Failure (HF) is a progressive disease and a major global public health concern. HF accounts for a substantial number of hospitalisations, major healthcare resource utilisation and costs. We aim to engineer biosensor platform to stratify the risk in HF patients will revolutionise current management of HF by providing the cardiologist information to risk stratify patients based on protein signature. This will lead to a substantial paradigm shift in clinical practice.
A Sweet Therapeutic For Vascular Disease In Pregnancy
Funder
National Health and Medical Research Council
Funding Amount
$685,453.00
Summary
This project will advance a new drug to treat pregnant women diagnosed with the disease preeclampsia, and prevent them and their baby from becoming seriously ill. It will investigate how a novel sugar compound acts directly on the mother's blood vessels to restore normal vascular function, and provide the necessary preclinical proof-of-concept data to proceed to clinical trials.
Osteoarthritis Compass: Predicting Personalized Disease Onset And Progression With Future Capacity For Clinical Use.
Funder
National Health and Medical Research Council
Funding Amount
$860,231.00
Summary
Knee osteoarthritis (OA) is common, painful, and costly. General guidelines for knee OA management exist but cannot be personalized to the patient. New computer modelling methods enable prediction of knee OA onset and progression on a patient by patient basis but need further testing. Our aims are to 1) apply these new computer modelling methods to legacy datasets acquired from patient groups at risk of, and with, knee OA, and 2) make these models simple and fast enough to be clinically useful.