A5077796433- Diabetes Management and Research
- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Diabetes Treatment and Management
- Advanced Memory and Neural Computing
- Diabetes and associated disorders
- Digital Mental Health Interventions
- Pancreatic function and diabetes
- Mobile Health and mHealth Applications
- Voice and Speech Disorders
- Gaze Tracking and Assistive Technology
- Phonocardiography and Auscultation Techniques
- Functional Brain Connectivity Studies
- Diabetes Management and Education
- Ethics in Clinical Research
- Machine Learning in Healthcare
- Respiratory and Cough-Related Research
- Epilepsy research and treatment
- Cardiac, Anesthesia and Surgical Outcomes
- Heart Failure Treatment and Management
The University of Melbourne
2020-2025
Melbourne Health
2021-2024
Australian Regenerative Medicine Institute
2022
Monash University
2022
Artificial Intelligence in Medicine (Canada)
2022
Abstract Objective. Common Spatial Patterns (CSP) has been established as a powerful feature extraction method in EEG signal processing with machine learning, but it shortcomings including sensitivity to noise and rigidity the value of weights. Our goal was transform CSP into trainable learning model that can learn from data, be regularized, integrated end-to-end classification networks. Approach. We developed novel Parameterised Orthogonally-Constrained Neural Network layer for (POC-CSP)...
AimsUnderstanding the lived experience of using a tubeless insulin pump and how this differs compared to usual care (tubed therapy (IPT) vs multiple daily injections (MDI)).MethodsInterviews were conducted after 12-weeks Omnipod DASH Insulin Management System (Insulet, Acton, MA) analysed thematic analysis.ResultsFifty-eight adults (35 female; mean age 42;SD 13 years; 35 previous MDI) interviewed. Most (84 %) wanted continue device. Experiences fit two themes: 1. Taking back control my...
Congestive Heart Failure (CHF) is a progressive disease that affects millions of people worldwide, severely impacting their quality life.Missed detection CHF and its progression life expectancy, thus it critical to develop applications continuously monitor symptoms in patient-centric cost-effective manner.This paper focuses on novel non-invasive technique identify using patients' speech traits.Pulmonary congestion breathlessness the most common symptom heart failure one major contributors...
Abstract Background Insulin pump therapy (IPT) improves glucose control in people with type 1 diabetes (T1D) compared multiple daily injections (MDI). However, their size, the tethered insulin infusion set, intrusiveness when operating device and need to disconnect during showering limit acceptance many who may benefit. The Omnipod DASH ® Management System is a small waterproof tubeless which wirelessly controlled by handheld be an acceptable alternative. there are no randomised trials...
In recent years, brain-computer interfaces (BCI) have gained lots of popularity as an assistive method for individuals with disabilities to regain their communication or mobility and interact the world more naturally. The utility such systems rely on accuracy in decoding user intentions. this research, we build previous BCI research that explored CNN models motor imagery tasks. Inspired by denoising autoencoders, introduce a deeper model very high drop out rates performs better at tasks...
Brain-Computer Interfaces (BCIs) have great potential for improving the lives of people with disabilities. The success a BCI system is largely driven by accuracy decoder. This accuracy, in turn, may be limited amount labelled training data available supervised machine learning algorithms. deep algorithms other computer science areas has not reached field decoding due to this lack abundant data. We use novel architecture trained self-supervised manner learn common vector representation...
Abstract Context Omnipod DASH Insulin Management System is a tubeless insulin pump that overcomes the physical inconveniences of conventional tubed therapy (IPT). Objective We compared treatment satisfaction with to usual care (multiple daily injections [MDIs] or IPT) in adults type 1 diabetes using self-monitoring blood glucose (SMBG). Methods Adults on MDI (n = 40) IPT 25) from 4 centers Australia were randomly assigned 1:1 nonblinded manner (Omnipod group) continue (Usual Care for 12...
Brain computer interfaces can help individuals with movement disabilities such as locked-in syndrome, tetraplegia and cerebral palsy by providing a direct interface between the brain various external mobility assistive devices, spellers, wheelchairs, prosthetics. Inspired recent advancements in vision, this paper, we investigate use of convolutional neural networks decoding signals evaluate performance our models on an existing dataset EEG acquired through hand squeeze task. Our model...
Abstract Avoidable and unplanned readmissions to hospital wards, especially the Intensive Care Unit, have significant implications for patients’ health poses additional economic burdens on system. If patients who are at risk of readmission identified early their risks mitigated, these complications can be avoided. Machine Learning has been a valuable tool automatic identification prediction various conditions situations, including readmissions. This is made possible through processing large...
Abstract Background Insulin pump therapy (IPT) improves glucose control in people with Type 1 diabetes (T1D) compared multiple daily injections (MDI). However, their size, the tethered insulin infusion set, intrusiveness when operating device, and need to disconnect during showering limits acceptance many who may benefit. The Omnipod DASH® Management System is a small waterproof tubeless device worn on upper arm which wirelessly controlled by handheld be an acceptable alternative. there are...
<h3>Objectives</h3> To demonstrate proof of concept/feasibility a novel digital platform using real-time capture patient-reported outcomes for real-world research involving patients with epilepsy. <h3>Methods</h3> The phone app collects multi-faceted including seizure frequency, medication side effects, mood, anxiety, quality life and cognition along voice images. Patients are invited through national consortium 18 adult epilepsy centres in Australia. information potentially allows feedback...