A5063447489- Cardiac Imaging and Diagnostics
- Cardiovascular Function and Risk Factors
- Acute Myocardial Infarction Research
- Coronary Interventions and Diagnostics
- Cardiovascular Disease and Adiposity
- Advanced X-ray and CT Imaging
- Lipoproteins and Cardiovascular Health
- Heart Failure Treatment and Management
- Cardiac Valve Diseases and Treatments
- Advanced MRI Techniques and Applications
- Sarcoidosis and Beryllium Toxicity Research
- Atrial Fibrillation Management and Outcomes
- Artificial Intelligence in Healthcare and Education
- Ultrasound and Hyperthermia Applications
- Cardiovascular Health and Disease Prevention
- Ultrasound in Clinical Applications
- Cardiac pacing and defibrillation studies
- Cardiac Structural Anomalies and Repair
- Diet and metabolism studies
- Antiplatelet Therapy and Cardiovascular Diseases
- Cardiac Arrhythmias and Treatments
- Infective Endocarditis Diagnosis and Management
- Machine Learning in Healthcare
- Atherosclerosis and Cardiovascular Diseases
- Pericarditis and Cardiac Tamponade
Harry Perkins Institute of Medical Research
2017-2025
Fiona Stanley Hospital
2017-2025
The University of Western Australia
2017-2025
University of Ottawa
2016-2025
Murdoch University
2018-2024
Stanley Foundation
2022-2023
Curtin University
2021-2023
Montreal Heart Institute
2023
Université de Montréal
2023
University Health Network
2023
The brain is the perfect place to look for inspiration develop more efficient neural networks. inner workings of our synapses and neurons provide a glimpse at what future deep learning might like. This article serves as tutorial perspective showing how apply lessons learned from several decades research in learning, gradient descent, backpropagation, neuroscience biologically plausible spiking networks (SNNs). We also explore delicate interplay between encoding data spikes process;...
Interest in artificial intelligence (AI) research has grown rapidly over the past few years, part thanks to numerous successes of modern machine learning techniques such as deep learning, availability large datasets and improvements computing power. AI is proving be increasingly applicable healthcare there a growing list tasks where algorithms have matched or surpassed physician performance. Despite remain significant concerns challenges surrounding algorithm opacity, trust patient data...
Background— There remains limited insight into the pathophysiology and therapeutic advances directed at improving prognosis for patients with heart failure preserved ejection fraction (HFpEF). Recent studies have suggested a role coronary microvascular dysfunction in HFpEF. Rb-82 cardiac positron emission tomography imaging is noninvasive, quantitative approach to measuring myocardial flow reserve (MFR), surrogate marker vascular health. The aim of this study was determine whether...
Abstract Aims Machine learning (ML) is widely believed to be able learn complex hidden interactions from the data and has potential in predicting events such as heart failure (HF) readmission death. Recent studies have revealed conflicting results likely due take into account class imbalance problem commonly seen with medical data. We developed a new ML approach predict 30 day HF or death compared performance of this model other used prediction models. Methods identified all Western...
Background— Cardiac allograft vasculopathy is a key prognostic determinant after heart transplant. Detection and risk stratification of patients with cardiac are problematic. Positron emission tomography using rubidium-82 allows quantification absolute myocardial blood flow may have utility for in this population. Methods Results— Patients history transplant undergoing dipyridamole positron were prospectively enrolled. Myocardial perfusion left ventricular ejection fraction recorded....
The brain is the perfect place to look for inspiration develop more efficient neural networks. inner workings of our synapses and neurons provide a glimpse at what future deep learning might like. This paper serves as tutorial perspective showing how apply lessons learnt from several decades research in learning, gradient descent, backpropagation neuroscience biologically plausible spiking We also explore delicate interplay between encoding data spikes process; challenges solutions applying...
Abstract Introduction The association of testosterone concentrations with dementia risk remains uncertain. We examined associations serum and sex hormone–binding globulin (SHBG) incidence Alzheimer's disease. Methods Serum total SHBG were measured by immunoassay. disease (AD) was recorded. Cox proportional hazards regression adjusted for age other variables. Results In 159,411 community‐dwelling men (median 61, followed 7 years), 826 developed dementia, including 288 from AD. Lower...
Abstract Aims With an ageing population, the presence of asymptomatic valvular heart disease (VHD) in community remains unknown. The aim this study is to determine prevalence and associated factors VHD individuals ≥60 years old evaluate feasibility echocardiographic screening for population. Methods results This was a prospective cohort conducted between 2007 2016 UK. Asymptomatic patients with no prior indication echocardiography were invited participate evaluated health questionnaire,...
Previous studies in obstructive sleep apnea (OSA) were limited by study cohorts with comorbidities that confound assessment of left ventricular (LV) systolic and diastolic function. We comprehensively evaluated LV function using 2-dimensional echocardiography (2DE), tissue Doppler imaging (TDI), 3-dimensional (3DE) subjects moderate-severe OSA, who compared disease (patients hypertension, no OSA) healthy control subjects.A total 120 (n=40 each matched hypertension cohorts) underwent...
Background The prediction of readmission or death after a hospital discharge for heart failure (HF) remains major challenge. Modern healthcare systems, electronic health records, and machine learning (ML) techniques allow us to mine data select the most significant variables (allowing reduction in number variables) without compromising performance models used death. Moreover, ML methods based on transformation may potentially further improve performance. Objective To use determine relevant...