A5086912690- Genetic Associations and Epidemiology
- Dementia and Cognitive Impairment Research
- AI in cancer detection
- Bioinformatics and Genomic Networks
- Genetic and phenotypic traits in livestock
- Infrared Thermography in Medicine
- Alzheimer's disease research and treatments
- Gene expression and cancer classification
- Genetic Mapping and Diversity in Plants and Animals
- Machine Learning in Healthcare
- Celiac Disease Research and Management
- Biomedical Text Mining and Ontologies
- Genomics and Phylogenetic Studies
- Intracerebral and Subarachnoid Hemorrhage Research
- Radiomics and Machine Learning in Medical Imaging
- Epigenetics and DNA Methylation
- Microscopic Colitis
- Health, Environment, Cognitive Aging
- Statistical Methods and Inference
- Machine Learning in Bioinformatics
- Functional Brain Connectivity Studies
- Global Cancer Incidence and Screening
- Diabetes and associated disorders
- Viral gastroenteritis research and epidemiology
- Gene Regulatory Network Analysis
Florey Institute of Neuroscience and Mental Health
2019-2025
The University of Melbourne
2016-2025
IBM Research - Australia
2012-2021
Data61
2011-2017
Baker Heart and Diabetes Institute
2011
The Alfred Hospital
2011
Objective— Traditional risk factors for coronary artery disease (CAD) fail to adequately distinguish patients who have atherosclerotic plaques susceptible instability from those more benign forms. Using plasma lipid profiling, this study aimed provide insight into pathogenesis and evaluate the potential of profiles assess future plaque instability. Methods Results— Plasma containing 305 lipids were measured on 220 individuals (matched healthy controls, n=80; stable angina, n=60; unstable...
It has been hypothesized that multivariate analysis and systematic detection of epistatic interactions between explanatory genotyping variables may help resolve the problem "missing heritability" currently observed in genome-wide association studies (GWAS). However, even simplest bivariate is still held back by significant statistical computational challenges are often addressed reducing set analysed markers. Theoretically, it shown combinations loci exist show weak or no effects...
Importance The ability to predict the onset of mild cognitive impairment (MCI) and Alzheimer dementia (AD) could allow older adults clinicians make informed decisions about care. Objective To assess whether age at MCI AD can be predicted using a statistical modeling approach. Design, Setting, Participants This prognostic study used data from 2 aging cohort studies—the Australian Imaging, Biomarker Lifestyle (AIBL) Alzheimer’s Disease Neuroimaging Initiative (ADNI)—for model development...
Cerebral amyloid angiopathy (CAA) is a cerebrovascular condition, the severity of which can only be determined post mortem. Here, we developed machine learning models, Florey CAA Score (FCAAS), to predict (none/mild/moderate/severe). Building on an auto-score-ordinal algorithm, FCAAS models were and validated using data collected by three cohort studies aging dementia. The digitized as web-based tool. A pilot trial was conducted this FCAAS-4 achieved mean area under receiver operating...
While the majority of cochlear implant recipients benefit from device, it remains difficult to estimate degree for a specific patient prior implantation. Using data 2,735 cochlear-implant across three clinics, largest retrospective study outcomes date, we investigate association between 21 preoperative factors and speech recognition approximately one year after implantation explore consistency their effects constituent datasets. We provide evidence 17 statistically significant associations,...
While cochlear implants have helped hundreds of thousands individuals, it remains difficult to predict the extent which an individual's hearing will benefit from implantation. Several publications indicate that machine learning may improve predictive accuracy implant outcomes compared classical statistical methods. However, existing studies are limited in terms model validation and evaluating factors like sample size on performance. We conduct a thorough examination approaches word...
Abstract Background The associations between mood disorders (anxiety and depression) mild cognitive impairment (MCI) or Alzheimer’s dementia (AD) remain unclear. Methods Data from the Australian Imaging, Biomarker & Lifestyle (AIBL) study were subjected to logistic regression determine both cross-sectional longitudinal anxiety/depression MCI/AD. Effect modification by selected covariates was analysed using likelihood ratio test. Results Cross-sectional analysis performed explore...
The recent biological redefinition of Alzheimer's Disease (AD) has spurred the development statistical models that relate changes in biomarkers with neurodegeneration and worsening condition linked to AD. ability measure such may facilitate earlier diagnoses for affected individuals help monitoring evolution their condition. Amongst tools, disease progression (DPMs) are quantitative, data-driven methods specifically attempt describe temporal dynamics relevant Due heterogeneous nature this...
Cerebral amyloid angiopathy (CAA) increases the risk of amyloid-related imaging abnormalities in Alzheimer's disease (AD) patients receiving anti-amyloid-beta therapies, emphasizing need to identify its factors. Data were collected from three cohort studies, and a machine learning model was developed predict CAA occurrence using selected The AD neuropathologic changes (ADNC)-CAA association significantly positive cross-sectional analysis. When stratified by factors, this generally stronger...
Abstract BACKGROUND Integrating non‐invasive measures to estimate abnormal amyloid beta accumulation (Aβ+) is key developing a screening tool for preclinical Alzheimer's disease (AD). The predictive capability of standard neuropsychological tests in estimating Aβ+ has not been quantified. METHODS We constructed machine learning models using six cognitive measurements alongside demographic and genetic risk factors predict Aβ status. Data were drawn from three cohorts: Anti‐Amyloid Treatment...
Genome-wide association studies (GWAS) are a common approach for systematic discovery of single nucleotide polymorphisms (SNPs) which associated with given disease. Univariate analysis approaches commonly employed may miss important SNP associations that only appear through multivariate in complex diseases. However, is currently limited by its inherent computational complexity. In this work, we present framework harnesses supercomputers. Based on our results, estimate three-way interaction...
Abstract Background We applied machine learning to find a novel breast cancer predictor based on information in mammogram. Methods Using image-processing techniques, we automatically processed 46 158 analog mammograms for 1345 cases and 4235 controls from cohort case–control study of Australian women, Japanese American extracting 20 textural features not pixel brightness threshold. used Bayesian lasso regression create individual- mammogram-specific measures risk, Cirrus. trained tested...
Knowledge of phase, the specific allele sequence on each copy homologous chromosomes, is increasingly recognized as critical for detecting certain classes disease-associated mutations. One approach such mutations through phased haplotype association analysis. While accuracy methods phasing genotype data has been widely explored, there little attention given to at block scale. Understanding combined impact tool and method used determine blocks error rate within determined essential conduct...
It is increasingly recognized that Alzheimer's disease (AD) exists before dementia present and shifts in amyloid beta occur long clinical symptoms can be detected. Early detection of these molecular changes a key aspect for the success interventions aimed at slowing down rates cognitive decline. Recent evidence indicates two established methods measuring amyloid, decrease cerebrospinal fluid (CSF) β
Young breast and bowel cancers (e.g., those diagnosed before age 40 or 50 years) have far greater morbidity mortality in terms of years life lost, are increasing incidence, but been less studied. For cancers, the familial relative risks, therefore variances age-specific log(incidence), much at younger ages, little these has explained. Studies families twins can address questions not easily answered by studies unrelated individuals alone. We describe existing emerging family twin data that...
Interaction analysis of GWAS can detect signal that would be ignored by single variant analysis, yet few robust interactions in humans have been detected. Recent work has highlighted the MHC region between known HLA risk haplotypes for various autoimmune diseases. To better understand genetic underlying celiac disease (CD), we conducted exhaustive genome-wide scans pairwise five independent CD case-control studies, using a rapid model-free approach to examine over 500 billion SNP pairs...
Epistatic interactions between genes are believed to be a critical component in the genetic architecture of complex diseases. Genome Wide Association Studies (GWAS) may able detect such indirectly, via identification associated SNP markers. Major obstacles progress this area are: unknown nature epistatic interactions, little understanding capabilities different filtering methods, and computational difficulties for exhaustive analysis. A common platform enabling various detection methods is...
Currently, the genetic variants strongly associated with risk for Multiple Sclerosis (MS) are located in Major Histocompatibility Complex. This includes DRB1*15:01 and DRB1*15:03 alleles at HLA-DRB1 locus, latter restricted to African populations; DQB1*06:02 allele HLA-DQB1 locus which is high linkage disequilibrium (LD) DRB1*15:01; protective A*02:01 HLA-A locus. HLA identification facilitated by co-inherited ('tag') single nucleotide polymorphisms (SNPs); however, SNP validation not...
Background: Alzheimer's disease is a progressive and irreversible neurological disorder characterized by cognitive deterioration. The cognition of patient at any given time not only reflects the stage (preclinical, prodromal, or dementia) but also serves as an index progression. In this study, we developed model to track trajectory, aiming predict onset mild impairment (MCI) dementia (ADem). Methods: Data from 1665 participants in Australian Imaging, Biomarker, Lifestyle (AIBL) study were...
Integrating scores from multiple cognitive tests into a single composite has been shown to improve sensitivity detect AD-related impairment. However, existing composites have little amyloid-β status (Aβ +/-) in preclinical AD.