ORCID Profile
0000-0001-8675-6631
Current Organisations
Deakin University
,
Australian Research Council
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Elsevier BV
Date: 03-2017
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Science and Business Media LLC
Date: 12-2014
Publisher: JMIR Publications Inc.
Date: 21-07-2016
Publisher: Elsevier BV
Date: 2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Publisher: IEEE
Date: 08-2014
Publisher: JMIR Publications Inc.
Date: 16-12-2016
DOI: 10.2196/JMIR.5870
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2021
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2012
Publisher: Critical Care and Resuscitation
Date: 07-12-2020
DOI: 10.51893/2020.4.SC1
Abstract: Using geotagged Twitter data in Victoria, we created a mobility index and studied the changes during the staged restrictions during the coronavirus disease 2019 (COVID-19) pandemic. We describe preliminary evidence that geotagged Twitter data may be used to provide real-time population mobility data and information on the impact of restrictions on such mobility.
Publisher: Elsevier BV
Date: 12-2023
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 03-04-2020
Abstract: Scaling Bayesian optimisation (BO) to high-dimensional search spaces is a active and open research problems particularly when no assumptions are made on function structure. The main reason is that at each iteration, BO requires to find global maximisation of acquisition function, which itself is a non-convex optimization problem in the original search space. With growing dimensions, the computational budget for this maximisation gets increasingly short leading to inaccurate solution of the maximisation. This inaccuracy adversely affects both the convergence and the efficiency of BO. We propose a novel approach where the acquisition function only requires maximisation on a discrete set of low dimensional subspaces embedded in the original high-dimensional search space. Our method is free of any low dimensional structure assumption on the function unlike many recent high-dimensional BO methods. Optimising acquisition function in low dimensional subspaces allows our method to obtain accurate solutions within limited computational budget. We show that in spite of this convenience, our algorithm remains convergent. In particular, cumulative regret of our algorithm only grows sub-linearly with the number of iterations. More importantly, as evident from our regret bounds, our algorithm provides a way to trade the convergence rate with the number of subspaces used in the optimisation. Finally, when the number of subspaces is "sufficiently large", our algorithm's cumulative regret is at most O*(√TγT) as opposed to O*(√DTγT) for the GP-UCB of Srinivas et al. (2012), reducing a crucial factor √D where D being the dimensional number of input space. We perform empirical experiments to evaluate our method extensively, showing that its s le efficiency is better than the existing methods for many optimisation problems involving dimensions up to 5000.
Publisher: Elsevier BV
Date: 11-2020
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2020
Abstract: We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering. Relaxing the common assumption made by current models that the object predicates pre-exist and stay static, passive to the reasoning process, we propose that these dynamic predicates expand across the domain borders to include pair-wise visual-linguistic object binding. In our method, these contextualized object links are actively found within each recurrent reasoning step without relying on external predicative priors. These dynamic structures reflect the conditional dual-domain object dependency given the evolving context of the reasoning through co-attention. Such discovered dynamic graphs facilitate multi-step knowledge combination and refinements that iteratively deduce the compact representation of the final answer. The effectiveness of this model is demonstrated on image question answering demonstrating favorable performance on major VQA datasets. Our method outperforms other methods in sophisticated question-answering tasks wherein multiple object relations are involved. The graph structure effectively assists the progress of training, and therefore the network learns efficiently compared to other reasoning models.
Publisher: Springer International Publishing
Date: 2016
Publisher: Elsevier BV
Date: 06-2016
Publisher: Frontiers Media SA
Date: 02-07-2019
Publisher: IEEE
Date: 08-2014
Publisher: Springer International Publishing
Date: 2014
Publisher: Public Library of Science (PLoS)
Date: 04-05-2015
Publisher: Springer International Publishing
Date: 2016
Publisher: Frontiers Media SA
Date: 20-09-2017
Publisher: Elsevier BV
Date: 10-2017
Publisher: Springer International Publishing
Date: 2021
Publisher: BMJ
Date: 24-03-2015
Abstract: The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the majority of the global burden of disease. These factors are complex and interact at biological, behavioural, environmental and policy levels presenting challenges for population monitoring and intervention evaluation. This paper explores the utility of machine learning methods applied to population-level web search activity behaviour as a proxy for chronic disease risk factors. Web activity output for each element of the WHO's Causes of NCD framework was used as a basis for identifying relevant web search activity from 2004 to 2013 for the USA. Multiple linear regression models with regularisation were used to generate predictive algorithms, mapping web search activity to Centers for Disease Control and Prevention (CDC) measured risk factor/disease prevalence. Predictions for subsequent target years not included in the model derivation were tested against CDC data from population surveys using Pearson correlation and Spearman's r. For 2011 and 2012, predicted prevalence was very strongly correlated with measured risk data ranging from fruits and vegetables consumed (r=0.81 95% CI 0.68 to 0.89) to alcohol consumption (r=0.96 95% CI 0.93 to 0.98). Mean difference between predicted and measured differences by State ranged from 0.03 to 2.16. Spearman's r for state-wise predicted versus measured prevalence varied from 0.82 to 0.93. The high predictive validity of web search activity for NCD risk has potential to provide real-time information on population risk during policy implementation and other population-level NCD prevention efforts.
Publisher: Elsevier BV
Date: 09-2018
Publisher: IEEE
Date: 12-2016
Publisher: Society for Industrial and Applied Mathematics
Date: 28-04-2014
Publisher: Elsevier BV
Date: 11-2016
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Cold Spring Harbor Laboratory
Date: 06-12-2022
DOI: 10.1101/2022.12.05.22283129
Abstract: Meta-analytic evidence confirms a range of interventions, including mindfulness, physical activity and sleep hygiene, can reduce psychological distress in university students. However, it is unclear which intervention is most effective. Artificial intelligence (AI) driven adaptive trials may be an efficient method to determine what works best and for whom. The primary purpose of the study is to rank the effectiveness of mindfulness, physical activity, sleep hygiene and an active control on reducing distress, using a multi-arm contextual bandit-based AI-adaptive trial method. Furthermore, the study will explore which interventions have the largest effect for students with different levels of baseline distress severity. The Vibe Up study is a pragmatically-oriented, decentralised AI-adaptive group sequential randomised controlled trial (RCT) comparing the effectiveness of one of three brief, two week digital self-guided interventions (mindfulness, physical activity, or sleep hygiene) or active control (ecological momentary assessment) in reducing self-reported psychological distress in Australian university students. The adaptive trial methodology involves up to 12 sequential mini-trials that allow for the optimisation of allocation ratios. The primary outcome is change in psychological distress (DASS-21 total score) from pre-intervention to post-intervention. Secondary outcomes include change in depression, anxiety, and stress (measured by DASS-21 subscales) from pre-intervention to post-intervention. Planned contrasts will compare the four groups (i.e., the three intervention and control) using self-reported psychological distress at pre-specified time points for interim analyses. The study aims to determine the best performing intervention, as well as ranking of other interventions. Ethical approval was sought and obtained from the UNSW Sydney Human Research Ethics Committee (HREC A, HC200466). A trial protocol adhering to the requirements of the Guideline for Good Clinical Practice [1] was prepared for and approved by the Sponsor, UNSW Sydney (Protocol number: HC200466_CTP). The trial is registered with the Australian New Zealand Clinical Trials Registry (AC-TRN12621001223820). The study addresses an important clinical question using novel, advanced methods The trial uses short-duration interventions designed to improve coping responses to transient stressors, which addresses the most common needs of university students A value of information analysis is included to compare the value of the new trial methods with traditionalapproaches Digital phenotyping is used to explore smartphone sensor information with clinical outcomes More than 12 mini-trials might be required to determine the ranking for the interventions The interventions may prove to be of the same level of effectiveness for each level of severity Interventions other than those examined in this study, such as CBT, may be more effective and remain untested The methodology assumes that the three digital interventions are configured to deliver similar doses and/or have approximate fidelity with standard methods
Publisher: Wiley
Date: 10-04-2015
DOI: 10.1002/SAM.11262
Publisher: Springer International Publishing
Date: 2016
Publisher: JMIR Publications Inc.
Date: 11-07-2016
DOI: 10.2196/MENTAL.5475
Abstract: Although physical illnesses, routinely documented in electronic medical records (EMR), have been found to be a contributing factor to suicides, no automated systems use this information to predict suicide risk. The aim of this study is to quantify the impact of physical illnesses on suicide risk, and develop a predictive model that captures this relationship using EMR data. We used history of physical illnesses (except chapter V: Mental and behavioral disorders) from EMR data over different time-periods to build a lookup table that contains the probability of suicide risk for each chapter of the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) codes. The lookup table was then used to predict the probability of suicide risk for any new assessment. Based on the different lengths of history of physical illnesses, we developed six different models to predict suicide risk. We tested the performance of developed models to predict 90-day risk using historical data over differing time-periods ranging from 3 to 48 months. A total of 16,858 assessments from 7399 mental health patients with at least one risk assessment was used for the validation of the developed model. The performance was measured using area under the receiver operating characteristic curve (AUC). The best predictive results were derived (AUC=0.71) using combined data across all time-periods, which significantly outperformed the clinical baseline derived from routine risk assessment (AUC=0.56). The proposed approach thus shows potential to be incorporated in the broader risk assessment processes used by clinicians. This study provides a novel approach to exploit the history of physical illnesses extracted from EMR (ICD-10 codes without chapter V-mental and behavioral disorders) to predict suicide risk, and this model outperforms existing clinical assessments of suicide risk.
Publisher: Springer International Publishing
Date: 2016
Publisher: Association for Computing Machinery (ACM)
Date: 07-2010
Abstract: The blogosphere has grown to be a mainstream forum of social interaction as well as a commercially attractive source of information and influence. Tools are needed to better understand how communities that adhere to in idual blogs are constituted in order to facilitate new personal, socially-focused browsing paradigms, and understand how blog content is consumed, which is of interest to blog authors, big media, and search. We present a novel approach to blog subcommunity characterization by modeling in idual blog readers using mixtures of an extension to the LDA family that jointly models phrases and time, Ngram Topic over Time (NTOT), and cluster with a number of similarity measures using Affinity Propagation. We experiment with two datasets: a small set of blogs whose authors provide feedback, and a set of popular, highly commented blogs, which provide indicators of algorithm scalability and interpretability without prior knowledge of a given blog. The results offer useful insight to the blog authors about their commenting community, and are observed to offer an integrated perspective on the topics of discussion and members engaged in those discussions for unfamiliar blogs. Our approach also holds promise as a component of solutions to related problems, such as online entity resolution and role discovery.
Publisher: IEEE
Date: 1996
Publisher: Springer Science and Business Media LLC
Date: 20-01-2020
DOI: 10.1038/S41746-019-0205-Y
Abstract: Complex health problems require multi-strategy, multi-target interventions. We present a method that uses machine learning techniques to choose optimal interventions from a set of possible interventions within a case study aiming to increase General Practitioner (GP) discussions of physical activity (PA) with their patients. Interventions were developed based on a causal loop diagram with 26 GPs across 13 clinics in Geelong, Australia. GPs prioritised eight from more than 80 potential interventions to increase GP discussion of PA with patients. Following a 2-week baseline, a multi-arm bandit algorithm was used to assign optimal strategies to GP clinics with the target outcome being GP PA discussion rates. The algorithm was updated weekly and the process iterated until the more promising strategies emerged (a duration of seven weeks). The top three performing strategies were continued for 3 weeks to improve the power of the hypothesis test of effectiveness for each strategy compared to baseline. GPs recorded a total of 11,176 conversations about PA. GPs identified 15 factors affecting GP PA discussion rates with patients including GP skills and awareness, fragmentation of care and fear of adverse outcomes. The two most effective strategies were correctly identified within seven weeks of the algorithm-based assignment of strategies. These were clinic reception staff providing PA information to patients at check in and PA screening questionnaires completed in the waiting room. This study demonstrates an efficient way to test and identify optimal strategies from multiple possible solutions.
Publisher: Springer International Publishing
Date: 2015
Publisher: Elsevier BV
Date: 2016
Publisher: JMIR Publications Inc.
Date: 06-11-2019
DOI: 10.2196/16399
Abstract: In this viewpoint we describe the architecture of, and design rationale for, a new software platform designed to support the conduct of digital phenotyping research studies. These studies seek to collect passive and active sensor signals from participants' smartphones for the purposes of modelling and predicting health outcomes, with a specific focus on mental health. We also highlight features of the current research landscape that recommend the coordinated development of such platforms, including the significant technical and resource costs of development, and we identify specific considerations relevant to the design of platforms for digital phenotyping. In addition, we describe trade-offs relating to data quality and completeness versus the experience for patients and public users who consent to their devices being used to collect data. We summarize distinctive features of the resulting platform, InSTIL (Intelligent Sensing to Inform and Learn), which includes universal (ie, cross-platform) support for both iOS and Android devices and privacy-preserving mechanisms which, by default, collect only anonymized participant data. We conclude with a discussion of recommendations for future work arising from learning during the development of the platform. The development of the InSTIL platform is a key step towards our research vision of a population-scale, international, digital phenotyping bank. With suitable adoption, the platform will aggregate signals from large numbers of participants and large numbers of research studies to support modelling and machine learning analyses focused on the prediction of mental illness onset and disease trajectories.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer Science and Business Media LLC
Date: 19-02-2016
Publisher: Springer International Publishing
Date: 2016
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 03-04-2020
Abstract: Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that formulates the problem as a multi-armed bandit problem, wherein each category corresponds to an arm with its reward distribution centered around the optimum of the objective function in continuous variables. Our goal is to identify the best arm and the maximizer of the corresponding continuous function simultaneously. Our algorithm uses a Thompson s ling scheme that helps connecting both multi-arm bandit and BO in a unified framework. We extend our method to batch BO to allow parallel optimization when multiple resources are available. We theoretically analyze our method for convergence and prove sub-linear regret bounds. We perform a variety of experiments: optimization of several benchmark functions, hyper-parameter tuning of a neural network, and automatic selection of the best machine learning model along with its optimal hyper-parameters (a.k.a automated machine learning). Comparisons with other methods demonstrate the effectiveness of our proposed method.
Publisher: Springer Science and Business Media LLC
Date: 13-05-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2015
Publisher: Cold Spring Harbor Laboratory
Date: 16-08-2018
DOI: 10.1101/393082
Abstract: Although neuropsychiatric disorders have a well-established genetic background, their specific molecular foundations remain elusive. This has prompted many investigators to design studies that identify explanatory biomarkers, and then use these biomarkers to predict clinical outcomes. One approach involves using machine learning algorithms to classify patients based on blood mRNA expression from high-throughput transcriptomic assays. However, these endeavours typically fail to achieve the high level of performance, stability, and generalizability required for clinical translation. Moreover, these classifiers can lack interpretability because informative genes do not necessarily have relevance to researchers. For this study, we hypothesized that annotation-based classifiers can improve classification performance, stability, generalizability, and interpretability. To this end, we evaluated the performance of four classification algorithms on six neuropsychiatric data sets using four annotation databases. Our results suggest that the Gene Ontology Biological Process database can transform gene expression into an annotation-based feature space that improves the performance and stability of blood-based classifiers for neuropsychiatric conditions. We also show how annotation features can improve the interpretability of classifiers: since annotation databases are often used to assign biological importance to genes, annotation-based classifiers are easy to interpret because the biological importance of the features are the features themselves. We found that using annotations as features improves the performance and stability of classifiers. We also noted that the top ranked annotations tend contain the top ranked genes, suggesting that the most predictive annotations are a superset of the most predictive genes. Based on this, and the fact that annotations are used routinely to assign biological importance to genetic data, we recommend transforming gene-level expression into annotation-level expression prior to the classification of neuropsychiatric conditions.
Publisher: JMIR Publications Inc.
Date: 25-09-2019
Abstract: n this viewpoint we describe the architecture of, and design rationale for, a new software platform designed to support the conduct of digital phenotyping research studies. These studies seek to collect passive and active sensor signals from participants' smartphones for the purposes of modelling and predicting health outcomes, with a specific focus on mental health. We also highlight features of the current research landscape that recommend the coordinated development of such platforms, including the significant technical and resource costs of development, and we identify specific considerations relevant to the design of platforms for digital phenotyping. In addition, we describe trade-offs relating to data quality and completeness versus the experience for patients and public users who consent to their devices being used to collect data. We summarize distinctive features of the resulting platform, InSTIL (Intelligent Sensing to Inform and Learn), which includes universal (ie, cross-platform) support for both iOS and Android devices and privacy-preserving mechanisms which, by default, collect only anonymized participant data. We conclude with a discussion of recommendations for future work arising from learning during the development of the platform. The development of the InSTIL platform is a key step towards our research vision of a population-scale, international, digital phenotyping bank. With suitable adoption, the platform will aggregate signals from large numbers of participants and large numbers of research studies to support modelling and machine learning analyses focused on the prediction of mental illness onset and disease trajectories.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2015
Publisher: IEEE
Date: 11-2017
DOI: 10.1109/ICDM.2017.44
Publisher: Cold Spring Harbor Laboratory
Date: 29-01-2019
DOI: 10.1101/533406
Abstract: Breast cancer is a collection of multiple tissue pathologies, each with a distinct molecular signature that correlates with patient prognosis and response to therapy. Accurately differentiating between breast cancer sub-types is an important part of clinical decision-making. Already, this problem has been addressed using machine learning methods that separate tissue s les into distinct groups. However, there remains unexplained heterogeneity within the established sub-types that cannot be resolved by the commonly used classification algorithms. In this paper, we propose a novel deep learning architecture, called DeepTRIAGE (Deep learning for the TRactable In idualised Analysis of Gene Expression), which not only classifies cancer sub-types with comparable accuracy, but simultaneously assigns each patient their own set of interpretable and in idualised biomarker scores. These personalised scores describe how important each feature is in the classification of each patient, and can be analysed post-hoc to generate new hypotheses about intra-class heterogeneity. We apply the DeepTRIAGE framework to classify the gene expression signatures of luminal A and luminal B breast cancer sub-types, and illustrate its use for genes and gene set (i.e., GO and KEGG) features. Using DeepTRIAGE, we find that the GINS1 gene and the kinetochore organisation GO term are the most important features for luminal sub-type classification. Through classification, DeepTRIAGE simultaneously reveals heterogeneity within the luminal A biomarker scores that significantly associate with tumour stage, placing all luminal s les along a continuum of severity. The proposed model is implemented in Python using Py-Torch framework. The analysis is done in Python and R. All Methods and models are freely available from dham/BiomarkerAttend .
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2015
Publisher: Cold Spring Harbor Laboratory
Date: 26-09-2018
DOI: 10.1101/426395
Abstract: Since the turn of the century, researchers have sought to diagnose cancer based on gene expression signatures measured from the blood or biopsy as biomarkers. This task, known as classification, is typically solved using a suite of algorithms that learn a mathematical rule capable of discriminating one group (e.g., cases) from another (e.g., controls). However, discriminatory methods can only identify cancerous s les that resemble those that the algorithm already saw during training. As such, we argue that discriminatory methods are fundamentally ill-suited for the classification of cancer: because the possibility space of cancer is definitively large, the existence of a one-of-a-kind gene expression signature becomes very likely. Instead, we propose using an established surveillance method that detects anomalous s les based on their deviation from a learned normal steady-state structure. By transferring this method to transcriptomic data, we can create an anomaly detector for tissue transcriptomes, a “tissue detector”, that is capable of identifying cancer without ever seeing a single cancer ex le. Using models trained on normal GTEx s les, we show that our “tissue detector” can accurately classify TCGA s les as normal or cancerous and that its performance is further improved by including more normal s les in the training set. We conclude this report by emphasizing the conceptual advantages of anomaly detection and by highlighting future directions for this field of study.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2016
Publisher: Elsevier BV
Date: 02-2016
DOI: 10.1016/J.JBI.2015.11.012
Abstract: Emerging Electronic Medical Records (EMRs) have reformed the modern healthcare. These records have great potential to be used for building clinical prediction models. However, a problem in using them is their high dimensionality. Since a lot of information may not be relevant for prediction, the underlying complexity of the prediction models may not be high. A popular way to deal with this problem is to employ feature selection. Lasso and l1-norm based feature selection methods have shown promising results. But, in presence of correlated features, these methods select features that change considerably with small changes in data. This prevents clinicians to obtain a stable feature set, which is crucial for clinical decision making. Grouping correlated variables together can improve the stability of feature selection, however, such grouping is usually not known and needs to be estimated for optimal performance. Addressing this problem, we propose a new model that can simultaneously learn the grouping of correlated features and perform stable feature selection. We formulate the model as a constrained optimization problem and provide an efficient solution with guaranteed convergence. Our experiments with both synthetic and real-world datasets show that the proposed model is significantly more stable than Lasso and many existing state-of-the-art shrinkage and classification methods. We further show that in terms of prediction performance, the proposed method consistently outperforms Lasso and other baselines. Our model can be used for selecting stable risk factors for a variety of healthcare problems, so it can assist clinicians toward accurate decision making.
No related grants have been discovered for svetha venkatesh.