Filters
Availability
Publication Year
Resource Type
Faculty
School/Institute
Publication Search Results
Sort
Results per page
1 - 10 of 14
-
(2021)ThesisDementia is a leading cause of disability affecting approximately 50 million people worldwide. Currently, in Australia, there is no optimum way of monitoring the incidence or prevalence of dementia at the population level. There are also many unanswered questions regarding crucial aspects of dementia care, such as whether the provision of home-based services can reduce the time spent in residential care. Routinely collected administrative data have the potential to fill these gaps. This thesis explores the use of linked administrative data for detecting and monitoring dementia in Australia, uses these data to understand the care pathways followed by people with dementia, and addresses policy-focused questions aimed at improving dementia care. It does so by presenting the results of four research studies using the 45 and Up Study, a cohort of 267,153, recruited in 2006-2009 in New South Wales, Australia. The 45 and Up baseline survey was linked to a range of administrative datasets including records of hospitalisations, emergency department visits, aged care assessments, and claims for pharmaceuticals, medical services, aged care services and deaths for the period 2006-2016. Key findings include: (i) measuring dementia incidence with multiple linked administrative datasets identifies almost 80% of expected dementia cases (92% for those aged 80-84 years) and produces age-specific incidence rates that mirror those based on clinical diagnosis; (ii) entering residential care is the norm among people with dementia, and home-based care may not be meeting their needs at end of life; (iii) high-level home care for people with dementia may reduce the subsequent time spent in residential care; and (iv) changing to a new general practitioner (GP) when entering residential care is related to increased polypharmacy and initiation of psychotropic medicines among people with dementia. These findings will inform on-going efforts to monitor dementia incidence and care in Australia. They also have major policy implications, including emphasising the pressing need in Australia for more high-level home care packages, and highlighting end-of-life dementia care as a priority for policy development and innovation in service delivery. The link between GP continuity and psychotropic prescribing highlights a new intervention point that could assist in the efforts to reduce psychotropic prescribing in residential aged care.
-
(2021)ThesisThe application of machine learning models to big data has become ubiquitous, however their successful translation into clinical practice is currently mostly limited to the field of imaging. Despite much interest and promise, there are many complex and interrelated barriers that exist in clinical settings, which must be addressed systematically in advance of wide-spread adoption of these technologies. There is limited evidence of comprehensive efforts to consider not only their raw performance metrics, but also their effective deployment, particularly in terms of the ways in which they are perceived, used and accepted by clinicians. The critical care outreach team at St Vincent’s Public Hospital want to automatically prioritise their workload by predicting in-patient deterioration risk, presented as a watch-list application. This work proposes that the proactive management of in-patients at risk of serious deterioration provides a comprehensive case-study in which to understand clinician readiness to adopt deep-learning technology due to the significant known limitations of existing manual processes. Herein is described the development of a proof of concept application uses as its input the subset of real-time clinical data available in the EMR. This data set has the noteworthy challenge of not including any electronically recorded vital signs data. Despite this, the system meets or exceeds similar benchmark models for predicting in-patient death and unplanned ICU admission, using a recurrent neural network architecture, extended with a novel data-augmentation strategy. This augmentation method has been re-implemented in the public MIMIC-III data set to confirm its generalisability. The method is notable for its applicability to discrete time-series data. Furthermore, it is rooted in knowledge of how data entry is performed within the clinical record and is therefore not restricted in applicability to a single clinical domain, instead having the potential for wide-ranging impact. The system was presented to likely end-users to understand their readiness to adopt it into their workflow, using the Technology Adoption Model. In addition to confirming feasibility of predicting risk from this limited data set, this study investigates clinician readiness to adopt artificial intelligence in the critical care setting. This is done with a two-pronged strategy, addressing technical and clinically-focused research questions in parallel.
-
(2023)ThesisInfertility affects 1 in 6 couples and >180 million people worldwide. It represents an increasingly important public health problem, amplified by the continuing global trend to later childbearing. Fertility treatment including in vitro fertilization (IVF) is not suited to traditional health technology assessment (HTA) methods, because its value is derived by its ability to create life, rather than extend, improve, or save existing lives. Consequently, there is a lack of guidance, and satisfactory HTA methods to determine whether fertility treatment provides good value for money. Moreover, the ever-increasing demand for elective egg freezing (EEF) to preserve female fertility poses additional challenges for economic assessments. This thesis describes 5 studies that move the research agenda forward for guiding the economic evaluation of fertility treatment. Study 1, a systematic review, identified and quantified 5 methodological categories for value-of-statistical-life elicitation. Based on these categories, Study 2 investigated methods for eliciting the value of a statistical baby (VSB) and concluded that discrete choice experiments (DCEs) are the most appropriate method in a fertility treatment context. Study 3 applied DCE outputs to derive a VSB estimate, which was used to assess value for money of publicly funded IVF in a cost-benefit analysis, finding that at least 5 IVF cycles likely provide good value for women <42 years. Study 4 elicited patient preferences for fertility treatment based on a DCE and Study 5 performed an incentive-compatible lab experiment to assess the impact of patient and treatment characteristics on the demand for IVF and EEF. Both experiments indicate that the demand for fertility treatment is price-inelastic and unresponsive to income level, which might explain why women continue fertility treatment once they have commenced despite their financial capacity. This research makes several methodological contributions and provides an evidence base to assess the public investment in fertility treatment. Overall, patients and society were found to value fertility treatment highly. New knowledge generated includes: (1) identifying the number of cost-beneficial IVF cycles by female age; (2) quantifying price and income elasticities for IVF and EEF; (3) bridging the gap between the proliferation of DCEs and policy by applying DCE outputs to HTA; and (4) demonstrating that government funding decisions can be explored in a lab experiment.
-
(2022)ThesisAortic valve replacement is the standard treatment for severe aortic stenosis and aortic regurgitation. Internationally and in Australia, there is limited clinical trial evidence for valve devices, and scant information about real-world use, benefits and harms once these devices are adopted into clinical practice. Data generated by the routine operation of health systems are being employed increasingly to provide real-world evidence for the study of valve devices. Longitudinal and population-level data generated within the Australian health system provides a unique opportunity to investigate the use and outcomes of aortic valve devices. This thesis profiles the use of aortic valve replacement (AVR) procedures — including surgical aortic valve replacement (SAVR) and the newer, less-invasive, transcatheter aortic valve implantation (TAVI)— in the population of New South Wales (NSW), Australia. It addresses important evidence gaps, including: (i) how the use of AVR devices has changed over time; (ii) whether there are differences in patient outcomes between types of valve prostheses: mechanical valves (MV) and bioprosthetic valves (BV); and (iii) whether patients are receiving guideline-recommended antithrombotic medicines following TAVI. The analyses reported here identified changing trends over time in the type of SAVR procedures being used in NSW between 2001-2013, with increasing use of BV (from 9 to 18 per 100,000 population ) and decreasing use of MV (7 to 4 per 100,000 population). TAVI is now established as the new standard of care among patients aged over 80 years, although it is also being increasingly used in younger patients, particularly those funded privately. Comparative analyses of age-specific incidence rates of clinical outcomes for patients implanted with BV and MV found that after 5 years of follow-up, patients aged 18-64 years who were implanted with BV had higher rates of reoperation, but lower rates of stroke and haemorrhage. Among patients aged 65+ years, those implanted with BV had lower rates of acute myocardial infarction (AMI), haemorrhage and mortality. After 6-10 years of follow-up, rates of AMI were lower among patients aged 18-64 years implanted with BV, and among patients aged 65+ years, rates of cardiovascular and all-cause mortality remained significantly lower for patients implanted with BV. Further analyses for patients aged <65 years found further age-specific differences in risks of reoperation and mortality over time: patients aged 18-54 years who received BV were consistently at greater risk of reoperation over 15-years of follow-up, whereas patients aged 55-64 years only had a greater risk of reoperation beyond 10 years. Although there was no difference in mortality by valve type in patients aged 18-54 years, patients aged 55-64 years who received BV had a greater risk of mortality after 10 years of follow-up. Finally, analyses of post-TAVI dispensing found that one-third of patients receiving TAVI were not dispensed guideline-recommended antithrombotic therapy, within 30-days of discharge. The strongest predictor of dispensing was prior exposure to antithrombotic medicines, suggesting that there may be potential gaps in adherence to clinical guidelines for patients who are new to the therapy. These findings highlight the importance of monitoring the use and outcomes of aortic valve devices in the long-term. They also demonstrate how routinely collected data sources, used in combination with appropriate methods, can offer valuable insight into clinical practice relating to medical devices. Real-world evidence generated using these data complement clinical trials and registries, offering a scalable solution for the challenges of evaluating device-related outcomes in the long-term.
-
(2021)ThesisThe central aim of this thesis is concerned with the elucidation of cause-effect relationships from observational data among variables or events in the context of personalised healthcare. Appropriate methodology for extracting such relationships has been developed and discussed within the scope of longitudinal survival analysis. The thesis rethinks two fundamental questions of causality: (1) What empirical evidence is required for legitimate inference of cause-effect relationships? (2) Given that we are willing to accept causal information about a phenomenon, how can we draw inferences from such information? These questions have been without satisfactory answers in the light of observational healthcare, in part because we have not had clear definitions for the causal effect given the ever complex data structure and clinical questions on the unobserved outcome of survival probability, and in part because we have not had effective mathematical tools for deriving individualised causal answers to these questions. In the last decade, owing partly to advances in machine learning models, causality has undergone a major transformation: from a concept shrouded in properly designed randomised experiments into a mathematical object with well-defined semantics which can potentially be identified from observational data. This development has significantly brought down the cost of personalised healthcare in both medication discovery and evaluation. This thesis provides a systematic account of this causal transformation, addressed primarily to epidemiologists, particularly the pharmacoepidemiologist. Following a description of the conceptual and mathematical languages used in causal inference, this thesis emphasizes the development of practical methods for elucidating potentially causal relationships from (longitudinal) observational data, estimating the effects of treatment, and providing recommendations of treatments based on observed scenarios. I have tried in this thesis to present machine learning tools that handle causal relationships side by side with statistical probability theory. The prerequisites are startlingly simple, the results are straightforward. No more than basic skills in probability theory and some familiarity with machine learning are needed for the reader to begin solving causal problems that are too complex for the unaided intellect. The sequence of discussion follows more or less the chronological order by which I have tackled these topics, thus recreating for the reader the sense of progress that accompanied these developments. Following the introductory chapter (Chapter 1), I start with the formal description and review of the mathematical language of causal inference, in particular, how one can go about discovering cause-effect relationships using observational data (Chapter 2). I then proceed to the question of the definition of treatment effect on time-to-event outcomes. In particular, a framework of heterogeneous treatment effect estimation in survival analysis is provided to estimate the effects of static binary treatment conditions on a range of time-to-event outcomes encountered in the healthcare context (Chapters 3 and 4). The framework is then discussed in Chapters 5 and 6 with a more complex data stream, first in the case of time-varying confounders and exposures and then in the contingency of stochastic treatment options, where I examine the concepts of survival treatment effect given longitudinal confounding as well as the contour of time-varying survival dose response function. Chapter 7 offers an application of treatment effect estimation models in a recommendation system, where I used extensive simulations and case studies to demonstrate the advantage of an explanatory model over a predictive model in providing optimal treatment recommendations to patients. I end this thesis with the pursuit of the viability of causal exploration in public health management in Chapter 8, where a case study aiming to answer the question of the effect of public health interventions during the recent SARS-COV-2 pandemic is presented. The work shows that when there is a lack of quality observational data, approaches based on the potential outcomes theory (including the projects presented in Chapters 3 to 7) may fail to make a valid inference and additional assumptions have to be made on the functional form of the causal process. Together, my thesis bridges studies in causal inference theory and machine learning methods in the context of observational healthcare. Significant progress has been made in the development of estimation frameworks for individualised treatment effects subject to longitudinal data with informative censoring. I aim to provide pragmatic insights on the applications and limitations of advanced machine learning models in relation to empirical evidence and draw a clear distinction between causal discovery and conventional predictive learning in the realm of public health and epidemiology.
-
(2022)ThesisYoung people who engage in multiple risky behaviours (high-risk young people), such as substance abuse, antisocial behaviour, or suicidal ideation, are more likely to experience serious harms later in life. Despite these harms, there is extraordinarily little intervention research available to guide policy makers’ or service providers’ decision making about investing in effective programs for high-risk young people (HRYP). One potential reason for this is that most interventions available for vulnerable populations globally, are implemented by NGO’s (Non-Government Organisations) that typically lack the capacity and capability to conduct rigorous evaluation in addition to their primary service delivery roles. There is also little to no consideration given to the application of Indigenous Data Sovereignty (IDS) principles in the context of generating evidence with young Indigenous peoples. This thesis presents a range of methods that could be adopted by NGOs to design and deliver evidence-based programs for HRYP, and to explore the capacity to integrate more routine monitoring and evaluation into NGO’s delivery of those programs. This thesis seeks to demonstrate how research can be grounded in principles of IDS and considers methods for how research might best be operationalised in the context of NGO-delivered programs for HRYP. It is hoped that this approach may provide an exemplar for other programs, research projects and organisations that use data from Indigenous controlled organisations and from Indigenous peoples. The implications of the findings from this thesis, and recommendations for future research and practice implementation, are discussed. Dissemination of the methods described in this thesis will not only improve the internal capacity and capability of NGO-delivered programs to conduct evaluations in collaboration with researchers but will also increase the capacity of Indigenous peoples and communities to advocate for greater sovereignty in relation to the data and research methods with which they choose to engage. These improvements will lead to better outcomes for HRYP and their communities.
-
(2021)ThesisChapter 1 - Introduction. This provides an overview of mental and behavioural disorders (MBD) definitions and current knowledge about MBD in pregnancy. Maternal MBD in pregnancy are often overlooked. Most studies of MBD in pregnancy focused on a single class of MBD. This thesis used linked data from NSW Perinatal Data Collection and the NSW Admitted Patient Data Collection to assess diagnosed MBD in NSW maternities between 2002 and 2006. Chapter 2 – Methods. Describes data linkage, MBD definitions and preliminary data processing. Chapter 3 – Admissions for MBD in pregnancy. A study to compare rates of MBD admissions in pregnancy relative to MBD admissions in a baseline period. Overall, admissions for MBD were lower in early pregnancy (RR 0.71) and higher in late pregnancy (RR 1.91). Drug disorder admissions were more than 3-fold higher in late pregnancy. Schizophrenia admissions increased from early pregnancy and alcohol admissions remained lower throughout pregnancy. Baseline MBD admissions rates were higher for multiparous than primiparous maternities. Chapter 4 – Admissions with MBD in pregnancy. MBD prevalence in pregnancy was 2.4% overall, 1.4% for drug/alcohol disorders (DA) and 1.2% mental disorders (MD). Pregnancy DA prevalence was the same, psychotic disorder prevalence was half, affective disorder a third and anxiety a tenth that of comparable disorders in women of reproductive age. Coexisting MBD ranged from 23.6% for anxiety to 91.5% for sedative disorders. Smokers and residents in outer regional or more remote locations were identified as maternity populations at high risk of MBD. Chapter 5 – Neonatal outcomes. Assessed relative risks of individual classes of MBD on perinatal mortality, preterm birth, small size at birth, neonatal morbidity, and admission to neonatal intensive care (NICU). Adverse outcomes were on average 3- 4-fold higher for MBD relative to no MBD. Effects were universally attenuated by adjustment for smoking and co-existing MBD. Independent effects of opiate and cannabis disorders remained for most adverse neonatal outcomes, but not for schizophrenia or bipolar disorder. Chapter 6 – Discussion and conclusions. This thesis demonstrates the value of linked population data; has added to the evidence for pregnancy as risk for MBD; provided the first comprehensive prevalence estimates of MBD in pregnancy for all maternities in NSW, including both high and low prevalence MBD; provided evidence to support findings elsewhere of an independent association of alcohol, cannabis, or opiate disorder with poor neonatal outcomes, but not for schizophrenia or bipolar disorder.
-
(2023)ThesisAims: The first study investigated the agreement between embryologists when assessing cytoplasmic strings (CS) in human blastocysts. The second study investigated the idea that embryos originating from fresh ejaculate sperm is comparable to those originating from frozen-thawed ejaculate sperm. The third study investigated and expanded on the association between the presence of CS, blastocyst quality and live birth rate. The fourth study used timelapse technology to investigate whether the presence of CS in human blastocysts was associated with a clinical pregnancy. Methods: In the first study, CS activity in one hundred blastocysts was assessed to measure inter- & intra-observer agreement. In the second study, timelapse was used to observe embryo development in those originating from fresh ejaculate sperm compared to those originating from frozen-thawed ejaculate sperm. In the third study, timelapse was used to investigate the association between the presence of CS and their characteristics, with blastocyst quality, development and live birth in one thousand day 5 human blastocysts. In the fourth study, timelapse was used to assess CS presence in blastocysts to investigate the link between those blastocysts that formed a fetal heart after transfer. Results: From the first study, a moderate level of inter and intra observer agreement was observed when five embryologist assessed day 5/6 blastocysts for the presence of CS and their vesicles. From the second study, it was found that no differences were detected in key developmental events between embryos originating from fresh ejaculate sperm compared to their frozen-thawed counterparts. The third study confirmed that CS presence in human blastocysts is associated with blastocyst quality. The fourth study, the presence of CS in human blastocysts was found to be associated with a fetal heart. Conclusions: The first study showed a moderate level of inter- and intra-observer agreement when the presence of CS and their vesicles was assessed. The second study found that there are no differences in the morphokinetic parameters of early embryo development when either fresh or frozen ejaculate sperm was used for ICSI insemination. The third study confirmed that CS presence in human blastocysts is associated with blastocyst quality. The fourth study found that the presence of cytoplasmic strings in human blastocysts is associated with the probability of clinical pregnancy with fetal heart.
-
(2023)ThesisFollicular lymphoma (FL) accounts for one-third of incident non-Hodgkin lymphomas in Western countries, but its etiology is largely unexplained. I performed systematic reviews and meta-analyses, and used a population-based family case-control study to investigate the relationship between lifestyle, environmental and occupational risk factors of FL. Meta-estimates from my random-effect models showed a non-significant association with smoking, heterogeneous results for alcohol, modest increased risk with obesity, and positive associations with exposure to polychlorinated biphenyls (PCBs), chlorinated solvents and dichlorodiphenyldichloroethylene (DDT, a pesticide). The population-based case-control study included 770 FL cases and 490 family controls (siblings, partners). Participants completed a lifetime residential and work calendar and health, lifestyle, and diet questionnaires. I used unconditional logistic regression to examine associations with FL risk, including group-based trajectory modeling to examine associations with body shape and outdoor hours over the life course. I identified deaths using record linkage and applied Cox proportional regression to estimate hazard ratios for all-cause and FL-specific mortality. I observed a positive association between smoking and FL risk and mortality. Associations with recent alcohol intake and FL were null. Being obese 5 years prior to enrolment and higher body mass index 5 years prior to enrolment was associated with a modest increased FL risk, but there was no association with body shape trajectory. Body size was not associated with mortality. I observed an elevated FL risk with consumption of oily fish, but no association with mortality. I found no significant association between occupational exposure to pesticides, or extremely-low frequency magnetic fields, and FL risk. For sun exposure, I observed an inverse association with high cumulative outdoor hours and high outdoor hour maintainers over the life course, and FL risk. Policies on tobacco control, maintaining body weight within normal range, and safe use of solvents and pesticides are crucial in reducing the burden from FL. Sun exposure is not recommended as a cancer control policy, but the association may inform research on targeted therapies for this malignancy. My key findings have advanced our understanding of FL etiology and help guide risk reduction strategies and future research.
-
(2023)ThesisThe widespread adoption of Electronic Medical Records (EMRs) in hospitals continues to increase the amount of patient data that are digitally stored. Although the primary use of the EMR is to support patient care by making all relevant information accessible, governments and health organisations are looking for ways to unleash the potential of these data for secondary purposes, including clinical research, disease surveillance and automation of healthcare processes and workflows. EMRs include large quantities of free text documents that contain valuable information. The greatest challenges in using the free text data in EMRs include the removal of personally identifiable information and the extraction of relevant information for specific tasks such as clinical coding. Machine learning-based automated approaches can potentially address these challenges. This thesis aims to explore and improve the performance of machine learning models for automated de-identification and clinical coding of free text data in EMRs, as captured in hospital discharge summaries, and facilitate the applications of these approaches in real-world use cases. It does so by 1) implementing an end-to-end de-identification framework using an ensemble of deep learning models; 2) developing a web-based system for de-identification of free text (DEFT) with an interactive learning loop; 3) proposing and implementing a hierarchical label-wise attention transformer model (HiLAT) for explainable International Classification of Diseases (ICD) coding; and 4) investigating the use of extreme multi-label long text transformer-based models for automated ICD coding. The key findings include: 1) An end-to-end framework using an ensemble of deep learning base-models achieved excellent performance on the de-identification task. 2) A new web-based de-identification software system (DEFT) can be readily and easily adopted by data custodians and researchers to perform de-identification of free text in EMRs. 3) A novel domain-specific transformer-based model (HiLAT) achieved state-of-the-art (SOTA) results for predicting ICD codes on a Medical Information Mart for Intensive Care (MIMIC-III) dataset comprising the discharge summaries (n=12,808) that are coded with at least one of the most 50 frequent diagnosis and procedure codes. In addition, the label-wise attention scores for the tokens in the discharge summary presented a potential explainability tool for checking the face validity of ICD code predictions. 4) An optimised transformer-based model, PLM-ICD, achieved the latest SOTA results for ICD coding on all the discharge summaries of the MIMIC-III dataset (n=59,652). The segmentation method, which split the long text consecutively into multiple small chunks, addressed the problem of applying transformer-based models to long text datasets. However, using transformer-based models on extremely large label sets needs further research. These findings demonstrate that the de-identification and clinical coding tasks can benefit from the application of machine learning approaches, present practical tools for implementing these approaches, and highlight priorities for further research.