ORCID Profile
0000-0001-5989-3614
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.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Human society | Criminology | Biomedical and clinical sciences | Dentistry | Health Information Systems (incl. Surveillance) | Stochastic Analysis and Modelling | Decision Support and Group Support Systems | Public Health and Health Services |
Evaluation of Health Outcomes | Health Status (e.g. Indicators of Well-Being) | Health Policy Economic Outcomes
Publisher: Oxford University Press (OUP)
Date: 20-12-2021
Abstract: Actualizing the vision of Global Digital Health is a central issue on the Global Health Diplomacy agenda. The COVID-reinforced need for accelerated digital health progress will require political structures and processes to build a foundation for Global Digital Health. Simultaneously, Global Health Diplomacy uses digital technologies in its enactment. Both phenomena have driven interest in the term “Digital Health Diplomacy.” A review of the literature revealed 2 emerging but distinct definitions that have been published very recently, each with its associated discourse and practice. This multiplicity of ideas demonstrates the myriad ways in which global digital and political systems are becoming increasingly entangled. Untangling these, this paper proposes and discusses 3 dimensions of Digital Health Diplomacy: “Diplomacy for digital health,” “Digital health for diplomacy,” and “Digital health in diplomacy.” It calls upon digital health professionals, diplomats, political and social scientists, epidemiologists, and clinicians to discuss, critique, and advance this emerging domain.
Publisher: MDPI AG
Date: 14-08-2022
Abstract: Background and Objectives: Statins have been extensively utilised in atherosclerotic cardiovascular disease (ASCVD) prevention and can inhibit inflammation. However, the association between statin therapy, subclinical inflammation and associated health outcomes is poorly understood in the primary care setting. Materials and Methods: Primary care electronic health record (EHR) data from the electronic Practice-Based Research Network (ePBRN) from 2012–2019 was used to assess statin usage and adherence in South-Western Sydney (SWS), Australia. Independent determinants of elevated C-reactive protein (CRP) were determined. The relationship between baseline CRP levels and hospitalisation rates at 12 months was investigated. Results: The prevalence of lipid-lowering medications was 14.0% in all adults and 44.6% in the elderly (≥65 years). The prevalence increased from 2012 to 2019 despite a drop in statin use between 2013–2015. A total of 55% of in iduals had good adherence ( %). Hydrophilic statin use and higher intensity statin therapy were associated with elevated CRP levels. However, elevated CRP levels were not associated with all-cause or ASCVD hospitalisations after adjusting for confounders. Conclusions: The prevalence and adherence patterns associated with lipid-lowering medications highlighted the elevated ASCVD-related burden in the SWS population, especially when compared with the Australian general population. Patients in SWS may benefit from enhanced screening protocols, targeted health literacy and promotion c aigns, and timely incorporation of evidence into ASCVD clinical guidelines. This study, which used EHR data, did not support the use of CRP as an independent marker of future short-term hospitalisations.
Publisher: Research Square Platform LLC
Date: 27-10-2023
Publisher: MDPI AG
Date: 31-07-2021
DOI: 10.3390/DIAGNOSTICS11081383
Abstract: Providing appropriate care for people suffering from COVID-19, the disease caused by the pandemic SARS-CoV-2 virus, is a significant global challenge. Many in iduals who become infected may have pre-existing conditions that may interact with COVID-19 to increase symptom severity and mortality risk. COVID-19 patient comorbidities are likely to be informative regarding the in idual risk of severe illness and mortality. Determining the degree to which comorbidities are associated with severe symptoms and mortality would thus greatly assist in COVID-19 care planning and provision. To assess this we performed a meta-analysis of published global literature, and machine learning predictive analysis using an aggregated COVID-19 global dataset. Our meta-analysis suggested that chronic obstructive pulmonary disease (COPD), cerebrovascular disease (CEVD), cardiovascular disease (CVD), type 2 diabetes, malignancy, and hypertension as most significantly associated with COVID-19 severity in the current published literature. Machine learning classification using novel aggregated cohort data similarly found COPD, CVD, CKD, type 2 diabetes, malignancy, and hypertension, as well as asthma, as the most significant features for classifying those deceased versus those who survived COVID-19. While age and gender were the most significant predictors of mortality, in terms of symptom–comorbidity combinations, it was observed that Pneumonia–Hypertension, Pneumonia–Diabetes, and Acute Respiratory Distress Syndrome (ARDS)–Hypertension showed the most significant associations with COVID-19 mortality. These results highlight the patient cohorts most likely to be at risk of COVID-19-related severe morbidity and mortality, which have implications for prioritization of hospital resources.
Publisher: JMIR Publications Inc.
Date: 15-12-2015
DOI: 10.2196/JMIR.4734
Publisher: Elsevier BV
Date: 07-2021
Publisher: BMJ
Date: 11-2022
DOI: 10.1136/BMJOPEN-2022-064375
Abstract: Implementing support and services early in the life course has been shown to promote positive developmental outcomes for children at high likelihood of developmental conditions including autism. This study examined parents’/caregivers’ experiences and perceptions about a digital developmental surveillance pathway for autism, the autism surveillance pathway (ASP), and usual care, the surveillance as usual (SaU) pathway, in the primary healthcare general practice setting. This qualitative study involves using a convenience selection process of the full s le of parents/caregivers that participated in the main programme, ‘General Practice Surveillance for Autism’, a cluster-randomised controlled trial study. All interviews were audio-recorded, transcribed and coded using NVivo V.12 software. An inductive thematic interpretive approach was adopted and data were analysed thematically. Twelve parents/caregivers of children with or without a developmental condition/autism (who participated in the main programme) in South Western Sydney and Melbourne were interviewed. All interviews were completed over the phone. There were seven major themes and 20 subthemes that included positive experiences, such as pre-existing patient–doctor relationships and their perceptions on the importance of knowing and accessing early support/services. Barriers or challenges experienced while using the SaU pathway included long waiting periods, poor communication and lack of action plans, complexity associated with navigating the healthcare system and lack of understanding by general practitioners (GPs). Common suggestions for improvement included greater awareness/education for parents/carers and the availability of accessible resources on child development for parents/caregivers. The findings support the use of digital screening tools for developmental surveillance, including for autism, using opportunistic contacts in the general practice setting. ANZCTR (ACTRN12619001200178).
Publisher: BMJ
Date: 08-2022
DOI: 10.1136/BMJOPEN-2022-065823
Abstract: The increasing prevalence of developmental disorders in early childhood poses a significant global health burden. Early detection of developmental problems is vital to ensure timely access to early intervention, and universal developmental surveillance is recommended best practice for identifying issues. Despite this, there is currently considerable variation in developmental surveillance and screening between Australian states and territories and low rates of developmental screening uptake by parents. This study aims to evaluate an innovative web-based developmental surveillance programme and a sustainable approach to referral and care pathways, linking primary care general practice (GP) services that fall under federal policy responsibility and state government-funded child health services. The proposed study describes a longitudinal cluster randomised controlled trial (c-RCT) comparing a ‘Watch Me Grow Integrated’ (WMG-I) approach for developmental screening, to Surveillance as Usual (SaU) in GPs. Forty practices will be recruited across New South Wales and Queensland, and randomly allocated into either the (1) WMG-I or (2) SaU group. A cohort of 2000 children will be recruited during their 18-month vaccination visit or opportunistic visit to GP. At the end of the c-RCT, a qualitative study using focus groups/interviews will evaluate parent and practitioner views of the WMG-I programme and inform national and state policy recommendations. The South Western Sydney Local Health District (2020/ETH01625), UNSW Sydney (2020/ETH01625) and University of Queensland (2021/HE000667) Human Research Ethics Committees independently reviewed and approved this study. Findings will be reported to the funding bodies, study institutes and partners families and peer-reviewed conferences ublications. ANZCTR12621000680864.
Publisher: JMIR Publications Inc.
Date: 22-01-2023
Abstract: he Health eLiteracy for Prevention in General Practice (HeLP-GP) trial is a primary healthcare-based behavior change intervention for weight loss in overweight and obese Australians from lower socioeconomic areas. In iduals from these areas are known to have low levels of health literacy and are particularly at risk for chronic conditions, including diabetes and cardiovascular disease. The intervention comprised health check visits with a practice nurse, a purpose-built patient-facing mobile app (mysnapp) and referral to telephone coaching his study aimed to assess the mysnapp app use within the HeLP-GP trial and its effects on study outcomes. n 2018, we recruited 22 general practices from 2 Australian states and randomized them by cluster to the intervention or usual care. Patients who met the main eligibility criteria (i.e. BMI 28 in previous 12 months and aged 40-74 years) were identified through the clinical software. The practice staff then provided the patients with details about the study. The intervention consisted of a health check with a practice nurse and a lifestyle app, a telephone coaching program, or both depending on the participants' choice. We collected data directly through the app and combined it with data from the 6-week health check with the practice nurses, the telephone coaching, and the participants' questionnaires at baseline, and 6-month follow-up. The analyses comprised descriptive and inferential statistics. f the 120 participants who received the intervention, 62 (52%) participants chose to use the app. The two groups did not differ significantly in demographics or recent hospital admissions. The median time between first and last app use was 52 (IQR 4-95) days, with a median of 5 (IQR 2-10) active days. App users were significantly more likely to attend the 6-week health check (χ21=6.4, P=.010) and participate in the telephone coaching (χ22=25.0, P .001) than non-app users. here seemed to be no differences in demographics or recent hospital admissions between those who chose to use the app and those who did not. App users were more likely to attend the 6-week health check and participate in telephone coaching. These finding suggest that participants who opted for several intervention components felt more committed to the study. NZCTR.org.au ACTRN12617001508369 R2-10.1136/bmjopen-2018-023239
Publisher: Elsevier BV
Date: 08-2023
Publisher: JMIR Publications Inc.
Date: 16-03-2018
Publisher: JMIR Publications Inc.
Date: 03-07-2023
DOI: 10.2196/43154
Abstract: Tuberculosis (TB) was the leading infectious cause of mortality globally prior to COVID-19 and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease. The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence–based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB. This systematic literature review (SLR) aims to assess the performance of machine learning (ML) and deep learning (DL) in the detection of TB using chest radiography (chest x-ray [CXR]). In conducting and reporting the SLR, we followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 309 records were identified from Scopus, PubMed, and IEEE (Institute of Electrical and Electronics Engineers) databases. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR. We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) and meta-analysis of 10 included studies that provided confusion matrix results. Various CXR data sets have been used in the included studies, with 2 of the most popular ones being Montgomery County (n=29) and Shenzhen (n=36) data sets. DL (n=34) was more commonly used than ML (n=7) in the included studies. Most studies used human radiologist’s report as the reference standard. Support vector machine (n=5), k-nearest neighbors (n=3), and random forest (n=2) were the most popular ML approaches. Meanwhile, convolutional neural networks were the most commonly used DL techniques, with the 4 most popular applications being ResNet-50 (n=11), VGG-16 (n=8), VGG-19 (n=7), and AlexNet (n=6). Four performance metrics were popularly used, namely, accuracy (n=35), area under the curve (AUC n=34), sensitivity (n=27), and specificity (n=23). In terms of the performance results, ML showed higher accuracy (mean ~93.71%) and sensitivity (mean ~92.55%), while on average DL models achieved better AUC (mean ~92.12%) and specificity (mean ~91.54%). Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0.9857 (95% CI 0.9477-1.00) and 0.9805 (95% CI 0.9255-1.00), respectively. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions. Findings from this SLR confirm the high potential of both ML and DL for TB detection using CXR. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects. PROSPERO CRD42021277155 www.crd.york.ac.uk rospero/display_record.php?RecordID=277155
Publisher: BMJ
Date: 09-2022
DOI: 10.1136/BMJOPEN-2022-063449
Abstract: Australia’s current healthcare system for children is neither sustainable nor equitable. As children (0–4 years) comprise the largest proportion of all primary care-type emergency department presentations, general practitioners (GPs) report feeling undervalued as an integral member of a child’s care, and lacking in opportunities for support and training in paediatric conditions. This Strengthening Care for Children (SC4C) randomised trial aims to evaluate a novel, integrated GP-paediatrician model of care, that, if effective, will improve GP quality of care, reduce burden to hospital services and ensure children receive the right care, at the right time, closer to home. SC4C is a stepped wedge cluster randomised controlled trial (RCT) of 22 general practice clinics in Victoria and New South Wales, Australia. General practice clinics will provide control period data before being exposed to the 12-month intervention which will be rolled out sequentially each month (one clinic per state) until all 22 clinics receive the intervention. The intervention comprises weekly GP-paediatrician co-consultation sessions monthly case discussions and phone and email paediatrician support, focusing on common paediatric conditions. The primary outcome of the trial is to assess the impact of the intervention as measured by the proportion of children’s (0– years) GP appointments that result in a hospital referral, compared with the control period. Secondary outcomes include GP quality of care GP experience and confidence in providing paediatric care family trust in and preference for GP care and the sustainability of the intervention. An implementation evaluation will assess the model to inform acceptability, adaptability, scalability and sustainability, while a health economic evaluation will measure the cost-effectiveness of the intervention. Human research ethics committee (HREC) approval was granted by The Royal Children’s Hospital Ethics Committee in August 2020 (Project ID: 65955) and site-specific HRECs. The investigators (including Primary Health Network partners) will communicate trial results to stakeholders and participating GPs and general practice clinics via presentations and publications. Australia New Zealand Clinical Trials Registry 12620001299998.
Publisher: BMJ
Date: 06-2018
Publisher: JMIR Publications Inc.
Date: 17-06-2020
Abstract: ARS-CoV-2 is straining health care systems globally. The burden on hospitals during the pandemic could be reduced by implementing prediction models that can discriminate patients who require hospitalization from those who do not. The COVID-19 vulnerability (C-19) index, a model that predicts which patients will be admitted to hospital for treatment of pneumonia or pneumonia proxies, has been developed and proposed as a valuable tool for decision-making during the pandemic. However, the model is at high risk of bias according to the “prediction model risk of bias assessment” criteria, and it has not been externally validated. he aim of this study was to externally validate the C-19 index across a range of health care settings to determine how well it broadly predicts hospitalization due to pneumonia in COVID-19 cases. e followed the Observational Health Data Sciences and Informatics (OHDSI) framework for external validation to assess the reliability of the C-19 index. We evaluated the model on two different target populations, 41,381 patients who presented with SARS-CoV-2 at an outpatient or emergency department visit and 9,429,285 patients who presented with influenza or related symptoms during an outpatient or emergency department visit, to predict their risk of hospitalization with pneumonia during the following 0-30 days. In total, we validated the model across a network of 14 databases spanning the United States, Europe, Australia, and Asia. he internal validation performance of the C-19 index had a C statistic of 0.73, and the calibration was not reported by the authors. When we externally validated it by transporting it to SARS-CoV-2 data, the model obtained C statistics of 0.36, 0.53 (0.473-0.584) and 0.56 (0.488-0.636) on Spanish, US, and South Korean data sets, respectively. The calibration was poor, with the model underestimating risk. When validated on 12 data sets containing influenza patients across the OHDSI network, the C statistics ranged between 0.40 and 0.68. ur results show that the discriminative performance of the C-19 index model is low for influenza cohorts and even worse among patients with COVID-19 in the United States, Spain, and South Korea. These results suggest that C-19 should not be used to aid decision-making during the COVID-19 pandemic. Our findings highlight the importance of performing external validation across a range of settings, especially when a prediction model is being extrapolated to a different population. In the field of prediction, extensive validation is required to create appropriate trust in a model.
Publisher: Elsevier BV
Date: 09-2016
DOI: 10.1016/J.IJMEDINF.2016.05.010
Abstract: There are increasing numbers of mHealth initiatives in middle and low income countries aimed at improving health outcomes. Bangladesh is no exception with more than 20 mobile health (mHealth) initiatives in place. A recent study in Bangladesh examined community readiness for mHealth using a framework based on quantitative data. Given the importance of a framework and the complementary role of qualitative exploration, this paper presents data from a qualitative study which complements findings from the quantitative study. The study was conducted in the Chakaria sub-district of Bangladesh. In total, 37 in-depth interviews were conducted between December 2012 and March 2013. Participants included the general public, students, community leaders, school teachers, and formal and informal healthcare providers. Thematic analysis was used to develop a logical and relevant framework to examine community readiness. As in the quantitative exploration, this study approached the investigation with four types of readiness in mind: core readiness, technological readiness, human resource readiness and motivational readiness. Community members, community leaders and healthcare providers expressed their interest in the use of mHealth in rural Bangladesh. Awareness of mHealth and its advantages was low among uneducated people. Participants who have used mHealth were attracted to the speed of access to qualified healthcare providers, time savings and low cost. Some participants did not see the value of using mobile phones for healthcare compared to a face-to-face consultation. Illiteracy, lack of English language proficiency, lack of trust and technological incapability were identified as barriers to mHealth use. However, a sense of ownership, evidence of utility, a positive attitude to the use of mHealth, and intentions towards future use of mHealth were driving forces in the adoption of mHealth services. This study re-affirmed the mHealth readiness conceptual framework with different dimensions of readiness and identified potential barriers and possible solutions for mHealth. Moving forward, emphasis should be placed on training users, providing low-cost services and improving trust of users.
Publisher: AMPCo
Date: 05-2021
DOI: 10.5694/MJA2.51039
Publisher: Elsevier BV
Date: 10-2023
Publisher: Elsevier BV
Date: 10-2023
Publisher: BMJ
Date: 11-2022
DOI: 10.1136/BMJOPEN-2021-060393
Abstract: To evaluate a multifaceted intervention on diet, physical activity and health literacy of overweight and obese patients attending primary care. A pragmatic two-arm cluster randomised controlled trial. Urban general practices in lower socioeconomic areas in Sydney and Adelaide. We aimed to recruit 800 patients in each arm. Baseline assessment was completed by 215 patients (120 intervention and 95 control). A practice nurse-led preventive health check, a mobile application and telephone coaching. Primary outcomes were measured at baseline, 6 and 12 months, and included patient health and eHealth literacy, weight, waist circumference and blood pressure. Secondary outcomes included changes in diet and physical activity, preventive advice and referral, blood lipids, quality of life and costs. Univariate and multivariate analyses of difference-in-differences (DiD) estimates for each outcome were conducted. At 6 months, the intervention group, compared with the control group, demonstrated a greater increase in Health Literacy Questionnaire domain 8 score (ability to find good health information mean DiD 0.22 95% CI 0.01 to 0.44). There were similar differences for domain 9 score (understanding health information well enough to know what to do) among patients below the median at baseline. Differences were reduced and non-statistically significant at 12 months. There was a small improvement in diet scores at 6 months (DiD 0.78 (0.10 to 1.47) p=0.026) but not at 12 months. There were no differences in eHealth literacy, physical activity scores, body mass index, weight, waist circumference or blood pressure. Targeted recruitment and engagement were challenging in this population. While the intervention was associated with some improvements in health literacy and diet, substantial differences in other outcomes were not observed. More intensive interventions and using codesign strategies to engage the practices earlier may produce a different result. Codesign may also be valuable when targeting lower socioeconomic populations. Australian New Zealand Clinical Trials Registry (ACTRN 12617001508369) (www.ANZCTR.org.au/ACTRN12617001508369.aspx). The protocol for this trial has been published (open access ontent/8/6/e023239).
Publisher: Oxford University Press (OUP)
Date: 30-11-2022
Abstract: A literature review of capability maturity models (MMs) to inform the conceptualization, development, implementation, evaluation, and mainstreaming of MMs in digital health (DH). Electronic databases were searched using “digital health,” “maturity models,” and related terms based on the Digital Health Profile and Maturity Assessment Toolkit Maturity Model (DHPMAT-MM). Covidence was used to screen, identify, capture, and achieve consensus on data extracted by the authors. Descriptive statistics were generated. A thematic analysis and conceptual synthesis were conducted. Diverse domain-specific MMs and model development, implementation, and evaluation methods were found. The spread and pattern of different MMs verified the essential DH foundations and five maturity stages of the DHPMAT-MM. An unanticipated finding was the existence of a new category of community-facing MMs. Common characteristics included: 1. A dynamic lifecycle approach to digital capability maturity, which is: a. responsive to environmental changes and may improve or worsen over time b. accumulative, incorporating the attributes of the preceding stage and c. sequential, where no maturity stage must be skipped. 2. Sociotechnical quality improvement of the DH ecosystem and MM, which includes: a. investing in the organization’s human, hardware, and software resources and b. a need to engage and improve the DH competencies of citizens. The ersity in MMs and variability in methods and content can create cognitive dissonance. A metamodel like the DHPMAT-MM can logically unify the many domain-specific MMs and guide the overall implementation and evaluation of DH ecosystems and MMs over the maturity lifecycle.
Publisher: Oxford University Press (OUP)
Date: 26-01-2021
Abstract: Data quality (DQ) must be consistently defined in context. The attributes, metadata, and context of longitudinal real-world data (RWD) have not been formalized for quality improvement across the data production and curation life cycle. We sought to complete a literature review on DQ assessment frameworks, indicators and tools for research, public health, service, and quality improvement across the data life cycle. The review followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Databases from health, physical and social sciences were used: Cinahl, Embase, Scopus, ProQuest, Emcare, PsycINFO, Compendex, and Inspec. Embase was used instead of PubMed (an interface to search MEDLINE) because it includes all MeSH (Medical Subject Headings) terms used and journals in MEDLINE as well as additional unique journals and conference abstracts. A combined data life cycle and quality framework guided the search of published and gray literature for DQ frameworks, indicators, and tools. At least 2 authors independently identified articles for inclusion and extracted and categorized DQ concepts and constructs. All authors discussed findings iteratively until consensus was reached. The 120 included articles yielded concepts related to contextual (data source, custodian, and user) and technical (interoperability) factors across the data life cycle. Contextual DQ subcategories included relevance, usability, accessibility, timeliness, and trust. Well-tested computable DQ indicators and assessment tools were also found. A DQ assessment framework that covers intrinsic, technical, and contextual categories across the data life cycle enables assessment and management of RWD repositories to ensure fitness for purpose. Balancing security, privacy, and FAIR principles requires trust and reciprocity, transparent governance, and organizational cultures that value good documentation.
Publisher: Oxford University Press (OUP)
Date: 22-07-2022
Abstract: In the wake of Coronavirus disease 2019 (COVID-19), several nations have sought to implement digital vaccine passports (DVPs) to enable the resumption of international travel. Comprising a minimum dataset for each unique in idual, DVPs have the makings of a global electronic health record, broaching key issues involved in building a global digital health ecosystem. Debate simulations offer a safe, interactive space to foster participatory policy discussions for advancing digital health diplomacy. This study used an online simulation of a Model World Health Assembly to critically analyze the sociotechnical issues associated with the global implementation of DVPs, and to generate useful insights and questions about the role of diplomacy in global digital health. The debate arguments addressed and provided insights into the technological, scientific, ethical, legal, policy, and societal aspects of DVPs. Reflecting on the simulation, we discuss its opportunities and challenges for the digitalization, decolonization, decentralization, and democratization of participatory policymaking.
Publisher: JMIR Publications Inc.
Date: 18-12-2017
Abstract: easonal variation has an impact on the hospitalization rate of patients with a range of cardiovascular diseases, including myocardial infarction and angina. This paper presents findings on the influence of seasonal variation on the results of a recently completed national trial of home telemonitoring of patients with chronic conditions, carried out at five locations along the east coast of Australia. he aim is to evaluate the effect of the seasonal timing of hospital admission and length of stay on clinical outcome of a home telemonitoring trial involving patients (age: mean 72.2, SD 9.4 years) with chronic conditions (chronic obstructive pulmonary disease coronary artery disease, hypertensive diseases, congestive heart failure, diabetes, or asthma) and to explore methods of minimizing the influence of seasonal variations in the analysis of the effect of at-home telemonitoring on the number of hospital admissions and length of stay (LOS). atients were selected from a hospital list of eligible patients living with a range of chronic conditions. Each test patient was case matched with at least one control patient. A total of 114 test patients and 173 control patients were available in this trial. However, of the 287 patients, we only considered patients who had one or more admissions in the years from 2010 to 2012. Three different groups were analyzed separately because of substantially different climates: (1) Queensland, (2) Australian Capital Territory and Victoria, and (3) Tasmania. Time series data were analyzed using linear regression for a period of 3 years before the intervention to obtain an average seasonal variation pattern. A novel method that can reduce the impact of seasonal variation on the rate of hospitalization and LOS was used in the analysis of the outcome variables of the at-home telemonitoring trial. est patients were monitored for a mean 481 (SD 77) days with 87% (53/61) of patients monitored for more than 12 months. Trends in seasonal variations were obtained from 3 years’ of hospitalization data before intervention for the Queensland, Tasmania, and Australian Capital Territory and Victoria subgroups, respectively. The maximum deviation from baseline trends for LOS was 101.7% (SD 42.2%), 60.6% (SD 36.4%), and 158.3% (SD 68.1%). However, by synchronizing outcomes to the start date of intervention, the impact of seasonal variations was minimized to a maximum of 9.5% (SD 7.7%), thus improving the accuracy of the clinical outcomes reported. easonal variations have a significant effect on the rate of hospital admission and LOS in patients with chronic conditions. However, the impact of seasonal variation on clinical outcomes (rate of admissions, number of hospital admissions, and LOS) of at-home telemonitoring can be attenuated by synchronizing the analysis of outcomes to the commencement dates for the telemonitoring of vital signs. ustralian New Zealand Clinical Trial Registry ACTRN12613000635763 www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=364030& isReview=true (Archived by WebCite at www.webcitation.org/ 6xLPv9QDb)
Publisher: Oxford University Press (OUP)
Date: 23-02-2021
Abstract: Toolkits are an important knowledge translation strategy for implementing digital health. We studied how toolkits for the implementation and evaluation of digital health were developed, tested, and reported. We conducted a systematic review of toolkits that had been used, field tested or evaluated in practice, and published in the English language from 2009 to July 2019. We searched several electronic literature sources to identify both peer-reviewed and gray literature, and records were screened as per systematic review conventions. Thirteen toolkits were eventually identified, all of which were developed in North America, Europe, or Australia. All reported their intended purpose, as well as their development process. Eight of the 13 toolkits involved a literature review, 3 did not, and 2 were unclear. Twelve reported an underlying conceptual framework, theory, or model: 3 cited the normalization process theory and 3 others cited the World Health Organization and International Telecommunication Union eHealth Strategy. Seven toolkits were reportedly evaluated, but details were unavailable. Forty-three toolkits were excluded for lack of field-testing. Despite a plethora of published toolkits, few were tested, and even fewer were evaluated. Methodological rigor was of concern, as several did not include an underlying conceptual framework, literature review, or evaluation and refinement in real-world settings. Reporting was often inconsistent and unclear, and toolkits rarely reported being evaluated. Greater attention needs to be paid to rigor and reporting when developing, evaluating, and reporting toolkits for implementing and evaluating digital health so that they can effectively function as a knowledge translation strategy.
Publisher: JMIR Publications Inc.
Date: 05-04-2021
DOI: 10.2196/21547
Abstract: SARS-CoV-2 is straining health care systems globally. The burden on hospitals during the pandemic could be reduced by implementing prediction models that can discriminate patients who require hospitalization from those who do not. The COVID-19 vulnerability (C-19) index, a model that predicts which patients will be admitted to hospital for treatment of pneumonia or pneumonia proxies, has been developed and proposed as a valuable tool for decision-making during the pandemic. However, the model is at high risk of bias according to the “prediction model risk of bias assessment” criteria, and it has not been externally validated. The aim of this study was to externally validate the C-19 index across a range of health care settings to determine how well it broadly predicts hospitalization due to pneumonia in COVID-19 cases. We followed the Observational Health Data Sciences and Informatics (OHDSI) framework for external validation to assess the reliability of the C-19 index. We evaluated the model on two different target populations, 41,381 patients who presented with SARS-CoV-2 at an outpatient or emergency department visit and 9,429,285 patients who presented with influenza or related symptoms during an outpatient or emergency department visit, to predict their risk of hospitalization with pneumonia during the following 0-30 days. In total, we validated the model across a network of 14 databases spanning the United States, Europe, Australia, and Asia. The internal validation performance of the C-19 index had a C statistic of 0.73, and the calibration was not reported by the authors. When we externally validated it by transporting it to SARS-CoV-2 data, the model obtained C statistics of 0.36, 0.53 (0.473-0.584) and 0.56 (0.488-0.636) on Spanish, US, and South Korean data sets, respectively. The calibration was poor, with the model underestimating risk. When validated on 12 data sets containing influenza patients across the OHDSI network, the C statistics ranged between 0.40 and 0.68. Our results show that the discriminative performance of the C-19 index model is low for influenza cohorts and even worse among patients with COVID-19 in the United States, Spain, and South Korea. These results suggest that C-19 should not be used to aid decision-making during the COVID-19 pandemic. Our findings highlight the importance of performing external validation across a range of settings, especially when a prediction model is being extrapolated to a different population. In the field of prediction, extensive validation is required to create appropriate trust in a model.
Publisher: JMIR Publications Inc.
Date: 10-2022
Abstract: uberculosis (TB) was the leading infectious cause of mortality globally prior to COVID-19 and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease. The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence–based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB. his systematic literature review (SLR) aims to assess the performance of machine learning (ML) and deep learning (DL) in the detection of TB using chest radiography (chest x-ray [CXR]). n conducting and reporting the SLR, we followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 309 records were identified from Scopus, PubMed, and IEEE (Institute of Electrical and Electronics Engineers) databases. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR. We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) and meta-analysis of 10 included studies that provided confusion matrix results. arious CXR data sets have been used in the included studies, with 2 of the most popular ones being Montgomery County (n=29) and Shenzhen (n=36) data sets. DL (n=34) was more commonly used than ML (n=7) in the included studies. Most studies used human radiologist’s report as the reference standard. Support vector machine (n=5), k-nearest neighbors (n=3), and random forest (n=2) were the most popular ML approaches. Meanwhile, convolutional neural networks were the most commonly used DL techniques, with the 4 most popular applications being ResNet-50 (n=11), VGG-16 (n=8), VGG-19 (n=7), and AlexNet (n=6). Four performance metrics were popularly used, namely, accuracy (n=35), area under the curve (AUC n=34), sensitivity (n=27), and specificity (n=23). In terms of the performance results, ML showed higher accuracy (mean ~93.71%) and sensitivity (mean ~92.55%), while on average DL models achieved better AUC (mean ~92.12%) and specificity (mean ~91.54%). Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0.9857 (95% CI 0.9477-1.00) and 0.9805 (95% CI 0.9255-1.00), respectively. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions. indings from this SLR confirm the high potential of both ML and DL for TB detection using CXR. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects. ROSPERO CRD42021277155 www.crd.york.ac.uk rospero/display_record.php?RecordID=277155
No related organisations have been discovered for Siaw-Teng Liaw.
Start Date: 12-2016
End Date: 05-2020
Amount: $270,000.00
Summary: Predictive analytics from at home telemonitoring of vital signs. Predictive analytics from at home telemonitoring of vital signs. This project aims to reduce unscheduled admissions to hospital, by developing statistical models of people’s health using longitudinal measurements of vital signs and questionnaires. Hospital costs are becoming unsustainable and will overwhelm state budgets within thirty years. Telehealth monitoring to manage chronic disease is becoming increasingly routine internatio .... Predictive analytics from at home telemonitoring of vital signs. Predictive analytics from at home telemonitoring of vital signs. This project aims to reduce unscheduled admissions to hospital, by developing statistical models of people’s health using longitudinal measurements of vital signs and questionnaires. Hospital costs are becoming unsustainable and will overwhelm state budgets within thirty years. Telehealth monitoring to manage chronic disease is becoming increasingly routine internationally and should reduce unnecessary hospital admissions and health service costs. To scale up telehealth services nationally, automated means of assessing changes in an individual health status are needed. This project’s automated risk assessment models are expected to identify exacerbations and orchestrate an optimal response from health services to reduce unscheduled admissions to hospital. Read more Read less
Funder: Australian Research Council
View Funded ActivityStart Date: 2015
End Date: 2018
Funder: National Health and Medical Research Council
View Funded Activity