Spatio-temporal Analysis of Acute Admissions for Ischemic Heart Disease in NSW, Australia

Burden, Sandy; Guha, Subharup; Morgan, Geoffrey G.; Ryan, Louise; Sparks, Ross; Young, Linda J.

doi:10.1007/s10651-005-1517-4

Cited by 8 publications

(14 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More specifically, the ecological investigations of response-exposure relationship presented in our recent studies [29,30,43,47] concern centrally with the associations at the regional or community level. With ecological effects being of primary interest, the underlying model assumption, inference and interpretation of the results are related to the 'at-risk' population and the geographical areas in which the population resides.…”

Section: Discussion and Future Researchmentioning

confidence: 99%

“…attribution of DALYs to regions of certain characteristic(s) under study. Ecological bias becomes an important issue when the ecological results are used to infer similar estimates and conclusions at individual level [47][48][49][50][51] (to name a few more recent papers). In this particular ecological analysis of BC injury and education data, for example, the DALY estimates were for men of age 20-39, whereas the covariate reflects the overall educational attainment for men and women age 25-54, both are at the local health area level.…”

Section: Discussion and Future Researchmentioning

confidence: 99%

“…Consequently, estimation and assessment of regional DALYs with respect to population of all ages or age groups will be influenced by regional demographic distribution. Our model framework can be readily extended to model data of several or all ages (or age groups) [28,47] and to explore the extent to which varying discount rate influence regional assessment of spatial DALY variations and temporal DALY trends. In addition, discounting future health 'can have a profound effect on the results of cost-effectiveness analysis', as pointed out by Murray and Lopez [1].…”

Section: Discussion and Future Researchmentioning

confidence: 99%

See 2 more Smart Citations

Mapping disability‐adjusted life years: a Bayesian hierarchical model framework for burden of disease and injury assessment

MacNab

2007

Statistics in Medicine

View full text Add to dashboard Cite

This paper presents a Bayesian disability-adjusted life year (DALY) methodology for spatial and spatiotemporal analyses of disease and/or injury burden. A Bayesian disease mapping model framework, which blends together spatial modelling, shared-component modelling (SCM), temporal modelling, ecological modelling, and non-linear modelling, is developed for small-area DALY estimation and inference. In particular, we develop a model framework that enables SCM as well as multivariate CAR modelling of non-fatal and fatal disease or injury rates and facilitates spline smoothing for non-linear modelling of temporal rate and risk trends. Using British Columbia (Canada) hospital admission-separation data and vital statistics mortality data on non-fatal and fatal road traffic injuries to male population age 20-39 for year 1991-2000 and for 84 local health areas and 16 health service delivery areas, spatial and spatiotemporal estimation and inference on years of life lost due to premature death, years lived with disability, and DALYs are presented. Fully Bayesian estimation and inference, with Markov chain Monte Carlo implementation, are illustrated. We present a methodological framework within which the DALY and the Bayesian disease mapping methodologies interface and intersect. Its development brings the relative importance of premature mortality and disability into the assessment of community health and health needs in order to provide reliable information and evidence for community-based public health surveillance and evaluation, disease and injury prevention, and resource provision.

show abstract

Section: Discussion and Future Researchmentioning

confidence: 99%

Section: Discussion and Future Researchmentioning

confidence: 99%

Section: Discussion and Future Researchmentioning

confidence: 99%

See 1 more Smart Citation

Mapping disability‐adjusted life years: a Bayesian hierarchical model framework for burden of disease and injury assessment

MacNab

2007

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…Burden et al (2005) analyze data from the Spatial Environmental Epidemiology in New South Wales (SEE NSW) project. Due to the computational demands of fitting a large administrative database, they…”

Section: Remarkmentioning

confidence: 99%

Gauss–Seidel Estimation of Generalized Linear Mixed Models With Application to Poisson Modeling of Spatially Varying Disease Rates

Guha

Ryan

Morara

2009

Journal of Computational and Graphical Statistics

Self Cite

View full text Add to dashboard Cite

Generalized linear mixed models (GLMMs) provide an elegant framework for the analysis of correlated data. Due to the non-closed form of the likelihood, GLMMs are often fit by computational procedures like penalized quasi-likelihood (PQL). Special cases of these models are generalized linear models (GLMs), which are often fit using algorithms like iterative weighted least squares (IWLS). High computational costs and memory space constraints often make it difficult to apply these iterative procedures to data sets with very large number of cases. This paper proposes a computationally efficient strategy based on the GaussSeidel algorithm that iteratively fits sub-models of the GLMM to subsetted versions of the data. Additional gains in efficiency are achieved for Poisson models, commonly used in disease mapping problems, because of their special collapsibility property which allows data reduction through summaries. Convergence of the proposed iterative procedure is guaranteed for canonical link functions. The strategy is applied to investigate the relationship between ischemic heart disease, socioeconomic status and age/gender category in New South Wales, Australia, based on outcome data consisting of approximately 33 million records. A simulation study demonstrates the algorithm's reliability in analyzing a data set with 12 million records for a (non-collapsible) logistic regression model. Gauss-Seidel Estimation of Generalized 1 Hosted by The Berkeley Electronic PressKeywords: Backfitting algorithm, CAR model, collapsibility, epidemiology, iterative weighted least squares, large sample sizes. AbstractGeneralized linear mixed models (GLMMs) provide an elegant framework for the analysis of correlated data. Due to the non-closed form of the likelihood, GLMMs are often fit by computational procedures like penalized quasi-likelihood (PQL). Special cases of these models are generalized linear models (GLMs), which are often fit using algorithms like iterative weighted least squares (IWLS).High computational costs and memory space constraints often make it difficult to apply these iterative procedures to data sets with very large number of cases. This paper proposes a computationally efficient strategy based on the Gauss-Seidel algorithm that iteratively fits sub-models of the GLMM to subsetted versions of the data. Additional gains in efficiency are achieved for Poisson models, commonly used in disease mapping problems, because of their special collapsibility property which allows data reduction through summaries. Convergence of the proposed iterative procedure is guaranteed for canonical link functions. The strategy is applied to investigate the relationship between ischemic heart disease, socioeconomic status and age/gender category in New South Wales, Australia, based on outcome data consisting of approximately 33 million records. A simulation study demonstrates the algorithm's reliability in analyzing a data set with 12 million records for a (non-collapsible) logistic regression model.

show abstract

“…Beggs & Siciliano 2001;Cass et al 2001;Furler et al 2002;Overland et al 2002;Page et al 2002;Burden et al 2005;Leonard et al 2005;Armfield 2007;Korda et al 2007;Amir & Donath 2008;Chen et al 2010), despite its use in these contexts being questioned (Pearce 2000;McCracken 2001;Kennedy & Firman 2004) as a potential example of the ecological fallacy (Robinson 1950), where inferences about individuals are made from group-level data for the group (or area) to which those individuals belong. Of particular concern for those involved in resource allocation and policy development for disadvantaged individuals and households, is where the needs of relatively disadvantaged individuals within relatively advantaged areas may be overlooked due to the incorrect inference that the area-based score accurately reflects the distribution of relative advantage and disadvantage at an individual level.…”

mentioning

confidence: 99%

Two Tales of a City: detecting socio-economic disadvantage in an ‘advantaged’ Australian urban centre

Goldie

Kakuk

Wood

2014

Australian Geographer

View full text Add to dashboard Cite

Understanding the distribution of socio-economic status (SES) within and between communities of varying spatial scales is vital for equitable and effective resource delivery and policy development. In Australia, the Socio-economic Indexes for Areas (SEIFA) have been used extensively for these purposes, in both research and government service delivery. As area-based averages, however, their use in these areas is potentially confounded by the ecological fallacy and the modifiable areal unit problem (MAUP), statistical issues which have widespread implications for the use of spatial data. The Socioeconomic Index for Individuals (SEIFI) is an individual-based index developed by the ABS to quantify SES at an individual level for 15-64 year-old Australians. Previous work investigated the potential disparities between these area-and individual-level indices, showing that considerable disparities exist, particularly in the Australian Capital Territory (ACT). Using spatial autocorrelation and pair-wise proportion analyses, we show that there was considerable diversity in individual-level SES at a very fine level of geography in 2006, a unique pattern in Australia. We also show that the SES ranking of areas within the ACT is, in many instances, not indicative of the proportions of individuals living within that area experiencing high levels of relative socio-economic disadvantage. We show that between 65-95 per cent of the ACT's disadvantaged population are masked within areas ranked as advantaged, depending on the index and level of spatial aggregation. Our results suggest that the use of SEIFA as a proxy for individual level disadvantage is highly problematic at both a theoretical and practical level, and necessitates further development of an individual-or household-level index as part of the regular suite of socio-economic indices produced by the ABS.

show abstract

Spatio-temporal Analysis of Acute Admissions for Ischemic Heart Disease in NSW, Australia

Cited by 8 publications

References 36 publications

Mapping disability‐adjusted life years: a Bayesian hierarchical model framework for burden of disease and injury assessment

Mapping disability‐adjusted life years: a Bayesian hierarchical model framework for burden of disease and injury assessment

Gauss–Seidel Estimation of Generalized Linear Mixed Models With Application to Poisson Modeling of Spatially Varying Disease Rates

Two Tales of a City: detecting socio-economic disadvantage in an ‘advantaged’ Australian urban centre

Contact Info

Product

Resources

About