Augmenting disease maps: a Bayesian meta-analysis approach

Jahan, Farzana; Duncan, Earl; Cramb, Susanna; Baade, Peter D.; Mengersen, Kerrie

doi:10.1098/rsos.192151

Cited by 4 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since correlation is a standardised form of covariance, the precision of estimates and the correlation between cancers are related. Since the choice of cancer types included may influence the results, we recommend comparing the multivariate results with the univariate results (using an approach such as [32]). Also, because this model was developed for summarised modelled estimates the proposed model cannot be applied to raw incidence rates without modifying, such as introducing some form of spatial smoothing and changing the distributional assumptions at different levels.…”

Section: Discussionmentioning

confidence: 99%

“…where µ i is the overall mean of ith cancer and ω i be the variance covariance term accounting for variation between the means of different regions and same cancers. We are not interested in these parameters as we already performed univariate analysis to see the means and variation due to remoteness for each cancer separately [32]. The overall mean of ith cancer, µ i can then be modelled as:…”

Section: A2 More Hierarchy In the Multivariate Meta-analysis Modelmentioning

confidence: 99%

“…In an earlier study, Bayesian hierarchical meta-analysis models for each of the 20 cancers were fitted separately and the pattern of incidence according to remoteness categories (major cities, regional and remote areas) was explored [32]. The univariate meta-analysis model, if extended to accommodate multiple selected cancers in the same model, can be employed to identify possible association between selected cancers and could also help in detecting small areas where multiple cancer types have higher incidence rates jointly.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Multivariate Bayesian meta-analysis: joint modelling of multiple cancer types using summary statistics

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background Cancer atlases often provide estimates of cancer incidence, mortality or survival across small areas of a region or country. A recent example of a cancer atlas is the Australian cancer atlas (ACA), that provides interactive maps to visualise spatially smoothed estimates of cancer incidence and survival for 20 different cancer types over 2148 small areas across Australia. Methods The present study proposes a multivariate Bayesian meta-analysis model, which can model multiple cancers jointly using summary measures without requiring access to the unit record data. This new approach is illustrated by modelling the publicly available spatially smoothed standardised incidence ratios for multiple cancers in the ACA divided into three groups: common, rare/less common and smoking-related. The multivariate Bayesian meta-analysis models are fitted to each group in order to explore any possible association between the cancers in three remoteness regions: major cities, regional and remote areas across Australia. The correlation between the pairs of cancers included in each multivariate model for a group was examined by computing the posterior correlation matrix for each cancer group in each region. The posterior correlation matrices in different remoteness regions were compared using Jennrich’s test of equality of correlation matrices (Jennrich in J Am Stat Assoc. 1970;65(330):904–12. 10.1080/01621459.1970.10481133). Results Substantive correlation was observed among some cancer types. There was evidence that the magnitude of this correlation varied according to remoteness of a region. For example, there has been significant negative correlation between prostate and lung cancer in major cities, but zero correlation found in regional and remote areas for the same pair of cancer types. High risk areas for specific combinations of cancer types were identified and visualised from the proposed model. Conclusions Publicly available spatially smoothed disease estimates can be used to explore additional research questions by modelling multiple cancer types jointly. These proposed multivariate meta-analysis models could be useful when unit record data are unavailable because of privacy and confidentiality requirements.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A2 More Hierarchy In the Multivariate Meta-analysis Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Multivariate Bayesian meta-analysis: joint modelling of multiple cancer types using summary statistics

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For parametric modelling of disease incidence or mortality, the response variable is usually assumed to have a Poisson distribution with an expected value that can be explained by a function of covariates and spatial random effects. Gaussian distributions are also commonly used for modelling continuous response variables such as standardised incidence ratios (SIRs) on a logarithmic scale [40] and binomial distributions are used for proportions [41]. There is a wide range of spatial prior formulations in the literature, including basis functions, deformation methods, Gaussian Markov Random Field (GMRF) methods etc.…”

Section: Recap Of Bayesian Parametric Spatial Modelsmentioning

confidence: 99%

Evaluation of spatial Bayesian Empirical Likelihood models in analysis of small area data

et al. 2022

Self Cite

View full text Add to dashboard Cite

Bayesian empirical likelihood (BEL) models are becoming increasingly popular as an attractive alternative to fully parametric models. However, they have only recently been applied to spatial data analysis for small area estimation. This study considers the development of spatial BEL models using two popular conditional autoregressive (CAR) priors, namely BYM and Leroux priors. The performance of the proposed models is compared with their parametric counterparts and with existing spatial BEL models using independent Gaussian priors and generalised Moran basis priors. The models are applied to two benchmark spatial datasets, simulation study and COVID-19 data. The results indicate promising opportunities for these models to capture new insights into spatial data. Specifically, the spatial BEL models outperform the parametric spatial models when the underlying distributional assumptions of data appear to be violated.

show abstract

“…Diggle et al [8] considered an application to the mapping of environmental count data. Jahan et al [11] proposed a hierarchical Bayesian meta-analysis model which analysed the point and interval estimates from an online atlas, where they modelled the published cancer incidence estimates available as part of the online Australian Cancer Atlas. Wakefield et al [24] looked into an application to the mapping of cancer risk in the United Kingdom.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Disease Mapping: A Literature Review With an Application, Using WinBugs Software

Raubenheimer,

Southey,

Sarah E. Radlof

2022

Stat., optim. inf. comput.

View full text Add to dashboard Cite

In this paper we review the improper and proper conditional autoregressive (CAR) models. A set of spatially correlated Gaussian random effects are assumed. The CAR model which contains components from both the uncorrelated heterogeneity (UH) and correlated heterogeneity (CH) models, have been applied to the South African acute pericarditis 2014 data set, where a Poisson model is used. Acute pericarditis is caused by an inflammation of the pericardium in the heart. The data set has been used to examine whether there is a significant difference between the proper conditional autoregressive prior and the intrinsic conditional autoregressive prior for the correlated heterogeneity component in a convolution model. Both the hyperpriors of the precision for the uncorrelated heterogeneity components were modelled by using the Jeffreys’ prior. The sensitivity of the hyperprior has also been investigated. The deaths from this disease in 2014 in South Africa have been considered, where disease maps and the relative risk of acquiring and dying from acute pericarditis have been investigated, as well as the standardised mortality ratio (SMR). The convergence and burn-in period of the models were assessed by the Brook-Gelman-Rubin (BGR) diagnostic. The deviance information criterion (DIC) was used to assess the models.

show abstract

Augmenting disease maps: a Bayesian meta-analysis approach

Cited by 4 publications

References 50 publications

Multivariate Bayesian meta-analysis: joint modelling of multiple cancer types using summary statistics

Multivariate Bayesian meta-analysis: joint modelling of multiple cancer types using summary statistics

Evaluation of spatial Bayesian Empirical Likelihood models in analysis of small area data

Bayesian Disease Mapping: A Literature Review With an Application, Using WinBugs Software

Contact Info

Product

Resources

About