Spatiotemporal mapping and detection of mortality cluster due to cardiovascular disease with Bayesian hierarchical framework using integrated nested Laplace approximation: A discussion of suitable statistic applications in Kersa, Oromia, Ethiopia

  • Melkamu Dedefo | melkyed@gmail.com School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Pietermaritzburg, South Africa. http://orcid.org/0000-0002-3466-1232
  • Henry Mwambi School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Pietermaritzburg, South Africa.
  • Sileshi Fanta School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Pietermaritzburg, South Africa.
  • Nega Assefa Kersa Health and Demographic Surveillance System (Kersa HDSS), Harar; College of Health and Medical Sciences, Haramaya University, Harar, Ethiopia.

Abstract

Cardiovascular diseases (CVDs) are the leading cause of death globally and the number one cause of death globally. Over 75% of CVD deaths take place in low- and middle-income countries. Hence, comprehensive information about the spatio-temporal distribution of mortality due to cardio vascular disease is of interest. We fitted different spatio-temporal models within Bayesian hierarchical framework allowing different space-time interaction for mortality mapping with integrated nested Laplace approximations to analyze mortality data extracted from the health and demographic surveillance system in Kersa District in Hararege, Oromia Region, Ethiopia. The result indicates that non-parametric time trends models perform better than linear models. Among proposed models, one with non-parametric trend, type II interaction and second order random walk but without unstructured time effect was found to perform best according to our experience and. simulation study. An application based on real data revealed that, mortality due to CVD increased during the study period, while administrative regions in northern and south-eastern part of the study area showed a significantly elevated risk. The study highlighted distinct spatiotemporal clusters of mortality due to CVD within the study area. The study is a preliminary assessment step in prioritizing areas for further and more comprehensive research raising questions to be addressed by detailed investigation. Underlying contributing factors need to be identified and accurately quantified.

Dimensions

Altmetric

PlumX Metrics

Downloads

Download data is not yet available.
Published
2018-11-12
Info
Issue
Section
Original Articles
Keywords:
Cardiovascular diseases, Integrated nested Laplace approximations, Second order random walk, Bayesian hierarchical framework, Spatio-temporal models, Kersa HDSS
Statistics
  • Abstract views: 1053

  • PDF: 483
  • HTML: 145
How to Cite
Dedefo, M., Mwambi, H., Fanta, S., & Assefa, N. (2018). Spatiotemporal mapping and detection of mortality cluster due to cardiovascular disease with Bayesian hierarchical framework using integrated nested Laplace approximation: A discussion of suitable statistic applications in Kersa, Oromia, Ethiopia. Geospatial Health, 13(2). https://doi.org/10.4081/gh.2018.681