Multivariate spatiotemporal using INLA: analysis of sexually transmitted infections in West Java, Indonesia
Abstract
Sexually transmitted infections (STIs), including human immunodeficiency virus (HIV) and hepatitis B/C, pose a significant public health challenge in Indonesia, particularly in West Java, the country’s most populous province. This study seeks to analyze the spatiotemporal distribution of STIs to enhance disease management strategies. Spatiotemporal multivariate M-models utilizing integrated nested laplace approximation (INLA) inference were applied to the Indonesian National Health Insurance data covering the period from 2015 to 2022 in West Java. Fifteen models were developed based on three spatial models, each paired with a temporal prior and five interaction types. The analysis identified the proper conditional autoregressive model with temporal interaction (pCAR type 2) as the best-performing model. This model revealed distinct temporal patterns in each region that did not influence neighboring areas. Notably, the posterior mean relative risk for HIV and hepatitis B/C was found to be higher in northern West Java (>1.00); however, the region most at risk for each infection differs, partially due to a lack of correlation between HIV and hepatitis B/C (\rho=-0.15). These findings underscore the need for customized mitigation strategies tailored to specific diseases and regional differences in risk patterns.
Keywords
Bayesian regression; Disease mapping; Hepatitis; Human immunodeficiency virus; Spatiotemporal M-models
Full Text:
PDFDOI: https://doi.org/10.11591/eei.v15i6.10627
Refbacks
- There are currently no refbacks.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191
,
e-ISSN: 2302-9285
This journal is published by the
Institute of Advanced Engineering and Science (IAES)
.