Bayesian hierarchical modeling of joint spatiotemporal risk patterns for Human Immunodeficiency Virus (HIV) and Tuberculosis (TB) in Kenya

Abstract

The spatiotemporal modeling of multiple diseases simultaneously is a recent extension that advances the space-time analysis to model multiple related diseases simultaneously. This approach strengthens inferences by borrowing information between related diseases. Numerous research contributions to spatiotemporal modeling approaches exhibit their strengths differently with increasing complexity. However, contributions that combine spatiotemporal approaches to modeling of multiple diseases simultaneously are not so common. We present a full Bayesian hierarchical spatio-temporal approach to the joint modeling of Human Immunodeficiency Virus and Tuberculosis incidences in Kenya. Using case notification data for the period 2012 - 2017, we estimated the model parameters and determined the joint spatial patterns and temporal variations. Our model included specific and shared spatial and temporal effects. The specific random effects allowed for departures from the shared patterns for the different diseases. The space-time interaction term characterized the underlying spatial patterns with every temporal fluctuation. We assumed the shared random effects to be the structured effects and the disease-specific random effects to be unstructured effects. We detected the spatial congruence in the distribution of Tuberculosis and Human Immunodeficiency Virus in approximately 29 counties around the western, central and southern regions of Kenya. The distribution of the shared relative risks had minimal difference with the Human Immunodeficiency Virus disease-specific relative risk whereas that of Tuberculosis presented many more counties as high-risk areas. The flexibility and informative outputs of Bayesian Hierarchical Models enabled us to identify the similarities and differences in the distribution of the relative risks associated with each disease. Estimating the Human Immunodeficiency Virus and Tuberculosis shared relative risks provide additional insights towards collaborative monitoring of the diseases and control efforts.

Analysis of joint spatio-temporal characteristics of multiple diseases

“…The spatio-temporal data of public health, as the disease case count of spatial region and temporal interval, is usually simulated based on the Poisson regression model. In order to explore the characteristics of multiple diseases, Downing [16], Gómez-Rubio [18], and Otiende [19] et al proposed a Bayesian spatio-temporal model of multiple diseases (Model 1):…”

“…It used its joint analysis of the time and space data of TB, HBV, and HIV to explore the similar and particular space and time modes and risk factors of the three diseases. Because similar risk factors usually cause these patterns, it is possible to find some common risk patterns by identifying diseases with similar patterns, which can highlight different risk change trends of specific conditions [19]. Compared with other multi-disease Bayesian spatio-temporal models [16,18,19], this study not only allows the definition of shared and specific disease spatiotemporal patterns but also provides a modular specification of shared and specific disease spatio-temporal patterns.…”

“…Because similar risk factors usually cause these patterns, it is possible to find some common risk patterns by identifying diseases with similar patterns, which can highlight different risk change trends of specific conditions [19]. Compared with other multi-disease Bayesian spatio-temporal models [16,18,19], this study not only allows the definition of shared and specific disease spatiotemporal patterns but also provides a modular specification of shared and specific disease spatio-temporal patterns. On the other hand, the model established in this research can not only expand to more than three diseases but also improve the fitting accuracy of the model by adding shared spatio-temporal interaction items and selecting appropriate spatio-temporal interaction types.…”

“…Gómez-Rubio [18] et al proposed a multi-disease Bayesian hierarchical spatiotemporal model to explore the similarities and differences between the causes of death of oral cancer, esophageal cancer, and gastric cancer at the provincial level in Spain. Otiende [19] et al proposed a multi-disease Bayesian hierarchical spatio-temporal method to estimate the common relative risk between HIV and TB in Kenya.…”