Joint spatial modelling of disease risk using multiple sources: an application on HIV prevalence from antenatal sentinel and demographic and health surveys in Namibia

Abstract

BackgroundIn disease mapping field, researchers often encounter data from multiple sources. Such data are fraught with challenges such as lack of a representative sample, often incomplete and most of which may have measurement errors, and may be spatially and temporally misaligned. This paper presents a joint model in the effort to deal with the sampling bias and misalignment.MethodsA joint (bivariate) spatial model was applied to estimate HIV prevalence using two sources: 2014 National HIV Sentinel survey (NHSS) among pregnant women aged 15–49 years attending antenatal care (ANC) and the 2013 Namibia Demographic and Health Surveys (NDHS).ResultsFindings revealed that health districts and constituencies in the northern part of Namibia were found to be highly associated with HIV infection. Also, the study showed that place of residence, gender, gravida, marital status, number of kids dead, wealth index, education, and condom use were significantly associated with HIV infection in Namibia.ConclusionThis study had shown determinants of HIV infection in Namibia and had revealed areas at high risk through HIV prevalence mapping. Moreover, a joint modelling approach was used in order to deal with spatially misaligned data. Finally, it was shown that prediction of HIV prevalence using the NDHS data source can be enhanced by jointly modelling other HIV data such as NHSS data. These findings would help Namibia to tailor national intervention strategies for specific regions and groups of population.

Spatial modeling with R‐INLA: A review

“…and allows us to create multivariate models for multiple responses through a shared component structure (Mathew, Holand, Koistinen, Léon, & Sillanpää, 2016;Ntirampeba, Neema, & Kazembe, 2017), to jointly model the response and a misaligned spatial covariate (Barber, Conesa, Lladosa, & López-Quílez, 2016;Sadykova et al, 2017), to model a spatial point pattern together with marks or covariates Simpson, Illian, Lindgren, Sørbye, & Rue, 2016) and to model replicated point patterns (Illian, Sørbye, Rue, & Hendrichsen, 2012), see below.…”

“…Divide the observations y ( s 1 ), y ( s 2 ), …, y ( s N ) into G groups, where g [ k ] denotes group k , and assign likelihoods f 1 , f 2 , …, f G for groups 1, …, G , respectively. Equation then generalizes to and allows us to create multivariate models for multiple responses through a shared component structure (Mathew, Holand, Koistinen, Léon, & Sillanpää, ; Ntirampeba, Neema, & Kazembe, ), to jointly model the response and a misaligned spatial covariate (Barber, Conesa, Lladosa, & López‐Quílez, ; Sadykova et al, ), to model a spatial point pattern together with marks or covariates (Illian, Sørbye, & Rue, ; Simpson, Illian, Lindgren, Sørbye, & Rue, ) and to model replicated point patterns (Illian, Sørbye, Rue, & Hendrichsen, ), see below.…”

Regional maldistribution of human resources of rehabilitation institutions in China Mainland based on spatial analysis

“…p40mm The Local Moran's I analysis results include four significant types that may be shown in LISA maps based on the size of the observed values: High–High type (HH), Low–Low type (LL), High–Low type (HL), Low–High type (LH), and one type with no significant difference (NG) ( 26 ). Each type represents different practical significance, indicating the spatial heterogeneity between adjacent provinces.…”