Spatio-Temporal Random Effects Modeling of Malaria Incidence and Mortality in Kenya

Malaria is a major public health challenge in sub-Saharan Africa, with transmission patterns that vary significantly across space and time due to environmental, socioeconomic, and epidemiological factors. These variations complicate efforts to design effective and targeted interventions, making it crucial to understand the dynamics of disease spread. This study employed Bayesian spatio-temporal random effects modeling framework to analyze malaria incidence and mortality ratio across Kenya. The approach incorporated spatial and temporal dependencies to provide a detailed understanding of malaria incidence and mortality risk patterns. Spatial random effects were modeled using conditional autoregressive (CAR) priors to account for correlations among neighboring counties, while temporal dependence was captured using autoregressive processes of order two (AR2), reflecting trends over multiple time periods. An evaluation was on the performance of Spatio-Temporal Poisson Linear Trend Model (STPLM), Spatio-Temporal Poisson ANOVA Model (STPAM), Spatio-Temporal Poisson Separable Model (STPSM) and Poisson Temporal Model for Spatio-Temporal Effects (PTSTN)using the Deviance Information Criterion (DIC), the effective number of parameters (p.d) and the Log Marginal Pseudo-Likelihood (LMPL). The Spatio-Temporal Poisson ANOVA Model (STPAM) was found as the best Poissson Spatial-Temporal Model and was used to develop a multivariate spatio-temporal model for the joint modeling of malaria incidence and mortality. Using the developed model, the study identified significant spatial clustering of malaria, with persistent high-risk zones in western and coastal counties. Temporal trends indicated an overall decline in transmission, though progress was uneven across counties, reflecting differences in intervention coverage, healthcare access, and local epidemiology. These findings underscored the value of multivariate spatio-temporal modeling of malaria incidence and mortality for guiding malaria control strategies. This study thus demonstrates that Bayesian Spatial-Temporal modeling is essential for understanding heterogeneous malaria incidence and mortality risk and informing strategies aimed at reducing disease burden and advancing toward malaria elimination in Kenya.