The SPDE-AR(1) model offers a strong and uncertainty-based early warning system for severe malaria in Cameroon, which allows interventions to be targeted in areas and populations at high risk.
Abstract
Background Malaria is a significant public health problem in Cameroon where spatial and temporal heterogeneities in transmission make early-warning and control complicated. The traditional forecasting methods have the limitation that they are not always able to model both the spatial dependency and the uncertainty; therefore, restricting their functionality. Methods We used a spatio-temporal bayesian model that incorporates a Stochastic Partial Differential Equation (SPDE) that models the spatial correlations and an autoregressive time prior AR(1), solved by Integrated Nested Laplace Approximation (INLA). The analysis of severe malaria cases in 2015–2024 was done separately for children <5 years, adults and pregnant women, and rainfall as a climatic covariate and population adjusted offsets for at-risk individuals. Exceedance probabilities were calculated considering historical risk to identify hotspots. Model performance was evaluated through DIC, WAIC and calibration diagnostics. Results Severe malaria risk was positively related to rainfall and this relationship was observed for all demographic groups. The Far North had long-term high risk foci; secondary risks were noted in the North, Centre and Littoral. The most intense hotspots were observed in pregnant women and children. Conclusions The SPDE-AR(1) model offers a strong and uncertainty-based early warning system for severe malaria in Cameroon, which allows interventions to be targeted in areas and populations at high risk.
Understanding how malaria incidence and mortality vary across space and time is important for strengthening malaria surveillance and supporting evidence-based planning of control interventions. This study examined the joint spatial and temporal patterns of malaria incidence and mortality in Kenya, identified high-risk counties and assessed whether the two outcomes shared common distributions. County-level malaria incidence and mortality data for 2013 to 2024 were analysed using a joint Bayesian hierarchical model based on a spatio-temporal conditional autoregressive framework, which accounted for spatial dependence among neighbouring counties and temporal correlation across successive years. Model performance was compared with a multivariate spatio-temporal modelling framework to evaluate shared and outcome-specific variation. Integrated Nested Laplace Approximation was used for Bayesian inference. Weighted adjacency matrices were constructed, and structured and unstructured spatial effects were incorporated to account for spatial heterogeneity, temporal dependence and unexplained variability. The results showed persistent spatial clustering of both outcomes throughout the study period. Counties in the lake-endemic region, particularly Kisumu, Siaya and Busia, consistently had higher spatial risks for malaria incidence and mortality than most other counties. The spatial distributions of incidence and mortality were positively associated, indicating that counties with higher incidence tended to have higher mortality. Temporal patterns differed between the outcomes, with incidence showing broader fluctuation and mortality showing less pronounced change. The findings indicate that joint spatio-temporal modelling can support malaria surveillance and guide spatially targeted control interventions in Kenya.
Polycarp Nyabuto, A. Wanjoya, Thomas Magetto et al.· Asian Journal of Probability...· 0 citations
Malaria elimination is shaped by complex interactions among climatic, environmental, socioeconomic, demographic, health-system, and intervention-related factors. However most studies examine only subsets of these drivers, limiting understanding of their combined influence on epidemiological risks. In this study, we integrated 25 years of data from 44 African countries on malaria burden and control, climate, environmental and land-use conditions, socioeconomic and demographic characteristics, and health-system capacity within a unified geospatial, explainable machine-learning, and forecasting framework to characterize spatiotemporal patterns of malaria, quantify the relative contributions of key determinants, and generate 10-year Africa-wide and country-specific forecasts of malaria incidence and mortality rates per 1,000 people at risk. We identified and mapped malaria incidence and mortality hotspots using the Getis-Ord Gi* statistic. Our analyses showed that both incidence and mortality burden remained highly heterogeneous across Africa, with persistent hotspots concentrated in the West and Central Africa. The explainable machine-learning model, that achieved high predictive performance (i.e., XGBoost for incidence, holdout R$^2$ = 0.92; Random Forest for mortality, holdout R$^2$ = 0.91), identified lower availability of hospital beds (per 1,000 people), higher mortality rate attributed to unsafe WASH (per 100,000), and lower percentage (%) of people using handwashing facilities as the top three most influential determinants of higher risk of infection across Africa whereas higher mortality rate attributed to unsafe WASH (per 100,000), lower % of people using at least basic sanitation services, and access to electricity (%) were associated with worse mortality outcomes. Forecasting models also demonstrated strong predictive accuracy (Naive persistence and Elastic Net, holdout R$^2$ = 0.98 for incidence and 0.97 for mortality). Assuming current intervention and structural conditions persist, Africa-wide malaria incidence was projected to remain broadly stable, with a modest upward trend by 2035, whereas mortality was projected to decline initially and subsequently remain relatively unchanged. However, substantial country-level heterogeneity showed both emerging transmission hotspots and persistently high-burden countries. this suggests there is a need for sustained control and accelerated elimination efforts. Overall, this study demonstrates that integrating geospatial analysis, explainable machine learning, and forecasting provides a robust framework for understanding malaria dynamics, identifying the key determinants of burden, anticipating future trends, and supporting geographically targeted malaria control across Africa. Beyond malaria, our analyses can be applied as a generalizable approach for infectious disease surveillance, early-warning systems, hotspot detection, resource prioritization, and precision public health using large-scale longitudinal health data.
Background: Dengue remains a major public health challenge in Eastern Visayas, Philippines, yet climate-driven transmission dynamics remain underexplored in the region. Methods: This retrospective ecological time-series study analyzed weekly surveillance and meteorological data from 2019 to 2023. Nonlinear exposure–response relationships and lagged associations between rainfall, temperature, and dengue incidence were modeled using a Distributed Lag Nonlinear Model (DLNM) within a Bayesian framework fitted via Integrated Nested Laplace Approximation (INLA), assessing lag effects up to 10 weeks. Results: Weekly rainfall strongly influenced dengue risk, peaking markedly at 200 mm with a cumulative Relative Risk (RR) of 19.4 (95% CrI: 10.3–36.5). Higher precipitation levels showed a downward risk trajectory, consistent with larval flushing. Temperature displayed a suggestive bimodal pattern with elevated risk at 24°C and 28–29°C across 4–6-week lags, though near-average temperatures (e.g., 28.5°C) showed no statistically strong cumulative risk changes.Conclusion: Dengue risk in Eastern Visayas is driven by precise rainfall thresholds and thermal lag windows. Incorporating 200 mm precipitation and 28–29°C temperature triggers into proactive climate-based surveillance—pending external validation—can enhance regional public health preparedness and local outbreak response.
N. Milla· Recoletos Multidisciplinary...· 0 citations
Abstract Background Malaria distribution in sub-Saharan Africa is becoming increasingly spatially heterogeneous. Pre-elimination areas, high-transmission settings and urban areas with increasing transmission may all coexist within the same country. Effective intervention planning requires identifying high-risk areas and their drivers—an area in which geospatial models can provide valuable insights. Yet these models often assume stationary risk factors across transmission levels and frequently rely on prevalence survey data, which are unreliable in low-transmission settings. This study uses routine public-sector health facility data (ie, DHIS2) to model malaria incidence in Senegal from 2017 to 2021, accounting for transmission levels, and introduces novel fine-scale estimates of reported malaria incidence derived from dasymetric disaggregation. Methods Health facility catchment populations were estimated using a probabilistic approach, allowing individuals to attend multiple facilities based on relative travel time. Malaria incidence per catchment was modelled using high-resolution environmental and socioeconomic covariates within a Bayesian hierarchical modelling framework. Separate models were fitted by season and endemicity-urbanisation level to assess the heterogeneity of risk factors. We adapted dasymetric disaggregation methods from population mapping to redistribute facility-level cases to 1 km pixels. Results Estimated malaria incidence increased from 60 cases per 1000 people in 2017 to 71 cases in 2021. Key risk factors varied across endemicity-urbanisation levels; some factors were uniquely associated with low (eg, distance to roads), moderate (eg, cropland) and high-transmission settings (eg, flooded vegetation). Fine-scale maps represent malaria cases that the public-sector health system routinely reports, rather than the total malaria burden, and revealed potential underdiagnosis in remote areas. Conclusions Our findings emphasise the importance of considering endemicity levels when evaluating malaria risk factors in heterogeneous transmission contexts. As health system data quality continues to improve, this approach offers a scalable alternative for mapping reported malaria incidence, supporting better targeted interventions and the identification of underdiagnosed areas.
Camille Morlighem, Corentin Visée, C. Nnanatu et al.· BMJ Global Health· 0 citations
The results reveal significant nonlinear and temporally lagged effects of rainfall and temperature on malaria incidence, with evidence of threshold behaviour across climatic ranges and evidence to support climate-informed early warning systems and adaptive malaria control strategies across SSA.
O. A. Okeke, S. Adebanjo· Scientific Reports· 0 citations
A data-driven spatio-temporal framework that integrates geospatial, ecological and climatic datasets to explain and forecast the dynamics of H5N1 outbreaks between 2021 and 2024 indicates that H5N1 transmission is structured by ecological drivers and local persistence mechanisms rather than purely seasonal effects.
Mehak Jindal, Samsung Lim, Raina MacIntyre· The International Archives o...· 0 citations