As found in the health studies literature, the levels of climate association between epidemiological diseases have been found to vary across regions. Therefore, it seems reasonable to allow for the possibility that relationships might vary spatially within regions. We implemented the geographically weighted random forest (GWRF) machine learning method to analyze ecological disease patterns caused by spatially non-stationary processes using a malaria incidence dataset for Rwanda. We first compared the geographically weighted regression (WGR), the global random forest (GRF), and the geographically weighted random forest (GWRF) to examine the spatial non-stationarity in the non-linear relationships between malaria incidence and their risk factors. We used the Gaussian areal kriging model to disaggregate the malaria incidence at the local administrative cell level to understand the relationships at a fine scale since the model goodness of fit was not satisfactory to explain malaria incidence due to the limited number of sample values. Our results show that in terms of the coefficients of determination and prediction accuracy, the geographical random forest model performs better than the GWR and the global random forest model. The coefficients of determination of the geographically weighted regression (R2), the global RF (R2), and the GWRF (R2) were 4.74, 0.76, and 0.79, respectively. The GWRF algorithm achieves the best result and reveals that risk factors (rainfall, land surface temperature, elevation, and air temperature) have a strong non-linear relationship with the spatial distribution of malaria incidence rates, which could have implications for supporting local initiatives for malaria elimination in Rwanda.

Childhood stunting is a serious public health concern in Rwanda. Although stunting causes have been documented, we still lack a more in‐depth understanding of their local factors at a more detailed geographic level. We cross‐sectionally examined 615 height‐for‐age prevalence observations in the Northern Province of Rwanda, linked with their related covariates, to explore the spatial heterogeneity in the low height‐for‐age prevalence by fitting linear and non‐linear spatial regression models and explainable machine learning. Specifically, complemented with generalized additive models, we fitted the ordinary least squares (OLS), a standard geographically weighted regression (GWR), and multiscale geographically weighted regression (MGWR) models to characterize the imbalanced distribution of stunting risk factors and uncover the nonlinear effect of significant predictors, explaining the height‐for‐age variations. The results reveal that 27% of the children measured were stunted, and that likelihood was found to be higher in the districts of Musanze, Gakenke, and Gicumbi. The local MGWR model outperformed the ordinary GWR and OLS, with coefficients of determination of 0.89, 0.84, and 0.25, respectively. At specific ranges, the study shows that height‐for‐age decreases with an increase in the number of days a child was left alone, elevation, and rainfall. In contrast, land surface temperature is positively associated with height‐for‐age. However, variables like the normalized difference vegetation index, slope, soil fertility, and urbanicity exhibited bell‐shaped and U‐shaped non‐linear associations with the height‐for‐age prevalence. Identifying areas with the highest rates of stunting will help determine the most effective measures for reducing the burden of undernutrition.

The study focused on the identification of theoretical and methodological constructs that can be used to analyse and improve the spatial performance of public health service delivery systems and the development of a corresponding spatial-analysis and GIS-based planning approach using the city of Kigali as a case study. Access to health care as a multi-tiered system was measured by using five dimensions of access, namely geographic accessibility, availability, affordability, acceptability and accommodation. Geo-statistical analysis was performed to measure and evaluate access to the district and referral health care. For geographic access, the travel time for every trip is approximated for the two main modes of transport (walking and public transport). To realistically represent the friction of distance, the street network was categorised into several road classes for which different travel speeds are estimated for each transport mode on the basis of local knowledge. A factor analysis model was used for availability, affordability, acceptability, and accommodation dimensions. Different indicators were evaluated in various units and scales and standardized to see how satisfaction levels varied with each dimension. Based on the type of indicator, for the cost or benefit, the score was zero (0) or one (1). One (1) was considered a positive impact, while zero (0) was considered a negative impact. Summary scores were developed for all indicators by combining more than one indicator into a single value. The created summary score also ranges from 0 to 1, and the higher the score, the better the access attainment. To find areas that need intervention, the comparison of all five indicators and the scores of access for each indicator was made. The dimensions of geographic accessibility and availability appeared to be the most problematic. The district health care dimensions have revealed a low performance level in geographic accessibility (0.64) and a high-performance level in affordability (0.94). The referral health care dimensions have revealed a low performance level of geographic accessibility (0.17) and a high-performance level of acceptability (0.92). Health planners and policy makers will commonly require such a planning method, particularly in the developing world where spatial contexts are highly dynamic as a result of rapid urbanisation.

Motorcycle emissions are a growing environmental and public health concern in many low- and middle-income countries. While several studies have examined the emission profiles from larger vehicles in urban areas, very few have analyzed motorcycle emissions through a parametric and non-parametric multivariate lens, combining technical, behavioral, and socioeconomic factors, a gap that this study attempts to address. MANOVA and Kruskal–Wallis H test analyses highlighted visible smoke emissions (hydrocarbon: H = 30.62, p < 0.001; carbon monoxide: H = 16.71, p < 0.001; dioxygen: H = 6.67, p = 0.010), year of manufacturing (carbon monoxide: H = 20.61, p < 0.001; hydrocarbon: H = 11.80, p = 0.008), average fuel consumption (carbon dioxide: H = 13.32, p = 0.004), and daily driving distance (carbon monoxide: H = 10.09, p = 0.018) as significant predictors of emissions. The results also indicate that newer and well-maintained motorcycles (2018–2021) consistently showed the lowest carbon monoxide and HC levels compared to the older and poorly maintained counterparts with the highest emissions. Consistently, motorcycles with visible smoke showed substantially elevated carbon monoxide and hydrocarbons and reduced dioxygen, establishing visible smoke as a practical marker for excessive emissions. Additionally, younger riders (19–28 years) exhibited higher hydrocarbon emissions, while greater riding experience and more passengers influenced dioxygen levels. Spearman correlation analysis reinforced these patterns, with visible smoke showing strong positive correlations with carbon monoxide (ρ = 0.21) and hydrocarbon (ρ = 0.28), and carbon monoxide was negatively associated with motorcycle age (ρ = −0.18). These findings underscore manufacturing year, vehicle maintenance, and visible smoke as practical, high-impact targets for reducing motorcycle emissions, offering a basis for targeted emission control strategies.