2026· Dutse Journal of Pure and Applied Sciences· Vol 12, pp. 65-79· 0 citations
TL;DR
A framework that serves as a proof-of-concept for the prediction of typhoid-malaria coinfection using machine learning, with diagnostic testing selected as the most reliable predictor is developed and it can be concluded that the validation of the model should be done with clinical data.
Abstract
Nigeria has a high percentage of burden of both typhoid fever and malaria, with climate change and population dynamics potentially influencing disease co-infection patterns. Emerging evidence suggest that climatic change may have influence in the coinfection dynamics of these diseases. However, a comprehensive epidemiological data on the pattern of coinfection is limited and this invariably affects the evidence-based interventions, the objective of this study is to develop and validate a predictive model that can serve as a framework for the coinfection of malaria and typhoid patterns in Nigeria using the effect of climate change, demographic factors and clinical presentations as contributing variables. An epidemiological informed datasets was generated synthetically using (n=10,000 cases) incorporating a probability distribution prevalence of the disease that were derived from literature on the disease prevalence, symptoms, demographic characteristics across the states in Nigeria. A random forest model classification algorithm was implemented in R programming language environment with the performance metrics evaluated and cross-validated correlation analysis and t-test was also examined to get the relationships between the predictors and the coinfection status. The random forest predictive model achieved an accuracy of 94.47Typhoid test result showed the strongest positive correlation with a co-infection rate of r = 0.533, followed by malaria test results with a co-infection rate of r = 0.361. Temperature as a climatic predictor showed a weak positive correlation of r = 0.040.The analyzed states showed that Borno, Gombe, and Osun have the highest co-infection rates of 65.8%, 65.6%, and 65.5% respectively, this study has developed a framework that serves as a proof-of-concept for the prediction of typhoid-malaria coinfection using machine learning, with diagnostic testing selected as the most reliable predictor, it can be concluded that the validation of the model should be done with clinical data.
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.
Infectious diseases such as malaria, tuberculosis, and cholera remain major public health concerns in Nigeria. This study investigated the temporal trends of malaria, tuberculosis, and cholera in Nigeria from 2010 to 2023 using epidemiological and statistical modelling approaches. Secondary data were obtained from national and international health databases alongside environmental variables including rainfall and temperature. Descriptive statistics, correlation analysis, SEIR modelling, logistic growth modelling, and ARIMA forecasting techniques were applied using SPSS and Python software. The results reveal significant correlations between disease prevalence and environmental factors, emphasizing the role of climate variables in disease dynamics. The SEIR model accurately simulated malaria transmission patterns, highlighting critical intervention points. Logistic growth modelling identified the impact of healthcare interventions on tuberculosis prevalence, while ARIMA forecasts provided actionable insights for cholera outbreak preparedness. Graphical visualizations, including time-series trends, correlation heatmaps, and model-based projections, underscore the value of these methods in understanding and mitigating infectious diseases. This study not only advances the application of statistical and mathematical models in public health but also provides evidence-based recommendations for targeted disease control strategies in Nigeria. The findings demonstrate the potential of integrating statistical and mathematical approaches in public health decision-making, paving the way for improved disease surveillance and management in resource-constrained settings Environmental variables, particularly rainfall and temperature, showed notable relationships with disease transmission patterns. The study highlights the importance of integrating statistical and mathematical models into disease surveillance and public health decision-making in Nigeria.
V. O. Tobi, T. J. Oluwafemi· Journal of Applied Sciences...· 0 citations
Lassa fever remains a major public health challenge in Nigeria, where recurrent outbreaks continue to impose substantial health and socioeconomic burdens. Although climatic variability has been implicated in disease transmission, the relative contributions of key environmental factors to outbreak occurrence remain insufficiently quantified. This study examined the influence of temperature, rainfall, humidity, and seasonality on Lassa fever epidemiology in Nigeria using national surveillance and meteorological data collected between 2020 and 2025. A total of 1,404 observations comprising confirmed cases and associated climatic variables were analysed using descriptive statistics, Pearson correlation analysis, and Negative Binomial Regression to account for overdispersion in disease counts. The findings revealed a pronounced seasonal pattern, with 77.1% of confirmed cases occurring during the dry season and peak transmission observed between January and March. Temperature was positively associated with disease incidence, whereas rainfall exhibited a significant inverse relationship. Negative Binomial Regression identified temperature (IRR = 1.024, p < .001), rainfall (IRR = 0.987, p < .001), humidity (IRR = 1.007, p = .001), and seasonality (IRR = 2.131, p < .001) as significant predictors of Lassa fever occurrence. After adjusting for climatic factors, disease incidence during the dry season was approximately 113% higher than during the wet season. These patterns suggest that climatic conditions influence transmission through their effects on environmental suitability, rodent ecology, and opportunities for human exposure. This study provides updated national-level evidence on the climatic determinants of Lassa fever transmission in Nigeria and demonstrates the dominant role of seasonality in shaping outbreak dynamics. By simultaneously quantifying the independent effects of multiple environmental drivers using a modelling framework appropriate for overdispersed disease count data, the study advances understanding of climate-sensitive Lassa fever epidemiology and provides an evidence base for climate-informed surveillance, early warning systems, and outbreak preparedness strategies.
A. Henry, K. Lasisi, Hamisu Idi et al.· American Journal of Bioscien...· 0 citations
Dengue is an arboviral disease of high public health relevance, characterized by pronounced temporal variability, nonlinearity, and recurrent outbreaks, which pose challenges to epidemiological surveillance and decision-making. This study evaluated the performance of machine learning methods for short-term forecasting of the weekly dengue morbidity rate in the 27 Brazilian capital cities, comprising the 26 state capitals and Brasília, Federal District, with horizons up to 4 weeks. Epidemiological, climatic, and socioeconomic data were compiled for these capital cities and used to compare a Gated Recurrent Unit (GRU) neural network, formulated as a Multi-Input Multi-Output (MIMO) model, and a Gradient Boosting model (CatBoost), implemented using a Direct forecasting strategy with horizon-specific models. Validation was conducted using a walk-forward approach, with evaluation based on absolute error metrics and the coefficient of determination. The results indicated that the GRU architecture presented recurring limitations, including underfitting, temporal lag, and low capacity to anticipate epidemic peaks. In contrast, the CatBoost model demonstrated greater robustness and better adaptation to the variability of epidemiological time series, showing superior performance in most of the analyzed capitals. The findings reinforce that greater architectural complexity does not necessarily imply better operational performance and highlight the potential of ensemble-based methods for short-term epidemiological surveillance applications. These findings contribute to dengue forecasting by showing that, under a common validation framework, ensemble-based strategies may provide greater operational robustness than recurrent MIMO architectures for short-term prediction in heterogeneous epidemiological settings.
D. C. da Cunha e Silva, L. M. Nery, Nícholas de Paula Nicomedes et al.· International journal of bio...· 0 citations
Vector borne disease like dengue continues to pose a significant climate-sensitive public health challenge in tropical regions such as Brazil, Peru, and India. This study examines the feasibility of predicting dengue outbreaks using weekly multivariate time-series data from San Juan (SJ), Puerto Rico and Iquitos (IQ), Peru. Dengue incidence was analyzed alongside meteorological, environmental, and vegetation-based variables to capture key climatic influences. Several machine learning and deep learning approaches were evaluated, including LightGBM. Model performance was assessed using root mean square error (RMSE) and mean absolute error (MAE). The results show that LightGBM achieved the low est RMSE/MAE, indicating strong short-term predictive accuracy and excellent interpretability. Feature importance analysis and principal component analysis (PCA) identified precipitation, dew point temperature, and humidity as the most influential predictors of dengue incidence. The study demonstrates that advanced machine learning models can serve as reliable early warning systems for vector-borne diseases. While this research focuses on dengue, the methodology is adaptable to other vector-bone datasets and diseases, offering a flexible tool for public health authorities to predict and mitigate outbreaks in diverse urban contexts.
Pratik S. Machchar, Purvi N. Ramanuj, Rajan Patel et al.· International Journal of Inf...· 0 citations
Malaria remains a significant public health concern and the leading cause of death in children under five in Benin. A comprehensive understanding of malaria’s transmission patterns is essential for guiding targeted and effective interventions, such as seasonal malaria chemoprevention (SMC) and the RTS,S/AS01 vaccine toward sustainable control and elimination efforts. This study explores the temporal, spatial, and demographic patterns of malaria transmission and examines the relationship between malaria incidence and both climate factors and interventions in Benin. A comprehensive descriptive analysis was conducted to explore the seasonality of malaria transmission and the correlation between malaria incidence and climate factors and interventions. Seasonal decomposition by locally estimated scatterplot smoothing (LOESS) was applied to monthly malaria surveillance data to isolate and assess seasonal patterns and long-term trends in malaria incidence across geographic regions and population subgroups. Spatial distribution was analysed using regional incidence data and time series analysis to identify geographic variation in disease burden. Demographic subgroup analysis compared malaria burden across age groups, sex, and among pregnant women. The relationship between malaria incidence and climate factors was assessed using a cross-correlation analysis. Interrupted time series analysis using a generalized additive model framework was used to assess the impact of SMC on malaria incidence across multiple health zones. The analysis revealed a consistent clear bimodal (two-peak) pattern each year in malaria incidence per province with notable provincial differences in burden and timing. The first peak occurs in July while the second peak occurs in October in most of the provinces. Median incidence during the first and second annual transmission peaks across provinces was 22.9 (IQR: 16.3–35.1) and 20.4 (IQR: 12.6–29.8) cases per 1,000 population, respectively. Children under five bear a disproportionate share of the malaria burden, with median monthly incidences of 30.1 versus 10.2 cases per 1,000 population in individuals older than five years, respectively. They also experienced a markedly higher maximum monthly incidence (154.5 vs 39.0 cases per 1,000 population). Mann–Whitney U test revealed no gender differences in malaria incidence among children under five across all provinces, but significantly higher incidence among females older than five years in several provinces. The impact of SMC on malaria incidence varied across health zones, with statistically significant reductions ranging from 28% to 58% in Tanguiéta-Cobly-Matéri, Kandi-Gogounou-Ségbana, Banikoara, and Malanville-Karimama. Cross-correlation analysis revealed that, in most provinces of Benin, increases in average monthly temperature were significantly associated with decreases in malaria incidence at a one-month lag, while rainfall showed a positive temporal association with malaria incidence at a 1–2 month lag, highlighting the influence of climate factors on malaria transmission dynamics. This study provides critical insights into the temporal, spatial, and demographic dynamics of malaria in Benin. The findings support the need for geographically and seasonally tailored malaria interventions and underscore the importance of considering environmental and demographic factors in malaria early warning and response systems. These results lay the groundwork for future modelling studies assessing the impact and cost-effectiveness of malaria control tools such as RTS,S and SMC at a sub-national level in Benin.
S. V. Alohoutade, R. Hounsell, Codjo Dandonougbo et al.· PLOS Global Public Health· 0 citations