Spatiotemporal Dynamics and Forecasting of Severe Malaria Incidence Among Pregnant Women in the Democratic Republic of Congo (2020-2024): A Retrospective Observational Study

Background Malaria remains a major public health concern in the Democratic Republic of Congo (DRC). This retrospective observational study examined the spatiotemporal variation in severe malaria incidence among pregnant women across DRC provinces from 2020 to 2024 and projected future trends to 2026. Methods Monthly data on severe malaria cases were obtained from the District Health Information Software 2 (DHIS2) managed by the DRC Ministry of Health. Data from 26 provinces were cleaned, harmonized, and analyzed using descriptive statistics, temporal trend visualizations, and spatial autocorrelation methods. Five forecasting models Seasonal Autoregressive Integrated Moving Average (SARIMA), Exponential Smoothing State Space (ETS), Trigonometric Box-Cox ARMA Trend Seasonal (TBATS), Autoregressive Neural Network (ARNN_NNAR), and Autoregressive Fractionally Integrated Moving Average (ARFIMA) were applied to predict future incidence. Model accuracy was assessed using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Symmetric Mean Absolute Percentage Error (sMAPE), and Mean Absolute Scaled Error (MASE), with sMAPE used to identify the best-performing model for each province. Results Considerable spatial and temporal heterogeneity was observed. Kinshasa, Haut-Katanga, and Kasaï-Central reported persistently high incidence, while Nord-Ubangi and Mongala showed the lowest. Seasonal peaks occurred mainly between May and December. The ETS, ARNN_NNAR, and ARFIMA models demonstrated superior accuracy across different provinces, reflecting varied epidemic patterns. Forecasts for 2026 indicated persistent high-incidence clusters in western and central provinces, particularly Kongo-Central and Kwango. Conclusion The study underscores significant spatial disparities and rising trends in severe malaria among pregnant women in the DRC. The findings provide critical evidence to guide geographically targeted, seasonally timed interventions and inform policy to strengthen malaria prevention and control.