Spatio-temporal modelling and prediction of malaria incidence in Mozambique using climatic indicators from 2001 to 2018

Abstract

Accurate malaria predictions are essential for implementing timely interventions, particularly in Mozambique, where climate factors strongly influence transmission. This study aims to develop and evaluate a spatial-temporal prediction model for malaria incidence in Mozambique for potential use in a malaria early warning system (MEWS). We used monthly data on malaria cases from 2001 to 2018 in Mozambique, the model incorporated lagged climate variables selected through Deviance Information Criterion (DIC), including mean temperature and precipitation (1-2 months), relative humidity (5-6 months), and Normalized Different Vegetation Index (NDVI) (3-4 months). Predictive distributions from monthly cross-validations were employed to calculate threshold exceedance probabilities, with district-specific thresholds set at the 75th percentile of historical monthly malaria incidence. The model's ability to predict high and low malaria seasons was evaluated using receiver operating characteristic (ROC) analysis. Results indicated that malaria incidence in Mozambique peaks from November to April, offering a predictive lead time of up to 4 months. The model demonstrated high predictive power with an area under the curve (AUC) of 0.897 (0.893-0.901), sensitivity of 0.835 (0.827-0.843), and specificity of 0.793 (0.787-0.798), underscoring its suitability for integration into a MEWS. Thus, incorporating climate information within a multisectoral approach is essential for enhancing malaria prevention interventions effectiveness.

Keywords: Climate; Early warning; Malaria; Mozambique; Prediction.

Fig. 1

Annual cycle of (A) malaria incidence rates (per 100,000 population) in Mozambique, (B) Precipitation, (C) Mean temperature, (D) maximum temperature, (E) relative humidity and (F) Normalized different vegetation index (NDVI) at the monthly time scale from January 2000 to December 2018.

Fig. 2

Spatial distribution of observed and predicted malaria cases for 2017 and 2018 in Mozambique. We used ggplot2 in R to create a spatial map visualizing the observed and predicted values for 2017 and 2018. The data is mapped using geom_sf() function, where regions are filled with colors based on the observed and predicted values, scaled using a log-transformed PiYG gradient for better contrast. A black border outlines the regions, while unnecessary plot elements are removed for a clean and focused visualization. The legend, positioned inside the map, enhances clarity by displaying the observed values (in thousands). This map was created using R software (version 4.2.0), which is freely available and can be downloaded from the following link: https://sourceforge.net/projects/rportable/files/R-Portable/4.2.0/.

Fig. 3

Predicted and observed malaria cases in Mozambique for the period of 2001–2018. The shaded area shows the 95% credible intervals of the predicted cases.

Fig. 4

Contribution to the model for each selected climate factors (A) normalized different vegetation index at lag3_4, (B) precipitation at lag1_2, (C) relative humidity at lag5_6 and (D) mean temperature at lag1_2. The shaded areas (light blue) correspond to the 95% confidence intervals.