Predicting malaria epidemics in Burkina Faso with machine learning

Abstract

Accurately forecasting the case rate of malaria would enable key decision makers to intervene months before the onset of any outbreak, potentially saving lives. Until now, methods that forecast malaria have involved complicated numerical simulations that model transmission through a community. Here we present the first data-driven malaria epidemic early warning system that can predict the 13-week case rate in a primary health facility in Burkina Faso. Using the extraordinarily high-fidelity data of infant consultations taken from the Integrated e-Diagnostic Approach (IeDA) system that has been rolled out throughout Burkina Faso, we train a combination of Gaussian Processes and Random Forest Regressors to estimate the weekly number of malaria cases over a 13 week period. We test our algorithm on historical epidemics and find that for our lowest threshold for an epidemic alert, our algorithm has 30% precision with > 99% recall at raising an alert. This rises to > 99% precision and 5% recall for the high alert threshold. Our two-tailed predictions have an average 1σ and 2σ precision of 5 cases and 30 cases respectively.

Climatic, land-use and socio-economic factors can predict malaria dynamics at fine spatial scales relevant to local health actors: Evidence from rural Madagascar

“…Longer time series would also allow for more explicit time series analysis. Finally, predictive power could also be increased in future work by increasing the number of predictors or by using specialized models that optimize predictive power at the expense of explanatory power, such as Support Vector Regression, Random Forest regression and other machine learning and deep learning models [50][51][52].…”

Prediction of the Risk Distributions for Anopheles sinensis, a Vector for Malaria in Shanghai, China

“…Harvey et al developed the first malaria epidemic early warning system and using classifications that meet the conditions. 69 They further tested this system and discovered that for the high alert threshold, precision increased to . 99% and recall to 5%.…”

“…developed the first malaria epidemic early warning system and using classifications that meet the conditions. 69 They further tested this system and discovered that for the high alert threshold, precision increased to > 99% and recall to 5%. In fact, several species, including the Oncomelania hupensis , Aedes albopictus , and Culicoides , have successfully used the output predictions from similar models for risk classification, which could contribute to the development of effective strategies to prevent further spread.…”

Machine Intelligence in Africa: a survey

“…Through numerous conferences and demonstrations, SENIA is not only a platform for exchange but also a business and networking environment for industry professionals. [418] focuses on predicting malaria epidemics in Burkina Faso using machine learning. The work in [419] maps patterns of urban development in Ouagadougou, Burkina Faso, utilizing machine learning regression modeling with bi-seasonal Landsat time series.…”