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.
Highlights
According the the World Health Organisation (WHO), in 2019 there were 229 million cases of malaria resulting in roughly 400 thousand deaths with 94% of these occurring in Africa
We have presented a combined Gaussian Process and Random Forest Regressor that can predict the case rate of malaria to within 5 and 30 cases at the 1σ and 2σ confidence level
Using a combination of historical data from the Integrated e-Diagnostic Approach (IeDA) database of consultations of infants less than five years old in Burkina Faso and external rain data, we construct a library of Gaussian Processes that we use to fit to observed data to make a 13 week prediction
Summary
According the the World Health Organisation (WHO), in 2019 there were 229 million cases of malaria resulting in roughly 400 thousand deaths with 94% of these occurring in Africa. Of those that die, children under five are the most vulnerable, accounting for 67% of all deaths [1]. In 2015 the WHO released a global plan that aimed to reduce cases and mortality by 90% and eliminate it from 35 countries by 2030 This ambitious goal is to be tackled by a host of different researchers and organisations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
