Raul Cruz-Cano, Ph.D., Department of Epidemiology & Biostatistics, Indiana University Bloomington

"A neural network based early warning system to enhance community resilience against diarrheal disease."

Ongoing climate change is having a considerable impact on the burden of climate sensitive bacterial infectious diseases across the globe. Warming temperature promotes bacterial growth while extreme precipitation enhances the spread of these pathogens, particularly in resource limited settings. Given extreme heat and precipitation events are projected to continue increasing in frequency and intensity, there is an urgent need to develop publicly available early warning systems to guide public health decision-making activities. Using historical diarrheal disease data from Taiwan, Nepal, and Vietnam, we show that shallow time-series neural network models can be successfully applied with environmental data to infer diarrheal disease risk with sub-seasonal and seasonal lead time. As expected, the performance of the networks varies based on the availability of the disease surveillance and meteorological data. Even when relying on weather forecasted months in advance, the early warning system for diarrheal disease is well suited to provide categorical probability (Low, Medium, High) of disease burden ahead of time and it is possible to present these predictions in a manner that can help guide public health decision-making at a seasonal level.

Stay connected TwitterFacebook LinkedIn YouTubeInstagram