Translating Big Data into Smart Data for Veterinary Epidemiology

VanderWaal, Kimberly; Morrison, Robert B.; Neuhauser, Claudia; Vilalta, Carles; Perez, Andres M.

Finally, data relevant to disease dynamics are representative of processes that operate at different spatial and temporal scales. Epidemiological modeling provides a means to connect processes across multiple scales and account for the inherent dynamic elements of disease systems. For stochastic disease models, thousands or even hundreds of thousands of simulations are performed to understand the behavior of the system and optimize parameter values, thus requiring extensive computational resources and generating big data. Machine learning techniques, such as random forests and genetic algorithms, are used to optimize parameter values so that the model simulates epidemiological dynamics that closely resemble real-world data. Computational modeling provides an effective means to link data to processes, and understand mechanistically how disparate data may interact to influence the occurrence of disease.