Abstract

The spread of pathogens in swine populations is partially determined by animal movements between farms. However, understanding additional characteristics that predict disease outbreaks and uncovering landscape factors related to between-farm spread are crucial steps toward risk mitigation. This study integrates animal movements with environmental risk factors to identify the occurrence of porcine epidemic diarrhea virus (PEDV) outbreaks. Using weekly farm-level incidence data from 332 sow farms, researchers applied machine-learning algorithms to quantify associations between risk factors and PEDV outbreaks with the ultimate goal of training predictive models and identifying the most important factors associated with PEDV occurrence. The best algorithm developed was able to correctly predict whether an outbreak occurred during one-week periods with greater than 80% accuracy. The most important predictors included pig movements into neighboring farms. Other significant neighborhood attributes encompassed hog density, environmental and weather factors such as vegetation, wind speed, temperature, and precipitation, and topographical features like slope. This neighborhood-based approach allowed the researchers to simultaneously capture disease risks associated with long-distance animal movement as well as local spatial dynamics. The model presented in the study forms the foundation for near real-time disease mapping and is expected to advance disease surveillance and control for endemic swine pathogens in the United States.