Identifying outbreaks of Porcine Epidemic Diarrhea virus through animal movements and spatial neighborhoods

Abstract

The spread of pathogens in swine populations is in part determined by movements of animals 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, we applied machine-learning algorithms to quantify associations between risk factors and PEDV outbreaks with the ultimate goal of training predictive models and to identify the most important factors associated with PEDV occurrence. Our best algorithm was able to correctly predict whether an outbreak occurred during one-week periods with >80% accuracy. The most important predictors included pig movements into neighboring farms. Other important neighborhood attributes included hog density, environmental and weather factors such as vegetation, wind speed, temperature, and precipitation, and topographical features such as slope. Our neighborhood-based approach allowed us to simultaneously capture disease risks associated with long-distance animal movement as well as local spatial dynamics. The model presented here forms the foundation for near real-time disease mapping and will advance disease surveillance and control for endemic swine pathogens in the United States.

Prediction for global African swine fever outbreaks based on a combination of random forest algorithms and meteorological data

“…The uncontrolled ASF epidemic in Eastern Europe poses a serious threat to the pig industry throughout Europe, Central Asia and even China. Some studies have shown that using machine learning algorithms can help to better understand the factors associated with disease transmission and establish appropriate predictive models (Ding, Fu, Jiang, Hao, & Lin, ; Jiang et al, ; Machado et al, ; Safarishahrbijari & Osgood, ). A better understanding of the disease‐associated factors is a crucial step towards the definition of strategies for control and eradication.…”

“…China. Some studies have shown that using machine learning algorithms can help to better understand the factors associated with disease transmission and establish appropriate predictive models (Ding, Fu, Jiang, Hao, & Lin, 2018;Jiang et al, 2018;Machado et al, 2019;Safarishahrbijari & Osgood, 2019 with BF search method was used to search for the optimal feature subset. By comparing the calculation times of the model before and after feature selection, it can be found that the model calculation speed can be accelerated after using feature selection.…”

Environmental persistence of foot‐and‐mouth disease virus applied to endemic regions

“…Specifically, these researchers evaluated transmission, beyond animal movement, that included wind speed, fomites, weather and topographical features. They found that disease risk could be predicted at the farm receiving animals and that disease risk, in a neighbourhood of farms, could be affected by long‐distance animal movement as well as the landscape and weather features, within a neighbourhood (Machado et al, ). This PEDV model demonstrates how models can be used to both better understand transmission dynamics and inform professionals seeking to prevent and control the spread of infectious disease.…”

Neural Network Based Country Wise Risk Prediction of COVID-19

“…Hamer et al [7] use ML algorithms to predict spatio-temporal epidemic spareness of pathological diseases. AI tools for predicting outbreak in cardiovascular diseases [8,9], Influenza [10], and epidemic Diarrhea [11] is also proposed. A nice review of the AI application on such a prediction is reported in [12].…”