This week, Dr. Kim VanderWaal and her team share an update on a highly anticipated project regarding the forecast of PEDv in the United States.Continue reading “Forecasting PEDv in the US through the use of machine learning”
Our ninth presentation is from Dr. Kim VanderWaal, our colleague at the University of Minnesota, who gives us a glimpse into a future when producers might be able to know when their farms are at risk of disease outbreaks.Continue reading “Best of Leman 2018 series #9: K. VanderWaal – Can we predict PRRS and PED outbreaks?”
This week, we are sharing a report from recent PhD graduate Kaushi Kanankege about predicting the monthly risk of PRRS.
- High risk of PRRS occurrence was observed in counties where >25% of MSHMP farms were fully or partially air-filtered, have high number of hog farms, and have farms belonged to multiple production systems.
- PRRS occurrence association with air filters may be due to attempts to mitigate risk in prevalent areas.
- Further research is required to understand the space-time association of the windborne local spread of the virus and the installation of air filters.
This is our Friday rubric: every week a new Science Page from the Bob Morrison’s Swine Health Monitoring Project. The previous editions of the science page are available on our website.
This week we are sharing a report by Dr. Linhares’ lab at Iowa State University. In this Science Page are the results of a study looking at biosecurity aspects associated with PRRS frequency.
- New methods allow estimation of the overall PRRS-vulnerability risk score by asking 20 or less questions.
- This can help producers and veterinarians to (a) measure and benchmark key biosecurity aspects, and (b) toidentify sites at relatively higher (or lower) risk of PRRSv introduction.
Study Summary: This study aimed to identify a small set of biosecurity aspects that, when combined, have a strong association with the frequency of PRRSv introduction into swine breeding herds.
Preliminary Results: A cross-sectional study assessed biosecurity aspects in 84 breeding herds from 14 production systems in 2017. Models were trained to predict whether a farm had or not reported a PRRS outbreak in the past 5 years, given a set of biosecurity aspects. Two methods were used, and both models were able to classify the herds with a great overall performance based on few biosecurity aspects (See figure). The variables used by both methods were related to the frequency of risk events in the farm, swine density around the farm, farm characteristics/ requirements to visitors, and operational connections to other sites.
Note: The Gini coefficient (or index) is a single number aimed at measuring the degree of inequality in a distribution. (Source: Wikipedia) The higher the number, the less equally distributed the farms will be.
When comparing the predicted positive value obtained by the models, they showed a strong positive correlation (0.7 and 0.76, respectively) with the frequency of past outbreaks.
Enroll on our follow-up study: Study farms will be asked to fill a short survey. Using the methods above, the PRRS-vulnerability risk score will be generated for each farm enrolled. The information will be collected via an Excel file and the name of the farms and production systems will be kept confidential.
To enroll or request additional information please contact: Gustavo Silva (gustavos-at-iastate.edu) or Daniel Linhares (linhares-at-iastate.edu) at Iowa State University.