Using farm management practices to predict Campylobacter prevalence in pastured poultry farms

• Main Authors: Xinran Xu, Michael J. Rothrock, Jr., Anand Mohan, Govindaraj Dev Kumar, Abhinav Mishra
• Format: Article
• Language: English
• Published: Elsevier 2021-06-01
• Series: Poultry Science
• Subjects: predictive microbiology; alternative poultry production; food safety; random forest; machine learning
• Online Access: http://www.sciencedirect.com/science/article/pii/S0032579121001565

ABSTRACT: Contamination of poultry products by Campylobacter is often associated with farm management practices and processing plant practices. A longitudinal study was conducted on 11 pastured poultry farms in southeastern United States from 2014 to 2017. In this study, farm practices and processing variables were used as predictors for a random forest (RF) model to predict Campylobacter prevalence in pastured poultry farms and processing environments. Individual RF models were constructed for fecal, soil and whole carcass rinse after processing (WCR-P) samples. The performance of models was evaluated by the area under curve (AUC) from the receiver operating characteristics curve. The AUC values were 0.902, 0.894, and 0.864 for fecal, soil, and WCR-P models, respectively. Relative importance plots were generated to predict the most important variable in each RF model. Animal source of feces was identified as the most important variable in fecal model and the soy content of the brood feed was the most important variable for soil model. For WCR-P model, the average flock age showed the strongest impact on RF model. These RF models can help pastured poultry growers with food safety control strategies to reduce Campylobacter prevalence in pastured poultry farms.