Classification of porcine reproductive and respiratory syndrome clinical impact in Ontario sow herds using machine learning approaches

Chadha, A., Dara, R., Pearl, D.L., Gillis, D., Rosendal, T., & Poljak, Z. (2023). Classification of porcine reproductive and respiratory syndrome clinical impact in Ontario sow herds using machine learning approaches. Frontiers in Veterinary Science, 10. https://doi.org/10.3389/fvets.2023.1175569

This study evaluated machine learning models to classify the clinical impact of porcine reproductive and respiratory syndrome (PRRS) outbreaks in Ontario sow herds. Four baseline models—logistic regression, random forest, k-nearest neighbor, and support vector machine—were used to assess the relationship between ORF-5 genetic sequences, demographic data, and clinical outcomes. Results showed that abortion and pre-weaning mortality classifiers improved over baseline accuracy, while sow mortality classifiers failed to establish significant linkages. The use of consensus voting ensembles increased prediction robustness but did not significantly enhance diagnostic accuracy.