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

Abstract

Since the early 1990s, porcine reproductive and respiratory syndrome (PRRS) virus outbreaks have been reported across various parts of North America, Europe, and Asia. The incursion of PRRS virus (PRRSV) in swine herds could result in various clinical manifestations, resulting in a substantial impact on the incidence of respiratory morbidity, reproductive loss, and mortality. Veterinary experts, among others, regularly analyze the PRRSV open reading frame-5 (ORF-5) for prognostic purposes to assess the risk of severe clinical outcomes. In this study, we explored if predictive modeling techniques could be used to identify the severity of typical clinical signs observed during PRRS outbreaks in sow herds. Our study aimed to evaluate four baseline machine learning (ML) algorithms: logistic regression (LR) with ridge and lasso regularization techniques, random forest (RF), k-nearest neighbor (KNN), and support vector machine (SVM), for the clinical impact classification of ORF-5 sequences and demographic data into high impact and low impact categories. First, baseline classifiers were evaluated using different input representations of ORF-5 nucleotides, amino acid sequences, and demographic data using a 10-fold cross-validation technique. Then, we designed a consensus voting ensemble approach to aggregate the different types of input representations for genetic and demographic data for classifying clinical impact. In this study, we observed that: (a) for abortion and pre-weaning mortality (PWM), different classifiers gained improvement over baseline accuracy, which showed the plausible presence of both genotypic-phenotypic and demographic-phenotypic relationships, (b) for sow mortality (SM), no baseline classifier successfully established such linkages using either genetic or demographic input data, (c) baseline classifiers showed good performance with a moderate variance of the performance metrics, due to high-class overlap and the small dataset size used for training, and (d) the use of consensus voting ensemble techniques helped to make the predictions more robust and stabilized the performance evaluation metrics, but overall accuracy did not substantially improve the diagnostic metrics over baseline classifiers.