Machine Learning Framework for Porcine Reproductive and Respiratory Syndrome Outbreak Forecasting

Abstract Porcine Reproductive and Respiratory Syndrome (PRRS) is one of the most challenging and costly viral infectious diseases impacting the swine industry. The disease transmission pathways for PRRS are very complex, requiring a combined approach of intensive surveillance (i.e., testing), biosecurity, and vaccination for control and eradication. This study builds a proactive framework to forecast the risk of having a PRRS outbreak on a farm. This forecasting allows for early detection of disease outbreaks and could direct risk-based, and thus more cost-effective, interventions. Machine learning algorithms were trained using multi-scale data (pig group-, farm-, and area-level data). For the first time, on-farm, between-farm, and environmental variables, including farm location, pig movements, production parameters, diagnostic data, and climatic information, were combined for the prediction of PRRS outbreaks. Multi-scale datasets were merged via feature extraction, followed by the wrapper and filter feature selection, to find those feature subsets with the best forecasting performance. The predictive value of each feature selection mechanism was evaluated in terms of its stability. Numerical results demonstrate good forecasting performance in terms of area under the ROC curve.