Leveraging Productivity Indicators for Anomaly Detection in Swine Breeding Herds with Unsupervised Learning

Mafalda Pedro Mil-Homens^1,2*Chong Wang^1,3Giovani Trevisan¹Fernanda Dórea^4,5Daniel C L Linhares¹Derald Holtkamp¹Gustavo S. Silva^1*

• ¹Department of Veterinary Diagnostic and Production Animal Medicine, College of Veterinary Medicine, Iowa State University, Ames, Iowa, United States
• ²Department of Animal Health and Anatomy, Faculty of Veterinary Medicine, Autonomous University of Barcelona, Barcelona, Catalonia, Spain
• ³Department of Statistics & Actuarial Science, College of Liberal Arts and Sciences, The University of Iowa, Iowa, Iowa, United States
• ⁴Swedish Veterinary Agency, Uppsala, Uppsala, Sweden
• ⁵Food and Agriculture Organization of the United Nations (Italy), Rome, Lazio, Italy

In swine disease surveillance, obtaining labeled data for supervised learning models can be challenging because many farms lack standardized diagnostic routines and consistent health monitoring systems. Unsupervised learning is particularly suitable in such scenarios because it does not require labeled data, allowing for detecting anomalies without predefined labels. This study evaluates the effectiveness of unsupervised machine learning models in detecting anomalies in productivity indicators in swine breeding herds. Anomalies, defined as deviations from expected patterns, were identified in indicators such as abortions per 1000 sows, prenatal losses, preweaning mortality, total born, liveborn, culled sows per 1000 sows, and dead sows per 1000 sows. Three unsupervised models—Isolation Forest, Autoencoder, and K-Nearest Neighbors (KNN)—were applied to data from two swine production systems. The herd-week was used as the unit of analysis, and anomaly scores above the 75th percentile were used to flag anomalous weeks. A permutation test assessed differences between anomalous and non-anomalous weeks. Performance was evaluated using F1-score, precision, and recall, with true anomalous weeks defined as those coinciding with reported health challenges, including porcine reproductive and respiratory syndrome (PRRS) and Seneca Valley virus outbreaks. A total of 8,044 weeks were analyzed. The models identified 336 anomalous weeks and 1,008 non-anomalous weeks in Production System 1, and 1,675 anomalous weeks and 5,025 non-anomalous weeks in Production System 2. The results from the permutation test revealed significant differences in productivity indicators between anomalous and non-anomalous weeks, especially during PRRS outbreaks, with more subtle changes observed during Seneca Valley virus outbreaks. The models performed well in detecting the PRRSV anomaly, achieving perfect precision (100%) across all models for both production systems. For anomalies like SVV the models showed lower performance compared to PRRSV. These findings suggest that unsupervised machine learning models are promising tools for early disease detection in swine herds, as they can identify anomalies in productivity data that may signal health challenges.