Submitted to: Translational Animal Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/12/2024
Publication Date: N/A
Citation: N/A

Interpretive Summary: Currently, swine producers rely solely on the skill level of animal caretakers to determine when pigs need management intervention. However, changes in the industry toward fewer and larger farms, coupled with a dwindling labor force, have made it difficult to recruit knowledgeable animal caretakers. Furthermore, like many sectors within the animal industry, the swine industry contends with a high turnover rate in its labor force, which can result in inconsistent animal care. Precision livestock farming technologies, such as wearable sensors and cameras, are revolutionizing animal welfare assessment by providing continuous animal monitoring. These technologies allow investigation of deviations from normality at the individual level, rather than trying to understand “average” animals. Automated feeding systems have been developed to monitor feeding behavior of pigs. Disruptions in feeding behavior can be indicative of the onset of illness and/or other impairments of animal well-being. ARS researchers have developed a mathematical model for predicting daily time at the feeder for individual pigs in the grow-finish stage of production. The predictive model was used to detect anomalous decreases in feeding behavior associated with the health status of the pig. Health issues were identified by the model, on average, 2.8 days earlier than diagnosis by the animal caretaker. Results from this work will serve as the basis for a decision support tool that can be implemented in the swine production continuum.

Technical Abstract: Early identification of animals in need of management intervention is critical to maximize animal health and welfare and minimize issues with productivity. Feeding behavior, captured by automated feeding systems, can be used to monitor the health and welfare status of individual pigs. Here, we present a framework for monitoring feeding behavior of grow-finish pigs in real-time, using a low-frequency radio frequency identification (RFID) system. Using historical data, an autoregressive linear model for predicting daily time at the feeder was developed and utilized to detect anomalous decreases in feeding behavior associated with health status of the pig. A total of 2,826 pigs were individually monitored with our warning system over the entire grow-finish period, and health warnings were compared to caretaker diagnoses. The system detected 55.7% of the caretaker diagnoses, and on average these events were detected 2.8 days earlier than diagnosis by the caretaker. High numbers of potentially spurious health warnings, generated by the system, can be partly explained by the lack of a reliable and repeatable gold standard reference data set. Results from this work provide a solid basis for monitoring individual animals, but further improvements to the system are necessary for practical implementation.