An Initial Study on the Use of Machine Learning and Radio Frequency Identification Data for Predicting Health Outcomes in Free-Range Laying Hens

SIMPLE SUMMARY: Maintaining the health and welfare of laying hens is essential to ensure optimal productivity and to build consumer confidence. Free-range egg production systems present unique challenges, including increased exposure to parasites, infection, and injury. The ability to predict and prevent these health problems translates into significant financial savings. This study examines the use of Radio Frequency Identification (RFID) to measure the movement behavior of laying hens and machine learning to forecast individual hens’ health status. The machine learning workflow incorporates data resampling and important feature identification to overcome the highly unbalanced dataset. Results indicate an average of 28% Spotty Liver Disease, 33% round worm, and 33% tape worm infection correctly predicted by the end of the production period. The monitoring of hens’ health during the early laying period can lead to similar performances in predicting infections compared to models trained with peak laying data. Future research can improve the initial predictions by incorporating additional data streams to provide a more comprehensive view of flock health. ABSTRACT: Maintaining the health and welfare of laying hens is key to achieving peak productivity and has become significant for assuring consumer confidence in the industry. Free-range egg production systems represent diverse environments, with a range of challenges that undermine flock performance not experienced in more conventional production systems. These challenges can include increased exposure to parasites and bacterial or viral infection, along with injuries and plumage damage resulting from increased freedom of movement and interaction with flock-mates. The ability to forecast the incidence of these health challenges across the production lifecycle for individual laying hens could result in an opportunity to make significant economic savings. By delivering the opportunity to reduce mortality rates and increase egg laying rates, the implementation of flock monitoring systems can be a viable solution. This study investigates the use of Radio Frequency Identification technologies (RFID) and machine learning to identify production system usage patterns and to forecast the health status for individual hens. Analysis of the underpinning data is presented that focuses on identifying correlations and structure that are significant for explaining the performance of predictive models that are trained on these challenging, highly unbalanced, datasets. A machine learning workflow was developed that incorporates data resampling to overcome the dataset imbalance and the identification/refinement of important data features. The results demonstrate promising performance, with an average 28% of Spotty Liver Disease, 33% round worm, and 33% of tape worm infections correctly predicted at the end of production. The analysis showed that monitoring hens during the early stages of egg production shows similar performance to models trained with data obtained at later periods of egg production. Future work could improve on these initial predictions by incorporating additional data streams to create a more complete view of flock health.