Modeling gait score of broiler chicken via production and behavioral data

Authors: YANG, XIAO - University Of Tennessee; ZHAO, YANG - University Of Tennessee; GAN, HAO - University Of Tennessee; HAWKINS, SHAWN - University Of Tennessee; ECKELKAMP, LIZ - University Of Tennessee; PARADO, MARIA - University Of Tennessee; BURNS, ROBERT - University Of Tennessee; Purswell, Joseph - Jody; TABLER, TOM - Mississippi State University

Submitted to: Animal
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/7/2022
Publication Date: 1/25/2023
Citation: Yang, X., Zhao, Y., Gan, H., Hawkins, S., Eckelkamp, L., Parado, M., Burns, R., Purswell, J.L., Tabler, T. 2023. Modeling gait score of broiler chicken via production and behavioral data. Animal. 1(2023): 100692. https://doi.org/10.1016/j.animal.2022.100692.
DOI: https://doi.org/10.1016/j.animal.2022.100692

Interpretive Summary: Lameness in broilers may be associated with pain and is considered a major broiler production and welfare concern. Manual gait score assessment in commercial broiler houses is discrete, time consuming, and laborious. As such, automatic methods for broiler gait score assessment are urgently needed. The objective of this study was to identify the relation of broiler gait score with several production and behavioral metrics (bird body weight, age, activity, and distribution), and establish prediction models for automatic gait score estimations in broiler production. Sixteen pens were used to rear two different broiler strains. Body weight and Gait score of was assessed weekly by trained assessors. Top-view cameras were installed to continuously record videos of broilers in all 16 pens. The results showed positive correlation between gait score and body weight, and negative correlation between gait score and activity. The three models showed high accuracy in predicting broiler gait score based on variables of body weight, age, activity index and distribution index. The findings of this study demonstrated the potential of estimating broiler gait score using bird body weight, age, activity index, and distribution index. This information will assist the development of automated gait score assessment systems in broiler production.

Technical Abstract: Lameness in broilers may be associated with pain and is considered a major broiler production and welfare concern. Manual gait score assessment in commercial broiler houses is discrete, time consuming, and laborious. As such, automatic methods for broiler gait score assessment are urgently needed. The objective of this study was to identify the relation of broiler gait score with several production and behavioral metrics (bird body weight, age, activity, and distribution), and establish prediction models for automatic gait score estimations in broiler production. Sixteen pens were used to rear Cobb 500 and Ross 708 broilers for eight and nine weeks, respectively (8 pens/strain, 12 birds/pen). Gait score of all birds was assessed weekly by trained assessors following a six-point (0-5) scoring protocol from the third week. Overall body weight of birds in each pen was measured weekly. Top-view cameras were installed to continuously record videos of broilers in all 16 pens. Images were extracted from video clips (10 min/hour) during 16-hour light period to determine activity index and distribution index through image processing. The results showed positive correlation between gait score and body weight (R2 = 0.97 for Cobb and R2 = 0.96 for Ross), and negative correlation between gait score and activity (R2 = 0.78 for Cobb and R2 = 0.73 for Ross). The three models showed high accuracy in predicting broiler gait score based on variables of body weight, age, activity index and distribution index (R2 = 0.90-0.91, RMSE = 0.38-0.41). The findings of this study demonstrated the potential of estimating broiler gait score using bird body weight, age, activity index, and distribution index. This information will assist the development of automated gait score assessment systems in broiler production.