TUCKER GA. – US Poultry & Egg Association (USPOULTRY) and the USPOULTRY Foundation announced researchers at the University of Arkansas completed a funded project using accelerometers and artificial intelligence (AI) to predict the presence of woody breast in broilers. The research is part of USPOULTRY’s Comprehensive Research Program encompassing all phases of poultry and egg production and processing. George’s Inc. partially funded the project through an endowment gift.

Casey Owens, PhD and Novus International Professor of Poultry Science, University of Arkansas, and colleagues completed Project #721: The Use of Accelerometers and Artificial Intelligence to Predict Presence of Woody Breast in Live Broilers Throughout Growout and in Broiler Fillets, to evaluate the use of accelerometers on live broilers to identify birds exhibiting woody breast characteristics and to assess vibration patterns of deboned fillets with varying degrees of woody breast severity.

Multiple trials were conducted on raw breast fillets to refine the methodology and improve detection. The accuracy of detection methods utilized varied between 60% and 85%. Detection accuracy in live bird accelerometer studies was generally lower than with fillets. Researchers found accelerometer patterns (i.e., vibration) did show some differences between normal, moderate and severe woody breast, but those patterns were not always consistent. Because the accelerometer is meant to detect small changes in vibrations, general activity of the birds appeared to mask the ability to detect the patterns.

The unfeasibility to detect woody breast in live birds and the low accuracy suggest that this detection method is not effective, and potential for this technology will require more research and refinement.