Jainonthee Chalita, Sanwisate Phutsadee, Sivapirunthep Panneepa, Chaosap Chanporn, Pichpol Duangporn, Mektrirat Raktham, Chadsuthi Sudarat, Punyapornwithaya Veerasak
Veterinary Academic Office, Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai 50100, Thailand; Veterinary Public Health and Food Safety Centre for Asia Pacific (VPHCAP), Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai 50100, Thailand; Research Center for Veterinary Biosciences and Veterinary Public Health, Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai 50100, Thailand.
Department of Livestock Development, Bangkok 10400, Thailand.
Poult Sci. 2025 Jun 13;104(9):105439. doi: 10.1016/j.psj.2025.105439.
Dead-on-arrival (DOA) rates are a critical welfare and economic concern in poultry production, reflecting the cumulative impact of handling, transport, and lairage conditions on bird mortality. Compared to broilers and layers, meat-type ducks have received less attention in DOA research, despite their distinct physiological responses to preslaughter stressors and increasing relevance in commercial poultry production. Although machine learning models have been widely applied for DOA prediction, their limited transparency can hinder practical application in real-world settings. This study analyzed 8220 truckload entries of meat-type ducks recorded between 2022 and 2023, with the objective of developing an explainable deep learning model to predict high DOA outcomes using preslaughter management and environmental data. Deep learning models, owing to their complex architecture, offer superior predictive capacity and can capture nonlinear interactions in high-dimensional datasets. To enhance model interpretability and support practical application, SHapley Additive exPlanations (SHAP) was applied to identify the most influential predictors of DOA classification. The final model demonstrated strong classification performance, with an accuracy of 80.29 %, precision of 79.25 %, recall of 80.29 %, F1-score of 79.66 %, and an AUC-ROC of 76.03 %. Key predictors of high DOA included duck head count, lairage temperature, duck age, and transport duration. Notably, a higher number of ducks per truckload was strongly associated with elevated DOA risk (i.e., truckloads classified in the high DOA group), along with lairage temperatures and duck ages below the respective medians. Additionally, shorter transport durations were linked to increased mortality, highlighting the complex interplay of preslaughter stressors. By leveraging SHAP analysis, this study provided both global and local interpretability, ensuring that model outputs were not only accurate but also explainable. These findings support precision-driven preslaughter interventions, enabling industry stakeholders to optimize handling, transport, and lairage practices to reduce mortality rates and enhance duck welfare.
到达即死（DOA）率是家禽生产中一个关键的福利和经济问题，反映了处理、运输和待宰条件对禽类死亡率的累积影响。与肉鸡和蛋鸡相比，肉鸭在DOA研究中受到的关注较少，尽管它们对宰前应激源有独特的生理反应，且在商业家禽生产中的相关性日益增加。尽管机器学习模型已被广泛应用于DOA预测，但其透明度有限，可能会阻碍在实际环境中的实际应用。本研究分析了2022年至2023年记录的8220个肉鸭卡车装载记录，目的是开发一个可解释的深度学习模型，使用宰前管理和环境数据预测高DOA结果。深度学习模型由于其复杂的架构，具有卓越的预测能力，能够捕捉高维数据集中的非线性相互作用。为了提高模型的可解释性并支持实际应用，应用了SHapley加性解释（SHAP）来识别DOA分类中最具影响力的预测因素。最终模型表现出强大的分类性能，准确率为80.29%，精确率为79.25%，召回率为80.29%，F1分数为79.66%，AUC-ROC为76.03%。高DOA的关键预测因素包括鸭的数量、待宰温度、鸭龄和运输时长。值得注意的是，每辆卡车上鸭的数量较多与较高的DOA风险密切相关（即归类为高DOA组的卡车装载），同时待宰温度和鸭龄低于各自的中位数。此外，较短的运输时长与死亡率增加有关，突出了宰前应激源之间复杂的相互作用。通过利用SHAP分析，本研究提供了全局和局部的可解释性，确保模型输出不仅准确，而且可解释。这些发现支持精准驱动的宰前干预措施，使行业利益相关者能够优化处理、运输和待宰操作，以降低死亡率并提高鸭的福利。
