Averós Xavier, Lavín Jose Luís, Estevez Inma
Department of Animal Production, NEIKER-Basque Institute for Agricultural Research and Development, Basque Research and Technology Alliance (BRTA), N-104, km. 355, 01192, Arkaute, Spain.
Department of Applied Mathematics, NEIKER-Basque Institute for Agricultural Research and Development, Basque Research and Technology Alliance (BRTA), Bizkaia Science and Technology Park 812L, 48160, Derio, Spain.
Sci Rep. 2024 Oct 3;14(1):22943. doi: 10.1038/s41598-024-74260-4.
To simplify fast-growth broiler welfare assessments and use them as a benchmarking tool, decision trees were used to identify iceberg indicators discriminating flocks passing/failing welfare assessments as with the complete AWIN protocol. A dataset was constructed with data from 57 flocks and 3 previous projects. A final flock assessment score, previously not included in the dataset, was calculated and used as the benchmarking assessment classifier (pass/fail). A decision tree to classify flocks was built using the Chi-square Automatic Interaction Detection (CHAID) criterion. Cost-complexity pruning, and tenfold cross-validation were used. The final decision tree included cumulative mortality (%), immobile, lame birds (%), and birds with back wounds (%). Values were (mean ± se) 2.77 ± 0.14%, 0.16 ± 0.02%, 0.25 ± 0.02%, and 0.003 ± 0.001% for flocks passing the assessment; and 4.39 ± 0.49%, 0.24 ± 0.05%, 0.49 ± 0.09%, and 0.015 ± 0.006% for flocks failing. Cumulative mortality had the highest relative importance. The validated model correctly predicted 80.70% of benchmarking assessment outcomes. Model specificity was 0.8696; sensitivity was 0.5455. Decision trees can be useful to simplify welfare assessments. Model improvements will be possible as more information becomes available, and predictions are based on more samples.
为简化快速生长肉鸡福利评估并将其用作基准工具，采用决策树来识别如完整的AWIN协议那样区分通过/未通过福利评估鸡群的冰山指标。利用来自57个鸡群和3个先前项目的数据构建了一个数据集。计算并使用了一个先前未包含在数据集中的最终鸡群评估分数作为基准评估分类器（通过/未通过）。使用卡方自动交互检测（CHAID）标准构建了一个用于对鸡群进行分类的决策树。采用了成本复杂度剪枝和十折交叉验证。最终的决策树包括累积死亡率（%）、不动的跛脚鸡（%）和有背部伤口的鸡（%）。通过评估的鸡群的值为（均值±标准误）2.77±0.14%、0.16±0.02%、0.25±0.02%和0.003±0.001%；未通过的鸡群的值为4.39±0.49%、0.24±0.05%、0.49±0.09%和0.015±0.006%。累积死亡率具有最高的相对重要性。经过验证的模型正确预测了80.70%的基准评估结果。模型特异性为0.8696；敏感性为0.5455。决策树有助于简化福利评估。随着更多信息可用且预测基于更多样本，模型改进将成为可能。
