School of Veterinary Medicine and Science, Sutton Bonington Campus, University of Nottingham, Leicestershire, LE12 5RD, UK.
Sci Rep. 2024 Apr 28;14(1):9737. doi: 10.1038/s41598-024-58206-4.
Previous research shows that feeding and activity behaviours in combination with machine learning algorithms has the potential to predict the onset of bovine respiratory disease (BRD). This study used 229 novel and previously researched feeding, movement, and social behavioural features with machine learning classification algorithms to predict BRD events in pre-weaned calves. Data for 172 group housed calves were collected using automatic milk feeding machines and ultrawideband location sensors. Health assessments were carried out twice weekly using a modified Wisconsin scoring system and calves were classified as sick if they had a Wisconsin score of five or above and/or a rectal temperature of 39.5 °C or higher. A gradient boosting machine classification algorithm produced moderate to high performance: accuracy (0.773), precision (0.776), sensitivity (0.625), specificity (0.872), and F1-score (0.689). The most important 30 features were 40% feeding, 50% movement, and 10% social behavioural features. Movement behaviours, specifically the distance walked per day, were most important for model prediction, whereas feeding and social features aided in the model's prediction minimally. These results highlighting the predictive potential in this area but the need for further improvement before behavioural changes can be used to reliably predict the onset of BRD in pre-weaned calves.
先前的研究表明，饮食和活动行为结合机器学习算法，具有预测牛呼吸道疾病（BRD）发作的潜力。本研究使用了 229 个新的和以前研究过的饮食、运动和社交行为特征，以及机器学习分类算法，来预测未断奶小牛的 BRD 事件。使用自动挤奶机和超宽带定位传感器收集了 172 头群体饲养小牛的数据。每周进行两次健康评估，使用改良的威斯康星评分系统，如果小牛的威斯康星评分达到 5 分或以上，或直肠温度达到 39.5°C 或更高，则将其归类为患病。梯度提升机分类算法产生了中等至高的性能：准确性（0.773）、精度（0.776）、灵敏度（0.625）、特异性（0.872）和 F1 评分（0.689）。最重要的 30 个特征包括 40%的饮食、50%的运动和 10%的社交行为特征。运动行为，特别是每天行走的距离，对模型预测最为重要，而饮食和社交特征对模型的预测帮助最小。这些结果突出了这一领域的预测潜力，但需要进一步改进，才能利用行为变化可靠地预测未断奶小牛的 BRD 发作。
