Betancor-Sánchez Manuel, González-Cabrera Marta, Morales-delaNuez Antonio, Hernández-Castellano Lorenzo E, Argüello Anastasio, Castro Noemí
IUSA-ONEHEALTH 4, Animal Production and Biotechnology, Institute of Animal Health and Food Safety, Universidad de Las Palmas de Gran Canaria, Campus Montaña Cardones, 35413 Arucas, Spain.
Animals (Basel). 2024 Dec 26;15(1):31. doi: 10.3390/ani15010031.
Circulating immunoglobulin G (IgG) concentrations in newborn goat kids are not sufficient to protect the animal against external agents. Therefore, consumption of colostrum, rich in immune components, shortly after birth is crucial. Traditional laboratory methods used to measure IgG concentrations, such as ELISA or RID, are reliable but costly and impractical for many farmers. This study proposes a more accessible alternative for farmers to predict IgG concentration in goat colostrum by integrating color-based techniques with machine learning models, specifically decision trees and neural networks, through the development of two regression models based on colostrum color data from Majorera dairy goats. A total of 813 colostrum samples were collected in a previous study (June 1997-April 2003) that utilized multiple regression analysis as a reference to verify that applying data science techniques improves accuracy and reliability. The decision tree model outperformed the neural network, achieving higher accuracy and lower error rates. Both models provided predictions that closely matched IgG concentrations obtained by ELISA. Therefore, this methodology offers a practical and affordable solution for the on-farm assessment of colostrum quality (i.e., IgG concentration). This approach could significantly improve farm management practices, ensuring better health outcomes in newborn animals by facilitating timely and accurate colostrum quality evaluation.
新生山羊幼崽体内循环免疫球蛋白G（IgG）的浓度不足以保护动物抵御外界病原体。因此，出生后不久食用富含免疫成分的初乳至关重要。用于测量IgG浓度的传统实验室方法，如酶联免疫吸附测定（ELISA）或放射免疫扩散法（RID），虽然可靠，但对许多养殖户来说成本高昂且不实用。本研究提出了一种更易于采用的方法，通过基于马约雷拉奶山羊初乳颜色数据开发两个回归模型，将基于颜色的技术与机器学习模型（具体为决策树和神经网络）相结合，帮助养殖户预测山羊初乳中的IgG浓度。在之前一项研究（1997年6月至2003年4月）中总共收集了813份初乳样本，该研究采用多元回归分析作为参考，以验证应用数据科学技术可提高准确性和可靠性。决策树模型的表现优于神经网络，具有更高的准确率和更低的错误率。两个模型的预测结果都与ELISA法测得的IgG浓度非常匹配。因此，这种方法为农场初乳质量（即IgG浓度）评估提供了一种实用且经济的解决方案。这种方法可以显著改善农场管理实践，通过促进及时、准确的初乳质量评估，确保新生动物获得更好的健康状况。
