Abstract：
Current research aims to generate an alternative model to classical methods in the determination of subclinical mastitis at 4 levels (healthy, suspicious, subclinical, and clinical). For this purpose, multilayer perceptron (MLP) artificial neural networks (ANN) was developed as test model. 5 variables from the physical properties of milk somatic cell count (SCC), electrical conductivity (EC), pH, density, and temperature at fore milking (TFM) were included in the model in the classification of mastitis. Model performance was validated on test data (%25) and compared with the multinomial logistic regression (MNLR). MLP model has shown a satisfactory performance with an accuracy of 95.14% and - 141 of AIC score better than the control model (MNLR) of 80.27% and - 133 AIC despite using higher number of parameters (104). Since the main problem is to diagnose subclinical mastitis, which does not cause any visible symptoms, it was important to distinguish between absolute subclinical (suspicious excluded positives) and absolute healthy (suspicious included positives) ones. Therefore, optimum cut-off threshold was evaluated for these two different scenarios with only variable SCC the gold standard indicator of subclinical mastitis and results were compared in the interpretation of model performance. The results show that the 5-variable MLP model exhibits a high sensitivity of 93.22% (AUC = 0.95 for healthy ones) at low cutoff thresholds as well. New studies should provide a better understanding by evaluating economics, sustainability, animal welfare and health aspects together to determine the optimal threshold value.
摘要：
当前的研究旨在为确定4级亚临床乳腺炎的经典方法提供替代模型（健康，可疑,亚临床，和临床）。为此,建立了多层感知器（MLP）人工神经网络（ANN）作为测试模型。来自牛奶体细胞计数（SCC）的物理性质的5个变量，电导率(EC)，pH值,密度,乳腺炎分类模型中包括挤奶前温度（TFM）。在测试数据（％25）上验证了模型性能，并与多项逻辑回归（MNLR）进行了比较。尽管使用了更多的参数（104），MLP模型已显示出令人满意的性能，其准确性为95.14％，AIC评分的-141优于对照模型（MNLR）的80.27％和-133AIC。因为主要的问题是诊断亚临床型乳腺炎,不会引起任何明显的症状，区分绝对亚临床(可疑排除阳性)和绝对健康(可疑纳入阳性)非常重要.因此,对于这两种不同的情况,评估了最佳截止阈值,只有可变的SCC(亚临床乳腺炎的金标准指标),并在解释模型性能时比较了结果.结果表明，5变量MLP模型在低截止阈值时也表现出93.22％的高灵敏度（健康模型的AUC=0.95）。新的研究应该通过评估经济学来提供更好的理解，可持续性动物福利和健康方面一起确定最佳阈值。
