Mastitis has a substantial impact on the dairy industry across the world, causing dairy producers to suffer losses due to the reduced quality and quantity of produced milk. A further problem, related to this issue, is the excessive use of antibiotics that leads to the development of resistance in different bacterial strains. The growing consumer awareness oriented toward food safety and rational use of antibiotics has promoted the search for new methods of early identification of cows that may be at risk of developing the disease. Subclinical mastitis does not cause any visible changes to the udder or milk, and therefore it is more difficult to detect than clinical mastitis. The collection of large amounts of data related to milk performance of cows allows using machine learning (ML) methods to build models that could be used for classifying cows into healthy and at risk of subclinical mastitis. The data used for the purpose of this study included information from routine milk recording procedures. The dataset consisted of 19,856 records of 2,227 Polish Holstein-Friesian cows from 3 herds. The authors decided to use the approach of building ensemble ML models, in particular bagging, boosting, stacking, and super-learner models, and comparing them for accuracy of identification of disease-affected cows against single ML models based on the support vector machines, logistic regression, Gaussian Naive Bayes, k-nearest neighbors, and decision tree algorithms. The models were trained and evaluated based on the information recorded for herd 1 and using an 80:20 train-test split ratio according to animal ID (to avoid data leakage). The information recorded for herds 2 and 3 was only used to evaluate on unseen data models developed using the herd 1 dataset. Among the single ML models, the support vector machines model was found to be the most accurate in predicting subclinical mastitis at subsequent test day when used both for the training set (mean F₁-score of 0.760) and the testing sets containing data for herds 1, 2, and 3 (F₁-score of 0.778, 0.790, and 0.741 respectively). The gradient boosting model was found to be the best performing model among the ensemble ML models (F₁-score of 0.762, 0.779, 0.791, and 0.723 for the training set and the testing sets, respectively). The super-learner model, featuring the most advanced design and logistic regression in the meta layer, achieved the highest mean F₁-score of 0.775 during the cross validation; however, it was characterized by a slightly worse prediction accuracy of the testing sets (mean F₁-score of 0.768, 0.790, and 0.693 for herds 1, 2 and 3 respectively). The study findings confirm the promising role of ensemble ML methods, which were found to be slightly superior with respect to most of the single ML models.

The diagnosis of subclinical ketosis in dairy cows based on blood ketone bodies is a challenging and costly procedure. Scientists are searching for tools based on results of milk performance assessment that would allow monitoring the risk of subclinical ketosis. The objective of the study was (1) to design a scoring system that would allow choosing the best machine learning models for the identification of cows-at-risk of subclinical ketosis, (2) to select the best performing models, and (3) to validate them using a testing dataset containing unseen data. The scoring system was developed using two machine learning modeling pipelines, one for regression and one for classification. As part of the system, different feature selections, outlier detection, data scaling and oversampling methods were used. Various linear and non-linear models were fit using training datasets and evaluated on holdout, testing the datasets. For the assessment of suitability of individual models for predicting subclinical ketosis, three β-hydroxybutyrate concentration in blood (bBHB) thresholds were defined: 1.0, 1.2 and 1.4 mmol/L. Considering the thresholds of 1.2 and 1.4, the logistic regression model was found to be the best fitted model, which included independent variables such as fat-to-protein ratio, acetone and β-hydroxybutyrate concentrations in milk, lactose percentage, lactation number and days in milk. In the cross-validation, this model showed an average sensitivity of 0.74 or 0.75 and specificity of 0.76 or 0.78, at the pre-defined bBHB threshold 1.2 or 1.4 mmol/L, respectively. The values of these metrics were also similar in the external validation on the testing dataset (0.72 or 0.74 for sensitivity and 0.80 or 0.81 for specificity). For the bBHB threshold at 1.0 mmol/L, the best classification model was the model based on the SVC (Support Vector Classification) machine learning method, for which the sensitivity in the cross-validation was 0.74 and the specificity was 0.73. These metrics had lower values for the testing dataset (0.57 and 0.72 respectively). Regression models were characterized by poor fitness to data (R² < 0.4). The study results suggest that the prediction of subclinical ketosis based on data from test-day records using classification methods and machine learning algorithms can be a useful tool for monitoring the incidence of this metabolic disorder in dairy cattle herds.

The aim of the study was to estimate the genetic parameters of milk fat-to-protein ratio in the first three lactations of Polish Holstein-Friesian cows. Data included 104 875 test-day records of 6299 cows calving from years 2000–2012. Genetic parameters were estimated with a multitrait random...

The purpose of this study was to find early indicators of cow fertility. Genetic correlations of two types of conformation evaluations, routine and modified, with reproduction traits were estimated. Data consisted of type evaluations and fertility measures of primiparous Holstein-Friesian cows...

Knowledge of the body weight of horses permits breeders to provide appropriate feeding and care regimen and allows veterinarians to monitor the animals’ health. It is not always possible to perform an accurate measurement of the body weight of horses using horse weighbridges, and therefore, new body weight formulas based on biometric measurements are required. The objective of this study is to develop and validate models for estimating body weight in Icelandic foals using machine learning methods. The study was conducted using 312 data records of body measurements on 24 Icelandic foals (12 colts and 12 fillies) from birth to 404 days of age. The best performing model was the polynomial model that included features such as heart girth, body circumference and cannon bone circumference. The mean percentage error for this model was 4.1% based on cross-validation and 3.8% for a holdout dataset. The body weight of Icelandic foals can also be estimated using a less complex model taking a single trait defined as the square of heart girth multiplied by body circumference. The mean percentage error for this model was up to 5% both for the training and the holdout datasets. The study results suggest that machine learning methods can be considered a useful tool for designing models for the estimation of body weight in horses.

The objective of this study was to compare five mathematical functions used for modeling lactation curves and to choose the most suitable one for Polish Holstein-Friesian cows. The data used were 1,944,818; 1,548,700; and 1,081,107 test-day milk yields from 220,487 first, 181,165 second, and...