Pattern of γ-glutamyl transferase activity in cow milk throughout lactation and relationships with metabolic conditions and milk composition

Prediction of detailed blood metabolic profile using milk infrared spectra and machine learning methods in dairy cattle

The adoption of preventive management decisions is crucial to dealing with metabolic impairments in dairy cattle. Various serum metabolites are known to be useful indicators of the health status of cows. In this study, we used milk Fourier-transform mid-infrared (FTIR) spectra and various machine learning (ML) algorithms to develop prediction equations for a panel of 29 blood metabolites, including those related to energy metabolism, liver function/hepatic damage, oxidative stress, inflammation/innate immunity, and minerals. For most traits, the data set comprised observations from 1,204 Holstein-Friesian dairy cows belonging to 5 herds. An exception was represented by β-hydroxybutyrate prediction, which contained observations from 2,701 multibreed cows pertaining to 33 herds. The best predictive model was developed using an automatic ML algorithm that tested various methods, including elastic net, distributed random forest, gradient boosting machine, artificial neural network, and stacking ensemble. These ML predictions were compared with partial least squares regression, the most commonly used method for FTIR prediction of blood traits. Performance of each model was evaluated using 2 cross-validation (CV) scenarios: 5-fold random (CV_r) and herd-out (CV_h). We also tested the best model's ability to classify values precisely in the 2 extreme tails, namely, the 25th (Q25) and 75th (Q75) percentiles (true-positive prediction scenario). Compared with partial least squares regression, ML algorithms achieved more accurate performance. Specifically, elastic net increased the R² value from 5% to 75% for CV_r and 2% to 139% for CV_h, whereas the stacking ensemble increased the R² value from 4% to 70% for CV_r and 4% to 150% for CV_h. Considering the best model, with the CV_r scenario, good prediction accuracies were obtained for glucose (R² = 0.81), urea (R² = 0.73), albumin (R² = 0.75), total reactive oxygen metabolites (R² = 0.79), total thiol groups (R² = 0.76), ceruloplasmin (R² = 0.74), total proteins (R² = 0.81), globulins (R² = 0.87), and Na (R² = 0.72). Good prediction accuracy in classifying extreme values was achieved for glucose (Q25 = 70.8%, Q75 = 69.9%), albumin (Q25 = 72.3%), total reactive oxygen metabolites (Q25 = 75.1%, Q75 = 74%), thiol groups (Q75 = 70.4%), total proteins (Q25 = 72.4%, Q75 = 77.2.%), globulins (Q25 = 74.8%, Q75 = 81.5%), and haptoglobin (Q75 = 74.4%). In conclusion, our study shows that FTIR spectra can be used to predict blood metabolites with relatively good accuracy, depending on trait, and are a promising tool for large-scale monitoring.

Metabolic and physiological adaptations to first and second lactation in Holstein dairy cows

Huge differences exist between cow yields and body sizes during their first and second lactations. The transition period is the most critical and investigated phase of the lactation cycle. We compared metabolic and endocrine responses between cows at different parities during the transition period and early lactation. Eight Holstein dairy cows were monitored at their first and second calving during which they were reared under the same conditions. Milk yield, dry matter intake (DMI), and body weight (BW) were regularly measured, and energy balance, efficiency, and lactation curves were calculated. Blood samples were collected on scheduled days from -21 d relative to calving (DRC) to 120 DRC for the assessment of metabolic and hormonal profiles (biomarkers of metabolism, mineral status, inflammation, and liver function). Large variations in the period in question for almost all variables investigated were observed. Compared with their first lactation, cows during their second lactation had higher DMI (+15%) and BW (+13%), their milk yield was greater (+26%), lactation peak was higher and earlier (36.6 kg/d at 48.8 DRC vs. 45.0 kg/d at 62.9 DRC), but persistency was reduced. Milk fat, protein, and lactose contents were higher during the first lactation and coagulation properties were better (higher titratable acidity, faster and firmer curd formation). Postpartum negative energy balance was more severe the during the second lactation (1.4-fold at 7 DRC) and plasma glucose was lower. Circulating insulin and insulin-like growth factor-1 were lower in second-calving cows during the transition period. At the same time, markers of body reserve mobilization (β-hydroxybutyrate and urea) increased. Moreover, albumin, cholesterol, and γ-glutamyl transferase were higher during second lactation, whereas bilirubin and alkaline phosphatase were lower. The inflammatory response after calving was not different, as suggested by the similar haptoglobin concentrations and only transient differences in ceruloplasmin. Blood growth hormone did not differ during the transition period but was lower during the second lactation at 90 DRC, whereas circulating glucagon was higher. These results agree with the differences in milk yield and confirmed the hypothesis of a different metabolic and hormonal status between the first and second lactation partly related to different degrees of maturity.

In-line near-infrared analysis of milk coupled with machine learning methods for the daily prediction of blood metabolic profile in dairy cattle

Precision livestock farming technologies are used to monitor animal health and welfare parameters continuously and in real time in order to optimize nutrition and productivity and to detect health issues at an early stage. The possibility of predicting blood metabolites from milk samples obtained during routine milking by means of infrared spectroscopy has become increasingly attractive. We developed, for the first time, prediction equations for a set of blood metabolites using diverse machine learning methods and milk near-infrared spectra collected by the AfiLab instrument. Our dataset was obtained from 385 Holstein Friesian dairy cows. Stacking ensemble and multi-layer feedforward artificial neural network outperformed the other machine learning methods tested, with a reduction in the root mean square error of between 3 and 6% in most blood parameters. We obtained moderate correlations (r) between the observed and predicted phenotypes for γ-glutamyl transferase (r = 0.58), alkaline phosphatase (0.54), haptoglobin (0.66), globulins (0.61), total reactive oxygen metabolites (0.60) and thiol groups (0.57). The AfiLab instrument has strong potential but may not yet be ready to predict the metabolic stress of dairy cows in practice. Further research is needed to find out methods that allow an improvement in accuracy of prediction equations.

Associations between ultrasound measurements and hematochemical parameters for the assessment of liver metabolic status in Holstein-Friesian cows

Metabolic disorders, including hepatic lipidosis and ketosis, severely affect animal health status and welfare with a large economic burden in dairy herds. The gold standard for diagnosing hepatic lipidosis is the liver biopsy, which is impractical and invasive for the screening at farm level. Ultrasound (US) imaging is a promising technique for identifying liver dysfunction, but standardized specifications in physiological conditions are needed. Herein, we described the features of four US measurements, namely the liver predicted triacylglycerol (pTAG) content, liver depth (LD), and portal vein area (PVA) and depth (PVD) and we investigated their associations with a set of hematochemical (HC) indicators in 342 clinically healthy Holstein Friesian dairy cows. Liver pTAG content was negatively associated with hematocrit and positively with globulin, whereas PVA was negatively associated with thiol group levels, and LD positively with ceruloplasmin. We found significant interactions between some HC parameters and parity: in particular, creatinine, thiol groups and globulin for PVA, and aspartate aminotransferase, paraoxonase and ceruloplasmin for PVD. This study offers new insights on variations in liver function occurring after calving and pave the way for the potential use of minimally invasive techniques for prompt detection of metabolic disorders in dairy herds.