This study hypothesizes that higher in-line milk lactose concentrations are indicative of enhanced dairy cow behaviors—including increased rumination, feeding, and locomotion activities—reflecting superior overall health and well-being. It posits that fluctuations in milk lactose levels have a substantial impact on the physiological and behavioral responses of dairy cows, thereby affecting their milk yields and compositions. Each cow’s milk lactose, fat, protein, and fat-to-protein ratio were continuously monitored using the BROLIS HerdLine in-line milk analyzer (Brolis Sensor Technology, Vilnius, Lithuania). The RumiWatch noseband sensor (RWS; ITIN + HOCH GmbH, Fütterungstechnik, Liestal, Switzerland) was employed to measure the biomarkers of the rumination, feeding, and locomotion behavior. The measurements were recorded over 5 days at the same time (during morning milking). A total of 502 cows were examined. During these 5 days, 2510 measurements were taken. Based on the lactose content in their milk, the cows were divided into two categories: the first group consisted of cows with milk lactose levels below 4.70%, while the second group included cows with milk lactose levels of 4.70% or higher. Our study showed that cows with higher milk lactose concentrations (≥4.70%) produced significantly more milk (16.14% increase) but had a lower milk protein concentration (5.05% decrease) compared to cows with lower lactose levels. These cows also exhibited changes in rumination and feeding behaviors, as recorded by the RWS: there was an increase in the mastication and rumination behaviors, evidenced by a 14.09% rise in other chews and a 13.84% increase in rumination chews, along with a 16.70% boost in bolus activity. However, there was a notable 16.18% reduction in their physical activity, as measured by the change in time spent walking.

Heat stress has a major impact on dairy cow health and productivity, especially during early lactation. Conventional heat stress monitoring methods frequently rely on single indicators, such as the temperature–humidity index (THI), which may miss subtle physiological and metabolic responses. This study presents a novel threshold-based classification framework that integrates biologically meaningful combinations of environmental, behavioural, and physiological variables to detect early-stage heat stress responses in dairy cows. Six composite heat stress conditions (C1–C6) were developed using real-time THI, milk temperature, reticulorumen pH, rumination time, milk lactose, and milk fat-to-protein ratio. The study applied and assessed five supervised machine learning models (Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Random Forest (RF0, Neural Network (NN), and an Ensemble approach) trained on daily datasets gathered from early-lactation dairy cows fitted with intraruminal boluses and monitored through milking parlour sensor systems. The dataset comprised approximately 36,000 matched records from 200 cows monitored over 60 days. The highest classification performance was observed for RF and NN models, particularly under C1 (THI > 73 and milk temperature > 38.6 °C) and C6 (THI > 74 and milk temperature > 38.7 °C), with AUC values exceeding 0.90. SHAP analysis revealed that milk temperature, THI, rumination time, and milk lactose were the most informative features across conditions. This integrative approach enhances precision livestock monitoring by enabling individualised heat stress risk classification well before clinical or production-level consequences emerge.

The early lactation phase in dairy cows is characterised by significant metabolic and inflammatory changes. This study aimed to evaluate the relationship between serum nonesterified fatty acids (NEFAs), a marker of negative energy balance (NEB), and serum amyloid A (SAA), an indicator of systemic inflammation. Blood samples were collected from 71 Holstein cows during the transition period 17 (±3) DIM, and serum concentrations of NEFAs and SAA were measured. The results revealed a significant negative correlation between NEFAs and SAA (r = −0.441, p < 0.001), suggesting that increased fat mobilisation may suppress the inflammatory response, thereby increasing the susceptibility to metabolic and infectious diseases. The emerging research indicates a negative association between SAA levels and milk fat-to-protein ratio in dairy cows, particularly under inflammatory conditions. The research indicates that elevated levels of SAA, which is an inflammatory biomarker, are frequently associated with alterations in milk composition, including a reduced fat-to-protein ratio. This study examined the correlations among serum NEFAs, SAA, milk composition, and dairy cattle health. A strong positive correlation was identified between serum NEFAs and milk fat content (r = 0.459, p < 0.001), as well as between serum NEFAs and the milk fat-to-protein ratio (r = 0.516, p < 0.001). Cows with elevated serum NEFA levels (classified as II-NEFA) exhibited significantly higher milk fat content (4.20%) and milk fat-to-protein ratios (1.33) compared to cows with lower serum NEFA levels (I-NEFA class; 3.81% and 1.17, respectively). The data indicate that elevated serum NEFA levels are associated with an increased milk fat synthesis, likely driven by enhanced fat mobilisation during NEB. A significant negative correlation was observed between SAA and both milk fat content (r = −0.426, p < 0.001) and the milk fat-to-protein ratio (r = −0.535, p < 0.001), indicating that inflammation may impair milk fat production. Elevated SAA levels were also associated with increased cow activity (r = 0.382, p < 0.001), suggesting that inflammation may lead to behavioural changes driven by discomfort. Our findings suggest that milk composition reflects the metabolic and inflammatory status of dairy cows and could serve as a non-invasive alternative to blood sampling for assessing energy balance and health. NEB, which typifies early lactation, promotes fat mobilisation, resulting in elevated serum NEFA levels and an increased risk of metabolic disorders such as fatty liver syndrome and ketosis. Moreover, high serum NEFA levels adversely affect immune function, increasing vulnerability to infections such as mastitis. Monitoring milk composition may enable the early detection of NEB and inflammatory conditions, thereby supporting proactive health management. However, further research is necessary to elucidate the role of NEFAs and inflammation in the development of metabolic diseases in cattle.

This study investigates the relationship between lameness, milk composition, and rumination behaviour in dairy cows by leveraging sensor-based data for automated monitoring. Lameness was found to significantly impact both rumination and milk production. Lameness was assessed in 24 multiparous Holstein dairy cows throughout early lactation (up to 100 days postpartum), utilising a 1-to-5 scale. Lameness was found to significantly impact both rumination and milk production. On the day of diagnosis, rumination time decreased by 26.64% compared to the pre-diagnosis period (p < 0.01) and by 26.06% compared to healthy cows, indicating the potential of rumination as an early health indicator. The milk yield on the day of diagnosis was 28.10% lower compared to pre-diagnosis levels (p < 0.01) and 40.46% lower than healthy cows (p < 0.05). These findings suggest that lameness manifests prior to clinical signs, affecting productivity and welfare. Milk composition was also influenced, with lame cows exhibiting altered fat (+0.68%, p < 0.05) and lactose (−2.15%, p < 0.05) content compared to healthy cows. Positive correlations were identified between rumination time and milk yield (r = 0.491, p < 0.001), while negative correlations were observed between milk yield and milk fat, protein, and the fat-to-protein ratio (p < 0.001). Additionally, lameness was associated with elevated somatic cell counts in the milk, although sample size limitations necessitate further validation. This study highlights the critical role of rumination and milk performance metrics in identifying subclinical lameness, emphasising the utility of automated systems in advancing dairy cow welfare and productivity. The findings underscore the importance of early detection and management strategies to mitigate the economic and welfare impacts of lameness in dairy farming.

The aim of this study was to evaluate the influence of the temperature and humidity index on reticulorumen parameters such as temperature, pH, rumination index, and cow walking activity levels. Throughout the experiment, the following parameters were recorded: reticulorumen pH (pH), reticulorumen temperature (RR temp.), reticulorumen temperature without drinking cycles, ambient temperature, ambient relative humidity, cow walking activity levels, heat index, and temperature–humidity index (THI). These parameters were registered with particular smaXtec boluses. SmaXtec boluses were applied on 1 July 2022; 24 days were the adaptation period. Measurements started at 25 July 2022 and finished at 29 August 2022. The THI was divided into two classes: THI < 72 (comfort zone) and THI ≥ 72 (higher risk of thermal stress). Cows assigned to the 2nd THI class had lower average values for pH, temperature, and rumination index, but not walking activity levels. The mean differences ranged from 0.36 percent in temperature to 11.61 percent in walking activity levels (p < 0.01). An analysis of the THI revealed a significant positive linear relation with hours, where the THI had a tendency to increase on average by 0.2403. The reticuloruminal pH showed a negative linear relation with hours, where the reticuloruminal pH had a tendency to decrease on average by 0.0032, p < 0.001. Data analysis revealed a significant positive linear relationship between walking activity levels and hours, where walking activity levels had a tendency to increase on average by 0.0622 steps per hour, p < 0.001. The rumination index was not significantly related to hours (p < 0.005), although the rumination index had a tendency to increase by 0.4376 per hour, p > 0.05. The influence of HS on reticulorumen parameters increased the risk of acidosis and cows’ activity levels. HS had a negative impact on reticulorumen pH, temperature, and the rumination index. A higher THI (≥72) increased the risk of ruminal acidosis and decreased cows’ physical activity levels. From a practical point of view, we can use innovative tools for the detection of HS and its impact on reticulorumen parameters and cow walking activity levels.

This study assessed five supervised machine learning (ML) models. Automated devices that continuously captured milk composition and behavioral data were used to monitor 206 Holstein cows from two commercial dairy farms. Milk yield, fat, protein, lactose, fat-to-protein ratio (FPR), somatic cell count (SCC), rumination time (RT), and body temperature were among the parameters that were noted. Cows were categorized as clinically healthy ( n = 45), subclinical ketosis ( n = 91), subclinical mastitis ( n = 28), or clinical mastitis ( n = 42) based on clinical examination, blood β -hydroxybutyrate (BHB) concentration, and milk indicators. Random Forest achieved the highest classification accuracy (0.857), followed by Gradient Boosting and Logistic Regression (0.833), while Decision Tree and Multilayer Perceptron reached 0.810. Compared to clinically healthy cows (4.45 ± 0.54%; 477.0 ± 36.0 min/day), subclinical ketosis cows had a greater milk fat content (5.21 ± 0.72%) and a shorter RT (336.9 ± 94.2 min/day). In comparison to clinically healthy cows (64.0 × 10 ³ cells/mL; 4.63 ± 0.16%), cows with clinical mastitis showed significantly greater SCC (416.8 × 10 ³ cells/mL) and lower lactose levels (4.56 ± 0.24%). These results demonstrate that integrating sensor-derived milk and behavioral data with ML algorithms enables early, non-invasive detection of health disorders, supporting proactive herd management.