Effectiveness of Stocking Density Reduction on Mitigating Lameness in a Charolais Finishing Beef Cattle Farm

Retrospective study of lameness in beef cattle in northeastern Sardinia, Italy

Lameness is one of the most prevalent diseases affecting dairy and beef cattle, resulting in decreased animal performance, decreased animal welfare, and substantial economic loss. In extensive beef cattle farming, the risk factors for this multifactorial disease are largely unexplored. This study aims to conduct a preliminary epidemiological survey of risk factors in beef cattle in extensive breeding, evaluate the farmer's perception of lameness, and determine the recurrence frequency of the pathologies under investigation in treated animals. The study was conducted in Sardinia, Italy. The population of the study consisted of 14379 cattle from 230 farms. An ad hoc questionnaire was developed to collect all the necessary data. A strong association was found between breed and the occurrence and recurrence of lameness (p < 0.0001). In addition, the Country of origin of both bulls and cows was found to be correlated with the incidence of lameness (p < 0.0001 and 0.0001, respectively). Farmers who indicated on the questionnaire that lameness was not important on their farm had more animals with recurrences (p < 0.0001) than other farmers. The veterinarian's treatment choice differed significantly by farmer concern (p = 0.007) and was associated with less disease recurrence (p < 0.0001), resulting in greater farmer satisfaction (p < 0.007). Pure cow breed, French bull origin, and farmer's age were detected as significant predictors of lameness issues, with pure cow breed and French bull origin having the strongest associations (p = 0.009). Even though the results of this study are preliminary, they indicate that breed selection is crucial in extensive beef farms to reduce lameness prevalence. In addition, it would be reasonable to train breeders to prevent and diagnose lameness early in order to collaborate with veterinarians to prevent recurrence.

Herd Level Yield Gap Analysis in a Local Scale Dairy Farming System: A Practical Approach to Discriminate between Nutritional and Other Constraining Factors

This study performed a yield gap analysis to help farmers understand whether their constraints were mainly due to nutritional factors or management and health issues. Twenty-nine farms were periodically evaluated. Milk yield (MY), dry matter intake (DMI), total mixed ration (TMR) composition and homogeneity index (HI), TMR digestibility, income over feed cost (IOFC), and MY summer-winter ratio (SWR) were collected. Farms were divided and compared according to the average annual MY: Low (L), Medium (M) and High (H), characterised by <31.1, 31.1-36.7 and >36.7 kg/head/day. An ANOVA mixed model and a stepwise regression to assess the relationship between nutritional variables and MY were run. H farms showed higher IOFC (p < 0.001), DMI (p = 0.006), DDM (p < 0.001), digestible crude protein (DCP, p = 0.019), HI (p = 0.09), SWR (p = 0.041) and lower HI coefficient of variation (p = 0.04). The conversion of DDM into milk was higher in H and M farms. Stepwise regression for MY selected DDM and CP (R² = 0.716, p < 0.05). M farms were mainly constrained by nutritional factors, whereas L farms were also affected by other factors such as those related to management and health.

Machine Learning to Detect Posture and Behavior in Dairy Cows: Information from an Accelerometer on the Animal's Left Flank

Simple Summary

This study analyzed the possibility of automatically detecting dairy cow behavior by combining the use of a single triaxial accelerometer applied to the animal’s left flank with a machine learning technique. This combination enabled the detection of posture and the main types of behavior that are extremely useful in evaluating the animal’s welfare and health such as resting, feeding, and rumination with a high degree of accuracy. The novelty of the study was the success in reaching a high accuracy in detecting five different behaviors and the animal posture by using a single sensor and allowing farmers to save money. To the best of our knowledge, this is the first study that has successfully explored the feasibility of locating a sensor on the animal’s left flank, showing the opportunity of automatically measuring some physiological parameters, such as those ones related to respiration and rumen health, in a non-invasive way.

Abstract

The aim of the present study was to develop a model to identify posture and behavior from data collected by a triaxial accelerometer located on the left flank of dairy cows and evaluate its accuracy and precision. Twelve Italian Red-and-White lactating cows were equipped with an accelerometer and observed on average for 136 ± 29 min per cow by two trained operators as a reference. The acceleration data were grouped in time windows of 8 s overlapping by 33.0%, for a total of 35,133 rows. For each row, 32 different features were extracted and used by machine learning algorithms for the classification of posture and behavior. To build up a predictive model, the dataset was split in training and testing datasets, characterized by 75.0 and 25.0% of the observations, respectively. Four algorithms were tested: Random Forest, K Nearest Neighbors, Extreme Boosting Algorithm (XGB), and Support Vector Machine. The XGB model showed the best accuracy (0.99) and Cohen’s kappa (0.99) in predicting posture, whereas the Random Forest model had the highest overall accuracy in predicting behaviors (0.76), showing a balanced accuracy from 0.96 for resting to 0.77 for moving. Overall, very accurate detection of the posture and resting behavior were achieved.