Evaluating machine learning algorithms to predict lameness in dairy cattle

Dairy cattle lameness represents one of the common concerns in intensive and commercial dairy farms. Lameness is characterized by gait-related behavioral changes in cows and multiple approaches are being utilized to associate these changes with lameness conditions including data from accelerometers, and other precision technologies. The objective was to evaluate the use of machine learning algorithms for the identification of lameness conditions in dairy cattle. In this study, 310 multiparous Holstein dairy cows from a herd in Northern Colorado were affixed with a leg-based accelerometer (Icerobotics® Inc, Edinburg, Scotland) to obtain the lying time (min/d), daily steps count (n/d), and daily change (n/d). Subsequently, study cows were monitored for 4 months and cows submitted for claw trimming (CT) were differentiated as receiving corrective claw trimming (CCT) or as being diagnosed with a lameness disorder and consequent therapeutic claw trimming (TCT) by a certified hoof trimmer. Cows not submitted to CT were considered healthy controls. A median filter was applied to smoothen the data by reducing inherent variability. Three different machine learning (ML) models were defined to fit each algorithm which included the conventional features (containing daily lying, daily steps, and daily change derived from the accelerometer), slope features (containing features extracted from each variable in Conventional feature), or all features (3 simple features and 3 slope features). Random forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Time series (ROCKET) were used as ML predictive approaches. For the classification of cows requiring CCT and TCT, ROCKET classifier performed better with accuracy (> 90%), ROC-AUC (> 74%), and F1 score (> 0.61) as compared to other algorithms. Slope features derived in this study increased the efficiency of algorithms as the better-performing models included All features explored. However, further classification of diseases into infectious and non-infectious events was not effective because none of the algorithms presented satisfactory model accuracy parameters. For the classification of observed cow locomotion scores into severely lame and moderately lame conditions, the ROCKET classifier demonstrated satisfactory accuracy (> 0.85), ROC-AUC (> 0.68), and F1 scores (> 0.44). We conclude that ML models using accelerometer data are helpful in the identification of lameness in cows but need further research to increase the granularity and accuracy of classification.

Predicting subacute ruminal acidosis from milk mid-infrared estimated fatty acids and machine learning on Canadian commercial dairy herds

Our objective was to validate the possibility of detecting SARA from milk Fourier transform mid-infrared spectroscopy estimated fatty acids (FA) and machine learning. Subacute ruminal acidosis is a common condition in modern commercial dairy herds for which the diagnostic remains challenging due to its symptoms often being subtle, nonexclusive, and not immediately apparent. This observational study aimed at evaluating the possibility of predicting SARA by developing machine learning models to be applied to farm data and to provide an estimated portrait of SARA prevalence in commercial dairy herds. A first data set composed of 488 milk samples of 67 cows (initial DIM = 8.5 ± 6.18; mean ± SD) from 7 commercial dairy farms and their corresponding SARA classification (SARA+ if rumen pH <6.0 for 300 min, else SARA-) was used for the development of machine learning models. Three sets of predictive variables: i) milk major components (MMC), ii) milk FA (MFA), and iii) MMC combined with MFA (MMCFA) were submitted to 3 different algorithms, namely Elastic net (EN), Extreme gradient boosting (XGB), and Partial least squares (PLS), and evaluated using 3 different scenarios of cross-validation. Accuracy, sensitivity, and specificity of the resulting 27 models were analyzed using a linear mixed model. Model performance was not significantly affected by the choice of algorithm. Model performance was improved by including fatty acids estimations (MFA and MMCFA as opposed to MMC alone). Based on these results, one model was selected (algorithm: EN; predictive variables: MMCFA; 60.4, 65.4, and 55.3% of accuracy, sensitivity, and specificity, respectively) and applied to a large data set comprising the first test-day record (milk major components and FA within the first 70 DIM of 211,972 Holstein cows (219,503 samples) collected from 3001 commercial dairy herds. Based on this analysis, the within-herd SARA prevalence of commercial farms was estimated at 6.6 ± 5.29% ranging from 0 to 38.3%. A subsequent linear mixed model was built to investigate the herd-level factors associated to higher within-herd SARA prevalence. Milking system, proportion of primiparous cows, herd size and seasons were all herd-level factors affecting SARA prevalence. Furthermore, milk production was positively, and milk fat yield negatively associated with SARA prevalence. Due to their moderate levels of accuracy, the SARA prediction models developed in our study, using data from continuous pH measurements on commercial farms, are not suitable for diagnostic purpose. However, these models can provide valuable information at the herd level.

Development of a real-time cattle lameness detection system using a single side-view camera

Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and classification. This research investigates the application of deep learning for cattle lameness detection in dairy farming. Our study employs image processing techniques and deep learning methods for cattle detection, tracking, and lameness classification. We utilize two powerful object detection algorithms: Mask-RCNN from Detectron2 and the popular YOLOv8. Their performance is compared to identify the most effective approach for this application. Bounding boxes are drawn around detected cattle to assign unique local IDs, enabling individual tracking and isolation throughout the video sequence. Additionally, mask regions generated by the chosen detection algorithm provide valuable data for feature extraction, which is crucial for subsequent lameness classification. The extracted cattle mask region values serve as the basis for feature extraction, capturing relevant information indicative of lameness. These features, combined with the local IDs assigned during tracking, are used to compute a lameness score for each cattle. We explore the efficacy of various established machine learning algorithms, such as Support Vector Machines (SVM), AdaBoost and so on, in analyzing the extracted lameness features. Evaluation of the proposed system was conducted across three key domains: detection, tracking, and lameness classification. Notably, the detection module employing Detectron2 achieved an impressive accuracy of 98.98%. Similarly, the tracking module attained a high accuracy of 99.50%. In lameness classification, AdaBoost emerged as the most effective algorithm, yielding the highest overall average accuracy (77.9%). Other established machine learning algorithms, including Decision Trees (DT), Support Vector Machines (SVM), and Random Forests, also demonstrated promising performance (DT: 75.32%, SVM: 75.20%, Random Forest: 74.9%). The presented approach demonstrates the successful implementation for cattle lameness detection. The proposed system has the potential to revolutionize dairy farm management by enabling early lameness detection and facilitating effective monitoring of cattle health. Our findings contribute valuable insights into the application of advanced computer vision methods for livestock health management.

Random forest classification as a tool in epidemiological modelling: Identification of farm-specific characteristics relevant for the occurrence of Fasciola hepatica on German dairy farms

Fasciola hepatica is an internal parasite of both human and veterinary relevance. In order to control fasciolosis, a multitude of attempts to predict the risk of infection such as risk maps or forecasting models have been developed. These attempts mainly focused on the influence of geo-climatic and meteorological features. Predicting bovine fasciolosis on farm level taking into account farm-specific settings yet remains challenging. In the present study, a new methodology for this purpose, a data-driven machine learning approach using a random forest classification algorithm was applied to a cross-sectional data set of farm characteristics, management regimes, and farmer aspects within two structurally different dairying regions in Germany in order to identify factors relevant for the occurrence of F. hepatica that could predict farm-level bulk tank milk positivity. The resulting models identified farm-specific key aspects in regard to the presence of F. hepatica. In study region North, farm-level production parameters (farm-level milk yield, farm-level milk fat, farm-level milk protein), leg hygiene, body condition (prevalence of overconditioned and underconditioned cows, respectively) and pasture access were identified as features relevant in regard to farm-level F. hepatica positivity. In study region South, pasture access together with farm-level lameness prevalence, farm-level prevalence of hock lesions, herd size, parity, and farm-level milk fat appeared to be important covariates. The stratification of the analysis by study region allows for the extrapolation of the results to similar settings of dairy husbandry. The local, region-specific modelling of F. hepatica presence in this work contributes to the understanding of on-farm aspects of F. hepatica appearance. The applied technique represents a novel approach in this context to model epidemiological data on fasciolosis which allows for the identification of farms at risk and together with additional findings in regard to the epidemiology of fasciolosis, can facilitate risk assessment and deepen our understanding of on-farm drivers of the occurrence of F. hepatica.

Associations of cow and farm characteristics with cow-level lameness using data from an extensive cross-sectional study across 3 structurally different dairy regions in Germany

The aim of the present study was to evaluate the associations between milk recording data, body condition score (BCS), housing factors, management factors, and lameness in freestall-housed dairy cows in 3 structurally different regions in Germany. These regions substantially vary regarding herd size, breeds, access to pasture, farm management (family run or company owned), and percentage of organic farms. The data used was collected in a large cross-sectional study from 2016 to 2019. A total of 58,144 cows from 651 farms in 3 regions of Germany (North, East, and South) was scored for locomotion and body condition. Additionally, data on milk yield, milk composition, breed, age, as well as information on housing and management were retrieved. One mixed-logistic regression model was fitted per region to evaluate the association of the data with the target variable "lame" and to allow for a comprehensive reflection across different kinds of farming types. In all regions, undercondition (BCS lower than recommended for the lactation stage; North: odds ratio [OR] 2.15, CI 1.96-2.34; East: OR 2.66, CI 2.45-2.88; South: OR 2.45, CI 2.01-2.98) and mid-lactation stage (102-204 d in milk; North: OR 1.15, CI 1.05-1.27; East: OR 1.24, CI 1.17-1.32; South: OR 1.38, CI 1.18-1.62) were associated with higher odds for lameness, whereas overcondition (BCS higher than recommended for the lactation stage; North: OR 0.51, CI 0.44-0.60; East: OR 0.51, CI 0.48-0.54; South: OR 0.65, CI 0.54-0.77) and parity of 1 or 2 was associated with lower odds (parity 1 = North: OR 0.32, CI 0.29-0.35; East: OR 0.19, CI 0.18-0.20; South: OR 0.28, CI 0.24-0.33; parity 2 = North: OR 0.51, CI 0.47-0.46; East: OR 0.41, CI 0.39-0.44; South: OR 0.49, CI 0.42-0.57), irrespective of the regional production characteristics. Low energy-corrected milk yield was associated with higher odds for lameness in South and North (North: OR 1.16, CI 1.05-1.27; South: OR 1.43, CI 1.22-1.69). Further factors such as pasture access for cows (North: OR 0.64, CI 0.50-0.82; and South: OR 0.65, CI 0.47-0.88), milk protein content (high milk protein content = North: OR 1.34, CI 1.18-1.52; East: OR 1.17, CI 1.08-1.28; low milk protein content = North: OR 0.79, CI 0.71-0.88; East: OR 0.84, CI 0.79-0.90), and breed (lower odds for "other" [other breeds than German Simmental and German Holstein] in East [OR 0.47, CI 0.42-0.53] and lower odds both for German Holstein and "other" in South [German Holstein: OR 0.62, CI 0.43-0.90; other: OR 0.46, CI 0.34 - 0.62]) were associated with lameness in 2 regions, respectively. The risk of ketosis (higher odds in North: OR 1.11, CI 1.01-1.22) and somatic cell count (higher odds in East: increased (>39.9 cells × 1,000/mL): OR 1.10; CI 1.03-1.17; high (>198.5 cells × 1,000/mL): OR 1.08; CI 1.01-1.06) altered the odds for lameness in 1 region, respectively. Cows from organic farms had lower odds for lameness in all 3 regions (North: OR 0.18, CI 0.11-0.32; East: OR 0.39, CI 0.28-0.56; South: OR 0.45, CI 0.29-0.68). As the dairy production systems differed substantially between the different regions, the results of this study can be viewed as representative for a wide variety of loose-housed dairy systems in Europe and North America. The consistent association between low BCS and lameness in all regions aligns with the previous literature. Our study also suggests that risk factors for lameness can differ between geographically regions, potentially due to differences in which dairy production system is predominantly used and that region-specific characteristics should be taken into account in comparable future projects.

A cross-sectional study of the prevalence of lameness and digital dermatitis in dairy cattle herds in Egypt

BACKGROUND

Lameness is a significant problem for the dairy industry worldwide. No previous studies have evaluated the prevalence of lameness or digital dermatitis (DD) in dairy cattle herds in Egypt. A total of 16,098 dairy cows from 55 dairy herds in 11 Egyptian governorates underwent visual locomotion scoring using a 4-point scoring system. Cows that had a lameness score ≥ 2 were considered clinically lame. Following manure removal with water and using a flashlight, the cows' hind feet were examined in the milking parlour to identify DD lesions and classify with M-score. Furthermore, each cow was assigned a hock score (a 3-point scale) and a hygiene score (a 4-point scale). The cow-, within-and between-herd prevalence of lameness and DD and associated 95% confidence intervals (CI) were calculated. The prevalence of hock lesions and poor cow hygiene was also calculated.

RESULTS

Of the examined cows, 6,883 were found to be clinically lame (42.8%, 95% CI = 42.0-43.5%). The average within-herd prevalence of lameness was 43.1% (95% CI = 35.9-50.3%). None of the dairy herds recruited into the study were found to be free from clinical lameness. The average within-herd prevalence of DD was 6.4% (95% CI = 4.9-8.0%). The herd-level prevalence of DD was 92.7% (95% CI = 85.9-99.6%). Active DD lesions (M1, M2, M4.1) were identified in 464 cows (2.9%) while inactive lesions (M3, M4) were identified in 559 cows (3.5%). The within-herd prevalence of hock lesions (score 2 or 3) was 12.6% (95% CI = 4.03-21.1%) while a severe hock lesion had within-herd prevalence of 0.31% (95% CI = 0.12-0.51%). Cow-level prevalence of hock lesions was 6.2% (n = 847, 95% CI = 5.8-6.2%). The majority of examined cows had a hygiene score of 4 (n = 10,814, prevalence = 70.3%, 95% CI = 69.5-71%).

CONCLUSIONS

The prevalence of lameness was higher than prevalence estimates reported for other countries which could be due to differing management and/or environmental factors. DD was identified at lower prevalence in most herds but with high herd-level prevalence. Poor cow hygiene was notable in most herds. Measures to reduce the prevalence of lameness and to improve cow hygiene in dairy cattle herds in Egypt are therefore needed.

Association between Milk Electrical Conductivity Biomarkers with Lameness in Dairy Cows

Early identification of lameness at all phases of lactation improves milk yield and reduces the incidence of mastitis in the herd. According to the literature we hypothesized that there are associations of electrical conductivity variables of milk flow with lameness in dairy cows. The aim of this study was to determine if blood cortisol and electrical conductivity in the milk flow phases correlate with each other and whether they are related to cow lameness. On one farm, out of 1500 cows, 64 cows with signs of lameness and 56 healthy cows were selected with an average of 2.8 lactations and 60 days in the postpartum period. A local veterinarian who specializes in hoof care treatments identified and scored lameness. During evening milking, the milk flow of all 120 cows was measured using electronic milk flow meters (Lactocorder®, WMB AG, Balgache, Switzerland). Before each milking, two electronic mobile milk flow meters (Lactocorders) were mounted between the milking apparatus and the milking tube to take measurements. We found that the average cortisol concentration in the blood of the studied cows was significantly correlated with the laminitis score. Results of this study indicate that the number of non-lame cows with a milk electrical conductivity level of <6 mS/cm even reached 90.8−92.3% of animals. Milk electrical conductivity indicators ≥ 6 mS/cm were determined in 17.8−29.0% more animals in the group of lame cows compared to the group of non-lame cows. According to our study, we detected that blood cortisol concentration had the strongest positive correlation with milk electrical conductivity indicators. Cows with a greater lameness score had a higher cortisol content and milk conductivity.

Effect of lameness on feeding behavior of zero grazed Jersey dairy cows

The dairy industry faces major challenges with high levels of lameness, in parallel to an increased consumer focus on animal welfare. This encourages farmers to consider more robust breeds, such as Jersey cows. As little is known about the behavior of this breed under loose housing conditions, the present study sought to describe the feeding behavior of lame and non-lame Jersey cows in different parities. Such breed-specific information of behavioral changes is needed for breed-specific herd management decisions and may contribute to identifying animals that are susceptible to developing lameness in the future, thus reducing impacts on the welfare and production of cows. Feeding data from 116 Danish Jersey cows were collected using automatic feeders, and lameness status was assessed by technicians every second week. The cows were kept in a loose housing system, with cubicles, a slatted concrete floor, and automatic milking robots. Eating time per visit and per day, the number of visits per day, and intervals between meals were analyzed using generalized linear mixed effects models. The effect of lameness was not significant for any variable. Primiparous Jersey cows had significantly longer eating times per day, shorter meal intervals, and a lower number of visits per day than older Jersey cows. Week in lactation affected the eating time per visit and per day, the number of visits, and between-meal intervals. In conclusion, we found no differences between lame and non-lame Jersey cows but between parities, which disagree with previous research on other breeds, suggesting that Jersey cows not just differ in size and looks but also in their behavioral reaction when lame. Although data from only one herd of a research center were used, this study has demonstrated the need for further research about breed-specific differences and their implications for the health and welfare of the animals.

Identifying cow - level factors and farm characteristics associated with locomotion scores in dairy cows using cumulative link mixed models

Lameness is a tremendous problem in intensively managed dairy herds all over the world. It has been associated with considerable adverse effects on animal welfare and economic viability. The majority of studies have evaluated factors associated with gait disturbance by categorising cows into lame and non-lame. This procedure yet entails a loss of information and precision. In the present study, we extend the binomial response to five categories acknowledging the ordered categorical nature of locomotion assessments, which conserves a higher level of information. A cumulative link mixed modelling approach was used to identify factors associated with increasing locomotion scores. The analysis revealed that a low body condition, elevated somatic cell count, more severe hock lesions, increasing parity, absence of pasture access, and poor udder cleanliness were relevant variables associated with higher locomotion scores. Furthermore, distinct differences in the locomotion scores assigned were identified in regard to breed, observer, and season. Using locomotion scores rather than a dichotomised response variable uncovers more refined relationships between gait disturbances and associated factors. This will help to understand the intricate nature of gait disturbances in dairy cows more deeply.

Precision Technologies to Address Dairy Cattle Welfare: Focus on Lameness, Mastitis and Body Condition

Specific animal-based indicators that can be used to predict animal welfare have been the core of protocols for assessing the welfare of farm animals, such as those produced by the Welfare Quality project. At the same time, the contribution of technological tools for the accurate and real-time assessment of farm animal welfare is also evident. The solutions based on technological tools fit into the precision livestock farming (PLF) concept, which has improved productivity, economic sustainability, and animal welfare in dairy farms. PLF has been adopted recently; nevertheless, the need for technological support on farms is getting more and more attention and has translated into significant scientific contributions in various fields of the dairy industry, but with an emphasis on the health and welfare of the cows. This review aims to present the recent advances of PLF in dairy cow welfare, particularly in the assessment of lameness, mastitis, and body condition, which are among the most relevant animal-based indications for the welfare of cows. Finally, a discussion is presented on the possibility of integrating the information obtained by PLF into a welfare assessment framework.

[Curative claw trimming for mechanical relief of sole ulcers - an ex-vivo study]

OBJECTIVE

Overloading or excessive mechanical stress to the claws may damage the sensitive claw tissues and subsequently lead to sole ulcers. Corrective treatment can prevent complications of these sole ulcers. The aim of this study was to investigate the effects of a wedge-shaped relief incision from the bulb to the tip of the outer claw of the pelvic limb on the pressure distribution beneath the pertaining claw. Furthermore, it aimed to clarify whether a change in the pressure distribution would lead to dermal pressure relief in the area of a horn defect.

MATERIAL AND METHODS

Nineteen isolated bovine limbs from an abattoir were gradually trimmed resulting in following stages. A: initial condition; B: functional claw trimming, steps 1-3; C: extension of the model and drill of a circular lesion at the Rusterholz site (outer claw ulcer simulation); D: wedge shaped, weight-relieving incision from the bulb halfway towards the sole tip; E: further extension of the wedge-shaped incision towards the sole tip. The limbs were loaded with 200 kg following each of the procedures. A pressure sensor system was used in order to analyze the pressure distribution beneath the claws. Furthermore, positioning of the claws on a glass plate allowed for an evaluation of corium resp. fat cushion protrusion through the artificial lesion.

RESULTS

In the untrimmed claws, an average of 63 % of the total force applied rested on the outer claw area. This value decreased to 30 % following step E. Maximum pressure values shifted from the bulb area towards the sole tip with increasing degree of claw trimming. The relative loading area of the inner claw increased to up to 18.4 % following the procedures. The described incision technique (step E) resulted in a significant reduction of corium protrusion through the artificial horn defect in comparison to the claw situation in step C.

CONCLUSION

The wedge-shaped, weight-relieving incision (step E) led to pressure reduction in the area of the outer claw and the bulb region in this ex-vivo-study. Therefore, this trimming method may serve to relieve pressure from the vulnerable Rusterholz site as well as providing means for reducing corium compression.

CLINICAL RELEVANCE

The described trimming method facilitates pressure relief on the outer claw area in live animals. In this, it may exert a positive effect on disease progression in Rusterholz sole ulcers.

Associations between body condition score, locomotion score, and sensor-based time budgets of dairy cattle during the dry period and early lactation

Lameness, one of the most important disorders in the dairy industry, is related to postpartum diseases and has an effect on dairy cow welfare, leading to changes in cows' daily behavioral variables. This study quantified the effect of lameness on the daily time budget of dairy cows in the transition period. In total, 784 multiparous dairy cows from 8 commercial Dutch dairy farms were visually scored on their locomotion (score of 1-5) and body condition (score of 1-5). Each cow was scored in the early and late dry period as well as in wk 4 and 8 postpartum. Cows with locomotion scores 1 and 2 were grouped together as nonlame, cows with score 3 were considered moderately lame, and cows with scores 4 and 5 were grouped together as severely lame. Cows were equipped with 2 types of sensors that measured behavioral parameters. The leg sensor provided number of steps, number of stand-ups (moving from lying to standing), lying time, number of lying bouts, and lying bout length. The neck sensor provided eating time, number of eating bouts, eating bout length, rumination time, number of rumination bouts, and rumination bout length. Sensor data for each behavioral parameter were averaged between 2 d before and 2 d after locomotion scoring. The percentage of nonlame cows decreased from 63% in the early dry period to 46% at 8 wk in lactation; this decrease was more severe for cows with higher parity. Cows that calved in autumn had the highest odds for lameness. Body condition score loss of >0.75 point in early lactation was associated with lameness in wk 4 postpartum. Moderately lame cows had a reduction of daily eating time of around 20 min, whereas severely lame cows had a reduction of almost 40 min. Similarly, moderately and severely lame dry cows showed a reduction of 200 steps/d, and severely lame cows in lactation showed a reduction of 600 steps/d. Daily lying time increased by 26 min and lying bout length increased by 8 min in severely lame cows compared with nonlame cows. These results indicate a high prevalence of lameness on Dutch dairy farms, with an increase in higher locomotion scores from the dry period into early lactation. Time budgets for multiparous dairy cows differed between the dry period and the lactating period, with a higher locomotion score (increased lameness) having an effect on cows' complete behavioral profile. Body condition score loss in early lactation was associated with poor locomotion postpartum, whereas lameness resulted in less eating time in the dry period and early lactation, creating a harmful cycle.

A Review: Development of Computer Vision-Based Lameness Detection for Dairy Cows and Discussion of the Practical Applications

The computer vision technique has been rapidly adopted in cow lameness detection research due to its noncontact characteristic and moderate price. This paper attempted to summarize the research progress of computer vision in the detection of lameness. Computer vision lameness detection systems are not popular on farms, and the accuracy and applicability still need to be improved. This paper discusses the problems and development prospects of this technique from three aspects: detection methods, verification methods and application implementation. The paper aims to provide the reader with a summary of the literature and the latest advances in the field of computer vision detection of lameness in dairy cows.

Factors Associated With Lameness in Tie Stall Housed Dairy Cows in South Germany

Lameness remains a major concern for animal welfare and productivity in modern dairy production. Even though a trend toward loose housing systems exists and the public expects livestock to be kept under conditions where freedom of movement and the expression of natural behavior are ensured, restrictive housing systems continue to be the predominant type of housing in some regions. Factors associated with lameness were evaluated by application of multiple logistic regression modeling on data of 1,006 dairy cows from 56 tie stall farms in Bavaria, South Germany. In this population, approximately every fourth cow was lame (24.44% of scored animals). The mean farm level prevalence of lameness was 23.28%. In total, 22 factors were analyzed regarding their association with lameness. A low Body Condition Score (BCS) (OR 1.54 [95%-CI 1.05-2.25]) as well as increasing parity (OR 1.41 [95%-CI 1.29-1.54]) entailed greater odds of lameness. Moreover, higher milk yield (OR 0.98 [95%-CI 0.96-1.00]) and organic farming (OR 0.48 [95%-0.25-0.92]) appeared to be protectively associated with lameness. Cows with hock injuries (OR 2.57 [95%-CI 1.41-4.67]) or with swellings of the ribs (OR 2.55 [95%-CI 1.53-4.23]) had higher odds of lameness. A similar association was observed for the contamination of the lower legs with distinct plaques of manure (OR 1.88 [95%-CI 1.14-3.10]). As a central aspect of tie stall housing, the length of the stalls was associated with lameness; with stalls of medium [(>158-171 cm) (OR 2.15 [95%-CI 1.29-3.58]) and short (≤158 cm) length (OR 4.07 [95%-CI 2.35-7.05]) increasing the odds compared with long stalls (>171 cm). These results can help both gaining knowledge on relevant factors associated with lameness as well as approaching the problem of dairy cow lameness in tie stall operations.

Evaluating the association between early-lactation lying behavior and hoof lesion development in lactating Jersey cows

Objectives were to evaluate the association between behavior and hoof lesions (HL) in lactating dairy cows. Jersey cows without any visible HL on all 4 legs were enrolled at 20 ± 3 d in milk (DIM), examined for body condition score (BCS), and had an automatic activity monitor (AfiTag II, AfiMilk, Afikim, Israel) attached to their right hind leg. At 120 ± 3 DIM, activity monitors were removed and cows were re-examined for HL and BCS. Cows were classified according to HL status as either healthy or with HL at d 120. Because sole hemorrhage (SH) accounted for over 80% of HL on d 120, SH was reclassified according to the number of feet affected. Daily activity data (daily lying duration, lying bouts, lying bout duration, and number of steps) of 344 cows collected between d 20 and d 120 were analyzed using restricted maximum likelihood linear mixed models with an autoregressive covariance structure. Separate models were built to include specific activities, HL status at d 120, DIM, interaction between lesion status at d 120 and DIM, parity, season of calving, and BCS change from d 20 to d 120 as fixed effects. Cow was included in all models as random effect. Incidence of HL at d 120 was 58.4% (n = 201 out of 344). Compared with healthy cows, cows with HL at d 120 had reduced daily lying duration (-0.53 h; 95% CI: -0.78 to -0.28 h) in the early postpartum period. We found no evidence for a difference in number of lying bouts (0.41; 95% CI: -0.76 to 1.59;), lying bout duration (-3.04 min; 95% CI: -6.6 to 0.49), and number of steps (62.14; 95% CI: -89.62 to 213.91) between cows that remained healthy and those that developed HL. Compared with healthy cows, cows that developed SH in 1 or more feet had reduced daily lying duration in the early postpartum period. Irrespective of lesion status at d 120, daily lying duration and lying bout duration increased from d 20 to d 120, whereas lying bout number and number of steps decreased from d 20 to d 120. We concluded that cows that developed HL had a reduced daily lying duration in the early postpartum period. Therefore, reduced daily lying duration should be considered a risk factor for HL development in lactating dairy cows.

Accurate detection of lameness in dairy cattle with computer vision: A new and individualized detection strategy based on the analysis of the supporting phase

Lameness has a considerable influence on the welfare and health of dairy cows. Many attempts have been made to develop automatic lameness detection systems using computer vision technology. However, these detection methods are easily affected by the characteristics of individual cows, resulting in inaccurate detection of lameness. Therefore, this study explores an individualized lameness detection method for dairy cattle based on the supporting phase using computer vision. This approach is applied to eliminate the influence of the characteristics of individual cows and to detect lame cows and lame hooves. In this paper, the correlation coefficient between lameness and the supporting phase is calculated, a lameness detection algorithm based on the supporting phase is proposed, and the accuracy of the algorithm is verified. Additionally, the reliability of this method using computer vision technology is verified based on deep learning. One hundred naturally walking cows are selected from video data for analysis. The results show that the correlation between lameness and the supporting phase was 0.864; 96% of cows were correctly classified, and 93% of lame hooves were correctly detected using the supporting phase-based lameness detection algorithm. The mean average precision is 87.0%, and the number of frames per second is 83.3 when the Receptive Field Block Net Single Shot Detector deep learning network was used to detect the locations of cow hooves in the video. The results show that the supporting phase-based lameness detection method proposed in this paper can be used for the detection and classification of cow lameness and the detection of lame hooves with high accuracy. This approach eliminates the influence of individual cow characteristics and could be integrated into an automatic detection system and widely applied for the detection of cow lameness.

Predicting Disease in Transition Dairy Cattle Based on Behaviors Measured Before Calving

Simple Summary

Dairy cattle often become ill after calving. We developed models designed to predict which cows are likely to become ill based upon measures of the cows’ feeding and competitive behaviors before calving. Our models had high sensitivity (73–71%), specificity (80–84%), positive predictive values (73–77%), and negative predictive values (80–80%) for both cows that had previously calved and for those calving for the first time. We conclude that behaviors at the feed bunk before calving can predict cows at risk of becoming sick in the weeks after calving.

Abstract

Dairy cattle are particularly susceptible to metritis, hyperketonemia (HYK), and mastitis in the weeks after calving. These high-prevalence transition diseases adversely affect animal welfare, milk production, and profitability. Our aim was to use prepartum behavior to predict which cows have an increased risk of developing these conditions after calving. The behavior of 213 multiparous and 105 primiparous Holsteins was recorded for approximately three weeks before calving by an electronic feeding system. Cows were also monitored for signs of metritis, HYK, and mastitis in the weeks after calving. The data were split using a stratified random method: we used 70% of our data (hereafter referred to as the “training” dataset) to develop the model and the remaining 30% of data (i.e., the “test” dataset) to assess the model’s predictive ability. Separate models were developed for primiparous and multiparous animals. The area under the receiver operating characteristic (ROC) curve using the test dataset for multiparous cows was 0.83, sensitivity and specificity were 73% and 80%, positive predictive value (PPV) was 73%, and negative predictive value (NPV) was 80%. The area under the ROC curve using the test dataset for primiparous cows was 0.86, sensitivity and specificity were 71% and 84%, PPV was 77%, and NPV was 80%. We conclude that prepartum behavior can be used to predict cows at risk of metritis, HYK, and mastitis after calving.

Symposium review: The impact of management and facilities on cow culling rates

This symposium review examines the association between comfort and cow longevity, with a particular emphasis on optimizing resting behavior in confinement-housed systems. Housed dairy cattle demonstrate a variety of negative behavioral and physiological effects when lying time is restricted, with cows prioritizing the recovery of rest over feeding when both are deprived. There is, however, wide individual-cow variation in daily lying times, influenced by an array of cow-, housing-, and management-related factors. Cow-related factors include individual preference, parity, stage of lactation cycle, milk yield, ill health, and lameness. Lying time tends to increase with age and days in milk and during periods of ill health, whereas milk yield is negatively correlated with lying time. The effect of lameness is complicated by severity and by interactions with bedding type, which modifies the cows' ability to rise and lie down. Generally, lame cows suffer prolonged lying bouts of greater variability in length and take fewer bouts per day. Often this results in an overall increase in lying time. Thus, higher standards of cow comfort and improved cow health are not always reflected by longer lying times. Housing and management factors that influence resting behavior include the design of the resting area, access to the resting space, and the thermal microenvironment of the lying area. Provision of dry, deep loose bedding, stocking cows to allow each animal access to a resting space, allowing sufficient time to access the resting area, and providing heat abatement to reduce heat load optimize resting behavior. Because lameness and poor body condition are commonly found in culled dairy cattle, the link between cow comfort and culling is likely mediated through lameness onset and management. Optimal comfort helps prevent the onset of lameness and facilitates recovery once cows become lame, which limits the effect of lameness on feeding behavior and reduces the risk for other health-related disorders, poor reproductive performance, and early herd removal. Cow comfort cannot be assessed by measuring the duration of lying time alone. Rather, comfort is reflected by the optimization of resting behavior, providing facilities and management to allow cows to lie down when they choose to do so for as long as they need to.

The relationship between transition period diseases and lameness, feeding time, and body condition during the dry period

In this longitudinal study, we tested the hypothesis that cows that are lame around dry-off are at increased risk of transition diseases (TD), including metritis, subclinical ketosis (SCK), retained fetal membranes, hypocalcemia, or displaced abomasum. We also hypothesized that the relationship between lameness and TD would be mediated through reduced feeding time. We enrolled 461 cows at 9 wk before their expected calving date on 6 commercial freestall farms in the lower Fraser Valley, British Columbia, Canada. Cows were gait-scored weekly using a scale of 1 to 5. Lameness status was classified based on consecutive gait scores as lame (2 consecutive gait scores = 3 or 1 score ≥4) or sound (2 consecutive gait scores ≤2). Lameness status was summarized as (1) lameness at dry-off (sound or lame); (2) lameness group (always sound = sound on all visits, chronically lame = lame on all visits, and other = changed from sound to lame or vice versa); and (3) proportion of weeks lame during the dry period. Body condition scores were recorded at dry-off and at calving and collectively used to calculate change in body condition for each cow. A subsample of cows (n = 159) was evaluated for feeding time once a week during the dry period. All cows were evaluated for SCK (positive = β-hydroxybutyrate ≥1.2 mmol/L) and metritis (positive = foul smell, red/brown watery vaginal discharge) every 3 to 4 d between d 3 and 17 after calving. We retrieved data on treatment of retained fetal membranes, hypocalcemia, and displaced abomasum during the first 17 d after calving, cow parity, and milk production in the previous lactation from farm records. We created a binary variable, TD (any of SCK, metritis, retained fetal membranes, hypocalcemia, or displaced abomasum), to differentiate between healthy cows and cows that developed TD. Lameness at dry-off was associated with the occurrence of metritis and TD, but not with SCK. Cows that were chronically lame and cows that had an increased proportion of weeks lame during the dry period had higher occurrence of metritis and TD. Lameness was also associated with reduced feeding time, which in turn was associated with increased likelihood of SCK and TD, but not with metritis. Lameness was not associated with change in body condition; however, cows that lost body condition score during the dry period had increased odds of developing SCK, metritis, and TD. Change in body condition was highly associated with body condition score at dry-off. These results suggest that association between lameness and TD is partially mediated through reduced feeding time.

Factors associated with lameness prevalence in lactating cows housed in freestall and compost-bedded pack dairy farms in southern Brazil

The aim of this cross-sectional study was to investigate factors associated with lameness in dairy cows on intensive farms in southern Brazil. Farms (freestall: n = 38; compost-bedded pack: n = 12) having on average 274 (range: 41-901) lactating cows were visited once in 2016 (March to October). Potential risk factors for lameness at the cow, pen and herd levels were investigated through inspection of facilities, examination of cows and the use of data collected on routine management practices. All milking cows on each farm were assessed for gait score and BCS (n = 13,716). Associations between lameness, days in milk (DIM), BCS, parity, and test-day milk yield were investigated in 16 farms with available data (n = 5,301 cows). Mixed-effects linear and logistic regressions were used to model the data. Within-herd lameness prevalence was 41.1% (range: 13.8-64.5, SD = 11.3). First- and second-lactation cows after 120 DIM and older cows after 335 DIM were more likely to be observed lame than early lactation cows. Greater parity and low BCS (≤ 2.75) were associated with increased odds of lameness. Severely lame cows had lower milk yield (on average 1.3 kg/d) than non-lame cows. Freestall dairies using mattresses as stall base had greater within-pen (95% CI: 52-69%) and herd-level (38-57%) lameness prevalence than compost-bedded farms. Higher lameness prevalence was observed on farms having slippery feed bunk alley floors (32-49%) and shortened dry periods (< 60 days: 32-42%). First-lactation pens had lower predicted within-pen lameness prevalence (0-4%) and special-needs pens higher (52-73%) compared with the prevalence observed in compost-bedded fresh-cow pens (19-41%). Freestall pens using sawdust deep-bedding had greater (46-68%) within-pen lameness prevalence, but the prevalence in barns using sand was not different from compost-bedded farms. Given the high lameness prevalence observed in this study, there is a great opportunity for implementation of lameness prevention programs. Providing walking surfaces with high traction that facilitates mobility and using soft and deep-bedded material, such as compost and sand (and avoiding the use of mattresses) may reduce lameness prevalence in the types of dairy farms visited in this study.