Scoping review on clinical definition of bovine respiratory disease complex and related clinical signs in dairy cows

Learning end-to-end respiratory rate prediction of dairy cows from RGB videos

Respiratory rate (RR) is an important indicator of the health and welfare status of dairy cows. In recent years, progress has been made in monitoring the RR of dairy cows using video data and learning methods. However, existing approaches often involve multiple processing modules, such as region of interest (ROI) detection and tracking, which can introduce errors that propagate through successive steps. The objective of this study was to develop an end-to-end computer vision method to predict RR of dairy cows continuously and automatically. The method leverages the capabilities of a state-of-the-art Transformer model, VideoMAE, which divides video frames into patches as input tokens, enabling the automated selection and featurization of relevant regions, such as a cow's abdomen, for predicting RR. The original encoder of VideoMAE was retained, and a classification head was added on top of it. Further, the weights of the first 11 layers of the pre-trained model were kept, while the weights of the final layer and classifier were fine-tuned using video data collected in a tie-stall barn from 6 dairy cows. Respiratory rates measured using a respiratory belt for individual cows were serving as the ground truth (GT). The evaluation of the developed model was conducted using multiple metrics, including mean absolute error (MAE) of 2.58 breaths per minute (bpm), root mean squared error (RMSE) of 3.52 bpm, root mean squared prediction error (RMSPE; as a proportion of observed mean) of 15.03%, and Pearson correlation (r) of 0.86. Compared with a conventional method involving multiple processing modules, the end-to-end approach performed better in terms of MAE, RMSE and RMSPE. These results suggest the potential to implement the developed computer vision method for an end-to-end solution, for monitoring RR of dairy cows automatically in a tie-stall setting. Future research on integrating this method with other behavioral detection and animal identification algorithms for animal monitoring in a free-stall dairy barn can be beneficial for a broader application.

Early detection of bovine respiratory disease in pre-weaned dairy calves using sensor based feeding, movement, and social behavioural data

Previous research shows that feeding and activity behaviours in combination with machine learning algorithms has the potential to predict the onset of bovine respiratory disease (BRD). This study used 229 novel and previously researched feeding, movement, and social behavioural features with machine learning classification algorithms to predict BRD events in pre-weaned calves. Data for 172 group housed calves were collected using automatic milk feeding machines and ultrawideband location sensors. Health assessments were carried out twice weekly using a modified Wisconsin scoring system and calves were classified as sick if they had a Wisconsin score of five or above and/or a rectal temperature of 39.5 °C or higher. A gradient boosting machine classification algorithm produced moderate to high performance: accuracy (0.773), precision (0.776), sensitivity (0.625), specificity (0.872), and F1-score (0.689). The most important 30 features were 40% feeding, 50% movement, and 10% social behavioural features. Movement behaviours, specifically the distance walked per day, were most important for model prediction, whereas feeding and social features aided in the model's prediction minimally. These results highlighting the predictive potential in this area but the need for further improvement before behavioural changes can be used to reliably predict the onset of BRD in pre-weaned calves.

Serological Profile for Major Respiratory Viruses in Unvaccinated Cows from High-Yielding Dairy Herds

This study aims to determine the serological profile of high-yielding dairy cows for four main viruses (bovine alphaherpesvirus 1 (BoAHV1), bovine viral diarrhea virus (BVDV), bovine parainfluenza virus 3 (BPIV3), and bovine respiratory syncytial virus (BRSV)) related to bovine respiratory disease (BRD) in cattle herds worldwide. In this survey, 497 blood serum samples were collected from non-vaccinated dairy cows without clinical respiratory signs in 39 herds in the central-eastern mesoregion of Paraná State, South Brazil. The presence of neutralizing antibodies was determined by virus neutralization (VN) tests. VN antibodies against BoAHV1, BVDV, BPIV3, and BRSV were detected in 355 (71.4%), 280 (56.3%), 481 (96.8%), and 315 (63.4%) serum samples, respectively. The frequencies of seropositive herds for BoAHV1, BVDV, BPIV3, and BRSV were 79.5 (n = 31), 82.0 (n = 32), 100 (n = 39), and 84.6% (n = 33), respectively. The frequencies of seropositive cows varied according to the type of herd management and the number of cows in the herd. The detection of VN antibodies in unvaccinated dairy cattle herds demonstrated the endemic circulation of the four viruses in the herds evaluated. For BRD prevention, it is recommended to implement a vaccination program for cows that provides passive immunity in calves and active immunity in cows.

Strategies for Bovine Respiratory Disease (BRD) Diagnosis and Prognosis: A Comprehensive Overview

Despite significant advances in vaccination strategies and antibiotic therapy, bovine respiratory disease (BRD) continues to be the leading disease affecting the global cattle industry. The etiology of BRD is complex, often involving multiple microbial agents, which lead to intricate interactions between the host immune system and pathogens during various beef production stages. These interactions present environmental, social, and geographical challenges. Accurate diagnosis is essential for effective disease management. Nevertheless, correct identification of BRD cases remains a daunting challenge for animal health technicians in feedlots. In response to current regulations, there is a growing interest in refining clinical diagnoses of BRD to curb the overuse of antimicrobials. This shift marks a pivotal first step toward establishing a structured diagnostic framework for this disease. This review article provides an update on recent developments and future perspectives in clinical diagnostics and prognostic techniques for BRD, assessing their benefits and limitations. The methods discussed include the evaluation of clinical signs and animal behavior, biomarker analysis, molecular diagnostics, ultrasound imaging, and prognostic modeling. While some techniques show promise as standalone diagnostics, it is likely that a multifaceted approach-leveraging a combination of these methods-will yield the most accurate diagnosis of BRD.

The Role of Mycoplasma bovirhinis in the Development of Singular and Concomitant Respiratory Infections in Dairy Calves from Southern Brazil

The role of Mycoplasma bovirhinis in the development of pulmonary disease in cattle is controversial and was never evaluated in cattle from Latin America. This study investigated the respiratory infection dynamics associated with M. bovirhinis in suckling calves from 15 dairy cattle herds in Southern Brazil. Nasal swabs were obtained from asymptomatic (n = 102) and calves with clinical manifestations (n = 103) of bovine respiratory disease (BRD) and used in molecular assays to identify the specific genes of viral and bacterial disease pathogens of BRD. Only M. bovirhinis, bovine coronavirus (BCoV), ovine gammaherpesvirus 2 (OvGHV2), Histophilus somni, Pasteurella multocida, and Mannheimia haemolytica were detected. M. bovirhinis was the most frequently diagnosed pathogen in diseased (57.8%; 59/102) and asymptomatic (55.3%; 57/103) calves at all farms. BCoV-related infections were diagnosed in diseased (52%; 53/102) and asymptomatic (51.4%; 53/103) calves and occurred in 93.3% (14/15) of all farms. Similarly, infectious due to OvGHV2 occurred in diseased (37.2%; 38/102) and asymptomatic (27.2%; /28/103) calves and were diagnosed in 80% (12/15) of all farms investigated. Significant statistical differences were not identified when the two groups of calves were compared at most farms, except for infections due to OvGHV2 that affected five calves at one farm. These results demonstrated that the respiratory infection dynamics of M. bovirhinis identified in Southern Brazil are similar to those observed worldwide, suggesting that there is not enough sufficient collected data to consider M. bovirhinis as a pathogen of respiratory infections in cattle. Additionally, the possible roles of BCoV and OvGHV2 in the development of BRD are discussed.

Serological profile of respiratory viruses in unvaccinated steers upon their arrival at Brazilian feedlot facilities

Bovine viral diarrhea virus (BVDV), bovine alphaherpesvirus 1 (BoAHV1), bovine respiratory syncytial virus (BRSV), and bovine parainfluenza virus 3 (BPIV-3) are involved in bovine respiratory disease. These viruses can infect the respiratory system and cause considerable economic losses to beef and dairy cattle herds. This study aimed to determine the serological profiles of steers for BVDV, BoAHV1, BRSV, and BPIV-3 upon their arrival at Brazilian feedlot facilities. A total of 1,282 serum samples from unvaccinated steers were obtained on the first day of feeding. Samples were collected from 31 beef cattle herds reared in an extensive rearing system in six Brazilian states. Antibodies against BVDV, BoAHV1, BRSV, and BPIV-3 were detected using a virus neutralization test. The steers were distributed in agreement with their age and the Brazilian state of origin. The highest seropositivity was for BoAHV1 and BPIV-3 at 92.1% (1,154/1,253) and 86.6% (1,100/1,270), respectively. The seropositivity of BRSV was 77.1% (959/1,244). BVDV presented a lower rate, at slightly more than 50% (51.8%; 656/1,266). Age was a risk factor for the presence of antibodies against BVDV, BoAHV1, and BPIV-3 but not BRSV. A positive correlation was identified between BoAHV1 and BPIV-3 (P = 0.85) and between BRSV and BPIV-3 (P = 0.47). The high rate of seropositive steers for these four respiratory viruses on the first day of confinement identified in this serological survey provides important epidemiological information on respiratory infections, as the seropositivity of the four main bovine respiratory viruses in Brazilian beef cattle herds in an extensive rearing system.

Environmental and biological factors that influence feeding behavior of Holstein calves in automated milk feeding systems

Automated milk feeders (AMF) used for dairy calves continuously provide individual feeding behavior measurements. The objective of this retrospective cohort study was to evaluate the association between temperature-humidity index (THI), birth weight, and dam parity characteristics on feeding behavior (i.e., milk consumption and drinking speed). Historical data sets generated from a single commercial dairy farm, where healthy (not treated for bovine respiratory disease, enteric disease, or injury) Holstein calves were fed up to 24 L/d of milk, were used for the analysis. A total of 5,312 female Holstein calves born between August 2015 and August 2021 (mean birth weight ± standard deviation: 40.7 ± 4.7 kg) on a commercial dairy farm were fed up to 24 L/d of nonsaleable milk for the first 32 d. For the analyses, feeding behavior data from the AMF system were combined with demographic data from the farm management software, and weather records from the closest public weather station (7 km away). Linear mixed models used to analyze daily milk consumption and drinking speed included THI, birth weight, dam parity, and feeding day as fixed effects, and feeder and calf within feeder as random effects. These models explained 57% of the total variation in milk consumption and 48% of the variation in drinking speed. Calves born from primiparous cows had the lowest milk consumption and the greatest drinking speed in comparison to calves born from multiparous cows. Calves with heavier birth weights had higher milk consumption and faster drinking speed than lighter calves. Drinking speed was negatively associated with THI. Including data derived from individual calves and their environmental conditions in data sets exploring feeding behavior from AMF would control for variation and improve the predictive models for performance assessment.

Monitoring the respiratory behavior of multiple cows based on computer vision and deep learning

Automatic respiration monitoring of dairy cows in modern farming not only helps to reduce manual labor but also increases the automation of health assessment. It is common for cows to congregate on farms, which poses a challenge for manual observation of cow status because they physically occlude each other. In this study, we propose a method that can monitor the respiratory behavior of multiple cows. Initially, 4,000 manually labeled images were used to fine-tune the YOLACT (You Only Look At CoefficienTs) model for recognition and segmentation of multiple cows. Respiratory behavior in the resting state could better reflect their health status. Then, the specific resting states (lying resting, standing resting) of different cows were identified by fusing the convolutional neural network and bidirectional long and short-term memory algorithms. Finally, the corresponding detection algorithms (lying and standing resting) were used for respiratory behavior monitoring. The test results of 60 videos containing different interference factors indicated that the accuracy of respiratory behavior monitoring of multiple cows in 54 videos was >90.00%, and that of 4 videos was 100.00%. The average accuracy of the proposed method was 93.56%, and the mean absolute error and root mean square error were 3.42 and 3.74, respectively. Furthermore, the effectiveness of the method was analyzed for simultaneous monitoring of respiratory behavior of multiple cows under movement, occlusion disturbance, and behavioral changes. It was feasible to monitor the respiratory behavior of multiple cows based on the proposed algorithm. This study could provide an a priori technical basis for respiratory behavior monitoring and automatic diagnosis of respiratory-related diseases of multiple dairy cows based on biomedical engineering technology. In addition, it may stimulate researchers to develop robots with health-sensing functions that are oriented toward precision livestock farming.

Voluntary Biosurveillance of Streptococcus equi Subsp. equi in Nasal Secretions of 9409 Equids with Upper Airway Infection in the USA

This study aimed to describe selected epidemiological aspects of horses with acute onset of fever and respiratory signs testing qPCR-positive for S. equi and to determine the effect of vaccination against S. equi on qPCR status. Horses with acute onset of fever and respiratory signs from all regions of the United States were included in a voluntary biosurveillance program from 2008 to 2020 and nasal secretions were tested via qPCR for S. equi and common respiratory viruses. A total of 715/9409 equids (7.6%) tested qPCR-positive for S. equi, with 226 horses showing coinfections with EIV, EHV-1, EHV-4, and ERBV. The median age for the S. equi qPCR-positive horses was 8 ± 4 years and there was significant difference when compared to the median age of the S. equi qPCR-negative horses (6 ± 2 years; p = 0.004). Quarter Horse, Warmblood, and Thoroughbred were the more frequent breed in this horse population, and these breeds were more likely to test qPCR-positive for S. equi compared to other breeds. There was not statistical difference for sex between S. equi qPCR-positive and qPCR-negative horses. Horses used for competition and ranch/farm use were more likely to test qPCR-positive for S. equi (p = 0.006). Horses that tested S. equi qPCR-positive were more likely to display nasal discharge, fever, lethargy, anorexia, and ocular discharge compared to horses that tested S. equi qPCR-negative (p = 0.001). Vaccination against S. equi was associated with a lower frequency of S. equi qPCR-positive status.

Risk factors associated with indicators of dairy cow welfare during the housing period in Irish, spring-calving, hybrid pasture-based systems

In a dairy production system where cows are grazing for a large portion of their lactation, little attention has been afforded to investigating multiple indicators of welfare for risk factors associated with the housing period. Yet regardless of the length of the housing period, cows still experience the positive and negative welfare impacts of both indoor and outdoor environments in a hybrid system. Thus, the objective of this study was to identify risk factors for indicators of dairy cow welfare during the housing period in a spring-calving, hybrid pasture-based system. Herd-level scores for seven indicators of welfare (locomotion, body condition, ocular and nasal discharge, integument damage, tail injury and human avoidance response) were collected from 82 Irish dairy farms during the housing period (October - February). Data were analysed using multiple beta regression or zero-inflated beta regression to identify associations between these welfare indicators and measured herd-level housing, resource and management factors. Thirty-six unique risk factors were associated with one or more welfare indicators (P < 0.05). Analyses identified two risk factors for body condition < 3.0 and four for body condition > 3.5, the target range during the housing period. Four risk factors were identified for each of ocular discharge, nasal discharge and avoidance response of > 1 m from human approach. Six risk factors each were associated with the proportion of lame cows and integument damage to the head-neck-back or hindquarter regions. The greatest number of risk factors, 12, were associated with tail injury (broken, lacerated or incomplete tails). Risk factors associated with multiple indicators of welfare were cow comfort index (tail lacerations and hindquarter integument damage), cubicle width (broken and incomplete tails), shed floor slipperiness (lameness and head-neck-back integument damage), shed light-level (tail lacerations, avoidance response and below target body condition), shed passage width (broken tails and head-neck-back integument damage) and presence (incomplete tails) or absence (broken tails) of a collecting yard backing gate. With the large number of risk factors associated with tail injury, continued research is necessary to identify causes and determine prevention methods to contribute to improved overall welfare of dairy cows. Housing features meeting recommended guidelines from the literature were frequently associated with greater negative indicators of welfare. In light of this, housing guidelines may benefit from regular re-evaluation to ensure facilities meet the welfare needs of cows during the housing period.

Review of Associated Health Benefits of Algal Supplementation in Cattle with Reference to Bovine Respiratory Disease Complex in Feedlot Systems

Within the Australian beef industry bovine respiratory disease is considered one of the most common disease and costs the industry an average net loss of $1647.53 Australian dollars per animal death to bovine respiratory disease complex (BRD). This is due to the disease overwhelming the animal’s immune system during a period where they experience multiple stressors that consequently increase the animal’s susceptivity to disease. Research into the bioactive compounds commonly found in marine algae is rapidly increasing due to its positive health benefits and potential immune modulating properties. Algal supplementation within previous studies has resulted in improved reproduction potential, growth performance, increases antioxidant activity and decreased proinflammatory cytokine concentrations. Additional research is required to further understand the aetiology of BRD and complete analysis of the bioavailability of these bioactive compounds within marine algae to fully explore the potential of marine algae supplementation.