Artificial Intelligence (AI) is being increasingly used for equid health and welfare. This study aimed to establish consensus on where and how AI should be developed to achieve maximum benefit in this field. A workshop involving 41 stakeholders generated statements about current welfare concerns, areas for AI development, and barriers and solutions to AI use. Statements were circulated through Delphi surveys (acceptance set at 75% agreement). One-hundred-and-six statements reached agreement. Ethological needs not being met and poor equid management practices were key welfare concerns. Participants identified that insufficient owner/carer knowledge and understanding were important factors contributing to welfare concerns. Priority areas for AI development included assessment of equid wellbeing, as well as individual and population-level monitoring. Barriers included limited understanding of both equine behaviour and AI, biased, unethical, or insufficient data collection, difficulties developing accurate models, challenges to validation, and uncertainty around interpretation. Proposed solutions included development of evidence-based, unbiased AI systems, following best practice guidelines, requiring approval/regulation of AI tools, collaboration, and education of AI users. This is the first study to identify stakeholders’ opinions about where AI is likely to have the greatest benefit for equids, potential barriers, and solutions. The findings should be used to prioritise funding and development.

Antimicrobial use (AMU) data are essential for monitoring usage over time, facilitating reduction strategies to combat the threat of antimicrobial resistance (AMR) to both human and animal health. The objective of this study was to measure and describe AMU over a 12-mo period in Irish dairy herds and compare 3 different recording methods to a reference method. A sample of 33 Irish dairy herds were randomly selected from 6 private veterinary practices across Ireland. The herds were followed for a 12-mo period and their AMU was monitored using 3 recording methods: 1. Veterinary prescription data (VET), 2. The inventory of medicine bins on the farms (BIN), and 3. Farmer treatment records from herd recording software (APP). Each recording method was compared with a previously developed reference method for AMU. The reference method used was based on pre- and poststudy medicine stock on the farms combined with veterinary prescription data. Antimicrobial use was analyzed using both mass- and dosed-based metrics, including mass (mg) of antimicrobial active ingredient per population correction unit (mg/PCU), defined daily doses for animals (DDDVET) and defined course doses for animals (DCDVET). Median AMU was 16.24, 10.47, 8.87 and 15.55 mg/PCU by mass, and 2.43, 1.55, 1.19 and 2.26 DDDVET by dose for VET, BIN, APP, and reference method data, respectively. Reliability of the agreement between each pair of methods was quantified using the concordance correlation coefficient (CCC). When compared with the reference method, VET data had excellent reliability [95% confidence interval (CI) of CCC: 0.992–0.998]. The BIN data had good to excellent reliability [95% CI of CCC: 0.776–0.936]. The APP data had poor reliability when compared with the reference method [95% CI of CCC: −0.167–0.156]. Our results highlight that a small number of herds were contributing most to overall use and farmers showed varying levels of consistency in recording AMU. Veterinary data were the most reliable approach for assessing AMU when compared with a reference method of AMU. This is an important finding for the future monitoring of AMU at a national level.

Abstract The experience of dairy cows in housed conditions is an important topic both internally and externally for the dairy industry. The term positive welfare is becoming more commonly used but is a complex subject. The environment an animal inhabits will have a direct impact on health, well-being and production. Living space, the baseline metric for space provision, is highly variable across dairy farms. Current positive welfare initiatives include the use of environmental enrichment, novel stimuli and choice. A method to objectively measure welfare is urgently required to aid the evaluation of a cow’s environment. It can be extremely challenging for vets and farmers to monitor behaviours associated with positive affective states continuously and objectively. The main research areas of focus for exploration of how to improve welfare for housed dairy cows are described in detail. These are assessment (split between the ‘-omics’ and computer vision) and infrastructure provision (living space and environmental enrichment in housing). This key research area has the potential to significantly improve cow health, production and welfare through optimisation of their living conditions. The utilisation of novel technological advancements in artificial intelligence alongside similar step changes in gene expression assessment, provides the potential to revolutionise management practices for livestock. Information © The Authors 2025

One suggested approach to improve the reproductive performance of dairy herds is through the targeted management of subgroups of biologically similar animals, such as those with similar probabilities of becoming pregnant, termed pregnancy risk. We aimed to use readily available farm data to develop predictive models of pregnancy risk in dairy cows.Data from a convenience sample of 108 dairy herds in the UK were collated and each herd was randomly allocated, at a ratio of 80:20, to either training or testing data sets. Following data cleaning, there were a total of 78 herds in the training data set and 20 herds in the testing data set. Data were further split by parity into nulliparous, primiparous, and multiparous subsets. An XGBoost model was trained to predict the insemination outcome in each parity subset, with predictors from farm records of breeding, calving and milk recording. Training data comprised 74,511 inseminations in 45,909 nulliparous animals, 86,420 inseminations in 39,439 primiparous animals, and 158,294 inseminations in 32,520 multiparous animals. The final models were evaluated by predicting with the testing data, comprising 31,740 inseminations in 19,647 nulliparous animals, 38,588 inseminations in 16,215 primiparous animals, and 65,049 inseminations in 12,439 multiparous animals. Model discrimination was assessed by calculating the area under receiver operating characteristic curves (AUC); model calibration was assessed by plotting calibration curves and compared across test herds by calculating the expected calibration error (ECE) in each test herd.The models were unable to discriminate between insemination outcomes with high accuracy, with an AUC of 0.63, 0.59 and 0.62 in the nulliparous, primiparous and multiparous subsets, respectively. The models were generally well-calibrated, meaning the model-predicted pregnancy risks were similar to the observed pregnancy risks. The mean (SD) ECE in the test herds was 0.038 (0.023), 0.028 (0.012) and 0.020 (0.008) in the nulliparous, primiparous and multiparous subsets respectively.The predictive models reported here could theoretically be used to identify subgroups of animals with similar pregnancy risk to facilitate targeted reproductive management; or provide information about cows' relative pregnancy risk compared with the herd average, which may support on-farm decision-making. Further research is needed to evaluate the generalizability of these predictive models and understand the source of variation in ECE between herds; however, this study demonstrates that it is possible to accurately predict pregnancy risk in dairy cows using readily available farm data.

Paratuberculosis (Johne’s disease), caused by Mycobacterium avium subsp. paratuberculosis (MAP), is a common, economically-important and potentially zoonotic contagious disease of cattle, with worldwide distribution. Disease management relies on identification of animals which are at high-risk of being infected or infectious. The disease is chronic in nature, and infected animals may be infectious in the absence of overt clinical signs. Coupled with limited sensitivity of available diagnostic tests, this creates difficulties in identifying high-risk animals. In some disease-control programmes, dairy cows are classified with regards to risk according to the results of serial tests which quantify MAP antibodies in milk samples. Such classification systems are limited by the influence of non-disease factors on test results, dichotomisation of continuous results into “positive” or “negative” according to an imperfect threshold, and subjectivity in defining which patterns of serial test results indicate different risk-categories. An unsupervised learning (clustering) approach was applied to paratuberculosis test results and milk-recording data collated from 47 farms over an approximately ten-year period between 2010 and 2021. Paratuberculosis test results were first adjusted according to influential non-disease factors using linear models. Continuous-time hidden Markov models were fit to the adjusted test results. The final model revealed four distinct latent states (clusters). Examination of the distribution of adjusted test results associated with each latent state suggested that states were ordinal and aligned with disease progression. Model transition probabilities demonstrated that the probability of an animal progressing to the highest state was dependent on its current state. Of particular note was the existence of a latent state, characterised by paratuberculosis test results below the conventional test-positive threshold, which was associated with a relatively high probability of progression to the highest cluster. This research has led to objective classification of animals according to serial test results, and furthermore suggests the presence of groups of different disease risk amongst animals whose test results fall below the routinely used test-positive threshold. Identification of such groups could be used to better manage disease on farms, through implementation of management practices which limit disease transmission from high-risk animals.

Mobility scoring data can be used to estimate the prevalence, incidence, and duration of lameness in dairy herds. Mobility scoring is often performed infrequently with variable sensitivity, but how this impacts the estimation of lameness parameters is largely unknown. We developed a simulation model to investigate the impact of the frequency and accuracy of mobility scoring on the estimation of lameness parameters for different herd scenarios. Herds with a varying prevalence (10, 30, or 50%) and duration (distributed around median days 18, 36, 54, 72, or 108) of lameness were simulated at daily time steps for five years. The lameness parameters investigated were prevalence, duration, new case rate, time to first lameness, and probability of remaining sound in the first year. True parameters were calculated from daily data and compared to those calculated when replicating different frequencies (weekly, two-weekly, monthly, quarterly), sensitivities (60–100%), and specificities (95–100%) of mobility scoring. Our results showed that over-estimation of incidence and under-estimation of duration can occur when the sensitivity and specificity of mobility scoring are <100%. This effect increases with more frequent scoring. Lameness prevalence was the only parameter that could be estimated with reasonable accuracy when simulating quarterly mobility scoring. These findings can help inform mobility scoring practices and the interpretation of mobility scoring data.

Currently, the dairy industry is facing many challenges that could affect its sustainability, including climate change and public perception of the industry. As a result, interest is increasing in the concept of identifying resilient animals, those with a long productive lifespan, as well as good reproductive performance and milk yield. There is much evidence that events in utero, that is, the developmental origins of health and disease hypothesis, alter the life-course health of offspring and we hypothesized that these could alter resilience in calves, where resilience is identified using lifetime data. The aim of this study was to quantify lifetime resilience scores (LRS) using an existing scoring system, based on longevity with secondary corrections for age at first calving and calving interval, and to quantify the effects of in utero events on the LRS using 2 datasets. The first was a large dataset of cattle on 83 farms in Great Britain born from 2006 to 2015 and the second was a smaller, more granular dataset of cattle born between 2003 and 2015 in the Langhill research herd at Scotland's Rural College. Events during dam's pregnancy included health events (lameness, mastitis, use of an antibiotic or anti-inflammatory medication), the effect of heat stress as measured by temperature-humidity index, and perturbations in milk yield and quality (somatic cell count, percentage fat, percentage protein and fat: protein ratio). Daughters born to dams that experienced higher temperature-humidity indexes while they were in utero during the first and third trimesters of pregnancy had lower LRS. Daughter LRS were also lower where milk yields or median fat percentages in the first trimester were low, and when milk yields were high in the third trimester. Dam LRS was positively associated with LRS of their offspring; however, as parity of the dam increased, LRS of their calves decreased. Similarly, in the Langhill herd, dams of a higher parity produced calves with lower LRS. Additionally, dams that recorded a high maximum locomotion score in the third trimester of pregnancy were negatively associated with lower calf LRS in the Langhill herd. Our results suggest that events that occur during pregnancy have lifelong consequences for the calf's lifetime performance. However, experience of higher temperature-humidity indexes, higher dam LRS, and mothers in higher parities explained a relatively small proportion of variation in offspring LRS, which suggests that other factors play a substantial role in determining calf LRS. Although "big data" can contain a considerable amount of noise, similar findings between the 2 datasets indicate it is likely these findings are real.

Artificial intelligence is a hot topic at present, although there is some confusion about what it involves. Translating artificial intelligence technology into production animal veterinary practice has the potential to transform how veterinary surgeons operate. The farm veterinarians of the future will no doubt require additional tools and skills that leverage advances in artificial intelligence for the improvement of animal health, welfare and productivity.

BACKGROUND:The aim of the study was to describe the longitudinal dynamics of antimicrobial use (AMU) on sheep farms and explore associations between AMU and management factors, vaccination strategies, reproductive performance and prevalence of lameness.METHODS:Antimicrobial supply data were collected for 272 British sheep farms for 3-6 consecutive years between 2015 and 2021. These data were obtained from the farms' veterinary practices.RESULTS:Annual median AMU ranged from 8.1 to 11.8 mg/kg population corrected unit. AMU was skewed in each year with a small proportion of very high users. AMU within farms varied substantially between years. High AMU farms in 1 year were not necessarily high in other years. No associations between AMU and either vaccine usage or lameness prevalence were found.LIMITATIONS:The study design requires veterinarians and farmers to volunteer their data. This unavoidably introduces the potential for a participation bias.CONCLUSIONS:AMU on sheep farms is generally low, with a small number of farms being responsible for high usage. Targeting antimicrobial stewardship effort towards the small minority of persistently high users may be more appropriate than a focus on generic, industry-wide attempts to reduce overall AMU.

Udder health remains a priority for the global dairy industry to reduce pain, economic losses, and antibiotic usage. The dry period is a critical time for the prevention of new intra-mammary infections and it provides a point for curing existing intra-mammary infections. Given the wealth of udder health data commonly generated through routine milk recording and the importance of udder health to the productivity and longevity of individual cows, an opportunity exists to extract greater value from cow-level data to undertake risk-based decision-making. The aim of this research was to construct a machine learning model, using routinely collected farm data, to make probabilistic predictions at drying off for an individual cow’s risk of a raised somatic cell count (hence intra-mammary infection) post-calving. Anonymized data were obtained as a large convenience sample from 108 UK dairy herds that undertook regular milk recording. The outcome measure evaluated was the presence of a raised somatic cell count in the 30 days post-calving in this observational study. Using a 56-farm training dataset, machine learning analysis was performed using the extreme gradient boosting decision tree algorithm, XGBoost. External validation was undertaken on a separate 28-farm test dataset. Statistical assessment to evaluate model performance using the external dataset returned calibration plots, a Scaled Brier Score of 0.095, and a Mean Absolute Calibration Error of 0.009. Test dataset model calibration performance indicated that the probability of a raised somatic cell count post-calving was well differentiated across probabilities to allow an end user to apply group-level risk decisions. Herd-level new intra-mammary infection rate during the dry period was a key driver of the probability that a cow had a raised SCC post-calving, highlighting the importance of optimizing environmental hygiene conditions. In conclusion, this research has determined that probabilistic classification of the risk of a raised SCC in the 30 days post-calving is achievable with a high degree of certainty, using routinely collected data. These predicted probabilities provide the opportunity for farmers to undertake risk decision-making by grouping cows based on their probabilities and optimizing management strategies for individual cows immediately after calving, according to their likelihood of intra-mammary infection.

Background Accurate surveillance of livestock antibiotic usage (ABU) at the farm level is an increasingly important part of national antibiotic stewardship initiatives. Numerous ABU indicators or metrics have been developed in Europe and North America but the comparability of these metrics is poorly understood. For policymakers, understanding the relationship between metrics is important when considering the risks posed by ABU and how to regulate them, at the national level, and regulate international trade access in livestock products between countries who use different ABU metrics. Objectives To quantify the patterns of ABU among beef (cattle) and lamb (sheep) production systems. To explore ABU variation between farm types across seven ABU metrics developed in Europe and North America using a common dataset of sheep and beef farms' antibiotic purchases from the UK. Methods A dataset of >16 200 antibiotic sales events to 686 farm enterprises of different types underwent quantitative analysis. Correlation matrixes were generated for seven international ABU metrics. Results ABU was significantly higher among calf-rearers. Across all farm types, tetracyclines and & beta;-lactams were the predominant groups by mass, but represent a similar dose equivalent to macrolides across most farm types. Good agreement (>0.9) was observed between metrics. Conclusions Reliable metrics to accurately benchmark farms are crucial for maintaining confidence of farmers in the fairness of any surveillance system, especially when the ranking of any given system may be linked to financial subsidies or penalties and also when negotiating import and export access for livestock products between countries.

Bovine respiratory disease (BRD) is a challenge in all housed farming systems that raise calves. Farm to farm variation in BRD prevalence can be partially attributed to variation in host immunity, pathogens and housing environment. Unlike host immunity and BRD pathogens, housing environment has not been well investigated. The objective of this systematic review was to identify the measurable environmental variables associated with BRD in housed preweaned calves. Pubmed, CAB Direct and Scopus databases were searched. To be considered for inclusion publications had to be published in English, before 24 November, 2022 and include at least one measurable/ manipulated environmental variable and a standardized method of BRD detection. In total 12 publications were included in this review. In this second part of the systematic review the environmental variables identified were; temperature (9 publications); relative humidity (8 publications); bedding (5 publications); ventilation (1 publication); air CO2 concentration (1 publication) and air velocity (4 publications). Of the publications that were examined a statistically significant relationship to BRD was identified in 4/9 publications examining temperature, 3/8 examining relative humidity, 2/4 examining air velocity, 2/5 examining bedding, 0/1 examining ventilation rates and 0/1 examining CO2 concentration. From this review it is clear high airspeed at calf level should be avoided as should deep, wet pack bedding. The relationship between BRD prevalence and both high and low temperature requires more investigation to identify temperature thresholds associated with increased risk of BRD as well as the most influential modifiers. An optimal environment for housed calves could not be clearly identified in this review.

Lameness in dairy cattle is a highly prevalent condition that impacts on the health and welfare of dairy cows. Prompt detection and implementation of effective treatment is important for managing lameness. However, major limitations are associated with visual assessment of lameness, which is the most commonly used method to detect lameness. The aims of this study were to investigate the use of metabolomics and machine learning to develop novel methods to detect lameness. Untargeted metabolomics using liquid chromatography-mass spectrometry (LC-MS) alongside machine learning models and a stability selection method were utilized to evaluate the predictive accuracy of differences in the metabolomics profile of first-lactation dairy cows before (during the transition period) and at the time of lameness (based on visual assessment using the 0–3 scale of the Agriculture and Horticulture Development Board). Urine samples were collected from 2 cohorts of dairy heifers and stored at −86°C before analysis using LC-MS. Cohort 1 (n = 90) cows were recruited as current first-lactation cows with weekly mobility scores recorded over a 4-mo timeframe, from which newly lame and nonlame cows were identified. Cohort 2 (n = 30) cows were recruited within 3 wk before calving, and lameness events (based on mobility score) were recorded through lactation until a minimum of 70 d in milk (DIM). All cows were matched paired by DIM ± 14 d. The median DIM at lameness identification was 187.5 and 28.5 for cohort 1 and 2, respectively. The best performing machine learning models predicted lameness at the time of lameness with an accuracy of between 81 and 82%. Using stability selection, the prediction accuracy at the time of lameness was 80 to 81%. For samples collected before and after calving, the best performing machine learning model predicted lameness with an accuracy of 71 and 75%, respectively. The findings from this study demonstrate that untargeted LC-MS profiling combined with machine learning methods can be used to predict lameness as early as before calving and before observable changes in gait in first-lactation dairy cows. The methods also provide accuracies for detecting lameness at the time of observable changes in gait of up to 82%. The findings demonstrate that these methods could provide substantial advancements in the early prediction and prevention of lameness risk. Further external validation work is required to confirm these findings are generalizable; however, this study provides the basis from which future work can be conducted.

Bovine respiratory disease (BRD) is one of the leading causes of mortality and morbidity in calves across diverse management systems. Despite expert opinion often citing the influence of housing environment on the level of respiratory disease in calf groups, there have been few reviews of environmental factors that predispose to BRD. This systematic review was undertaken to identify the measurable environmental variables associated with respiratory disease in housed preweaned calves. To achieve this Pubmed, CAB Direct and Scopus databases were searched. To be considered for inclusion, publications had to be fully published in English, published before 24 November, 2022 and include at least one measurable/ manipulated environmental variable and a standardized method of BRD detection. Twelve publications were included in this review. These examined a wide range of risk factors including air microbial count (four publications), air particulate matter (one publication); air endotoxins (one publication) and air ammonia (four publications). From the included publications, a statistically significant relationship to BRD was identified in 2/4 examining air microbial count, 1/1 examining air particulate matter, 1/1 examining air endotoxins and 2/4 examining air ammonia. This review indicated a paucity of evidence from the peer-review literature demonstrating a significant association between the many investigated exposure factors and BRD occurrence. An optimal environment for housed calves could not be clearly identified in this review.