Search Results (152)

During commercial pig production, weaning is a major stressor that disrupts the gut microbiome, compromises intestinal barrier integrity, and increases the susceptibility of piglets to pathogens. This often results in post-weaning diarrhoea (PWD), leading to growth retardation, morbidity, and economic loss. This study investigated the effects of dietary xylo-oligosaccharide (XOS) supplementation on the growth performance and gut health of 216 piglets with naturally occurring PWD. Piglets received either 0 (CON), 50 (XOS-50), or 500 (XOS-500) mg XOS/kg feed from weaning at 28 days of age (d1) for 54 days. XOS-500 significantly improved body weight at d22 and d54, but had no effect on average daily gain, daily feed intake (DFI), or feed conversion ratio. The intestinal microbiota alpha-diversity was unaffected by XOS, though jejunal beta diversity differed between CON and XOS-500 groups at d22. Jejunal Chao richness correlated positively with d54 body weight, while ileal Chao richness correlated negatively with DFI. Salmonella was present in all diet groups but did not differ in abundance; however, the levels were negatively correlated with alpha diversity. XOSs increased Lactobacillus (d22, d54) and Clostridium_XI (d22), while reducing Veillonellaceae spp. (d22). XOSs reduced jejunal goblet cell (GC) density at d22 but increased duodenal and jejunal GCs and reduced duodenal crypt depth at d54. XOSs upregulated the genes for the tight junction proteins CLDN2, CLDN3, ALPI, and ZO-1, while downregulating the cytokine IL-8. These findings highlight XOSs’ potential to improve growth and gut health in weaning piglets with naturally occurring PWD, to maintain productivity and enhance welfare. Full article

The automatic recognition of animal vocalizations is a valuable tool for monitoring pigs’ behavior, health, and welfare. This study investigates the feasibility of implementing a convolutional neural network (CNN) model for classifying pig vocalizations using tiny machine learning (TinyML) on a low-cost, resource-constrained embedded system. The dataset was collected in 2011 at the University of Illinois at Urbana-Champaign on an experimental pig farm. In this experiment, 24 piglets were housed in environmentally controlled rooms and exposed to gradual thermal variations. Vocalizations were recorded using directional microphones, processed to reduce background noise, and categorized into “agonistic” and “social” behaviors using a CNN model developed on the Edge Impulse platform. Despite hardware limitations, the proposed approach achieved an accuracy of over 90%, demonstrating the potential of TinyML for real-time behavioral monitoring. These findings underscore the practical benefits of integrating TinyML into swine production systems, enabling early detection of issues that may impact animal welfare, reducing reliance on manual observations, and enhancing overall herd management. Full article

Animal welfare is one of the core concerns in the field of animal science, with behavior serving as a direct reflection of emotional state and health, and thus a key indicator for welfare assessment. With the widespread adoption of intensive farming systems, abnormal behaviors in pigs have become a prominent marker of compromised welfare. In the past few years, the role of gut microbes in the regulation of animal behavior has received increasing attention. This review summarizes the strong relationship between pig behavior and welfare, and focuses on the emerging research linking gut microbiota to behavioral expression in pigs. Furthermore, it outlines the mechanisms by which the microbiota modulates behavior through the microbiota–gut–brain axis (MGBA), including immune, endocrine, and neural pathways. Additionally, the potential of microbiota-targeted interventions to improve pig welfare, including probiotics and prebiotics, will be evaluated. As a critical bridge connecting physiology and psychology, the gut microbiota shows significant promise for advancing welfare regulation in pigs. Full article

Sow mortality is a critical issue in intensive pig farming, impacting animal welfare, farm sustainability, and profitability. This study investigated the occurrence and causes of sow mortality on 15 Flemish sow farms, focusing on management practices, housing conditions, feeding strategies, and genetics. The average sow mortality rate across the farms was 11.4% in 2022, which decreased to 8.1% in 2023 following the implementation of targeted control measures. Necropsies performed on 100 deceased sows, coming from the 15 different farms, revealed that the primary causes of mortality were positional changes in internal organs (32%), arthritis (19%), and urogenital disorders (7%). Key recommendations to reduce sow mortality included optimizing sow health and body condition, improving housing and feeding management, and addressing genetic factors. The study highlights the multifaceted nature of sow mortality and the importance of a comprehensive approach to mitigate risks and improve sow welfare and productivity. Full article

The understanding of sustainability is shifting from that of a purely environmental dimension to one that includes social concerns. Combined with the growing customer interest in livestock husbandry practices, this study investigates the assessment of animal welfare as a socially influenced impact category for the life cycle assessment (LCA) of pig farming. The weighting of animal welfare impacts is based on a quantitative approach using a set of indicators derived from an expert survey using the Analytic Hierarchy Process (AHP). The aim is to develop an easy-to-implement score that translates the characteristics of several animal welfare indicators into a comparable value. To demonstrate the feasibility of the weighting part of the framework, a case study is conducted with nine experts in the fields of animal husbandry, agricultural sciences, and veterinary medicine. The case study results show that the main criteria of single animal observation and feed intake are the most relevant factors, at 30.6%, followed by operation-specific parameters at 23.9% and husbandry conditions at 14.9%. This case study highlights that animal losses (13.9%) significantly influence the impact category, while access to outdoor areas (1.4%) is less important. The overall conclusion is that an animal health-centered approach is preferable when assessing animal welfare. Full article

This study aimed to evaluate the effects of no tail docking on the performance, health, and behavior of piglets raised under commercial conditions in Brazil. The study included 768 weaned piglets from the Pietrain synthetic line, randomly divided into two groups: DT = the final third part of the tail-docked (n = 384) and NTD = non-tail-docked (n = 384). Tail docking was performed on day two using an electrocautery clipper for piglets from the DT group, and both groups were subjected to standard environmental enrichment with branched chains. In cases of tail biting, a contingency plan was adopted to mitigate this problem by enriching the pen with a sisal rope. Behavioral measurements were performed using scan sampling. Tail biting, reactivity to humans, and health were assessed using a methodology adapted from the Welfare Quality Protocol^®. The piglets were weighed at 140 days of age and inspected according to the parameters established by the Pig Genealogical Registration Service to be used as reproduction animals. The off-test rate was calculated based on the total number of piglets approved for animal use relative to the total number evaluated. During the nursery stage, the NDT piglets showed a trend toward significance (p = 0.07) toward a higher occurrence of tail biting than the DT piglets and exhibited a higher incidence of severe lesions. They also engaged more frequently (p < 0.05) in exploratory behavior, interacting with branched chains and sisal rope, than the DT piglets. During the finishing phase, tail biting was observed only in the NDT piglets (p = 0.001). The NDT piglets that did not require the contingency plan exhibited lower fear responses (p = 0.02) during human interactions in the nursery phase than the DT piglets. Conversely, the NDT piglets that required a contingency plan showed higher fear levels (p < 0.001). Productivity performance was not affected (p > 0.05), and new cases of tail biting ceased after the contingency plan was implemented. The number of animals that died or were removed did not differ between the treatments (p > 0.05). In conclusion, managing piglets with intact tails on commercial farms presents a significant welfare challenge. By contrast, docking the final third of the tail, in accordance with regulations, was associated with fewer negative welfare outcomes, even when best management practices were applied. Full article

Against the backdrop of precision livestock farming, sow behavior analysis holds significant theoretical and practical value. Traditional production methods face challenges such as low production efficiency, high labor intensity, and increased disease prevention risks. With the rapid advancement of optoelectronic technology and deep learning, more technologies are being integrated into smart agriculture. Intelligent large-scale pig farming has become an effective means to improve sow quality and productivity, with behavior recognition technology playing a crucial role in intelligent pig farming. Specifically, monitoring sow behavior enables an effective assessment of health conditions and welfare levels, ensuring efficient and healthy sow production. This study constructs a 3D-CNN model based on video data from the sow estrus cycle, achieving analysis of SOB, SOC, SOS, and SOW behaviors. In typical behavior classification, the model attains accuracy, recall, and F1-score values of (1.00, 0.90, 0.95; 0.96, 0.98, 0.97; 1.00, 0.96, 0.98; 0.86, 1.00, 0.93), respectively. Additionally, under conditions of multi-pig interference and non-specifically labeled data, the accuracy, recall, and F1-scores for the semantic recognition of SOB, SOC, SOS, and SOW behaviors based on the 3D-CNN model are (1.00, 0.90, 0.95; 0.89, 0.89, 0.89; 0.91, 1.00, 0.95; 1.00, 1.00, 1.00), respectively. These findings provide key technical support for establishing the classification and semantic recognition of typical sow behaviors during the estrus cycle, while also offering a practical solution for rapid video-based behavior detection and welfare monitoring in precision livestock farming. Full article

The accurate recognition of pig behaviors in intensive farming is crucial for health monitoring and growth assessment. To address multi-scale recognition challenges caused by perspective distortion (non-frontal camera angles), this study proposes MACA-Net, a YOLOv8n-based model capable of detecting four key behaviors: eating, lying on the belly, lying on the side, and standing. The model incorporates a Mamba Global–Local Extractor (MGLE) Module, which leverages Mamba to capture global dependencies while preserving local details through convolutional operations and channel shuffle, overcoming Mamba’s limitation in retaining fine-grained visual information. Additionally, an Adaptive Multi-Path Attention (AMPA) mechanism integrates spatial-channel attention to enhance feature focus, ensuring robust performance in complex environments and low-light conditions. To further improve detection, a Cross-Layer Feature Pyramid Transformer (CFPT) neck employs non-upsampled feature fusion, mitigating semantic gap issues where small target features are overshadowed by large target features during feature transmission. Experimental results demonstrate that MACA-Net achieves a precision of 83.1% and mAP of 85.1%, surpassing YOLOv8n by 8.9% and 4.4%, respectively. Furthermore, MACA-Net significantly reduces parameters by 48.4% and FLOPs by 39.5%. When evaluated in comparison to leading detectors such as RT-DETR, Faster R-CNN, and YOLOv11n, MACA-Net demonstrates a consistent level of both computational efficiency and accuracy. These findings provide a robust validation of the efficacy of MACA-Net for intelligent livestock management and welfare-driven breeding, offering a practical and efficient solution for modern pig farming. Full article

Gastrointestinal health is critical to the productivity and welfare of pigs. The transition from milk to plant-based feeds represents an intestinal challenge at wean that can result in dysbiosis and pathogen susceptibility. Prebiotic galacto-oligosaccharides (GOS) and xylo-oligosaccharides (XOS) are non-digestible carbohydrates that can reach the hind gut to promote gut health, either by enhancing the abundance of beneficial members of the intestinal microbiota or via direct interaction with the gut epithelium. Amongst the changes in the intestinal microbiota, GOS and XOS promote populations of short-chain fatty acid (SCFA)-producing bacteria of the genera Lactobacillus, Bifidobacterium and Streptococcus. SCFAs benefit the host by providing nutritional support for the gut, enhance intestinal barrier function and regulate inflammatory responses. By modifying the indigenous microbiota, prebiotics offer a sustainable alternative to the use of antimicrobial growth promoters that have led to the dissemination of antimicrobial resistance and represent a growing threat to public health. This review examines microbial and cellular mechanisms whereby prebiotic feed supplements can support the development of a diverse and robust microbiota associated with a healthy and productive digestive system over the lifetime of the animal, and which is in sharp contrast to the development of dysbiosis often associated with existing antimicrobial treatments. The application of prebiotic feed supplements should be tailored to their modes of action and the developmental challenges in production, such as the provision of GOS to late gestational sows, GOS and XOS to pre-weaning piglets and GOS and XOS to growing/fattening pigs. Full article

The prediction that the world population will reach almost 10 billion people by 2050 means an increase in pork production is required. Efforts to meet increased demand have made pig production one of the most technologically advanced branches of production and one which is growing continuously. Precision Livestock Production (PLF) is an increasingly widespread model in pig farming and describes a management system based on the continuous automatic monitoring and control of production, reproduction, animal health and welfare in real time, as well as the impact of animal husbandry on the environment. Today, a wide range of technologies is available, such as 2D and 3D cameras to assess body weight, behavior and activity, thermal imaging cameras to monitor body temperatures and determine estrus, microphones to monitor vocalizations, various measuring cells to monitor food intake, body weight and weight gain, and many others. By combining and applying the available technologies, it is possible to obtain a variety of data that allow livestock farmers to automatically monitor animals and improve pig health and welfare as well as environmental sustainability. Nevertheless, PLF systems need further research to improve the technologies and create cheap and affordable but accurate models to ensure progress in pig production. Full article

Animal welfare in barns is strongly influenced by air quality, with gaseous emissions like ammonia posing significant respiratory health risks. However, current state-of-the-art ammonia monitoring systems are labor-intensive and expensive. Metal Oxide Semiconductor (MOS) sensors offer a promising alternative due to their compatibility with sensor networks, enabling high-resolution ammonia monitoring across spatial and temporal scales. While MOS sensors exhibit high sensitivity to various volatile compounds, temperature-cycled operation is commonly employed to enhance selectivity, effectively creating virtual sensor arrays. This study aims to improve ammonia detection by designing a virtual sensor array through a cyclic data-driven approach, integrating machine learning with solid-state sensor modeling. The results of a two-week dataset with measurements of four different pig barns demonstrate ammonia sensing with a sampling rate of about 2/min and a range of 1–30 ppm. The method is robust and exhibits a 10% increase in normalized RMSE when comparing testing results of an unseen sensor module with results of the training dataset. A filter membrane boosts accuracy and prevents data loss due to contamination, such as flyspecks. Overall, the used MOS sensor BME688 is effective and economical for widespread continuous ammonia monitoring and localization of ammonia sources in pig barns. Full article

Mycoplasma hyopneumoniae (Mhyo) and porcine circovirus type 2 (PCV2) are critical pathogens in the swine industry, both contributing significantly to the porcine respiratory disease complex (PRDC). Given their impact, it is logical to control these pathogens simultaneously. Consequently, combined vaccinations against Mhyo and PCV2 are gaining popularity in swine health management. We present the efficacy of the first commercial combined vaccine prepared of a genotype PCV2d strain and Mhyo and tested against experimental challenge infections with target pathogens in comparative trials with other commercial products. In these studies, three-week-old piglets were vaccinated according to the manufacturers’ instructions. Five weeks later, they were challenged with two Mhyo strains over three consecutive days or with a PCV2d strain once. Positive controls included challenged pigs without prior vaccination, while non-vaccinated/non-challenged pigs served as negative controls. The key parameters measured were lung lesion scores and seroconversion for Mhyo, and viraemia, rectal shedding, lymph node and lung viral content, and seroconversion for PCV2. Findings and conclusion: The results showed no compromising effects between the vaccine components and highlighted significant differences in efficacy among the various products tested. Additionally, oral fluid sampling demonstrated a strong correlation with the viraemia and fecal shedding of PCV2, underscoring the diagnostic and animal welfare benefits of this sampling method. Full article

Leptospirosis is one of the world’s major neglected tropical zoonotic diseases (NTZDs), implicated in animal health and welfare with economic consequences for livestock production. This study aims to estimate the seroprevalence of Leptospira spp. and identify potential risk factors in small ruminant herds. This epidemiological cross-sectional study was conducted in Nuevo León, a semi-arid region of Mexico. A total of 389 blood samples from goats and 385 from sheep older than eight months were randomly collected from 128 herds. Anti-Leptospira antibodies were detected using the microscopic agglutination test (MAT), and univariate and multivariate logistic regression analyses were performed to determine their association with leptospirosis infection. The overall prevalence was 13.5% (105/774), with 14.4% (56/389) in goats and 12.7% (49/385) in sheep. Sejroe was the most predominant serogroup. The main risk factors in sheep were contact with domestic cattle, ≥100 animals per herd, congenital abnormalities, contact with feral pigs, meat production system, absence of veterinary care, and abortions with odds ratios (OR) between 1.7 and 4.1. In goats, the main risk factors included lack of quarantine measures, contact with feral pigs, absence of veterinary care, and abortions where the OR ranged from 1.7 to 3.3. These findings indicate that Leptospira spp. is present in small ruminant herds. This is the first study aimed at understanding leptospirosis epidemiology in the northeastern region of Mexico, as goats and sheep may act as potential reservoirs. Continuous monitoring of Leptospira infections is imperative, as well as developing educational initiatives for farmers to implement biosecurity and prevention measures to prevent infections within herds and protect public health. Full article

Poor health and increased susceptibility to infectious diseases are among the main sources of economic losses in the pig industry worldwide, and they also serve as indicators of compromised animal welfare. However, there is limited information on long-lasting biomarkers of poor health and common infections experienced by piglets early in life. Hair cortisol, dehydroepiandrosterone sulfate (DHEA(S)), and their ratio have been proposed as components of the mammalian stress response due to the activation of the hypothalamus–pituitary–adrenal axis and were investigated in this study using 30 batches of pigs from 16 farms. The research hypothesis was that batches of piglets experiencing clinical syndromes (as indicated by enteric, neurological, cutaneous, and locomotor scores) during suckling would exhibit a different pattern of resilience and allostatic load later in life compared to healthy ones. Hair from 25 gilts per batch were collected at either 3.5 or 9 months of age, and hormone extraction was subsequently performed. The farm of origin and the age of the animals significantly influenced hormone concentrations. Moreover, batches affected by enteric disease showed lower DHEA(S) levels (p < 0.0001; 15.89 vs. 23.51 pg/mg) and higher cortisol/DHEA(S) ratio (p < 0.0001; 82.83 vs. 55.02) than healthy batches. Similar results were observed in batches with a neurological syndrome (DHEA(S): p < 0.0001; 12.91 vs. 19.43; cortisol/DHEA(S) ratio: p < 0.0001; 97.15 vs. 70.26 pg/mg). These results suggest that pig hair biomarkers carry an intrinsic and temporally stable signal related to early life health status. Full article

Background: The social interactions of farm animals affect their performance, health and welfare. This proof-of-concept study addresses, for the first time, the hypothesis that applying social network analysis (SNA) on AI-automated monitoring data could potentially facilitate the analysis of social structures of farm animals. Methods: Data were collected using automated recording systems that captured 2D-camera images and videos of pigs in six pens (16–19 animals each) on a PIC breeding company farm (USA). The system provided real-time data, including ear-tag readings, elapsed time, posture (standing, lying, sitting), and XY coordinates of the shoulder and rump for each pig. Weighted SNA was performed, based on the proximity of “standing” animals, for two 3-day period—the early (first month after mixing) and the later period (60 days post-mixing). Results: Group-level degree, betweenness, and closeness centralization showed a significant increase from the early-growing period to the later one (p < 0.02), highlighting the pigs’ social dynamics over time. Individual SNA traits were stable over these periods, except for the closeness centrality and clustering coefficient, which significantly increased (p < 0.00001). Conclusions: This study demonstrates that combining AI-assisted monitoring technologies with SNA offers a novel approach that can help farmers and breeders in optimizing on-farm management, breeding and welfare practices. Full article