Search Results (283)

Stress in pigs poses significant challenges to animal welfare and productivity in modern pig farming, contributing to increased antimicrobial use and the rise of antimicrobial resistance (AMR). This study involves stress classification in pregnant sows by exploring five deep learning models: ConvNeXt, EfficientNet_V2, MobileNet_V3, RegNet, and Vision Transformer (ViT). These models are used for stress detection from facial images, leveraging an expanded dataset. A facial image dataset of sows was collected at Scotland’s Rural College (SRUC) and the images were categorized into primiparous Low-Stressed (LS) and High-Stress (HS) groups based on expert behavioural assessments and cortisol level analysis. The selected deep learning models were then trained on this enriched dataset and their performance was evaluated using cross-validation on unseen data. The Vision Transformer (ViT) model outperformed the others across the dataset of annotated facial images, achieving an average accuracy of 0.75, an F1 score of 0.78 for high-stress detection, and consistent batch-level performance (up to 0.88 F1 score). These findings highlight the efficacy of transformer-based models for automated stress detection in sows, supporting early intervention strategies to enhance welfare, optimize productivity, and mitigate AMR risks in livestock production. Full article

European pig farmers are challenged by increasingly stringent EU regulations to protect the environment from pollution, to meet animal welfare standards and to make pig farming more sustainable. Economic sustainability is defined as the ability to achieve higher profits by respecting social and natural resources. This study is focused on the analysis of the economic resilience of intensive and extensive farming systems, based on data collected from 56 farms located in Denmark, Poland, Italy and Spain. Productive and economic performances of these farms are analyzed, and economic resilience is assessed through a survey including a selection of indicators, belonging to different themes: [i] resilience of resources, [ii] entrepreneurship, [iii] propensity to extensification. The qualitative data from the questionnaire allow for an exploration of how production systems relate to the three dimensions of resilience. Different levels of resilience were found and discussed for intensive and extensive farms. The findings suggest that intensive farms benefit from high standards and greater bargaining power within the supply chain. Extensive systems can achieve profitability through value-added strategies and generally display good resilience. Policies that support investment and risk reduction are essential for enhancing farm resilience and robustness, while strengthening farmer networks can improve adaptability. Full article

Over the years, macromycete fungi have been used as a source of food, part of religious rites and rituals, and as a medicinal remedy. Species with strong health-promoting potential include Hericium erinaceus, Cordyceps militaris, Ganoderma lucidum, Pleurotus ostreatus, Flammulina velutipes, and Inonotus obliquus. These species contain many bioactive compounds, including β-glucans, endo- and exogenous amino acids, polyphenols, terpenoids, sterols, B vitamins, minerals, and lovastatin. The level of some biologically active substances is species-specific, e.g., hericenones and erinacines, which have neuroprotective properties, and supporting the production of nerve growth factor in the brain for Hericium erinaceus. Due to their high health-promoting potential, mushrooms and substances isolated from them have found applications in livestock nutrition, improving their welfare and productivity. This phenomenon may be of particular importance in the nutrition of laying hens and broiler chickens, where an increase in pathogen resistance to antibiotics has been observed in recent years. Gallus gallus domesticus is a key farm animal for meat and egg production, so the search for new compounds to support bird health is important for food safety. Studies conducted to date indicate that feed supplementation with mushrooms has a beneficial effect on, among other things, bird weight gain; bone mineralisation; and meat and egg quality, including the lipid profile and protein content and shell thickness, and promotes the development of beneficial microbiota, thereby increasing immunity. Full article

Staphylococcus aureus frequently causes intramammary infections in dairy cows (bovine mastitis), which impair animal welfare, milk yield, and food safety. This study determined the prevalence and genetic diversity of S. aureus in bulk tank milk (BTM) samples from community-based Alpine dairy pastures in Tyrol, a major milk-producing region in Austria. Throughout the 2023 Alpine season (May–September), 60.3% (94/156) of BTM samples tested positive for S. aureus at least once over the course of up to four samplings. A total of 140 isolates collected from the 94 S. aureus-positive community-based Alpine dairy pastures revealed 33 distinct spa types, with t2953 (n = 33), t529 (n = 12), t267 (n = 11), and t024 (n = 10) being the most common. Selected isolates representing the different spa types were characterised by DNA microarray-based genotyping, multi-locus sequence typing (MLST), and antimicrobial susceptibility testing. Isolates with spa types associated with bovine-adapted CC8 (CC8bov/GTB) were identified as the most common subtype, being detected in BTM samples from 35.3% (55/156) of the pastures. This emphasises the high prevalence of this subtype in dairy herds across European Alpine countries. Other common bovine-associated subtypes were also detected, including CC97, CC151, and CC479. While antimicrobial resistance was rare, enterotoxin-producing genes were detected in all CC8bov-associated spa types. Overall, these findings underscore the importance of rigorous hygiene practices in dairy farming, particularly in community-based Alpine dairy pastures, where the risk of transmission is particularly high. It also emphasises the need for continued surveillance and subtyping to improve animal health, ensure food safety, and promote sustainable milk production. Full article

Reproductive efficiency is a critical determinant of productivity and profitability in sheep farming. Traditional selection methods have largely relied on phenotypic traits and historical reproductive records, which are often limited by subjectivity and delayed feedback. Recent advancements in artificial intelligence (AI), including video tracking, wearable sensors, and machine learning (ML) algorithms, offer new opportunities to identify behavior-based indicators linked to key reproductive traits such as estrus, lambing, and maternal behavior. This review synthesizes the current research on AI-powered behavioral monitoring tools and proposes a conceptual model, ReproBehaviorNet, that maps age- and sex-specific behaviors to biological processes and AI applications, supporting real-time decision-making in both intensive and semi-intensive systems. The integration of accelerometers, GPS systems, and computer vision models enables continuous, non-invasive monitoring, leading to earlier detection of reproductive events and greater breeding precision. However, the implementation of such technologies also presents challenges, including the need for high-quality data, a costly infrastructure, and technical expertise that may limit access for small-scale producers. Despite these barriers, AI-assisted behavioral phenotyping has the potential to improve genetic progress, animal welfare, and sustainability. Interdisciplinary collaboration and responsible innovation are essential to ensure the equitable and effective adoption of these technologies in diverse farming contexts. Full article

Background: Reliable and non-invasive methods for assessing welfare in poultry are essential for improving evidence-based welfare monitoring and advancing management practices in commercial production systems. The iris-to-pupil (IP) ratio, previously validated by our group in primates and cattle, reflects autonomic nervous system balance and may serve as a physiological indicator of stress in laying hens. This study evaluated the utility of the IP ratio under field conditions across diverse commercial layer housing systems. Materials and Methods: In total, 296 laying hens (Lohmann Brown, n = 269; White Leghorn, n = 27) were studied across four locations in Canada housed under different systems: Guelph (indoor; pen), Spring Island (outdoor and scratch; organic), Ottawa (outdoor, indoor and scratch; free-range), and Toronto (outdoor and hobby; free-range). High-resolution photographs of the eye were taken under ambient lighting. Light intensity was measured using the light meter app. The IP ratio was calculated using NIH ImageJ software (Version 1.54p). Statistical analysis included one-way ANOVA and linear regression using GraphPad Prism (Version 5). Results: Birds housed outdoors had the highest IP ratios, followed by those in scratch systems, while indoor and pen-housed birds had the lowest IP ratios (p < 0.001). Subgroup analyses of birds in Ottawa and Spring Island farms confirmed significantly higher IP ratios in outdoor environments compared to indoor and scratch systems (p < 0.001). The IP ratio correlated weakly with ambient light intensity (r² = 0.25) and age (r² = 0.05), indicating minimal influence of these variables. Although White Leghorn hens showed lower IP ratios than Lohmann Browns, this difference was confounded by housing type; all White Leghorns were housed in pens. Thus, housing system but not breed was the primary driver of IP variation. Conclusions: The IP ratio is a robust, non-invasive physiological marker of welfare assessment in laying hens, sensitive to housing environment but minimally influenced by light or age. Its potential for integration with digital imaging technologies supports its use in scalable welfare assessment protocols. Full article

Efficient individual identification is essential for advancing precision broiler farming. In this study, we propose YOLO-IFSC, a high-precision and lightweight face recognition framework specifically designed for dense broiler farming environments. Building on the YOLOv11n architecture, the proposed model integrates four key modules to overcome the limitations of traditional methods and recent CNN-based approaches. The Inception-F module employs a dynamic multi-branch design to enhance multi-scale feature extraction, while the C2f-Faster module leverages partial convolution to reduce computational redundancy and parameter count. Furthermore, the SPPELANF module reinforces cross-layer spatial feature aggregation to alleviate the adverse effects of occlusion, and the CBAM module introduces a dual-domain attention mechanism to emphasize critical facial regions. Experimental evaluations on a self-constructed dataset demonstrate that YOLO-IFSC achieves a mAP@0.5 of 91.5%, alongside a 40.8% reduction in parameters and a 24.2% reduction in FLOPs compared to the baseline, with a consistent real-time inference speed of 36.6 FPS. The proposed framework offers a cost-effective, non-contact alternative for broiler face recognition, significantly advancing individual tracking and welfare monitoring in precision farming. Full article

This study presents a bibliometric review aimed at mapping and analyzing the scientific literature related to the ethical implications of artificial intelligence (AI) in livestock farming, which is a rapidly emerging yet still underexplored field in international research. Based on the Scopus database, 151 documents published between 2015 and 2025 were identified and analyzed using the VOSviewer version 1.6.20 and Biblioshiny for Bibliometrix (RStudio version 2023.12.1) tools. The results show a significant increase in publications from 2021 onwards, reflecting the growing maturity of discussions around the integration of digital technologies in the agricultural sector. Keyword co-occurrence and bibliographic coupling analyses revealed the formation of four main thematic clusters, covering technical applications in precision livestock farming as well as reflections on governance, animal welfare, and algorithmic justice. The most influential authors, high-impact journals, and leading countries in the field were also identified. As a key contribution, this study highlights the lack of robust ethical guidelines and proposes future research directions for the development of regulatory frameworks, codes of conduct, and interdisciplinary approaches. The findings underscore the importance of aligning technological innovation with ethical responsibility and social inclusion in the transition to digital livestock farming. Full article

Hoof disorders in small ruminants pose significant challenges to animal welfare and farm productivity. This study presents the first attempt to determine the prevalence of lameness and hoof disorders and their associated risk factors in goat and sheep farms in Selangor, Malaysia. Locomotion scores were collected from 226 animals (126 sheep and 100 goats) across 10 farms. A hoof examination was conducted, and hoof lesions were identified through detailed photographic evaluation. On-farm assessments and interviews were conducted to gather information on management practices from the farms. Data were analysed using descriptive statistics, bivariate analysis, and logistic regression models. The prevalence of lameness was 42.8% (95% CI 34.2 to 51.9) in sheep and 23.0% (95% CI 16.3–38.4) in goats. Significant variation (p > 0.05) in lameness prevalence was observed across farms, ranging from 26.7% to 61.5% in sheep and 7.7% to 30.8% in goat farms. The majority of lameness and hoof lesions were observed in the hindlimbs of both species. The prevalence of hoof disorders was 91.3% (95% CI 84.6–95.4) in sheep and 43.0% in goats (95% CI 21.4–58.0). The predominant hoof disorders were overgrown wall horn, white line disease, sole bruise, and wall fissures. No hoof affections of infectious origin were observed in the sampled animals. Risk factors for lameness and hoof lesions in sheep included pregnancy, semi-intensive management, and breeds other than Damara. Higher odds of lameness were observed in exotic goat breeds and those with overgrown wall horns. In conclusion, this study revealed a high prevalence of lameness and hoof disorders in goat and sheep farms, highlighting the need to address these important welfare and economic issues. While the identified risk factors could be considered for the management of hoof disorders in small ruminant farms, a larger sample size that is representative of the sheep and goat population is recommended for more generalizable results. Full article

The Argentine Campero-INTA slow-growing chicken, a widely used breed in family poultry farming, faces high coccidiosis prevalence, impairing productivity. Control often relies on management and drugs due to vaccination costs. This pilot study assessed the breed’s susceptibility to local Eimeria and the impact of good animal welfare practices (AWPs) and an organic fermented additive, locally produced, combined with AWPs (OF-AWPs). Two trials evaluated productive (body weight gain and feed conversion), infection (oocyst excretion and lesion score), and histopathological parameters (villus height and crypt depth). The productivity (PI) and anticoccidial (ACI) indexes were calculated. Metagenomic analysis of the additive was also conducted. Mild to moderate coccidiosis significantly reduced PI (7.99–16.83 vs. 29.29 in unchallenged controls). In the second trial, AWPs showed good anticoccidial efficacy (ACI 173.9), while OF-AWPs demonstrated high efficacy, especially in birds of 28 days (ACI 180.6), improving productive parameters, reducing oocyst shedding, and enhancing the villus height to crypt depth ratio. Over a 75-day cycle, the OF-AWP increased the PI by 24.44% compared to untreated chickens (108.8 vs. 87.43). Lactic acid bacteria were the main component of the organic fermented additive. This research highlights the potential of an agroecological strategy to manage coccidiosis in Campero-INTA chickens. Full article

Rising rates of antimicrobial-resistant infections have prompted increased scrutiny on antimicrobial use (AMU) in livestock agriculture. Dairy farms primarily use antimicrobials to maintain animal health and welfare by treating and preventing infectious diseases. However, the impact of dairy farm AMU practices on the cattle fecal microbiome remains largely unclear, partly due to difficulties in quantifying AMU. This study leveraged quantitative AMU data from 40 large commercial dairy farms to identify farms with low (n = 4) and high (n = 4) AMU. Using 16S rRNA gene amplicon sequencing, we compared the fecal bacterial communities of dairy calves and cows (healthy, cull, sick) by both AMU designation (high/low) and by individual farm AMU, summarized by animal defined daily dose (DDD) and mg/kg. We found significant differences in beta-diversity between cattle from high- and low-AMU groups using either method and found that Corynebacterium and Clostridium abundances increased with farm AMU. Additionally, we found fecal bacterial communities differed across farms within high- and low-AMU groupings, highlighting the need to account for farm-to-farm variation when assessing AMU impacts. These findings suggest that dairy farm AMU influences the fecal microbiome and identifies specific taxa that warrant further investigation as potential reservoirs for antimicrobial resistance genes. Full article

The aquaculture sector is essential for meeting seafood demand while ensuring sustainability. It involves farming fish, mollusks, crustaceans, other invertebrates, and algae in controlled environments, helping to conserve marine resources and reduce ecological pressures. Sustainable practices, such as an integrated multitrophic recirculating aquaculture system (IMTA-RAS) with fish and seaweed, can minimize the environmental impact of fish aquaculture. However, the impact of the introduction of macroalgae on the fish muscle metabolism has not been studied. This research examines the impact of growing Senegalese sole (Solea senegalensis) together with sea lettuce (Ulva ohnoi) on fish metabolism using high-resolution ¹H-NMR-based metabolomics. Three farming systems were compared. These were E₁, a recirculating aquaculture system (RAS); E₂, an IMTA-RAS integrating U. ohnoi for biofiltration; and E₃, an IMTA-RAS with U. ohnoi and Phaeobacter sp. strain 4UAC3, a probiotic bacterium isolated from wild U. australis known to counteract fish pathogens. A metabolomic analysis revealed that energy metabolism was enhanced in IMTA-RAS and even more in IMTA-RAS-Phaeobacter–grown fish, increasing overall metabolic activity. These results indicate that the presence of the algae with the probiotic had a clear impact on the physiological state of the fish, and this deserves further investigation. This study contributes to the understanding of the physiological responses of fish to innovative aquaculture practices, supporting the development of more sustainable and efficient management that reduces the environmental impact and increases fish health and welfare. Full article

Convolutional neural networks (CNNs) and their application in animal husbandry have in-depth mathematical expressions, which usually revolve around how well they map input data such as images or video frames of animals to meaningful outputs like health status, behavior class, and identification. Likewise, computer vision and deep learning models are driven by CNNs to act intelligently in improving productivity and animal management for sustainable animal husbandry. In animal husbandry, CNNs play a vital role in the management and monitoring of livestock’s health and productivity due to their high-performance accuracy in analyzing images and videos. Monitoring animals’ health is important for their welfare, food abundance, safety, and economic productivity. This paper aims to comprehensively review recent advancements and applications of relevant models that are based on CNNs for livestock health monitoring, covering the detection of their various diseases and classification of their behavior, for overall management gain. We selected relevant articles with various experimental results addressing animal detection, localization, tracking, and behavioral monitoring, validating the high-performance accuracy and efficiency of CNNs. Prominent anchor-based object detection models such as R-CNN (series), YOLO (series) and SSD (series), and anchor-free object detection models such as key-point based and anchor-point based are often used, demonstrating great versatility and robustness across various tasks. From the analysis, it is evident that more significant research contributions to animal husbandry have been made by CNNs. Limited labeled data, variation in data, low-quality or noisy images, complex backgrounds, computational demand, species-specific models, high implementation cost, scalability, modeling complex behaviors, and compatibility with current farm management systems are good examples of several notable challenges when applying CNNs in animal husbandry. By continued research efforts, these challenges can be addressed for the actualization of sustainable animal husbandry. Full article

Metritis is one of the most common postpartum diseases in dairy cows, associated with impaired reproductive performance and substantial economic losses. In this study, we investigated the potential of machine learning (ML) techniques applied to physiological, behavioural, and milk quality parameters for the early detection of metritis in dairy cows during the postpartum period. A total of 2707 daily observations were collected from 94 cows in early lactation, of which 11 cows (275 records) were diagnosed with metritis. The dataset included daily measurements of body weight, rumination time, milk yield, milk composition (fat, protein, lactose), somatic cell count (SCC), and feed intake. Five classification models—partial least squares discriminant analysis (PLS-DA), random forest (RF), support vector machine (SVM), neural network (NN), and an Ensemble model—were developed using standardised features and stratified 80/20 training/test splits. To address class imbalance, model loss functions were adjusted using class weights. Models were evaluated based on accuracy, sensitivity, specificity, positive and negative predictive values (PPV, NPV), area under the receiver operating characteristic (ROC) area under the curve (AUC), and Matthews correlation coefficient (MCC). The NN model demonstrated the highest overall performance (accuracy = 96.1%, AUC = 96.3%, MCC = 0.79), indicating strong capability in distinguishing both healthy and diseased animals. The SVM achieved the highest sensitivity (90.9%), while RF and Ensemble models showed high specificity (>98%) and PPV. This study provides novel evidence that ML methods can effectively detect metritis using routinely collected, non-invasive on-farm data. Our findings support the integration of neural and Ensemble learning models into automated health monitoring systems to enable earlier disease detection and improved animal welfare. Although external validation was not performed, internal cross-validation demonstrated consistent performance across models, suggesting suitability for application in multi-farm settings. To the best of our knowledge, this is among the first studies to apply ML for early metritis detection based exclusively only automated herd data. Full article

We used an animal welfare-certified open-type layer farm and analyzed the egg production, egg quality, rectal temperature, and yolk corticosterone levels of laying hens supplied with cool water during the summer season (avg. 33 ± 3.89 °C). A total of 5750 Hy-Line Brown laying hens at 53 weeks of age were used, and two treatment groups were established: a control group (2900 hens) and a cool water treatment group (2850 hens). The water temperature of the control group was 25.3 ± 0.8 °C and the cool water was 20.1 ± 0.3 °C; all other environment parameters (lighting, ventilation, temperature, feed, etc.) were the same. The experiment was conducted for a total of 9 weeks (between July and September 2024), and during this period, the temperature–humidity index (THI) inside the breeding facility averaged 85.21, which corresponds to the cool water supply range (80 < THI < 90). As a result, the cool water treatment group maintained high productivity and showed low mortality (p < 0.05). In addition, hens provided with cool water showed high eggshell strength and low yolk corticosterone levels (p < 0.05). The core finding of this study is that the supply of cool water in summer is effective in maintaining the productivity and egg quality of laying hens and reducing HS. This is significant in that it suggests it is possible to manage laying hens in summer in a simple way, and it can also be used as basic data for designing future studies, such as using a combination of natural products including vitamins and minerals. Full article