Preventive veterinary medicine最新文献

{"title":"Improving cestode diagnosis in domestic dogs and cats: the need for accurate and non-invasive techniques","authors":"Georgiana Deak,&nbsp;Adriana Györke,&nbsp;Cristina Daniela Pop,&nbsp;Viorica Mircean","doi":"10.1016/j.prevetmed.2025.106654","DOIUrl":"10.1016/j.prevetmed.2025.106654","url":null,"abstract":"<div><div>Cestode infections in companion animals pose a significant diagnostic challenge due to intermittent egg shedding and the limitations of traditional coproscopic techniques. This study aimed to evaluate the performance of microscopy and PCR in detecting cestodes in dogs and cats, using necropsy as the gold standard.</div><div>A total of 81 animals (46 dogs and 35 cats) were examined by necropsy, with gastrointestinal tracts inspected for cestodes. Fecal samples were collected and analyzed by coproscopy and PCR targeting cestode infections.</div><div>Necropsy identified cestodes in 7 (8.6 %; 95 % CI: 4.3 – 16.8) out of 81 animals: <em>Dipylidium caninum</em> was found in 3 (3.7 %; 95 % CI: 1.3 – 10.3) of animals (1/46 dogs; 2/35 cats), and <em>Hydatigera taeniaeformis</em> in 4 (11.4 %; 95 % CI: 4.5 – 26.0) out of 35 cats. Coproscopy and PCR detected only infection with <em>H. taeniaeformis</em> in 2 (5.7 %; 95 % CI: 1.6 – 18.6), and 3 (8.6 %; 95 CI: 3.0–22.4) cats, respectively., No PCR positives were recorded for <em>D. caninum</em>, despite its presence at necropsy. Overall agreement with necropsy was moderate for both methods (coproscopy k = 0.42; PCR k = 0.58), with higher sensitivity and agreement for <em>Taenia</em> spp. and <em>H. taeniaeformis</em> detection. These findings highlight the poor sensitivity of current non-invasive diagnostic methods for cestodes, particularly <em>D. caninum</em>, and the limited correlation between infection intensity and fecal detection. The study advocates for the urgent need for a commercially available coproantigen test to improve the accuracy of diagnosis.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106654"},"PeriodicalIF":2.4,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cannabidiol treatment for refractory idiopathic epilepsy in dogs: A systematic review with risk of bias assessment","authors":"Helene Ane Jensen ,&nbsp;Abbey Olsen ,&nbsp;Maja Arendt ,&nbsp;Peter Sandøe ,&nbsp;Søren Saxmose Nielsen","doi":"10.1016/j.prevetmed.2025.106649","DOIUrl":"10.1016/j.prevetmed.2025.106649","url":null,"abstract":"<div><div>We conducted a systematic literature review of randomised controlled trials (RCTs) on the use of cannabidiol (CBD) as a supplementary treatment for refractory idiopathic epilepsy in dogs. The objective was to summarise the efficacy and adverse effects of CBD treatment and assess the potential risk of bias in conducted studies, including an assessment of the effects thereof on the evaluation of CBD for clinical use. Studies were included in the review if they were RCTs comparing groups of dogs with refractory idiopathic epilepsy treated with CBD oil or placebo oil, respectively. The outcomes had to be efficacy and adverse effects of the treatment. English-language reports of studies published in any year were considered. A total of three studies were included in the review. All studies suggested a reduction in seizure frequency during CBD treatment, and all observed ataxia as an adverse effect of CBD treatment or a reason for withdrawal from the studies. Additionally, studies found increased levels of serum alkaline phosphatase (ALP) in dogs treated with CBD. Adverse effects included vomiting and diarrhoea, changes in appetite, behavioural changes and somnolence. The studies were characterised by a moderate to high risk of bias, which affected their validity and reliability. Based on the existing literature, it is not possible to draw conclusions concerning the efficacy and potential adverse effects of CBD as a supplementary treatment for refractory idiopathic epilepsy in dogs, and more high-quality studies are needed to evaluate clinical efficacy, the optimal treatment dose and adverse effects.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"245 ","pages":"Article 106649"},"PeriodicalIF":2.4,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144866602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cost assessment of a preventive vaccination program against highly pathogenic avian influenza in Austrian poultry farms","authors":"Tatiana Marschik ,&nbsp;Susanne Sawodny ,&nbsp;Ian Kopacka ,&nbsp;Andrea Höflechner-Pöltl ,&nbsp;Sandra Revilla-Fernández ,&nbsp;Irene Zimpernik ,&nbsp;Friedrich Schmoll ,&nbsp;Annemarie Käsbohrer","doi":"10.1016/j.prevetmed.2025.106655","DOIUrl":"10.1016/j.prevetmed.2025.106655","url":null,"abstract":"<div><div>The ongoing global epidemic of highly pathogenic avian influenza (HPAI) has led to the culling of millions of birds across the European Union and beyond. In response, preventive vaccination has been increasingly considered alongside existing measures to control HPAI in poultry. This study focusses on the costs and logistical implications of a potential preventive vaccination program for HPAI in Austrian poultry farms across multiple scenarios, considering different animal and production types, vaccination areas, and vaccination periods. Results show that targeting high-density poultry areas, specific farm types, and seasonal risks can optimize resources and reduce costs. Depending on the scenario, the total cost per vaccinated animal ranges from €1.52 to €4.06. Sensitivity analysis identifies vaccine costs and post-vaccination diagnostics as key cost drivers. The 2024 outbreak season resulted in an estimated €3 million in control-related costs in Austria, with most affected farms located in predefined high-risk zones, highlighting the potential cost-effectiveness of targeting vaccination efforts in these areas. This study provides a basis for policymakers to assess vaccination cost-effectiveness, supporting decisions on implementing an economically viable program to prevent HPAI outbreaks in Austria and other comparable settings.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106655"},"PeriodicalIF":2.4,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatial and temporal risk assessment of Epizootic Hemorrhagic Disease Virus introduction in Europe: A comparative analysis of trade and wind dispersal pathways","authors":"Amandine Bibard ,&nbsp;Davide Martinetti ,&nbsp;Albert Picado ,&nbsp;Karine Chalvet-Monfray ,&nbsp;Thibaud Porphyre","doi":"10.1016/j.prevetmed.2025.106656","DOIUrl":"10.1016/j.prevetmed.2025.106656","url":null,"abstract":"<div><div>Epizootic Hemorrhagic Disease Virus (EHDV), transmitted by <em>Culicoides</em> biting midges, is a threat for the livestock sector in Europe. A quantitative risk assessment model framework was developed to assess the risk of EHDV introduction in Europe, through wind dispersal of <em>Culicoides</em> and trade in live animals. The model integrates meteorological data, wind trajectories, vector biology, livestock trade information and considers disease dynamic in infected sources as well as disease susceptibility in potential destinations. The full risk zone combining both pathways encompassed 42 different countries with 30 in Europe and 12 outside, each with highly-variable levels of risk. The highest risk countries included three sources: France, Spain, Italy, and one disease-free, Germany. The period of highest risk corresponded to the favourable period of <em>Culicoides</em> activity, between May and October. Risk estimates were markedly higher for the wind pathway, spanning 20 countries mainly in Western Europe, compared to the trade pathway that covered 40 countries, including distant Eastern ones, like Romania. The Pathway Risk Ratio (PRR) showed a higher wind pathway contribution in most countries where both pathways were present. France was the primary source country, regardless of the pathway. Alternative scenarios suggested that limiting the source area to 2024 infected areas or considering long trade history could reduce the list of at-risk countries. However, underreporting or reducing PCR testing at borders could increase risk estimates. This research aims to guide disease risk management measures by providing insights into the risk of <em>Culicoides</em>-borne disease extension.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"245 ","pages":"Article 106656"},"PeriodicalIF":2.4,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An assessment of knowledge, attitudes, and practices concerning rabies among communities with a high disease risk in Timor-Leste","authors":"Abrao J. Pereira ,&nbsp;Deolindo Ximenes ,&nbsp;Alberto A.D.C. João ,&nbsp;Marito B. Gomes ,&nbsp;Nicodemos B. Lonai ,&nbsp;Joanita Bendita D.C. Jong ,&nbsp;Shawn Ting","doi":"10.1016/j.prevetmed.2025.106653","DOIUrl":"10.1016/j.prevetmed.2025.106653","url":null,"abstract":"<div><div>Timor-Leste reported its first rabies outbreak in March 2024, making it an emerging zoonotic health threat in the country. However, there was a lack of information about community knowledge, attitudes, and practices (KAP) regarding rabies which is crucial for informing disease response plans. This study investigated the KAP regarding rabies among communities in high-risk areas for rabies incursion and spread. Between July to September 2023, 660 heads of households were interviewed using structured questionnaires in municipalities bordering Indonesian West Timor, and Dili municipality. Dog ownership by households was high (65.3 %, 431/660) and almost all households that owned dogs allowed free-roaming of dogs (98.1 %, 423/431). A small proportion of participants (2.3 %; 15/660) imported dogs from Indonesia. Around half of the participants (52.3 %, 345/660) have heard of rabies, and the majority of these participants were knowledgeable about the disease (86.7 %, 299/345). Almost one-third (30.8 %, 203/660) of households reported dog bite events and only two-thirds of households that experienced dog bites in the last 12 months (67.0 %, 132/197) reported seeking professional medical assistance. Multivariable logistic regression showed that participants with higher education and from Dili municipality were more likely to have positive attitudes towards rabies prevention. This study found limited community awareness about rabies, but positive attitudes towards rabies prevention. Healthcare-seeking behaviour was poor following dog bite events. There is a need to enhance rabies risk communication and community engagement to improve dog rabies vaccination uptake, health-seeking behavior after dog bites, and prevention of unauthorized import and in-country movement of dogs.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106653"},"PeriodicalIF":2.4,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting future tropical theileriosis risk in China using tick distribution and climate models","authors":"Tao Zhang ,&nbsp;Mengshi Yan ,&nbsp;Jiaqi Fang ,&nbsp;Xinyao Li ,&nbsp;Lili Wang ,&nbsp;Haoran Wang","doi":"10.1016/j.prevetmed.2025.106652","DOIUrl":"10.1016/j.prevetmed.2025.106652","url":null,"abstract":"<div><div>Tropical theileriosis, caused by <em>Theileria annulata</em>, is a tick-borne protozoan disease with high morbidity and mortality rates. While climate change and expanding livestock trade may increase transmission risks, the spatial distribution dynamics of tropical theileriosis in China under future climate scenarios remain poorly understood. This study aimed to predict the future distribution dynamics of tropical theileriosis in China by integrating climate variables and tick vector distribution data. We developed two MaxEnt-based prediction frameworks: one incorporating 19 climatic variables alone, and another combining these with distribution data of four major tick vectors (<em>H. scupense</em>, <em>H. anatolicum</em>, <em>H. detritum</em>, and <em>H. asiaticum</em>). Risk zones were projected across three periods (2021–2041, 2041–2060, and 2061–2080) under three climate scenarios (SSP126, SSP245, and SSP585). Model performance was evaluated using the Area Under Curve (AUC) metric. The results showed that integration of tick vector distribution data improved model prediction accuracy (AUC: 0.874–0.882). Current high-risk zones, predominantly in central and northwestern China, showed strong correlation with <em>H. detritum</em> distribution. Under future climate scenarios, the model projected a contraction of tick vector habitable areas and disease risk zones. The most substantial reduction (14.39 %) was predicted for 2061–2080 under the SSP126 scenario. This study provides a systematic assessment of tropical theileriosis risk dynamics in China under climate change scenarios. The improved prediction accuracy achieved through vector distribution integration emphasizes the importance of combining vector ecology with climate data in disease risk modeling. These findings support the development of targeted prevention strategies that account for both vector distribution patterns and regional climate characteristics. Future disease management planning should prioritize vector surveillance and formulate relevant policies to effectively reduce the risk of disease transmission.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106652"},"PeriodicalIF":2.4,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An economic evaluation of preventing vs. suppressing HPAI outbreaks: A case study from Iowa","authors":"Peter Koppes ,&nbsp;Travis Guerrant ,&nbsp;David Marks ,&nbsp;Eric Balcerzak ,&nbsp;Jill Brown ,&nbsp;Matt Harman ,&nbsp;Stephanie Shwiff","doi":"10.1016/j.prevetmed.2025.106651","DOIUrl":"10.1016/j.prevetmed.2025.106651","url":null,"abstract":"<div><div>This study presents an analysis comparing the costs of preventing Highly Pathogenic Avian Influenza (HPAI) in Iowa's poultry industry through wildlife management versus the costs of suppressing outbreaks once they occur. Using data from the USDA Animal and Plant Health Inspection Service's Veterinary Services and Wildlife Services, we conducted a cost-effectiveness analysis of prevention activities that reduce interactions between wild birds and domestic poultry. Our findings demonstrate that prevention efforts cost approximately $0.05 per bird, while suppression activities average $8.15 per bird in Iowa ($11.86 nationally). Results indicate that wildlife-based prevention programs would be cost-efficient, under current expenditures, if they reduced HPAI incidence by just over 3 %. The study provides compelling evidence that preventive wildlife management represents an opportunity for a more cost-effective approach to HPAI control compared to suppression measures alone, particularly given the recurrent and extensive economic impacts of recent outbreaks that have affected over 97 million birds nationally since 2022 and cost over $1.13 billion in response activities. These findings identify the need for continued evaluation of approaches to disease management to enhance the resilience of the U.S. poultry industry against the persistent threat of HPAI.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106651"},"PeriodicalIF":2.4,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144810235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seasonal trend analysis of sporotrichosis with zoonotic potential","authors":"Dafne Fontoura de Lima ,&nbsp;Juliana Batista Andrade Silva ,&nbsp;Wilson Mansho ,&nbsp;Nilson Roberti Benites","doi":"10.1016/j.prevetmed.2025.106632","DOIUrl":"10.1016/j.prevetmed.2025.106632","url":null,"abstract":"<div><div>Sporotrichosis is a zoonotic subcutaneous mycosis caused by fungi of the genus Sporothrix. It is considered a neglected disease, already reported in almost all Brazilian states in both animals and humans, highlighting the urgent need to understand the disease's behavior to guide public control and surveillance policies. Therefore, the objective of this study was to elucidate the hypothesis of seasonality in sporotrichosis based on the cases recorded in the municipality of Guarulhos, where notification is mandatory. For this purpose, animal sporotrichosis cases from 2016 to 2023 were provided by the Guarulhos Zoonosis Control Center, along with the date of the first consultation, and analyzed through observation of time series and their moving averages, and statistical comparisons between the seasons. Two models were used for time series decomposition: classical decomposition and seasonal trend decomposition (STL). Both models revealed a seasonal component with a uniform and repetitive pattern, showing little correlation with the residuals of the decomposition. The moving averages displayed annual fluctuations, with more cases recorded in the central months of the year (autumn and winter), supporting the hypothesis of a seasonal pattern of the disease. However, the comparison of case numbers between seasons using an ANOVA test indicated no statistical difference between the seasons, with p = 0.810. It is concluded there is a indication of potential seasonality, which reinforces the importance of implementing preventive and control measures targeting feline populations.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106632"},"PeriodicalIF":2.4,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144757154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characteristics and spatio-temporal distribution of fetal loss in thoroughbred mares in New South Wales, Australia","authors":"Cara S. Wilson ,&nbsp;Joan Carrick ,&nbsp;Angela Begg ,&nbsp;Pat Shearer ,&nbsp;Melinda Stewart ,&nbsp;Victoria J. Brookes","doi":"10.1016/j.prevetmed.2025.106635","DOIUrl":"10.1016/j.prevetmed.2025.106635","url":null,"abstract":"<div><h3>Introduction</h3><div>Despite emerging disease syndromes in Australian Thoroughbred horses in recent years, there is no formal surveillance for fetal loss in the industry. This study aimed to characterise the distribution of equine pregnancy loss &gt; 45 days of gestation in a major Thoroughbred breeding region to provide insights into causes, prevention, and surveillance feasibility.</div></div><div><h3>Methods</h3><div>Data were collected from 574 fetal loss submissions to veterinary pathology services between February 2015 and November 2021. Variables included date of fetal loss, gestational age, diagnosis, foal weight, and mare age. Diagnoses were grouped into 14 categories, including infectious and non-infectious causes. Time-series analysis was conducted to identify trends and seasonality, while spatial analysis used Kulldorf’s space-time permutation scan statistic to detect spatio-temporal clusters of fetal loss cases.</div></div><div><h3>Results</h3><div>Of the 574 cases analysed, 467 had a confirmed cause, with infectious agents responsible for 54 % and non-infectious causes for 46 %. The most common diagnoses were cord occlusion (19.5 %) and unknown causes (18.6 %). Time-series analysis revealed seasonal trends in fetal loss, with a peak in 2016 due to a <em>Chlamydia psittaci</em> placentitis outbreak. This was also the only cause for which spatial clusters were identified.</div></div><div><h3>Conclusion</h3><div>The findings indicate that, while cases of twinning and EHV-1 still exist, conditions such as placentitis due to <em>C. psittaci</em> are emerging. Despite these changes, the overall predictable temporal distribution of pregnancy loss indicates the potential for early outbreak detection within a surveillance system for Thoroughbred pregnancy loss in this region.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106635"},"PeriodicalIF":2.4,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating machine learning classifiers and explainability for monitoring cow behaviour with wearable nose rings","authors":"Daniel Edison Essien ,&nbsp;Saviour Inyang ,&nbsp;Imeh Umoren","doi":"10.1016/j.prevetmed.2025.106630","DOIUrl":"10.1016/j.prevetmed.2025.106630","url":null,"abstract":"<div><div>Wearable technologies are revolutionizing precision livestock monitoring by allowing continuous real-time monitoring of animal behaviour. This study investigates and evaluates the use of machine learning techniques to classify dairy cow behaviours using tri-axial accelerometer data collected from novel wearable nose ring sensor. The raw dataset initially included five distinct behaviours: Feeding, Ruminating, Standing, Lying and Walking. However due to data imbalance and data limitations we refined the classification to three core categories: Feeding, Rumination and Walking. While previous studies on this dataset focused solely on Long Short-Term Memory(LSTM) network, the comparative potential of other models remained unexplored. To address this gap, we performed a comparative study on multiple classifiers, including Random Forest (RF), Artificial Neural Network (ANN), Gated Recurrent Unit (GRU) and a hybrid Convolutional Neural Network with LSTM (CNN-LSTM). The obtained results showed that GRU model performed well with an accuracy of 97.78 %, followed by CNN-LSTM, ANN and RF which scored 97.78 %, 68.27 % and 67.6 % respectively. To enhance model transparency, Explainable AI techniques were utilized. SHAP and LIME were utilized to showcase feature importance and interpretability of these models. These findings showcase the effectiveness of deep learning models (GRU, CNN-LSTM) and emphasizes the importance of model explainability in precision livestock management.</div></div>","PeriodicalId":20413,"journal":{"name":"Preventive veterinary medicine","volume":"244 ","pages":"Article 106630"},"PeriodicalIF":2.4,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}