Omneity® Pellets
All-In-One Vitamin & Mineral Pellet
Topic:Predictive Model
Predictive models in equine research involve the use of statistical and computational techniques to forecast outcomes related to horse health, performance, and behavior. These models integrate various data inputs, such as genetic information, physiological parameters, and environmental factors, to predict future events or conditions. Applications of predictive models in equine science include anticipating disease outbreaks, assessing performance potential, and optimizing breeding strategies. By analyzing historical and real-time data, these models can provide insights that assist in decision-making processes. This page compiles peer-reviewed research studies and scholarly articles that explore the development, validation, and application of predictive models in the context of equine science.
Development of a prognostic scoring system for systemic inflammatory response syndrome in donkeys. Systemic inflammatory response syndrome (SIRS) is associated with increased mortality in horses with gastrointestinal (GI) disease. However, there are no data relating to naturally occurring SIRS in donkeys. Objective: To determine SIRS frequency in donkeys with GI disease. To develop a donkey-specific prognostic SIRS score. Methods: Retrospective case series. Methods: Clinical records from donkeys presenting with GI disease in two independent cohorts (development cohort: n = 400, UK; validation cohort: n = 36, Australia) were reviewed. Age, sex, heart rate, respiratory rate, rectal te...
Water and cryoprotectant permeability of mature equine oocytes: experimental measurements and in silico predictions. Vitrification of equine oocytes is an essential practice for advancing assisted reproductive technologies however, its efficiency remains limited due to the lack of stage and species-specific information on membrane permeability parameters. In this study, water (L) and CPA permeability (P) for dimethyl sulfoxide (Me₂SO) and ethylene glycol (EG) were measured in in vitro matured (MII) equine oocytes. Cumulus oocyte complexes were obtained from abattoir ovaries or by ovum pick-up and matured in vitro for 30 h at 6% CO. Oocytes followed ideal osmometer behavior principles, with an osmotically ...
A Genetic Algorithm-Based Approach for Quantitative Prediction of Drug-Drug Interactions Caused by Cytochrome P450 3A Inhibition or Induction in Horses. A genetic algorithm (GA)-based approach was designed to predict drug-drug interactions (DDIs) triggered by cytochrome P450 3A (CYP3A) inhibition or induction in horses. Area under the concentration-time curve ratios (AUCRs), obtained from published in vivo DDI studies in horses, were used to compute the following parameters: (1) the contribution ratio (CR), i.e., the fraction of the substrate dose metabolized via the CYP3A pathway, and (2) the interacting drug's inhibitory potency or inducing efficacy (IR or IC, respectively). AUCRs for 9 substrates, 12 inhibitors, and 1 inducer of equine C...
Comparison of Two Different Finite Element Modeling Pipelines for Virtual Mechanical Testing of The Distal Third Metacarpal Bone In Thoroughbred Racehorses. Condylar stress fracture of the third metacarpal bone (MC3) in Thoroughbred racehorses is a common catastrophic injury and identification of horses at heightened risk remains subjective. Standing computed tomography (sCT) is a practical screening tool that enables patient-specific finite element analysis (FEA) of the distal MC3 and prediction of subchondral bone strain, as a potential objective classifier of racehorses at heightened risk. The goal of this study was to compare two independently developed sCT-based subject-specific FEA pipelines for virtual mechanical testing of the distal MC3. ...
Venous blood lactate concentration as a predictor of intestinal viability in horses with acquired indirect inguinal hernia. Background: Acquired indirect inguinal hernia represents a life-threatening emergency. Therapeutic decision-making largely depends on intestinal viability, for which specific predictive parameters (such as venous lactate) have not been evaluated.Objectives: Investigating the predictive performance of venous blood lactate and other laboratory results on intestinal viability in horses with acquired indirect inguinal hernias.Study designRetrospective multicentre observational study.Methods: Seventy-four horses diagnosed with acquired indirect inguinal hernia (treated surgically) at two referral h...
Risk assessment of West Nile fever in equines in Europe based on an ecological niche model. West Nile fever is a zoonotic viral disease transmitted by Culex mosquitoes, capable of causing severe neurological illness in humans, equines, and birds. Over the past dozen years, Europe has experienced numerous WNF outbreaks of varying severity, leading to significant public health and economic impacts. Consequently, WNF has emerged as a major concern for both public health and veterinary sectors. In this study, we employed spatiotemporal analysis techniques alongside an optimized ecological niche model to investigate the spatiotemporal distribution patterns of historical WNF outbreaks, pre...
Monitoring horse behaviour with deep learning models. Detailed analysis of stabled horse behaviour can reveal accurate information about its well-being. Advances in deep learning now allow these behaviours to be tracked without being invasive through the use of video data. This study evaluated a convolutional neural network for recognising standing, lying, and drinking behaviours in a horse housed in a wooden stall and recorded continuously over 29 consecutive days. Model predictions were compared with manually annotated ground truth data. Standing was detected with high precision (97.5%) and high recall (89.2%). Lying behaviour was classified wi...
Audio-Based Characterization of Gait Parameters in Mangalarga Marchador, Campolina, and Piquira Horses Using Deep Learning. The evaluation of biomechanical parameters in four-beat gaited horses remains limited by the subjectiveness and complexity of current standard methods. Through a deep learning approach, we aimed to infer dissociation % using only acoustic signals. A total of 268 audio samples were extracted from publicly available videos featuring three Brazilian horse breeds (Mangalarga Marchador, Campolina, and Piquira) performing marcha batida and marcha picada. Acoustic features, including root mean square energy (RMS), zero-crossing rate (ZCR), and 13 Mel-frequency cepstral coefficients (MFCCs), were extr...
ProAKAP4 as a predictor of semen freezability in Asturcon ponies. Cryopreservation is a valuable tool in equine reproduction, although its success remains highly variable among stallions. The proAKAP4 protein has been proposed as a molecular marker of sperm quality and cryotolerance. Objective: This study aimed to evaluate the relationship between proAKAP4 concentration and sperm cryotolerance in ejaculates from Asturcon ponies, and to assess whether proAKAP4 levels in fresh semen can predict post-thaw sperm quality parameters before and after cryopreservation. Methods: Twenty-four ejaculates from eight different stallions were used (three ejaculates per ani...
Multi-Modal Feature Fusion and Hierarchical Classification for Automated Equine-Human Interaction Behavior Recognition. Automated recognition of equine-human interaction behaviors from video represents a significant challenge in computational ethology, with critical applications spanning animal welfare assessment, equine-assisted services evaluation, and safety monitoring in equestrian environments. Existing approaches to animal behavior recognition typically focus on single species in isolation, rely solely on facial expression analysis while ignoring full-body posture, or employ flat classification architectures that fail under the severe class imbalances characteristic of naturalistic behavioral datasets. Fu...
Perspectives of UK horse carers towards the use of artificial intelligence in equine healthcare. Artificial intelligence (AI) is becoming increasingly prevalent in the modern world, including in veterinary medicine. This cross-sectional study aimed to investigate horse carers' attitudes towards using AI use in equine care. Methods: An online survey was distributed to UK horse owners/carers in 2025, covering participants' demographics and use of AI and their opinions of AI for equine care. Statistical analysis included descriptive statistics, categorisation of free-text responses and logistic regression to determine factors associated with opinions. Results: Ninety-seven resp...
Preoperative risk assessment in horses: agreement and predictive value of CHARIOT (Combined Horse Anaesthetic Risk Identification and Optimisation Tool). To assess interobserver agreement and predictive value of the Combined Horse Anaesthetic Risk Identification and Optimisation Tool (CHARIOT) compared with the American Society of Anesthesiologists Physical Status (ASA-PS) classification system among five groups of evaluators with different levels of expertise, and to explore the association between risk scores and 7-day postoperative mortality. Methods: Prospective, observational, single-centre pilot study. Methods: A group of 50 client-owned horses. Methods: Each horse was assessed (ASA-PS and CHARIOT) before general anaesthesia by one evalua...
Detection of exercising ectopic atrial and ventricular beats using non-linear analysis of clinically normal racehorse electrocardiograms at rest or low-intensity exercise. Cardiac arrhythmias are common in healthy athletic horses and may lead to poor athletic performance or exercise-associated sudden death. Early detection of high-risk horses is an important goal of cardiovascular diagnostics. We hypothesised that non-linear analysis of electrocardiogram disorderliness can be used to identify horses exhibiting intermittent ectopic atrial and ventricular heart rhythm abnormalities at exercise using brief, artifact-free recordings of normal sinus rhythm electrocardiograms collected at submaximal heart rates. In a convenience prospective cross-sectional study, ambu...
Machine learning-based prediction and quantification of OCD surgery and pedigree effects on racehorse performance. Osteochondritis dissecans (OCD) is a common developmental orthopedic condition in Thoroughbred racehorses and although arthroscopic surgery is widely used for treatment, its long-term effects on race performance remain unclear. This retrospective study evaluated the effect of OCD surgery on race performance, compared the predictive power of pedigree and management variables and applied interpretable machine learning methods for forecasting race performance outcomes. Data were collected from 75 Thoroughbreds that underwent OCD surgery between 2015 and 2017 and 257 maternal siblings without reco...
Deep learning cascade networks for segmentation of fluorine-18 sodium fluoride positron emission tomography scans of equine metacarpo- and metatarsophalangeal joints outperform atlas-based method. To create a labeled dataset and evaluate a convolutional neural network (CNN) for segmentation of fluorine-18 sodium fluoride PET scans of the equine metacarpo- and metatarsophalangeal joint (fetlock), targeting the third metacarpal bone, proximal phalanx, proximal sesamoid bone(s), and soft tissue. Unassigned: PET and corresponding CT scans were retrospectively selected from June 2024 through November 2025 using convenience sampling and coregistered to a common reference frame. The coregistered PET-CT scans were manually labeled; the labels were then transferred to PET-only images and used to...
The majority of proximal sesamoid and condylar fractures occurred in horses identified as high risk by inertial measurement unit sensors. To determine whether targeted lesion-specific algorithms developed from data collected with accelerometer-based inertial measurement units worn by racing Thoroughbreds could retrospectively identify horses at high risk of incurring forelimb condylar or proximal sesamoid fractures. Unassigned: Fracture-specific algorithms were generated from July 2021 to December 2024 with accelerometer data from 42,623 races by 15,755 horses, including 54 races by 23 horses that subsequently suffered condylar fractures and 90 races by 31 horses that later sustained proximal sesamoid fractures. Fracture-specifi...
Bridging Species with AI: A Cross-Species Deep Learning Model for Fracture Detection and Beyond. Fractures are a leading cause of morbidity and mortality in Thoroughbred racehorses, posing a significant threat to their welfare and careers. This study introduces a deep learning model specifically designed to facilitate fracture detection in equine athletes. By leveraging extensive training on human fracture data and refining the model with equine imaging, it highlights the transformative potential of transfer learning across species and medical contexts. This approach is not limited to equine fractures but could be adapted for use in detecting injuries or conditions in other veterinary spe...
Evaluation of Pulse Pressure as a Hemodynamic Marker of Cardiac Disease in Dogs and Horses Undergoing Pre-Anesthetic Assessment. Pulse pressure (PP) reflects ventricular stroke volume and arterial compliance, but its utility as a marker of cardiac disease in animals is not well established. This study evaluated the association between PP and echocardiographically confirmed cardiac abnormalities in dogs and horses and assessed its potential in pre-anesthetic evaluation. Clinical and echocardiography examination of 20 dogs and 20 horses was sufficient for inter-group comparisons and assignments to a Cardiac group (echocardiographically confirmed cardiac disease) or a Control group (healthy animals). Non-invasive oscillome...
Space-use by feral cattle and horses shapes vegetation structure in a trophic rewilding area. Feral cattle (Bos taurus) and horses (Equus ferus caballus) are commonly introduced to European rewilding areas to halt vegetation succession and to conserve light-demanding species. Yet, we still do not understand how the habitat preference of animals shapes vegetation structure at the landscape scale. Here, we used spatial preference modeling to understand drivers of space-use based on GPS-collared horses and cattle in a 120-ha rewilding area in Denmark. Using a time series of a satellite-based vegetation productivity index, we tested the ability of animal space-use to explain changes in veg...
Relationship Between Mean Faecal Gastrointestinal Nematode Egg Excretion in Horses and Its Variability: Implications for Control. Faecal egg counts (FECs) are used to assess the intensity of gastrointestinal nematode (GIN) infections in herbivores. FEC distribution is aggregated, meaning that approximately 20% of animals harbour 80% of infections. In times of escalating anthelmintic resistance, it may be necessary to restrict treatment to the animals with the heaviest infections. This strategy is called targeted selective treatment (TST) and is relevant to GIN, for example. The difficulty lies in identifying which animals to treat. One solution is to select potentially at-risk animals based on age (for example, treating ...
Development of an Explainable Machine Learning Computational Model for the Prediction of Severe Complications After Orchiectomy in Stallions. The objective of the present study was to apply supervised Machine Learning to predict severe complications after equine orchiectomy. A dataset of 612 cases of orchiectomies in stallions was used for the development of a computational model, among which in 8.5% of cases severe complications (colic, continued stallion-like behaviour, evisceration, funiculitis, haemorrhage, and scrotal infection) were diagnosed post-orchiectomy. Three supervised Machine Learning tools were employed: Logistic Regression (12 different models evaluated), Random Forest (64 models), and Gradient Boosting (8 models). ...
Complications Following Orchiectomy in Stallions in Field Conditions: Descriptive Results and Predictors in a Study of 612 Cases. The objectives of this work were (i) to evaluate the incidence of complications in male horses after orchiectomy performed in the field, i.e., away from a veterinary hospital, (ii) to describe the post-operative complications that occurred in these animals and (iii) to study the potential predictors for the development of such complications. This study involved 612 animals, on which orchiectomy was performed. The operative part of the study was carried out by one of three experienced veterinary surgeons. Standard pre-operative procedures were followed. Orchiectomy was performed using one of th...
Herding as an emergent behaviour in harem groups of feral Garrano ponies. Collective decision-making and movement coordination are essential behaviours observed in biological systems, from animal herds to human crowds. Horses are a highly social species with a multilevel society. Herding, where the harem is collected to move in a certain direction, is an often-cited example of agonistic behaviour in horses, yet poorly understood in a granular, quantitative sense. We use transfer entropy to measure herding in a harem group of feral Garrano ponies in Serra D'Arga, Portugal. First, we characterize the harem's leader-follower relationships by quantifying the time lag (a...
Equine fetal-sex determination from mid-gestation to term using serum conjugated steroid profiling by liquid chromatography-tandem mass spectrometry. Refined profiling of conjugated estrogens and androgens during equine pregnancy using liquid chromatography-tandem mass spectrometry (LC-MS/MS) could provide accurate fetal-sex determination. Current methods for fetal-sex prediction remain limited by timing, accuracy, and operator expertise. This study investigated sex-specific differences in maternal conjugated steroid profiles to develop a reliable, non-invasive predictive method. Samples were collected from 141 mares of various breeds starting at sixteen weeks of pregnancy. The samples were pooled according to gestational stage, divided int...
Evaluating the Accuracy of a Vision-Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles. Equine lameness diagnosis largely relies on subjective visual assessments, which can be biased. Although marker-based methods, force plates and inertial measurement units (IMUs) provide objective measurements, they require specialized setups. Vision-based algorithms offer a portable, markerless alternative, but their accuracy needs thorough testing. Objective: To evaluate a custom vision-based algorithm for estimating the groundline across multiple camera angles, including handheld use in horses trotting on a treadmill. Methods: Experimental comparative study. Methods: Eight Standardbred trott...
Standing CT-based finite element models efficiently identify regions of high mechanical strain in equine metacarpal subchondral bone. Stress fractures are common in racehorses, with the metacarpophalangeal (MCP) joint being the most frequently affected site as it is subjected to high-magnitude and high-rate cyclic loads during training and racing. These loads lead to repeated compressive stresses, resulting in subchondral bone (SCB) sclerosis, fatigue microcracks, and matrix damage that can progress to parasagittal fractures or palmar osteochondral disease (POD). The present study developed joint-specific 3D FE models and slice-based FE models using standing CT images for three trained racehorses, each presenting distinct SC...
Is There a Genetic Link Between Resting Infrared Thermography in Young Horses and Longevity in Jumping Competition? The objective was to evaluate the genetic relationship between the surface temperature of regions of interest, measured using infrared images of young horses and functional longevity in jumping. This relationship was assessed by comparing the temperatures measured in the offspring of two groups of sires, one favourable and one unfavourable, to longevity. The study used a specific data collection protocol on a sample of 921 young progeny, before they began competing, of 141 extreme stallions, comprising 61 favourable and 80 unfavourable sires. These stallions had been selected based on estimate...
Using Satellite Remote Sensing to Estimate Rangeland Carrying Capacity for Sustainable Management of the Marismeño Horse in Doñana National Park, Spain. Rangeland degradation poses a serious challenge for the sustainable management of free-ranging livestock in Mediterranean wetlands. In National Park, Spain, the endangered horse depends exclusively on natural forage, making it essential to monitor vegetation productivity and grazing suitability under increasing climate variability. This study presents a satellite-based assessment of rangeland carrying capacity to support the adaptive management of this iconic breed. A six-year time series (2015-2020) of 1242 images from Landsat 8 OLI/TIRS and Sentinel-2 (L1C/L2A) was processed using ILWIS an...
A modern AI framework integrating deep imputation, synthetic data balancing, and explainable modeling for survival prediction in horse colic. Artificial intelligence (AI) has emerged as one of the most transformative tools for developing clinical decision-support systems in veterinary medicine. Despite its growing use, its full potential remains underutilized in equine medicine, an area of both high economic and clinical importance. Accurate survival prediction in horses with colic is crucial for timely intervention and improved clinical outcomes. Methods: This study aimed to predict survival outcomes in horse colic cases by developing models that combine traditional machine-learning algorithms (XGBoost, Light Gradient Boosting Mach...
Fine-scale assessment of ROH patterns and genomic inbreeding in diverse horse breeds using two SNP array densities. Inbreeding is caused by mating between related individuals and is associated with reduced fitness and performance. Generally, in the horse population, inbreeding is caused by geographically restricted areas and intensive natural or artificial selection. For this reason, assessing accurate inbreeding is essential for developing and implementing effective breeding strategies aimed at preserving genetic diversity and reducing the harmful consequences of inbreeding. One of the most accurate approaches for assessing genomic inbreeding and autozygosity is through the analysis of runs of homozygosity...
