Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
The Horse Grimace Pain Scale with images and explanations for each of the 6 facial action units (FAUs). Each FAU is scored according to whether it is not present (score of 0), moderately present (score of 1) and obliviously present (score of 2).
Source publication
The assessment of pain is critical for the welfare of horses, in particular when pain is induced by common management procedures such as castration. Existing pain assessment methods have several limitations, which reduce the applicability in everyday life. Assessment of facial expression changes, as a novel means of pain scoring, may offer numerous...
Citations
... Additional recent research has been done to assess the use of machine learning in recognition of horse expressions and behavior related to welfare, specifically in using the equine pain face [64] and grimace scale [65,66]. Studies in 2018 and 2021 supported the use of machine learning to recognize facial expressions of horses, especially related to the research on facial expressions related to pain [67,68]. ...
This research applies unsupervised learning on a large original dataset of horses in the wild to identify previously unidentified horse emotions. We construct a novel, high-quality, diverse dataset of 3929 images consisting of five wild horse breeds worldwide at different geographical locations. We base our analysis on the seven Panksepp emotions of mammals “Exploring”, “Sadness”, “Playing”, “Rage”, “Fear”, “Affectionate” and “Lust”, along with one additional emotion “Pain” which has been shown to be highly relevant for horses. We apply the contrastive learning framework MoCo (Momentum Contrast for Unsupervised Visual Representation Learning) on our dataset to predict the seven Panksepp emotions and “Pain” using unsupervised learning. We significantly modify the MoCo framework, building a custom downstream classifier network that connects with a frozen CNN encoder that is pretrained using MoCo. Our method allows the encoder network to learn similarities and differences within image groups on its own without labels. The clusters thus formed are indicative of deeper nuances and complexities within a horse’s mood, which can possibly hint towards the existence of novel and complex equine emotions.
... Thus, children and teenagers often have opportunities to interact with both human and nonhuman partners. Just like humans, animals emit various communication signals, mainly non-verbal via facial expressions (e.g., pain: rabbit (Keating et al., 2012), horse (Costa et al., 2014), sheep (McLennan et al., 2016), rat (Sotocinal et al., 2011)). ...
1) Background: Animals provide many benefits in children's lives, but few studies assess the effects of animal presence-especially service dogs-in schools. This pilot study examined whether a year-long exposure to a service dog could improve facial expression recognition in adolescents with cognitive function disorders. (2) Method: Twenty-three adolescents participated: 10 with cognitive function disorders who were part of a specialized French teaching program (LUSI) that included a service dog (LUSI group), and 13 neurotypical adolescents who served as controls (not in LUSI, no service dog exposure). Participants assigned one of five facial expressions (sadness, joy, fear, neutral, anger) to images of human, dog, and cat faces at three intervals: before dog integration, at 5-8 months, and 11-14 months later (same intervals for controls). (3) Results: Identification of facial expressions of both dog (p = 0.001) and human (p = 0.01) but not cat (p > 0.05) faces by LUSI participants exposed to service dog improved with time. The performance of LUSI participants was better when they lived with various species of animals at home. Control participants' performance did not change significantly (all p > 0.05). (4) Conclusions: After a school year, the presence of a service dog had helped adolescents with cognitive function disorders to better identify human and dog facial expressions.
... To quantify this, methods for the clinical recognition and objective quantification of a horse's behavior and pain continue to receive attention in the equine scientific literature. This includes multiple variations of equine pain scales, including the 'horse grimace scale' and the 'ridden horse pain ethogram' (RHpE) [7][8][9]. The potential confounding roles of training, rider/handler skill level, breed, arousal level, and personality are particularly important to consider when applying pain and behavioral assessment tools. ...
Behavioral problems are a common complaint in equine practice, particularly in sport horses [...]
... It has been established that ongoing discomfort/pain behaviors of horses typically cease or are greatly reduced in the presence of people compared to when alone and undisturbed [7]. The Horse Grimace Scale (HGS) is a rubric developed for the recognition of pain in horses based on systematic evaluation of the tension of various facial muscles [8]. ...
Gastric ulcer disease and other potentially painful gastric conditions are among the most common afflictions adversely affecting the welfare of domestic equids. A large percentage of affected animals may not display the classic signs of gastric disease, such as unexplained weight loss, poor hair coat, and inappetence until the disease becomes severe. As a clinical service within our equine referral hospital, we routinely evaluate 24-h video recorded samples of horses to assist clinicians in identifying subtle discomfort and potential sources or to scan for infrequent neurologic or cardiac-related behavioral events. Empirically, we have recognized discomfort behaviors that appear to be uniquely associated with gastric disease. These include frequent attention to the cranial abdomen (nuzzling, swatting, nipping, and/or caudal gaze focused on the abdomen caudal to the elbow) and/or deep abdominal stretching, often within the context of eating, drinking, and/or anticipating feeding. To systematically evaluate the reliability of these purported gastric discomfort behaviors, we reviewed 30 recent 24-h video behavior evaluation cases for which (1) the clinical video behavior evaluation had been carried out without knowledge of the history and presenting complaint and (2) direct gastric examination had confirmed gastric disease status at the time. Twenty-four of the thirty cases showed gastric discomfort behavior, and all twenty-four had either gastric ulcers (n = 21) and/or gastric impaction (n = 3). Of the six cases not showing gastric discomfort behaviors, four were free of gastric disease, while two had mild lesions. Comparing horses with and without gastric disease, gastric discomfort behaviors were reported in 24 of the 26 (92%) with gastric ulcers or gastric impaction, compared to none of the four gastric disease-free horses. Although a larger prospectively designed study is needed to confidently estimate the sensitivity and specificity or the associations of behavior with the type or severity of gastric disease, these results confirm our long-held clinical impression of a behavioral signature for gastric discomfort in the horse.
... based on behavior have also been validated for domestic species, like cats 32 , dogs 33 , rabbits 34 , pigs 35 , goats 36 , sheep 37 , horses 25 , donkeys 38 and cattle 39 . ...
This study explores the question whether Artificial Intelligence (AI) can outperform human experts in animal pain recognition using sheep as a case study. It uses a dataset of N = 48 sheep undergoing surgery with video recordings taken before (no pain) and after (pain) surgery. Four veterinary experts used two types of pain scoring scales: the sheep facial expression scale (SFPES) and the Unesp-Botucatu composite behavioral scale (USAPS), which is the ‘golden standard’ in sheep pain assessment. The developed AI pipeline based on CLIP encoder significantly outperformed human facial scoring (AUC difference = 0.115, p < 0.001) when having access to the same visual information (front and lateral face images). It further effectively equaled human USAPS behavioral scoring (AUC difference = 0.027, p = 0.163), but the small improvement was not statistically significant. The fact that the machine can outperform human experts in recognizing pain in sheep when exposed to the same visual information has significant implications for clinical practice, which warrant further scientific discussion.
... Dalla Costa y cols. 179 evaluaron los cambios que se presentan en las expresiones faciales de caballos sometidos a procedimientos quirúrgicos. Los caballos se integraron en grupos de sementales a los que se les administraron diferentes dosis de analgésicos prequirúrgico, postquirúrgico o ambos y un grupo control sin procedimiento invasivo o que pudiese provocarles dolor. ...
... En grandes especies como el caballo, la seguridad que proporciona la aplicación de este tipo de escala aumenta considerablemente ya que no es necesario invadir el espacio del sujeto. Asimismo, a diferencia de las escalas de dolor utilizadas bajo condiciones graves como el cólico o laminitis, la HGS permite evaluar el rango de dolor leve a severo o crónico y esto en conjunto facilita la evaluación, conservando el nivel de confiabilidad de la herramienta 177,179,182 . ...
... Animals unlikely to be able to defend themselves, such as sheep, vocalize far less when caught by a predator, probably because such an extreme response merely © CAB International 2024 NOT FOR RESALE gives information to the predator that the animal attacked is severely injured and hence unlikely to be able to escape. Studies of several species, including sheep, goats and horses, show that facial grimace scales are useful indicators of pain (Dalla Costa et al., 2014;McLennan et al., 2016). In cattle, a useful indicator of fear is the amount of eye white visible (Core et al., 2009). ...
There is increasing public concern about the welfare of farmed animals, in part because there is now an appreciation that all are sentient beings. Consumers are demanding sustainable production systems, and the welfare of livestock is one of the key components of sustainability. Positive and negative aspects of the welfare of animals during transport should be assessed
using a range of behavioural, physiological and carcass-quality measures. Health is an important part of welfare, so the extent of any disease, injury or mortality resulting from, or exacerbated by, transport should be measured. Many of the indicators of welfare are measures of stress, involving long-term adverse effects or indicators of pain, fear or other feelings. Some welfare assessment methods are research tools while others are welfare outcome indicators that can be used by a farmer, veterinary or other inspector. New monitoring and analysis methodologies are providing easier ways to improve welfare.
... Species-specific pain assessment tools, known as grimace scales, focus on changes in an animal's facial features, and together with behavioral pain scales, they have been developed and validated for nearly all commonly domesticated species (with the notable exception of the dog, given their exceptional facial morphological diversity). Originally developed for rodents, these grimace scales have since been adapted for a range of mammalian species, including rats (14), rabbits (15), horses (16), pigs (17), ferrets (18), sheep (19,20), and cats (21,22). ...
Facial landmarks, widely studied in human affective computing, are beginning to gain interest in the animal domain. Specifically, landmark-based geometric morphometric methods have been used to objectively assess facial expressions in cats, focusing on pain recognition and the impact of breed-specific morphology on facial signaling. These methods employed a 48-landmark scheme grounded in cat facial anatomy. Manually annotating these landmarks, however, is a labor-intensive process, deeming it impractical for generating sufficiently large amounts of data for machine learning purposes and for use in applied real-time contexts with cats. Our previous work introduced an AI pipeline for automated landmark detection, which showed good performance in standard machine learning metrics. Nonetheless, the effectiveness of fully automated, end-to-end landmark-based systems for practical cat facial analysis tasks remained underexplored. In this paper we develop AI pipelines for three benchmark tasks using two previously collected datasets of cat faces. The tasks include automated cat breed recognition, cephalic type recognition and pain recognition. Our fully automated end-to-end pipelines reached accuracy of 75% and 66% in cephalic type and pain recognition respectively, suggesting that landmark-based approaches hold promise for automated pain assessment and morphological explorations.
... Para poder dar una interpretación de esta comunicación no verbal que se presenta entre perros y humanos, se ha prestado mayor interés en regiones faciales como labios, ojos y cejas de los perros, con el fin de asociar las expresiones involucradas a ciertos estímulos positivos o negativos y, con ello, identificar e interpretar sus emociones 15 . Lo anterior, no sólo en un contexto etológico, sino también clínico para el reconocimiento de la intensidad del dolor mediante los cambios en las expresiones faciales de los perros, de manera similar a los hallazgos encontrados en el caballo 16,17 . Por tal motivo, el objetivo de este capítulo es discutir los avances recientes sobre la anatomía y la fisiología de la expresión facial. ...
... Outro método que pode ser eficiente para avaliar bem-estar em equinos é o uso de aplicativo onde a expressão facial é usada como instrumento de mensuração de dor (Hand et al., 2010;Ranger et al., 2013). O Horse Grimace Scale (HGS) é um método prático, baseado em comportamento para melhor avaliação do desconforto/dor facial em equinos (Dalla Costa et al., 2014;Gontijo et al., 2018). Assim, a presente pesquisa visa medir a adaptabilidade de equinos das raças Brasileira de Hipismo e Sem Raça Definida às condições climáticas da Amazônia Oriental. ...
O trabalho objetivou utilizar o aplicativo Horse Grimace Scale (HGS) para avaliar o bem-estar de equinos, submetidos às condições de clima da Amazônia Oriental. A pesquisa foi conduzida no Centro Hípico (latitude 1°23'33.4" sul e longitude 48°24'27.6"oeste), Ananindeua, Pará, Brasil, durante o período menos chuvoso do ano. Foram utilizados 14 equinos machos, sendo oito da raça Brasileiro de Hipismo (BH) e seis sem raça definida (SRD), com cerca de 12 anos de idade e peso médio de 492,55 Kg. Nos turnos da manhã (de 8h00 às 9h00) e tarde (de 14h00 às 15h00) foram registrados dados de temperatura do ar (TA), umidade relativa do ar (UR) e temperatura de globo negro (TGN) para cálculo dos índices de conforto ambiental Índice de Temperatura e Umidade (ITU) e Índice de Temperatura de Globo e Umidade (ITGU) e foram medidos dados de expressão facial dos animais com o uso do aplicativo Horse Grimace Scale (HGS), a fim de medir o bem-estar. Foi constatada diferença significativa (P<0,05) de ITGU, ITU e HGS entre os turnos, onde os maiores valores foram encontrados durante a tarde. Os equinos BH e SRD estão sujeitos a ambiente hostil nas condições climáticas da Amazônia Oriental, e o turno da tarde é o mais propício a causar estresse térmico.