EquiMoves: A Wireless Networked Inertial Measurement System for Objective Examination of Horse Gait

Functional infrared thermography imaging can be used to assess the effectiveness of Maxicam Gel® in pre-emptively treating transient synovitis and lameness in horses

Introduction

Diagnosing and treating lameness in horses is essential to improving their welfare. In equine orthopedic practice, infrared thermography (IRT) can indirectly detect soreness. Non-steroidal anti-inflammatory drugs can treat painful and inflammatory processes in horses. Using IRT, the efficacy of meloxicam (Maxicam Gel®) was evaluated in pre-treating transient synovitis in horses induced by a middle carpal joint injection of lipopolysaccharides (LPS) from E. coli 055:B5 at a dose of 10 endotoxin units.

Methods

In a cross-over design, six healthy horses were randomly assigned to receive either 0.6 mg/kg of oral Maxicam Gel® (MAXVO) or a mock administration (control group, C) following a two-week washout period. IRT of the middle carpal joint, visual lameness assessment and joint circumference were recorded over time. Clinical and hematological evaluations were performed. Synovial fluid aspirates were analyzed for total nucleated cell count, total protein, and prostaglandin E2. A mixed effects analysis of variance was performed for repeated measures over time, followed by Tukey's test. A multinomial logistic regression was conducted to determine whether there is a relationship between a thermography temperature change and the lameness score.

Results

There were no changes in joint circumference. The MAXVO group showed a lower rectal temperature 4 h after synovitis induction. The C group presented an increase in neutrophils and a decrease in total hemoglobin and hematocrit 8 h after induction. No changes were observed in the synovial fluid between groups. The horses that received meloxicam did not show clinically significant lameness at any time, while the C group showed an increase in lameness 2, 4, and 8 h after synovitis induction.

Discussion

IRT indicated that the skin surface temperature of the middle carpal joint was lower in horses who received meloxicam, suggesting a reduction in the inflammatory process induced by LPS. It was observed that the maximum temperature peaks in the dorsopalmar and lateropalmar positions can be utilized to predict the severity of lameness, particularly when the temperature rises above 34°C. Horses pre-treated with meloxicam showed either reduced or no indication of mild to moderate pain and presented a lowehr thermographic temperature, which indicates the effectiveness of Maxicam Gel® as an anti-inflammatory.

The Poses for Equine Research Dataset (PFERD)

Studies of quadruped animal motion help us to identify diseases, understand behavior and unravel the mechanics behind gaits in animals. The horse is likely the best-studied animal in this aspect, but data capture is challenging and time-consuming. Computer vision techniques improve animal motion extraction, but the development relies on reference datasets, which are scarce, not open-access and often provide data from only a few anatomical landmarks. Addressing this data gap, we introduce PFERD, a video and 3D marker motion dataset from horses using a full-body set-up of densely placed over 100 skin-attached markers and synchronized videos from ten camera angles. Five horses of diverse conformations provide data for various motions from basic poses (eg. walking, trotting) to advanced motions (eg. rearing, kicking). We further express the 3D motions with current techniques and a 3D parameterized model, the hSMAL model, establishing a baseline for 3D horse markerless motion capture. PFERD enables advanced biomechanical studies and provides a resource of ground truth data for the methodological development of markerless motion capture.

Adaptation strategies of the Icelandic horse with induced forelimb lameness at walk, trot and tölt

BACKGROUND AND OBJECTIVE

Lameness assessment in the gaited Icelandic horse is complex. We aimed to describe their kinematic and temporal adaptation strategies in response to forelimb lameness at walk, trot and tölt.

STUDY DESIGN

In vivo experiment.

METHODS

Ten clinically non-lame Icelandic horses were measured before and after reversible forelimb lameness induction. Upper body and limb kinematics were measured using 11 inertial measurement units mounted on the poll, withers, pelvis (tubera sacrale) and all four limbs and hoofs (Equimoves®, 500 Hz). Horses were measured on a straight line at walk and trot in-hand and at walk, trot and tölt while ridden. Linear mixed models were used to compare baseline and lame conditions (random factor = 'horse'), and results are presented as the difference in estimated marginal means or percentage of change.

RESULTS

Lameness induction significantly (p < 0.05) increased head vertical movement asymmetry at walk (HDmin/HDmaxHAND: 18.8/5.7 mm, HDmin/HDmaxRIDDEN: 9.8/0.3 mm) and trot (HDmin/HDmaxHAND: 18.1/7.8 mm, HDmin/HDmaxRIDDEN: 24.0/9.3 mm). At the tölt, however, HDmin did not change significantly (1.1 mm), but HDmax increased by 11.2 mm (p < 0.05). Furthermore, pelvis vertical movement asymmetry (PDmax) increased by 4.9 mm, sound side dissociation decreased (-8.3%), and sound diagonal dissociation increased (6.5%). Other temporal stride variables were also affected, such as increased stance duration of both forelimbs at walk, tölt and in-hand trot.

MAIN LIMITATIONS

Only one degree of lameness (mild) was induced with an acute lameness model.

CONCLUSIONS

Classical forelimb lameness metrics, such as vertical head and withers movement asymmetry, were less valuable at tölt compared to walk and trot, except for HDmax. Therefore, it is advised to primarily use the walk and trot to detect and quantify forelimb lameness in the Icelandic horse.

Objective movement asymmetry in horses is comparable between markerless technology and sensor-based systems

BACKGROUND

A markerless artificial intelligence (AI) system for lameness detection has recently become available but has not been extensively compared with commonly used inertial measurement unit (IMU) systems for detecting asymmetry under field conditions.

OBJECTIVE

Comparison of classification of asymmetric limbs under field conditions and comparison of normalised asymmetry data using a markerless AI system (SleipAI; recorded on a tripod mounted iPhone 14pro [SL]); the Equinosis Q Lameness Locator (LL); the EquiMoves (EM); and subjective evaluation (SE).

STUDY DESIGN

Descriptive clinical study.

METHODS

Straight line trot data were collected from 52 client-owned horses in regular training. Limbs were categorised as symmetric or asymmetric. Number of analysed strides were compared with Wilcoxon's each pairs test. Inter-rater reliability in classification of asymmetric limbs was assessed with Light's Kappa. Bland Altman analysis of normalised asymmetry data was performed.

RESULTS

Data from 41 horses were included. Most horses showed mild asymmetry. The EM analysed significantly more strides than the other systems, both for forelimbs and for hindlimbs (53 ± 11 strides for both, respectively; p < 0.006). The LL analysed significantly more hindlimbs strides (45 ± 13) than the SL (27 ± 6; p < 0.001). Moderate inter-rater agreement for asymmetry classification was found between systems (k = 0.59 forelimbs; 0.44 hindlimbs); agreement decreased when including the SE. For the normalised asymmetry data, the strongest agreement was found between the two IMU systems.

MAIN LIMITATIONS

Horses were assessed during straight-line trot only.

CONCLUSIONS

The objective systems were comparable in classification of asymmetric limbs under field conditions when using defined asymmetry thresholds. Discrepancies stemmed largely from the imposed thresholds (i.e., systems largely identified same-side asymmetry). Overall, the strongest agreement was found between LL and EM. The SL analysed significantly fewer hindlimb strides than the LL and EM which could represent a limitation of the Sleip AI.

A Method for Quantifying Back Flexion/Extension from Three Inertial Measurement Units Mounted on a Horse's Withers, Thoracolumbar Region, and Pelvis

Back mobility is a criterion of well-being in a horse. Veterinarians visually assess the mobility of a horse's back during a locomotor examination. Quantifying it with on-board technology could be a major breakthrough to help them. The aim of this study was to evaluate the accuracy of a method of quantifying the back mobility of horses from inertial measurement units (IMUs) compared to motion capture (MOCAP) as a gold standard. Reflective markers and IMUs were positioned on the withers, eighteenth thoracic vertebra, and pelvis of four sound horses. The horses performed a walk and trot in straight lines and performed a gallop in circles on a soft surface. The developed method, based on the three IMUs, consists of calculating the flexion/extension angle of the thoracolumbar region. The IMU method showed a mean bias of 0.8° (±1.5°) (mean (±SD)) and 0.8° (±1.4°), respectively, for the flexion and extension movements, all gaits combined, compared to the MOCAP method. The results of this study suggest that the developed method has a similar accuracy to that of MOCAP, opening up possibilities for easy measurements under field conditions. Future studies will need to examine the correlations between these biomechanical measures and clinicians' visual assessment of back mobility defects.

Back motion in unridden horses in walk, trot and canter on a circle

Equine back function is of concern to riders, as well as to veterinarians and physiotherapists; these groups may benefit from knowledge about spinal motion on the circle. This descriptive and comparative study aimed to quantify equine neck, back and pelvic motion in walk, trot and canter on a 9 m circle. Sixteen healthy horses in training, of varying breed and conformation, were measured using optical motion capture (150 Hz), with optical markers on the poll, withers, T15, tubera coxae and lumbosacral joint. Cervicothoracic and thoracolumbar flexion-extension and lateral bending, and pelvic roll, pitch and yaw, were statistically evaluated using mixed models. Motion patterns showed distinct differences between gaits, but were generally similar between horses. The thoracolumbar back was bent towards the inside of the circle (stride mean 5-6º for all gaits). The cervicothoracic spine was more flexed in walk (18°), and more extended in canter (-4--8°), compared to trot (6-7°), whereas the thoracolumbar spine was slightly less extended in canter than in walk. Thoracolumbar flexion-extension range of motion (ROM) increased from walk (4°) to canter (9°), as did pelvic pitch ROM (walk 7° and canter 15-16°), while back lateral bending ROM and pelvic yaw ROM were lowest in trot. Taken together, the study findings suggest that neck and back motion patterns on the circle reflect an interaction between the constraints of circular movement, and the mechanics and characteristics of each gait.

Comparing Inertial Measurement Units to Markerless Video Analysis for Movement Symmetry in Quarter Horses

BACKGROUND

With an increasing number of systems for quantifying lameness-related movement asymmetry, between-system comparisons under non-laboratory conditions are important for multi-centre or referral-level studies. This study compares an artificial intelligence video app to a validated inertial measurement unit (IMU) gait analysis system in a specific group of horses.

METHODS

Twenty-two reining Quarter horses were equipped with nine body-mounted IMUs while being videoed with a smartphone app. Both systems quantified head and pelvic movement symmetry during in-hand trot (hard/soft ground) and on the lunge (left/right rein, soft ground). Proportional limits of agreement (pLoA) were established.

RESULTS

Widths of pLoA were larger for head movement (29% to 50% in-hand; 22% to 38% on lunge) than for pelvic movement (13% to 24% in-hand; 14% to 24% on lunge).

CONCLUSION

The between-system pLoAs exceed current "lameness thresholds" aimed at identifying the affected limb(s) in lame horses. They also exceed published limits of agreement for stride-matched data but are similar to repeatability values and "lameness thresholds" from "non-lame" horses. This is encouraging for multi-centre studies and referral-level veterinary practice. The narrower pLoA values for pelvic movement asymmetry are particularly encouraging, given the difficulty of grading hind limb lameness "by eye".

Evaluating Overall Performance in High-Level Dressage Horse-Rider Combinations by Comparing Measurements from Inertial Sensors with General Impression Scores Awarded by Judges

In the sport of dressage, one or more judges score the combined performance of a horse and rider with an emphasis on the technical correctness of the movements performed. At the end of the test, a single score is awarded for the 'general impression', which considers the overall performance of the horse and rider as a team. This study explored original measures that contributed to the general impression score in a group of 20 horse-rider combinations. Horses and riders were equipped with inertial measurement units (200 Hz) to represent the angular motion of a horse's back and the motions of a rider's pelvis and trunk. Each combination performed a standard dressage test that was recorded to video. Sections of the video were identified for straight-line movements. The videos were analyzed by two or three judges. Four components were scored separately: gaits of the horse, rider posture, effectiveness of aids, and harmony with the horse. The main contributor to the score for gaits was stride frequency (R = -0.252, p = 0.015), with a slower frequency being preferred. Higher rider component scores were associated with more symmetrical transverse-plane trunk motion, indicating that this original measure is the most useful predictor of rider performance.

Inertial Sensor Technologies-Their Role in Equine Gait Analysis, a Review

Objective gait analysis provides valuable information about the locomotion characteristics of sound and lame horses. Due to their high accuracy and sensitivity, inertial measurement units (IMUs) have gained popularity over objective measurement techniques such as force plates and optical motion capture (OMC) systems. IMUs are wearable sensors that measure acceleration forces and angular velocities, providing the possibility of a non-invasive and continuous monitoring of horse gait during walk, trot, or canter during field conditions. The present narrative review aimed to describe the inertial sensor technologies and summarize their role in equine gait analysis. The literature was searched using general terms related to inertial sensors and their applicability, gait analysis methods, and lameness evaluation. The efficacy and performance of IMU-based methods for the assessment of normal gait, detection of lameness, analysis of horse-rider interaction, as well as the influence of sedative drugs, are discussed and compared with force plate and OMC techniques. The collected evidence indicated that IMU-based sensor systems can monitor and quantify horse locomotion with high accuracy and precision, having comparable or superior performance to objective measurement techniques. IMUs are reliable tools for the evaluation of horse-rider interactions. The observed efficacy and performance of IMU systems in equine gait analysis warrant further research in this population, with special focus on the potential implementation of novel techniques described and validated in humans.

Poor Association between Facial Expression and Mild Lameness in Thoroughbred Trot-Up Examinations

Musculoskeletal injuries in racehorses are difficult to detect prior to catastrophic breakdown. Lameness is commonly attributed to orthopaedic pain in horses, therefore, subtle lameness may be a pre-clinical sign of injury and, if identified early, could allow for preventative intervention. Our objective was to determine if facial expressions could be used to detect mild lameness as an indicator of orthopaedic pain in 'fit to race' horses. The Horse Grimace Scale (HGS) and the facial expressions in ridden horses (FEReq), were used to score images (n = 380) of mildly lame (n = 21) and non-lame (n = 17) Thoroughbred horses by two independent observers. Using an Equinosis Lameness Locator®, the lameness status of each horse was determined according to published thresholds [forelimb lameness (>|14.5 mm|) and hindlimb lameness (>|7.5 mm|)]. Inter and intraobserver reliability were assessed using two-way random-effects models. Univariable associations between lameness and facial expression parameters were identified using logistic and linear regression. Interobserver reliability was moderate (κ 0.45; 95% CI 0.36, 0.55). Horses with moderate mouth strain (HGS) and tense and extended upper lip (FEReq) were less likely to be lame (p = 0.042 and p = 0.027, respectively). Exposed sclera was associated with lameness (p = 0.045). Higher orbital tightening (HGS) scores were associated with a lower degree of maximum head amplitude (HDmax) lameness (p = 0.044). Tension and moderate tension above the eye, for the HGS and FEReq scores, were associated with increasing amplitude of HDmax (p = 0.048 and p = 0.034, respectively). Inconsistent associations between lameness status and HGS and FEReq scores may limit the potential use of the facial expression for the prediction of mild orthopaedic pain during pre-race lameness examinations. More objective parameters associated with mild orthopaedic pain should be explored.

Validation of Alogo Move Pro: A GPS-Based Inertial Measurement Unit for the Objective Examination of Gait and Jumping in Horses

Quantitative information on how well a horse clears a jump has great potential to support the rider in improving the horse's jumping performance. This study investigated the validation of a GPS-based inertial measurement unit, namely Alogo Move Pro, compared with a traditional optical motion capture system. Accuracy and precision of the three jumping characteristics of maximum height (Zmax), stride/jump length (lhorz), and mean horizontal speed (vhorz) were compared. Eleven horse-rider pairs repeated two identical jumps (an upright and an oxer fence) several times (n = 6 to 10) at different heights in a 20 × 60 m tent arena. The ground was a fiber sand surface. The 24 OMC (Oqus 7+, Qualisys) cameras were rigged on aluminum rails suspended 3 m above the ground. The Alogo sensor was placed in a pocket on the protective plate of the saddle girth. Reflective markers placed on and around the Alogo sensor were used to define a rigid body for kinematic analysis. The Alogo sensor data were collected and processed using the Alogo proprietary software; stride-matched OMC data were collected using Qualisys Track Manager and post-processed in Python. Residual analysis and Bland-Altman plots were performed in Python. The Alogo sensor provided measures with relative accuracy in the range of 10.5-20.7% for stride segments and 5.5-29.2% for jump segments. Regarding relative precision, we obtained values in the range of 6.3-14.5% for stride segments and 2.8-18.2% for jump segments. These accuracy differences were deemed good under field study conditions where GPS signal strength might have been suboptimal.

Is Markerless More or Less? Comparing a Smartphone Computer Vision Method for Equine Lameness Assessment to Multi-Camera Motion Capture

Computer vision is a subcategory of artificial intelligence focused on extraction of information from images and video. It provides a compelling new means for objective orthopaedic gait assessment in horses using accessible hardware, such as a smartphone, for markerless motion analysis. This study aimed to explore the lameness assessment capacity of a smartphone single camera (SC) markerless computer vision application by comparing measurements of the vertical motion of the head and pelvis to an optical motion capture multi-camera (MC) system using skin attached reflective markers. Twenty-five horses were recorded with a smartphone (60 Hz) and a 13 camera MC-system (200 Hz) while trotting two times back and forth on a 30 m runway. The smartphone video was processed using artificial neural networks detecting the horse's direction, action and motion of body segments. After filtering, the vertical displacement curves from the head and pelvis were synchronised between systems using cross-correlation. This rendered 655 and 404 matching stride segmented curves for the head and pelvis respectively. From the stride segmented vertical displacement signals, differences between the two minima (MinDiff) and the two maxima (MaxDiff) respectively per stride were compared between the systems. Trial mean difference between systems was 2.2 mm (range 0.0-8.7 mm) for head and 2.2 mm (range 0.0-6.5 mm) for pelvis. Within-trial standard deviations ranged between 3.1-28.1 mm for MC and between 3.6-26.2 mm for SC. The ease of use and good agreement with MC indicate that the SC application is a promising tool for detecting clinically relevant levels of asymmetry in horses, enabling frequent and convenient gait monitoring over time.

Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks

Vertical ground reaction force (GRFz) measurements are the best tool for assessing horses' weight-bearing lameness. However, collection of these data is often impractical for clinical use. This study evaluates GRFz predicted using data from body-mounted IMUs and long short-term memory recurrent neural networks (LSTM-RNN). Twenty-four clinically sound horses, equipped with IMUs on the upper-body (UB) and each limb, walked and trotted on a GRFz measuring treadmill (TiF). Both systems were time-synchronised. Data from randomly selected 16, 4, and 4 horses formed training, validation, and test datasets, respectively. LSTM-RNN with different input sets (All, Limbs, UB, Sacrum, or Withers) were trained to predict GRFz curves or peak-GRFz. Our models could predict GRFz shapes at both gaits with RMSE below 0.40 N.kg^-1. The best peak-GRFz values were obtained when extracted from the predicted curves by the all dataset. For both GRFz curves and peak-GRFz values, predictions made with the All or UB datasets were systematically better than with the Limbs dataset, showing the importance of including upper-body kinematic information for kinetic parameters predictions. More data should be gathered to confirm the usability of LSTM-RNN for GRFz predictions, as they highly depend on factors like speed, gait, and the presence of weight-bearing lameness.

Efficient Development of Gait Classification Models for Five-Gaited Horses Based on Mobile Phone Sensors

Automated gait classification has traditionally been studied using horse-mounted sensors. However, smartphone-based sensors are more accessible, but the performance of gait classification models using data from such sensors has not been widely known or accessible. In this study, we performed horse gait classification using deep learning models and data from mobile phone sensors located in the rider's pocket. We gathered data from 17 horses and 14 riders. The data were gathered simultaneously from movement sensors in a mobile phone located in the rider's pocket and a gait classification system based on four wearable sensors attached to the horse's limbs. With this efficient approach to acquire labelled data, we trained a Bi-LSTM model for gait classification. The only input to the model was a 50 Hz signal from the phone's accelerometer and gyroscope that was rotated to the horse's frame of reference. We demonstrate that sensor data from mobile phones can be used to classify the five gaits of the Icelandic horse with up to 94.4% accuracy. The result suggests that horse riding activities can be studied at a large scale using mobile phones to gather data on gaits. While our study showed that mobile phone sensors could be effective for gait classification, there are still some limitations that need to be addressed in future research. For example, further studies could explore the effects of different riding styles or equipment on gait classification accuracy or investigate ways to minimize the influence of factors such as phone placement. By addressing these questions, we can continue to improve our understanding of horse gait and its role in horse riding activities.

A Pilot Study on the Inter-Operator Reproducibility of a Wireless Sensors-Based System for Quantifying Gait Asymmetries in Horses

Repeatability and reproducibility of any measuring system must be evaluated to assess possible limitations for its use. The objective of this study was to establish the repeatability and the inter-operator reproducibility of a sensors-based system (EQUISYM^®) for quantifying gait asymmetries in horses.. Seven wireless IMUs were placed on the head, the withers, the pelvis, and the 4 cannon bones on three horses, by four different operators, four times on each horse, which led to a total of 48 repetitions randomly assigned. Data were collected along three consecutive days and analysed to calculate total variance, standard deviation and the variance attributable to the operator on multiple asymmetry variables. Maximal percentage of variance due to the operator (calculated out of the total variance) was 5.3% and was related to the sensor placed on the head. The results suggest a good reproducibility of IMU-based gait analysis systems for different operators repositioning the system and repeating the same measurements at a succession of time intervals. Future studies will be useful to confirm that inter-operator reproducibility remains valid in larger groups and on horses with different degrees of locomotor asymmetry.

Variability of Jump Biomechanics Between Horses of Different Age and Experience Using Commercial Inertial Measurement Unit Technology

The application of commercial inertial measurement units has become popular in equestrian sports, which may help to eliminate a gap of knowledge concerning many aspects of biomechanics in training. This study employed the Seaver IMU system to measure jumping characteristics of horses with differing age-competition experience during regular training. It was hypothesized that experience level results in lower variability of jumping parameters. Twelve Warmblood horses aged 5 to 6 years with/without competition experience and 7 to 11 years with experience were investigated during regular training in 2 training centers. Consistent number of 10 successive jumps of the individual chosen course of vertical and spread obstacles (5th -15th) were analyzed and the following parameters were measured: jump height, reserve and length; taking off angle, acceleration, velocity; jump spatial shifting, energy by landing, and frequency of approach strides. Preliminary analysis confirmed comparable physiological effort in 2 training center based on heart rate, distance and duration measurements. The multifactorial analysis of variance for biomechanical data included in the statistical model the random effect of horse and fixed effects of training center, age-experience group, successive jump number, obstacle type and height. Four parameters were significantly different between the younger, inexperienced group and experienced younger and older horses: height of jump (P = .01), frequency of approach strides (P = .005), acceleration of taking off (P = .01), and energy by landing (P = .0013). Standard errors for almost all the parameters reached higher values for the youngest, inexperienced horses. Variability of jumping parameters was lower for experienced groups of horses, suggesting higher precision on obstacle courses.

The Limb Kinetics of Goat Walking on the Slope with Different Angles

The study aimed to assess the gait adjustment techniques of limbs on different slopes and investigate the relationship between forelimb and hindlimb kinetics and the center of mass (COM) during the uphill movement of a specific Boer goat using a pressure-sensitive walkway (PSW). During the uphill and downhill movements at a comfortable walking speed, we measured the ground reaction force (GRF) of the forelimbs and hindlimbs on the slope, the change in the included angle of the propulsive force direction of the forelimbs and hindlimbs, and the impulse relationship between GRF and propulsive force. According to the study, since the forelimbs of the goat were nearer the COM, they were primarily adjusted during the movement on the slope. By lowering the initial included angle of the propulsive force and the angle variation range, the forelimbs and hindlimbs could walk steadily. The forelimbs and hindlimbs exhibited completely different adjustment strategies during uphill and downhill movements. In particular, the forelimbs performed braking and the hindlimbs performed driving. In addition, we discovered that the goat altered its adjustment strategy when climbing the steep slope. All findings of this study indicate the need to understand the gait adjustment mode of the Boer goat during movement on the slope to thoroughly comprehend the driving strategy of quadrupeds with the ability to walk on specialized terrains.

Timing of Vertical Head, Withers and Pelvis Movements Relative to the Footfalls in Different Equine Gaits and Breeds

Simple Summary

Movement symmetry of the head and pelvis are used to measure lameness in horses in trot. Although head, pelvis and limb movements have been described, less is known about the temporal relationships between them. This information is needed to understand how the movements change with lameness. This is particularly relevant in gaited horses, such as the Icelandic horse that perform gaits such as tölt and pace, which are challenging to evaluate. This study used inertial measurement units to investigate head, withers and pelvis motion relative to limb movements in Icelandic, Warmblood and Iberian horses. Limb movements, together with vertical movements and lowest/highest positions of the head, withers and pelvis were calculated, and the relative timing of the events was compared across breeds. Additionally, data for tölt and pace were collected and evaluated in ridden Icelandic horses. For all gaits except walk and pace, the lowest/highest positions of the head/withers/pelvis were closely temporally related to midstance and hoof-off, respectively. Pelvic and withers total range of motion differed between all breeds. The Icelandic horses showed shorter stride duration and smaller movements of the upper body than the other breeds at trot, which may explain why lameness evaluation in this breed is challenging.

Abstract

Knowledge of vertical motion patterns of the axial body segments is a prerequisite for the development of algorithms used in automated detection of lameness. To date, the focus has been on the trot. This study investigates the temporal synchronization between vertical motion of the axial body segments with limb kinematic events in walk and trot across three popular types of sport horses (19 Warmbloods, 23 Iberians, 26 Icelandics) that are known to have different stride kinematics, and it presents novel data describing vertical motion of the axial body segments in tölting and pacing Icelandic horses. Inertial measurement unit sensors recorded limb kinematics, vertical motion of the axial body at all symmetrical gaits that the horse could perform (walk, trot, tölt, pace). Limb kinematics, vertical range of motion and lowest/highest positions of the head, withers and pelvis were calculated. For all gaits except walk and pace, lowest/highest positions of the pelvis and withers were found to be closely related temporally to midstance and start of suspension of the hind/fore quarter, respectively. There were differences in pelvic/withers range of motion between all breeds where the Icelandic horses showed the smallest motion, which may explain why lameness evaluation in this breed is challenging.

Artificial Intelligence for Lameness Detection in Horses-A Preliminary Study

Lameness in horses is a long-known issue influencing the welfare, as well as the use, of a horse. Nevertheless, the detection and classification of lameness mainly occurs on a subjective basis by the owner and the veterinarian. The aim of this study was the development of a lameness detection system based on pose estimation, which permits non-invasive and easily applicable gait analysis. The use of 58 reference points on easily detectable anatomical landmarks offers various possibilities for gait evaluation using a simple setup. For this study, three groups of horses were used: one training group, one analysis group of fore and hindlimb lame horses and a control group of sound horses. The first group was used to train the network; afterwards, horses with and without lameness were evaluated. The results show that forelimb lameness can be detected by visualising the trajectories of the reference points on the head and both forelimbs. In hindlimb lameness, the stifle showed promising results as a reference point, whereas the tuber coxae were deemed unsuitable as a reference point. The study presents a feasible application of pose estimation for lameness detection, but further development using a larger dataset is essential.

Development of a Novel Approach for Detection of Equine Lameness Based on Inertial Sensors: A Preliminary Study

Both as an aid for less experienced clinicians and to enhance objectivity and sharp clinical skills in professionals, quantitative technologies currently bring the equine lameness diagnostic closer to evidence-based veterinary medicine. The present paper describes an original, inertial sensor-based wireless device system, the Lameness Detector 0.1, used in ten horses with different lameness degrees in one fore- or hind-leg. By recording the impulses on three axes of the incorporated accelerometer in each leg of the assessed horse, and then processing the data using custom-designed software, the device proved its usefulness in lameness identification and severity scoring. Mean impulse values on the horizontal axis calculated for five consecutive steps above 85, regardless of the leg, indicated the slightest subjectively recognizable lameness, increasing to 130 in severe gait impairment. The range recorded on the same axis (between 61.2 and 67.4) in the sound legs allowed a safe cut-off value of 80 impulses for diagnosing a painful limb. The significance of various comparisons and several correlations highlighted the potential of this simple, affordable, and easy-to-use lameness detector device for further standardization as an aid for veterinarians in diagnosing lameness in horses.

Bilateral Change in Vertical Hoof Force Distribution in Horses with Unilateral Forelimb Lameness before and after Successful Diagnostic Anaesthesia

Kinetic examinations of horses with induced lameness as well as the effect of perineural anaesthesia in sound horses have shown promise, but clinical studies regarding the effect of diagnostic anaesthesia during the different stance phases are rare. Fourteen horses with unilateral forelimb lameness were examined with the Hoof™ System during trot to assess vertical force distribution (in kg) affecting both front hooves before and after diagnostic anaesthesia during landing, midstance, and breakover. For statistical analysis, a covariance analysis with repeated measurements regarding the limb (lame/sound) as well as anaesthesia (before/after) and the covariable body weight was performed. The p-values for the pairwise comparisons were adjusted using the Bonferroni−Holm correction (p < 0.05). For all phases of the stance, a significant interaction between the factors limb and anaesthesia was shown. Before diagnostic anaesthesia, vertical force was significantly reduced on the lame limb compared to the sound limb during landing (−25%, p < 0.001), midstance (−20%, p < 0.001) and breakover (−27%, p < 0.001). After anaesthesia, the difference between both forelimbs was not significant anymore for all phases. The vertical force on the lame limb increased significantly after positive anaesthesia during the whole stance phase, with breakover being most affected (+27%, p = 0.001). Pressure measurements with the Hoof™ System can be used to evaluate the effect of diagnostic anaesthesia in a clinical setting with pain-related vertical force asymmetries being neutralised after diagnostic anaesthesia. Breakover is the main event influenced by lameness.

Fetlock Joint Angle Pattern and Range of Motion Quantification Using Two Synchronized Wearable Inertial Sensors per Limb in Sound Horses and Horses with Single Limb Naturally Occurring Lameness

Fetlock joint angle (FJA) pattern is a sensitive indicator of lameness. The first aim of this study is to describe a network of inertial measurement units system (IMUs) for quantifying FJA simultaneously in all limbs. The second aim is to evaluate the accuracy of IMUs for quantifying the sagittal plane FJA overground in comparison to bi-dimensional (2-D) optical motion capture (OMC). 14 horses (7 free from lameness and 7 lame) were enrolled and analyzed with both systems at walk and trot on a firm surface. All enrolled horses were instrumented with 8 IMUs (a pair for each limb) positioned at the dorsal aspect of the metacarpal/metatarsal bone and pastern and acquiring data at 200 Hz. Passive markers were glued on the center of rotation of carpus/tarsus, fetlock, and distal interphalangeal joint, and video footages were captured at 60 Hz and digitalized for OMC acquisition. The IMU system accuracy was reported as Root Mean Square Error (RMSE) and Pearson Correlation Coefficient (PCC). The Granger Causality Test (GCT) and the Bland−Altman analysis were computed between the IMUs and OMC patterns to determine the agreement between the two systems. The proposed IMU system was able to provide FJAs in all limbs using a patented method for sensor calibration and related algorithms. Fetlock joint range of motion (FJROM) variability of three consecutive strides was analyzed in the population through 3-way ANOVA. FJA patterns quantified by IMUs demonstrated high accuracy at the walk (RMSE 8.23° ± 3.74°; PCC 0.95 ± 0.03) and trot (RMSE 9.44° ± 3.96°; PCC 0.96 ± 0.02) on both sound (RMSE 7.91° ± 3.19°; PCC 0.97 ± 0.03) and lame horses (RMSE 9.78° ± 4.33°; PCC 0.95 ± 0.03). The two systems’ measurements agreed (mean bias around 0) and produced patterns that were in temporal agreement in 97.33% of the cases (p < 0.01). The main source of variability between left and right FJROM in the population was the presence of lameness (p < 0.0001) and accounted for 28.46% of this total variation. IMUs system accurately quantified sagittal plane FJA at walk and trot in both sound and lame horses.

Detection of Horse Locomotion Modifications Due to Training with Inertial Measurement Units: A Proof-of-Concept

Detecting fatigue during training sessions would help riders and trainers to optimize their training. It has been shown that fatigue could affect movement patterns. Inertial measurement units (IMUs) are wearable sensors that measure linear accelerations and angular velocities, and can also provide orientation estimates. These sensors offer the possibility of a non-invasive and continuous monitoring of locomotion during training sessions. However, the indicators extracted from IMUs and their ability to show these locomotion changes are not known. The present study aims at defining which kinematic variables and indicators could highlight locomotion changes during a training session expected to be particularly demanding for the horses. Heart rate and lactatemia were measured to attest for the horse’s fatigue following the training session. Indicators derived from acceleration, angular velocities, and orientation estimates obtained from nine IMUs placed on 10 high-level dressage horses were compared before and after a training session using a non-parametric Wilcoxon paired test. These indicators were correlation coefficients (CC) and root mean square deviations (RMSD) comparing gait cycle kinematics measured before and after the training session and also movement smoothness estimates (SPARC, LDLJ). Heart rate and lactatemia measures did not attest to a significant physiological fatigue. However, the statistics show an effect of the training session (p < 0.05) on many CC and RMSD computed on the kinematic variables, indicating a change in the locomotion with the training session as well as on SPARCs indicators (p < 0.05), and revealing here a change in the movement smoothness both in canter and trot. IMUs seem then to be able to track locomotion pattern modifications due to training. Future research should be conducted to be able to fully attribute the modifications of these indicators to fatigue.

Upper Body Movement Symmetry in Reining Quarter Horses during Trot In-Hand, on the Lunge and during Ridden Exercise

Veterinary lameness examinations often comprise assessing ridden horses. Quantitative movement symmetry measurements can aid evidence-based decision making. While these are available for ‘English’ style riding, they are not for ‘Western’ style riding. This quantitative observational study quantified movement symmetry in reining Quarter Horses (QHs). Movement symmetry of the head, withers and sacrum (differences between minima, maxima and upward amplitudes) were quantified with inertial sensors in N = 30 medium/high level reining QHs during trot in-hand, on the lunge and ridden by one experienced rider (straight-line/circles) on reining-purpose riding surfaces. Mixed linear models for movement symmetry assessed the effects of ridden exercise and movement direction (fixed factors), stride time (covariate) and horse (random factor): single factors and two-way interactions with Bonferroni correction at p < 0.05. Three withers and pelvic parameters showed marginally more symmetrical movement when ridden (p ≤ 0.044; 1−5 mm differences). Three withers, three sacrum and one head parameter were significantly affected by movement direction (all p ≤ 0.026), five showed increased asymmetry on the inside rein, and two, quantifying vertical displacement maximum difference, showed the opposite. Riding QHs in ‘Western’ style showed small movement symmetry differences. Circular exercise confirmed increases in weight bearing asymmetry on the inside rein and in pushoff asymmetry on the outside rein. This should be further investigated for differentiating between different causes of lameness.

Stance Phase Detection by Inertial Measurement Unit Placed on the Metacarpus of Horses Trotting on Hard and Soft Straight Lines and Circles

The development of on-board technologies has enabled the development of quantification systems to monitor equine locomotion parameters. Their relevance among others relies on their ability to determine specific locomotor events such as foot-on and heel-off events. The objective of this study was to compare the accuracy of different methods for an automatic gait events detection from inertial measurement units (IMUs). IMUs were positioned on the cannon bone, hooves, and withers of seven horses trotting on hard and soft straight lines and circles. Longitudinal acceleration and angular velocity around the latero-medial axis of the cannon bone, and withers dorso-ventral displacement data were identified to tag the foot-on and a heel-off events. The results were compared with a reference method based on hoof-mounted-IMU data. The developed method showed bias less than 1.79%, 1.46%, 3.45% and −1.94% of stride duration, respectively, for forelimb foot-on and heel-off, and for hindlimb foot-on and heel-off detection, compared to our reference method. The results of this study showed that the developed gait-events detection method had a similar accuracy to other methods developed for straight line analysis and extended this validation to other types of exercise (circles) and ground surface (soft surface).

Cross-Modality Interaction Network for Equine Activity Recognition Using Imbalanced Multi-Modal Data

With the recent advances in deep learning, wearable sensors have increasingly been used in automated animal activity recognition. However, there are two major challenges in improving recognition performance—multi-modal feature fusion and imbalanced data modeling. In this study, to improve classification performance for equine activities while tackling these two challenges, we developed a cross-modality interaction network (CMI-Net) involving a dual convolution neural network architecture and a cross-modality interaction module (CMIM). The CMIM adaptively recalibrated the temporal- and axis-wise features in each modality by leveraging multi-modal information to achieve deep intermodality interaction. A class-balanced (CB) focal loss was adopted to supervise the training of CMI-Net to alleviate the class imbalance problem. Motion data was acquired from six neck-attached inertial measurement units from six horses. The CMI-Net was trained and verified with leave-one-out cross-validation. The results demonstrated that our CMI-Net outperformed the existing algorithms with high precision (79.74%), recall (79.57%), F1-score (79.02%), and accuracy (93.37%). The adoption of CB focal loss improved the performance of CMI-Net, with increases of 2.76%, 4.16%, and 3.92% in precision, recall, and F1-score, respectively. In conclusion, CMI-Net and CB focal loss effectively enhanced the equine activity classification performance using imbalanced multi-modal sensor data.

Kinematic gait characteristics of straight line walk in clinically sound dairy cows

The aim of this study is to describe the kinematic gait characteristics of straight line walk in clinically sound dairy cows using body mounted Inertial Measurement Units (IMUs) at multiple anatomical locations. The temporal parameters used are speed and non-speed normalized stance duration, bipedal and tripedal support durations, maximal protraction and retraction angles of the distal limbs and vertical displacement curves of the upper body. Gait analysis was performed by letting 17 dairy cows walk in a straight line at their own chosen pace while equipped with IMU sensors on tubera sacrale, left and right tuber coxae (LTC and RTC), back, withers, head, neck and all four lower limbs. Data intervals with stride by stride regularity were selected based on video data. For temporal parameters, the median was calculated and 95% confidence intervals (CI) were estimated based on linear mixed model (LMM) analysis, while for limb and vertical displacement curves, the median and most typical curves were calculated. The temporal parameters and distal limb angles showed consistent results with low variance and LMM analysis showed non-overlapping CI for all temporal parameters. The distal limb angle curves showed a larger and steeper retraction angle range for the distal front limbs compared with the hind limbs. The vertical displacement curves of the sacrum, withers, LTC and RTC showed a consistent sinusoidal pattern while the head, back and collar curves were less consistent and showed more variation between and within cows. This kinematic description might allow to objectively differentiate between normal and lame gait in the future and determine the best anatomical location for sensor attachment for lameness detection purposes.

The Protraction and Retraction Angles of Horse Limbs: An Estimation during Trotting Using Inertial Sensors

The protraction and retraction angles of horse limbs are important in the analysis of horse locomotion. This study explored two methods from an IMU positioned on the canon bone of eight horses to estimate these angles. Each method was based on a hypothesis in order to define the moment corresponding with the verticality of the canon bone: (i) the canon bone is in a vertical position at 50% of the stance phase or (ii) the verticality of the canon bone corresponds with the moment when the horse’s withers reach their lowest point. The measurements were carried out on a treadmill at a trot and compared with a standard gold method based on motion capture. For the measurement of the maximum protraction and retraction angles, method (i) had average biases (0.7° and 1.7°) less than method (ii) (−1.3° and 3.7°). For the measurement of the protraction and retraction angles during the stance phase, method (i) had average biases (4.1° and −3.3°) higher to method (ii) (2.1° and −1.3°). This study investigated the pros and cons of a generic method (i) vs. a specific method (ii) to determine the protraction and retraction angles of horse limbs by a single IMU.

Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses-A Machine Learning Approach

Speed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate during IMU signals integration. In an attempt to overcome these issues, we have investigated the possibility of estimating the horse speed by developing machine learning (ML) models using the signals from seven body-mounted IMUs. Since motion patterns extracted from IMU signals are different between breeds and gaits, we trained the models based on data from 40 Icelandic and Franches-Montagnes horses during walk, trot, tölt, pace, and canter. In addition, we studied the estimation accuracy between IMU locations on the body (sacrum, withers, head, and limbs). The models were evaluated per gait and were compared between ML algorithms and IMU location. The model yielded the highest estimation accuracy of speed (RMSE = 0.25 m/s) within equine and most of human speed estimation literature. In conclusion, highly accurate horse speed estimation models, independent of IMU(s) location on-body and gait, were developed using ML.

Reliable and clinically applicable gait event classification using upper body motion in walking and trotting horses

Objectively assessing horse movement symmetry as an adjunctive to the routine lameness evaluation is on the rise with several commercially available systems on the market. Prerequisites for quantifying such symmetries include knowledge of the gait and gait events, such as hoof to ground contact patterns over consecutive strides. Extracting this information in a robust and reliable way is essential to accurately calculate many kinematic variables commonly used in the field. In this study, optical motion capture was used to measure 222 horses of various breeds, performing a total of 82 664 steps in walk and trot under different conditions, including soft, hard and treadmill surfaces as well as moving on a straight line and in circles. Features were extracted from the pelvis and withers vertical movement and from pelvic rotations. The features were then used in a quadratic discriminant analysis to classify gait and to detect if the left/right hind limb was in contact with the ground on a step by step basis. The predictive model achieved 99.98% accuracy on the test data of 120 horses and 21 845 steps, all measured under clinical conditions. One of the benefits of the proposed method is that it does not require the use of limb kinematics making it especially suited for clinical applications where ease of use and minimal error intervention are a priority. Future research could investigate the extension of this functionality to classify other gaits and validating the use of the algorithm for inertial measurement units.

Improving gait classification in horses by using inertial measurement unit (IMU) generated data and machine learning

For centuries humans have been fascinated by the natural beauty of horses in motion and their different gaits. Gait classification (GC) is commonly performed through visual assessment and reliable, automated methods for real-time objective GC in horses are warranted. In this study, we used a full body network of wireless, high sampling-rate sensors combined with machine learning to fully automatically classify gait. Using data from 120 horses of four different domestic breeds, equipped with seven motion sensors, we included 7576 strides from eight different gaits. GC was trained using several machine-learning approaches, both from feature-extracted data and from raw sensor data. Our best GC model achieved 97% accuracy. Our technique facilitated accurate, GC that enables in-depth biomechanical studies and allows for highly accurate phenotyping of gait for genetic research and breeding. Our approach lends itself for potential use in other quadrupedal species without the need for developing gait/animal specific algorithms.

A composite hydrogel-3D printed thermoplast osteochondral anchor as example for a zonal approach to cartilage repair: in vivo performance in a long-term equine model

Recent research has been focusing on the generation of living personalized osteochondral constructs for joint repair. Native articular cartilage has a zonal structure, which is not reflected in current constructs and which may be a cause of the frequent failure of these repair attempts. Therefore, we investigated the performance of a composite implant that further reflects the zonal distribution of cellular component both in vitro and in vivo in a long-term equine model. Constructs constituted of a 3D-printed poly(ϵ-caprolactone) (PCL) bone anchor from which reinforcing fibers protruded into the chondral part of the construct over which two layers of a thiol-ene cross-linkable hyaluronic acid/poly(glycidol) hybrid hydrogel (HA-SH/P(AGE-co-G)) were fabricated. The top layer contained Articular Cartilage Progenitor Cells (ACPCs) derived from the superficial layer of native cartilage tissue, the bottom layer contained mesenchymal stromal cells (MSCs). The chondral part of control constructs were homogeneously filled with MSCs. After six months in vivo, microtomography revealed significant bone growth into the anchor. Histologically, there was only limited production of cartilage-like tissue (despite persistency of hydrogel) both in zonal and non-zonal constructs. There were no differences in histological scoring; however, the repair tissue was significantly stiffer in defects repaired with zonal constructs. The sub-optimal quality of the repair tissue may be related to several factors, including early loss of implanted cells, or inappropriate degradation rate of the hydrogel. Nonetheless, this approach may be promising and research into further tailoring of biomaterials and of construct characteristics seems warranted.

Automatic hoof-on and -off detection in horses using hoof-mounted inertial measurement unit sensors

For gait classification, hoof-on and hoof-off events are fundamental locomotion characteristics of interest. These events can be measured with inertial measurement units (IMUs) which measure the acceleration and angular velocity in three directions. The aim of this study was to present two algorithms for automatic detection of hoof-events from the acceleration and angular velocity signals measured by hoof-mounted IMUs in walk and trot on a hard surface. Seven Warmblood horses were equipped with two wireless IMUs, which were attached to the lateral wall of the right front (RF) and hind (RH) hooves. Horses were walked and trotted on a lead over a force plate for internal validation. The agreement between the algorithms for the acceleration and angular velocity signals with the force plate was evaluated by Bland Altman analysis and linear mixed model analysis. These analyses were performed for both hoof-on and hoof-off detection and for both algorithms separately. For the hoof-on detection, the angular velocity algorithm was the most accurate with an accuracy between 2.39 and 12.22 ms and a precision of around 13.80 ms, depending on gait and hoof. For hoof-off detection, the acceleration algorithm was the most accurate with an accuracy of 3.20 ms and precision of 6.39 ms, independent of gait and hoof. These algorithms look highly promising for gait classification purposes although the applicability of these algorithms should be investigated under different circumstances, such as different surfaces and different hoof trimming conditions.

Automatic detection of break-over phase onset in horses using hoof-mounted inertial measurement unit sensors

A prolonged break-over phase might be an indication of a variety of musculoskeletal disorders and can be measured with optical motion capture (OMC) systems, inertial measurement units (IMUs) and force plates. The aim of this study was to present two algorithms for automatic detection of the break-over phase onset from the acceleration and angular velocity signals measured by hoof-mounted IMUs in walk and trot on a hard surface. The performance of these algorithms was evaluated by internal validation with an OMC system and a force plate separately. Seven Warmblood horses were equipped with two wireless IMUs which were attached to the lateral wall of the right front (RF) and hind (RH) hooves. Horses were walked and trotted over a force plate for internal validation while simultaneously the 3D position of three reflective markers, attached to lateral heel, lateral toe and lateral coronet of each hoof, were measured by six infrared cameras of an OMC system. The performance of the algorithms was evaluated by linear mixed model analysis. The acceleration algorithm was the most accurate with an accuracy between -9 and 23 ms and a precision around 24 ms (against OMC system), and an accuracy between -37 and 20 ms and a precision around 29 ms (against force plate), depending on gait and hoof. This algorithm seems promising for quantification of the break-over phase onset although the applicability for clinical purposes, such as lameness detection and evaluation of trimming and shoeing techniques, should be investigated more in-depth.

Temporo-spatial and kinetic gait parameters in English setter dogs

Walking analysis systems have begun to be used in veterinary medicine in recent years. The pressure-sensitive walkway is one of the systems through which we can obtain temporo-spatial and kinetic variables of walking. Therefore, the aim of this study was to investigate the walking characteristics of English Setter dogs using a pressure-sensitive system. Twenty-five English Setter dogs were included in the study. Temporo-spatial and kinetic gait parameters were obtained with the pressure-sensitive walkway system. Centre of pressure values were taken separately for the forelimbs and hindlimbs and were statistically analysed. The force values in the forelimb were found to be greater than in the hindlimb during walking. According to the results of dynamic pedobarographic evaluation, the highest-pressure values were found at the 2nd and 3rd digital pads for the forelimbs and on the 3rd and 4th digital pads for the hindlimbs. During the stance, 64.58% of the weight was found to be on the forelimbs. No difference was found between the forelimbs and the hindlimbs in centre of pressure analysis. As conclusion, the gait data obtained from the English Setter dogs can be used in future research to identify animals that may have neurological or orthopaedic problems.

Comparison of Trotting Stance Detection Methods from an Inertial Measurement Unit Mounted on the Horse's Limb

The development of on-board sensors, such as inertial measurement units (IMU), has made it possible to develop new methods for analyzing horse locomotion to detect lameness. The detection of spatiotemporal events is one of the keystones in the analysis of horse locomotion. This study assesses the performance of four methods for detecting Foot on and Foot off events. They were developed from an IMU positioned on the canon bone of eight horses during trotting recording on a treadmill and compared to a standard gold method based on motion capture. These methods are based on accelerometer and gyroscope data and use either thresholding or wavelets to detect stride events. The two methods developed from gyroscopic data showed more precision than those developed from accelerometric data with a bias less than 0.6% of stride duration for Foot on and 0.1% of stride duration for Foot off. The gyroscope is less impacted by the different patterns of strides, specific to each horse. To conclude, methods using the gyroscope present the potential of further developments to investigate the effects of different gait paces and ground types in the analysis of horse locomotion.

Automated Step Detection in Inertial Measurement Unit Data From Turkeys

Locomotion is an important welfare and health trait in turkey production. Current breeding values for locomotion are often based on subjective scoring. Sensor technologies could be applied to obtain objective evaluation of turkey gait. Inertial measurement units (IMUs) measure acceleration and rotational velocity, which makes them attractive devices for gait analysis. The aim of this study was to compare three different methods for step detection from IMU data from turkeys. This is an essential step for future feature extraction for the evaluation of turkey locomotion. Data from turkeys walking through a corridor with IMUs attached to each upper leg were annotated manually. We evaluated change point detection, local extrema approach, and gradient boosting machine in terms of step detection and precision of start and end point of the steps. All three methods were successful in step detection, but local extrema approach showed more false detections. In terms of precision of start and end point of steps, change point detection performed poorly due to significant irregular delay, while gradient boosting machine was most precise. For the allowed distance to the annotated steps of 0.2 s, the precision of gradient boosting machine was 0.81 and the recall was 0.84, which is much better in comparison to the other two methods (<0.61). At an allowed distance of 1 s, performance of the three models was similar. Gradient boosting machine was identified as the most accurate for signal segmentation with a final goal to extract information about turkey gait; however, it requires an annotated training dataset.

A Method to Estimate Horse Speed per Stride from One IMU with a Machine Learning Method

With the emergence of numerical sensors in sports, there is an increasing need for tools and methods to compute objective motion parameters with great accuracy. In particular, inertial measurement units are increasingly used in the clinical domain or the sports one to estimate spatiotemporal parameters. The purpose of the present study was to develop a model that can be included in a smart device in order to estimate the horse speed per stride from accelerometric and gyroscopic data without the use of a global positioning system, enabling the use of such a tool in both indoor and outdoor conditions. The accuracy of two speed calculation methods was compared: one signal based and one machine learning model. Those two methods allowed the calculation of speed from accelerometric and gyroscopic data without any other external input. For this purpose, data were collected under various speeds on straight lines and curved paths. Two reference systems were used to measure the speed in order to have a reference speed value to compare each tested model and estimate their accuracy. Those models were compared according to three different criteria: the percentage of error above 0.6 m/s, the RMSE, and the Bland and Altman limit of agreement. The machine learning method outperformed its competitor by giving the lowest value for all three criteria. The main contribution of this work is that it is the first method that gives an accurate speed per stride for horses without being coupled with a global positioning system or a magnetometer. No similar study performed on horses exists to compare our work with, so the presented model is compared to existing models for human walking. Moreover, this tool can be extended to other equestrian sports, as well as bipedal locomotion as long as consistent data are provided to train the machine learning model. The machine learning model’s accurate results can be explained by the large database built to train the model and the innovative way of slicing stride data before using them as an input for the model.

Irish Equine Industry Stakeholder Perspectives of Objective Technology for Biomechanical Analyses in the Field

Wearable sensing technologies are increasingly used in human and equine gait research to improve ecological validity of research findings. It is unclear how these tools have penetrated the equine industry or what perspectives industry stakeholders' hold in relation to these relatively new devices. Semi-structured interviews were conducted with Irish equine industry stakeholders to understand their perception of objective tools for biomechanical analysis in the field. The study participants came from professional/elite backgrounds in both the sport horse (n = 6) and thoroughbred (n = 6) sectors. The interview data were analysed using thematic analysis, resulting in four analytical themes. The first theme conveys the importance of tacit knowledge and experience in the holistic analysis of a horse. Theme two highlights that the perfect horse does not exist therefore, equine athlete management is complex and requires a multi-layered problem-solving approach. Theme three describes an awareness among stakeholders of technologies, however they are sceptical of their value. The final theme identified that one of the key barriers to technology adoption is the economic value of the horse and the cost of implementing technology herd-wide. Our findings highlight the need for a user-centred design in this domain, which requires greater consultation and learning between technology developers and equine stakeholders to develop fit-for-purpose analysis and monitoring tools.

Sensor-based equine gait analysis: more than meets the eye?

Quantitative gait analysis in the lame horse has gained in popularity, likely related to the potential to remove bias from the clinical decision-making process. Its implementation into clinical practice is, however, not without challenges. This review visits some of the challenges related to the use of thresholds and guideline values in the context of clinical decision making, as well as when applied to scientific studies based on relevant published studies: issues such as ‘normal day-to-day variation’, conformational asymmetry and the often limited number of parameters that are being quantified. Emphasis is put on outlining the basic underlying principles relating to head nod and hip hike, which are explained in the context of Newtonian mechanics associating reduced vertical acceleration of the upper body to reduced force production with the limb that is in contact with the ground during that time period. Further to quantifying what can be seen ‘by eye’, the review also visits phenomena such as asymmetries in weight bearing or pushoff and compensatory mechanisms, with emphasis on measurement of withers movement and thoughts about multilimb lameness. The review concludes with thoughts about additional parameters such as limb movement and movement of the thoraco-lumbo-sacral area, which may provide additional insights into lameness and poor performance but are at current less frequently included into clinical gait analysis in the horse.

Variation in gait parameters used for objective lameness assessment in sound horses at the trot on the straight line and the lunge

Background

Objective lameness assessment is gaining more importance in a clinical setting, necessitating availability of reference values.

Objectives

To investigate the between ‐path, ‐trial and ‐day variation, between and within horses, in the locomotion symmetry of horses in regular use that are perceived sound.

Study design

Observational study with replicated measurement sessions.

Methods

Twelve owner‐sound horses were trotted on the straight line and on the lunge. Kinematic data were collected from these horses using 3D optical motion capture. Examinations were repeated on 12 occasions over the study which lasted 42 days in total. For each horse, measurements were grouped as five replicates on the first and second measurement days and two replicates on the third measurement day. Between measurement days 2 and 3, every horse had a break from examination of at least 28 days. Previously described symmetry parameters were calculated: RUD and RDD (Range Up/Down Difference; difference in upward/downward movement between right and left halves of a stride); MinDiff and MaxDiff (difference between the two minima/maxima of the movement); HHDswing and HHDstance (Hip Hike Difference‐swing/‐stance; difference between the upward movement of the tuber coxae during swingphase/stancephase). Data are described by the between‐measurement variation for each parameter. A linear mixed model was used to test for the effect of time, surface and path. Intraclass correlation coefficients (ICC) were calculated to access repeatability.

Results

Mean between‐measurement variation was (MinDiff, MaxDiff, RUD, RDD): 13, 12, 20, 16 mm (head); 4, 3, 6, 4 mm (withers) and 5, 4, 6, 6 mm (pelvis); (HHDswing, HHDstance): 7 and 7 mm. More between‐measurement variation is seen on the first measurement day compared to the second and third measurement days. In general, less variation is seen with increasing number of repetitions. Less between‐measurement variation is seen on hard surface compared to soft surface. More between‐measurement variation is seen on the circle compared to the straight line. Between‐horse variation was clearly larger than within‐horse variation. ICC values for the head, withers and pelvis symmetry parameters were 0.68 (head), 0.76 (withers), 0.85 (pelvis).

Main limitations

Lunge measurements on a hard surface were not performed.

Conclusions

Between‐measurement variation may be substantial, especially in head motion. This should be considered when interpreting clinical data after repeated measurements, as in routine lameness assessments.