Abstract: Fatigue in sport horses is a multifactorial phenomenon that critically affects performance, injury risk, and welfare, yet its real-time, field-based assessment remains an unmet challenge. Objective: To synthesise evidence on the use of wearable sensors and machine learning for fatigue-related monitoring in sport horses and to identify priorities for future fatigue assessment. Methods: Scoping review. Methods: This scoping review was conducted in accordance with PRISMA-ScR guidelines. Publications from 2015 to 2026 were identified through Web of Science, Scopus, and ScienceDirect. Evidence from 102 publications was synthesised across five sensing modalities-heart rate (HR)/heart rate variability (HRV), thermometry, inertial measurement units (IMUs), surface electromyography (sEMG), and GPS-alongside machine learning applications for feature extraction, state classification, and risk modelling. Results: Our synthesis reveals a fundamental disconnect: while each technology captures distinct physiological or biomechanical correlates of load, including autonomic response, thermoregulatory strain, gait stability, neuromuscular activation, and external workload, none provides a standalone signature of fatigue. Only a minority of studies used fatigue as a direct modelling label, with most relying on proxy outcomes such as asymmetry or performance decrement. Conclusions: The included literature was heterogeneous in sensor modalities, study designs, outcome measures, and application contexts. In addition, the limited use of directly defined fatigue outcomes restricted comparison across studies and constrained conclusions regarding fatigue-specific monitoring. Conclusions: The path forward lies not in developing yet another single-sensor solution, but in establishing a multidimensional, context-aware framework that integrates complementary data streams, individualised baselines, and interpretable models. Future research should prioritise: (1) operationalised fatigue definitions; (2) longitudinal, within-horse monitoring designs; (3) robust multimodal fusion architectures; (4) rigorous external validation across equestrian disciplines; and (5) explainable artificial intelligence to bridge the gap between algorithmic output and actionable training decisions.
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.
Overview
This research reviews how wearable sensors and machine learning have been used to assess fatigue in sport horses, highlighting that no single technology effectively captures fatigue alone.
The study emphasizes the need for integrated, multidimensional approaches and provides recommendations for future research to improve real-time fatigue monitoring in equine sports.
Introduction and Background
Fatigue in sport horses affects their performance, injury risk, and welfare significantly.
It is a complex phenomenon influenced by multiple physiological and biomechanical factors.
Real-time, field-based assessment of fatigue in horses remains an unmet challenge despite technological advances.
Objectives of the Study
To synthesise existing evidence on the use of wearable sensors combined with machine learning techniques for monitoring fatigue in sport horses.
To identify current gaps and future priorities in fatigue assessment research for equine athletes.
Methodology
The study is a scoping review conducted according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines.
Literature from 2015 to 2026 was sourced from Web of Science, Scopus, and ScienceDirect databases.
102 relevant publications were included for synthesis and analysis.
Wearable Sensor Modalities Explored
Heart Rate (HR) and Heart Rate Variability (HRV): Measure autonomic nervous system responses related to physiological load and stress.
Thermometry: Assesses thermoregulatory strain, which can correlate with fatigue levels.
Inertial Measurement Units (IMUs): Track gait and movement stability, offering biomechanical insights linked to fatigue.
Surface Electromyography (sEMG): Measures neuromuscular activation patterns indicative of muscle fatigue and load.
Global Positioning System (GPS): Records external workload metrics such as speed, distance, and movement patterns during exercise.
Role of Machine Learning
Applied to extract meaningful features from complex sensor data.
Used for classification tasks such as identifying fatigue states or predicting fatigue-related risk.
Supports risk modelling to potentially forecast injury related to fatigue.
Facilitates handling and fusion of multimodal data for better understanding of fatigue.
Key Findings
Each wearable technology captures different physiological or biomechanical correlates of fatigue, but none alone is sufficient to definitively measure fatigue.
Majority of studies use indirect or proxy outcomes such as movement asymmetry or drops in performance, rather than direct fatigue measurements.
There is heterogeneity in sensor types, study protocols, outcome definitions, and contexts across research, limiting cross-study comparisons.
The limited application of directly defined fatigue outcomes constrains the ability to draw conclusive evidence on targeted fatigue monitoring.
Conclusions and Recommendations
Developing another single-sensor solution is unlikely to fully capture the multifaceted nature of fatigue in horses.
A multidimensional and context-aware framework integrating multiple sensor data streams is necessary for effective fatigue assessment.
This approach should incorporate individualised baseline measures for each horse and use interpretable machine learning models.
Priorities for future research include:
Establishing clear, operationalised definitions of fatigue specific to equine athletes.
Designing longitudinal studies that monitor the same horses over time to track fatigue progression.
Developing robust multimodal data fusion architectures that integrate physiological, biomechanical, and workload data.
Rigorously validating fatigue assessment models across different equestrian disciplines and real-world conditions.
Utilizing explainable artificial intelligence techniques to make model outputs understandable and actionable for trainers and veterinarians.
Implications for the Equine Sports Community
Real-time and accurate fatigue monitoring can improve training decisions, reduce injury risk, and enhance horse welfare.
The integration of multiple sensor technologies supported by advanced machine learning will enable better personalized monitoring strategies.
Greater clarity and standardization in fatigue definitions and assessment methods will help the community adopt these technologies effectively.
Cite This Article
APA
Li Y, Yan Z, Chen X.
(2026).
Wearable sensing technologies and machine learning for fatigue assessment in sport horses.
Equine Vet J.
https://doi.org/10.1002/evj.70360
Hennes N, Briant C, Lorcet C, Ruet A, Lansade L. Behaviours exhibited during training predict physical tiredness in harness trotter horses. Appl Anim Behav Sci 2024;274:106245.
Siegers EW, Sloet van Oldruitenborgh‐Oosterbaan MM, Munsters CCBM. The use of exercise testing to assess training efficacy in sport horses. Equine Vet Educ 2026;38(7):382–396.
Boffi FM, Lindner A, Lopez RA, Botta V, Sadaba S, Muriel M. Effect of recovery periods during conditioning of horses on fitness parameters. J Equine Vet Sci 2011;31(11):661–666.
Waran N, Randle H. What we can measure, we can manage: the importance of using robust welfare indicators in equitation science. Appl Anim Behav Sci 2017;190:74–81.
Aarts RM, Siegers EW, Serra Bragança FM, van Weeren PR. Technologies for equine welfare and performance monitoring under field conditions—where do we stand?. Equine Vet J 2026;58(4):872–888.
Tornero‐Aguilera JF, Jimenez‐Morcillo J, Rubio‐Zarapuz A, Clemente‐Suárez VJ. Central and peripheral fatigue in physical exercise explained: a narrative review.. Int J Environ Res Public Health 2022;19(7):3909.
Tricco AC, Lillie E, Zarin W, O'Brien KK, Colquhoun H, Levac D. PRISMA extension for scoping reviews (PRISMA‐ScR): checklist and explanation.. Ann Intern Med 2018;169(7):467–473.
Nery J, Racioppi F, Valle E, Assenza A, Bergero D. Proof of concept on energy expenditure assessment using heart rate monitoring and inertial platforms in show‐jumping and riding school horses.. J Equine Vet Sci 2018;61:1–6.
Lorello O, Ramseyer A, Burger D, Gerber V, Bruckmaier RM, van der Kolk JH. Repeated measurements of markers of autonomic tone over a training season in eventing horses. J Equine Vet Sci 2017;53:38–44.
de Mira MC, Williams J, dos Santos RG, Rodrigues P, Arroja B, Marlin D. Do waiting times in endurance vet gates affect the cardiac recovery index?. Comp Exerc Physiol 2020;16(5):415–422.
Šmondrková M, Halo M, Zaťko S, Mlyneková E, Halo M. Physiological indicators of workload in horses: analysis of heart rate and energy expenditure during riding. Acta Fytotech Zootech 2025;28(4):336–342.
Tischner M, Tischner M, Lis M, Maciejczyk M. Analysis of work intensity in draft horses based on the heart rate recovery index. Med Weter 2022;78(10):509–512.
Murphy K, Solomon C, Stefanovski D, Lorello O, Robinson M, Haughan J. Correlation of detrended fluctuation analysis alpha 1 with blood lactate concentration in field standardized exercise tests in sport horses. Comp Exerc Physiol 2024;20(2):121–129.
Brownlow M, Smith T. The use of the hand‐held infrared thermometer as an early detection tool for exertional heat illness in Thoroughbred racehorses: a study at racetracks in eastern Australia. Equine Vet Educ 2021;33(6):296–305.
Ebisuda Y, Mukai K, Takahashi Y, Ohmura H. Effect of high ambient temperature on physiological responses during incremental exercise in Thoroughbred horses. Comp Exerc Physiol 2023;19(2):159–167.
Costa GG, Passini R. Thermographic analysis of physiological conditions and after exercise in classic equestrian horses. Semina Cienc Agrar 2024;45(3):677–688.
Gerardi B, Denadai DS, Pereira MS, Chaves AA, Barbosa JPB, Peiró JR. Use of infrared thermography in Quarter Horse submitted to team roping. Pesqui Vet Bras 2019;39(7):530–537.
Marlin DJ, Reynolds H, Mukai K, Neil K, Akerstrom G. Estimating rectal temperature in exercising horses in a competition environment using infrared thermal imaging. Comp Exerc Physiol 2024;20(1):45–53.
Soroko M, Howell K, Dudek K, Wilk I, Zastrzeżyńska M, Janczarek I. A pilot study into the utility of dynamic infrared thermography for measuring body surface temperature changes during treadmill exercise in horses. J Equine Vet Sci 2018;62:44–46.
Aarts RM, Smit IH, Ferraz GDC, Rhodin M, Serra Bragança FM, Hernlund E. Quantitative assessment of gait alterations and variability in sulky‐driven Standardbred trotters after a standardized exercise test. Equine Vet J 2026;58(5):1482–1492.
Borowska A, Błachowiak W, Lewczuk D. Comparison of the training and gait parameters of sport and leisure warmblood horses using the Seaver device. Anim Sci‐Genet 2025;21(3):133–144.
Fercher C. Performance‐related data capture based on inertial sensors for movement monitoring in equestrian show jumping. Pferdeheilkunde 2017;33(4):377–385.
Lopes MAF, Eleuterio A, Mira MC. Objective detection and quantification of irregular gait with a portable inertial sensor‐based system in horses during an endurance race—a preliminary assessment. J Equine Vet Sci 2018;70:123–129.
Horan K, Pfau T. Effects of jockey position and surfaces on horse movement asymmetry and horse‐jockey synchronization during trotting exercise. PLoS One 2025;20(5):e0324753.
Landsbergen K, Davis BL, Garcia K, Kenny O, Kernot N, Scott WM. Movement symmetry and back range of motion in reining Quarter Horses. J Equine Vet Sci 2024;2:100011.
Rodrigues APD, Azevedo MD, Pozzobon R. Assessment of movement asymmetry in horses without saddle, saddled, and ridden by different riders in a straight line. Cienc Rural 2025;55(11):e20240270.
Buchner HHF, Zimmer L, Haase L, Perrier J, Peham C. Effects of whole body vibration on the horse: actual vibration, muscle activity, and warm‐up effect. J Equine Vet Sci 2017;51:54–60.
Eldridge F, St George L, Chapman M, Harrison L, Tabor G, Uttley C. A comparison of equine hindlimb muscle activation and joint motion between forward and backward walking. J Equine Rehabil 2025;3:100036.
Hernández‐Fernández T, Gutiérrez‐Cepeda L, López‐Sanromán J, Manso‐Díaz G, Cediel R. Electromyographic and ultrasonographic evaluation of neuromuscular electrical stimulation training on the equine rectus abdominis muscle. Comp Exerc Physiol 2020;16(2):87–100.
Kirsch K, Düe M, Holzhausen H, Sandersen C. Correlation of competition performance with heart rate and blood lactate response during interval training sessions in eventing horses.. Comp Exerc Physiol 2019;15(3):187–198.
Lee YW, Hwang HS, Song HE, Shim ST, Ko JJ, Seo JP. The application of the measurement of heart rate and velocity during training to assess racing performance in Thoroughbred horses.. J Vet Clin 2019;36(1):62–67.
Nardelli M, Lanatà A, Valenza G, Felici M, Baragli P, Scilingo EP. A tool for the real‐time evaluation of ECG signal quality and activity: application to submaximal treadmill test in horses.. Biomed Signal Process Control 2020;56:101666.
Rana M, Mittal V. Horse gait analysis using wearable inertial sensors and machine learning. Proc Inst Mech Eng Part P J Sports Eng Technol 2025;239(4):711–725.
Mouloodi S, Rahmanpanah H, Martin C, Gohery S, Burvill C, Davies HMS. The use of deep learning algorithms to predict mechanical strain from linear acceleration and angular rates of motion recorded from a horse hoof during exercise. Int J Mech Sci 2022;216:106972.
Darbandi H, Serra Bragança FM, van der Zwaag BJ, Voskamp JP, Gmel AI, Haraldsdóttir EH. Using different combinations of body‐mounted IMU sensors to estimate speed of horses: a machine learning approach. Sensors (Basel) 2021;21(3):798.
Yigit T, Han F, Rankins E, Yi J, McKeever KH, Malinowski K. Wearable inertial sensor‐based limb lameness detection and pose estimation for horses. IEEE Trans Autom Sci Eng 2022;19(3):1365–1379.
Lee JN, Byeon YH, Kwak KC. Design of ensemble stacked auto‐encoder for classification of horse gaits with MEMS inertial sensor technology. Micromachines (Basel) 2018;9(8):411.
De Waele T, Shahid A, Peralta D, Eerdekens A, Deruyck M, Tuyttens F. Time‐series‐based feature selection and clustering for equine activity recognition using accelerometers. IEEE Sensors J 2023;23(11):11855–11868.
Eerdekens A, Deruyck M, Fontaine J, Martens L, De Poorter E, Plets D. A framework for energy‐efficient equine activity recognition with leg accelerometers. Comput Electron Agric 2021;183:106020.
Eerdekens A, Deruyck M, Fontaine J, Martens L, De Poorter E, Joseph W. Automatic equine activity detection by convolutional neural networks using accelerometer data. Comput Electron Agric 2020;168:105139.
Bourdon PC, Cardinale M, Murray A, Gastin P, Kellmann M, Varley MC. Monitoring athlete training loads: consensus statement. Int J Sports Physiol Perform 2017;12(Suppl 2):S2‐161–S2‐170.