FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Equine Vet J / Objective movement asymmetry in horses is comparable between...
Equine veterinary journal2024; doi: 10.1111/evj.14089

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

Abstract: 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). Methods: 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. Conclusions: 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.
© 2024 The Authors. Equine Veterinary Journal published by John Wiley & Sons Ltd on behalf of EVJ Ltd.
Get Full Text
Publication Date: 2024-04-02 PubMed ID: 38566453DOI: 10.1111/evj.14089Google Scholar: Lookup
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.
LinkedInCopy
  • Journal Article

Summary

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.

This research article focuses on the comparison of a markerless artificial intelligence system for lameness detection in horses with common inertial measurement unit (IMU) systems under real-world conditions. The main finding supports the hypothesis that both markerless technology and sensor-based approaches are equivalently effective in categorizing limb asymmetry when using established thresholds.

Methods of the Study

  • The researchers carried out a descriptive clinical study where data were gathered from 52 client-owned horses.
  • Utilizing a markerless AI system (SleipAI), the Equinosis Q Lameness Locator (LL), and the EquiMoves (EM), they captured the horses’ straight line trot details.
  • Different limbs were classified as symmetric or asymmetric, and the various systems analyzed the number of strides.
  • The researchers used Wilcoxon’s each pairs test to compare analyzed strides numbers and Light’s Kappa to determine the inter-rater reliability for limb asymmetry classification.
  • Finally, they performed a Bland Altman analysis on the normalized asymmetry data.

Findings of the Study

  • The results utilized 41 horses’ data, with most of these horses demonstrating a slight asymmetry in their movement.
  • The EquiMoves system was found to analyze significantly more strides than the other systems for both fore and hindlimbs.
  • On the other hand, the Lameness Locator system analyzed more hindlimb strides than the markerless SleipAI system.
  • There was a moderate agreement between systems when classifying limb asymmetry, but the agreement lessened when subjective evaluation was included.
  • In terms of analyzing normalized asymmetry data, the highest agreement was found between the two IMU systems (LL and EM).

Conclusions

  • The study limited its assessments of the horses during straight-line trotting only.
  • The systems are suitably comparative in terms of classifying asymmetric limbs under field conditions when designated asymmetry thresholds were utilized.
  • The main differences essentially arose from the defined thresholds, in that they identified the asymmetry on the same side.
  • Moreover, the strongest agreement was found between the Lameness Locator and EquiMoves systems.
  • One notable limitation of the SleipAI system observed was it analyzed considerably fewer hindlimb strides than the LL and EM systems.

Cite This Article

APA
Kallerud AS, Marques-Smith P, Bendiksen HK, Fjordbakk CT. (2024). Objective movement asymmetry in horses is comparable between markerless technology and sensor-based systems. Equine Vet J. https://doi.org/10.1111/evj.14089

Publication

Equine veterinary journal
ISSN: 2042-3306
NlmUniqueID: 0173320
Country: United States
Language: English

Researcher Affiliations

Kallerud, Anne S
  • Department of Companion Animal Clinical Sciences, Norwegian University of Life Sciences, Aas, Norway.
Marques-Smith, Patrick
  • Department of Companion Animal Clinical Sciences, Norwegian University of Life Sciences, Aas, Norway.
Bendiksen, Helle K
  • Veterinærene Bendiksen & Smith, Aas, Norway.
Fjordbakk, Cathrine T
  • Department of Companion Animal Clinical Sciences, Norwegian University of Life Sciences, Aas, Norway.

Grant Funding

  • Norwegian University of Life Sciences (NMBU)

References

This article includes 21 references
  1. Keegan KG, Dent EV, Wilson DA, Janicek J, Kramer J, Lacarrubba A. Repeatability of subjective evaluation of lameness in horses. Equine Vet J 2010;42(2):92–97.
    doi: 10.2746/042516409x479568google scholar: lookup
  2. Hammarberg M, Egenvall A, Pfau T, Rhodin M. Rater agreement of visual lameness assessment in horses during lungeing. Equine Vet J 2016;48(1):78–82.
    doi: 10.1111/evj.12385google scholar: lookup
  3. Starke SD, Oosterlinck M. Reliability of equine visual lameness classification as a function of expertise, lameness severity and rater confidence. Vet Rec 2019;184(2):63.
    doi: 10.1136/vr.105058google scholar: lookup
  4. McCracken MJ, Kramer J, Keegan KG, Lopes M, Wilson DA, Reed SK. Comparison of an inertial sensor system of lameness quantification with subjective lameness evaluation. Equine Vet J 2012;44(6):652–656.
    doi: 10.1111/j.2042-3306.2012.00571.xgoogle scholar: lookup
  5. Leelamankong P, Estrada R, Mahlmann K, Rungsri P, Lischer C. Agreement among equine veterinarians and between equine veterinarians and inertial sensor system during clinical examination of hindlimb lameness in horses. Equine Vet J 2020;52(2):326–331.
    doi: 10.1111/evj.13144google scholar: lookup
  6. Arkell M, Archer RM, Guitian FJ, May SA. Evidence of bias affecting the interpretation of the results of local anaesthetic nerve blocks when assessing lameness in horses. Vet Rec 2006;159(11):346–349.
    doi: 10.1136/vr.159.11.346google scholar: lookup
  7. Maliye S, Voute L, Lund D, Marshall JF. An inertial sensor‐based system can objectively assess diagnostic anaesthesia of the equine foot. Equine Vet J 2013;45(S45):26–30.
    doi: 10.1111/evj.12158google scholar: lookup
  8. Keegan KG, Wilson DA, Kramer J, Reed SK, Yonezawa Y, Maki H. Comparison of a body‐mounted inertial sensor system‐based method with subjective evaluation for detection of lameness in horses. Am J Vet Res 2013;74(1):17–24.
    doi: 10.2460/ajvr.74.1.17google scholar: lookup
  9. Lawin FJ, Bystrom A, Roepstorff C, Rhodin M, Almlof M, Silva M. Is markerless more or less? Comparing a smartphone computer vision method for equine lameness assessment to multi‐camera motion capture. Animals (Basel) 2023;13(3):1–44.
    doi: 10.3390/ani13030390google scholar: lookup
  10. Pfau T, Landsbergen K, Davis BL, Kenny O, Kernot N, Rochard N. Comparing inertial measurement units to markerless video analysis for movement symmetry in quarter horses. Sensors (Basel) 2023;23(20):1–14.
    doi: 10.3390/s23208414google scholar: lookup
  11. Keegan KG, Kramer J, Yonezawa Y, Maki H, Pai PF, Dent EV. Assessment of repeatability of a wireless, inertial sensor‐based lameness evaluation system for horses. Am J Vet Res 2011;72(9):1156–1163.
    doi: 10.2460/ajvr.72.9.1156google scholar: lookup
  12. Bosch S, Serra Braganca F, Marin-Perianu M, Marin-Perianu R, van der Zwaag BJ, Voskamp J. EquiMoves: a wireless networked inertial measurement system for objective examination of horse gait. Sensors (Basel) 2018;18(3):1–35.
    doi: 10.3390/s18030850google scholar: lookup
  13. Ross MW, Dyson SJ. Diagnosis and management of lameness in the horse. 2nd ed. St Louis: Saunders Elsevier; 2011. p. 1424.
  14. Pitts JB, Kramer J, Reed SK, Schiltz P, Thombs L, Keegan KG. Effect of induced hindlimb length difference on body‐mounted inertial sensor measures used to evaluate hindlimb lameness in horses. PLoS One 2020;15(2):e0228872.
    doi: 10.1371/journal.pone.0228872google scholar: lookup
  15. Hardeman AM, Serra Braganca FM, Swagemakers JH, van Weeren PR, Roepstorff L. Variation in gait parameters used for objective lameness assessment in sound horses at the trot on the straight line and the lunge. Equine Vet J 2019;51(6):831–839.
    doi: 10.1111/evj.13075google scholar: lookup
  16. Cicchetti DV. Multiple comparison methods: establishing guidelines for their valid application in neuropsychological research. J Clin Exp Neuropsychol 1994;16(1):155–161.
    doi: 10.1080/01688639408402625google scholar: lookup
  17. van Weeren PR, Pfau T, Rhodin M, Roepstorff L, Serra Braganca F, Weishaupt MA. Do we have to redefine lameness in the era of quantitative gait analysis?. Equine Vet J 2017;49(5):567–569.
    doi: 10.1111/evj.12715google scholar: lookup
  18. Reed SK, Kramer J, Thombs L, Pitts JB, Wilson DA, Keegan KG. Comparison of results for body‐mounted inertial sensor assessment with final lameness determination in 1,224 equids. J Am Vet Med Assoc 2020;256(5):590–599.
    doi: 10.2460/javma.256.5.590google scholar: lookup
  19. Peham C, Licka T, Girtler D, Scheidl M. The influence of lameness on equine stride length consistency. Vet J 2001;162(2):153–157.
    doi: 10.1053/tvjl.2001.0593google scholar: lookup
  20. Donnell JR, Frisbie DD, King MR, Goodrich LR, Haussler KK. Comparison of subjective lameness evaluation, force platforms and an inertial‐sensor system to identify mild lameness in an equine osteoarthritis model. Vet J 2015;206(2):136–142.
    doi: 10.1016/j.tvjl.2015.08.004google scholar: lookup
  21. Keegan KG, Wilson DA, Wilson DJ, Smith B, Gaughan EM, Pleasant RS. Evaluation of mild lameness in horses trotting on a treadmill by clinicians and interns or residents and correlation of their assessments with kinematic gait analysis. Am J Vet Res 1998;59(11):1370–1377.

Citations

This article has been cited 6 times.
  1. Key K, Berg K, Kirkegaard J, Andresen KR, Hansen SS. Evaluating the Accuracy of a Vision-Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles. Vet Med Sci 2026 Jan;12(1):e70739.
    doi: 10.1002/vms3.70739pubmed: 41467589google scholar: lookup
  2. Shaffer SK, Medjaouri O, Swenson B, Eliason T, Nicolella DP. A Markerless Approach for Full-Body Biomechanics of Horses. Animals (Basel) 2025 Aug 5;15(15).
    doi: 10.3390/ani15152281pubmed: 40805071google scholar: lookup
  3. Geiger T, Lindenhahn L, Delarocque J, Geburek F. Evaluation of water treadmill training, lunging and treadmill training in the rehabilitation of horses with back pain. BMC Vet Res 2025 Jul 29;21(1):495.
    doi: 10.1186/s12917-025-04950-2pubmed: 40731015google scholar: lookup
  4. Meistro F, Ralletti MV, Rinnovati R, Spadari A. Objective Evaluation of Gait Asymmetries in Traditional Racehorses During Pre-Race Inspection: Application of a Markerless AI System in Straight-Line and Lungeing Conditions. Animals (Basel) 2025 Jun 18;15(12).
    doi: 10.3390/ani15121797pubmed: 40564348google scholar: lookup
  5. de Chiara M, Montano C, De Matteis A, Guidi L, Buono F, Auletta L, Del Prete C, Pasolini MP. Agreement between subjective gait assessment and markerless video gait-analysis in endurance horses. Equine Vet J 2026 Jan;58(1):60-67.
    doi: 10.1111/evj.14516pubmed: 40257418google scholar: lookup
  6. Clayton HM, Hobbs SJ, Rhodin M, Hernlund E, Peterson M, Bos R, Bragança FS. Vertical Movement of Head, Withers, and Pelvis of High-Level Dressage Horses Trotting in Hand vs. Being Ridden. Animals (Basel) 2025 Jan 16;15(2).
    doi: 10.3390/ani15020241pubmed: 39858241google scholar: lookup
Subscribe to our newsletter
Join 99,075 horse owners like you who receive our email updates on horse health and nutrition.