Related Experiment Video
Updated: Jun 29, 2025
Movement Retraining using Real-time Feedback of Performance
Published on: January 17, 2013
Objective movement asymmetry in horses is comparable between markerless technology and sensor-based systems
Anne S Kallerud1, Patrick Marques-Smith1, Helle K Bendiksen2
1Department of Companion Animal Clinical Sciences, Norwegian University of Life Sciences, Aas, Norway.
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.
