Objective Assessment of Equine Locomotor Symmetry Using an Inertial Sensor System and Artificial Intelligence: A Comparative Study.

This research aimed to compare the accuracy and agreement of two different systems, Inertial Measurement Units (IMUs) and an Artificial Intelligence Marker-less Motion Tracking System (AI-MTS), in assessing equine locomotion symmetry. It was found that the AI-MTS showed greater sensitivity compared to IMUs and there were more instances of asymmetry detected by the former. The effectiveness of these systems was also compared with traditional visual clinical assessment.

Introduction and Aim of the Study

• This research study was aimed at comparing the efficiency and accuracy of an Inertial Measurement Units system (IMUs), an Artificial Intelligence Marker-less Motion Tracking System (AI-MTS), and visual clinical assessment in assessing locomotion symmetry in horses.
• It was noted that the conventional approaches, such as IMUs, although useful, require extensive financial investment and are time-consuming. On the other hand, AI-MTS promises to overcome these limitations.

Methodology

• The study involved twenty horses which underwent locomotion analysis by visual assessment, IMUs, and the AI-MTS system.
• Various conditions under which the horses were assessed include straight hard (SH), straight soft (SS), left and right circle hard (LCH, RCH), and soft (LCS, RCS).

Comparative Analysis

• The results of the research indicated that there was a greater number of horses that were considered sound by clinical examination, as compared to those identified as symmetric by the gait analysis systems – IMUs and AI-MTS.
• The AI-MTS system appeared to be more sensitive since it considered more limbs asymmetric compared to the IMUs system.
• The greatest agreement between the AI-MTS and the IMUs was found for the difference between two ‘minima’ in vertical head position in SH.
• The lowest agreement was for the difference between two ‘minima’ of the vertical pelvis position in SS, which reflects the difficulties in assessing the asymmetry of the hindlimbs.

Conclusion

• One of the major outcomes of this study was that it remains unclear what degree of locomotor asymmetry in horses is clinically relevant. This suggests the need for more consistent use of these systems in training horses to determine a set threshold for asymmetry.
• The research also concludes that some degree of asymmetry may be clinically relevant, advocating for its regular use in training horses.