Equine Movement Analysis and Lameness Assessment

Equine movement analysis and lameness assessment have evolved from purely observational methods to sophisticated, quantitative approaches that combine biomechanical measurement, sensor technology and computational modelling. Accurate appraisal of gait asymmetries and weight-bearing irregularities is vital for early detection of musculoskeletal injury, optimisation of rehabilitation protocols and enhancement of performance. Wearable sensors, high-speed cameras and pressure platforms yield detailed kinematic and kinetic data, while emerging machine-learning algorithms enable prediction of ground reaction forces and automated classification of movement deviations. Thermal imaging and neurophysiological techniques further enrich the diagnostic repertoire, revealing changes in blood flow or neuronal function associated with pain or neurological disorders. These developments have global significance, improving welfare standards in sport, leisure and working horse populations by providing objective criteria for treatment decisions and return-to-work assessments.

Research from Nature Portfolio

Recent studies have demonstrated that body-mounted inertial sensors, when coupled with long short-term memory recurrent neural networks, can accurately predict vertical ground reaction force curves in walking and trotting horses. By integrating data from multiple sensor locations on both the upper body and limbs, the models achieve prediction errors below 0.40 N·kg⁻¹ and reliably estimate peak force values. This approach offers a practical alternative to stationary force-measuring treadmills or plates, paving the way for clinical tools that monitor weight-bearing lameness in field conditions. The inclusion of upper-body kinematics alongside limb data was shown to be critical for robust force predictions across different gaits and speeds, underscoring the value of holistic motion capture in equine biomechanics.

Equine Movement Analysis and Lameness Assessment publication trend

The graph below shows the total number of articles in equine movement analysis and lameness assessment across all publications each year (not limited to Nature Index journals).

Technical terms

Inertial measurement unit (IMU): A wearable sensor that records acceleration and angular velocity to capture kinematic data in three dimensions.

Ground reaction force (GRF): The force exerted by the ground on the hoof during stance, reflecting weight-bearing and loading patterns.

Long short-term memory recurrent neural network (LSTM-RNN): A class of machine-learning model capable of learning temporal dependencies to predict sequential data such as force curves.

Thermography: An imaging technique that maps surface temperature distributions, used to identify areas of altered blood flow or inflammation.

References

1. Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks. Scientific Reports (2023).
2. Horse movement analyze with MEMS sensors and 2D visualization of measurement data. Sensors and Actuators A Physical (2024).
3. Inertial Sensor Technologies—Their Role in Equine Gait Analysis, a Review. Sensors (2023).
4. Evaluation of Thermal Changes of the Sole Surface in Horses with Palmar Foot Pain: A Pilot Study. Biology (2023).
5. Evaluation of the diagnostic value of transcranial electrical stimulation (TES) to assess neuronal functional integrity in horses. Frontiers in Neuroscience (2024).