Bridging the Gap Between AI and Reality • Rhodes, Greece
Time: Wednesday, 5.11
Room: Room C
Authors: Stephen Ryan
Abstract: The biomechanical optimisation of equine performance, particularly in competitive racing, is often constrained by limited access to high-resolution gait data and the complexity of integrating multi-sensor measurements such as stride length, limb kinematics, and ground reaction forces. Traditional modelling approaches require extensive coding expertise, manual configuration, and iterative visualisation, creating barriers for trainers, veterinarians, and sports scientists who lack programming backgrounds. This research introduces a Low-Code/No-Code (LC/NC) modelling framework designed to democratise data-driven insights in equine biomechanics. By automating data ingestion, interpolation, and analysis workflows, the platform enables domain experts to systematically explore stride dynamics, detect performance-limiting asymmetries, and optimise training regimes with minimal technical overhead. Preliminary evaluations suggest that this approach accelerates hypothesis refinement, improves reproducibility in gait analysis, and offers a scalable pathway for integrating biomechanical modelling into the equine racing industry. Beyond performance monitoring, this work highlights the potential of LC/NC paradigms to transform veterinary care, injury prevention, and evidence-based decision-making in high-stakes animal sports.