Editorial: Wearable Sensors and Machine Learning in Sports Biomechanics

A central challenge in sports biomechanics has long been to translate precise laboratory-based measurements into meaningful insights for real-world sport performance and injury prevention. Wearable sensors, particularly inertial measurement units, combined with machine learning methods, are central to this transition because they enable the estimation of biomechanical variables outside controlled laboratory environments. This Editorial introduces the Special Issue “Wearable Sensors and Machine Learning in Sports Biomechanics”, which brings together four contributions illustrating the current state and future potential of this rapidly developing field. The articles address key methodological and applied questions: the quantification of whole-body technique in soccer penalty kicks using IMU-based principal component analysis; the detection of psychological and physiological processes through multimodal sensor data and gamification; the estimation of running kinetics in outdoor environments using convolutional neural networks; and a structured overview of current research on field-based biomechanical load assessment across diverse sports. ... mehrCollectively, these contributions demonstrate how wearable sensors and machine learning are becoming important methodological components for studying movement, biomechanical load, and performance in ecologically valid settings. While highlighting substantial advances, the Special Issue also identifies ongoing challenges, including methodological heterogeneity, limited external validation, and the need for explainable and physics-informed approaches. Ultimately, wearable sensors and machine learning can support a new generation of biomechanical tools, but their impact will depend on generating interpretable, valid, and actionable insights in real-world sporting environments.