Exploring of a novel monitoring tool for injury risk when sidestepping: Using unsupervised learning to characterize movement patterns

Abstract

AbstractThe monitoring of athletes is crucial to prevent injuries, identify fatigue or support return-to-play decisions. The purpose of this study was to explore the ability of Kohonen neural network self-organizing maps (SOM) to objectively visualize and characterize different movement patterns during sidestepping and to detect those patterns that are associated with signs of injury risk or fatigue. The marker trajectories of 631 pre-planned sidestepping trials were used to train a SOM. Out of 61913 input vectors, the SOM identified 1250 unique body postures, determined by the 3D marker positions. Visualizing the movement trajectories and adding the latent parameter time, allows for the investigation of different movement patterns. Additionally, the SOM can be used to identify zones with increased injury risk, by adding more latent parameters more directly linked to injuries which opens the option to monitor athletes and give feedback. The results highlight the ability of unsupervised learning to visualize movement patterns and to give further insight into an individual athlete’s status without the necessity to reduce the complexity of the data describing the movement.