Abstract

Ground reaction forces are often used by sport scientists and clinicians to analyze the mechanical risk-factors of running related injuries or athletic performance during a running analysis. An interesting ground reaction force-derived variable to track is the maximal vertical instantaneous loading rate (VILR). This impact characteristic is traditionally derived from a fixed force platform, but wearable inertial sensors nowadays might approximate its magnitude while running outside the lab. The time-discrete axial peak tibial acceleration (APTA) has been proposed as a good surrogate that can be measured using wearable accelerometers in the field. This paper explores the hypothesis that applying machine learning to time continuous data (generated from bilateral tri-axial shin mounted accelerometers) would result in a more accurate estimation of the VILR. Therefore, the purpose of this study was to evaluate the performance of accelerometer-based predictions of the VILR with various machine learning models trained on data of 93 rearfoot runners. A subject-dependent gradient boosted regression trees (XGB) model provided the most accurate estimates (mean absolute error: 5.39 ± 2.04 BW⋅s–1, mean absolute percentage error: 6.08%). A similar subject-independent model had a mean absolute error of 12.41 ± 7.90 BW⋅s–1 (mean absolute percentage error: 11.09%). All of our models had a stronger correlation with the VILR than the APTA (p < 0.01), indicating that multiple 3D acceleration features in a learning setting showed the highest accuracy in predicting the lab-based impact loading compared to APTA.

Highlights

  • Ground reaction forces are relevant parameters for running analysis (Pohl et al, 2009; Crowell and Davis, 2011; Van Der Worp et al, 2016; Clark et al, 2017)

  • A commonly used ground reaction force-derived variable is the maximal vertical instantaneous loading rate (VILR), which is calculated as the maximal slope of the rising vertical ground reaction force – time curve (Ueda et al, 2016)

  • Learning Approach We considered two different learning settings, each learned on different subsets of the data (Figure 3): Subject-independent model This setting trained a model using the data from all runners except for one

Read more

Summary

Introduction

Ground reaction forces are relevant parameters for running analysis (Pohl et al, 2009; Crowell and Davis, 2011; Van Der Worp et al, 2016; Clark et al, 2017). VILR has been used to characterize the impact (i.e., high rate of force development due to the rapid deceleration of all body segments during the foot-ground collision) during running (Gerritsen et al, 1995). This measure could discriminate groups of rearfoot runners with a history of stress fractures (Van Der Worp et al, 2016) and plantar fasciitis (Pohl et al, 2009). VILR has been considered clinically relevant and has been a main outcome variable in gait retraining studies targeting runners with high VILR (Crowell and Davis, 2011; Clansey et al, 2014; Willy et al, 2016)

Objectives
Methods
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call