Categories
Publication

Research Summary: Unsupervised Clustering Techniques Identify Movement Strategies in the Countermovement Jump Associated with Musculoskeletal Injury Risk during US Marine Corps Officer Candidates School

Bird MB, Mi Q, Koltun KJ, Lovalekar M, Martin BJ, Fain A, Bannister A, Vera Cruz A, Doyle TLA and Nindl BC (2022) Unsupervised Clustering Techniques Identify Movement Strategies in the Countermovement Jump Associated with Musculoskeletal Injury Risk During US Marine Corps Officer Candidates School. Front. Physiol. 13:868002. https://doi.org/10.3389/fphys.2022.868002

Key takeaways:

  • Countermovement jump data can be used to predict risk of musculoskeletal injuries in military trainees
  • More efficient CMJ movement strategies, characterized by greater kinetics and lower/shorter kinematics, were found to be associated with lower MSKI risk in this population 
  • Clustering methods were found to outperform linear approaches for modeling the effect of movement strategies on MSKI risk due to the complex interactions between kinetic and kinematic variables

“These results provide actionable thresholds of key performance indicators for practitioners to use for screening measures in classifying greater MSKI risk. These tools may add value in creating modifiable strength and conditioning training programs before or during military training.”

Population: 668 Marine officer candidates (MOCs) enrolled in Officer Candidates School, a 10-week initial military training course

Summary

The questions covered:

  • Do unsupervised clustering methods run on countermovement jump (CMJ) variables classify musculoskeletal injury risk?
  • How do the CMJ variables describe the movement strategies within the clusters?
  • Do movement strategies associate with hip, knee, and ankle MSKI risk?

This study used markerless motion capture and force plate technologies to assess countermovement jump in 547 male and 121 female MOCs prior to beginning the Officer Candidates School training program. An unsupervised machine learning approach (k-means clustering) used on CMJ variables identified three distinct clusters of MOCs on the basis of distinct movement strategies while performing the countermovement jump. These clusters were then evaluated in terms of their component kinetic and kinematic CMJ variables, MOC demographics, and MSKI injuries sustained.

Upon assessment of MSKI injury data from the full 10-week training period, it was demonstrated that the three clusters described low-risk, moderate-risk, and high-risk trainee subgroups, of which 13.8%, 22.5%, and 30.5% experienced lower extremity or torso MSKIs, respectively. Analysis of specific joint MSKIs found no association between knee or hip injuries and cluster assignment, while ankle MSKIs were significantly more prevalent in the high-risk cluster than the low- or moderate-risk clusters. Evaluation of the component biomechanical variables indicated that greater kinetic values and lower or shorter kinematic values in the CMJ were associated with lower risk of MSKI. Additionally, female MOCs made up approximately 41% of the high-risk cluster, but only ~4% of the low- and moderate-risk clusters, while male MOCs were evenly distributed across all three clusters.

The results of this study indicate that movement strategies, as described using clusters identified via machine learning methods, are relevant to MSKI risk stratification in military trainee populations. The descriptions of the clusters and their MOCs suggest potential thresholds for injury risk prediction and targeted training opportunities.

Abstract

Musculoskeletal injuries (MSKI) are a significant burden on the military healthcare system. Movement strategies, genetics, and fitness level have been identified as potential contributors to MSKI risk. Screening measures associated with MSKI risk are emerging, including novel technologies, such as markerless motion capture (mMoCap) and force plates (FP) and allow for field expedient measures in dynamic military settings. The aim of the current study was to evaluate movement strategies (i.e., describe variables) of the countermovement jump (CMJ) in Marine officer candidates (MOCs) via mMoCap and FP technology by clustering variables to create distinct movement strategies associated

with MSKI sustained during Officer Candidates School (OCS). 728 MOCs were tested and 668 MOCs (Male MOCs = 547, Female MOCs = 121) were used for analysis. MOCs performed 3 maximal CMJs in a mMoCap space with FP embedded into the system. Deidentified MSKI data was acquired from internal OCS reports for those who presented to the OCS Physical Therapy department for MSKI treatment during the 10 weeks of OCS training. Three distinct clusters were formed with variables relating to CMJ kinetics and kinematics from the mMoCap and FPs. Proportions of MOCs with a lower extremity and torso MSKI across clusters were significantly different (p < 0.001), with the high-risk cluster having the highest proportions (30.5%), followed by moderate-risk cluster (22.5%) and low-risk cluster (13.8%). Kinetics, including braking rate of force development (BRFD), braking net impulse and propulsive net impulse, were higher in low-risk cluster compared to the high-risk cluster (p < 0.001). Lesser degrees of flexion and shorter CMJ phase durations (braking phase and propulsive phase) were observed in low-risk cluster compared to both moderate-risk and high-risk clusters. Male MOCs were distributed equally across clusters while female MOCs were primarily distributed in the high-risk cluster. Movement strategies (i.e., clusters), as quantified by mMoCap and FPs, were successfully described with MOCs MSKI risk proportions between clusters. These results provide actionable thresholds of key performance indicators for practitioners to use for screening measures in classifying greater MSKI risk. These tools may add value in creating modifiable strength and conditioning training programs before or during military training.