Certain homogeneous running subgroups demonstrate distinct kinematic patterns in running; however, the running mechanics of competitive and recreational runners are not well understood. Therefore, the purpose of this study was to determine whether we could separate and classify competitive and recreational runners according to gait kinematics using multivariate analyses and a machine learning approach. Participants were allocated to the ‘competitive’ (n = 20) or ‘recreational’ group (n = 15) based on age, sex, and recent race performance. Three-dimensional (3D) kinematic data were collected during treadmill running at 2.7 m/s. A support vector machine (SVM) was used to determine if the groups were separable and classifiable based on kinematic time point variables as well as principal component (PC) scores. A cross-fold classification accuracy of 80% was found between groups using the top 5 ranked time point variables, and the groups could be separated with 100% cross-fold classification accuracy using the top 14 ranked PCs explaining 60.29% of the variance in the data. The features were primarily related to pelvic tilt, as well as knee flexion and ankle eversion in late stance. These results suggest that competitive and recreational runners have distinct, ‘typical’ running patterns that may help explain differences in injury mechanisms.
Christian A. Clermont, Sean T. Osis, Angkoon Phinyomark and Reed Ferber
Christian A. Clermont, Lauren C. Benson, W. Brent Edwards, Blayne A. Hettinga and Reed Ferber
The purpose of this study was to use wearable technology data to quantify alterations in subject-specific running patterns throughout a marathon race and to determine if runners could be clustered into subgroups based on similar trends in running gait alterations throughout the marathon. Using a wearable sensor, data were collected for cadence, braking, bounce, pelvic rotation, pelvic drop, and ground contact time for 27 runners. A composite index was calculated based on the “typical” data (4–14 km) for each runner and evaluated for 14 individual 2-km sections thereafter to detect “atypical” data (ie, higher indices). A cluster analysis assigned all runners to a subgroup based on similar trends in running alterations. Results indicated that the indices became significantly higher starting at 20 to 22 km. Cluster 1 exhibited lower indices than cluster 2 throughout the marathon, and the only significant difference in characteristics between clusters was that cluster 1 had a lower age–grade performance score than cluster 2. In summary, this study presented a novel method to investigate the effects of fatigue on running biomechanics using wearable technology in a real-world setting. Recreational runners with higher age–grade performance scores had less atypical running patterns throughout the marathon compared with runners with lower age–grade performance scores.