Predicting Musculoskeletal Loading at Common Running Injury Locations Using Machine Learning and Instrumented Insoles.

Abstract

Wearables have the potential to provide accurate estimates of tissue loads at common running injury locations. Here we investigate the accuracy by which commercially available instrumented insoles (ARION; ATO-GEAR, Eindhoven, The Netherlands) can predict musculoskeletal loading at common running injury locations. Nineteen runners (10 males) ran at five different speeds, four slopes, with different step frequencies, and forward trunk lean on an instrumented treadmill while wearing instrumented insoles. The insole data were used as input to an artificial neural network that was trained to predict the Achilles tendon strain, and tibia and patellofemoral stress impulses and weighted impulses (damage proxy) as determined with musculoskeletal modeling. Accuracy was investigated using leave-one-out cross-validation and correlations. The effect of different input metrics was also assessed. The neural network predicted tissue loading with overall relative percentage errors of 1.95 ± 8.40%, -7.37 ± 6.41%, and -12.8 ± 9.44% for the patellofemoral joint, tibia, and Achilles tendon impulse, respectively. The accuracy significantly changed with altered running speed, slope, or step frequency. Mean (95% confidence interval) within-individual correlations between modeled and predicted impulses across conditions were generally nearly perfect, being 0.92 (0.89 to 0.94), 0.95 (0.93 to 0.96), and 0.95 (0.94 to 0.96) for the patellofemoral, tibial, and Achilles tendon stress/strain impulses, respectively. This study shows that commercially available instrumented insoles can predict loading at common running injury locations with variable absolute but (very) high relative accuracy. The absolute error was lower than the methods that measure only the step count or assume a constant load per speed or slope. This developed model may allow for quantification of in-field tissue loading and real-time tissue loading-based feedback to reduce injury risk.