Personalized Machine Learning Approach to Estimating Knee Kinematics Using Only Shank-Mounted IMU

Knee kinematics is a valuable measure of knee joint function. However, collecting that data outside the clinic is difficult, especially with a limited number of wearable sensors and when you only use an ankle-mounted inertial measurement unit (IMU) to estimate knee kinematics. Due to the cyclic nature of gait, it is possible to use machine learning to extract joint angles from only ankle-mounted sensors. This study aimed to use time-series feature extraction and a random forest regressor to generate a person-specific surrogate model for estimating knee joint flexion angles from a single-mounted IMU above the ankle. Optical motion capture (OMC) and inertial data from ten healthy participants walking on a treadmill were collected to create ten personalized surrogate models for estimating right knee flexion angles during gait. An additional ten models were created for a leave-one-out analysis to test the generalisability of the models. Temporal cross validation of the personalized models and a leave-one-out analysis was performed on the selected feature set. The personalized models achieved an average root-mean-square error (RMSE) of
$2.45^{\circ } \pm {0.65}^{\circ }$
(
${R}^{{2}}$
of 0.98) compared to a gold-standard OMC. The generalized models achieved an average RMSE of
$6.77^{\circ } \pm {3.38}^{\circ }$
(
${R}^{{2}}$
of 0.83) in the leave-one-out analysis. Time-series feature-based personalized surrogate models could be used to accurately estimate knee kinematics by using a single ankle-mounted sensor. However, more data are required to train a generalized model using the presented method.