Estimating range of pelvic motion during gait by using in-shoe motion sensors

Lower back pain is an extremely common health problem. Therefore, accurate, inexpensive, and easy-to-assess technology is needed to assess lower back pain during daily activities. We respectively constructed models for estimating the range of pelvic motion during gait (RoPM) in sagittal, frontal and horizontal planes, by using in-shoe motion sensors as the first step in lower back pain assessment during daily activities, e.g., walking. We successfully collected data from 45 healthy participants to construct the estimation models. We found a correlation between foot motion and RoPM from the late terminal stance phase to initial swing phase. We evaluated our models using the intra-class correlation coefficient (ICC) and determined that the RoPMs on all three planes achieved fair to good ICC agreement. The precision of the RoPMs enables the estimation of 0.58-0.75 xstandard deviation of the true value. The adjusted coefficient of determination suggested that all models achieved large effect size of multilinear regression. We also demonstrated the possibility of monitoring the condition of the pelvis by measuring foot motion.