Date Published: January 31, 2019
Publisher: Public Library of Science
Author(s): Łukasz Kidziński, Scott Delp, Michael Schwartz, Manoj Srinivasan.
Annotation of foot-contact and foot-off events is the initial step in post-processing for most quantitative gait analysis workflows. If clean force plate strikes are present, the events can be automatically detected. Otherwise, annotation of gait events is performed manually, since reliable automatic tools are not available. Automatic annotation methods have been proposed for normal gait, but are usually based on heuristics of the coordinates and velocities of motion capture markers placed on the feet. These heuristics do not generalize to pathological gait due to greater variability in kinematics and anatomy of patients, as well as the presence of assistive devices. In this paper, we use a data-driven approach to predict foot-contact and foot-off events from kinematic and marker time series in children with normal and pathological gait. Through analysis of 9092 gait cycle measurements we build a predictive model using Long Short-Term Memory (LSTM) artificial neural networks. The best-performing model identifies foot-contact and foot-off events with an average error of 10 and 13 milliseconds respectively, outperforming popular heuristic-based approaches. We conclude that the accuracy of our approach is sufficient for most clinical and research applications in the pediatric population. Moreover, the LSTM architecture enables real-time predictions, enabling applications for real-time control of active assistive devices, orthoses, or prostheses. We provide the model, usage examples, and the training code in an open-source package.
One of the key elements in analysis of gait is the quantitative assessment of gait parameters collected in a reproducible setting. Modern gait laboratories are equipped with motion capture systems that allow experimenters to track trajectories of markers positioned on a subject’s body. After collecting such data, experimenters fit a musculoskeletal model with associated markers and reconstruct body movement. This procedure allows computation of joint angles over time using inverse kinematics. These data are used in a variety of applications, ranging from basic scientific studies about the nature of human movement to clinical assessments used for planning treatments and assessing outcomes.
Our comparisons show a substantial advantage of our method over the two selected heuristic-based algorithms. Both coordinate-based and velocity-based methods fail to detect any events in between 7% and 16% of cases. In contrast, our algorithm fails to detect foot contact in less than 1% cases and foot-off in less than 5% cases. Manual investigation of these cases did not reveal any clear pattern distinguishing these cases.
We combined three approaches to detect gait events: velocity-based, coordinate-based, and our machine learning approach derived from combining kinematic characteristics. We built a neural network leveraging a large dataset of the kinematics of children with cerebral palsy. Results indicate that the new model is superior to the heuristic-based models.