Human gait-labeling uncertainty and a hybrid model for gait segmentation

Abstract

Motion capture systems are widely accepted as ground-truth for gait analysis and are used for the validation of other gait analysis systems. To date, their reliability and limitations in manual labeling of gait events have not been studied.ObjectivesEvaluate manual labeling uncertainty and introduce a hybrid stride detection and gait-event estimation model for autonomous, long-term, and remote monitoring.MethodsEstimate inter-labeler inconsistencies by computing the limits-of-agreement. Develop a hybrid model based on dynamic time warping and convolutional neural network to identify valid strides and eliminate non-stride data in inertial (walking) data collected by a wearable device. Finally, detect gait events within a valid stride region.ResultsThe limits of inter-labeler agreement for key gait events heel off, toe off, heel strike, and flat foot are 72, 16, 24, and 80 ms, respectively; The hybrid model's classification accuracy for stride and non-stride are 95.16 and 84.48%, respectively; The mean absolute error for detected heel off, toe off, heel strike, and flat foot are 24, 5, 9, and 13 ms, respectively, when compared to the average human labels.ConclusionsThe results show the inherent labeling uncertainty and the limits of human gait labeling of motion capture data; The proposed hybrid-model's performance is comparable to that of human labelers, and it is a valid model to reliably detect strides and estimate the gait events in human gait data.SignificanceThis work establishes the foundation for fully automated human gait analysis systems with performances comparable to human-labelers.

Accuracy, concurrent validity, and test–retest reliability of pressure-based insoles for gait measurement in chronic stroke patients

“…A GoPro Hero 8 camera (GoPro, Inc., San Mateo CA, USA) served as the reference system because, unlike optoelectronic systems, it does not suffer from the uncertainty associated with human gait labeling ( 15 ). The use of manual labeling can lead to inaccuracies due to human error.…”

“…Most metrics for the evaluation of gait performance and quality center around the accurate detection of two main gait events: the foot strike (FS; when the foot first touches the ground), and the foot off (FO; when the foot first leaves the ground) ( 15 ). These events, which are well-established and well-described anchors for the calculation of gait quality features, are also relevant for measures of gait quantity, such as the number of steps ( 16 ).…”