A new deep learning-based method for the detection of gait events in children with gait disorders: Proof-of-concept and concurrent validity

• Published in: Journal of biomechanics Vol. 98; p. 109490
• Main Authors: Lempereur, Mathieu, Rousseau, François, Rémy-Néris, Olivier, Pons, Christelle, Houx, Laetitia, Quellec, Gwenolé, Brochard, Sylvain
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 02.01.2020; Elsevier Limited; Elsevier
• Subjects: Acceleration; Accuracy; Algorithms; Biomechanics; Cerebral palsy; Children; Deep learning; Engineering Sciences; Feet; Force plates; Gait; Heels; Heuristic methods; Kinematics; Literature reviews; Long short-term memory; Machine learning; Markers; Neural networks; Neuromuscular diseases; Problem solving; Recurrent neural network; Recurrent neural networks; Sensitivity analysis; Three dimensional motion; Toe; Velocity; Deep learning; Children; Gait; Recurrent neural network
• ISSN: 0021-9290; 1873-2380; 1873-2380
• DOI: 10.1016/j.jbiomech.2019.109490

The stance and swing phases of the gait cycle are defined by foot strike (FS) and foot off (FO). Accurate determination of these events is thus an essential component of 3D motion recordings processing. Several methods have been developed for the automatic detection of these events (based on the heuristics of 3D marker position, velocity and acceleration), however the results may be inaccurate due to the high variability that is intrinsic to pathological gait. For this reason, gait events are still commonly determined manually, which is a tedious process. Here we propose a new application (DeepEvent) of a long short term memory recurrent neural network for the automatic detection of gait events. The 3D position and velocity of the markers on the heel, toe and lateral malleolus were used by the network to determine FS and FO. The method was developed from 10526 FS and 9375 FO from 226 children. DeepEvent predicted FS within 5.5 ms and FO within 10.7 ms of the gold standard (automatic determination using force platform data) and was more accurate than common heuristic marker trajectory-based methods proposed in the literature and another deep learning method. A sensitivity analysis showed that DeepEvent mainly used the toe and heel markers (z-axis (longitudinal) position and velocity) at the beginning and end of gait cycle to predict FS, and the toe marker (x-axis (anterior/posterior) velocity and z-axis position and velocity) at around 60% of the gait cycle to predict FO.