Gait Analysis of Hemiparetic Adult Patients with a Quadripod Cane and a Rolling Cane.

Stroke consequences include hemiparesis and difficulty walking. Several types of canes exist to overcome these alterations, but little data compares the quadripod cane and the rolling cane in hemiparetic patients. The objective of this work is twofold: to determine whether the gait speed-the most often used parameter to assess gait performance-depends on the type of cane, and to establish which spatiotemporal parameters have the most influence. Thirty-four hemiparetic patients performed 10 m walking tests at comfortable and fast speed conditions, using both canes on two different days. To objectively analyze their gait patterns, we used a tri-axial Inertial Measurement Units (IMU)-based system to record the walking signals from which we extracted the gait spatiotemporal parameters. We particularly examined the speed, stride length, and durations of stance, swing, and double support phases. The results showed that hemiparetic patients walked faster with the rolling cane during both speed conditions. These speed increases could be explained by the decrease in the stance phase duration of the affected leg, the decrease in the double support duration, and the increase in cadence. Our findings suggest that the rolling cane allows safe and faster walking.

Optimizing the performance of convolutional neural network for enhanced gesture recognition using sEMG.

Deep neural networks (DNNs) have demonstrated higher performance results when compared to traditional approaches for implementing robust myoelectric control (MEC) systems. However, the delay induced by optimising a MEC remains a concern for real-time applications. As a result, an optimised DNN architecture based on fine-tuned hyperparameters is required. This study investigates the optimal configuration of convolutional neural network (CNN)-based MEC by proposing an effective data segmentation technique and a generalised set of hyperparameters. Firstly, two segmentation strategies (disjoint and overlap) and various segment and overlap sizes were studied to optimise segmentation parameters. Secondly, to address the challenge of optimising the hyperparameters of a DNN-based MEC system, the problem has been abstracted as an optimisation problem, and Bayesian optimisation has been used to solve it. From 20 healthy people, ten surface electromyography (sEMG) grasping movements abstracted from daily life were chosen as the target gesture set. With an ideal segment size of 200 ms and an overlap size of 80%, the results show that the overlap segmentation technique outperforms the disjoint segmentation technique (p-value < 0.05). In comparison to manual (12.76 ± 4.66), grid (0.10 ± 0.03), and random (0.12 ± 0.05) search hyperparameters optimisation strategies, the proposed optimisation technique resulted in a mean classification error rate (CER) of 0.08 ± 0.03 across all subjects. In addition, a generalised CNN architecture with an optimal set of hyperparameters is proposed. When tested separately on all individuals, the single generalised CNN architecture produced an overall CER of 0.09 ± 0.03. This study's significance lies in its contribution to the field of EMG signal processing by demonstrating the superiority of the overlap segmentation technique, optimizing CNN hyperparameters through Bayesian optimization, and offering practical insights for improving prosthetic control and human-computer interfaces.

Using supervised learning machine algorithm to identify future fallers based on gait patterns: A two-year longitudinal study.

INTRODUCTION: Given their major health consequences in the elderly, identifying people at risk of fall is a major challenge faced by clinicians. A lot of studies have confirmed the relationships between gait parameters and falls incidence. However, accurate tools to predict individual risk among independent older adults without a history of falls are lacking. OBJECTIVE: This study aimed to apply a supervised learning algorithm to a data set recorded in a two-year longitudinal study, in order to build a classification tree that could discern subsequent fallers based on their gait patterns. METHODS: A total of 105 adults aged >65 years, living independently at home and without a recent fall history were included in a two-year longitudinal study. All underwent physical and functional assessment. Gait speed, stride length, frequency, symmetry and regularity, and minimum toe clearance were recorded in comfortable, fast and dual task walking conditions in a standardized laboratory environment. Fall events were recorded using personal falls diaries. A supervised machine learning algorithm (J48) has been applied to the data recorded at inclusion in order to obtain a classification tree able to identify future fallers. RESULTS: Based on fall information from 96 volunteers, a classification tree correctly identifying 80% of future fallers based on gait patterns, gender, and stiffness, was obtained, with accuracy of 84%, sensitivity of 80%, specificity of 87%, a positive predictive value of 78%, and a negative predictive value of 88%. DISCUSSION: While the performances of the classification tree warrant further confirmation, it is the first predictive tool based on gait parameters that are identified (not clustered) allowing its use by other research teams. CONCLUSION: This original longitudinal pilot study using a supervised machine learning algorithm, shows that gait parameters and clinical data can be used to identify future fallers among independent older adults.

Gait symmetry in the dual task condition as a predictor of future falls among independent older adults: a 2-year longitudinal study.

BACKGROUND: Given the potential consequences of falls among older adults, a major challenge is to identify people at risk before the first event. In this context, gait parameters have been suggested as markers of fall risk. AIM: To examine, among older people, the prospective relationship between gait patterns assessed in comfortable and challenging walking conditions, and future fall(s). METHOD: A total of 105 adults older than 65 years, living independently at home and without a recent fall history were included in a 2-year, longitudinal, observational study. All underwent physical and functional assessment. Gait speed, stride length, frequency, symmetry and regularity and Minimum Toe Clearance (MTC) were recorded in comfortable (CW), fast (FW) and dual task walking (DTW) conditions. Gait parameter changes occurring between CW and FW and between CW and DTW were calculated and expressed in percent. DTW cost was calculated as the change of DTW relative to CW. Fall events were recorded using fall diaries. Comparisons according to fall occurrence were performed by means of univariate analysis and multivariate binary logistic regression analysis. RESULTS: Two-year follow-up was available for 96 participants, of whom 35 (36.5%) fell at least once. Comparative analysis showed that future fallers had shorter FW stride length and higher symmetry DTW cost than non-fallers (p < 0.05). Binary logistic regression analysis showed that each additional percent of stride symmetry cost was associated with an increase in future fall risk (odds ratio 1.018, 95% Confidence Interval (CI) 1.002-1.033; p = 0.027). DISCUSSION: Our results confirm the association between a symmetry decrease in DTW and future fall(s). Indeed in this study, the mean symmetry DTW cost in fallers is almost 20% higher than in non-fallers, meaning a fall risk that is around 36% higher than among non-fallers. CONCLUSION: This exploratory study shows the usefulness of considering gait parameters, particularly symmetry in challenging walking conditions, for early identification of future fallers.

Does negative information about aging influence older adults' physical performance and subjective age?

This study investigated the way negative stereotypes influence older adults' physical performance and how old they feel mentally and physically. Sixty-four older adults aged 65 years and older performed different physical tasks using a 3D optoelectronic system under a low or high stereotype threat condition. Self-perceptions of aging were considered as a moderator of the effects of threat. Overall, the effects of threat on physical performance were mostly not significant across tasks. However, threat condition influenced older adults' mental subjective age after they had performed the physical tests; people in the high-threat condition felt closer to their chronological age. Threat also influenced participants' physical subjective age, and this effect was moderated by self-perceptions of aging. More precisely, participants in the high-threat condition felt 7% physically older than their chronological age when they had more negative self-perceptions, while participants in the low-threat condition felt 13% younger. No differences emerged for participants who had more positive self-perceptions. The present findings suggest that performing physical tests under stereotype threat might worsen older people's subjective experience of their own aging by making them feel older.

Contribution of a Trunk Accelerometer System to the Characterization of Gait in Patients With Mild-to-Moderate Parkinson's Disease.

OBJECTIVE: Gait disturbances like shuffling and short steps are obvious at visual observation in patients with advanced Parkinson's disease (PD). However, quantitative methods are increasingly used to evaluate the wide range of gait abnormalities that may occur over the disease course. The goal of this study was to test the ability of a trunk accelerometer system to quantify the effects of PD on several gait features when walking at self-selected speed. METHODS: We recruited 96 subjects split into three age-matched groups: 32 healthy controls (HC), 32 PD patients at Hoehn and Yahr stage < II (PD-1), and 32 patients at Hoehn and Yahr stage II-III (PD-2). The following outcomes were extracted from the signals of the triaxial accelerometer worn on the lower back: stride length, cadence, regularity index, symmetry index, and mechanical powers yielded in the cranial-caudal, anteroposterior, and medial-lateral directions. Walking speed was measured using a stopwatch. RESULTS: Besides other gait features, the PD-1 and the PD-2 groups showed significantly reduced stride length normalized to height (p < 0.02) and symmetry index (p < 0.009) in comparison to the HC. Regularity index was the only feature significantly decreased in the PD-2 group as compared with the two other groups (p < 0.01). The clinical relevance of this finding was supported by significant correlations with mobility and gait scales (r is around -0.3; p < 0.05). CONCLUSION: Gait quantified by a trunk accelerometer may provide clinically useful information for the screening and follow-up of PD patients.

Development and validation of an accelerometer-based method for quantifying gait events.

An original signal processing algorithm is presented to automatically extract, on a stride-by-stride basis, four consecutive fundamental events of walking, heel strike (HS), toe strike (TS), heel-off (HO), and toe-off (TO), from wireless accelerometers applied to the right and left foot. First, the signals recorded from heel and toe three-axis accelerometers are segmented providing heel and toe flat phases. Then, the four gait events are defined from these flat phases. The accelerometer-based event identification was validated in seven healthy volunteers and a total of 247 trials against reference data provided by a force plate, a kinematic 3D analysis system, and video camera. HS, TS, HO, and TO were detected with a temporal accuracy ± precision of 1.3 ms ± 7.2 ms, -4.2 ms ± 10.9 ms, -3.7 ms ± 14.5 ms, and -1.8 ms ± 11.8 ms, respectively, with the associated 95% confidence intervals ranging from -6.3 ms to 2.2 ms. It is concluded that the developed accelerometer-based method can accurately and precisely detect HS, TS, HO, and TO, and could thus be used for the ambulatory monitoring of gait features computed from these events when measured concurrently in both feet.

A Perturbation Method for the 3D Finite Element Modeling of Electrostatically Driven MEMS.

In this paper, a finite element (FE) procedure for modeling electrostatically actu-ated MEMS is presented. It concerns a perturbation method for computing electrostatic fielddistortions due to moving conductors. The computation is split in two steps. First, an un-perturbed problem (in the absence of certain conductors) is solved with the conventional FEmethod in the complete domain. Second, a perturbation problem is solved in a reduced re-gion with an additional conductor using the solution of the unperturbed problem as a source.When the perturbing region is close to the original source field, an iterative computation maybe required. The developed procedure offers the advantage of solving sub-problems in re-duced domains and consequently of benefiting from different problem-adapted meshes. Thisapproach allows for computational efficiency by decreasing the size of the problem.