An Advanced Attention-Enhanced Hybrid Deep Learning Model for WBSNs’ Gait Pattern Recognition

Background: The deep learning techniques have been attracted increasing attention on wireless body sensor networks (WBSNs) gait pattern recognition that has a great contribution to monitoring gait change in clinical application. However, in existing studies, there are some challenging issues such as low generalization performance and no potential interpretation for gait variability. It is necessary to search for the advanced deep learning models to resolve these issues. Method: A public WARD database including acceleration and gyroscope data acquired from each subject wearing five sensors was selected, and the gait with different combination of on-body multi-sensors is considered as a WBSNs’ gait pattern. An advanced attention-enhanced hybrid deep learning model of DCNN and LSTM for WBSNs’ gait pattern recognition was proposed. In our proposed technique, the combination model of DCNN with LSTM is firstly to discover the spatial-temporary gait correlation features. And then the attention mechanism is introduced to exploit the more valuable intrinsic nonlinear dynamic correlation gait characteristics associated with gait variability hidden in spatial-temporary gait space obtained. This significantly contributes to enhancing the generalization performance and taking insight on gait variability in a certain anatomical region. Results: The ten gait patterns are randomly selected from WARD database to evaluate the feasibility of our proposed method. Our experiments demonstrated the superior generalization ability of our method to some models such as CNN-LSTM, DCNN-LSTM. Our proposed model could classify ten gait patterns with the highest accuracy and F1-score of 91.48% and 91.46%, respectively. Moreover, we also found that the classification performance of a certain gait pattern was almost same best when the combinations of three or five on-body sensors were employed respectively, suggesting that our method possibly take insight on gait variability in a certain anatomical region. Conclusion: Our proposed technique could feasibly discover the more intrinsic nonlinear dynamic correlation gait characteristics associated with gait variability from on-body multi-sensors gait data, which greatly contributed to best generalization performance and potential clinical interpretation. Our proposed technique would hopefully become a powerful tool of monitoring gait change in clinical application.

Comparison of Shod and Unshod Gait in Patients With Parkinson's Disease With Subthalamic and Nigral Stimulation

Background: The Parkinsonian [i.e., Parkinson's disease (PD)] gait disorder represents a therapeutical challenge with residual symptoms despite the use of deep brain stimulation of the subthalamic nucleus (STN DBS) and medical and rehabilitative strategies. The aim of this study was to assess the effect of different DBS modes as combined stimulation of the STN and substantia nigra (STN+SN DBS) and environmental rehabilitative factors as footwear on gait kinematics.Methods: This single-center, randomized, double-blind, crossover clinical trial assessed shod and unshod gait in patients with PD with medication in different DBS conditions (i.e., STIM OFF, STN DBS, and STN+SN DBS) during different gait tasks (i.e., normal gait, fast gait, and gait during dual task) and compared gait characteristics to healthy controls. Notably, 15 patients participated in the study, and 11 patients were analyzed after a dropout of four patients due to DBS-induced side effects.Results: Gait was modulated by both factors, namely, footwear and DBS mode, in patients with PD. Footwear impacted gait characteristics in patients with PD similarly to controls with longer step length, lower cadence, and shorter single-support time. Interestingly, DBS exerted specific effects depending on gait tasks with increased cognitive load. STN+SN DBS was the most efficient DBS mode compared to STIM OFF and STN DBS with intense effects as step length increment during dual task.Conclusion: The PD gait disorder is a multifactorial symptom, impacted by environmental factors as footwear and modulated by DBS. DBS effects on gait were specific depending on the gait task, with the most obvious effects with STN+SN DBS during gait with increased cognitive load.

Insole-Based Systems for Health Monitoring: Current Solutions and Research Challenges

Wearable health monitoring devices allow for measuring physiological parameters without restricting individuals’ daily activities, providing information that is reflective of an individual’s health and well-being. However, these systems need to be accurate, power-efficient, unobtrusive and simple to use to enable a reliable, convenient, automatic and ubiquitous means of long-term health monitoring. One such system can be embedded in an insole to obtain physiological data from the plantar aspect of the foot that can be analyzed to gain insight into an individual’s health. This manuscript provides a comprehensive review of insole-based sensor systems that measure a variety of parameters useful for overall health monitoring, with a focus on insole-based PPD measurement systems developed in recent years. Existing solutions are reviewed, and several open issues are presented and discussed. The concept of a fully integrated insole-based health monitoring system and considerations for future work are described. By developing a system that is capable of measuring parameters such as PPD, gait characteristics, foot temperature and heart rate, a holistic understanding of an individual’s health and well-being can be obtained without interrupting day-to-day activities. The proposed device can have a multitude of applications, such as for pathology detection, tracking medical conditions and analyzing gait characteristics.

Ankle-Injury Patients Perform More Microadjustments during Walking: Evidence from Velocity Profiles in Gait Analysis

Introduction. We evaluated the velocity profiles of patients with lateral collateral ligament (LCL) injuries of the ankle with a goal of understanding the control mechanism involved in walking. Methods. We tracked motions of patients’ legs and feet in 30 gait cycles recorded from patients with LCL injuries of the ankle and compared them to 50 gait cycles taken from normal control subjects. Seventeen markers were placed on the foot following the Heidelberg foot measurement model. Velocity profiles and microadjustments of the knee, ankle, and foot were calculated during different gait phases and compared between the patient and control groups. Results. Patients had a smaller first rocker percentage and larger second rocker percentage in the gait cycle compared to controls. Patients also displayed shorter stride length and slower strides and performed more microadjustments in the second rocker phase than in other rocker/swing phases. Patients’ mean velocities of the knee, ankle, and foot in the second rocker phase were also significantly higher than that in control subjects. Discussion. Evidence from velocity profiles suggested that patients with ligament injury necessitated more musculoskeletal microadjustments to maintain body balance, but these may also be due to secondary injury. Precise descriptions of the spatiotemporal gait characteristics are therefore crucial for our understanding of movement control during locomotion.

Dual task walking in healthy aging: Effects of narrow and wide walking paths

Dual-task walking may lead to gait instability and a higher fall risk in older adults, particularly when walking in a busy city street. Challenging street features such as narrow sidewalks not only discourage walking, but are also likely to be taxing for older adults’ cognitive resources and gait characteristics. The aim of this study was to assess the way older adults’ gait characteristics are affected by walking on a narrow path while performing a challenging cognitive task in lab conditions imitating common urban environments. Nineteen young and eighteen older adults walked on a narrow (40cm) and a wide (80cm) path and performed a cognitive (n-back) task individually adjusted to 80% accuracy. The two tasks were performed separately (Single-Task) and concurrently (Dual-Task). Both groups walked faster, and their step width was narrower on the narrow path. During dual-task walking on the narrow path, older adults showed significant dual-task costs in the cognitive task, gait speed, step width, and stride length. Dual-task walking was associated with decreased gait speed and stride length in both age groups, suggesting that dual-task walking may adversely affect gait, particularly when walking on narrow paths. These conditions may lead to gait instability and an increased fall risk for older adults, particularly when walking along the narrow sidewalks commonly found within the built environment. However, more research is needed in an urban setting to determine the extent of the fall risk narrow sidewalks present for older adults.

Longitudinal Changes in Temporospatial Gait Characteristics during the First Year Post-Stroke

Given the paucity of longitudinal data in gait recovery after stroke, we compared temporospatial gait characteristics of stroke patients during subacute (<2 months post-onset, T0) and at approximately 6 and 12 months post-onset (T1 and T2, respectively) and explored the relationship between gait characteristics at T0 and the changes in gait speed from T0 to T1. Forty-six participants were assessed at T0 and a subsample of 24 participants at T2. Outcome measures included Fugl-Meyer lower-extremity motor score, 14 temporospatial gait parameters and symmetry indices of 5 step parameters. Except for step width, all temporospatial parameters improved from T0 to T1 (p ≤ 0.0001). Additionally, significant improvements in symmetry were found for the initial double-support time and single-support time (p ≤ 0.0001). Although group results at T2 were not different from those at T1, the individual analysis revealed that 42% (10/24) of the subsample showed a significant increase in gait speed. The increase in gait speed from T0 to T1 was negatively correlated with gait speed and stride length, and positively correlated with the symmetry indices of stance and single-support times at T0 (p ≤ 0.002). Temporospatial gait parameters and stance time symmetry improve over the first 6 months after stroke with an apparent plateau thereafter. Approximately 40% of the subsample continue to increase gait speed from 6 to 12 months post-stroke. A greater increase in gait speed during the first 6 months post-stroke is associated with initially slower walking, shorter stride length, and more pronounced asymmetry in stance and single-support times. The improvement in lower-extremity motor function and bilateral improvements in step parameters collectively suggest that gait changes over the first 12 months after stroke are likely due to neurological recovery, although some compensation by the non-paretic side cannot be excluded.

Gait, physical function, and physical activity in three groups of home-dwelling older adults with different severity of cognitive impairment – a cross-sectional study

Background The research on associations between gait, physical function, physical activity (PA), and cognitive function is growing. Still, clinical assessments of cognitive function and motor function is often kept separate. In this study, we aimed to look at a broad range of measures of gait, physical function, and PA in three groups of home-dwelling older adults with no or questionable dementia, mild dementia, and moderate/severe dementia. Methods This cross-sectional study included 100 home-dwelling older adults, recruited from an outpatient geriatric memory clinic. Severity of dementia was categorised using the clinical dementia rating scale (CDR), with no or questionable dementia (CDR score 0 and 0.5), mild dementia (CDR score 1) and moderate/severe dementia (CDR score 2 and 3). We used thigh worn accelerometers to measure daily PA, the Short Physical Performance Battery (SPPB) to measure physical function, and an electronic gait mat to evaluate gait characteristics. Associations between severity of dementia and measures of PA, physical function, and gait characteristics were assessed by linear regression. Results Participants’ (mean age 78.9 (SD 6.7) years, 57% women) average gait speed was 0.93 m/sec, and average upright time was 301 min/day. Statistically significant associations were found for the severity of dementia and gait speed (p=0.002), step time (p=0.001), physical function (SPPB, p=0.007), and PA (upright time, p=0.031), after adjusting for age. Overall, having no or questionable dementia was associated with faster gait speed (mean difference 0.163 (95% CI: 0.053 to 0.273)), shorter step time (-0.043 (-0.082 to -0.005)), better SPPB score (1.7 (0.5 to 2.8)), and longer upright time (78.9 (18.9 to 139.0)), compared to those with mild dementia. Furthermore, having no or questionable dementia was also associated with faster gait speed and better SPPB scores, as compared to those with moderate to severe dementia. No evidence of any differences was found between the participants with the mild dementia versus the moderate to severe dementia. Conclusions After adjusting for age, we found that the no or questionable dementia group to be associated with better gait and physical function, and more PA, as compared with the two groups with mild or moderate/severe dementia. Evaluation of gait, physical function, and PA can add clinically important information of everyday functioning in memory clinics meeting geriatric patients, but investigations on how to use these results to guide interventions are still needed.