Gait Characteristics Research Articles

Experimental study on mechanical transfer regularity and step distance of individuals under different collision impulse

In the process of emergency evacuation, the fall of an individual may lead to the instability of surrounding pedestrians. The evacuation routes would be obstructed by fallen pedestrians, thereby diminishing the evacuation efficiency and increasing the overall crowd risk. The purpose of this study is to explore the balance-recovery process of pedestrians under collision. The study conducted a series of experiments to obtain the total step distance and number of steps taken by individuals during the balance-recovery process under different impulses. The impulse applied by the unstable individual to the obstacle ahead for balance recovery was also measured. The gait characteristics and mechanical principles of the individuals in the balance-recovery process after collision force were analyzed. The results indicate that individuals can recover balance within a 90 cm step distance if the impulse received is in the range of 20–160 N s. The relationship between the step distance of an individual and the impulse received can be expressed as a quadratic function. When stepping is prohibited, the impulse applied by the individual to the obstacle ahead is approximately 1.85 times the impulse he received. However, if stepping is allowed, the dispersion of the impulse applied to the obstacle gradually decreases with increasing step space. Additionally, logistic regression models were constructed to calculate individual instability probabilities for different conditions based on the experimental data. These results can serve as a foundation method for evaluating the individual and group instability risk during emergency evacuation scenarios.

Association between Elastic Modulus of Foot Soft Tissues and Gait Characteristics in Young Individuals with Flatfoot.

Flatfoot is a common foot deformity, causing foot pain, osteoarthritis of the midfoot, and even knee and hip dysfunction. The elastic modulus of foot soft tissues and its association with gait biomechanics still remain unclear. For this study, we recruited 20 young individuals with flatfoot and 22 age-matched individuals with normal foot arches. The elastic modulus of foot soft tissues (posterior tibial tendon, flexor digitorum brevis, plantar fascia, heel fat pad) was obtained via ultrasound elastography. Gait data were acquired using an optical motion capture system. The association between elastic modulus and gait data was analyzed via correlation analysis. The elastic modulus of the plantar fascia (PF) in individuals with flatfoot was higher than that in individuals with normal foot arches. There was no significant difference in the elastic modulus of the posterior tibial tendon (PTT), the flexor digitorum brevis (FDB), or the heel fat pad (HFD), or the thickness of the PF, PTT, FDB, and HFD. Individuals with flatfoot showed greater motion of the hip and pelvis in the coronal plane, longer double-support phase time, and greater maximum hip adduction moment during walking. The elastic modulus of the PF in individuals with flatfoot was positively correlated with the maximum hip extension angle (r = 0.352, p = 0.033) and the maximum hip adduction moment (r = 0.429, p = 0.039). The plantar fascia is an important plantar structure in flatfoot. The alteration of the plantar fascia's elastic modulus is likely a significant contributing factor to gait abnormalities in people with flatfoot. More attention should be given to the plantar fascia in the young population with flatfoot.

The impact of foot orthoses on gait in children with Osteogenesis Imperfecta type I, III and IV – a cross-sectional study

BackgroundFor children with Osteogenesis Imperfecta (OI), a rare genetic bone disease, walking can be difficult to carry out due to a combination of bone fragility and deformity, muscle weakness, joint hypermobility, and pain. Bisphosphonate treatment has facilitated more children being able to walk, but for many, foot and ankle hypermobility is a limiting factor. Current evidence on foot orthoses in children with OI is sparse. This study aimed to evaluate gait characteristics in children with OI walking barefoot as compared to walking with foot orthoses.MethodsTwenty-three children with OI and hypermobility (mean age 8.3 ± 3.0 years) were included in this cross-sectional study. Children conducted three-dimensional gait analysis barefoot, and with foot orthoses and appropriate foot wear (stable yet light-weight), respectively. Walking speed, step length, lower limb kinematics and kinetics were collected. Differences in gait characteristics between test conditions were evaluated using paired sample t-tests.ResultsWhen walking with foot orthoses, the external foot progression angle was reduced, peak ankle dorsiflexion angle increased, and peak plantarflexion moment increased as compared to barefoot. No difference was found in walking speed between test conditions, however, children with OI walked with longer steps with foot orthoses as compared to barefoot.ConclusionThe observed gait alterations suggest that foot orthoses, aiming to support the foot and ankle joint, contributed to reduced overall foot rotation as measured by external foot progression, increased peak plantarflexion moment, and increased step length. In a wider perspective, the ability to walk provides the opportunity to be physically active, and thereby increase skeletal loading and prevent fractures, thus, foot orthoses may be an important treatment option to consider in children with OI.Level of evidenceIII.

Knee sleeves improve gait symmetry during fast walking in older adults.

Knee sleeves are commonly used to address knee-related concerns, particularly in older individuals. Although previous studies have demonstrated their efficacy in improving gait and functional outcomes in knees with pathological conditions, the effectiveness of knee sleeves for improving gait characteristics in healthy older adults remains unclear. The harmonic ratio (HR), an index for assessing gait symmetry commonly used to discriminate between individuals with different functional levels, can be used to detect alterations in gait characteristics. This study investigated the effects of knee sleeves on gait symmetry in healthy older adults. Sixteen healthy community-dwelling older adults walked barefoot with and without knee sleeves at normal and fast speeds. Gait symmetry indices (HR and improved HR [iHR]) and spatiotemporal gait parameters were compared under different conditions. A significant interaction between knee condition and walking speed was observed for mean iHR in the anteroposterior direction (p = 0.006). A significant simple main effect of knee condition was found during fast walking, with a larger iHR with knee sleeves than without (p = 0.002). In the condition without knee sleeves, the iHR was significantly lower during fast walking than during normal walking (p = 0.035). Furthermore, a significant main effect of knee condition was observed for the variability of iHR in the anteroposterior direction, with a smaller variability when walking with knee sleeves than when walking without (p = 0.006). These results suggest that knee sleeves may enhance gait symmetry along the anteroposterior direction, particularly during fast walking, where symmetry disruption is more likely than walking at a comfortable pace. A significant reduction in gait symmetry variability also suggests a stabilizing effect on gait dynamics. These findings provide the first evidence supporting the efficacy of knee sleeves for improving gait symmetry. The use of knee sleeves could be a valuable option for restoring disrupted gait symmetry during fast walking, with potential implications for reducing the risk of falls.

Automatic Parkinson’s Disease Diagnosis with Wearable Sensor Technology for Medical Robot

The clinical diagnosis of Parkinson’s disease (PD) has been the subject of medical robotics research. Currently, a hot research topic is how to accurately assess the severity of Parkinson’s disease patients and enable medical robots to better assist patients in the rehabilitation process. The walking task on the Unified Parkinson’s Disease Rating Scale (UPDRS) is a well-established diagnostic criterion for PD patients. However, the clinical diagnosis of PD is determined based on the clinical experience of neurologists, which is subjective and inaccurate. Therefore, in this study, an automated diagnostic method for PD based on an improved multiclass support vector machine (MCSVM) is proposed in which wearable sensors are used. Kinematic analysis was performed to extract gait features, both spatiotemporal and kinematic, from the installed IMU and pressure sensors. Comparison experiments of three different kernel functions and linear trajectory experiments were designed. The experimental results show that the accuracies of the three kernel functions of the proposed improved MCSVM are 92.43%, 93.45%, and 95.35%. The simulation trajectories of the MCSVM are the closest to the real trajectories, which shows that the technique performs better in the clinical diagnosis of PD.

Lower limb kinematic changes during gait after hallux valgus surgery: A prospective observational study

BackgroundPatients with hallux valgus are known to alter lower limb joint kinematics during gait. However, little information is available about gait changes following hallux valgus surgery. We aimed to longitudinally investigate lower limb kinematic changes at the mid and terminal stances of gait after hallux valgus surgery. MethodsThis prospective observational study included 11 female patients (17 feet), who underwent first metatarsal osteotomy. Gait analyses were performed preoperatively and 1- and 2-year postoperatively using a three-dimensional motion capture system. Toe-out angle, ankle, knee, and hip joint angles during gait were calculated from the recorded data. The spatiotemporal parameters and these angles at the mid and terminal stances of gait were statistically compared between preoperative and postoperative periods. FindingsAll spatiotemporal parameters remained unchanged postoperatively. The toe-out angle was significantly greater at 1- and 2-year postoperatively. The ankle pronation angle, the knee abduction angle, and the hip adduction angle at the mid and terminal stances of gait were smaller postoperatively compared to the preoperative. These angular changes showed a similar trend at 1 and 2 years postoperatively. However, the postoperative changes of the sagittal joint angles were relatively small. InterpretationHallux valgus surgery can affect the toe-out angle and the lower limb coronal kinematics at the mid and terminal stances of gait in patients with hallux valgus. However, surgical correction of hallux valgus deformity did not directly improve the gait characteristics in patients with hallux valgus.

Gait Characteristics and Adaptation Strategies of Ants with Missing Legs

Gait Characteristics and Adaptation Strategies of Ants with Missing Legs

Concurrent Validity of Depth-Sensor-Based Quantification of Compensatory Movements during the Swing Phase of Gait in Healthy Individuals

The advancement in depth-sensor technology increased the potential for the clinical use of markerless three-dimensional motion analysis (3DMA); however, the accurate quantification of depth-sensor-based 3DMA on gait characteristics deviating from normal patterns is unclear. This study investigated the concurrent validity of the measurements of compensatory movements measured by depth-sensor-based 3DMA compared to those measured by marker-based 3DMA. We induced swing-phase compensatory movements due to insufficient toe clearance by restricting unilateral ankle and knee joint movements in healthy individuals. Thirty-two healthy young adults (nineteen males, aged 20.4 ± 2.0 years, height 164.4 ± 9.8 cm, weight 60.0 ± 9.3 kg [average ± standard deviation]) walked the 6 m walkway in slow speed, very slow speed, and knee–ankle–foot orthosis (KAFO; participants wore KAFOs on the right leg) conditions. Gait kinematics were measured with marker-based and depth-sensor-based 3DMA systems. The intraclass correlation coefficient (ICC3,1) was used to measure the relative agreement between depth-sensor-based and marker-based 3DMA and demonstrated good or moderate validity for swing-phase compensatory movement measurement. Additionally, the ICC2,1 measured absolute agreement between the systems and showed lower validity than the ICC3,1. The measurement errors for contralateral vaulting, trunk lateral flexion, hip hiking, swing-side hip abduction, and circumduction between instruments were 0.01 m, 1.30°, 1.99°, 2.37°, and 1.53°, respectively. Depth-sensor-based 3DMA is useful for determining swing-phase compensatory movements, although the possibility of missing a slight measurement error of 1–2° must be considered.

Prediction of Freezing of Gait in Parkinson’s disease based on multi-channel time-series neural network

Freezing of Gait (FOG) is a noticeable symptom of Parkinson’s disease, like being stuck in place and increasing the risk of falls. The wearable multi-channel sensor system is an efficient method to predict and monitor the FOG, thus warning the wearer to avoid falls and improving the quality of life. However, the existing approaches for the prediction of FOG mainly focus on a single sensor system and cannot handle the interference between multi-channel wearable sensors. Hence, we propose a novel multi-channel time-series neural network (MCT-Net) approach to merge multi-channel gait features into a comprehensive prediction framework, alerting patients to FOG symptoms in advance. Owing to the causal distributed convolution, MCT-Net is a real-time method available to give optimal prediction earlier and implemented in remote devices. Moreover, intra-channel and inter-channel transformers of MCT-Net extract and integrate different sensor position features into a unified deep learning model. Compared with four other state-of-the-art FOG prediction baselines, the proposed MCT-Net obtains 96.21% in accuracy and 80.46% in F1-score on average 2 s before FOG occurrence, demonstrating the superiority of MCT-Net.

Uncertainty-aware ensemble model for stride length estimation in gait analysis

Deep neural network (DNN) models have become highly effective tools for function estimation in regression tasks, with applications in various domains, including human gait stride length estimation. Several studies have developed DNN models that use gait cycle data from wearable devices equipped with inertial measurement units to accurately predict stride lengths within a cycle. However, many of these deep learning approaches do not quantify predictive uncertainty and fail to consider individual gait characteristics. To address these limitations, we introduced an ensemble model based on a heteroscedastic neural network that quantifies the uncertainty in stride length predictions. Additionally, we proposed a novel stride training strategy that uses the average stride instead of individual strides to optimize the training process and improve model efficiency. Our extensive performance evaluations demonstrate the robustness and adaptability of our model, accurately predicting both the uncertainty of individual stride lengths and the specific stride lengths for each gait cycle. Our study represents a significant advancement in stride length estimation, addressing the challenges of uncertainty quantification and capturing the unique aspects of human gait. The proposed model has considerable potential for practical applications in gait analysis and related fields.

Research on Monitoring Assistive Devices for Rehabilitation of Movement Disorders through Multi-Sensor Analysis Combined with Deep Learning.

This study aims to integrate a convolutional neural network (CNN) and the Random Forest Model into a rehabilitation assessment device to provide a comprehensive gait analysis in the evaluation of movement disorders to help physicians evaluate rehabilitation progress by distinguishing gait characteristics under different walking modes. Equipped with accelerometers and six-axis force sensors, the device monitors body symmetry and upper limb strength during rehabilitation. Data were collected from normal and abnormal walking groups. A knee joint limiter was applied to subjects to simulate different levels of movement disorders. Features were extracted from the collected data and analyzed using a CNN. The overall performance was scored with Random Forest Model weights. Significant differences in average acceleration values between the moderately abnormal (MA) and severely abnormal (SA) groups (without vehicle assistance) were observed (p < 0.05), whereas no significant differences were found between the MA with vehicle assistance (MA-V) and SA with vehicle assistance (SA-V) groups (p > 0.05). Force sensor data showed good concentration in the normal walking group and more scatter in the SA-V group. The CNN and Random Forest Model accurately recognized gait conditions, achieving average accuracies of 88.4% and 92.3%, respectively, proving that the method mentioned above provides more accurate gait evaluations for patients with movement disorders.

Effects of 12 weeks of head-down strong abdominal breathing on motor and cognitive performance during dual-tasking in patients with chronic obstructive pulmonary disease: Study protocol for a randomised controlled trial

ObjectiveHead-down training can affect behavioural and neurocognitive control while performing dual tasks (DT). Breathing training improves motor and cognitive performance in patients with chronic obstructive pulmonary disease (COPD). As a neurorehabilitation tool, functional near-infrared spectroscopy (fNIRS) has been demonstrated to be an effective method for detecting changes in brain activation during motor recovery, as well as monitoring patients' long-term progress during DT in motor and cognitive performance. However, no studies have examined the combined effect of head-down position and breathing exercises on motor and cognitive performance during DT. This study will employ a novel intervention involving head-down strong abdominal breathing training to investigate its effects on motor and cognitive performance during DT in patients with COPD aiming to inform future training modalities in the community and at home. MethodsWe will recruit participants from Anqing, China, through community announcements, bulletin board postings, WeChat, and offline visits and screen 72 patients with stable COPD, classified as Global Initiative for Chronic Obstructive Lung Disease (GOLD) I-II, by pulmonologists at the university hospital. All participants will be randomly assigned to the head-down strong abdominal breathing (tilt angle 0–30° on the inversion apparatus, respiratory rate 20–30 breaths/min), head-down training, and strong abdominal breathing training groups in a 1:1:1 ratio. The intervention will last 12 weeks, with sessions performed thrice weekly for 1 h. ResultsThe primary outcomes will be motor-cognitive DT time, dual-task effects, correct responses to cognitive tasks, and gait characteristics assessed at baseline, 6 and 12 weeks of intervention. The patient’s dorsolateral prefrontal cortex (PFC) will also be stimulated with fNIRS at wavelengths of 730 and 850 nm, with a sampling rate of 11 Hz, to record oxy-haemoglobin (oxy-Hb), deoxy-haemoglobin (deoxy-Hb), and total oxyhaemoglobin (total-Hb). Secondary outcomes will include pre- and post-intervention scales for dyspnoea, overall cognitive function, balance, and anxiety and depression. ConclusionAlterations in the PFC involved in attentional control, planning, and decision-making may partially explain cognitive and motor deficits (such as impaired balance and slower walking speed) in patients with COPD. This study may help to understand the effects of head-down strong abdominal breathing training on cognitive and motor performance under DT in patients with COPD and compare it with head-down training and breathing training alone. It may also help to determine whether it is a simple and effective form of exercise at home and in the community.

Wearable sensor-based quantitative gait analysis in Parkinson’s disease patients with different motor subtypes

Gait impairments are among the most common and disabling symptoms of Parkinson’s disease and worsen as the disease progresses. Early detection and diagnosis of subtype-specific gait deficits, as well as progression monitoring, can help to implement effective and preventive personalized treatment for PD patients. Yet, the gait features have not been fully studied in PD and its motor subtypes. To characterize comprehensive and objective gait alterations and to identify the potential gait biomarkers for early diagnosis, subtype differentiation, and disease severity monitoring. We analyzed gait parameters related to upper/lower limbs, trunk and lumbar, and postural transitions from 24 tremor-dominant (TD) and 20 postural instability gait difficulty (PIGD) dominant PD patients who were in early stage and 39 matched healthy controls (HC) during the Timed Up and Go test using wearable sensors. Results show: (1) Both TD and PIGD groups showed restricted backswing range in bilateral lower extremities and more affected side (MAS) arm, reduced trunk and lumbar rotation range in the coronal plane, and low turning efficiency. The receiver operating characteristic (ROC) analysis revealed these objective gait features had high discriminative value in distinguishing both PD subtypes from the HC with the area under the curve (AUC) values of 0.7~0.9 (p < 0.01). (2) Subtle but measurable gait differences existed between TD and PIGD patients before the onset of clinically apparent gait impairment. (3) Specific gait parameters were significantly associated with disease severity in TD and PIGD subtypes. Objective gait biomarkers based on wearable sensors may facilitate timely and personalized gait treatments in PD subtypes through early diagnosis, subtype differentiation, and disease severity monitoring.

Wearable biofeedback device to assess gait features and improve gait pattern in people with parkinson’s disease: a case series

IntroductionPeople with Parkinson’s Disease (PD) show abnormal gait patterns compromising their independence and quality of life. Among all gait alterations due to PD, reduced step length, increased cadence, and decreased ground-reaction force during the loading response and push-off phases are the most common. Wearable biofeedback technologies offer the possibility to provide correlated single or multi-modal stimuli associated with specific gait events or gait performance, hence promoting subjects’ awareness of their gait disturbances. Moreover, the portability and applicability in clinical and home settings for gait rehabilitation increase the efficiency in the management of PD. The Wearable Vibrotactile Bidirectional Interface (BI) is a biofeedback device designed to extract gait features in real-time and deliver a customized vibrotactile stimulus at the waist of PD subjects synchronously with specific gait phases. The aims of this study were to measure the effect of the BI on gait parameters usually compromised by the typical bradykinetic gait and to assess its usability and safety in clinical practice.MethodsIn this case series, seven subjects (age: 70.4 ± 8.1 years; H&Y: 2.7 ± 0.3) used the BI and performed a test on a 10-meter walkway (10mWT) and a two-minute walk test (2MWT) as pre-training (Pre-trn) and post-training (Post-trn) assessments. Gait tests were executed in random order with (Bf) and without (No-Bf) the activation of the biofeedback stimulus. All subjects performed three training sessions of 40 min to familiarize themselves with the BI during walking activities. A descriptive analysis of gait parameters (i.e., gait speed, step length, cadence, walking distance, double-support phase) was carried out. The 2-sided Wilcoxon sign-test was used to assess differences between Bf and No-Bf assessments (p < 0.05).ResultsAfter training subjects improved gait speed (Pre-trn_No-Bf: 0.72(0.59,0.72) m/sec; Post-trn_Bf: 0.95(0.69,0.98) m/sec; p = 0.043) and step length (Pre-trn_No-Bf: 0.87(0.81,0.96) meters; Post-trn_Bf: 1.05(0.96,1.14) meters; p = 0.023) using the biofeedback during the 10mWT. Similarly, subjects’ walking distance improved (Pre-trn_No-Bf: 97.5 (80.3,110.8) meters; Post-trn_Bf: 118.5(99.3,129.3) meters; p = 0.028) and the duration of the double-support phase decreased (Pre-trn_No-Bf: 29.7(26.8,31.7) %; Post-trn_Bf: 27.2(24.6,28.7) %; p = 0.018) during the 2MWT. An immediate effect of the BI was detected in cadence (Pre-trn_No-Bf: 108(103.8,116.7) step/min; Pre-trn_Bf: 101.4(96.3,111.4) step/min; p = 0.028) at Pre-trn, and in walking distance at Post-trn (Post-trn_No-Bf: 112.5(97.5,124.5) meters; Post-trn_Bf: 118.5(99.3,129.3) meters; p = 0.043). SUS scores were 77.5 in five subjects and 80.3 in two subjects. In terms of safety, all subjects completed the protocol without any adverse events.ConclusionThe BI seems to be usable and safe for PD users. Temporal gait parameters have been measured during clinical walking tests providing detailed outcomes. A short period of training with the BI suggests improvements in the gait patterns of people with PD. This research serves as preliminary support for future integration of the BI as an instrument for clinical assessment and rehabilitation in people with PD, both in hospital and remote environments.Trial registrationThe study protocol was registered (DGDMF.VI/P/I.5.i.m.2/2019/1297) and approved by the General Directorate of Medical Devices and Pharmaceutical Service of the Italian Ministry of Health and by the ethics committee of the Lombardy region (Milan, Italy).

Machine vision-based gait scan method for identifying cognitive impairment in older adults.

Early identification of cognitive impairment in older adults could reduce the burden of age-related disabilities. Gait parameters are associated with and predictive of cognitive decline. Although a variety of sensors and machine learning analysis methods have been used in cognitive studies, a deep optimized machine vision-based method for analyzing gait to identify cognitive decline is needed. This study used a walking footage dataset of 158 adults named West China Hospital Elderly Gait, which was labelled by performance on the Short Portable Mental Status Questionnaire. We proposed a novel recognition network, Deep Optimized GaitPart (DO-GaitPart), based on silhouette and skeleton gait images. Three improvements were applied: short-term temporal template generator (STTG) in the template generation stage to decrease computational cost and minimize loss of temporal information; depth-wise spatial feature extractor (DSFE) to extract both global and local fine-grained spatial features from gait images; and multi-scale temporal aggregation (MTA), a temporal modeling method based on attention mechanism, to improve the distinguishability of gait patterns. An ablation test showed that each component of DO-GaitPart was essential. DO-GaitPart excels in backpack walking scene on CASIA-B dataset, outperforming comparison methods, which were GaitSet, GaitPart, MT3D, 3D Local, TransGait, CSTL, GLN, GaitGL and SMPLGait on Gait3D dataset. The proposed machine vision gait feature identification method achieved a receiver operating characteristic/area under the curve (ROCAUC) of 0.876 (0.852-0.900) on the cognitive state classification task. The proposed method performed well identifying cognitive decline from the gait video datasets, making it a prospective prototype tool in cognitive assessment.

Interpretable video-based tracking and quantification of parkinsonism clinical motor states

Quantification of motor symptom progression in Parkinson’s disease (PD) patients is crucial for assessing disease progression and for optimizing therapeutic interventions, such as dopaminergic medications and deep brain stimulation. Cumulative and heuristic clinical experience has identified various clinical signs associated with PD severity, but these are neither objectively quantifiable nor robustly validated. Video-based objective symptom quantification enabled by machine learning (ML) introduces a potential solution. However, video-based diagnostic tools often have implementation challenges due to expensive and inaccessible technology, and typical “black-box” ML implementations are not tailored to be clinically interpretable. Here, we address these needs by releasing a comprehensive kinematic dataset and developing an interpretable video-based framework that predicts high versus low PD motor symptom severity according to MDS-UPDRS Part III metrics. This data driven approach validated and robustly quantified canonical movement features and identified new clinical insights, not previously appreciated as related to clinical severity, including pinkie finger movements and lower limb and axial features of gait. Our framework is enabled by retrospective, single-view, seconds-long videos recorded on consumer-grade devices such as smartphones, tablets, and digital cameras, thereby eliminating the requirement for specialized equipment. Following interpretable ML principles, our framework enforces robustness and interpretability by integrating (1) automatic, data-driven kinematic metric evaluation guided by pre-defined digital features of movement, (2) combination of bi-domain (body and hand) kinematic features, and (3) sparsity-inducing and stability-driven ML analysis with simple-to-interpret models. These elements ensure that the proposed framework quantifies clinically meaningful motor features useful for both ML predictions and clinical analysis.

Machine learning model comparison for freezing of gait prediction in advanced Parkinson's disease.

Freezing of gait (FOG) is a paroxysmal motor phenomenon that increases in prevalence as Parkinson's disease (PD) progresses. It is associated with a reduced quality of life and an increased risk of falls in this population. Precision-based detection and classification of freezers are critical to developing tailored treatments rooted in kinematic assessments. This study analyzed instrumented stand-and-walk (SAW) trials from advanced PD patients with STN-DBS. Each patient performed two SAW trials in their OFF Medication-OFF DBS state. For each trial, gait summary statistics from wearable sensors were analyzed by machine learning classification algorithms. These algorithms include k-nearest neighbors, logistic regression, naïve Bayes, random forest, and support vector machines (SVM). Each of these models were selected for their high interpretability. Each algorithm was tasked with classifying patients whose SAW trials MDS-UPDRS FOG subscore was non-zero as assessed by a trained movement disorder specialist. These algorithms' performance was evaluated using stratified five-fold cross-validation. A total of 21 PD subjects were evaluated (average age 64.24 years, 16 males, mean disease duration of 14 years). Fourteen subjects had freezing of gait in the OFF MED/OFF DBS. All machine learning models achieved statistically similar predictive performance (p < 0.05) with high accuracy. Analysis of random forests' feature estimation revealed the top-ten spatiotemporal predictive features utilized in the model: foot strike angle, coronal range of motion [trunk and lumbar], stride length, gait speed, lateral step variability, and toe-off angle. These results indicate that machine learning effectively classifies advanced PD patients as freezers or nonfreezers based on SAW trials in their non-medicated/non-stimulated condition. The machine learning models, specifically random forests, not only rely on but utilize salient spatial and temporal gait features for FOG classification.

Assessment of lumbar disc herniation-impaired gait by using IMU data fusion method

The inertial motion unit (IMU) is an effective tool for monitoring and assessing gait impairment in patients with lumbar disc herniation(LDH). However, the current clinical assessment methods for LDH gait focus on patients’ subjective scoring indicators and lack the assessment of kinematic ability; at the same time, individual differences in the motor function degradation of the healthy and affected lower limbs of LDH patients are also ignored. To solve this problem, we propose an LDH gait feature model based on multi-source adaptive Kalman data fusion of acceleration and angular velocity. The gait phase is segmented by using an adaptive Kalman data fusion algorithm to estimate the attitude angle, and obtaining gait events through a zero-velocity update technique and a peak detection algorithm. Two IMUs were used to analyze the gait characteristics of lumbar disc patients and healthy gait people, including 12 gait characteristics such as gait spatiotemporal parameters, kinematic parameters, gait variability and stability. Statistical methods were used to analyze the characteristic model and verify the biological differences between the healthy affected side of LDH and healthy subjects. Finally, feature engineering and machine learning technology were used to identify the gait pattern of inertial movement units in patients with lumbar intervertebral disc disease, and achieved a classification accuracy of 95.50%, providing an effective gait feature set and method for clinical evaluation of LDH.

External Validation and Further Exploration of Fall Prediction Models Based on Questionnaires and Daily-Life Trunk Accelerometry

Ambulatory measurements of trunk accelerations can provide valuable insight into the amount and quality of daily life activities. Such information has been used to create models to identify individuals at high risk of falls. However, external validation of such prediction models is lacking, yet crucial for clinical implementation. We externally validated 3 previously described fall prediction models. Complete questionnaires and 1-week trunk acceleration data were obtained from 263 community-dwelling people (mean age 71.8 years, 68.1% female). To validate models, we first used the coefficients and optimal cutoffs from the original cohort, then recalibrated the original models, as well as optimized parameters based on our new cohort. Among all participants, 39.9% experienced falls during a 6-month follow-up. All models showed poor precision (0.20-0.49), poor sensitivity (0.32-0.58), and good specificity (0.45-0.89). Calibration of the original models had limited effect on model performance. Using coefficients and cutoffs optimized on the external cohort also had limited benefits. Lastly, the odds ratios in our cohort were different from those in the original cohort, which indicated that gait characteristics, except for the index of harmonicity ML (medial-lateral direction), were not statistically associated with falls. Fall risk prediction in our cohort was not as effective as in the original cohort. Recalibration as well as optimized model parameters resulted in a limited increase in accuracy. Fall prediction models are highly specific to the cohort studied. This highlights the need for large representative cohorts, preferably with an external validation cohort.

Postural change, gait, and physical function in older adults

In a more clinical setting, abrupt posture change may be used to determine the presence of orthostatic hypotension, a hemodynamic response with relationships to physical function. Certain gait features and physical function performance are also associated with risk of falling in older adults. However, the extent to which posture change is associated with subsequent gait and physical function has received little attention in the literature. This study aims to determine the effects of posture change on spatiotemporal parameters of gait and Timed Up-and-Go (TUG) performance. Methods. Forty-two volunteers (age 73.21 ± 6.22 years) participated in the study. A custom Tekscan Strideway (Tekscan, Boston, MA.) gait system was used to measure gait velocity (VEL), cadence (CAD), stride length (SL), and percent of time spent in active propulsion (AP). Dependent t-tests were used to compare TUG time, VEL, CAD, SL and AP after at least 10 mins of seated rest and supine rest. Results. Time to complete the TUG was significantly slower after supine rest compared to seated (11.47 ± 0.51 and 10.01 ± 0.33 s, respectively, p<0.001); VEL was significantly slower after supine rest compared to seated (0.888 ± 0.042 and 1.049 ± 0.033 m/s, respectively, p=0.003); CAD was significantly slower after supine rest compared to seated (111.21 ± 2.87 and 120.97 ± 2.56spm, respectively, p=0.001); and AP was significantly lower after supine rest compared to seated (56.87 ± 4.76 and 70.79 ± 4.05 %, respectively, p<0.001). No significant differences were detected in stride length between conditions. Conclusions. Among this sample of older adults, standing from a supine posture is associated with spatiotemporal gait parameters consistent with a risk for falling and aging. Additionally, TUG performance worsens significantly after supine rest. Future studies could explore the sensitivity and specificity of falls risk screening after supine rest.