Human Activity Recognition of Individuals with Lower Limb Amputation in Free-Living Conditions: A Pilot Study

This pilot study aimed to investigate the implementation of supervised classifiers and a neural network for the recognition of activities carried out by Individuals with Lower Limb Amputation (ILLAs), as well as individuals without gait impairment, in free living conditions. Eight individuals with no gait impairments and four ILLAs wore a thigh-based accelerometer and walked on an improvised route in the vicinity of their homes across a variety of terrains. Various machine learning classifiers were trained and tested for recognition of walking activities. Additional investigations were made regarding the detail of the activity label versus classifier accuracy and whether the classifiers were capable of being trained exclusively on non-impaired individuals’ data and could recognize physical activities carried out by ILLAs. At a basic level of label detail, Support Vector Machines (SVM) and Long-Short Term Memory (LSTM) networks were able to acquire 77–78% mean classification accuracy, which fell with increased label detail. Classifiers trained on individuals without gait impairment could not recognize activities carried out by ILLAs. This investigation presents the groundwork for a HAR system capable of recognizing a variety of walking activities, both for individuals with no gait impairments and ILLAs.

Effect of Neurorepair for Motor Functional Recovery Enhanced by Total Saponins From Trillium tschonoskii Maxim. Treatment in a Rat Model of Focal Ischemia

Trillium tschonoskii Maxim. (TTM), is a perennial herb from Liliaceae, that has been widely used as a traditional Chinese medicine treating cephalgia and traumatic hemorrhage. The present work was designed to investigate whether the total saponins from Trillium tschonoskii Maxim. (TSTT) would promote brain remodeling and improve gait impairment in the chronic phase of ischemic stroke. A focal ischemic model of male Sprague-Dawley (SD) rats was established by permanent middle cerebral artery occlusion (MCAO). Six hours later, rats were intragastrically treated with TSTT (120, 60, and 30 mg/kg) and once daily up to day 30. The gait changes were assessed by the CatWalk-automated gait analysis system. The brain tissues injuries, cerebral perfusion and changes of axonal microstructures were detected by multimodal magnetic resonance imaging (MRI), followed by histological examinations. The axonal regeneration related signaling pathways including phosphatidylinositol 3-kinases (PI3K)/protein kinase B (AKT)/glycogen synthase kinase-3 (GSK-3)/collapsin response mediator protein-2 (CRMP-2) were measured by western blotting. TSTT treatment significantly improved gait impairment of rats. MRI analysis revealed that TSTT alleviated tissues injuries, significantly improved cerebral blood flow (CBF), enhanced microstructural integrity of axon and myelin sheath in the ipsilesional sensorimotor cortex and internal capsule. In parallel to MRI findings, TSTT preserved myelinated axons and promoted oligodendrogenesis. Specifically, TSTT interventions markedly up-regulated expression of phosphorylated GSK-3, accompanied by increased expression of phosphorylated PI3K, AKT, but reduced phosphorylated CRMP-2 expression. Taken together, our results suggested that TSTT facilitated brain remodeling. This correlated with improving CBF, encouraging reorganization of axonal microstructure, promoting oligodendrogenesis and activating PI3K/AKT/GSK-3/CRMP-2 signaling, thereby improving poststroke gait impairments.

Perception and Use of Compensation Strategies for Gait Impairment by Persons With Parkinson Disease

Background and ObjectivesGait impairments are common and disabling in Parkinson disease (PD). Applying compensation strategies helps to overcome these gait deficits. Clinical observations suggest that the efficacy of different compensation strategies varies depending on both individual patient characteristics and the context in which the strategies are applied. This has never been investigated systematically, hampering the ability of clinicians to provide a more personalized approach to gait rehabilitation. We had 3 aims: (1) to evaluate patients' awareness and actual use of compensation categories for gait impairments in PD, (2) to investigate the patient-rated efficacy of the various compensation strategies and whether this efficacy depends on the context in which the strategies are applied, and (3) to explore differences in the efficacy between subgroups based on sex, age, disease duration, freezing status, and ability to perform a dual task.MethodsA survey was conducted among 4,324 adults with PD and self-reported disabling gait impairments.ResultsThe main findings are as follows: (1) compensation strategies for gait impairments are commonly used by persons with PD, but their awareness of the full spectrum of available strategies is limited; (2) the patient-rated efficacy of compensation strategies is high but varies depending on the context in which they are applied; and (3) compensation strategies are useful for all types of patients with PD, but the efficacy of the different strategies varies per person.DiscussionThe choice of compensation strategies for gait impairment in PD should be tailored to the individual patient and to the context in which the strategy needs to be applied.Classification of EvidenceThis data provides Class IV evidence that compensation strategies are an effective treatment for gait impairment in patients with PD.

A Clinically Interpretable Computer-Vision Based Method for Quantifying Gait in Parkinson’s Disease

Gait is a core motor function and is impaired in numerous neurological diseases, including Parkinson’s disease (PD). Treatment changes in PD are frequently driven by gait assessments in the clinic, commonly rated as part of the Movement Disorder Society (MDS) Unified PD Rating Scale (UPDRS) assessment (item 3.10). We proposed and evaluated a novel approach for estimating severity of gait impairment in Parkinson’s disease using a computer vision-based methodology. The system we developed can be used to obtain an estimate for a rating to catch potential errors, or to gain an initial rating in the absence of a trained clinician—for example, during remote home assessments. Videos (n=729) were collected as part of routine MDS-UPDRS gait assessments of Parkinson’s patients, and a deep learning library was used to extract body key-point coordinates for each frame. Data were recorded at five clinical sites using commercially available mobile phones or tablets, and had an associated severity rating from a trained clinician. Six features were calculated from time-series signals of the extracted key-points. These features characterized key aspects of the movement including speed (step frequency, estimated using a novel Gamma-Poisson Bayesian model), arm swing, postural control and smoothness (or roughness) of movement. An ordinal random forest classification model (with one class for each of the possible ratings) was trained and evaluated using 10-fold cross validation. Step frequency point estimates from the Bayesian model were highly correlated with manually labelled step frequencies of 606 video clips showing patients walking towards or away from the camera (Pearson’s r=0.80, p<0.001). Our classifier achieved a balanced accuracy of 50% (chance = 25%). Estimated UPDRS ratings were within one of the clinicians’ ratings in 95% of cases. There was a significant correlation between clinician labels and model estimates (Spearman’s ρ=0.52, p<0.001). We show how the interpretability of the feature values could be used by clinicians to support their decision-making and provide insight into the model’s objective UPDRS rating estimation. The severity of gait impairment in Parkinson’s disease can be estimated using a single patient video, recorded using a consumer mobile device and within standard clinical settings; i.e., videos were recorded in various hospital hallways and offices rather than gait laboratories. This approach can support clinicians during routine assessments by providing an objective rating (or second opinion), and has the potential to be used for remote home assessments, which would allow for more frequent monitoring.

Repurposing an EMG Biofeedback Device for Gait Rehabilitation: Development, Validity and Reliability

Gait impairment often limits physical activity and negatively impacts quality of life. EMG-Biofeedback (EMG-BFB), one of the more effective interventions for improving gait impairment, has been limited to laboratory use due to system costs and technical requirements, and has therefore not been tested on a larger scale. In our research, we aimed to develop and validate a cost-effective, commercially available EMG-BFB device for home- and community-based use. We began by repurposing mTrigger® (TJM Electronics, Warminster, PA, USA), a cost-effective, portable EMG-BFB device, for gait application. This included developing features in the cellphone app such as step feedback, success rate, muscle activity calibration, and cloud integration. Next, we tested the validity and reliability of the mTrigger device in healthy adults by comparing it to a laboratory-grade EMG system. While wearing both devices, 32 adults walked overground and on a treadmill at four speeds (0.3, 0.6, 0.9, and 1.2 m/s). Statistical analysis revealed good to excellent test–retest reliability (r > 0.89) and good to excellent agreement in the detection of steps (ICC > 0.85) at all speeds between two systems for treadmill walking. Our results indicated that mTrigger compared favorably to a laboratory-grade EMG system in the ability to assess muscular activity and to provide biofeedback during walking in healthy adults.

Gait Impairment and Upper Extremity Disturbance Are Associated With Total Magnetic Resonance Imaging Cerebral Small Vessel Disease Burden

Background and Purpose: Cerebral small vessel disease (cSVD)—including white matter hyperintensities (WMHs), cerebral microbleeds (CMBs), lacunes, and enlarged perivascular spaces (EPVS)—is related to gait impairment. However, the association between the total magnetic resonance imaging (MRI) cSVD burden and gait and upper extremity function remains insufficiently investigated. This study aimed to assess the correlation between the total MRI cSVD burden score and gait impairment as well as upper extremity impairment.Method: A total of 224 participants underwent MRI scans, and the presence of lacunes, WMHs, CMBs, and EPVS was evaluated and recorded as a total MRI cSVD burden score (range 0–4). Gait was assessed by 4-m walkway, Tinetti, Timed Up and Go (TUG), and Short Physical Performance Battery (SPPB) tests. Upper extremity function was assessed by 10-repeat hand pronation-supination time, 10-repeat finger-tapping time, and 10-repeat hand opening and closing time.Result: The mean age of the 224 participants was 60.6 ± 10.5 years, and 64.3% were men. Independent of age, sex, height, and vascular risk factors, multivariable linear regression analyses showed that a higher total MRI cSVD burden score was related to a shorter stride length, wider step width, higher cadence, and poorer performance on the Tinetti, TUG, and SPPB tests and upper extremity tests (all P &lt; 0.05).Conclusion: Total MRI cSVD burden was associated with gait impairment and upper extremity disturbances, suggesting that total MRI cSVD burden might contribute to motor function decline. Longitudinal studies are required to determine whether there is a causal relationship between total MRI cSVD burden and motor function decline.