Measuring freezing of gait during daily-life: an open-source, wearable sensors approach

Development, Validation, and Limits of Freezing of Gait Detection Using a Single Waist-Worn Device

OBJECTIVE

Freezing of Gait (FOG) is prevalent in people with Parkinson's disease (PD) and severely disrupts mobility. Detecting the exact boundaries of FOG episodes may facilitate new technologies in "breaking" FOG in real-time. This study investigates the performance of automatic device-based FOG detection.

METHODS

Eight machine-learning classifiers (including Neural Networks, Ensemble methods, and Support Vector Machines) were developed using (i) accelerometer and (ii) combined accelerometer and gyroscope data from a waist-worn device. While wearing the device, 107 people with PD completed mobility tasks designed to elicit FOG. Two clinicians independently annotated exact FOG episodes using synchronized video and a flowchart algorithm based on international guidelines. Device-detected FOG episodes were compared to annotated episodes using 10-fold cross-validation and Interclass Correlation Coefficients (ICC) for agreement.

RESULTS

Development used 50,962 windows of data and annotated activities (>10 hours). Strong agreement between clinicians for precise FOG episodes was observed (90% sensitivity, 92% specificity, and ICC1,1 = 0.97 for total FOG duration). Device performance varied by method, complexity, and cost matrix. The Neural Network using 67 accelerometer features achieved high sensitivity to FOG (89% sensitivity, 81% specificity, and ICC1,1 = 0.83) and stability (validation loss 5%).

CONCLUSION

The waist-worn device consistently reported accurate detection of precise FOG episodes and compared well to more complex systems. The strong clinician agreement indicates room for improvement in future device-based FOG detection.

SIGNIFICANCE

This study may enhance PD care by reducing reliance on visual FOG inspection, demonstrating that high sensitivity in automatic FOG detection is achievable.

Knowledge mapping of freezing of gait in Parkinson's disease: a bibliometric analysis

Objective

Among the disturbing motor symptoms in Parkinson's disease (PD), freezing of gait (FOG) stands out as one of the most severe challenges. It typically arises during the initiation of gait or when turning. This phenomenon not only impose a heavy burden on patients, but also on their families. We conduct a bibliometric analysis to summarize current research hotspots and trends concerning freezing of gait in Parkinson's disease (PD-FOG) over past two decades.

Methods

We retrieved articles and reviews published in English about PD-FOG in the Web of science Core Collection database from 2000 to 2023 on November 30,2023. The tools VOSviewer and CiteSpace facilitated a visual analysis covering various aspects such as publications, countries/regions, organizations, authors, journals, cited references, and keywords.

Result

This study includes 1,340 articles from 64 countries/regions. There is a growth in publications related to PD-FOG over the past two decades, maintaining a stable high output since 2018, indicating a promising research landscape in the field of PD-FOG. The United States holds a leading position in this field, with Nieuwboer A and Giladi N being two of the most influential researchers. Over the past two decades, the research hotspots for PD-FOG have primarily encompassed the kinematic characteristics, diagnosis and detection, cognitive deficits and neural connectivity, as well as therapy and rehabilitation of PD-FOG. Topics including functional connectivity, virtual reality, deep learning and machine learning will be focal points of future research.

Conclusion

This is the first bibliometric analysis of PD-FOG. We construct this study to summarize the research in this field over past two decades, visually show the current hotspots and trends, and offer scholars in this field concepts and strategies for subsequent studies.

Human-exoskeleton interaction portrait

Human-robot physical interaction contains crucial information for optimizing user experience, enhancing robot performance, and objectively assessing user adaptation. This study introduces a new method to evaluate human-robot interaction and co-adaptation in lower limb exoskeletons by analyzing muscle activity and interaction torque as a two-dimensional random variable. We introduce the interaction portrait (IP), which visualizes this variable's distribution in polar coordinates. We applied IP to compare a recently developed hybrid torque controller (HTC) based on kinematic state feedback and a novel adaptive model-based torque controller (AMTC) with online learning, proposed herein, against a time-based controller (TBC) during treadmill walking at varying speeds. Compared to TBC, both HTC and AMTC significantly lower users' normalized oxygen uptake, suggesting enhanced user-exoskeleton coordination. IP analysis reveals that this improvement stems from two distinct co-adaptation strategies, unidentifiable by traditional muscle activity or interaction torque analyses alone. HTC encourages users to yield control to the exoskeleton, decreasing overall muscular effort but increasing interaction torque, as the exoskeleton compensates for user dynamics. Conversely, AMTC promotes user engagement through increased muscular effort and reduces interaction torques, aligning it more closely with rehabilitation and gait training applications. IP phase evolution provides insight into each user's interaction strategy formation, showcasing IP analysis's potential in comparing and designing novel controllers to optimize human-robot interaction in wearable robots.

Virtual reality-based supportive care interventions for patients with cancer: an umbrella review of systematic reviews and meta-analyses

PURPOSE

This umbrella review aimed to identify, critically appraise, and synthesize current evidence from systematic reviews and meta-analyses on the applications of virtual reality-based supportive care interventions in cancer.

METHODS

Three bibliographic databases were searched from inception to February 1, 2024. Two independent reviewers screened the titles and abstracts of 421 records and retrieved 26 full-text systematic reviews. Assessing the Methodological Quality of Systematic Reviews 2 (AMSTAR-2) was used for quality assessment. Qualitative syntheses were performed to investigate the effects of virtual reality-based supportive care interventions on quality of life and physical, psychological, cognitive, and functional outcomes. Meta-analysis was performed based on data from the distinct primary studies that were extracted from the included reviews.

RESULTS

This umbrella review included 20 systematic reviews that were published between 2018 and 2023; nine of them conducted meta-analyses. A total of 86 distinct primary studies were identified. According to the AMSTAR-2 assessment, two reviews were evaluated as moderate quality, nine as low, and nine as critically low. Meta-analyses of primary studies revealed significant effects of virtual reality on anxiety (p < 0.001), depression (p < 0.001), and pain (p < 0.001), but not fatigue (p = 0.263). Qualitative syntheses revealed positive effects of virtual reality on physical function, cognitive function, and quality of life. Limited evidence was reported regarding outcomes of balance, gait, mobility, and activities of daily living.

CONCLUSION

Virtual reality has proven to be a safe and feasible approach to deliver supportive care in cancer. Virtual reality can be implemented in various stages and settings of the cancer care continuum to support patients undergoing painful procedures, during or after chemotherapy, and after surgical interventions. Virtual reality can serve as an effective supportive care intervention to manage anxiety, pain, and depression for patients with cancer.

Assessing the clinical utility of inertial sensors for home monitoring in Parkinson's disease: a comprehensive review

This review screened 296 articles on wearable sensors for home monitoring of people with Parkinson's Disease within the PubMed Database, from January 2017 to May 2023. A three-level maturity framework was applied for classifying the aims of 59 studies included: demonstrating technical efficacy, diagnostic sensitivity, or clinical utility. As secondary analysis, user experience (usability and patient adherence) was evaluated. The evidences provided by the studies were categorized and stratified according to the level of maturity. Our results indicate that approximately 75% of articles investigated diagnostic sensitivity, i.e. correlation of sensor-data with clinical parameters. Evidence of clinical utility, defined as improvement on health outcomes or clinical decisions after the use of the wearables, was found only in nine papers. A third of the articles included reported evidence of user experience. Future research should focus more on clinical utility, to facilitate the translation of research results within the management of Parkinson's Disease.

Simplification of Mobility Tests and Data Processing to Increase Applicability of Wearable Sensors as Diagnostic Tools for Parkinson's Disease

Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson's disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.

Development of a Tremor Detection Algorithm for Use in an Academic Movement Disorders Center

Tremor, defined as an "involuntary, rhythmic, oscillatory movement of a body part", is a key feature of many neurological conditions including Parkinson's disease and essential tremor. Clinical assessment continues to be performed by visual observation with quantification on clinical scales. Methodologies for objectively quantifying tremor are promising but remain non-standardized across centers. Our center performs full-body behavioral testing with 3D motion capture for clinical and research purposes in patients with Parkinson's disease, essential tremor, and other conditions. The objective of this study was to assess the ability of several candidate processing pipelines to identify the presence or absence of tremor in kinematic data from patients with confirmed movement disorders and compare them to expert ratings from movement disorders specialists. We curated a database of 2272 separate kinematic data recordings from our center, each of which was contemporaneously annotated as tremor present or absent by a movement physician. We compared the ability of six separate processing pipelines to recreate clinician ratings based on F1 score, in addition to accuracy, precision, and recall. The performance across algorithms was generally comparable. The average F1 score was 0.84±0.02 (mean ± SD; range 0.81-0.87). The second highest performing algorithm (cross-validated F1=0.87) was a hybrid that used engineered features adapted from an algorithm in longstanding clinical use with a modern Support Vector Machine classifier. Taken together, our results suggest the potential to update legacy clinical decision support systems to incorporate modern machine learning classifiers to create better-performing tools.

A method for the synchronization of inertial sensor signals and local field potentials from deep brain stimulation systems

Objective. Recent innovative neurostimulators allow recording local field potentials (LFPs) while performing motor tasks monitored by wearable sensors. Inertial sensors can provide quantitative measures of motor impairment in people with subthalamic nucleus deep brain stimulation. To the best of our knowledge, there is no validated method to synchronize inertial sensors and neurostimulators without an additional device. This study aims to define a new synchronization method to analyze disease-related brain activity patterns during specific motor tasks and evaluate how LFPs are affected by stimulation and medication.Approach. Fourteen male subjects treated with subthalamic nucleus deep brain stimulation were recruited to perform motor tasks in four different medication and stimulation conditions. In each condition, a synchronization protocol was performed consisting of taps on the implanted neurostimulator, which produces artifacts in the LFPs that a nearby inertial sensor can simultaneously record.Main results. In 64% of the recruited subjects, induced artifacts were detected at least in one condition. Among those subjects, 83% of the recordings could be synchronized offline analyzing LFPs and wearables data. The remaining recordings were synchronized by video analysis.Significance. The proposed synchronization method does not require an external system (e.g., TENS electrodes) and can be easily integrated into clinical practice. The procedure is simple and can be carried out in a short time. A proper and simple synchronization will also be useful to analyze subthalamic neural activity in the presence of specific events (e.g., freezing of gait events) to identify predictive biomarkers.

Causality-Enhanced Multiple Instance Learning With Graph Convolutional Networks for Parkinsonian Freezing-of-Gait Assessment

Freezing of gait (FoG) is a common disabling symptom of Parkinson's disease (PD). It is clinically characterized by sudden and transient walking interruptions for specific human body parts, and it presents the localization in time and space. Due to the difficulty in extracting global fine-grained features from lengthy videos, developing an automated five-point FoG scoring system is quite challenging. Therefore, we propose a novel video-based automated five-classification FoG assessment method with a causality-enhanced multiple-instance-learning graph convolutional network (GCN). This method involves developing a temporal segmentation GCN to segment each video into three motion stages for stage-level feature modeling, followed by a multiple-instance-learning framework to divide each stage into short clips for instance-level feature extraction. Subsequently, an uncertainty-driven multiple-instance-learning GCN is developed to capture spatial and temporal fine-grained features through GCN scheme and uncertainty learning, respectively, for acquiring global representations. Finally, a causality-enhanced graph generation strategy is proposed to exploit causal inference for mining and enhancing human structures causally related to clinical assessment, thereby extracting spatial causal features. Extensive experimental results demonstrate the excellent performance of the proposed method on five-classification FoG assessment with an accuracy of 62.72% and an acceptable accuracy of 91.32%, which is confirmed by independent testing. Additionally, it enables temporal and spatial localization of FoG events to a certain extent, facilitating reasonable clinical interpretations. In conclusion, our method provides a valuable tool for automated FoG assessment in PD, and the proposed causality-related component exhibits promising potential for extension to other general and medical fine-grained action recognition tasks.

A machine learning contest enhances automated freezing of gait detection and reveals time-of-day effects

Freezing of gait (FOG) is a debilitating problem that markedly impairs the mobility and independence of 38-65% of people with Parkinson's disease. During a FOG episode, patients report that their feet are suddenly and inexplicably "glued" to the floor. The lack of a widely applicable, objective FOG detection method obstructs research and treatment. To address this problem, we organized a 3-month machine-learning contest, inviting experts from around the world to develop wearable sensor-based FOG detection algorithms. 1,379 teams from 83 countries submitted 24,862 solutions. The winning solutions demonstrated high accuracy, high specificity, and good precision in FOG detection, with strong correlations to gold-standard references. When applied to continuous 24/7 data, the solutions revealed previously unobserved patterns in daily living FOG occurrences. This successful endeavor underscores the potential of machine learning contests to rapidly engage AI experts in addressing critical medical challenges and provides a promising means for objective FOG quantification.

On-Demand Cueing for Freezing of Gait in Parkinson's Disease: A Randomized Controlled Trial

BACKGROUND

Cueing can alleviate freezing of gait (FOG) in people with Parkinson's disease (PD), but using the same cues continuously in daily life may compromise effectiveness. Therefore, we developed the DeFOG-system to deliver personalized auditory cues on detection of a FOG episode.

OBJECTIVES

We aimed to evaluate the effects of DeFOG during a FOG-provoking protocol: (1) after 4 weeks of DeFOG-use in daily life against an active control group; (2) after immediate DeFOG-use (within-group) in different medication states.

METHOD

In this randomized controlled trial, 63 people with PD and daily FOG were allocated to the DeFOG or active control group. Both groups received feedback on their daily living step counts using the device, but the DeFOG group also received on-demand cueing. Video-rated FOG severity was compared pre- and post-intervention through a FOG-provoking protocol administered at home off and on-medication, but without using DeFOG. Within-group effects were tested by comparing FOG during the protocol with and without DeFOG.

RESULTS

DeFOG-use during the 4 weeks was similar between groups, but we found no between-group differences in FOG-severity. However, the within-group analysis showed that FOG was alleviated by DeFOG (effect size d = 0.57), regardless of medication state. Combining DeFOG and medication yielded an effect size of d = 0.67.

CONCLUSIONS

DeFOG reduced FOG considerably in a population of severe freezers both off and on medication. Nonetheless, 4 weeks of DeFOG-use in daily life did not ameliorate FOG during the protocol unless DeFOG was worn. These findings suggest that on-demand cueing is only effective when used, similar to other walking aids. © 2024 International Parkinson and Movement Disorder Society.

Unveiling the Unpredictable in Parkinson's Disease: Sensor-Based Monitoring of Dyskinesias and Freezing of Gait in Daily Life

BACKGROUND

Dyskinesias and freezing of gait are episodic disorders in Parkinson's disease, characterized by a fluctuating and unpredictable nature. This cross-sectional study aims to objectively monitor Parkinsonian patients experiencing dyskinesias and/or freezing of gait during activities of daily living and assess possible changes in spatiotemporal gait parameters.

METHODS

Seventy-one patients with Parkinson's disease (40 with dyskinesias and 33 with freezing of gait) were continuously monitored at home for a minimum of 5 days using a single wearable sensor. Dedicated machine-learning algorithms were used to categorize patients based on the occurrence of dyskinesias and freezing of gait. Additionally, specific spatiotemporal gait parameters were compared among patients with and without dyskinesias and/or freezing of gait.

RESULTS

The wearable sensor algorithms accurately classified patients with and without dyskinesias as well as those with and without freezing of gait based on the recorded dyskinesias and freezing of gait episodes. Standard spatiotemporal gait parameters did not differ significantly between patients with and without dyskinesias or freezing of gait. Both the time spent with dyskinesias and the number of freezing of gait episodes positively correlated with the disease severity and medication dosage.

CONCLUSIONS

A single inertial wearable sensor shows promise in monitoring complex, episodic movement patterns, such as dyskinesias and freezing of gait, during daily activities. This approach may help implement targeted therapeutic and preventive strategies for Parkinson's disease.

Mixed-method usability investigation of ARROWS: augmented reality for roadway work zone safety

This article explores the usability and user experience challenges of ARROWS, a novel augmented reality (AR) and wearable technology (WT) safety system for roadway work zones, an area with limited existing usability research. We utilized a mixed-method approach with two complementary experiments in indoor and outdoor settings, using the Wizard of Oz methodology and a high-fidelity prototype. We focused on identifying usability challenges, factors contributing to user experience and the distinct needs of highway workers, documenting results using the system usability scale (SUS), the rating scale mental effort (RSME) and a trust score. Participants rated the usability of ARROWS above average in both settings, while making a reasonable level of mental effort. The findings also indicate a significant correlation between perceived trust and usability, highlighting the importance of trust in user experience.

Freezing of gait assessment with inertial measurement units and deep learning: effect of tasks, medication states, and stops

BACKGROUND

Freezing of gait (FOG) is an episodic and highly disabling symptom of Parkinson's Disease (PD). Traditionally, FOG assessment relies on time-consuming visual inspection of camera footage. Therefore, previous studies have proposed portable and automated solutions to annotate FOG. However, automated FOG assessment is challenging due to gait variability caused by medication effects and varying FOG-provoking tasks. Moreover, whether automated approaches can differentiate FOG from typical everyday movements, such as volitional stops, remains to be determined. To address these questions, we evaluated an automated FOG assessment model with deep learning (DL) based on inertial measurement units (IMUs). We assessed its performance trained on all standardized FOG-provoking tasks and medication states, as well as on specific tasks and medication states. Furthermore, we examined the effect of adding stopping periods on FOG detection performance.

METHODS

Twelve PD patients with self-reported FOG (mean age 69.33 ± 6.02 years) completed a FOG-provoking protocol, including timed-up-and-go and 360-degree turning-in-place tasks in On/Off dopaminergic medication states with/without volitional stopping. IMUs were attached to the pelvis and both sides of the tibia and talus. A temporal convolutional network (TCN) was used to detect FOG episodes. FOG severity was quantified by the percentage of time frozen (%TF) and the number of freezing episodes (#FOG). The agreement between the model-generated outcomes and the gold standard experts' video annotation was assessed by the intra-class correlation coefficient (ICC).

RESULTS

For FOG assessment in trials without stopping, the agreement of our model was strong (ICC (%TF) = 0.92 [0.68, 0.98]; ICC(#FOG) = 0.95 [0.72, 0.99]). Models trained on a specific FOG-provoking task could not generalize to unseen tasks, while models trained on a specific medication state could generalize to unseen states. For assessment in trials with stopping, the agreement of our model was moderately strong (ICC (%TF) = 0.95 [0.73, 0.99]; ICC (#FOG) = 0.79 [0.46, 0.94]), but only when stopping was included in the training data.

CONCLUSION

A TCN trained on IMU signals allows valid FOG assessment in trials with/without stops containing different medication states and FOG-provoking tasks. These results are encouraging and enable future work investigating automated FOG assessment during everyday life.

Gait quality in prosthesis users is reflected by force-based metrics when learning to walk on a new research-grade powered prosthesis

Introduction

Powered prosthetic feet require customized tuning to ensure comfort and long-term success for the user, but tuning in both clinical and research settings is subjective, time intensive, and the standard for tuning can vary depending on the patient's and the prosthetist's experience levels.

Methods

Therefore, we studied eight different metrics of gait quality associated with use of a research-grade powered prosthetic foot in seven individuals with transtibial amputation during treadmill walking. We compared clinically tuned and untuned conditions with the goal of identifying performance-based metrics capable of distinguishing between good (as determined by a clinician) from poor gait quality.

Results

Differences between the tuned and untuned conditions were reflected in ankle power, both the vertical and anterior-posterior impulse symmetry indices, limb-force alignment, and positive ankle work, with improvements seen in all metrics during use of the tuned prosthesis.

Discussion

Notably, all of these metrics relate to the timing of force generation during walking which is information not directly accessible to a prosthetist during a typical tuning process. This work indicates that relevant, real-time biomechanical data provided to the prosthetist through the future provision of wearable sensors may enhance and improve future clinical tuning procedures associated with powered prostheses as well as their long-term outcomes.

Detection and prediction of freezing of gait with wearable sensors in Parkinson's disease

Freezing of gait (FoG) is one of the most distressing symptoms of Parkinson's Disease (PD), commonly occurring in patients at middle and late stages of the disease. Automatic and accurate FoG detection and prediction have emerged as a promising tool for long-term monitoring of PD and implementation of gait assistance systems. This paper reviews the recent development of FoG detection and prediction using wearable sensors, with attention on identifying knowledge gaps that need to be filled in future research. This review searched the PubMed and Web of Science databases to collect studies that detect or predict FoG with wearable sensors. After screening, 89 of 270 articles were included. The data description, extracted features, detection/prediction methods, and classification performance were extracted from the articles. As the number of papers of this area is increasing, the performance has been steadily improved. However, small datasets and inconsistent evaluation processes still hinder the application of FoG detection and prediction with wearable sensors in clinical practice.

Wearable devices for gait and posture monitoring via telemedicine in people with movement disorders and multiple sclerosis: a systematic review

INTRODUCTION

Wearable devices and telemedicine are increasingly used to track health-related parameters across patient populations. Since gait and postural control deficits contribute to mobility deficits in persons with movement disorders and multiple sclerosis, we thought it interesting to evaluate devices in telemedicine for gait and posture monitoring in such patients.

METHODS

For this systematic review, we searched the electronic databases MEDLINE (PubMed), SCOPUS, Cochrane Library, and SPORTDiscus. Of the 452 records retrieved, 12 met the inclusion/exclusion criteria. Data about (1) study characteristics and clinical aspects, (2) technical, and (3) telemonitoring and teleconsulting were retrieved, The studies were quality assessed.

RESULTS

All studies involved patients with Parkinson's disease; most used triaxial accelerometers for general assessment (n = 4), assessment of motor fluctuation (n = 3), falls (n = 2), and turning (n = 3). Sensor placement and count varied widely across studies. Nine used lab-validated algorithms for data analysis. Only one discussed synchronous patient feedback and asynchronous teleconsultation.

CONCLUSIONS

Wearable devices enable real-world patient monitoring and suggest biomarkers for symptoms and behaviors related to underlying gait disorders. thus enriching clinical assessment and personalized treatment plans. As digital healthcare evolves, further research is needed to enhance device accuracy, assess user acceptability, and integrate these tools into telemedicine infrastructure.

PROSPERO REGISTRATION

CRD42022355460.

Soft robotic apparel to avert freezing of gait in Parkinson's disease

Freezing of gait (FoG) is a profoundly disruptive gait disturbance in Parkinson's disease, causing unintended stops while walking. Therapies for FoG reveal modest and transient effects, resulting in a lack of effective treatments. Here we show proof of concept that FoG can be averted using soft robotic apparel that augments hip flexion. The wearable garment uses cable-driven actuators and sensors, generating assistive moments in concert with biological muscles. In this n-of-1 trial with five repeated measurements spanning 6 months, a 73-year-old male with Parkinson's disease and substantial FoG demonstrated a robust response to robotic apparel. With assistance, FoG was instantaneously eliminated during indoor walking (0% versus 39 ± 16% time spent freezing when unassisted), accompanied by 49 ± 11 m (+55%) farther walking compared to unassisted walking, faster speeds (+0.18 m s-1) and improved gait quality (-25% in gait variability). FoG-targeting effects were repeatable across multiple days, provoking conditions and environment contexts, demonstrating potential for community use. This study demonstrated that FoG was averted using soft robotic apparel in an individual with Parkinson's disease, serving as an impetus for technological advancements in response to this serious yet unmet need.

Quantitative gait analysis and prediction using artificial intelligence for patients with gait disorders

Quantitative Gait Analysis (QGA) is considered as an objective measure of gait performance. In this study, we aim at designing an artificial intelligence that can efficiently predict the progression of gait quality using kinematic data obtained from QGA. For this purpose, a gait database collected from 734 patients with gait disorders is used. As the patient walks, kinematic data is collected during the gait session. This data is processed to generate the Gait Profile Score (GPS) for each gait cycle. Tracking potential GPS variations enables detecting changes in gait quality. In this regard, our work is driven by predicting such future variations. Two approaches were considered: signal-based and image-based. The signal-based one uses raw gait cycles, while the image-based one employs a two-dimensional Fast Fourier Transform (2D FFT) representation of gait cycles. Several architectures were developed, and the obtained Area Under the Curve (AUC) was above 0.72 for both approaches. To the best of our knowledge, our study is the first to apply neural networks for gait prediction tasks.

Blind people can actively manipulate virtual objects with a novel tactile device

Frequently in rehabilitation, visually impaired persons are passive agents of exercises with fixed environmental constraints. In fact, a printed tactile map, i.e. a particular picture with a specific spatial arrangement, can usually not be edited. Interaction with map content, instead, facilitates the learning of spatial skills because it exploits mental imagery, manipulation and strategic planning simultaneously. However, it has rarely been applied to maps, mainly because of technological limitations. This study aims to understand if visually impaired people can autonomously build objects that are completely virtual. Specifically, we investigated if a group of twelve blind persons, with a wide age range, could exploit mental imagery to interact with virtual content and actively manipulate it by means of a haptic device. The device is mouse-shaped and designed to jointly perceive, with one finger only, local tactile height and inclination cues of arbitrary scalar fields. Spatial information can be mentally constructed by integrating local tactile cues, given by the device, with global proprioceptive cues, given by hand and arm motion. The experiment consisted of a bi-manual task, in which one hand explored some basic virtual objects and the other hand acted on a keyboard to change the position of one object in real-time. The goal was to merge basic objects into more complex objects, like a puzzle. The experiment spanned different resolutions of the tactile information. We measured task accuracy, efficiency, usability and execution time. The average accuracy in solving the puzzle was 90.5%. Importantly, accuracy was linearly predicted by efficiency, measured as the number of moves needed to solve the task. Subjective parameters linked to usability and spatial resolutions did not predict accuracy; gender modulated the execution time, with men being faster than women. Overall, we show that building purely virtual tactile objects is possible in absence of vision and that the process is measurable and achievable in partial autonomy. Introducing virtual tactile graphics in rehabilitation protocols could facilitate the stimulation of mental imagery, a basic element for the ability to orient in space. The behavioural variable introduced in the current study can be calculated after each trial and therefore could be used to automatically measure and tailor protocols to specific user needs. In perspective, our experimental setup can inspire remote rehabilitation scenarios for visually impaired people.

Overview on wearable sensors for the management of Parkinson's disease

Parkinson's disease (PD) is affecting about 1.2 million patients in Europe with a prevalence that is expected to have an exponential increment, in the next decades. This epidemiological evolution will be challenged by the low number of neurologists able to deliver expert care for PD. As PD is better recognized, there is an increasing demand from patients for rigorous control of their symptoms and for therapeutic education. In addition, the highly variable nature of symtoms between patients and the fluctuations within the same patient requires innovative tools to help doctors and patients monitor the disease in their usual living environment and adapt treatment in a more relevant way. Nowadays, there are various body-worn sensors (BWS) proposed to monitor parkinsonian clinical features, such as motor fluctuations, dyskinesia, tremor, bradykinesia, freezing of gait (FoG) or gait disturbances. BWS have been used as add-on tool for patients' management or research purpose. Here, we propose a practical anthology, summarizing the characteristics of the most used BWS for PD patients in Europe, focusing on their role as tools to improve treatment management. Consideration regarding the use of technology to monitor non-motor features is also included. BWS obviously offer new opportunities for improving management strategy in PD but their precise scope of use in daily routine care should be clarified.

An Interpretable Deep Learning Optimized Wearable Daily Detection System for Parkinson's Disease

Walking detection in the daily life of patients with Parkinson's disease (PD) is of great significance for tracking the progress of the disease. This study aims to implement an accurate, objective, and passive detection algorithm optimized based on an interpretable deep learning architecture for the daily walking of patients with PD and to explore the most representative spatiotemporal motor features. Five inertial measurement units attached to the wrist, ankle, and waist are used to collect motion data from 100 subjects during a 10-meter walking test. The raw data of each sensor are subjected to the continuous wavelet transform to train the classification model of the constructed 6-channel convolutional neural network (CNN). The results show that the sensor located at the waist has the best classification performance with an accuracy of 98.01%±0.85% and the area under the receiver operating characteristic curve (AUC) of 0.9981±0.0017 under ten-fold cross-validation. The gradient-weighted class activation mapping shows that the feature points with greater contribution to PD were concentrated in the lower frequency band (0.5~3Hz) compared with healthy controls. The visual maps of the 3D CNN show that only three out of the six time series have a greater contribution, which is used as a basis to further optimize the model input, greatly reducing the raw data processing costs (50%) while ensuring its performance (AUC=0.9929±0.0019). To the best of our knowledge, this is the first study to consider the visual interpretation-based optimization of an intelligent classification model in the intelligent diagnosis of PD.

Smart ankle bracelet-laser device to improve gait and detect freezing of gait in Parkinsonism patients: a case series

Freezing of gait (FOG) is one of the most disabling symptoms of Parkinsonism. Moreover, it does not respond well to medication. Visual cues have been shown to alleviate FOG in Parkinsonism; however, their efficacy is inconsistent. Currently, most mobile cueing devices are used as an open-loop cueing system, which requires manual control to enable constant visual cues. Thus, such devices may not be suitable for some people, especially those who have attention deficits. In addition, objective measurements of FOG in real-life situations remain challenging. Therefore, we developed a smart-ankle laser as a closed-loop cueing system that can detect the patient's walking pattern and automatically project a laser line that follows each walking step, thus requires less attention. Real-time motion was also recorded within the device for FOG measurement. We studied the efficacy of the device in three Parkinsonism patients with FOG (one man and two women, aged 58-76 years) immediately after use and two patients at 1-week follow-up. Gait speed, Timed Up and Go test performance, stride length, and % FOG improved with the use of the laser, without adverse effects.

Pediatric powered mobility training: powered wheelchair versus simulator-based practice

METHOD

Participants included 30 children and adolescents (23 males, 13 females) with cerebral palsy and other neuromuscular diseases, aged 6-18. Data were collected and compared at baseline and after 12 weeks of home-based practice via a powered wheelchair or a simulator. Powered mobility ability was determined by the Powered Mobility Program (PMP), the Israel Ministry of Health's Powered Mobility Proficiency Test (PM-PT) and the Assessment of Learning Powered Mobility (ALP).

RESULTS

All participants practiced for the required amount of time and both groups reported a similar user experience. Both groups achieved significant improvement following the practice period as assessed by the PMP and PM-PT assessments, with no significant differences between them. A significant improvement was found in the ALP assessment outcomes for the powered wheelchair group only.

CONCLUSIONS

This is the first study, to our knowledge, that compares two different wheelchair training methods. Simulator-based practice is an effective training option for powered mobility for children with physical disabilities aged 6-18 years old, demonstrating that it is possible to provide driving skill practice opportunities safe, controlled environments.

Effectiveness of the "Evidence-Based Scientific Exercise Guidelines" in Increasing Cardiorespiratory Fitness, Cardiometabolic Health, and Muscle Strength in Acute Spinal Cord Injury Rehabilitation: A Systematic Review

Objective

To determine the effect of exercise and physical activity interventions that meet current guideline recommendations on cardiorespiratory fitness, cardiometabolic health, and muscle strength in adults in the acute stage (<1 year post onset) of spinal cord injury (SCI) rehabilitation.

Data Sources

Six electronic databases (PubMed, CINAHL, SPORTDiscus, Google Scholar, National Institute Clinical Excellence, World Health Organization) were searched (January 2016-March 2022) to extend a previously published review.

Study Selection

Included studies implemented exercise interventions in the acute stage of SCI rehabilitation participants which met the exercise guidelines and measured cardiorespiratory fitness, cardiometabolic health, and strength outcomes.

Data Extraction

Titles and abstracts were screened against eligibility criteria and duplicates removed using EndNote X8. Full texts were independently assessed and results presented in a Preferred Reporting Items for Systematic Reviews and Meta-Analyses flowchart. Data extraction was completed on included studies by 2 reviewers (L.R. and V.B.) using a modified Cochrane Group form.

Data Synthesis

Data were synthesized, appraised using the Modified Downs & Black checklist and presented in narrative and tabular format. This review was registered on PROSPERO (Register ID:CRD42021249441). Of the 1255 studies, 4 were included, featuring 108 total participants <1-year post-SCI. Functional electrical stimulation cycle ergometry reduced muscle atrophy after 3 months training and increased lean body mass after 6 months. Resistance training increased muscle peak torque, perceived muscle strength and function. Aerobic exercise interventions did not increase cardiorespiratory fitness.

Conclusions

Interventions meeting the exercise guidelines did not increase cardiorespiratory fitness but were shown to improve cardiometabolic health and perceived muscle strength and function in adults in the acute stage of SCI rehabilitation. Further empirical research using standardized outcome measures are required to explore the effectiveness of aerobic exercise and strengthening interventions in acute stage of SCI rehabilitation to support the development of exercise guidelines.

Challenges and advances in the use of wearable sensors for lower extremity biomechanics

The use of wearable sensors for the collection of lower extremity biomechanical data is increasing in popularity, in part due to the ease of collecting data and the ability to capture movement outside of traditional biomechanics laboratories. Consequently, an increasing number of researchers are facing the challenges that come with utilizing the data captured by wearable sensors. These challenges include identifying/calculating meaningful measures from unfamiliar data types (measures of acceleration and angular velocity instead of positions and joint angles), defining sensor-to-segment alignments for calculating traditional biomechanics metrics, using reduced sensor sets and machine learning to predict unmeasured signals, making decisions about when and how to make algorithms freely available, and developing or replicating methods to perform basic processing tasks such as recognizing activities of interest or identifying gait events. In this perspective article, we present our own approaches to common challenges in lower extremity biomechanics research using wearable sensors and share our perspectives on approaching several of these challenges. We present these perspectives with examples that come mostly from gait research, but many of the concepts also apply to other contexts where researchers may use wearable sensors. Our goal is to introduce common challenges to new users of wearable sensors, and to promote dialogue amongst experienced users towards best practices.

Can post stroke walking improve via telerehabilitation? A systematic review in adults with stroke

Objectives

The purpose of this systematic review is to analyze primary studies investigating the effects of telerehabilitation on walking outcomes for the treatment of adult stroke survivors.

Methods

Data sources included PubMed, Embase and CINAHL searched until August 2022, using combinations of several keywords such as "telerehabilitation", "stroke", and "gait". Studies were required to have bidirectional form of videoconferencing with assessor presence, and include assessment of walking function (speed, endurance and/or balance). Data extraction was performed from each full text by one author, and quality and bias were assessed using the Physiotherapy Evidence Database (PEDro).

Results

Eight studies involving 248 participants met the inclusion criteria. Seven reported significant improvements in outcomes of balance and two showed improvements in endurance after telerehabilitation. Two studies observed greater balance improvements in the telerehabilitation group compared to control and/or in-person therapy. Differences in frequency, training duration, intervention type, and absence of an in-person therapy control group were identified as causes of variation between studies.

Conclusions

The effectiveness of telerehabilitation as a mode of therapy for walking could not be definitively determined due to the limited number of studies that directly measured walking speed or endurance. However, strong evidence was found for the use of telerehabilitation for balance improvements, which has implications for walking recovery.

Impact statement

Telerehabilitation appears to be safe, feasible and demonstrated high adherence. Our results highlighted limited studies using real-time supervision to administer telerehabilitation and lack of studies focusing on outcomes of walking speed and endurance, needed to fully determine the role of telerehabilitation for gait recovery.

Systematic review registration number

PROSPERO number CRD42021238197.

Closed-Loop Adaptive Deep Brain Stimulation in Parkinson's Disease: Procedures to Achieve It and Future Perspectives

Parkinson's disease (PD) is a neurodegenerative disease with a heavy burden on patients, families, and society. Deep brain stimulation (DBS) can improve the symptoms of PD patients for whom medication is insufficient. However, current open-loop uninterrupted conventional DBS (cDBS) has inherent limitations, such as adverse effects, rapid battery consumption, and a need for frequent parameter adjustment. To overcome these shortcomings, adaptive DBS (aDBS) was proposed to provide responsive optimized stimulation for PD. This topic has attracted scientific interest, and a growing body of preclinical and clinical evidence has shown its benefits. However, both achievements and challenges have emerged in this novel field. To date, only limited reviews comprehensively analyzed the full framework and procedures for aDBS implementation. Herein, we review current preclinical and clinical data on aDBS for PD to discuss the full procedures for its achievement and to provide future perspectives on this treatment.

Dealing with the heterogeneous presentations of freezing of gait: how reliable are the freezing index and heart rate for freezing detection?

BACKGROUND

Freezing of gait (FOG) is an unpredictable gait arrest that hampers the lives of 40% of people with Parkinson's disease. Because the symptom is heterogeneous in phenotypical presentation (it can present as trembling/shuffling, or akinesia) and manifests during various circumstances (it can be triggered by e.g. turning, passing doors, and dual-tasking), it is particularly difficult to detect with motion sensors. The freezing index (FI) is one of the most frequently used accelerometer-based methods for FOG detection. However, it might not adequately distinguish FOG from voluntary stops, certainly for the akinetic type of FOG. Interestingly, a previous study showed that heart rate signals could distinguish FOG from stopping and turning movements. This study aimed to investigate for which phenotypes and evoking circumstances the FI and heart rate might provide reliable signals for FOG detection.

METHODS

Sixteen people with Parkinson's disease and daily freezing completed a gait trajectory designed to provoke FOG including turns, narrow passages, starting, and stopping, with and without a cognitive or motor dual-task. We compared the FI and heart rate of 378 FOG events to baseline levels, and to stopping and normal gait events (i.e. turns and narrow passages without FOG) using mixed-effects models. We specifically evaluated the influence of different types of FOG (trembling vs akinesia) and triggering situations (turning vs narrow passages; no dual-task vs cognitive dual-task vs motor dual-task) on both outcome measures.

RESULTS

The FI increased significantly during trembling and akinetic FOG, but increased similarly during stopping and was therefore not significantly different from FOG. In contrast, heart rate change during FOG was for all types and during all triggering situations statistically different from stopping, but not from normal gait events.

CONCLUSION

When the power in the locomotion band (0.5-3 Hz) decreases, the FI increases and is unable to specify whether a stop is voluntary or involuntary (i.e. trembling or akinetic FOG). In contrast, the heart rate can reveal whether there is the intention to move, thus distinguishing FOG from stopping. We suggest that the combination of a motion sensor and a heart rate monitor may be promising for future FOG detection.

Robust walking control of a lower limb rehabilitation exoskeleton coupled with a musculoskeletal model via deep reinforcement learning

BACKGROUND

Few studies have systematically investigated robust controllers for lower limb rehabilitation exoskeletons (LLREs) that can safely and effectively assist users with a variety of neuromuscular disorders to walk with full autonomy. One of the key challenges for developing such a robust controller is to handle different degrees of uncertain human-exoskeleton interaction forces from the patients. Consequently, conventional walking controllers either are patient-condition specific or involve tuning of many control parameters, which could behave unreliably and even fail to maintain balance.

METHODS

We present a novel, deep neural network, reinforcement learning-based robust controller for a LLRE based on a decoupled offline human-exoskeleton simulation training with three independent networks, which aims to provide reliable walking assistance against various and uncertain human-exoskeleton interaction forces. The exoskeleton controller is driven by a neural network control policy that acts on a stream of the LLRE's proprioceptive signals, including joint kinematic states, and subsequently predicts real-time position control targets for the actuated joints. To handle uncertain human interaction forces, the control policy is trained intentionally with an integrated human musculoskeletal model and realistic human-exoskeleton interaction forces. Two other neural networks are connected with the control policy network to predict the interaction forces and muscle coordination. To further increase the robustness of the control policy to different human conditions, we employ domain randomization during training that includes not only randomization of exoskeleton dynamics properties but, more importantly, randomization of human muscle strength to simulate the variability of the patient's disability. Through this decoupled deep reinforcement learning framework, the trained controller of LLREs is able to provide reliable walking assistance to patients with different degrees of neuromuscular disorders without any control parameter tuning.

RESULTS AND CONCLUSION

A universal, RL-based walking controller is trained and virtually tested on a LLRE system to verify its effectiveness and robustness in assisting users with different disabilities such as passive muscles (quadriplegic), muscle weakness, or hemiplegic conditions without any control parameter tuning. Analysis of the RMSE for joint tracking, CoP-based stability, and gait symmetry shows the effectiveness of the controller. An ablation study also demonstrates the strong robustness of the control policy under large exoskeleton dynamic property ranges and various human-exoskeleton interaction forces. The decoupled network structure allows us to isolate the LLRE control policy network for testing and sim-to-real transfer since it uses only proprioception information of the LLRE (joint sensory state) as the input. Furthermore, the controller is shown to be able to handle different patient conditions without the need for patient-specific control parameter tuning.

Combining robot-assisted therapy with virtual reality or using it alone? A systematic review on health-related quality of life in neurological patients

BACKGROUND

In the field of neurorehabilitation, robot-assisted therapy (RAT) and virtual reality (VR) have so far shown promising evidence on multiple motor and functional outcomes. The related effectiveness on patients' health-related quality of life (HRQoL) has been investigated across neurological populations but still remains unclear. The present study aimed to systematically review the studies investigating the effects of RAT alone and with VR on HRQoL in patients with different neurological diseases.

METHODS

A systematic review of the studies evaluating the impact of RAT alone and combined with VR on HRQoL in patients affected by neurological diseases (i.e., stroke, multiple sclerosis, spinal cord injury, Parkinson's Disease) was conducted according to PRISMA guidelines. Electronic searches of PubMed, Web of Science, Cochrane Library, CINAHL, Embase, and PsychINFO (2000-2022) were performed. Risk of bias was evaluated through the National Institute of Health Quality Assessment Tool. Descriptive data regarding the study design, participants, intervention, rehabilitation outcomes, robotic device typology, HRQoL measures, non-motor factors concurrently investigated, and main results were extracted and meta-synthetized.

RESULTS

The searches identified 3025 studies, of which 70 met the inclusion criteria. An overall heterogeneous configuration was found regarding the study design adopted, intervention procedures and technological devices implemented, rehabilitation outcomes (i.e., related to both upper and lower limb impairment), HRQoL measures administered, and main evidence. Most of the studies reported significant effects of both RAT and RAT plus VR on patients HRQoL, whether they adopted generic or disease-specific HRQoL measures. Significant post-intervention within-group changes were mainly found across neurological populations, while fewer studies reported significant between-group comparisons, and then, mostly in patients with stroke. Longitudinal investigations were also observed (up to 36 months), but significant longitudinal effects were exclusively found in patients with stroke or multiple sclerosis. Finally, concurrent evaluations on non-motor outcomes beside HRQoL included cognitive (i.e., memory, attention, executive functions) and psychological (i.e., mood, satisfaction with the treatment, device usability, fear of falling, motivation, self-efficacy, coping, and well-being) variables.

CONCLUSIONS

Despite the heterogeneity observed among the studies included, promising evidence was found on the effectiveness of RAT and RAT plus VR on HRQoL. However, further targeted short- and long-term investigations, are strongly recommended for specific HRQoL subcomponents and neurological populations, through the adoption of defined intervention procedures and disease-specific assessment methodology.

An Explainable Spatial-Temporal Graphical Convolutional Network to Score Freezing of Gait in Parkinsonian Patients

Freezing of gait (FOG) is a poorly understood heterogeneous gait disorder seen in patients with parkinsonism which contributes to significant morbidity and social isolation. FOG is currently measured with scales that are typically performed by movement disorders specialists (i.e., MDS-UPDRS), or through patient completed questionnaires (N-FOG-Q) both of which are inadequate in addressing the heterogeneous nature of the disorder and are unsuitable for use in clinical trials The purpose of this study was to devise a method to measure FOG objectively, hence improving our ability to identify it and accurately evaluate new therapies. A major innovation of our study is that it is the first study of its kind that uses the largest sample size (>30 h, N = 57) in order to apply explainable, multi-task deep learning models for quantifying FOG over the course of the medication cycle and at varying levels of parkinsonism severity. We trained interpretable deep learning models with multi-task learning to simultaneously score FOG (cross-validated F1 score 97.6%), identify medication state (OFF vs. ON levodopa; cross-validated F1 score 96.8%), and measure total PD severity (MDS-UPDRS-III score prediction error ≤ 2.7 points) using kinematic data of a well-characterized sample of N = 57 patients during levodopa challenge tests. The proposed model was able to explain how kinematic movements are associated with each FOG severity level that were highly consistent with the features, in which movement disorders specialists are trained to identify as characteristics of freezing. Overall, we demonstrate that deep learning models' capability to capture complex movement patterns in kinematic data can automatically and objectively score FOG with high accuracy. These models have the potential to discover novel kinematic biomarkers for FOG that can be used for hypothesis generation and potentially as clinical trial outcome measures.

Mobility recorded by wearable devices and gold standards: the Mobilise-D procedure for data standardization

Wearable devices are used in movement analysis and physical activity research to extract clinically relevant information about an individual's mobility. Still, heterogeneity in protocols, sensor characteristics, data formats, and gold standards represent a barrier for data sharing, reproducibility, and external validation. In this study, we aim at providing an example of how movement data (from the real-world and the laboratory) recorded from different wearables and gold standard technologies can be organized, integrated, and stored. We leveraged on our experience from a large multi-centric study (Mobilise-D) to provide guidelines that can prove useful to access, understand, and re-use the data that will be made available from the study. These guidelines highlight the encountered challenges and the adopted solutions with the final aim of supporting standardization and integration of data in other studies and, in turn, to increase and facilitate comparison of data recorded in the scientific community. We also provide samples of standardized data, so that both the structure of the data and the procedure can be easily understood and reproduced.

The development of a home-based technology to improve gait in people with Parkinson's disease: a feasibility study

BACKGROUND

People with Parkinson's disease (PwP) may experience gait impairment and freezing of gait (FOG), a major cause of falls. External cueing, including visual (e.g., spaced lines on the floor) and auditory (e.g., rhythmic metronome beats) stimuli, are considered effective in alleviating mobility deficits and FOG. Currently, there is a need for a technology that delivers automatic, individually adjusted cues in the homes of PwP. The aims of this feasibility study were to describe the first step toward the development of a home-based technology that delivers external cues, test its effect on gait, and assess user experience.

METHODS

Iterative system development was performed by our multidisciplinary team. The system was designed to deliver visual and auditory cues: light stripes projected on the floor and metronome beats, separately. Initial testing was performed using the feedback of five healthy elderly individuals on the cues' clarity (clear visibility of the light stripes and the sound of metronome beats) and discomfort experienced. A pilot study was subsequently conducted in the homes of 15 PwP with daily FOG. We measured participants' walking under three conditions: baseline (with no cues), walking with light stripes, and walking to metronome beats. Outcome measures included step length and step time. User experience was also captured in semi-structured interviews.

RESULTS

Repeated-measures ANOVA of gait assessment in PwP revealed that light stripes significantly improved step length (p = 0.009) and step time (p = 0.019) of PwP. No significant changes were measured in the metronome condition. PwP reported that both cueing modalities improved their gait, confidence, and stability. Most PwP did not report any discomfort in either modality and expressed a desire to have such a technology in their homes. The metronome was preferred by the majority of participants.

CONCLUSIONS

This feasibility study demonstrated the usability and potential effect of a novel cueing technology on gait, and represents an important first step toward the development of a technology aimed to prevent FOG by delivering individually adjusted cues automatically. A further full-scale study is needed. Trial registration This study was registered in ClinicalTrials.gov at 1/2/2022 NCT05211687.

An explainable spatial-temporal graphical convolutional network to score freezing of gait in parkinsonian patients

Freezing of gait (FOG) is a poorly understood heterogeneous gait disorder seen in patients with parkinsonism which contributes to significant morbidity and social isolation. FOG is currently measured with scales that are typically performed by movement disorders specialists (ie. MDS-UPDRS), or through patient completed questionnaires (N-FOG-Q) both of which are inadequate in addressing the heterogeneous nature of the disorder and are unsuitable for use in clinical trials The purpose of this study was to devise a method to measure FOG objectively, hence improving our ability to identify it and accurately evaluate new therapies. We trained interpretable deep learning models with multi-task learning to simultaneously score FOG (cross-validated F1 score 97.6%), identify medication state (OFF vs. ON levodopa; cross-validated F1 score 96.8%), and measure total PD severity (MDS-UPDRS-III score prediction error ≤ 2.7 points) using kinematic data of a well-characterized sample of N=57 patients during levodopa challenge tests. The proposed model was able to identify kinematic features associated with each FOG severity level that were highly consistent with the features that movement disorders specialists are trained to identify as characteristic of freezing. In this work, we demonstrate that deep learning models' capability to capture complex movement patterns in kinematic data can automatically and objectively score FOG with high accuracy. These models have the potential to discover novel kinematic biomarkers for FOG that can be used for hypothesis generation and potentially as clinical trial outcome measures.

Recent trends in wearable device used to detect freezing of gait and falls in people with Parkinson's disease: A systematic review

Background

The occurrence of freezing of gait (FOG) is often observed in moderate to last-stage Parkinson's disease (PD), leading to a high risk of falls. The emergence of the wearable device has offered the possibility of FOG detection and falls of patients with PD allowing high validation in a low-cost way.

Objective

This systematic review seeks to provide a comprehensive overview of existing literature to establish the forefront of sensors type, placement and algorithm to detect FOG and falls among patients with PD.

Methods

Two electronic databases were screened by title and abstract to summarize the state of art on FOG and fall detection with any wearable technology among patients with PD. To be eligible for inclusion, papers were required to be full-text articles published in English, and the last search was completed on September 26, 2022. Studies were excluded if they; (i) only examined cueing function for FOG, (ii) only used non-wearable devices to detect or predict FOG or falls, and (iii) did not provide sufficient details about the study design and results. A total of 1,748 articles were retrieved from two databases. However, only 75 articles were deemed to meet the inclusion criteria according to the title, abstract and full-text reviewed. Variable was extracted from chosen research, including authorship, details of the experimental object, type of sensor, device location, activities, year of publication, evaluation in real-time, the algorithm and detection performance.

Results

A total of 72 on FOG detection and 3 on fall detection were selected for data extraction. There were wide varieties of the studied population (from 1 to 131), type of sensor, placement and algorithm. The thigh and ankle were the most popular device location, and the combination of accelerometer and gyroscope was the most frequently used inertial measurement unit (IMU). Furthermore, 41.3% of the studies used the dataset as a resource to examine the validity of their algorithm. The results also showed that increasingly complex machine-learning algorithms had become the trend in FOG and fall detection.

Conclusion

These data support the application of the wearable device to access FOG and falls among patients with PD and controls. Machine learning algorithms and multiple types of sensors have become the recent trend in this field. Future work should consider an adequate sample size, and the experiment should be performed in a free-living environment. Moreover, a consensus on provoking FOG/fall, methods of assessing validity and algorithm are necessary.Systematic Review Registration: PROSPERO, identifier CRD42022370911.

The Ziegler Test Is Reliable and Valid for Measuring Freezing of Gait in People With Parkinson Disease

OBJECTIVE

The purpose of this study was to determine interrater and test-retest reliability of the Ziegler test to measure freezing of gait (FOG) severity in people with Parkinson disease. Secondary aims were to evaluate test validity and explore Ziegler test duration as a proxy FOG severity measure.

METHODS

Physical therapists watched 36 videos of people with Parkinson disease and FOG perform the Ziegler test and rated FOG severity using the rating scale in real time. Two researchers rated 12 additional videos and repeated the ratings at least 1 week later. Interrater and test-retest reliability were calculated using intraclass correlation coefficients (ICCs). Bland-Altman plots were used to visualize agreement between the researchers for test-retest reliability. Correlations between the Ziegler scores, Ziegler test duration, and percentage of time frozen (based on video annotations) were determined using Pearson r.

RESULTS

Twenty-four physical therapists participated. Overall, the Ziegler test showed good interrater (ICC2,1 = 0.80; 95% CI = 0.65-0.92) and excellent test-retest (ICC3,1 = 0.91; 95% CI = 0.82-0.96) reliability when used to measure FOG. It was also a valid measure, with a high correlation (r = 0.72) between the scores and percentage of time frozen. Ziegler test duration was moderately correlated (r = 0.67) with percentage of time frozen and may be considered a proxy FOG severity measure.

CONCLUSION

The Ziegler test is a reliable and valid tool to measure FOG when used by physical therapists in real time. Ziegler test duration may be used as a proxy for measuring FOG severity.

IMPACT

Despite FOG being a significant contributor to falls and poor mobility in people with Parkinson disease, current tools to assess FOG are either not suitably responsive or too resource intensive for use in clinical settings. The Ziegler test is a reliable and valid measure of FOG, suitable for clinical use, and may be used by physical therapists regardless of their level of clinical experience.

Suitability of a Low-Cost Wearable Sensor to Assess Turning in Healthy Adults

Background: Turning is a complex measure of gait that accounts for over 50% of daily steps. Traditionally, turning has been measured in a research grade laboratory setting, however, there is demand for a low-cost and portable solution to measure turning using wearable technology. This study aimed to determine the suitability of a low-cost inertial sensor-based device (AX6, Axivity) to assess turning, by simultaneously capturing and comparing to a turn algorithm output from a previously validated reference inertial sensor-based device (Opal), in healthy young adults. Methodology: Thirty participants (aged 23.9 ± 4.89 years) completed the following turning protocol wearing the AX6 and reference device: a turn course, a two-minute walk (including 180° turns) and turning in place, alternating 360° turn right and left. Both devices were attached at the lumbar spine, one Opal via a belt, and the AX6 via double sided tape attached directly to the skin. Turning measures included number of turns, average turn duration, angle, velocity, and jerk. Results: Agreement between the outcomes from the AX6 and reference device was good to excellent for all turn characteristics (all ICCs > 0.850) during the turning 360° task. There was good agreement for all turn characteristics (all ICCs > 0.800) during the two-minute walk task, except for moderate agreement for turn angle (ICC 0.683). Agreement for turn outcomes was moderate to good during the turns course (ICCs range; 0.580 to 0.870). Conclusions: A low-cost wearable sensor, AX6, can be a suitable and fit-for-purpose device when used with validated algorithms for assessment of turning outcomes, particularly during continuous turning tasks. Future work needs to determine the suitability and validity of turning in aging and clinical cohorts within low-resource settings.

Association between Severity of Freezing of Gait and Turning Characteristics in People with Parkinson's Disease

For people with Parkinson's disease (PD) with freezing of gait (FOG) (freezers), symptoms mainly exhibit as unilateral motor impairments that may cause difficulty during postural transitions such as turning during daily activities. We investigated the turning characteristics that distinguished freezers among people with PD and analyzed the association between the New Freezing of Gait Questionnaire (NFOGQ) scores and the gait characteristics according to the turning direction for the affected limbs of freezers. The study recruited 57 people with PD (27 freezers, 30 non-freezers). All experiments measured the maximum 180° turning task with the "Off" medication state. Results revealed that the outer ankle range of motion in the direction of the inner step of the more affected limb (IMA) was identified to distinguish freezers and non-freezers (R_N² = 0.735). In addition, higher NFOGQ scores were associated with a more significant anteroposterior root mean square distance of the center of mass in the IMA direction and a greater inner stance phase in the outer step of the more affected limb (OMA) direction; explanatory power was 50.1%. Assessing the maximum speed and turning direction is useful for evaluating the differences in turning characteristics between freezers and non-freezers, which can help define freezers more accurately.

On-Field Deployment and Validation for Wearable Devices

Wearable sensors are an important tool in the study of head acceleration events and head impact injuries in sporting and military activities. Recent advances in sensor technology have improved our understanding of head kinematics during on-field activities; however, proper utilization and interpretation of data from wearable devices requires careful implementation of best practices. The objective of this paper is to summarize minimum requirements and best practices for on-field deployment of wearable devices for the measurement of head acceleration events in vivo to ensure data evaluated are representative of real events and limitations are accurately defined. Best practices covered in this document include the definition of a verified head acceleration event, data windowing, video verification, advanced post-processing techniques, and on-field logistics, as determined through review of the literature and expert opinion. Careful use of best practices, with accurate acknowledgement of limitations, will allow research teams to ensure data evaluated is representative of real events, will improve the robustness of head acceleration event exposure studies, and generally improve the quality and validity of research into head impact injuries.

Motorless cadence control of standard and low duty cycle-patterned neural stimulation intensity extends muscle-driven cycling output after paralysis

Background

Stimulation-driven exercise is often limited by rapid fatigue of the activated muscles. Selective neural stimulation patterns that decrease activated fiber overlap and/or duty cycle improve cycling exercise duration and intensity. However, unequal outputs from independently activated fiber populations may cause large discrepancies in power production and crank angle velocity among pedal revolutions. Enforcing a constant cadence through feedback control of stimulus levels may address this issue and further improve endurance by targeting a submaximal but higher than steady-state exercise intensity.

Methods

Seven participants with paralysis cycled using standard cadence-controlled stimulation (S-Cont). Four of those participants also cycled with a low duty cycle (carousel) cadence-controlled stimulation scheme (C-Cont). S-Cont and C-Cont patterns were compared with conventional maximal stimulation (S-Max). Outcome measures include total work (W), end power (P_end), power fluctuation (PFI), charge accumulation (Q) and efficiency (η). Physiological measurements of muscle oxygenation (SmO₂) and heart rate were also collected with select participants.

Results

At least one cadence-controlled stimulation pattern (S-Cont or C-Cont) improved P_end over S-Max in all participants and increased W in three participants. Both controlled patterns increased Q and η and reduced PFI compared with S-Max and prior open-loop studies. S-Cont stimulation also delayed declines in SmO2 and increased heart rate in one participant compared with S-Max.

Conclusions

Cadence-controlled selective stimulation improves cycling endurance and increases efficiency over conventional stimulation by incorporating fiber groups only as needed to maintain a desired exercise intensity. Closed-loop carousel stimulation also successfully reduces power fluctuations relative to previous open-loop efforts, which will enable neuroprosthesis recipients to better take advantage of duty cycle reducing patterns.

Non-Contact Hand Movement Analysis for Optimal Configuration of Smart Sensors to Capture Parkinson's Disease Hand Tremor

Parkinson’s disease affects millions worldwide with a large rise in expected burden over the coming decades. More easily accessible tools and techniques to diagnose and monitor Parkinson’s disease can improve the quality of life of patients. With the advent of new wearable technologies such as smart rings and watches, this is within reach. However, it is unclear what method for these new technologies may provide the best opportunity to capture the patient-specific severity. This study investigates which locations on the hand can be used to capture and monitor maximal movement/tremor severity. Using a Leap Motion device and custom-made software the volume, velocity, acceleration, and frequency of Parkinson’s (n = 55, all right-handed, majority right-sided onset) patients’ hand locations (25 joints inclusive of all fingers/thumb and the wrist) were captured simultaneously. Distal locations of the right hand, i.e., the ends of fingers and the wrist showed significant trends (p < 0.05) towards having the largest movement velocities and accelerations. The right hand, compared with the left hand, showed significantly greater volumes, velocities, and accelerations (p < 0.01). Supplementary analysis showed that the volumes, acceleration, and velocities had significant correlations (p < 0.001) with clinical MDS-UPDRS scores, indicating the potential suitability of using these metrics for monitoring disease progression. Maximal movements at the distal hand and wrist area indicate that these locations are best suited to capture hand tremor movements and monitor Parkinson’s disease.

Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks

BACKGROUND

Freezing of gait (FOG) is a common and debilitating gait impairment in Parkinson's disease. Further insight into this phenomenon is hampered by the difficulty to objectively assess FOG. To meet this clinical need, this paper proposes an automated motion-capture-based FOG assessment method driven by a novel deep neural network.

METHODS

Automated FOG assessment can be formulated as an action segmentation problem, where temporal models are tasked to recognize and temporally localize the FOG segments in untrimmed motion capture trials. This paper takes a closer look at the performance of state-of-the-art action segmentation models when tasked to automatically assess FOG. Furthermore, a novel deep neural network architecture is proposed that aims to better capture the spatial and temporal dependencies than the state-of-the-art baselines. The proposed network, termed multi-stage spatial-temporal graph convolutional network (MS-GCN), combines the spatial-temporal graph convolutional network (ST-GCN) and the multi-stage temporal convolutional network (MS-TCN). The ST-GCN captures the hierarchical spatial-temporal motion among the joints inherent to motion capture, while the multi-stage component reduces over-segmentation errors by refining the predictions over multiple stages. The proposed model was validated on a dataset of fourteen freezers, fourteen non-freezers, and fourteen healthy control subjects.

RESULTS

The experiments indicate that the proposed model outperforms four state-of-the-art baselines. Moreover, FOG outcomes derived from MS-GCN predictions had an excellent (r = 0.93 [0.87, 0.97]) and moderately strong (r = 0.75 [0.55, 0.87]) linear relationship with FOG outcomes derived from manual annotations.

CONCLUSIONS

The proposed MS-GCN may provide an automated and objective alternative to labor-intensive clinician-based FOG assessment. Future work is now possible that aims to assess the generalization of MS-GCN to a larger and more varied verification cohort.

Competitive motivation increased home use and improved prosthesis self-perception after Cybathlon 2020 for neuromusculoskeletal prosthesis user

Background

Assistive technologies, such as arm prostheses, are intended to improve the quality of life of individuals with physical disabilities. However, certain training and learning is usually required from the user to make these technologies more effective. Moreover, some people can be encouraged to train more through competitive motivation.

Methods

In this study, we investigated if the training for and participation in a competitive event (Cybathlon 2020) could promote behavioral changes in an individual with upper limb amputation (the pilot). We defined behavioral changes as the active time while his prosthesis was actuated, ratio of opposing and simultaneous movements, and the pilot’s ability to finely modulate his movement speeds. The investigation was based on extensive home-use data from the period before, during and after the Cybathlon 2020 competition.

Results

Relevant behavioral changes were found from both quantitative and qualitative analyses. The pilot’s home use of his prosthesis nearly doubled in the period before the Cybathlon, and remained 66% higher than baseline after the competition. Moreover, he improved his speed modulation when controlling his prosthesis, and he learned and routinely operated new movements in the prosthesis (wrist rotation) at home. Additionally, as confirmed by semi-structured interviews, his self-perception of the prosthetic arm and its functionality also improved.

Conclusions

An event like the Cybathlon may indeed promote behavioral changes in how competitive individuals with amputation use their prostheses. Provided that the prosthesis is suitable in terms of form and function for both competition and at-home daily use, daily activities can become opportunities for training, which in turn can improve prosthesis function and create further opportunities for daily use. Moreover, these changes appeared to remain even well after the event, albeit relevant only for individuals who continue using the technology employed in the competition.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12984-022-01024-4.

Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism

A challenging task for the biological neural signal-based human-exoskeleton interface is to achieve accurate lower limb movement prediction of patients with hemiplegia in rehabilitation training scenarios. The human-exoskeleton interface based on single-modal biological signals such as electroencephalogram (EEG) is currently not mature in predicting movements, due to its unreliability. The multimodal human-exoskeleton interface is a very novel solution to this problem. This kind of interface normally combines the EEG signal with surface electromyography (sEMG) signal. However, their use for the lower limb movement prediction is still limited—the connection between sEMG and EEG signals and the deep feature fusion between them are ignored. In this article, a Dense con-attention mechanism-based Multimodal Enhance Fusion Network (DMEFNet) is proposed for predicting lower limb movement of patients with hemiplegia. The DMEFNet introduces the con-attention structure to extract the common attention between sEMG and EEG signal features. To verify the effectiveness of DMEFNet, an sEMG and EEG data acquisition experiment and an incomplete asynchronous data collection paradigm are designed. The experimental results show that DMEFNet has a good movement prediction performance in both within-subject and cross-subject situations, reaching an accuracy of 82.96 and 88.44%, respectively.

Musculoskeletal modelling and simulation of oil palm fresh fruit bunch harvesting

Oil palm harvesting is a labor-intensive activity and yet it was rarely investigated. Studies showed that complementing human motion analysis with musculoskeletal modelling and simulation can provide valuable information about the dynamics of the joints and muscles. Therefore, this study aims to be the first to create and evaluate an upper extremity musculoskeletal model of the oil palm harvesting motion and to assess the associated Musculoskeletal Disorder (MSD) risk. Tests were conducted at a Malaysia oil palm plantation. Six Inertial Measurement Units (IMU) and Surface Electromyography (sEMG) were used to collect kinematics of the back, shoulder and elbow joints and to measure the muscle activations of longissimus, multifidus, biceps and triceps. The simulated joint angles and muscle activations were validated against the commercial motion capture tool and sEMG, respectively. The muscle forces, joint moments and activations of rectus abdominis, iliocostalis, external oblique, internal oblique and latissimus dorsi were investigated. Findings showed that the longissimus, iliocostalis and rectus abdominis were the primary muscles relied on during harvesting. The harvesters were exposed to a higher risk of MSD while performing back flexion and back rotation. These findings provide insights into the dynamical behavior of the upper extremity muscles and joints that can potentially be used to derive ways to improve the ergonomics of oil palm harvesting, minimize the MSD risk and to design and develop assistive engineering and technological devices or tools for this activity.

A low-dimensional representation of arm movements and hand grip forces in post-stroke individuals

Characterizing post-stroke impairments in the sensorimotor control of arm and hand is essential to better understand altered mechanisms of movement generation. Herein, we used a decomposition algorithm to characterize impairments in end-effector velocity and hand grip force data collected from an instrumented functional task in 83 healthy control and 27 chronic post-stroke individuals with mild-to-moderate impairments. According to kinematic and kinetic raw data, post-stroke individuals showed reduced functional performance during all task phases. After applying the decomposition algorithm, we observed that the behavioural data from healthy controls relies on a low-dimensional representation and demonstrated that this representation is mostly preserved post-stroke. Further, it emerged that reduced functional performance post-stroke correlates to an abnormal variance distribution of the behavioural representation, except when reducing hand grip forces. This suggests that the behavioural repertoire in these post-stroke individuals is mostly preserved, thereby pointing towards therapeutic strategies that optimize movement quality and the reduction of grip forces to improve performance of daily life activities post-stroke.

Stepping up to meet the challenge of freezing of gait in Parkinson's disease

There has been a growing appreciation for freezing of gait as a disabling symptom that causes a significant burden in Parkinson’s disease. Previous research has highlighted some of the key components that underlie the phenomenon, but these reductionist approaches have yet to lead to a paradigm shift resulting in the development of novel treatment strategies. Addressing this issue will require greater integration of multi-modal data with complex computational modeling, but there are a number of critical aspects that need to be considered before embarking on such an approach. This paper highlights where the field needs to address current gaps and shortcomings including the standardization of definitions and measurement, phenomenology and pathophysiology, as well as considering what available data exist and how future studies should be constructed to achieve the greatest potential to better understand and treat this devastating symptom.

A Multi-Modal Analysis of the Freezing of Gait Phenomenon in Parkinson’s Disease

Background: Freezing of Gait (FOG) is one of the most disabling motor complications of Parkinson’s disease, and consists of an episodic inability to move forward, despite the intention to walk. FOG increases the risk of falls and reduces the quality of life of patients and their caregivers. The phenomenon is difficult to appreciate during outpatients visits; hence, its automatic recognition is of great clinical importance. Many types of sensors and different locations on the body have been proposed. However, the advantages of a multi-sensor configuration with respect to a single-sensor one are not clear, whereas this latter would be advisable for use in a non-supervised environment. Methods: In this study, we used a multi-modal dataset and machine learning algorithms to perform different classifications between FOG and non-FOG periods. Moreover, we explored the relevance of features in the time and frequency domains extracted from inertial sensors, electroencephalogram and skin conductance. We developed both a subject-independent and a subject-dependent algorithm, considering different sensor subsets. Results: The subject-independent and subject-dependent algorithms yielded accuracies of 85% and 88% in the leave-one-subject-out and leave-one-task-out test, respectively. Results suggest that the inertial sensors positioned on the lower limb are generally the most significant in recognizing FOG. Moreover, the performance impairment experienced when using a single tibial accelerometer instead of the optimal multi-modal configuration is limited to 2–3%. Conclusions: The achieved results disclose the possibility of getting a good FOG recognition using a minimally invasive set-up made of a single inertial sensor. This is very significant in the perspective of implementing a long-term monitoring of patients in their homes, during activities of daily living.