Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review

Channel Selection for Gesture Recognition Using Force Myography: A Universal Model for Gesture Measurement Points

Gesture recognition has emerged as a significant research domain in computer vision and human-computer interaction. One of the key challenges in gesture recognition is how to select the most useful channels that can effectively represent gesture movements. In this study, we have developed a channel selection algorithm that determines the number and placement of sensors that are critical to gesture classification. To validate this algorithm, we constructed a Force Myography (FMG)-based signal acquisition system. The algorithm considers each sensor as a distinct channel, with the most effective channel combinations and recognition accuracy determined through assessing the correlation between each channel and the target gesture, as well as the redundant correlation between different channels. The database was created by collecting experimental data from 10 healthy individuals who wore 16 sensors to perform 13 unique hand gestures. The results indicate that the average number of channels across the 10 participants was 3, corresponding to an 75% decrease in the initial channel count, with an average recognition accuracy of 94.46%. This outperforms four widely adopted feature selection algorithms, including Relief-F, mRMR, CFS, and ILFS. Moreover, we have established a universal model for the position of gesture measurement points and verified it with an additional five participants, resulting in an average recognition accuracy of 96.3%. This study provides a sound basis for identifying the optimal and minimum number and location of channels on the forearm and designing specialized arm rings with unique shapes.

Can We Target Close Therapeutic Goals in the Gait Re-Education Algorithm for Stroke Patients at the Beginning of the Rehabilitation Process?

(1) Background: The study aimed to determine the most important activities of the knee joints related to gait re-education in patients in the subacute period after a stroke. We focused on the tests that a physiotherapist could perform in daily clinical practice. (2) Methods: Twenty-nine stroke patients (SG) and 29 healthy volunteers (CG) were included in the study. The patients underwent the 5-meter walk test (5mWT) and the Timed Up and Go test (TUG). Tests such as step up, step down, squat, step forward, and joint position sense test (JPS) were also performed, and the subjects were assessed using wireless motion sensors. (3) Results: We observed significant differences in the time needed to complete the 5mWT and TUG tests between groups. The results obtained in the JPS show a significant difference between the paretic and the non-paretic limbs compared to the CG group. A significantly smaller range of knee joint flexion (ROM) was observed in the paretic limb compared to the non-paretic and control limbs in the step down test and between the paretic and non-paretic limbs in the step forward test. (4) Conclusions: The described functional tests are useful in assessing a stroke patient's motor skills and can be performed in daily clinical practice.

Utility and usability of a wearable system and progressive-challenge cued exercise program for encouraging use of the more involved arm at-home after stroke-a feasibility study with case reports

BACKGROUND

Understanding the role of adherence to home exercise programs for survivors of stroke is critical to ensure patients perform prescribed exercises and maximize effectiveness of recovery.

METHODS

Survivors of hemiparetic stroke with impaired motor function were recruited into a 7-day study designed to test the utility and usability of a low-cost wearable system and progressive-challenge cued exercise program for encouraging graded-challenge exercise at-home. The wearable system comprised two wrist-worn MetaMotionR+ activity monitors and a custom smartphone app. The progressive-challenge cued exercise program included high-intensity activities (one repetition every 30 s) dosed at 1.5 h per day, embedded within 8 h of passive activity monitoring per day. Utility was assessed using measures of system uptime and cue response rate. Usability and user experience were assessed using well-validated quantitative surveys of system usability and user experience. Self-efficacy was assessed at the end of each day on a visual analog scale that ranged from 0 to 100.

RESULTS

The system and exercise program had objective utility: system uptime was 92 ± 6.9% of intended hours and the rate of successful cue delivery was 99 ± 2.7%. The system and program also were effective in motivating cued exercise: activity was detected within 5-s of the cue 98 ± 3.1% of the time. As shown via two case studies, accelerometry data can accurately reflect graded-challenge exercise instructions and reveal differentiable activity levels across exercise stages. User experience surveys indicated positive overall usability in the home settings, strong levels of personal motivation to use the system, and high degrees of satisfaction with the devices and provided training. Self-efficacy assessments indicated a strong perception of proficiency across participants (95 ± 5.0).

CONCLUSIONS

This study demonstrates that a low-cost wearable system providing frequent haptic cues to encourage graded-challenge exercise after stroke can have utility and can provide an overall positive user experience in home settings. The study also demonstrates how combining a graded exercise program with all-day activity monitoring can provide insight into the potential for wearable systems to assess adherence to-and effectiveness of-home-based exercise programs on an individualized basis.

MultiSenseBadminton: Wearable Sensor-Based Biomechanical Dataset for Evaluation of Badminton Performance

The sports industry is witnessing an increasing trend of utilizing multiple synchronized sensors for player data collection, enabling personalized training systems with multi-perspective real-time feedback. Badminton could benefit from these various sensors, but there is a scarcity of comprehensive badminton action datasets for analysis and training feedback. Addressing this gap, this paper introduces a multi-sensor badminton dataset for forehand clear and backhand drive strokes, based on interviews with coaches for optimal usability. The dataset covers various skill levels, including beginners, intermediates, and experts, providing resources for understanding biomechanics across skill levels. It encompasses 7,763 badminton swing data from 25 players, featuring sensor data on eye tracking, body tracking, muscle signals, and foot pressure. The dataset also includes video recordings, detailed annotations on stroke type, skill level, sound, ball landing, and hitting location, as well as survey and interview data. We validated our dataset by applying a proof-of-concept machine learning model to all annotation data, demonstrating its comprehensive applicability in advanced badminton training and research.

NSF DARE-Transforming modeling in neurorehabilitation: Four threads for catalyzing progress

We present an overview of the Conference on Transformative Opportunities for Modeling in Neurorehabilitation held in March 2023. It was supported by the Disability and Rehabilitation Engineering (DARE) program from the National Science Foundation's Engineering Biology and Health Cluster. The conference brought together experts and trainees from around the world to discuss critical questions, challenges, and opportunities at the intersection of computational modeling and neurorehabilitation to understand, optimize, and improve clinical translation of neurorehabilitation. We organized the conference around four key, relevant, and promising Focus Areas for modeling: Adaptation & Plasticity, Personalization, Human-Device Interactions, and Modeling 'In-the-Wild'. We identified four common threads across the Focus Areas that, if addressed, can catalyze progress in the short, medium, and long terms. These were: (i) the need to capture and curate appropriate and useful data necessary to develop, validate, and deploy useful computational models (ii) the need to create multi-scale models that span the personalization spectrum from individuals to populations, and from cellular to behavioral levels (iii) the need for algorithms that extract as much information from available data, while requiring as little data as possible from each client (iv) the insistence on leveraging readily available sensors and data systems to push model-driven treatments from the lab, and into the clinic, home, workplace, and community. The conference archive can be found at (dare2023.usc.edu). These topics are also extended by three perspective papers prepared by trainees and junior faculty, clinician researchers, and federal funding agency representatives who attended the conference.

Artificial intelligence-driven virtual rehabilitation for people living in the community: A scoping review

Virtual Rehabilitation (VRehab) is a promising approach to improving the physical and mental functioning of patients living in the community. The use of VRehab technology results in the generation of multi-modal datasets collected through various devices. This presents opportunities for the development of Artificial Intelligence (AI) techniques in VRehab, namely the measurement, detection, and prediction of various patients' health outcomes. The objective of this scoping review was to explore the applications and effectiveness of incorporating AI into home-based VRehab programs. PubMed/MEDLINE, Embase, IEEE Xplore, Web of Science databases, and Google Scholar were searched from inception until June 2023 for studies that applied AI for the delivery of VRehab programs to the homes of adult patients. After screening 2172 unique titles and abstracts and 51 full-text studies, 13 studies were included in the review. A variety of AI algorithms were applied to analyze data collected from various sensors and make inferences about patients' health outcomes, most involving evaluating patients' exercise quality and providing feedback to patients. The AI algorithms used in the studies were mostly fuzzy rule-based methods, template matching, and deep neural networks. Despite the growing body of literature on the use of AI in VRehab, very few studies have examined its use in patients' homes. Current research suggests that integrating AI with home-based VRehab can lead to improved rehabilitation outcomes for patients. However, further research is required to fully assess the effectiveness of various forms of AI-driven home-based VRehab, taking into account its unique challenges and using standardized metrics.

Detection and Assessment of Point-to-Point Movements During Functional Activities Using Deep Learning and Kinematic Analyses of the Stroke-Affected Wrist

Stoke is a leading cause of long-term disability, including upper-limb hemiparesis. Frequent, unobtrusive assessment of naturalistic motor performance could enable clinicians to better assess rehabilitation effectiveness and monitor patients' recovery trajectories. We therefore propose and validate a two-phase data analytic pipeline to estimate upper-limb impairment based on the naturalistic performance of activities of daily living (ADLs). Eighteen stroke survivors were equipped with an inertial sensor on the stroke-affected wrist and performed up to four ADLs in a naturalistic manner. Continuous inertial time series were segmented into sliding windows, and a machine-learned model identified windows containing instances of point-to-point (P2P) movements. Using kinematic features extracted from the detected windows, a subsequent model was used to estimate upper-limb motor impairment, as measured by the Fugl-Meyer Assessment (FMA). Both models were evaluated using leave-one-subject-out cross-validation. The P2P movement detection model had an area under the precision-recall curve of 0.72. FMA estimates had a normalized root mean square error of 18.8% with R2=0.72. These promising results support the potential to develop seamless, ecologically valid measures of real-world motor performance.

Upper limb assessment with inertial measurement units according to the international classification of functioning in stroke: a systematic review and correlation meta-analysis

OBJECTIVE

To investigate the usefulness of inertial measurement units (IMUs) in the assessment of motor function of the upper limb (UL) in accordance with the international classification of functioning (ICF).

DATA SOURCES

PubMed; Scopus; Embase; WoS and PEDro databases were searched from inception to 1 February 2022.

METHODS

The current systematic review follows PRISMA recommendations. Articles including IMU assessment of UL in stroke individuals have been included and divided into four ICF categories (b710, b735, b760, d445). We used correlation meta-analysis to pool the Fisher Z-score of each correlation between kinematics and clinical assessment.

RESULTS

A total of 35 articles, involving 475 patients, met the inclusion criteria. In the included studies, IMUs have been employed to assess the mobility of joint functions (n = 6), muscle tone functions (n = 4), control of voluntary movement functions (n = 15), and hand and arm use (n = 15). A significant correlation was found in overall meta-analysis based on 10 studies, involving 213 subjects: (r = 0.69) (95% CI: 0.69/0.98; p < 0.001) as in the d445 (r = 0.71) and b760 (r = 0.64) ICF domains, with no heterogeneity across the studies.

CONCLUSION

The literature supports the integration of IMUs and conventional clinical assessment in functional evaluation of the UL after a stroke. The use of a limited number of wearable sensors can provide additional kinematic features of UL in all investigated ICF domains, especially in the ADL tasks when a strong correlation with clinical evaluation was found.

Investigating Activity Recognition for Hemiparetic Stroke Patients Using Wearable Sensors: A Deep Learning Approach with Data Augmentation

Measuring the daily use of an affected limb after hospital discharge is crucial for hemiparetic stroke rehabilitation. Classifying movements using non-intrusive wearable sensors provides context for arm use and is essential for the development of a home rehabilitation system. However, the movement classification of stroke patients poses unique challenges, including variability and sparsity. To address these challenges, we collected movement data from 15 hemiparetic stroke patients (Stroke group) and 29 non-disabled individuals (ND group). The participants performed two different tasks, the range of motion (14 movements) task and the activities of daily living (56 movements) task, wearing five inertial measurement units in a home setting. We trained a 1D convolutional neural network and evaluated its performance for different training groups: ND-only, Stroke-only, and ND and Stroke jointly. We further compared the model performance with data augmentation from axis rotation and investigated how the performance varied based on the asymmetry of movements. The joint training of ND + Stroke yielded an increased F1-score by a margin of 31.6% and 10.6% compared to ND-only training and Stroke-only training, respectively. Data augmentation further enhanced F1-scores across all conditions by an average of 11.3%. Finally, asymmetric movements decreased the F1-score by 25.9% compared to symmetric movements in the Stroke group, indicating the importance of asymmetry in movement classification.

A metric for characterizing the arm nonuse workspace in poststroke individuals using a robot arm

An overreliance on the less-affected limb for functional tasks at the expense of the paretic limb and in spite of recovered capacity is an often-observed phenomenon in survivors of hemispheric stroke. The difference between capacity for use and actual spontaneous use is referred to as arm nonuse. Obtaining an ecologically valid evaluation of arm nonuse is challenging because it requires the observation of spontaneous arm choice for different tasks, which can easily be influenced by instructions, presumed expectations, and awareness that one is being tested. To better quantify arm nonuse, we developed the bimanual arm reaching test with a robot (BARTR) for quantitatively assessing arm nonuse in chronic stroke survivors. The BARTR is an instrument that uses a robot arm as a means of remote and unbiased data collection of nuanced spatial data for clinical evaluations of arm nonuse. This approach shows promise for determining the efficacy of interventions designed to reduce paretic arm nonuse and enhance functional recovery after stroke. We show that the BARTR satisfies the criteria of an appropriate metric for neurorehabilitative contexts: It is valid, reliable, and simple to use.

Deep fit_predic: a novel integrated pyramid dilation EfficientNet-B3 scheme for fitness prediction system

This study introduces novel deep learning (DL) techniques for effective fitness prediction using a person's health data. Initially, pre-processing is performed in which data cleaning, one-hot encoding and data normalization are performed. The pre-processed data are then fed into the feature selection stage, where the useful features are extracted using the enhanced chameleon swarm (ECham-Sw) optimization technique. Then, a clustering process is performed using Minkowski integrated gravity center clustering (Min-GCC) to cluster the health profiles of each individual. Finally, the Pyramid Dilated EfficientNet-B3 (PyDi-EfficientNet-B3) technique is proposed to predict the fitness of each individual efficiently with enhanced accuracy of 99.8%.

Monitoring and Predicting Health Status in Neurological Patients: The ALAMEDA Data Collection Protocol

(1) Objective: We explore the predictive power of a novel stream of patient data, combining wearable devices and patient reported outcomes (PROs), using an AI-first approach to classify the health status of Parkinson's disease (PD), multiple sclerosis (MS) and stroke patients (collectively named PMSS). (2) Background: Recent studies acknowledge the burden of neurological disorders on patients and on the healthcare systems managing them. To address this, effort is invested in the digital transformation of health provisioning for PMSS patients. (3) Methods: We introduce the data collection journey within the ALAMEDA project, which continuously collects PRO data for a year through mobile applications and supplements them with data from minimally intrusive wearable devices (accelerometer bracelet, IMU sensor belt, ground force measuring insoles, and sleep mattress) worn for 1-2 weeks at each milestone. We present the data collection schedule and its feasibility, the mapping of medical predictor variables to wearable device capabilities and mobile application functionality. (4) Results: A novel combination of wearable devices and smartphone applications required for the desired analysis of motor, sleep, emotional and quality-of-life outcomes is introduced. AI-first analysis methods are presented that aim to uncover the prediction capability of diverse longitudinal and cross-sectional setups (in terms of standard medical test targets). Mobile application development and usage schedule facilitates the retention of patient engagement and compliance with the study protocol.

Development and Testing of a Daily Activity Recognition System for Post-Stroke Rehabilitation

Those who survive the initial incidence of a stroke experience impacts on daily function. As a part of the rehabilitation process, it is essential for clinicians to monitor patients' health status and recovery progress accurately and consistently; however, little is known about how patients function in their own homes. Therefore, the goal of this study was to develop, train, and test an algorithm within an ambient, in-home depth sensor system that can classify and quantify home activities of individuals post-stroke. We developed the Daily Activity Recognition and Assessment System (DARAS). A daily action logger was implemented with a Foresite Healthcare depth sensor. Daily activity data were collected from seventeen post-stroke participants' homes over three months. Given the extensive amount of data, only a portion of the participants' data was used for this specific analysis. An ensemble network for activity recognition and temporal localization was developed to detect and segment the clinically relevant actions from the recorded data. The ensemble network, which learns rich spatial-temporal features from both depth and skeletal joint data, fuses the prediction outputs from a customized 3D convolutional-de-convolutional network, customized region convolutional 3D network, and a proposed region hierarchical co-occurrence network. The per-frame precision and per-action precision were 0.819 and 0.838, respectively, on the test set. The outcomes from the DARAS can help clinicians to provide more personalized rehabilitation plans that benefit patients.

The Application of Wearable Sensors and Machine Learning Algorithms in Rehabilitation Training: A Systematic Review

The integration of wearable sensor technology and machine learning algorithms has significantly transformed the field of intelligent medical rehabilitation. These innovative technologies enable the collection of valuable movement, muscle, or nerve data during the rehabilitation process, empowering medical professionals to evaluate patient recovery and predict disease development more efficiently. This systematic review aims to study the application of wearable sensor technology and machine learning algorithms in different disease rehabilitation training programs, obtain the best sensors and algorithms that meet different disease rehabilitation conditions, and provide ideas for future research and development. A total of 1490 studies were retrieved from two databases, the Web of Science and IEEE Xplore, and finally 32 articles were selected. In this review, the selected papers employ different wearable sensors and machine learning algorithms to address different disease rehabilitation problems. Our analysis focuses on the types of wearable sensors employed, the application of machine learning algorithms, and the approach to rehabilitation training for different medical conditions. It summarizes the usage of different sensors and compares different machine learning algorithms. It can be observed that the combination of these two technologies can optimize the disease rehabilitation process and provide more possibilities for future home rehabilitation scenarios. Finally, the present limitations and suggestions for future developments are presented in the study.

Automatic Post-Stroke Severity Assessment Using Novel Unsupervised Consensus Learning for Wearable and Camera-Based Sensor Datasets

Stroke survivors often suffer from movement impairments that significantly affect their daily activities. The advancements in sensor technology and IoT have provided opportunities to automate the assessment and rehabilitation process for stroke survivors. This paper aims to provide a smart post-stroke severity assessment using AI-driven models. With the absence of labelled data and expert assessment, there is a research gap in providing virtual assessment, especially for unlabeled data. Inspired by the advances in consensus learning, in this paper, we propose a consensus clustering algorithm, PSA-NMF, that combines various clusterings into one united clustering, i.e., cluster consensus, to produce more stable and robust results compared to individual clustering. This paper is the first to investigate severity level using unsupervised learning and trunk displacement features in the frequency domain for post-stroke smart assessment. Two different methods of data collection from the U-limb datasets-the camera-based method (Vicon) and wearable sensor-based technology (Xsens)-were used. The trunk displacement method labelled each cluster based on the compensatory movements that stroke survivors employed for their daily activities. The proposed method uses the position and acceleration data in the frequency domain. Experimental results have demonstrated that the proposed clustering method that uses the post-stroke assessment approach increased the evaluation metrics such as accuracy and F-score. These findings can lead to a more effective and automated stroke rehabilitation process that is suitable for clinical settings, thus improving the quality of life for stroke survivors.

Emerging technologies in wearable sensors

This Editorial highlights some current challenges and emerging solutions in wearable sensors, a maturing field where interdisciplinary crosstalk is of paramount importance. Currently, investigation efforts are aimed at expanding the application scenarios and at translating early developments from basic research to widespread adoption in personal health monitoring for diagnostic and therapeutic purposes. This translation requires addressing several old and new challenges that are summarized in this editorial. The special issue "Emerging technologies in wearable sensors" includes four selected contributions from leading researchers, exploring the topic from different perspectives. The aim is to provide the APL Bioengineering readers with a solid and timely overall vision of the field and with some recent examples of wearable sensors, exploring new research avenues.

Monocular 3D Human Pose Markerless Systems for Gait Assessment

Gait analysis plays an important role in the fields of healthcare and sports sciences. Conventional gait analysis relies on costly equipment such as optical motion capture cameras and wearable sensors, some of which require trained assessors for data collection and processing. With the recent developments in computer vision and deep neural networks, using monocular RGB cameras for 3D human pose estimation has shown tremendous promise as a cost-effective and efficient solution for clinical gait analysis. In this paper, a markerless human pose technique is developed using motion captured by a consumer monocular camera (800 × 600 pixels and 30 FPS) for clinical gait analysis. The experimental results have shown that the proposed post-processing algorithm significantly improved the original human pose detection model (BlazePose)'s prediction performance compared to the gold-standard gait signals by 10.7% using the MoVi dataset. In addition, the predicted T² score has an excellent correlation with ground truth (r = 0.99 and y = 0.94x + 0.01 regression line), which supports that our approach can be a potential alternative to the conventional marker-based solution to assist the clinical gait assessment.

Sensor-Based Rehabilitation in Neurological Diseases: A Bibliometric Analysis of Research Trends

BACKGROUND

As the field of sensor-based rehabilitation continues to expand, it is important to gain a comprehensive understanding of its current research landscape. This study aimed to conduct a bibliometric analysis to identify the most influential authors, institutions, journals, and research areas in this field.

METHODS

A search of the Web of Science Core Collection was performed using keywords related to sensor-based rehabilitation in neurological diseases. The search results were analyzed with CiteSpace software using bibliometric techniques, including co-authorship analysis, citation analysis, and keyword co-occurrence analysis.

RESULTS

Between 2002 and 2022, 1103 papers were published on the topic, with slow growth from 2002 to 2017, followed by a rapid increase from 2018 to 2022. The United States was the most active country, while the Swiss Federal Institute of Technology had the highest number of publications among institutions. Sensors published the most papers. The top keywords included rehabilitation, stroke, and recovery. The clusters of keywords comprised machine learning, specific neurological conditions, and sensor-based rehabilitation technologies.

CONCLUSIONS

This study provides a comprehensive overview of the current state of sensor-based rehabilitation research in neurological diseases, highlighting the most influential authors, journals, and research themes. The findings can help researchers and practitioners to identify emerging trends and opportunities for collaboration and can inform the development of future research directions in this field.

Methods for the metrological characterization of wearable devices for the measurement of physiological signals: state of the art and future challenges

Wearable devices are rapidly spreading in many different application fields and with diverse measurement accuracy targets. However, data on their metrological characterization are very often missing or obtained with non-standardized methods, hence resulting in barely comparable results. The aim of this review paper is to discuss the existing methods for the metrological characterization of wearable sensors exploited for the measurement of physiological signals, highlighting the room for research still available in this field. Furthermore, as a case study, the authors report a customized method they have tuned for the validation of wireless electrocardiographic monitors. The literature provides a plethora of test/validation procedures, but there is no shared consensus on test parameters (e.g. test population size, test protocol, output parameters of validation procedure, etc.); on the other hand, manufacturers rarely provide measurement accuracy values and, even when they do, the test protocol and data processing pipelines are generally not disclosed. Given the increasing interest and demand of wearable sensors also for medical and diagnostic purposes, the metrological performance of such devices should be always considered, to be able to adequately interpret the results and always deliver them associated with the related measurement accuracy.•The sensor metrological performance should be always properly considered.•There are no standard methods for wearable sensors metrological characterization.•It is important to define rigorous test protocols, easily tunable for specific target applications.

Managing challenging behaviours in adults with traumatic brain injury: A scoping review of technology-based interventions

Challenging behaviours are one of the most serious sequelae after a traumatic brain injury (TBI). These chronic behaviours must be managed to reduce the associated burden for caregivers, and people with TBI. Though technology-based interventions have shown potential for managing challenging behaviours, no review has synthesised evidence of technology aided behaviour management in the TBI population. The objective of this scoping review was to explore what technology-based interventions are being used to manage challenging behaviours in people with TBI. Two independent reviewers analysed 3505 studies conducted between 2000 and 2023. Studies were selected from five databases using search strategies developed in collaboration with a university librarian. Sixteen studies were selected. Most studies used biofeedback and mobile applications, primarily targeting emotional dysregulation. These technologies were tested in a variety of settings. Two interventions involved both people with TBI and their family caregivers. This review found that technology-based interventions have the potential to support behavioural management, though research and technology development is at an early stage. Future research is needed to further develop technology-based interventions that target diverse challenging behaviours, and to document their effectiveness and acceptability for use by people with TBI and their families.

Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke

Background: Arm use metrics derived from wrist-mounted movement sensors are widely used to quantify the upper limb performance in real-life conditions of individuals with stroke throughout motor recovery. The calculation of real-world use metrics, such as arm use duration and laterality preferences, relies on accurately identifying functional movements. Hence, classifying upper limb activity into functional and non-functional classes is paramount. Acceleration thresholds are conventionally used to distinguish these classes. However, these methods are challenged by the high inter and intra-individual variability of movement patterns. In this study, we developed and validated a machine learning classifier for this task and compared it to methods using conventional and optimal thresholds. Methods: Individuals after stroke were video-recorded in their home environment performing semi-naturalistic daily tasks while wearing wrist-mounted inertial measurement units. Data were labeled frame-by-frame following the Taxonomy of Functional Upper Limb Motion definitions, excluding whole-body movements, and sequenced into 1-s epochs. Actigraph counts were computed, and an optimal threshold for functional movement was determined by receiver operating characteristic curve analyses on group and individual levels. A logistic regression classifier was trained on the same labels using time and frequency domain features. Performance measures were compared between all classification methods. Results: Video data (6.5 h) of 14 individuals with mild-to-severe upper limb impairment were labeled. Optimal activity count thresholds were ≥20.1 for the affected side and ≥38.6 for the unaffected side and showed high predictive power with an area under the curve (95% CI) of 0.88 (0.87,0.89) and 0.86 (0.85, 0.87), respectively. A classification accuracy of around 80% was equivalent to the optimal threshold and machine learning methods and outperformed the conventional threshold by ∼10%. Optimal thresholds and machine learning methods showed superior specificity (75-82%) to conventional thresholds (58-66%) across unilateral and bilateral activities. Conclusion: This work compares the validity of methods classifying stroke survivors' real-life arm activities measured by wrist-worn sensors excluding whole-body movements. The determined optimal thresholds and machine learning classifiers achieved an equivalent accuracy and higher specificity than conventional thresholds. Our open-sourced classifier or optimal thresholds should be used to specify the intensity and duration of arm use.

Accuracy of gait and posture classification using movement sensors in individuals with mobility impairment after stroke

Background: Stroke leads to motor impairment which reduces physical activity, negatively affects social participation, and increases the risk of secondary cardiovascular events. Continuous monitoring of physical activity with motion sensors is promising to allow the prescription of tailored treatments in a timely manner. Accurate classification of gait activities and body posture is necessary to extract actionable information for outcome measures from unstructured motion data. We here develop and validate a solution for various sensor configurations specifically for a stroke population.

Methods: Video and movement sensor data (locations: wrists, ankles, and chest) were collected from fourteen stroke survivors with motor impairment who performed real-life activities in their home environment. Video data were labeled for five classes of gait and body postures and three classes of transitions that served as ground truth. We trained support vector machine (SVM), logistic regression (LR), and k-nearest neighbor (kNN) models to identify gait bouts only or gait and posture. Model performance was assessed by the nested leave-one-subject-out protocol and compared across five different sensor placement configurations.

Results: Our method achieved very good performance when predicting real-life gait versus non-gait (Gait classification) with an accuracy between 85% and 93% across sensor configurations, using SVM and LR modeling. On the much more challenging task of discriminating between the body postures lying, sitting, and standing as well as walking, and stair ascent/descent (Gait and postures classification), our method achieves accuracies between 80% and 86% with at least one ankle and wrist sensor attached unilaterally. The Gait and postures classification performance between SVM and LR was equivalent but superior to kNN.

Conclusion: This work presents a comparison of performance when classifying Gait and body postures in post-stroke individuals with different sensor configurations, which provide options for subsequent outcome evaluation. We achieved accurate classification of gait and postures performed in a real-life setting by individuals with a wide range of motor impairments due to stroke. This validated classifier will hopefully prove a useful resource to researchers and clinicians in the increasingly important field of digital health in the form of remote movement monitoring using motion sensors.

Interpretable evaluation for the Brunnstrom recovery stage of the lower limb based on wearable sensors

With the increasing number of stroke patients, there is an urgent need for an accessible, scientific, and reliable evaluation method for stroke rehabilitation. Although many rehabilitation stage evaluation methods based on the wearable sensors and machine learning algorithm have been developed, the interpretable evaluation of the Brunnstrom recovery stage of the lower limb (BRS-L) is still lacking. The paper propose an interpretable BRS-L evaluation method based on wearable sensors. We collected lower limb motion data and plantar pressure data of 20 hemiplegic patients and 10 healthy individuals using seven Inertial Measurement Units (IMUs) and two plantar pressure insoles. Then we extracted gait features from the motion data and pressure data. By using feature selection based on feature importance, we improved the interpretability of the machine learning-based evaluation method. Several machine learning models are evaluated on the dataset, the results show that k-Nearest Neighbor has the best prediction performance and achieves 94.2% accuracy with an input of 18 features. Our method provides a feasible solution for precise rehabilitation and home-based rehabilitation of hemiplegic patients.

Smart Home Technology Solutions for Cardiovascular Diseases: A Systematic Review

Cardiovascular diseases (CVD) are the leading cause of mortality globally. Despite improvement in therapies, people with CVD lack support for monitoring and managing their condition at home and out of hospital settings. Smart Home Technologies have potential to monitor health status and support people with CVD in their homes. We explored the Smart Home Technologies available for CVD monitoring and management in people with CVD and acceptance of the available technologies to end-users. We systematically searched four databases, namely Medline, Web of Science, Embase, and IEEE, from 1990 to 2020 (search date 18 March 2020). “Smart-Home” was defined as a system using integrated sensor technologies. We included studies using sensors, such as wearable and non-wearable devices, to capture vital signs relevant to CVD at home settings and to transfer the data using communication systems, including the gateway. We categorised the articles for parameters monitored, communication systems and data sharing, end-user applications, regulations, and user acceptance. The initial search yielded 2462 articles, and the elimination of duplicates resulted in 1760 articles. Of the 36 articles eligible for full-text screening, we selected five Smart Home Technology studies for CVD management with sensor devices connected to a gateway and having a web-based user interface. We observed that the participants of all the studies were people with heart failure. A total of three main categories—Smart Home Technology for CVD management, user acceptance, and the role of regulatory agencies—were developed and discussed. There is an imperative need to monitor CVD patients’ vital parameters regularly. However, limited Smart Home Technology is available to address CVD patients’ needs and monitor health risks. Our review suggests the need to develop and test Smart Home Technology for people with CVD. Our findings provide insights and guidelines into critical issues, including Smart Home Technology for CVD management, user acceptance, and regulatory agency’s role to be followed when designing, developing, and deploying Smart Home Technology for CVD.

Using Wearable Inertial Sensors to Estimate Clinical Scores of Upper Limb Movement Quality in Stroke

Neurorehabilitation is progressively shifting from purely in-clinic treatment to therapy that is provided in both clinical and home-based settings. This transition generates a pressing need for assessments that can be performed across the entire continuum of care, a need that might be accommodated by application of wearable sensors. A first step toward ubiquitous assessments is to augment validated and well-understood standard clinical tests. This route has been pursued for the assessment of motor functioning, which in clinical research and practice is observation-based and requires specially trained personnel. In our study, 21 patients performed movement tasks of the Action Research Arm Test (ARAT), one of the most widely used clinical tests of upper limb motor functioning, while trained evaluators scored each task on pre-defined criteria. We collected data with just two wrist-worn inertial sensors to guarantee applicability across the continuum of care and used machine learning algorithms to estimate the ARAT task scores from sensor-derived features. Tasks scores were classified with approximately 80% accuracy. Linear regression between summed clinical task scores (across all tasks per patient) and estimates of sum task scores yielded a good fit (R 2 = 0.93; range reported in previous studies: 0.61-0.97). Estimates of the sum scores showed a mean absolute error of 2.9 points, 5.1% of the total score, which is smaller than the minimally detectable change and minimally clinically important difference of the ARAT when rated by a trained evaluator. We conclude that it is feasible to obtain accurate estimates of ARAT scores with just two wrist worn sensors. The approach enables administration of the ARAT in an objective, minimally supervised or remote fashion and provides the basis for a widespread use of wearable sensors in neurorehabilitation.

Quantitative Evaluation System of Wrist Motor Function for Stroke Patients Based on Force Feedback

Motor function evaluation is a significant part of post-stroke rehabilitation protocols, and the evaluation of wrist motor function helps provide patients with individualized rehabilitation training programs. However, traditional assessment is coarsely graded, lacks quantitative analysis, and relies heavily on clinical experience. In order to objectively quantify wrist motor dysfunction in stroke patients, a novel quantitative evaluation system based on force feedback and machine learning algorithm was proposed. Sensors embedded in the force-feedback robot record the kinematic and movement data of the subject, and the rehabilitation doctor used an evaluation scale to score the wrist function of the subject. The quantitative evaluation models of wrist motion function based on random forest (RF), support vector machine regression (SVR), k-nearest neighbor (KNN), and back propagation neural network (BPNN) were established, respectively. To verify the effectiveness of the proposed quantitative evaluation system, 25 stroke patients and 10 healthy volunteers were recruited in this study. Experimental results show that the evaluation accuracy of the four models is all above 88%. The accuracy of BPNN model is 94.26%, and the Pearson correlation coefficient between model prediction and clinician scores is 0.964, indicating that the BPNN model can accurately evaluate the wrist motor function for stroke patients. In addition, there was a significant correlation between the prediction score of the quantitative assessment system and the physician scale score (p < 0.05). The proposed system enables quantitative and refined assessment of wrist motor function in stroke patients and has the feasibility of helping rehabilitation physicians in evaluating patients’ motor function clinically.