Exoskeletal wearable robot on ambulatory function in patients with stroke: a protocol for an international, multicentre, randomised controlled study.

INTRODUCTION: The purpose of this study is to determine the effect of overground gait training using an exoskeletal wearable robot (exoskeleton) on the recovery of ambulatory function in patients with subacute stroke. We also investigate the assistive effects of an exoskeleton on ambulatory function in patients with subacute stroke. METHODS AND ANALYSIS: This study is an international, multicentre, randomised controlled study at five institutions with a total of 150 patients with subacute stroke. Participants will be randomised into two groups (75 patients in the robot-assisted gait training (RAGT) group and 75 patients in the control group). The gait training will be performed with a total of 20 sessions (60 min/session); 5 sessions a week for 4 weeks. The RAGT group will receive 30 min of gait training using an exoskeleton (ANGEL LEGS M20, Angel Robotics) and 30 min of conventional gait training, while the control group will receive 60 min conventional gait training. In all the patients, the functional assessments such as ambulation, motor and balance will be evaluated before and after the intervention. Follow-up monitoring will be performed to verify whether the patient can walk without physical assistance for 3 months. The primary outcome is the improvement of the Functional Ambulatory Category after the gait training. The functional assessments will also be evaluated immediately after the last training session in the RAGT group to assess the assistive effects of an exoskeletal wearable robot. This trial will provide evidence on the effects of an exoskeleton to improve and assist ambulatory function in patients with subacute stroke. ETHICS AND DISSEMINATION: This protocol has been approved by the Institutional Review Board of each hospital and conforms to the Declaration of Helsinki. The results will be disseminated through publication. TRIAL REGISTRATION NUMBER: Protocol was registered at ClinicalTrials.gov (NCT05157347) on 15 December 2021 and CRIS (KCT0006815) on 19 November 2021.

Clinical Spasticity Assessment Assisted by Machine Learning Methods and Rule-Based Decision.

The Modified Ashworth Scale (MAS) is commonly used to assess spasticity in clinics. The qualitative description of MAS has resulted in ambiguity during spasticity assessment. This work supports spasticity assessment by providing measurement data acquired from wireless wearable sensors, i.e., goniometers, myometers, and surface electromyography sensors. Based on in-depth discussions with consultant rehabilitation physicians, eight (8) kinematic, six (6) kinetic, and four (4) physiological features were extracted from the collected clinical data from fifty (50) subjects. These features were used to train and evaluate the conventional machine learning classifiers, including but not limited to Support Vector Machine (SVM) and Random Forest (RF). Subsequently, a spasticity classification approach combining the decision-making logic of the consultant rehabilitation physicians, SVM, and RF was developed. The empirical results on the unknown test set show that the proposed Logical-SVM-RF classifier outperforms each individual classifier, reporting an accuracy of 91% compared to 56-81% achieved by SVM and RF. A data-driven diagnosis decision contributing to interrater reliability is enabled via the availability of quantitative clinical data and a MAS prediction.

Elucidating factors influencing machine learning algorithm prediction in spasticity assessment: a prospective observational study.

The Machine Learning Model (MLM) has garnered popularity in rehabilitation, ranging from developing algorithms in outcome prediction, prognostication, and training artificial intelligence. High-quality data plays a critical role in algorithm development. Limited studies have explored factors that may influence the MLM algorithm performance in predicting spasticity severity level. The objectives of this study were to train and validate a MLM algorithm for spasticity assessment and determine the algorithm's prediction performance in predicting ambiguous spasticity datasets. Forty-seven persons with central nervous system pathology that fulfilled the inclusion and exclusion criteria were recruited. Four biomechanical properties of spasticity were obtained using off-the-shelf wearable sensors. The data were analyzed individually, and ambiguous datasets were separated. The acceptable inertial data were used to train and validate MLM in predicting spasticity. The trained and validated MLM algorithm was later deployed to predict the ambiguous spasticity datasets. A series of MLM were applied, including Support Vector Machine, Decision Tree, and Random Forest. The MLM's performance accuracy of the validation data was 96%, 52%, and 72%, respectively. The validated MLM accuracy performance level predicting ambiguous datasets reduces to 20%, 23%, and 23%, respectively. This study elucidates data biases and variances of disease background, pathophysiological and anatomical factors that have to be considered in MLM training.

Effects of Concurrent Tasks on Gait Performance in Children With Traumatic Brain Injury Versus Children With Typical Development.

OBJECTIVE: To investigate how gait parameters in children with traumatic brain injury (TBI) versus typically developing (TD) children are influenced by secondary concurrent tasks and examine the correlations between gait parameters and attention and balance in children with TBI. METHODS: Sixteen children with TBI (mean age, 11.63±1.89 years) and 22 TD controls (mean age, 11.41±2.24 years) participated in this case-control study. Attention and functional balance were measured using the Children's Color Trail Test (CCTT) and Pediatric Balance Scale (PBS). All participants first walked without concurrent tasks and then with concurrent motor and cognitive tasks. The APDM Mobility Lab was used to measure gait parameters, including gait velocity, stride length, stride duration, cadence, and double support time. Repeatedmeasures analysis of variance and Spearman correlation coefficient were used for the analysis. RESULTS: Children with TBI showed significantly more deterioration in gait performance than TD children (p<0.05). Concurrent tasks (motor and cognitive) significantly decreased gait velocity and cadence and increased stride time; the differences were more obvious during the concurrent cognitive task. A moderate correlation was found between gait parameters (gait velocity and stride length) and CCTT-2 and PBS scores in children with TBI. CONCLUSION: Gait performance may be affected by task complexity following TBI. Attention and balance deficits caused deterioration in gait performance under the concurrent task condition in children with TBI. This study illustrates the crucial role of task demand and complexity in dual-task interference.

Robot applications for autism: a comprehensive review.

PURPOSE: Technological advances in robotics have brought about exciting developments in different areas such as education, training, and therapy. Recent research has suggested that the robot can be even more effective in rehabilitation, therapy, and education for individuals with Autism Spectrum Disorder (ASD). In this paper, a comprehensive review of robotic technology for children with ASD is presented wherein a large number of journals and conference proceedings in science and engineering search engines' databases were implicated. MATERIALS AND METHODS: A search for related literature was conducted in three search engines' databases, Web of Science, Scopus, and IEEE Xplore. Thematic keywords were used to identify articles in the recent ten years in titles, keywords, and abstracts. The retrieved articles were filtered, analysed, and evaluated based on specific inclusion and exclusion criteria. RESULTS: A total of 208 studies were retrieved, while 166 met the inclusion criteria. The selected studies were reviewed according to the type of robot, the participants, objectives, and methods. 68 robots were used in all studies, NAO robot was used in 30.5% of those studies. The total number of participants in all studies was 1671. The highest percentage of the studies reviewed were dedicated to augmenting the learning skills. CONCLUSIONS: Robots and the associated schemes were used to determine their feasibility and validity for augmenting the learning skills of autistic children. Most of the studies reviewed were focused on improving the social communication skills of autistic children and measuring the extent of robot mitigation of stereotyped autistic behaviours.Implications for rehabilitationSocial robots are not considered as promising tools to be utilized for rehabilitation of autistic children only, but also has been used for children and young people with severe intellectual disability.Rehabilitation for individuals with ASD using robots can augment their cognitive and social skills, but further studies should be conducted to clarify its effectiveness based on other factors such as sex, age and IQ of the participates.Robotic-based rehabilitation is not limited to the physical robots only, but virtual robots have been used also, whereas each of which can be used individually or simultaneously. However, further study is required to assess the extent of its efficiency and effectiveness for both cases.

Effect of Dual-Task Conditions on Gait Performance during Timed Up and Go Test in Children with Traumatic Brain Injury.

BACKGROUND: Tasks requiring simultaneous mobility and cognition (dual tasks) have been associated with incidence of falls. Although these deficits have been documented in individuals with neurologic disorder, the effect of dual task in children with traumatic brain injury has not been fully explored. OBJECTIVE: To investigate the effect of dual-task (dual-motor and dual-cognitive task) conditions on spatiotemporal gait parameters during timed up and go test in children with traumatic brain injury. METHODS AND MATERIAL: A total of 14 children with traumatic brain injury and 21 typically developing children participated in this case-control study. Functional balance was assessed before the actual testing to predict the risk of falls. Timed up and go test was performed under single-task and dual-task (dual-motor and dual-cognitive task) conditions. Spatiotemporal gait parameters were determined using the APDM Mobility Lab system. The descriptive statistics and t-test were used to analyze demographic characteristics and repeated measure ANOVA test was used to analyze the gait parameters. RESULTS: Under dual-task (dual-motor and dual-cognitive task) conditions during the timed up and go test, gait performance significantly deteriorated. Furthermore, the total time to complete the timed up and go test, stride velocity, cadence, and step time during turning were significantly different between children with traumatic brain injury and typically developing children. CONCLUSIONS: These findings suggest that gait parameters were compromised under dual-task conditions in children with traumatic brain injury. Dual-task conditions may become a component of gait training to ensure a complete and comprehensive rehabilitation program.

Predicting return to work following a cardiac event in Malaysia.

BACKGROUND: Return to work is an important aspect for cardiac rehabilitation following a major cardiac event. OBJECTIVE: The aim was to understand the local prevalence and factors associated with returning to work in Malaysia after a cardiac event. METHODS: A cross sectional design was used. All patients attending the cardiac rehabilitation program after major cardiac event during an 11-months period (2011-2012) were included. Data relating to socio-demographic, work-related, risk factors and acute myocardial infarction were collected. The SF-36 questionnaire was used to assess quality of life. Regression analysis was used to determine the predicting factors to return to work. RESULTS: A total of 398 files were screened, 112 respondents agreed to participate giving a response rate of 47.3%. The prevalence of returned to work (RTW) was 66.1% [95% CI: 57.2-75.0]. Factors associated with work resumption were age (Adj. OR: 0.92 (95% CI: 0.84-0.99), diabetes mellitus (Adj. OR: 3.70, 95% CI: 1.35-10.12), Mental Component Summary (MCS) score (Adj. OR: 1.05 (95% CI: 1.01-1.09) and baseline angiography findings. Patients with single vessel and two vessel disease were 8.9 times and 3.78 times more likely to return to work compared to those with 3 vessels (Adj. OR: 8.90 (95% CI: 2.29-34.64) and Adj. OR: 3.78, (95% CI: 1.12, 12.74). CONCLUSIONS: We proposed a cardiac rehabilitation program to emphasize mental health as it may improve successful return to work after cardiac event.

Developing interactive and simple electromyogram PONG game for foot dorsiflexion and plantarflexion rehabilitation exercise.

Gaming systems have been proven to be able to improve physical and cognitive skills. Several studies have integrated games to be part of rehabilitation program to improve functional ability of human limbs in performing activities of daily living. This paper presents the development of an interactive electromyogram (EMG) based PONG game for foot dorsifexion and plantarflexion exercise. PONG game is selected because it is a classical game that can be easily comprehended and can be played by young and old people. Two surface EMG sensors were used in this work to acquire muscle activity of tibialis anterior muscle and gastrocnemius muscle. An experimental study was carried out to examine the viability of this sensor as input to play the game. The results were satisfactory. This study further strengthens the viability of using muscle activity as an input for gaming system and as a mean to monitor patient rehabilitation progress.