Rehabilitation Engineering Research Articles

Dual-Stream Multiple Instance Learning for Depression Detection With Facial Expression Videos.

Depression is a common mental illness which has brought great harm to the individuals. With recent evidence that many objective physiological signals are associated with depression, automated detection of depression is urgent and important for the growing concern of mental illness. We investigate the problem of classifying depression by facial expressions, which may aid in online diagnosis and rehabilitation engineering of depression. In this work, We propose a weakly supervised learning approach employing multiple instance learning (MIL) on 150 videos data from 75 depressed and 75 healthy subjects. In addition, we present a novel MIL dual-stream aggregator that considers both the instance-level and the bag-level in order to emphasize the information with symptoms. Specifically, our method named ADDMIL uses max-pooling at the instance level to capture symptom information and further integrates the contribution of each instance at the bag level using attention weights. Our method achieves 74.7% accuracy and 74.5% recall on the collected dataset, which not only improves 10.1% accuracy and 9.8% recall over the baseline but also exceeds the best accuracy result of MIL-based method by 2.1%. Our work achieves results that are comparable to the state-of-the-art methods and demonstrates that multiple instance learning has great potential for depression classification. We present for the first time a weakly supervised learning approach in the detection of depression through raw facial expressions, which may provide a new framework for other psychiatric disorders detection methods.

Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder.

Major depressive disorder (MDD) is a prevalent mental health condition and has become a pressing societal challenge. Early prediction of treatment response may aid in the rehabilitation engineering of depression, which is of great practical significance for the relief of suffering and burden of MDD. In this paper, we present a sequence modeling approach that uses data collected by passive sensing techniques to predict patients with an outcome of treatment responded defined by the reduction in clinical administrated scales. Hundreds of patients with MDD have been recruited from outpatient clinics at 4 psychiatric sites. Each has been delivered with a self-developed app to passively record their daily phone usage and physical data with minimal human action. An unavoidable dilemma in passive sensing is missing values. To overcome that, the proposed approach combined feature extraction and sequence modeling methods to fully utilize the pattern of missing values from longitudinal data. With no treatment constraints, it enables us to predict the treatment response of MDD 8-10 weeks before the completion of the treatment course, leaving time for preventative measures. Our work explored the feasibility of treatment response prediction using longitudinal passive sensing data and sparse ground truth, and also has the potential for preventing depression by forecasting treatment outcomes weeks in advance.

REIMAGINING AGING WITH DISABILITY THROUGH TECHNOLOGY

Abstract Individuals aging with long-term disabilities are likely to require support for managing challenges with everyday activities. To effectively promote independence and aging-in-place for this population, we must consider innovative technology solutions that go beyond traditional direct care services. This symposium will highlight technology research and development efforts from the Rehabilitation Engineering Research Center on Technologies to Support Aging-in-Place for People with Long-Term Disabilities (RERC TechSAge). TechSAge is an interdisciplinary collaboration between Georgia Tech, the University of Illinois Urbana-Champaign, and Georgia State University, dedicated to understanding the needs of, and developing supportive technologies for people aging with long-term vision, hearing, and mobility disabilities. First, Remillard et al., will present interview findings from individuals aging with long-term vision loss on challenges performing instrumental activities of daily living. Next, Mitzner et al., will describe TechSAge research-driven guidelines for designing and delivering wellness classes via video-conferencing to older adults with and without disabilities. Blocker et al., will highlight a field trial evaluating how digital home assistants (e.g., Amazon Echo devices) and smart home devices, along with user-friendly support guides, can support older adults with mobility disabilities at home. Finally, Jones et al., will describe the latest feature of the SmartBathroom laboratory – a SmartBathing Transfer Testbed prototype that will enable us to study of how different bathing environment configurations can impact transfer performance. Margaret Campbell (Retired Senior Scientist for Planning and Policy Support, National Institute on Disability, Independent Living, and Rehabilitation Research) will serve as the discussant for the symposium.

Customized Textile Capacitive Insole Sensor for Center of Pressure Analysis

Center of pressure refers to the centroid of the ground reaction force vector detected underneath the walking foot, which is a summary measure representing body segment movements during human locomotion. In this study, we developed a cost-effective, lightweight insole-type textile capacitive sensor (I-TCPs) to analyze plantar pressure (PP) distribution and center of pressure (COP) trajectory. To test the accuracy of I-TCPs, the measured pressure data was compared with that of F-scan. The sensor performance test was divided into a static baseline test and a dynamic gait experiment, both at two different gait speeds self-selected by the subjects. Static gait results showed that I-TCPs were capable of recognizing PP segments at different gait speeds. Dynamic gait results showed an average RMSE of 1.29 ± 0.47 mm in COPx (mediolateral shift) and 12.55 ± 5.08 mm in COPy (anteroposterior shift) at a comfortable gait speed. The COP correlation between I-TCPs and F-scan was 0.54 ± 0.09 in COPx and 0.92 ± 0.04 in COPy in comfortable gait speed conditions, in which COPy values presented a stronger correlation. RMSE and correlation in fast gait speed conditions also showed similar results. The findings of this study can be the basis for future research, including rehabilitation engineering, developing ICT devices, and creating smart wearable sensors to improve quality of life for patients and healthy individuals.

TERMINOLOGY OF BIOMEDICAL ENGINEERING BY MEANS OF BINARY TEXTS: LINGUOCOGNITIVE AND TRANSLATION ASPECTS

The article examines the peculiarities of cognitive and translational aspects of studying English and Ukrainian terminology of biomedical engineering. It is noted that the specialized language of such an interdisciplinary field as biomedical engineering contains concepts that concentrate specific knowledge of technical, medical and topically scientific experience. In cognitive linguistics, concepts are considered in connection with the background knowledge. The specialized language of biomedical engineering is presented as a cognitive-communicative organization of concepts, notions and related terms in such highly specialized fields as bioinstrumentation, biomedical cybernetics, biomechanics, system physiology, rehabilitation engineering, diagnosis of diseases and disorders, etc. It is argued that biomedical engineering is primarily focused on the latest advances in technology and medicine to develop new devices and equipment to improve human health. It is emphasized that the linguistic-cognitive analysis of binary specialized texts is a relevant method for compiling thematic highly specialized dictionaries, taking into account the relevance, intensive development of the researched modern field, as well as the fact that information from foreign sources in the theoretical aspect is not sufficiently represented in the Ukrainian translation. Translators should always take into account the following context criteria in the translation process: linguistic context, situational context and cognitive context. Based on the comparative analysis of binary texts – texts of the same genre and issue – the concept “sleep disturbance” is considered as a certain matrix of the terminological base of the concepts of the specified issue and basis for compiling highly specialized thematic mini-dictionaries. Keywords: biomedical engineering; specialized language; concept; term; translation; specialized terminology glossaries;binary texts.

An Experiential Learning Based Design Program in Rehabilitation Engineering

An Experiential Learning Based Design Program in Rehabilitation Engineering

A three-dimensional whole-body model to predict human walking on level ground

Predictive simulation of human walking has great potential in clinical motion analysis and rehabilitation engineering assessment, but large computational cost and reliance on measurement data to provide initial guess have limited its wide use. We developed a computationally efficient model combining optimization and inverse dynamics to predict three-dimensional whole-body motions and forces during human walking without relying on measurement data. Using the model, we explored two different optimization objectives, mechanical energy expenditure and the time integral of normalized joint torque. Of the two criteria, the sum of the time integrals of the normalized joint torques produced a more realistic walking gait. The reason for this difference is that most of the mechanical energy expenditure is in the sagittal plane (based on measurement data) and this leads to difficulty in prediction in the other two planes. We conclude that mechanical energy may only account for part of the complex performance criteria driving human walking in three dimensions.

Neural and Rehabilitation Engineering: Applications, Process, and Role in the Future of Medicine

The rate of neuro-psychological issues has been increasing day by the day due to increasing rate of social and environmental pollution all around the world. It has been actually escalating the demand for neural and rehabilitation treatment worldwide. Neural and rehabilitation engineering is one of the key inventions of modern science which most significantly enhance the entire diagnosis, communication and treatment process in the neural and rehabilitation process. Hence, the study has been keeping its concerns on developing a superior idea about Neural and rehabilitation engineering. A number of concepts relevant to Neural and rehabilitation engineering has been discussed within the overall study. It also developed understanding on the applications and process involved with Neural and rehabilitation engineering. It helps to evaluate the role of Neural and rehabilitation engineering in future of medical filed. A large number of secondary data and formations has been gathered following inductive approach within the entire process within the study to comes forth with a suitable and effective output results. The study has been found that the application of various technological support through Neural and rehabilitation engineering enhance the treatment success and impact a positive role in upcoming future of medical science. Keyword : Neural, rehabilitation, engineering, medical

Special Issue Orthopedic and Rehabilitation Engineering II

This is the second of two issues on orthopedic and rehabilitation engineering [...]

Towards the Mechatronic Development of a New Upper-Limb Exoskeleton (SAMA)

Modern neuromuscular rehabilitation engineering and assistive technology research have been constantly developing in the last 20 years. The upper body exoskeleton is an example of an assistive rehabilitation device. However, in order to solve its technological problems, interdisciplinary research is still necessary. This paper presents a new three-degrees of freedom (DOF) active upper-body exoskeleton for medical rehabilitation named “SAMA”. Its mechanical structure is inspired by the geometry and biomechanics of the human body, particularly the ranges of motion (ROM) and the needed torque. The SAMA exoskeleton was manufactured and assembled into an ergonomic custom-made wheelchair in a sitting posture in order to provide portability and subject comfort during experimental testing and rehabilitation exercises. Dynamic modeling using MATLAB–Simulink was used for calculating the inverse kinematics, dynamic analysis, trajectory generation and implementation of proportional–integral–derivative (PID) computed torque control (PID-CTC). A new framework has been developed for rapid prototyping (the dynamic modeling, control, and experimentation of SAMA) based on the integration between MATLAB–Simulink and the Robot Operating System (ROS) environment. This framework allows the robust position and torque control of the exoskeleton and real-time monitoring of SAMA and its subject. Two joints of the developed exoskeleton were successfully tested experimentally for the desired arm trajectory. The angular position and torque controller responses were recorded and the exoskeleton joints showed a maximum delay of 200° and a maximum steady state error of 0.25°. These successful results encourage further development and testing for different subjects and more control strategies.

Model and experimental studies on the effects of load characteristics and polyurethane densities on fatigue damage of rigid polyurethane grouting materials

This work aims to theoretically and experimentally investigate the fatigue damage evolution characteristics for rigid polyurethane grouting materials (RPGM). From the theoretical perspective, based on the integral method and classic Chaboche damage evolution model, a theoretical fatigue damage model considering load characteristics (load speed and magnitude) was established. From the experimental perspective, based on the three-point bending experimental fitting, the effects of polyurethane densities on fatigue damage characteristics were considered. In this case, the damage evolution model of semi-empirical and semi-theoretical for RPGM was established. The results show that the fatigue life of RPGM decreases with the increase of load magnitude and polyurethane density but increases with the increase of load speed. On the contrary, the fatigue damage of RPGM increases with the increase of load magnitude and polyurethane density but decreases with the increase of load speed. In addition, the mean relative error between predicted values and experimental results is less than 10 %. At last, the sensitivity analysis shows that the influences of density, load magnitude, and load speed on fatigue life decrease in turn. The damage evolution model established in this work can well predict the damage behavior of RPGM in the entire life cycle. It also can provide good theoretical guidance for the design of rehabilitation and reinforcement engineering.

Enhancement of lower limb motor imagery ability via dual-level multimodal stimulation and sparse spatial pattern decoding method.

Recently, motor imagery brain-computer interfaces (MI-BCIs) with stimulation systems have been developed in the field of motor function assistance and rehabilitation engineering. An efficient stimulation paradigm and Electroencephalogram (EEG) decoding method have been designed to enhance the performance of MI-BCI systems. Therefore, in this study, a multimodal dual-level stimulation paradigm is designed for lower-limb rehabilitation training, whereby visual and auditory stimulations act on the sensory organ while proprioceptive and functional electrical stimulations are provided to the lower limb. In addition, upper triangle filter bank sparse spatial pattern (UTFB-SSP) is proposed to automatically select the optimal frequency sub-bands related to desynchronization rhythm during enhanced imaginary movement to improve the decoding performance. The effectiveness of the proposed MI-BCI system is demonstrated on an the in-house experimental dataset and the BCI competition IV IIa dataset. The experimental results show that the proposed system can effectively enhance the MI performance by inducing the α, β and γ rhythms in lower-limb movement imagery tasks.

Application Status of Rehabilitation Engineer in Rehabilitation Medicine

Application Status of Rehabilitation Engineer in Rehabilitation Medicine

History, Current Practice, and the Future of Wound Care for Occupational and Physical Therapists.

History, Current Practice, and the Future of Wound Care for Occupational and Physical Therapists.

Semi-supervised Learning Based EEG Detection Approach for Rehabilitation Engineering

<p>A semi-supervised learning based EEG signal detection method was studied in this paper. The feature engineering system of this paper was established, which contains novel AutoEncoders mapping features. The optimal channel combination for all subjects was determined to improve recognition accuracy by ReliefF algorithm and recursive feature elimination. What’s more, the semi-supervised learning method based on pseudo-labelling was introduced to the character recognition method, in which the training samples were dynamically reorganized and updated, so that the proposed method could complete the symbol recognition with limited number of training samples. Based on the features extacted and the optimal channel combination, the recognition accuracy of the character recognition method can reach up to 100%.</p> <p> </p>

Smart Home Technologies and Services for Geriatric Rehabilitation

This text consists of nine chapters and is the product of 25 contributors, nine reviewers, and two editors. The book offers a toolbox for health care stakeholders involved in decision-making for the design, development, and implementation of smart home solutions. The book is designed for rehabilitation students and engineers as well as those with an interest for geriatric rehabilitation that includes biomedical engineers, electrical engineers, computer scientists, software developers. The body of this text consists of roughly 185 pages (counting all tables and the inserted 35-page appendix 1), and there are an additional 41 pages of references. With less than 130 pages of written text, this book is quite expensive and is primarily a review of the literature, rather than a “toolbox.” Furthermore, in these references, one would expect more than one reference to RESNA, the Rehabilitation Engineering and Assistive Technology Society of North America! One would also expect more than zero attributions to the two editors. It is also the experience of this reviewer that some mention of patient therapy would involve music therapy, but the word “music” Not recommended.

Can a digital twin of the residuum improve bionic solutions for individuals suffering from limb loss?

Introduction: Understanding the influence of whole-body activity (e.g., physical training) on the biophysics at organ-, tissue-, and sub-tissue-levels is important for designing optimal physical training/rehabilitation and effective control of assistive devices. The Griffith Centre of Biomedical and Rehabilitation Engineering (GCORE) has developed mature rehabilitation and assistive device technologies underpinned by the Personalized Digital Human (PDH). Method framework: The PDH is a physics-based digital twin of the human (and devices), which includes representation of an individual’s bones, articulations, muscles, and other soft tissues. Coupled with peripheral muscle excitation (e.g., electromyograms), PDH encodes muscle activations specific to the individual (e.g., sensitive to training and disease) and task (e.g. sensitive to control task)1. Examples: To analyze human performance, PDH quantifies mechanical parameters such as net loading to the body, organ (e.g., whole bone; Fig. 2), joint, tissue (e.g., ligament; Fig. 1)2, and sub-tissue (e.g., local strain in tendon; Fig. 1)1. Within a control system3, PDH predicts muscle activations that produce target mechanics (e.g., torque on rehabilitation ergometer), compliment an assistive device (e.g., torque above motor-driven assistance), sensory afferents that augment/simulate sensory experience (e.g., haptics), and safety margins (e.g., critical stresses) (Fig. 2).Fig. 2The PDH used within a control system to interpret sensor data, model the internal states of the human, provide augmented sensory afferents, and perform safety checks on the loading of musculoskeletal tissues3.View Large Image Figure ViewerDownload Hi-res image Download (PPT) Discussion/future directions: Currently, we are developing direct fusion of PDH with prosthesis design to optimize amputee residuum health4. Further, PDH could readily be extended to become the personalized digital soldier, with extensive scope for use in monitoring training loads, improving rehabilitation efficacy, and designing equipment to better interface with humans. Acknowledgements: The PDH is the result of numerous nationally-competitive and industry grants for over 2 decades. References 1Pizzolato C, Shim VB, Lloyd DG, et al. Targeted achilles tendon training and rehabilitation using personalized and real-time multi-scale models of the neuromusculoskeletal system. Front Bioeng Biotechnol 2020; 8:878. https://doi.org/10.3389/fbioe.2020.00878 2Nasseri A, Khataee H, Bryant AL, et al. Modelling the loading mechanics of anterior cruciate ligament. Comp Meth Prog Biomed 2020; 184:105098. https://doi.org/10.1016/j.cmpb.2019.105098 3Pizzolato C, Gunduz MA, Palipana D, et al. Non-invasive approaches to functional recovery after spinal cord injury: therapeutic targets and multimodal device interventions. Exp Neurol 2021; 330:113612. https://doi.org/10.1016/j.expneurol.2021.113612 4Frossard LA, Lloyd DG. The future of bionic limbs. Res Feat 2021; 134:74-77. https://doi.org/10.26904/RF-134-7477

Assessing the use of co-design to produce bespoke assistive technology solutions within a current healthcare service: a service evaluation

Purpose Co-design involves engaging with the end-user in the design process and may help reduce the barriers to assistive technology use. Previous research has used co-design in the provision of assistive technology, but no research has looked at applying it within a healthcare setting. This service evaluation examines the use of co-design in providing customized assistive devices within a current UK healthcare based Rehabilitation Engineering department. Methods This evaluation reports on three case studies. Individuals identified a range of challenges in daily living. The participants worked with the clinician in trialling prototypes and providing feedback to develop custom devices. A mixed-method approach of questionnaires and semi-structured interviews were used to evaluate the devices provided and the co-design approach. The resources required to provide the device were also calculated. Results Five different devices were developed, which were able to overcome the challenges identified. Results indicated participants were satisfied with both the devices and service provided. Participants expressed other benefits including increased independence, increased positive emotions and reduced mental load. Participants indicated they liked being involved in the design process and their feedback helped ensure the devices were customized to their needs. Conclusions The use of co-design was able to produce customized assistive device that met the needs of the individuals within a current healthcare service. Further work is required to assess the feasibility of utilising a co-design approach for the provision of other custom assistive technology in the future and explore if this can overcome the barriers to assistive technology use. Implications for rehabilitation End-user involvement, the design process can help enable customized assistive devices to be provided that better meet the user’s needs. The custom assistive devices provided not only helped the individuals overcome the challenges identified but had wider reaching benefits for the individuals physical and mental health and wellbeing. End-users valued being able to input into the co-design process and working closely with the clinician in developing the device.

Residual Neural Network and Long Short-Term Memory–Based Algorithm for Estimating the Motion Trajectory of Inertial Measurement Units

Motion trajectory is a technology used in smart medicine, rehabilitation engineering, and interactive games. Studies have proposed several motion trajectory tracking systems based on inertial measurement units (IMUs). However, these systems are beset by problems such as low adaptability to various activities and the capacity for only two-dimensional trajectory estimation. To solve these problems, this study proposed a three-dimensional (3D) motion trajectory tracking system based on a residual neural network (ResNet) and bidirectional long short-term memory (Bi-LSTM) to estimate the user’s trajectory of daily activities. A participant was asked to wear the IMU device and perform two types of specified activities, namely hand-movement tasks and walking. Nine degrees of freedom data from the IMUs were collected during these activities and input into the deep learning model, which combines ResNet and Bi-LSTM, to detect features and predict the motion trajectory. Several experiments were conducted to obtain the optimal system architecture and parameter settings and to evaluate the accuracy of motion trajectory estimation. The accuracy of the proposed system was also compared with those in other studies. The results demonstrated that the relative trajectory error of walking is 0.81 m and that of general cases is 0.54 m, which all outperforms the other related studies. The evidence indicated that the proposed system can predict the 3D motion trajectory of daily activities accurately and can be easily applied to track the motion of most daily activities.

Telerehabilitation Innovation in Response to Covid-19

The State of the Science Symposium is held multiple times per year to enhance the knowledge and skills of individuals working in the fields such as rehabilitation medicine, engineering, and public health. The Symposium has continually focused on the health and well-being of active-duty military members, reserve/guard components, veterans, and their families. With the onset of the COVID-19 pandemic and the social distancing protocols adopted to combat viral spread, the State of the Science Symposium was moved to an online platform to minimize risk. In December 2020, the symposium invited professionals to discuss necessary changes in their fields of practice in light of the pandemic protocols, and how telehealth has expanded to encompass multiple disciplines. It is concluded that the adoption of telemedicine as a standard of care wherever appropriate will benefit all parties involved, even after restrictions on gatherings and interpersonal contact are eased.