Nowadays, a stroke is the fourth leading cause of death in the United States. In fact, every 40 seconds, someone in the US is having a stroke. Moreover, around 50% of stroke survivors suffer damage to the upper extremity –. Many actions of treating and recovering from a stroke have been developed over the years, but recent studies show that combining the recovery process with the existing rehabilitation plan provides better results and a raise in the patients quality of life –. Part of the stroke recovery process is a rehabilitation plan . The process can be difficult, intensive and long depending on how adverse the stroke and which parts of the brain were damaged. These processes usually involve working with a team of health care providers in a full extensive rehabilitation plan, which includes hospital care and home exercises.
1. D. Tsoupikova, N. S. Stoykov, M. Corrigan, K. Thielbar, R. Vick, Y. Li, K. Triandafilou, F. Preuss, D. Kamper, “Virtual immersion for poststroke hand rehabilitation therapy”, Annals of biomedical engineering, vol. 43, no. 2, pp. 467-477, 2015.
2. J. E. Pompeu, T. H. Alonso, I. B. Masson, S. M. A. A. Pompeu, C. Torriani-Pasin, “The effects of virtual reality on stroke rehabilitation: a systematic review”, Motricidade, vol. 10, no. 4, pp. 111-122, 2014.
3. J.-H. Shin, S. B. Park, S. H. Jang, “Effects of game-based virtual reality on health-related quality of life in chronic stroke patients: A randomized controlled study”, Computers in biology and medicine, vol. 63, pp. 92-98, 2015.
4. R. W. Teasell, L. Kalra, “Whats new in stroke rehabilitation”, Stroke, vol. 35, no. 2, pp. 383-385, 2004.
5. E. McDade, S. Kittner, “Ischemic stroke in young adults” in Stroke Essentials for Primary Care, Springer, pp. 123-146, 2009.
6. P. Langhorne, J. Bernhardt, G. Kwakkel, “Stroke rehabilitation”, The Lancet, vol. 377, no. 9778, pp. 1693-1702, 2011.
7. C. J. Winstein, J. Stein, R. Arena, B. Bates, L. R. Cherney, S. C. Cramer, F. Deruyter, J. J. Eng, B. Fisher, R. L. Harvey et al., “Guidelines for adult stroke rehabilitation and recovery: a guideline for healthcare professionals from the american heart association/american stroke association”, Stroke, vol. 47, no. 6, pp. e98-e169, 2016.
8. R. Ibanez, A. Soria, A. Teyseyre, M. Campo, “Easy gesture recognition for kinect”, Advances in Engineering Software, vol. 76, pp. 171-180, 2014.
9. R. Ibañez, A. Soria, A. R. Teyseyre, L. Berdun, M. R. Campo, “A comparative study of machine learning techniques for gesture recognition using kinect”, Handbook of Research on Human-Computer Interfaces Developments and Applications, pp. 1-22, 2016.
10. S. Bhattacharya, B. Czejdo, N. Perez, “Gesture classification with machine learning using kinect sensor data”, Emerging Applications of Information Technology (EAIT) 2012 Third International Conference on, pp. 348-351, 2012.
11. K. Laver, S. George, S. Thomas, J. E. Deutsch, M. Crotty, “Virtual reality for stroke rehabilitation”, Stroke, vol. 43, no. 2, pp. e20-e21, 2012.
12. G. Saposnik, M. Levin, S. O. R. C. S. W. Group et al., “Virtual reality in stroke rehabilitation: a meta-analysis and implications for clinicians”, Stroke, vol. 42, no. 5, pp. 1380-1386, 2011.
13. K. R. Anderson, M. L. Woodbury, K. Phillips, L. V. Gauthier, “Virtual reality video games to promote movement recovery in stroke rehabilitation: a guide for clinicians”, Archives of physical medicine and rehabilitation, vol. 96, no. 5, pp. 973-976, 2015.
14. A. Estepa, S. S. Piriz, E. Albornoz, C. Martínez, “Development of a kinect-based exergaming system for motor rehabilitation in neurological disorders”, Journal of Physics: Conference Series, vol. 705, pp. 012060, 2016.
15. E. Chang, X. Zhao, S. C. Cramer et al., “Home-based hand rehabilitation after chronic stroke: Randomized controlled single-blind trial comparing the musicglove with a conventional exercise program”, Journal of rehabilitation research and development, vol. 53, no. 4, pp. 457, 2016.
16. L. Ebert, P. Flach, M. Thali, S. Ross, “Out of touch-a plugin for controlling osirix with gestures using the leap controller”, Journal of Forensic Radiology and Imaging, vol. 2, no. 3, pp. 126-128, 2014.
17. W.-J. Li, C.-Y. Hsieh, L.-F. Lin, W.-C. Chu, “Hand gesture recognition for post-stroke rehabilitation using leap motion”, Applied System Innovation (ICASI) 2017 International Conference on, pp. 386-388, 2017.
18. K. Vamsikrishna, D. P. Dogra, M. S. Desarkar, “Computer-vision-assisted palm rehabilitation with supervised learning”, IEEE Transactions on Biomedical Engineering, vol. 63, no. 5, pp. 991-1001, 2016.
19. A. Butt, E. Rovini, C. Dolciotti, P. Bongioanni, G. De Petris, F. Cavallo, “Leap motion evaluation for assessment of upper limb motor skills in parkinson’s disease”, Rehabilitation Robotics (ICORR) 2017 International Conference on, pp. 116-121, 2017.
20. L. Di Tommaso, S. Aubry, J. Godard, H. Katranji, J. Pauchot, “A new human machine interface in neurosurgery: The leap motion (®). technical note regarding a new touchless interface”, Neuro-Chirurgie, vol. 62, no. 3, pp. 178-181, 2016.
21. O. Chapelle, “Training a support vector machine in the primal”, Neural computation, vol. 19, no. 5, pp. 1155-1178, 2007.
22. Y. Ma, G. Guo, Support vector machines applications, Springer, 2014.
23. J. Guna, G. Jakus, M. Pogačnik, S. Tomažič, J. Sodnik, “An analysis of the precision and reliability of the leap motion sensor and its suitability for static and dynamic tracking”, Sensors, vol. 14, no. 2, pp. 3702-3720, 2014.
24. T. DOrazio, R. Marani, V. Renó, G. Cicirelli, “Recent trends in gesture recognition: how depth data has improved classical approaches”, Image and Vision Computing, vol. 52, pp. 56-72, 2016.
25. L. Motion, Leap motion sdk, 2015.
via Hand Rehabilitation via Gesture Recognition Using Leap Motion Controller – IEEE Conference Publication
Electromyography (EMG), a technique used to analyze and record electric current produced by skeletal muscles, has been used to control replacement limbs, and diagnose muscle irregularities. In this work, an EMG based system comprising of an orthotic arm and finger device to aid in muscle rehabilitation, is presented. As the user attempts to contract their bicep or forearm muscles, the system senses the change in the EMG signals and in turn triggers the motors to assist with flexion and extension of the arm and fingers. As brain is a major factor for muscle growth, mental training using motor imagery was incorporated into the system. Subjects underwent mental training to show the capability of muscle growth. The measured data reveals that the subjects were able to compensate for the loss of muscle growth, due to shorter physical training sessions, with mental training. Subjects were then tested using the orthotic arm and finger rehabilitation device with motor imagery. The findings also showed a positive increase in muscle growth using the rehabilitation system. Based on the experimental results, the EMG rehabilitation system presented in this paper has the potential to increase muscle strength and improve the recovery rate for muscle injuries, partial paralysis, or muscle irregularities.
via Electromyography Based Orthotic Arm and Finger Rehabilitation System – IEEE Conference Publication
In the modern world, due to an increased aging population, hand disability is becoming increasingly common. The prevalence of conditions such as stroke is placing an ever-growing burden on the limited fiscal resources of health care providers and the capacity of their physical therapy staff. As a solution, this paper presents a novel design for a wearable and adaptive glove for patients so that they can practice rehabilitative activities at home, reducing the workload for therapists and increasing the patient’s independence. As an initial evaluation of the design’s feasibility the prototype was subjected to motion analysis to compare its performance with the hand in an assessment of grasping patterns of a selection of blocks and spheres. The outcomes of this paper suggest that the theory of design has validity and may lead to a system that could be successful in the treatment of stroke patients to guide them through finger flexion and extension, which could enable them to gain more control and confidence in interacting with the world around them.
In the modern world an extended life expectancy coupled with a sedentary lifestyle raises concerns over long term health in the population. This is highlighted by the increasing incidence of disability stemming from multiple sources, for example medical conditions such as cancer or stroke . While avoiding the lifestyle factors that have a high association with these diseases would be the preferred solutions of health services the world over, as populations get progressively older and more sedentary, this becomes increasingly more difficult , . The treatment of these conditions is often complex; in stroke for example, the initial incident is a constriction of blood flow in the brain which in turn damages the nervous system’s ability to communicate with the rest of the body. This damage will occur in one hemisphere of the body but can impact both the upper and lower limbs, as well as impairing functional processes such as speech and cognitive thinking.
via Design and Evaluation of a Soft and Wearable Robotic Glove for Hand Rehabilitation – IEEE Journals & Magazine
Soft robotic devices have the potential to be widely used in daily lives for their inherent compliance and adaptability, which result in high safety under unexpected situations. System complexity and requirements are much lower, comparing with conventional rigid-bodied robotic devices, which also result in significantly lower costs. This paper presents a robotic glove by utilizing soft artificial muscles providing redundant degrees of freedom (DOFs) to generate both flexion and extension hand motions for daily grasping and manipulation tasks. Different with the existing devices, to minimize the weight applied to the user’s hands, pneumatic soft actuators were located on the fore arm and drive each finger via cable-transmission mechanisms. This actuation mechanism brings extra adaptability, motion smoothness, and user safety to the system. This design makes wearable robotic gloves more light-weight and user-friendly. Both theoretical and experimental analyses were conducted to explore the mechanical properties of pneumatic soft actuators. In addition, the fingertip trajectories were analyzed using Finite Element Methods, and a series of experiments were conducted evaluating both the technical and practical performances of the proposed glove.
Glove-type wearable robotic devices are developed to assist people with impaired hand functions both in their activities of daily living (ADLs) and in rehabilitation –. Most of such wearable robotic devices generate hand movements with linkage systems actuated by electrical motors which usually are heavy and inconvenient for using. Moreover, because of the human hand variation, most wearable robotic devices require customization in order to fulfill the geometrical fitting requirements between the exoskeleton device and the human hand joints. Approximating the high dexterity of human hands usually requires high complexity in both the mechanical and controller structures of the robotic systems, and hence also results in high costs for most users.
via A soft robotic glove for hand motion assistance – IEEE Conference Publication
Recent technological developments regarding wearable soft-robotic devices extend beyond the current application of rehabilitation robotics and enable unobtrusive support of the arms and hands during daily activities. In this light, the HandinMind (HiM) system was developed, comprising a soft-robotic, grip supporting glove with an added computer gaming environment. The present study aims to gain first insight into the feasibility of clinical application of the HiM system and its potential impact. In order to do so, both the direct influence of the HiM system on hand function as assistive device and its therapeutic potential, of either assistive or therapeutic use, were explored. A pilot randomized clinical trial was combined with a cross-sectional measurement (comparing performance with and without glove) at baseline in 5 chronic stroke patients, to investigate both the direct assistive and potential therapeutic effects of the HiM system. Extended use of the soft-robotic glove as assistive device at home or with dedicated gaming exercises in a clinical setting was applicable and feasible. A positive assistive effect of the soft-robotic glove was proposed for pinch strength and functional task performance `lifting full cans’ in most of the five participants. A potential therapeutic impact was suggested with predominantly improved hand strength in both participants with assistive use, and faster functional task performance in both participants with therapeutic application.
Neurorehabilitation research has shown that training programs for patients after stroke should ideally consist of high intensity, task-specific and functional exercises with active contribution of the patient, to have the best chance for improving arm/hand function , . Conventional rehabilitation involves predominantly one-to-one attention of a therapist for each patient, which is a challenge when aiming to provide high intensity training and involves high costs , . This is impeded further by an increased ageing of the population, associated with a higher prevalence of stroke patients and less healthcare professionals available to provide such intensive training.
via Applying a soft-robotic glove as assistive device and training tool with games to support hand function after stroke: Preliminary results on feasibility and potential clinical impact – IEEE Conference Publication
After leaving hospital, patients can carry out rehabilitation by using rehabilitation devices. However, they cannot evaluate the recovery by themselves. For this problem, a device which can both carry out the rehabilitation and evaluation of the degree of recovery is required. This paper proposes the method that quantifies the recovery of the paralysis of fingers to evaluate a patient automatically. A finger movement is measured by a pressure sensor on the rehabilitation device we have developed. A measured data is used as a time-series signal, and the recovery of the paralysis is quantified by calculating the dissimilarity between a healthy subject’s signal and the patient’s signal. The results of those dissimilarities are integrated over all finger to be used as a quantitative scale of recovery. From the experiment conducted with hemiplegia patients and healthy subjects, we could trace the process of the recovery by the proposed method.
Source: Quantification method of motor function recovery of fingers by using the device for home rehabilitation – IEEE Conference Publication
Published in: Rehabilitation Robotics (ICORR), 2017 International Conference on
Recent technological developments regarding wearable soft-robotic devices extend beyond the current application of rehabilitation robotics and enable unobtrusive support of the arms and hands during daily activities. In this light, the HandinMind (HiM) system was developed, comprising a soft-robotic, grip supporting glove with an added computer gaming environment. The present study aims to gain first insight into the feasibility of clinical application of the HiM system and its potential impact. In order to do so, both the direct influence of the HiM system on hand function as assistive device and its therapeutic potential, of either assistive or therapeutic use, were explored. A pilot randomized clinical trial was combined with a cross-sectional measurement (comparing performance with and without glove) at baseline in 5 chronic stroke patients, to investigate both the direct assistive and potential therapeutic effects of the HiM system. Extended use of the soft-robotic glove as assistive device at home or with dedicated gaming exercises in a clinical setting was applicable and feasible. A positive assistive effect of the soft-robotic glove was proposed for pinch strength and functional task performance ‘lifting full cans’ in most of the five participants. A potential therapeutic impact was suggested with predominantly improved hand strength in both participants with assistive use, and faster functional task performance in both participants with therapeutic application.
Source: Applying a soft-robotic glove as assistive device and training tool with games to support hand function after stroke: Preliminary results on feasibility and potential clinical impact – IEEE Xplore Document
Surface electromyographic (sEMG) signals is one most commonly used control source of exoskeleton for hand rehabilitation. Due to the characteristics of non-invasive, convenient collection and safety, sEMG can conform to the particularity of hemiplegic patients’ physiological state and directly reflect human’s neuromuscular activity. By way of collecting, analyzing and processing, sEMG signals corresponding to identify the target movement model would be translated into robot movement control instructions and input into hand rehabilitation exoskeleton controller. Then patients’ hand can be directed to achieve the realization of the similar action finally. In this paper, the recent key technologies of sEMG-based control for hand rehabilitation robots are reviewed. Then a summarization of controlling technology principle and methods of sEMG signal processing employed by the hand rehabilitation exoskeletons is presented. Finally suitable processing methods of multi-channel sEMG signals for the controlling of hand rehabilitation exoskeleton are put forward tentatively and the practical application in hand exoskeleton control is commented also.
Source: A survey on sEMG control strategies of wearable hand exoskeleton for rehabilitation – IEEE Xplore Document
Finger recovery is much harder than other parts on the upper limbs, because finger recovery movement has several key problems need to overcome, including high precision of movement, high control resolution requirements, variable data with different person, as well as the fuzzy signal during the movement. In order to overcome the difficulties, a new scheme of finger recovery is presented in the paper based on symmetric rehabilitation. In the paralyzed hand side, a mechanical exoskeleton hand is designed and simulated to provide skeletal traction, while in the regular hand side, the curve magnitude of every joint during movement is detected. Then the hand motion is analyzed and recognized using Multi-class SVM. Many candidates were chosen to perform the experiment, and the data produced by the candidates were divided the training parts and recognition parts. Experiments shows that the Multi-class SVM is effective and practical for classification and recognition, and could be helpful in the finger recovery process.
Source: A novel scheme of finger recovery based on symmetric rehabilitation: Specially for hemiplegia – IEEE Xplore Document
This paper describes the design of a FES system automatically controlled in a closed loop using a Microsoft Kinect sensor, for assisting both cylindrical grasping and hand opening. The feasibility of the system was evaluated in real-time in stroke patients with hand function deficits. A hand function exercise was designed in which the subjects performed an arm and hand exercise in sitting position. The subject had to grasp one of two differently sized cylindrical objects and move it forward or backwards in the sagittal plane. This exercise was performed with each cylinder with and without FES support. Results showed that the stroke patients were able to perform up to 29% more successful grasps when they were assisted by FES. Moreover, the hand grasp-and-hold and hold-and-release durations were shorter for the smaller of the two cylinders. FES was appropriately timed in more than 95% of all trials indicating successful closed loop FES control. Future studies should incorporate options for assisting forward reaching in order to target a larger group of stroke patients.
Source: Design and Test of a Closed-Loop FES System for Supporting Function of the Hemiparetic Hand Based on Automatic Detection using the Microsoft Kinect sensor – IEEE Xplore Document