Cloud-supported framework for patients in post-stroke disability rehabilitation

https://doi.org/10.1016/j.tele.2017.12.001Get rights and content

Highlights

  • Cloud-based rehabilitation services for post-stroke hand disability.

  • Tensor-based pattern recognition technique to detect the real-time condition of patient.

  • The integration of cloud computing with AR-based rehabilitation system.

  • Multi-sensory big data oriented tensor approach to handle patient’s collected data.

Abstract

Given the flexibility and potential of cloud technologies, cloud-based rehabilitation frameworks have shown encouraging results as assistive tools for post-stroke disability rehabilitation exercises and treatment. To treat post-stroke disability, cloud-based rehabilitation offers great advantages over conventional, clinic-based rehabilitation, providing ubiquitous flexible rehabilitation services and storage while offering therapeutic feedback from a therapist in real-time during patients' rehabilitative movements. With the development of sensory technologies, cloud computing technology integrated with Augmented Reality (AR) may make therapeutic exercises more enjoyable. To achieve these objectives, this paper proposes a framework for cloud-based rehabilitation services, which uses AR technology along with other sensory technologies. We have designed a prototype of the framework that uses the mechanism of sensor gloves to recognize gestures, detecting the real-time condition of a patient doing rehabilitative exercises. This prototype framework is tested on twelve patients not using sensor gloves and on four patients wearing sensor gloves over six weeks. We found statistically significant differences between the forces exerted by patients’ fingers at week one compared to week six. Significant improvements in finger strength were found after six weeks of therapeutic rehabilitative exercises.

Introduction

Stroke is one of the most important reasons of long-term impairment in Saudi Arabia (Asirvatham and Marwan, 2014, Health Statistical, 2013, Al Khathaami et al., 2011, Al Jadid, 2011, Hamad et al., 2011, Al-Jadid and Robert, 2010) and around the world (Go et al., 2013, Heidenreich et al., 2011, HSF Canada, 2014, Hossain et al., 2016). Every year, many people suffer strokes, which lead to various disabilities on different parts of their bodies. To avoid and recover from disability, patients require rehabilitation services. The traditional stroke rehabilitation (Takeuchi and Izumi, 2013, Heart and Stroke Foundation of Canada, 2013) exercises are carried out in rehabilitation centers, located in special clinics or medical centers that may offer inadequate admission to patients living in the countryside. In this typical rehabilitation approach, a single patient can be provided therapy session by each therapist at a time. Patients might lose interest in doing repetitive tasks (Chen et al., 2008), such as moving their hands repeatedly. To address these challenges, rehabilitation systems may be based on Augmented Reality (AR), as have many recent rehabilitation systems (Alamri et al., 2008, Burke et al., 2010, Hu et al., 2016, Hossain et al., 2016), for seamless interaction with the combined real and virtual environment (Grealy and Nasser, 2012) so that patients’ treatment and performance can be monitored and measured.

Although AR-based serious games (Burke et al., 2010, Hu et al., 2016, Hossain et al., 2016) have countless advantages for post-stroke rehabilitation, existing rehabilitation systems (Al Jadid, 2011, Al-Jadid and Robert, 2010, Takeuchi and Izumi, 2013, Hossain et al., 2016, Grealy and Nasser, 2012, Dobkin, 2005, Karime et al., 2012) still require perfections with regards to their effectiveness, patient inspiration, cost-effectiveness, interactivity, and applicability to a wide variety of real-life treatments. Recently, cloud-assisted rehabilitation systems have emerged so that patients can do real-time exercises, ubiquitously. To improve the accuracy of the systems’ ability to recognize patients’ conditions and track their improvements, advanced technologies (AR, gesture/touch, etc.) are used in cloud-based rehabilitation, which deploys ubiquitous rehabilitation services with flexible data processing and storage services. The promise of cloud computing is that the patient, the doctor, and the therapist can access and share real-time healthcare-related data remotely, from anywhere and at any time. Computationally intensive tasks are deployed in the cloud server, and while client devices render user interfaces.

Considerable research efforts have been related to cloud-based (Hoda et al., 2015, Fardoun et al., 2013, Woodman et al., 2015) and remote-home-based rehabilitation (Karime et al., 2015, Karime et al., 2014, Atashzar et al., 2017) for the improvement of motor function at different aspects or levels. Hoda et al. (2015) proposed a cloud-based framework for the recovery of affected arms from stroke, where a therapist, based on feedback, can interact with patients to see the improvements in their upper limbs. Fardoun et al. (2013) presented CRehab, a cloud-oriented framework to provide virtual environments for rehabilitation exercises; a child was considered for this exercise, but no simulated or experimental results were presented. Woodman et al. (2015) illustrated an architecture for the cloud-based deployment of a therapy for upper-limb rehabilitation, with therapeutic data used to see the deployment of games. Game data are used in clinical settings only for user management, processing and storage. Atashzar et al. (2017) reported a tele-robotic rehabilitation architecture for analyzing stability, mentioning the possibility of deploying augmented-reality therapeutic capabilities. Recently, sensory technologies (Lange et al., 2011) have been used to capture human motion and gestures for rehabilitative purposes. These technologies open great opportunities for monitoring patients and tracking their progress. Much of the reported work provides some sort of rehabilitative exercise using the potential of cloud technology. However, the integration of AR-based serious games and cloud computing presents several challenges that have not yet been enough explored by the research community. Some of these challenges are the seamless transmission of patients’ real-time data to the cloud, effective analysis and correlation, processing of related data with regard to tracking patients’ progress, and finally integrating therapist feedback.

In this paper, we attempt to investigate these challenges to enable the design and development of a cloud-based framework for rehabilitation services that uses AR and other sensory technologies. We have designed cloud-supported, AR-based serious games in which a patient holds and moves a cup during a rehabilitation session. We also designed sensory gloves equipped with a gesture-recognition mechanism that detects patients’ real-time progress during their rehabilitation exercises. The sensory data from the gloves are delivered to the cloud server for later processing.

With the use of serious games and visual feedback in the rehabilitation process of the upper limb, objective measurements showed significant improvement in motor function and in patients’ control of the fingers during the study period. To track patient improvement from rehabilitation exercises, sensory gloves were used in the prototype, which was tested by two patients for six weeks; the patients demonstrated signification improvements in week six compared to week one. The contributions of this paper are as follows: (a) a framework that uses the combined potential of AR and cloud-based technologies to track patients' progress through colorful visual cues for the affected hand movements while holding cups in post-stroke rehabilitative exercises and (b) a prototype upper-limb, post-stroke rehabilitative exercise using sensor gloves that capture real patients' kinematics. Significant improvement in finger strength was observed after six weeks.

The rest of this article proceeds as follows. In Section 2, we presents some of the related works conducted in the cloud-supported post-stroke rehabilitation. Then, we briefly describe the proposed cloud-supported framework for disability rehabilitation in Section 3. Section 4 reports an early experimental evaluation of AR-based serious games without the use of sensory gloves, followed by the reported effects of sensory gloves on the rehabilitation process. Finally, Section 4 concludes.

Section snippets

Related study

Recently, cloud-oriented or tele-rehabilitation has gained tremendous insights with the evolutions of Augmented Reality (AR)–based video and/or serious games and smart sensors (e.g., Microsoft Kinect). Augmented Reality (AR)–based video and/or serious games can provide enjoyable environment for post-stroke disability rehabilitation exercises remotely by considering a Physical Therapist’s (PT) supervision or guidance. Here, we report some of the notable related works (Chen et al., 2008, Burke et

Cloud-supported framework for rehabilitation

The cloud-based, upper limb, post-stroke rehabilitation service adjusts and caters to patients’ rehabilitative needs. The framework provides real-time feedback to patients, summaries feedback after each session, and predicts the performance of rehabilitative services. Moreover, the cloud-oriented rehabilitative approach motivates patients to do rehabilitative exercises and allows therapists to remotely assess and control the progress of their patients. Fig. 1 depicts the proposed framework for

Experimental evaluation

This section reports an experimental evaluation with stroke-disabled patients of gameplay without and with sensory gloves. The first experiment, without sensory gloves, involved 12 patients, while gloves were tested with four real patients over six weeks.

Conclusion

This paper proposed a cloud-supported therapeutic rehabilitation framework for post-stroke patients utilizing the combined potential of cloud computing technology and AR, along with sensory gloves, to evaluate patients' performance and improvement while therapists interact with the system. Two sets of experimental evaluations were conducted to evaluate the suitability of the proposed framework. After six weeks of therapeutic rehabilitative exercises, improvements were observed in terms of the

Acknowledgement

The authors are grateful to the Deanship of Scientific Research at King Saud University – Saudi Arabia for funding this paper through the Vice Deanship of Scientific Research Chairs.

References (35)

  • A. Chatzitofis

    HeartHealth: a cardiovascular disease home-based rehabilitation system

    Proc. Comput. Sci.

    (2015)
  • M.S. Al Jadid

    Rehabilitation medicine in the Kingdom of Saudi Arabia

    Saudi Med. J.

    (2011)
  • A.M. Al Khathaami et al.

    The status of acute stroke care in Saudi Arabia: an urgent call for action

    Int. J. Stroke

    (2011)
  • A. Alamri

    Ar-rehab: an augmented reality framework for post-stroke patient rehabilitation

    IEEE Tran. Instr. Meas.

    (2008)
  • M.S. Al-Jadid et al.

    Determinants of length of stay in an inpatient stroke rehabilitation unit in Saudi Arabia

    Saudi Med. J.

    (2010)
  • A.R. Asirvatham et al.

    Stroke in Saudi Arabia: A review of the recent literature

    Pan Afr. Med. J.

    (2014)
  • S.F. Atashzar et al.

    A small-gain approach for nonpassive bilateral telerobotic rehabilitation: Stability analysis and controller synthesis

    IEEE Trans. Rob.

    (2017)
  • S.F. Atashzar et al.

    A passivity-based approach for stable patient–robot interaction in haptics-enabled rehabilitation systems: modulated time-domain passivity control

    IEEE Trans. Control Syst. Technol.

    (2017)
  • J.W. Burke et al.

    Augmented reality games for upper-limb stroke rehabilitation

    Proc. VS-GAMES

    (2010)
  • Y. Chen

    A dynamic decision network framework for online media adaptation in stroke rehabilitation

    ACM Trans. Multimedia Comput. Commun. Appl.

    (2008)
  • L. Connelly et al.

    A pneumatic glove and immersive virtual reality environment for hand rehabilitative training after stroke

    IEEE Trans. Neural Syst. Rehabil. Eng.

    (2010)
  • B. Dobkin

    Rehabilitation after stroke

    N. Engl. J. Med.

    (2005)
  • Fardoun, H.M., Altalhi, A.H., Cipres, A.P., Castillo, J.R., Albiol-Pérez, S., 2013. CRehab: a cloud-based framework for...
  • L.V. Gauthier et al.

    Video game rehabilitation for outpatient stroke (VIGoROUS): protocol for a multi-center comparative effectiveness trial of in-home gamified constraint-induced movement therapy for rehabilitation of chronic upper extremity hemiparesis

    BMC Neurol.

    (2017)
  • A.S. Go

    Heart disease and stroke statistics, 2014 update: a report from the American Heart Association

    Circulation

    (2013)
  • M. Grealy et al.

    The use of virtual reality in assisting rehabilitation

    ACNR

    (2012)
  • A.M. Hamad et al.

    Post stroke depression in acute stroke: Correlating with site and stroke severity

    Neurosciences

    (2011)
  • Cited by (0)

    View full text