ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Factors affecting real-time evaluation of muscle function in smart rehab systems

  • Hyunwoo Joe (Mobility UX Research Section, Electronics and Telecommunications Research Institute) ;
  • Hyunsuk Kim (Mobility UX Research Section, Electronics and Telecommunications Research Institute) ;
  • Seung-Jun Lee (Mobility UX Research Section, Electronics and Telecommunications Research Institute) ;
  • Tae Sung Park (Department of Convergence Medical Institute of Technology, Pusan National University Hospital) ;
  • Myung-Jun Shin (Department of Rehabilitation Medicine, Pusan National University Hospital) ;
  • Lee Hooman (EXOSYSTEMS) ;
  • Daesub Yoon (Mobility UX Research Section, Electronics and Telecommunications Research Institute) ;
  • Woojin Kim (Mobility UX Research Section, Electronics and Telecommunications Research Institute)
  • Received : 2021.10.30
  • Accepted : 2022.11.07
  • Published : 2023.08.10
Download PDF
⟨ Previous Next ⟩

Abstract

Advancements in remote medical technologies and smart devices have led to expectations of contactless rehabilitation. Conventionally, rehabilitation requires clinicians to perform routine muscle function assessments with patients. However, assessment results are difficult to cross-reference owing to the lack of a gold standard. Thus, the application of remote smart rehabilitation systems is significantly hindered. This study analyzes the factors affecting the real-time evaluation of muscle function based on biometric sensor data so that we can provide a basis for a remote system. We acquired real clinical stroke patient data to identify the meaningful features associated with normal and abnormal musculature. We provide a system based on these emerging features that assesses muscle functionality in real time via streamed biometric signal data. A system view based on the amount of data, data processing speed, and feature proportions is provided to support the production of a rudimentary remote smart rehabilitation system.

Keywords

Acknowledgement

This work was partly supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) with a grant funded by the Korean Government (MSIT) (No. 2022-0-00501, Development of Wearable Device Assessment Technology, 50%) and the Korea Evaluation Institute of Industrial Technology (KEIT) with a grant funded by the Korean Government (MOTIE) (No. P0007114, InterConnected Intelligent Sensing and Actuation Solutions for At-home Rehabilitation (iCARE), 50%). The authors thank all iCARE project members in the Republic of Korea and Spain, as well as the patients who agreed to support our clinical trials (IRB No. 1870-012-068) in PNUH.

References

  1. World Health Organization, Global health estimates summary tables: projection of deaths by cause, age and sex, World Bank Income Group, Geneva, 2018.
  2. J. K. Burton, E. E. Ferguson, A. J. Barugh, K. E. Walesby, A. M. Maclullich, S. D. Shenkin, and T. J. Quinn, Predicting discharge to institutional long-term care after stroke: a systematic review and metaanalysis, J. Am. Geriatr. Soc. 66 (2018), no. 1, 161-169. https://doi.org/10.1111/jgs.15101
  3. A. David, R. Ramadoss, A. Ramachandran, and S. Sivapatham, Activity recognition of stroke-affected people using wearable sensor, ETRI J. 2023. https://doi.org/10.4218/etrij.2022-0242
  4. C. Salgueiro, G. Urrutia, and R. Cabanas-Valdes, Available apps for stroke telerehabilitation during corona virus disease 2019 confinement in Spain, Disabil. Rehabil. Assist. Technol. 12, no. 2021, 1-11. https://doi.org/10.1080/17483107.2021.1883751
  5. M. W. B. Zhang and R. Ho, Harnessing the potential of the Kinect sensor for psychiatric rehabilitation for stroke survivors, Technol. Health Care 24 (2016), no. 4, 599-602. https://doi.org/10.3233/THC-161147
  6. N.B. Ogur, M. Al-Hubaishi, and C. Ceken, IoT data analytics architecture for smart healthcare using RFID and WSN, ETRI J. 44 (2022) 1, 135-146. https://doi.org/10.4218/etrij.2020-0036
  7. T. S. Park, S. H. Kim, J. H. Kang, and M.-J. Shin, The assessment of balance ability and development of indicators for normal adults in Korea in their 20s using digital equipment (FRA 510 S), J. Convergence Inform. Technol. 10 (2020), no. 9, 215-221.
  8. S. H. An and C. S. Park, The reliability and validity of short form of the Fugl-Meyer assessment scale in patients with stroke, J. Special Education & Rehabil. Sci. 54 (2015), no. 1, 159-172. https://doi.org/10.15870/jsers.2015.03.54.1.159
  9. Ethical approval, Pusan National University Hospital Institutional Review Board (IRB No. 1870-012-068).
  10. H. Zeng and Y. Zhao, Sensing movement: microsensors for body motion measurement, Sensors 11 (2011), 638-660. https://doi.org/10.3390/s110100638
  11. W. Kim, H. Joe, H. Kim, S.-J. Lee, D. Yoon, J. H. Jung, B. B. Acuna, H. Lee, J. F. Raton, C. F. Isoird, I. Marinelarena, M. A. A. Alonso, M.-J. Shin and T. S. Park, Requirements for upper-limb rehabilitation with FES and exoskeleton, (International Conference on Intelligent Human Computer Interaction, Daegu, Republic of Korea), 2020, pp. 172-177.
  12. J. Krukowska, M. Bugajski, M. Sienkiewicz, and J. Czernicki, The influence of NDT-Bobath and PNF methods on the field support and total path length measure foot pressure (COP) in patients after stroke, Neurol. Neurochir. Pol. 50 (2016), no. 6, 449-454. https://doi.org/10.1016/j.pjnns.2016.08.004
  13. J.-S. Wang, S.-B. Lee, and S.-H. Moon, The immediate effect of PNF pattern on muscle tone and muscle stiffness in chronic stroke patient, J. Phys. Ther. Sci. 28 (2016), no. 3, 967-970. https://doi.org/10.1589/jpts.28.967
  14. M. Bhadane, J. Liu, W. Z. Rymer, P. Zhou, and S. Li, Re-evaluation of EMG-torque relation in chronic stroke using linear electrode array EMG recordings, Sci. Rep. 6 (2016), no. 1, 1-10. https://doi.org/10.1038/s41598-016-0001-8
  15. X. Song, S. Chen, J. Jia, and P. B. Shull, Cellphone-based automated Fugl-Meyer assessment to evaluate upper extremity motor function after stroke, IEEE Trans. Neural Syst. Rehabil. Eng. 27 (2019), no. 10, 2186-2195. https://doi.org/10.1109/TNSRE.2019.2939587
  16. J. V. Basmajian and C. J. De Luca, Muscles alive: their functions revealed by electromyography, Williams & Wilkins, Baltimore, MD, 1985.
  17. M. A. Oskoei and H. Hu, Support vector machine-based classification scheme for myoelectric control applied to upper limb, IEEE Trans. Biomed. Eng. 55 (2008), no. 8, 1956-1965. https://doi.org/10.1109/TBME.2008.919734
  18. H. J. Chizeck, O. Johnson, and J. Herron, U.S. Patent No. 9,223,459, U.S. Patent and Trademark Office, Washington, DC, 2015.
  19. Korea Institute of Science and Technology, Korea Patent No. 10-2014-0107741, Korean Intellectual Property Office, 2014.
  20. D.-H. Kim, C.-Y. Cho, and J. Ryu, Real-time locomotion mode recognition employing correlation feature analysis using EMG pattern, ETRI J. 36 (2014), no. 1, 99-105. https://doi.org/10.4218/etrij.14.0113.0064
  21. J.-U. Chu, I. Moom, Y.-J. Lee, S.-K. Kim, and M.-S. Mun, A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control, IEEE/ASME Trans. Mechatronics 12 (2007), no. 3, 282-290. https://doi.org/10.1109/TMECH.2007.897262
  22. K. Ma, Y. Chen, X. Zhang, H. Zheng, S. Yu, S. Cai, and L. Xie, sEMG-based trunk compensation detection in rehabilitation training, Front. Neurosci. 13 (2019). https://doi.org/10.3389/fnins.2019.01250
  23. Z. Yang and Y. Chen, Surface EMG-based sketching recognition using two analysis windows and gene expression programming, Front. Neurosci. 10 (2016). https://doi.org/10.3389/fnins.2016.00445
  24. E. Trigili, L. Grazi, S. Crea, A. Accogli, J. Carpaneto, S. Micera, N. Vitiello, and A. Panarese, Detection of movement onset using EMG signals for upper-limb exoskeletons in reaching tasks, J. Neuroeng. Rehabil. 16 (2019), no. 1, 1-16. https://doi.org/10.1186/s12984-018-0454-z
  25. A. Phinyomark, P. Phukpattaranont, and C. Limsakul, The usefulness of wavelet transform to reduce noise in the SEMG signal, In EMG methods for evaluating muscle and nerve function, Mark Schwartz, Rijeka, Croatia, InTech, 2012. https://doi.org/10.5772/25757
  26. R. Boostani and M. H. Moradi, Evaluation of the forearm EMG signal features for the control of a prosthetic hand, Physiol. Meas. 24 (2003), 309-319. https://doi.org/10.1088/0967-3334/24/2/307
  27. A. Phinyomark, S. Hirunviriya, C. Limsakul, and P. Phukpattaranont, Evaluation of EMG Feature Extraction for Hand Movement Recognition Based on Euclidean Distance and Standard Deviation, (International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, Chiang Mai, Thailand,) 2010.
  28. F. Khanam and M. Ahmad, Frequency Based EMG Power Spectrum Analysis of Salat Associated Muscle Contraction, (International Conference on Electrical & Electronic Engineering, Rajshahi, Bangladesh), 2015. https://doi.org/10.1109/CEEE.2015.7428245
  29. A. Phinyomark, S. Thongpanja, H. Hu, P. Phukpattaranont, and C. Limsakul, The Usefulness of Mean and Median Frequencies in Electromyography Analysis, in Computational Intelligence in Electromyography Analysis-A Perspective on Current Applications and Future Challenges, 2011. https://doi.org/10.5772/50639
  30. H. Joe and H. Kim, Effects of dynamic isolation for full virtualized RTOS and GPOS guests, Future Gener. Comput. Syst. 70 (2017), 26-41. https://doi.org/10.1016/j.future.2016.12.020
  31. R. Ma, F. Zhou, E. Zhu, and H. Guan, Performance tuning towards a KVM-based embedded real-time virtualization system, J. Inf. Sci. Eng. 29 (2013), 1021-1035.
  32. J. Kiszka, Towards Linux as a real-time hypervisor, (Proceedings of the 11th Real-Time Linux Workshop), 2009, pp. 205-215.
  33. Tensorflow lite. https://www.tensorflow.org/lite (accessed on 24.10.21)
  34. X. Zhang, H. Huang, and Q. Yang, Real-time implementation of a self-recovery EMG pattern recognition interface for artificial arms, (Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society [EMBC], Osaka, Japan), 3-7 July 2013, pp. 5926-5929.
  35. E. Mastinu, S. Member, and J. Ahlberg, An alternative myoelectric pattern recognition approach for the control of hand prostheses: a case study of use in daily life by a dysmelia subject, IEEE J. Transl. Eng. Health Med. 6 (2018), 1-12. https://doi.org/10.1109/JTEHM.2018.2811458
  36. S. Raurale, J. McAllister, J. M. del Rincon, EMG Wrsit-Hand Motion Recognition System for Real-Time Embedded Platform, (IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, UK), 2019, pp. 1523-1527.
  37. R. B. Woodward and L. J. Hargrove, Adapting myoelectric control in real-time using a virtual environment, J. Neuroeng. Rehabil. 16 (2019), 11.
  38. T. A. Kuiken, B. A. Lock, R. D. Lipschutz, L. A. Miller, K. A. Stubblefield, and K. B. Englehart, Targeted muscle reinnervation for real-time myoelectric control of multifunction artificial arms, JAMA J. Am. Med. Assoc. 301 (2009), 619-628. https://doi.org/10.1001/jama.2009.116
  39. B. Chen, C. Chen, J. Hu, T. N. Nguyen, J. Qi, B. Yang, D. Chen, Y. Alshahrani, Y. Zhou, A. Tsai, and T. Frush, A realtime myoelectric signal based fixed-bandwidth frequency-domain embedded system for robotic hand, Front. Neurorobot. 16 (2022), 880073.