Journal of the Korean Society of Physical Medicine (대한물리의학회지)

The Korean Society of Physical Medicine (대한물리의학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Field Application and Prospect of Artificial Intelligence and Bio-Sensing Technology in Physical Therapy: Focusing on Customized Rehabilitation Treatment

물리치료 분야에서 인공지능 및 바이오센싱 기술의 현장적용 및 전망에 관한 연구: 맞춤형 재활치료를 중심으로

  • 유경태 (남서울대학교 물리치료학과)
  • Received : 2023.07.04
  • Accepted : 2023.07.20
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

PURPOSE: This study analyzed the impact of AI and biosensors on physical therapy, identifying the stage of customized technology development and future prospects. AI and biosensors improve the efficiency, establish customized treatment plans, and expand patient treatment opportunities. The study employed a literature review by searching databases and collecting research. METHODS: This study searched various databases related to the topic, collected existing research, papers, and reports, evaluated the literature, and summarize the results. RESULTS: Exercise therapy utilizing artificial intelligence can provide personalized and optimal exercise plans while monitoring rehabilitation progress. In addition, biosensors such as EMG sensors and accelerometers can monitor the individual progress in physical therapy, particularly in stroke patients, which can help improve physical therapy strategy and promote patient recovery. CONCLUSION: This study suggested that artificial intelligence can be applied in many areas of physical therapy, such as exercise therapy, customized treatment plans, rehabilitation and management, pain management, neuro rehabilitation, and auxiliary devices. Using AI technology, it is possible to analyze and improve exercise and posture, retrain the central nervous system, establish customized treatment plans for individual patients, predict and compare patient progress before and after treatment, and provide customized pain analysis and treatment methods. In addition, AI can provide neuro rehabilitation programs and customized auxiliary devices.

Keywords

Acknowledgement

Funding for this paper was provided by Namseoul University

References

  1. Faddis A. The digital transformation of healthcare technology management. Biomed Instrum Technol. 2018;52(s2):34-8. https://doi.org/10.2345/0899-8205-52.s2.34
  2. Kraus S, Schiavone F, Pluzhnikova, A. et al. Digital transformation in healthcare: analyzing the current state-of-research. J Bus Res. 2021;123(C):557-67. https://doi.org/10.1016/j.jbusres.2020.10.030
  3. Morillas G, Juan J. The digital transformation of the aerospace industry in the madrid region: a study of the situation and future trends. technology, business, innovation, and entrepreneurship in industry 4.0. Cham: Springer International Publishing, 2022.
  4. Ovais M , Zia N, Ahmad I, Khalil AT, Raza A, Ayaz M, Sadiq A, Ullah F, Shinwari ZK. Phyto-therapeutic and nanomedicinal approaches to cure alzheimer's disease: Present status and future opportunities. Front Aging Neurosci. 2018;10:284.
  5. Helm JM, Swiergosz AM, Haeberle HS, Karnuta JM, Schaffer JL, Krebs VE, Spitzer AI, Ramkumar PN. Machine learning and artificial intelligence: definitions, applications, and future directions. Curr Rev Musculoskelet Med. 2020;13(1):69-76. https://doi.org/10.1007/s12178-020-09600-8
  6. Wu Y, Ma Z, Zhao H, et al. Achieve personalized exercise intensity through an intelligent system and cycling equipment: A machine learning approach. Appl Sci. 2020;10:7688.
  7. Issam B, Xiaojun Z, Victor U, et al. Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review. Biomed. Signal Processing. Control. 2022;71:103197.
  8. Ian G, Yoshua B, Aaron Courville. Deep learning. The MIT Press. 2016.
  9. Jordan MI, Tom MM. Machine learning: Trends, perspectives, and prospects. Science 349. 2015;255-60. https://doi.org/10.1126/science.aaa8415
  10. Domingos P. The master algorithm: how the quest for the ultimate learning machine will remake our world. Basic Books. 2015.
  11. Ruiz-Real JL, Juan UT, Jose AT, et al. Artificial intelligence in business and economics research: trends and future. J Bus Econ Manag. 2021;22(1):98-117. https://doi.org/10.3846/jbem.2020.13641
  12. Hansen EB, Simon B. Artificial intelligence and internet of things in small and medium-sized enterprises: A survey. J Manuf Syst. 2021;58:362-72. https://doi.org/10.1016/j.jmsy.2020.08.009
  13. Susan L, Anu M, James M, et al. The future of work after COVID-19. McKinsey Global Institute 18. 2021.
  14. Brougham D, Jarrod H. Smart technology, artificial intelligence, robotics, and algorithms (STARA): Employees' perceptions of our future workplace. J Manag Organ. 2018;24(2):239-57. https://doi.org/10.1017/jmo.2016.55
  15. Xiao C, Choi E, Sun J. Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review. J Am Med Inform Assoc. 2018;25(10):1419-28. https://doi.org/10.1093/jamia/ocy068
  16. Doi K. Current status and future potential of computer-aided diagnosis in medical imaging. Br J Radiol. 2005;78(1): S3-S19. https://doi.org/10.1259/bjr/82933343
  17. Wang Z, Allam M, Mingbiao L. Research on e-commerce personalized recommendation system based on big data technology. 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA). 2021;2.
  18. Safdar NM, Banja JD, Meltzer CC. Ethical considerations in artificial intelligence. Eur J Radiol. 2020;122:108768.
  19. Jayanthi VSPKSA, Das AB, Saxena U. Recent advances in biosensor development for the detection of cancer biomarkers. Biosens Bioelectron. 2017;91:15-23. https://doi.org/10.1016/j.bios.2016.12.014
  20. de Faria LV, Lisboa TP, Campos NDS, Alves GF, Matos MAC, Matos RC, Munoz RAA. Electrochemical methods for the determination of antibiotic residues in milk: A critical review. Anal Chim Acta. 2021;1173:338569.
  21. Justino CIL, Duarte AC, Rocha-Santos TAP. Recent progress in biosensors for environmental monitoring: a review. Sensors (Basel). 2017;17(12):2918.
  22. Christian G, Antje JB. Biosensors to support sustainable agriculture and food safety. TrAC Trends in Analytical Chemistry 2020;128:115906.
  23. Velusamy V, Arshak K, Korostynska O, et al. An overview of foodborne pathogen detection: in the perspective of biosensors. Biotechnol Adv. 2010;28(2):232-54. https://doi.org/10.1016/j.biotechadv.2009.12.004
  24. Kairy D, Lehoux P, Vincent C, et al. A systematic review of clinical outcomes, clinical process, healthcare utilization and costs associated with telerehabilitation. Disabil Rehabil. 2009;31(6):427-47. https://doi.org/10.1080/09638280802062553
  25. Eliasz K. Recognition of sedentary behavior by machine learning analysis of wearable sensors during activities of daily living for telemedical assessment of cardiovascular risk. Sensors. 2018;18(10):3219.
  26. Peretti A, Amenta F, Tayebati SK, Nittari G, Mahdi SS. Telerehabilitation: review of the state-of-the-art and areas of application. JMIR Rehabil Assist Technol. 2017;4(2):e7.
  27. Saba Raoof S, Durai MAS. A comprehensive review on smart health care: applications, paradigms, and challenges with case studies. Contrast Media Mol Imaging. 2022;2022:4822235.
  28. Kabir ZN, Leung AYM, Grundberg A, et al. Care of family caregivers of persons with dementia (CaFCa) through a tailor-made mobile app: study protocol of a complex intervention study. BMC Geriatr. 2020;20(1): 305.
  29. Gregory K, Dimitrios C, Despoina P, et al. Gamified platform for rehabilitation after total knee replacement surgery employing low cost and portable inertial measurement sensor node. Multimed Tools Appl. 2020;79:3161-88. https://doi.org/10.1007/s11042-018-6572-6
  30. David W, Zaki H. Developing an artificial intelligence-enabled health care practice: rewiring health care professions for better care. J Medical Imaging Radiat Sci. 2019;50(4): S8-S14. https://doi.org/10.1016/j.jmir.2019.09.010
  31. Saravi B, Zink A, ulkumen S, et al. Performance of artificial intelligence-based algorithms to predict prolonged length of stay after lumbar decompression surgery. J Clin Med. 2022;11(14):4050.
  32. Giansanti D, Castrichella L, Giovagnoli MR. New models of e-learning for healthcare professionals: a training course for biomedical laboratory technicians. J Telemed Telecare. 2007;13(7):374-6. https://doi.org/10.1258/135763307782215334
  33. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018;2(10):719-31. https://doi.org/10.1038/s41551-018-0305-z
  34. Gordon AM, Richard M. Motor learning: application of principles to pediatric rehabilitation. Campbell's Physical Therapy for Children Expert Consult-E-Book. 2016.
  35. Yao S, Swetha P, Zhu Y. Nanomaterial-enabled wearable sensors for healthcare. Adv Healthc Mater. 2018; 7(1):1-10 https://doi.org/10.11648/j.am.20180701.11
  36. Wang Q, Wei C, Panos M. Literature review on wearable systems in upper extremity rehabilitation. IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI). IEEE, 2014.
  37. Butte NF, Ekelund U, Westerterp KR. Assessing physical activity using wearable monitors: measures of physical activity. Med Sci Sports Exerc. 2012;44(1):S5-12. https://doi.org/10.1249/MSS.0b013e3182399c0e
  38. Vas Peter. Artificial-intelligence-based electrical machines and drives: application of fuzzy, neural, fuzzy-neural, and genetic-algorithm-based techniques. Vol. 45. Oxford university press, 1999.
  39. Luxton DD. Artificial intelligence in psychological practice: Current and future applications and implications. Professional Psychology: Research and Practice. 2014;45(5):332-39. https://doi.org/10.1037/a0034559
  40. Esfahlani SS, Javaid B, Hassan S. Fusion of artificial intelligence in neuro-rehabilitation video games. IEEE Access. 2019;7(1):102617-27.
  41. Alrefaei AF, Hawsawi YM, Almaleki D, et al. Genetic data sharing and artificial intelligence in the era of personalized medicine based on a cross-sectional analysis of the Saudi human genome program. Sci Rep. 2022;12(1):1405.
  42. Kavakiotis I, Tsave O, Salifoglou A, et al. Machine learning and data mining methods in diabetes research. comput struct biotechnol J. 2017;15(1):104-16. https://doi.org/10.1016/j.csbj.2016.12.005
  43. Zeng C, Huang Y, Yu L, et al. Long-term assessment of rehabilitation treatment of sports through artificial intelligence research. Comput Math Methods Med. 2021;1(1):1-8 https://doi.org/10.1155/2021/4980718
  44. Meheli S, Sinha C, Kadaba M. Understanding people with chronic pain who use a cognitive behavioral therapy-based artificial intelligence mental health app (wysa): mixed methods retrospective observational study. JMIR Hum Factors. 2022;9(2):e35671.
  45. Zhijie Z, Daniel WHN, Park HS, et al. 3D-printed multifunctional materials enabled by artificial-intelligence-assisted fabrication technologies. Nature Reviews Materials. 2021;6(1):27-7.
  46. Subbu R, Weiler R, Whyte G. The practical use of surface electromyography during running: does the evidence support the hype? A narrative review. BMJ Open Sport Exerc Med. 2015;1(1):e000026.
  47. Giansanti D. Investigation of fall-risk using a wearable device with accelerometers and rate gyroscopes. Physiol Meas. 2006;27(11):1081-90. https://doi.org/10.1088/0967-3334/27/11/003
  48. Qiu S, Wang H, Li J, Zhao H, Wang Z, Wang J, Wang Q, Plettemeier D, Barhold M, Bauer T, Ru B. Towards wearable-inertial-sensor-based gait posture evaluation for subjects with unbalanced gaits. Sensors (Basel). 2020;20(4):1193.
  49. Wu YC, Lin SX, Lin JY, et al. Development of AI algorithm for weight training using inertial measurement units. Appl Sci. 2022;12(3):1422.
  50. Rampp A, Barth J, Schulein S, et al. Inertial sensor-based stride parameter calculation from gait sequences in geriatric patients. IEEE Trans Biomed Eng. 2015;62(4):1089-97. https://doi.org/10.1109/TBME.2014.2368211
  51. Hao L, Ghamisi P, Rasti B, et al. A multi-sensor fusion framework based on coupled residual convolutional neural networks. Remote Sens. 2020;12(12):2067.