Development Of Ai-Driven Systems for Real-Time Joint Movement Detection and Correction in Frozen Shoulder Therapy Using Sensor-Based Shoulder Rehabilitation Devices

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 15 | Issue : 01 | Page :
    By

    Manmeet Kaur Bhalla,

  • Niraj Kumar,

  • Adharika Agrawal,

  • Mohammad Junaid,

  • Prachi Seth Singh,

  1. PhD Scholar, Department of Physiotherapy, Shri Guru Ram Rai University, Dehradun, Uttarakhand,
  2. Professor and Head of Department, Department of Physiotherapy, Shri Guru Ram Rai University, Dehradun, Uttarakhand, India
  3. Multi Rehabilitation Worker (Physiotherapist), Department of Physical Medicine & Rehabilitation (PM&R), AIIMS Patna, Patna, Bihar, India
  4. AI/ML Engineer, MBA Candidate, Bayes Business School, City St George’s, University of London, London, United Kingdom
  5. Associate Professor, Department of Physiotherapy, Sai Institute of Paramedical and Allied Sciences, Dehradun, Uttarakhand, India

Abstract

Frozen shoulder, or adhesive capsulitis, is a common musculoskeletal disorder characterized by progressive pain, stiffness, and restricted range of motion that significantly impairs functional ability and quality of life. Recent advancements in artificial intelligence and sensor-based technologies have enabled the development of intelligent rehabilitation systems capable of real-time joint movement detection and correction. Wearable sensors such as inertial measurement units, electromyography sensors, and flexible strain sensors capture continuous biomechanical data that is processed using machine learning algorithms to analyze movement patterns, detect abnormalities, and provide immediate corrective feedback. This improves exercise accuracy and reduces compensatory movements. These AI-driven systems support personalized rehabilitation by adapting therapy protocols based on patient performance and recovery progression. They also enable remote monitoring and reduce dependency on constant clinical supervision. Integration with robotic-assisted devices and virtual reality platforms further enhances engagement, precision, and therapeutic outcomes. Although challenges such as cost, technical complexity, and data privacy remain, ongoing advancements are expected to improve accessibility and clinical adoption. AI-driven rehabilitation systems therefore represent a promising solution for effective and efficient management of frozen shoulder.

Keywords: Frozen Shoulder, Adhesive Capsulitis, Artificial Intelligence, Sensor-Based Rehabilitation, Real-Time Motion Detection,

[This article belongs to Research and Reviews : A Journal of Medical Science and Technology ]

How to cite this article:
Manmeet Kaur Bhalla, Niraj Kumar, Adharika Agrawal, Mohammad Junaid, Prachi Seth Singh. Development Of Ai-Driven Systems for Real-Time Joint Movement Detection and Correction in Frozen Shoulder Therapy Using Sensor-Based Shoulder Rehabilitation Devices. Research and Reviews : A Journal of Medical Science and Technology. 2026; 15(01):-.
How to cite this URL:
Manmeet Kaur Bhalla, Niraj Kumar, Adharika Agrawal, Mohammad Junaid, Prachi Seth Singh. Development Of Ai-Driven Systems for Real-Time Joint Movement Detection and Correction in Frozen Shoulder Therapy Using Sensor-Based Shoulder Rehabilitation Devices. Research and Reviews : A Journal of Medical Science and Technology. 2026; 15(01):-. Available from: https://journals.stmjournals.com/rrjomst/article=2026/view=240339


References

  1. Kim H, et al. Clustering-based movement analysis. IEEE J Biomed Health Inform. 2025;29(2):450–460.
  2. Kim J, Campbell AS, de Ávila BEF, Wang J. Wearable biosensors for healthcare monitoring. Nat Biotechnol. 2020;38(7):793–808. doi:10.1038/s41587-020-0585-0
  3. Lee D, et al. Movement classification using wearable sensors. Sensors (Basel). 2021;21(5):1802. doi:10.3390/s21051802
  4. Lee S, Kim J, Park Y. Deep learning-based motion recognition using wearable sensors. J Neuroeng Rehabil. 2024;21(1):88.
  5. Lewis J. Frozen shoulder contracture syndrome: Aetiology, diagnosis and management. Man Ther. 2015;20(1):2–9.
  6. Lingampally A, et al. Robotic-assisted physiotherapy systems. Healthcare (Basel). 2024;12(6):789.
  7. Liu Y, Chen X, Zhang Q. Machine learning approaches for rehabilitation monitoring using wearable sensors. IEEE Access. 2023;11:45678–45689.
  8. Liu Z, et al. Real-time AI monitoring in rehabilitation systems. Appl Sci. 2025;15(3):1234.
  9. Longo UG, et al. Virtual reality in musculoskeletal rehabilitation: A systematic review. BMC Musculoskelet Disord. 2023;24:861.
  10. Luo H, et al. Intelligent robotic rehabilitation systems. Artif Intell Med. 2025;140:102500.
  11. Green S, Buchbinder R, Hetrick S. Physiotherapy interventions for shoulder pain (adhesive capsulitis). Cochrane Database Syst Rev. 2014;(8):CD011275.
  12. Moore J, et al. Challenges in AI healthcare systems. Health Informatics J. 2025;31(2):1460458225123456.
  13. Moreira A, et al. Gamification in rehabilitation: A systematic review. Appl Sci. 2024;14(10):4086.
  14. Navarro-Ledesma S, et al. Clinical and pathophysiological aspects of adhesive capsulitis. J Clin Med. 2021;10(12):2603. doi:10.3390/jcm10122603
  15. Ouyang F, et al. Machine learning for musculoskeletal diagnosis. IEEE Access. 2023;11:99876–99888.
  16. Paredes S, et al. Wearable sensor systems for rehabilitation monitoring: A review. Sensors (Basel). 2017;17(3):456. doi:10.3390/s17030456
  17. Patel S, Park H, Bonato P, Chan L, Rodgers M. A review of wearable sensors and systems with application in rehabilitation. J Neuroeng Rehabil. 2012;9:21.
  18. Perez Peralta A, et al. EMG-based analysis for rehabilitation systems. Biomed Signal Process Control. 2025;95:105012.
  19. Rai S, Kumar N, Singh A. Wearable sensor technologies in rehabilitation: A review. Healthc Technol Lett. 2024;11(2):45–52.
  20. Raji P, et al. Assistive robotic systems in rehabilitation. Biomed Eng Lett. 2025;15(1):45–56.
  21. Rasa I. Adaptive AI systems in rehabilitation. Int J Med Inform. 2024;182:105287.
  22. Recent advances in AI healthcare: Emerging trends in AI validation. Annu Rev Biomed Eng. 2026;28:1–25.
  23. Refai M, et al. AI in musculoskeletal rehabilitation. Front Physiol. 2023;14:1156520. doi:10.3389/fphys.2023.1156520
  24. Riccio D, et al. Temporal deep learning models for motion classification. IEEE Trans Neural Netw Learn Syst. 2024;35(2):1120–1132.
  25. Ryan V, Brown H, Minns Lowe CJ, Lewis JS. The pathophysiology associated with primary (idiopathic) frozen shoulder. BMC Musculoskelet Disord. 2016;17:340. doi:10.1186/s12891-016-1190-9
  26. Srichaisak P, et al. Sensor fusion techniques in healthcare monitoring. IEEE Sens J. 2025;25(4):3021–3030.
  27. Stanica I, et al. Sensor-integrated VR rehabilitation. Appl Sci. 2024;14(19):9093.
  28. StatPearls Publishing. Adhesive capsulitis (frozen shoulder). In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2022.
  29. Sun Y, Lu S, Zhang P, Wang Z, Chen J. Steroid injection versus physiotherapy for adhesive capsulitis: A systematic review and meta-analysis. Arch Phys Med Rehabil. 2018;99(4):815–825. doi:10.1016/j.apmr.2017.10.009
  30. Um TT, et al. Data augmentation of wearable sensor data for Parkinson’s disease monitoring. In: Proc ACM Int Conf Multimodal Interact. 2016:216–220. doi:10.1145/2993148.2993162
  31. Varma R. Continuous monitoring in digital health. Digit Health. 2024;10:20552076241234567.
  32. Vega R, et al. AI optimization in rehabilitation systems. Comput Biol Med. 2024;165:107423.
  33. Wang H, et al. AI-driven feedback systems in physiotherapy. Sensors (Basel). 2023;23(1):425. doi:10.3390/s23010425
  34. Wang W, Li Z, Liu Y. Artificial intelligence in rehabilitation: Current trends and future directions. Sensors (Basel). 2022;22(20):7654. doi:10.3390/s22207654
  35. Wei Q, et al. Wearable systems for real-time rehabilitation feedback. Sensors (Basel). 2023;23(18):7667. doi:10.3390/s23187667
  36. Weiner J, et al. Ethical issues in AI healthcare. Lancet Digit Health. 2024;6(3):e134–e136.
  37. Wu Y, et al. Real-time monitoring using AI wearable devices. IEEE Access. 2024;12:55678–55689.
  38. Yang C, Hsu Y, Shih K. Motion tracking using IMU sensors for rehabilitation. Sensors (Basel). 2022;22(3):1123. doi:10.3390/s22031123
  39. Zhang X, et al. Adaptive control in robotic rehabilitation. IEEE Trans Med Robot Bionics. 2026;8(1):120–130.
  40. Zhou L, Bao J, Setiawan IMA, Saptono A, Parmanto B. The mHealth app usability questionnaire (MAUQ): Development and validation study. JMIR Mhealth Uhealth. 2019;7(4):e11500. doi:10.2196/11500
Regular Issue Subscription Review Article
Volume 15
Issue 01
Received 09/04/2026
Accepted 13/04/2026
Published 18/04/2026
Publication Time 9 Days
1

Login


My IP

PlumX Metrics