Deep multimodal biomechanical analysis for lower back pain rehabilitation to improve patients stability
Frontiers in Bioengineering and Biotechnology · 07.11.2025 · 13
DOI: 10.3389/fbioe.2025.1631910 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 07.11.2025. Verfasst von Muhammad Abrar Ashraf und 7 weiteren Autor:innen. Beteiligte Einrichtung: Guodian Nanjing Automation Co., Ltd, Nanjing, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Advancements in artificial intelligence are transforming rehabilitation by enabling scalable, patient-centric solutions within modern healthcare systems. This study introduces 3D-PoseFormer, a deep multimodal framework designed for the telerehabilitation of individuals with lower back pain (LBP).
Methods
The proposed system performs automated data acquisition using synchronized RGB and depth video streams to enable real-time, markerless, and sensor-free analysis of physiotherapy exercises. From the depth sensing module, 3D body joint positions are extracted and used to generate SMPL-based mesh vertices for detailed biomechanical analysis and postural representation. Simultaneously, RGB frames are processed using keypoint detection algorithms—Shi-Tomasi, AKAZE, BRISK, SIFT, and Harris corner detection. Extracted features are enhanced through semantic contour analysis of segmented body parts to capture localized appearance-based information relevant to LBP therapy. The fused multimodal features are then passed to a Transformer-based machine learning model that captures temporal motion patterns for accurate exercise classification and human intention recognition.
Results
The system removes the need for wearable sensors and supports autonomous, continuous monitoring in home-based rehabilitation. Validation on the KIMORE dataset (baseline, including rehabilitation exercises by patients with lower back pain), mRI dataset (rehabilitation exercises), and UTKinect-Action3D dataset (comprising diverse subjects and activity scenarios) achieved state-of-the-art accuracies of 94.73%, 91%, and 94.2%, respectively.
Discussion
Results demonstrate the robustness, generalizability, and clinical potential of 3D-PoseFormer in AI-assisted rehabilitation, offering a scalable and intelligent healthcare system for remote physiotherapy and patient monitoring.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guodian Nanjing Automation Co., Ltd, Nanjing, China.
- Department of Electrical and Computer Engineering Riphah International University, Islamabad, Pakistan.
- Department of Electrical Engineering, Bahria University, Islamabad, Pakistan.
- Department of Computer Science, King Khalid University, Abha, Saudi Arabia.
- Department of Informatics and Computer Systems, King Khalid University, Abha, Saudi Arabia.
- Computer Sciences Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University (PNU), Riyadh, Saudi Arabia.
Zitieren
APA
Ashraf, M. A., Wu, Y., Najam, S., Alshehri, M., AlQahtani, Y., Aljuaid, H., Jalal, A., & Liu, H. (2025). Deep multimodal biomechanical analysis for lower back pain rehabilitation to improve patients stability. Frontiers in Bioengineering and Biotechnology, 13. https://doi.org/10.3389/fbioe.2025.1631910
Vancouver
Ashraf MA, Wu Y, Najam S, Alshehri M, AlQahtani Y, Aljuaid H, et al. Deep multimodal biomechanical analysis for lower back pain rehabilitation to improve patients stability. Frontiers in Bioengineering and Biotechnology. 2025;13. doi:10.3389/fbioe.2025.1631910
BibTeX
@article{Ashraf2025,
author = {Ashraf, Muhammad Abrar and Wu, Yanfeng and Najam, Shaheryar and Alshehri, Mohammed and AlQahtani, Yahya and Aljuaid, Hanan and Jalal, Ahmad and Liu, Hui},
title = {Deep multimodal biomechanical analysis for lower back pain rehabilitation to improve patients stability},
journal = {Frontiers in Bioengineering and Biotechnology},
year = {2025},
volume = {13},
doi = {10.3389/fbioe.2025.1631910}
}
EUVIMED