Automated UPDRS Gait Scoring Using Wearable Sensor Fusion and Deep Learning
Bioengineering · 24.06.2025 · 12 (7) · 686
DOI: 10.3390/bioengineering12070686 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 24.06.2025. Verfasst von Xiangzhi Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: The State Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSFC, the National Key Laboratory of Transient Impact, Scientific Research Fund of Zhejiang University.
Abstract (Originalsprache)
The quantitative assessment of Parkinson’s disease (PD) is critical for guiding diagnosis, treatment, and rehabilitation. Conventional clinical evaluations—heavily dependent on manual rating scales such as the Unified Parkinson’s Disease Rating Scale (UPDRS)—are time-consuming and prone to inter-rater variability. In this study, we propose a fully automated UPDRS gait-scoring framework. Our method combines (a) surface electromyography (EMG) signals and (b) inertial measurement unit (IMU) data into a single deep learning model. Our end-to-end network comprises three specialized branches—a diagnosis head, an evaluation head, and a balance head—whose outputs are integrated via a customized fusion-detection module to emulate the multidimensional assessments performed by clinicians. We validated our system on 21 PD patients and healthy controls performing a simple walking task while wearing a four-channel EMG array on the lower limbs and 2 shank-mounted IMUs. It achieved a mean classification accuracy of 92.8% across UPDRS levels 0–2. This approach requires minimal subject effort and sensor setup, significantly cutting clinician workload associated with traditional UPDRS evaluations while improving objectivity. The results demonstrate the potential of wearable sensor-driven deep learning methods to deliver rapid, reliable PD gait assessment in both clinical and home settings.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The State Key Laboratory of Fluid Power and Mechatronic Systems, School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China.
- Beijing Research Institute of Mechanical and Electrical Engineering, Beijing 102202, China.
- The Second School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou 310053, China.
ORCID-Profile: Xiangzhi Liu, Tao Liu
Förderung
- NSFC
- the National Key Laboratory of Transient Impact
- Scientific Research Fund of Zhejiang University
- National Key Laboratory of Transient Impact
Zitieren
APA
Liu, X., Zhang, X., Li, J., Pan, W., Sun, Y., Lin, S., & Liu, T. (2025). Automated UPDRS Gait Scoring Using Wearable Sensor Fusion and Deep Learning. Bioengineering, 12(7), 686. https://doi.org/10.3390/bioengineering12070686
Vancouver
Liu X, Zhang X, Li J, Pan W, Sun Y, Lin S, et al. Automated UPDRS Gait Scoring Using Wearable Sensor Fusion and Deep Learning. Bioengineering. 2025;12(7):686. doi:10.3390/bioengineering12070686
BibTeX
@article{Liu2025,
author = {Liu, Xiangzhi and Zhang, Xiangliang and Li, Juan and Pan, Wenhao and Sun, Yiping and Lin, Shuanggen and Liu, Tao},
title = {Automated UPDRS Gait Scoring Using Wearable Sensor Fusion and Deep Learning},
journal = {Bioengineering},
year = {2025},
volume = {12},
number = {7},
pages = {686},
doi = {10.3390/bioengineering12070686}
}
EUVIMED