EUVIMEDEUVIMED entdecken
Open Access

Deep Learning–Based Automated Clinical Gait Assessment From Kinematic Data in People With Stroke: Development and Validation Study

Zhexuan Gu, Jiaqi Li, Wenbin Zhou, Kenneth N K Fong, Lin Wang, Eng Keong Lua, Patrick W H Kwong, Yancheng Yuan

JMIR Rehabilitation and Assistive Technologies · 19.08.2026 · 13 · e94031-e94031

DOI: 10.2196/94031 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Rehabilitation and Assistive Technologies, online erschienen am 19.08.2026. Verfasst von Zhexuan Gu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Science & Artificial Intelligence, Hong Kong Polytechnic University, Hong Kong, China (Hong Kong). Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Gait impairment is a prevalent sequela of stroke. Although observational gait analysis remains a standard clinical practice for assessing neuromotor impairments in people with stroke, it is prone to subjective bias. Consequently, objective assessment is required to inform effective rehabilitation protocols.

Objective

This study aimed to validate a deep learning framework for automating clinical gait assessment using kinematic data.

Methods

This study was conducted in a university-affiliated gait analysis laboratory. Kinematic data were collected from 51 individuals with hemiparetic stroke and 18 healthy controls using wearable inertial measurement units, and video recordings were obtained for the Wisconsin Gait Scale (WGS) scoring. WGS scores, rated by 2 experienced physiotherapists, were used to establish the expert reference standard. A statistical graph convolutional network (STAT-GCN), incorporating a STAT-Attention Head module, was developed to predict WGS items 2 to 14 from kinematic data. Model evaluation was performed using a stratified, participant-level 5-fold cross-validation protocol, with all gait cycles from the same participant kept within the same fold. Model performance was assessed at the participant level using exact accuracy, mean absolute error, and weighted κ metrics. A descriptive comparison involving 4 final-year physiotherapy students was also conducted.

Results

Among participants with stroke, STAT-GCN achieved an overall exact accuracy of 75.42% for WGS items 2 to 14, with a mean absolute error of 0.290 score levels. Across the participant-level 5-fold cross-validation test sets, STAT-GCN achieved a mean exact accuracy of 75.64% (SD 6.58%), whereas the 4 student evaluators achieved mean accuracies ranging from 56.19% (SD 7.03%) to 67.09% (SD 4.03%).

Conclusions

The proposed STAT-GCN framework demonstrated reasonable preliminary performance for automated WGS item prediction in individuals with stroke. The results suggest that kinematic data–driven models may support more standardized gait assessment, but performance should be interpreted cautiously given the limited sample size, class imbalance across WGS score items, and absence of external validation. Further studies with larger and more clinically diverse stroke cohorts are needed before clinical implementation.

Schlagwörter

Stichwörter der Autor:innen

Wisconsin Gait Scaledeep learninggaitgraph convolution networkstroke

Autor:innen und Institutionen

  • Department of Data Science & Artificial Intelligence, Hong Kong Polytechnic University, Hong Kong, China (Hong Kong).
  • Department of Rehabilitation Sciences, The Hong Kong Polytechnic University, 11 Yuk Choi Road, Hung Hom, KLN, Hong Kong, China (Hong Kong), 852 3400 3958.
  • Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
  • Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, China (Hong Kong).
  • Computer Laboratory, University of Cambridge, Cambridge, England, United Kingdom.
  • Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China (Hong Kong).

Zitieren

APA

Gu, Z., Li, J., Zhou, W., Fong, K. N. K., Wang, L., Lua, E. K., Kwong, P. W. H., & Yuan, Y. (2026). Deep Learning–Based Automated Clinical Gait Assessment From Kinematic Data in People With Stroke: Development and Validation Study. JMIR Rehabilitation and Assistive Technologies, 13, e94031-e94031. https://doi.org/10.2196/94031

Vancouver

Gu Z, Li J, Zhou W, Fong KNK, Wang L, Lua EK, et al. Deep Learning–Based Automated Clinical Gait Assessment From Kinematic Data in People With Stroke: Development and Validation Study. JMIR Rehabilitation and Assistive Technologies. 2026;13:e94031-e94031. doi:10.2196/94031

BibTeX
@article{Gu2026,
  author = {Gu, Zhexuan and Li, Jiaqi and Zhou, Wenbin and Fong, Kenneth N K and Wang, Lin and Lua, Eng Keong and Kwong, Patrick W H and Yuan, Yancheng},
  title = {Deep Learning–Based Automated Clinical Gait Assessment From Kinematic Data in People With Stroke: Development and Validation Study},
  journal = {JMIR Rehabilitation and Assistive Technologies},
  year = {2026},
  volume = {13},
  pages = {e94031--e94031},
  doi = {10.2196/94031}
}
Kostenlos starten →