Automated Gait Assessment for Rehabilitation Training Using Pose Tracking and Dynamic Time Warping
In this preliminary validation, the proposed 2D AI posture tracking showed good agreement with the gold standard 3D motion capture for gait in healthy individuals. While the average systematic bias was within clinically acceptable limits, the observed limits of agreement suggest that this system is currently optimal as a foundational tool for gait screening. These results establish a technical foundation for the clinical application of this system.
Authors
- Yasumitsu Fujii (ORCID: https://orcid.org/0009-0008-3452-5557)
- Naomi Yagi (ORCID: https://orcid.org/0000-0002-2435-6509)
- Yoshitada Sakai (ORCID: https://orcid.org/0000-0002-0435-8398)
- Kentaro Mori (ORCID: https://orcid.org/0000-0001-6107-8555)
- Yutaka Hata
- Yuki Yamanaka
- Kazuki Otsuka
Institutions
- Himeji Dokkyo University (JP)
- University of Hyogo (JP)
- National Institute of Technology, Maizuru College (JP)
- Nishikawa Hospital (JP)
- Himeji Medical Center (JP)
- Kobe University (JP)
Publication Details
- Journal
- Diagnostics
- Published
- 2026-04-14
- DOI
- https://doi.org/10.3390/diagnostics16081164
- Primary Topic
- Balance, Gait, and Falls Prevention
- Type
- article
- Field-Weighted Citation Impact
- 0.00