EUVIMEDEUVIMED entdecken
Crossref

Gait Video–Based Prediction of Severity of Cerebellar Ataxia Using Deep Neural Networks

Katsuki Eguchi iD, Hiroaki Yaguchi iD, Hisashi Uwatoko, Yuki Iida, Shinsuke Hamada, Sanae Honma, Asako Takei, Fumio Moriwaka, Ichiro Yabe

Movement Disorders · 2025

DOI: 10.1002/mds.30113 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Movement Disorders, 2025. Verfasst von Katsuki Eguchi und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan. Hauptthemen laut MEDLINE: Cerebellar Ataxia, Deep Learning, Neural Networks, Computer, Gait Disorders, Neurologic. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 21 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science, The Ministry of Health, Labor and Welfare, Japan, Ministry of Health Mexico.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Pose estimation algorithms applied to two‐dimensional videos evaluate gait disturbances; however, a few studies have used this method to evaluate ataxic gait.

Objective

The aim was to assess whether a pose estimation algorithm can predict the severity of cerebellar ataxia by applying it to gait videos.

Methods

We video‐recorded 66 patients with degenerative cerebellar diseases performing the timed up‐and‐go test. Key points from the gait videos extracted by a pose estimation algorithm were input into a deep learning model to predict the Scale for the Assessment and Rating of Ataxia (SARA) score. We also evaluated video segments that the model focused on to predict ataxia severity.

Results

The model achieved a root‐mean‐square error of 2.30 and a coefficient of determination of 0.79 in predicting the SARA score. It primarily focused on standing, turning, and body sway to assess severity.

Conclusions

This study demonstrated that the model may capture gait characteristics from key‐point data and has the potential to predict SARA scores. © 2025 International Parkinson and Movement Disorder Society.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cerebellar AtaxiaDeep LearningNeural Networks, ComputerGait Disorders, NeurologicGaitHumansMaleFemaleMiddle AgedAgedSeverity of Illness IndexVideo RecordingAdultAlgorithmsGait Analysis

Stichwörter der Autor:innen

ataxiagait analysismachine learningpose estimation algorithm

Autor:innen und Institutionen

  • Department of Neurology, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan.
  • Department of Neurology, Hokuyukai Neurological Hospital, Sapporo, Japan.

ORCID-Profile: Katsuki Eguchi, Hiroaki Yaguchi

Förderung

  • Japan Society for the Promotion of Science
  • The Ministry of Health, Labor and Welfare, Japan
  • Ministry of Health Mexico

Zitieren

APA

Eguchi, K., Yaguchi, H., Uwatoko, H., Iida, Y., Hamada, S., Honma, S., Takei, A., Moriwaka, F., & Yabe, I. (2025). Gait Video–Based Prediction of Severity of Cerebellar Ataxia Using Deep Neural Networks. Movement Disorders. https://doi.org/10.1002/mds.30113

Vancouver

Eguchi K, Yaguchi H, Uwatoko H, Iida Y, Hamada S, Honma S, et al. Gait Video–Based Prediction of Severity of Cerebellar Ataxia Using Deep Neural Networks. Movement Disorders. 2025. doi:10.1002/mds.30113

BibTeX
@article{Eguchi2025,
  author = {Eguchi, Katsuki and Yaguchi, Hiroaki and Uwatoko, Hisashi and Iida, Yuki and Hamada, Shinsuke and Honma, Sanae and Takei, Asako and Moriwaka, Fumio and Yabe, Ichiro},
  title = {Gait Video–Based Prediction of Severity of Cerebellar Ataxia Using Deep Neural Networks},
  journal = {Movement Disorders},
  year = {2025},
  doi = {10.1002/mds.30113}
}
Kostenlos starten →