EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an iOS Application (TDPT-GT)

Chifumi Iseki iD, Tatsuya Hayasaka iD, Hyota Yanagawa, Yuta Komoriya, Toshiyuki Kondo, Masayuki Hoshi iD, Tadanori Fukami, Yoshiyuki Kobayashi, Shigeo Ueda iD, Kaneyuki Kawamae, Masatsune Ishikawa, Shigeki Yamada iD und 2 weitere

Sensors · 2023

DOI: 10.3390/s23136217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Chifumi Iseki und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Neurology and Clinical Neuroscience, Department of Internal Medicine III, Yamagata University School of Medicine, Yamagata 990-2331, Japa…. Hauptthemen laut MEDLINE: Artificial Intelligence, Motion Capture. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Japan Society for the Promotion of Science, KAKENHI, G-7 Scholarship Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Distinguishing pathological gait is challenging in neurology because of the difficulty of capturing total body movement and its analysis. We aimed to obtain a convenient recording with an iPhone and establish an algorithm based on deep learning. From May 2021 to November 2022 at Yamagata University Hospital, Shiga University, and Takahata Town, patients with idiopathic normal pressure hydrocephalus (n = 48), Parkinson’s disease (n = 21), and other neuromuscular diseases (n = 45) comprised the pathological gait group (n = 114), and the control group consisted of 160 healthy volunteers. iPhone application TDPT-GT captured the subjects walking in a circular path of about 1 meter in diameter, a markerless motion capture system, with an iPhone camera, which generated the three-axis 30 frames per second (fps) relative coordinates of 27 body points. A light gradient boosting machine (Light GBM) with stratified k-fold cross-validation (k = 5) was applied for gait collection for about 1 min per person. The median ability model tested 200 frames of each person’s data for its distinction capability, which resulted in the area under a curve of 0.719. The pathological gait captured by the iPhone could be distinguished by artificial intelligence.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceMotion CaptureHumansGaitWalkingAlgorithmsBiomechanical PhenomenaMotion

Stichwörter der Autor:innen

artificial intelligencemarkerless motion capturemotion trackingneuromuscular diseasesquantitative gait assessmentsmartphone device

Autor:innen und Institutionen

  • Division of Neurology and Clinical Neuroscience, Department of Internal Medicine III, Yamagata University School of Medicine, Yamagata 990-2331, Japan.
  • Department of Behavioral Neurology and Cognitive Neuroscience, Tohoku University Graduate School of Medicine, Sendai 980-8575, Japan.
  • Department of Anesthesiology, Yamagata University School of Medicine, Yamagata 990-2331, Japan.
  • Department of Medicine, Yamagata University School of Medicine, Yamagata 990-2331, Japan.
  • Department of Physical Therapy, Fukushima Medical University School of Health Sciences, 10-6 Sakaemachi, Fukushima 960-8516, Japan.
  • Department of Informatics, Faculty of Engineering, Yamagata University, Yonezawa 992-8510, Japan.

ORCID-Profile: Chifumi Iseki, Tatsuya Hayasaka, Masayuki Hoshi, Shigeo Ueda, Shigeki Yamada

Förderung

  • Japan Society for the Promotion of Science
  • Japan Society for the Promotion of Science, KAKENHI
  • G-7 Scholarship Foundation
  • Taiju Life Social Welfare Foundation
  • Osaka Gas Group Welfare Foundation

Zitieren

APA

Iseki, C., Hayasaka, T., Yanagawa, H., Komoriya, Y., Kondo, T., Hoshi, M., Fukami, T., Kobayashi, Y., Ueda, S., Kawamae, K., Ishikawa, M., Yamada, S., Aoyagi, Y., & Ohta, Y. (2023). Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an iOS Application (TDPT-GT). Sensors. https://doi.org/10.3390/s23136217

Vancouver

Iseki C, Hayasaka T, Yanagawa H, Komoriya Y, Kondo T, Hoshi M, et al. Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an iOS Application (TDPT-GT). Sensors. 2023. doi:10.3390/s23136217

BibTeX
@article{Iseki2023,
  author = {Iseki, Chifumi and Hayasaka, Tatsuya and Yanagawa, Hyota and Komoriya, Yuta and Kondo, Toshiyuki and Hoshi, Masayuki and Fukami, Tadanori and Kobayashi, Yoshiyuki and Ueda, Shigeo and Kawamae, Kaneyuki and Ishikawa, Masatsune and Yamada, Shigeki and Aoyagi, Yukihiko and Ohta, Yasuyuki},
  title = {Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an iOS Application (TDPT-GT)},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23136217}
}
Kostenlos starten →