EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Machine Learning Framework for Post-Stroke Gait Abnormality Classification Using Wearable Gyroscope Features

Stamatios Orfanos iD, Thanita Sanghan iD, Andreas Menychtas iD, Christos Panagopoulos iD, Ilias Maglogiannis iD, Surapong Chatpun iD

Sensors · 15.05.2026 · 26 (10) · 3143

DOI: 10.3390/s26103143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.05.2026. Verfasst von Stamatios Orfanos und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bioassist SA, 26504 Rio, Greece. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Stroke, Machine Learning, Gait. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Horizon Europe Framework Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately classifying gait abnormalities is crucial for the effective monitoring and rehabilitation of stroke patients. This study proposed a lightweight machine learning framework for distinguishing healthy from abnormal gait patterns using statistical features extracted from wearable gyroscope data. Statistical z-axis angular velocity values from both limbs were derived and used to evaluate the performance of multiple classifiers, including logistic regression, support vector machines, and ensemble methods. A leave-one-out cross-validation strategy was employed to enhance generalizability across subjects. The results indicated that several classifiers achieve accuracy and area under the curve (AUC) values exceeding 0.95, with random forest and support vector machine-based models demonstrating near-perfect class separability, with an AUC of 0.98. These findings highlighted the effectiveness of using minimal set of biomechanically relevant gyroscope features for gait classification in real-world healthcare applications. The proposed pipeline is computationally efficient, making it well suited for implementing in wearable and remote monitoring systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesStrokeMachine LearningGaitHumansClassification AlgorithmsRandom ForestSupport Vector MachineStroke Rehabilitation

Stichwörter der Autor:innen

gait classificationgyroscope featuresmachine learningstroke rehabilitationwearable sensors

Autor:innen und Institutionen

  • Bioassist SA, 26504 Rio, Greece.
  • Department of Biomedical Sciences and Biomedical Engineering, Faculty of Medicine, Prince of Songkla University, Songkhla 90110, Thailand.
  • Department of Digital Systems, Faculty of Information and Communication Technologies, University of Piraeus, 18534 Piraeus, Greece.

ORCID-Profile: Stamatios Orfanos, Thanita Sanghan, Andreas Menychtas, Christos Panagopoulos, Ilias Maglogiannis, Surapong Chatpun

Förderung

  • the Horizon Europe Framework Program

Zitieren

APA

Orfanos, S., Sanghan, T., Menychtas, A., Panagopoulos, C., Maglogiannis, I., & Chatpun, S. (2026). A Lightweight Machine Learning Framework for Post-Stroke Gait Abnormality Classification Using Wearable Gyroscope Features. Sensors, 26(10), 3143. https://doi.org/10.3390/s26103143

Vancouver

Orfanos S, Sanghan T, Menychtas A, Panagopoulos C, Maglogiannis I, Chatpun S. A Lightweight Machine Learning Framework for Post-Stroke Gait Abnormality Classification Using Wearable Gyroscope Features. Sensors. 2026;26(10):3143. doi:10.3390/s26103143

BibTeX
@article{Orfanos2026,
  author = {Orfanos, Stamatios and Sanghan, Thanita and Menychtas, Andreas and Panagopoulos, Christos and Maglogiannis, Ilias and Chatpun, Surapong},
  title = {A Lightweight Machine Learning Framework for Post-Stroke Gait Abnormality Classification Using Wearable Gyroscope Features},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3143},
  doi = {10.3390/s26103143}
}
Kostenlos starten →