A deep learning framework for gait-based frailty classification using inertial measurement units
PLOS One · 2026
DOI: 10.1371/journal.pone.0343402 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Arslan Amjad und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Graphics, Vision and Digital Systems, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of T…. Hauptthemen laut MEDLINE: Deep Learning, Frailty, Gait. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Gerontologische Pflege
Abstract (Originalsprache)
Frailty in older adults leads to heightened vulnerability to adverse health outcomes, significantly burdening individuals and society by increasing healthcare costs and dependency. To address this issue, an advanced frailty assessment method combining wearable sensors measurements with Deep Learning (DL) techniques is proposed to classify individuals into frail or non-frail stages. Wearable sensors provide real-time monitoring, facilitating early detection and timely interventions. Two diverse datasets, i.e., GSTRIDE and FRAILPOL, were utilized for enhanced frailty analysis, employing one to five Inertial Measurement Unit (IMU) sensors with varying configurations and mounting positions. A participant-centric data partitioning framework based on signal windows segmentation is proposed and applied to DL algorithms. Among the DL algorithms, InceptionTime outperformed, achieving 82% accuracy on GSTRIDE and 79% on the FRAILPOL dataset. Furthermore, the area under the ROC curve (AUC) and evaluation metrics such as precision, recall, and F1-score confirm InceptionTime’s effectiveness in classifying frail and non-frail stages by capturing spatio-temporal features from raw IMU signals.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Graphics, Vision and Digital Systems, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Gliwice, Poland.
- Department of Physical Education and Sport, Faculty of Physical Education and Physiotherapy, Opole University of Technology, Opole, Poland.
- Department of Cardiology, University Hospital, Institute of Medical Sciences, University of Opole, Opole, Poland.
- Department of Family Medicine and Public Health, Institute of Medical Sciences, Faculty of Medicine, University of Opole, Opole, Poland.
- Department of Rehabilitation, University Hospital, Institute of Medical Sciences, University of Opole, Opole, Poland.
- Faculty of Science, Institute of Mathematical Sciences, Universiti Malaya, Kuala Lumpur, Malaysia.
ORCID-Profile: Arslan Amjad, Mariusz Konieczny
Zitieren
APA
Amjad, A., Szczęsna, A., Błaszczyszyn, M., Sacha, J., Sacha, M., Feusette, P., Wolański, W., Konieczny, M., Borysiuk, Z., & Khan, B. (2026). A deep learning framework for gait-based frailty classification using inertial measurement units. PLOS One. https://doi.org/10.1371/journal.pone.0343402
Vancouver
Amjad A, Szczęsna A, Błaszczyszyn M, Sacha J, Sacha M, Feusette P, et al. A deep learning framework for gait-based frailty classification using inertial measurement units. PLOS One. 2026. doi:10.1371/journal.pone.0343402
BibTeX
@article{Amjad2026,
author = {Amjad, Arslan and Szczęsna, Agnieszka and Błaszczyszyn, Monika and Sacha, Jerzy and Sacha, Magdalena and Feusette, Piotr and Wolański, Wojciech and Konieczny, Mariusz and Borysiuk, Zbigniew and Khan, Basheir},
title = {A deep learning framework for gait-based frailty classification using inertial measurement units},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0343402}
}
EUVIMED