Assessing Locomotive Syndrome Through Instrumented Five-Time Sit-to-Stand Test and Machine Learning

Aug 4, 2026

Upload by Oliver

Locomotive syndrome (LS) describes difficulties performing activities of daily living, and early detection is essential to limit dependence on nursing care. The Geriatric Locomotive Function Scale (GLFS-25) stratifies LS using 25 questions, but its subjectivity motivates objective, technology-based measurement. This study applies machine learning to an instrumented five-time sit-to-stand test (FTSTS). Participants wore a single pelvic inertial measurement unit, with acceleration signals used to extract 144 features. Seven models were trained, and the multilayer perceptron (MLP) performed best. After data augmentation and PCA, the MLP+PCA pipeline reached accuracy 0.9, precision 0.92, recall 0.9, and F1 0.91, supporting the feasibility of remote LS assessment using common devices such as smartphones.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Locomotive syndrome and early diagnosis

Locomotive syndrome assessment and GLFS-25

Methods

Instrumented five-time sit-to-stand test

Inertial measurement unit and feature extraction

Machine learning models

Results

Model performance and evaluation metrics

Conclusion and future work

Toward remote LS assessment

sensors Article Assessing Locomotive Syndrome Through Instrumented Five-Time Sit-to-Stand Test and Machine Learning † Iman Hosseini 1, *,‡ and Maryam Ghahramani 2,‡ Citation: Hosseini, I.; Ghahramani, M. Assessing Locomotive Syndrome Through Instrumented Five-Time Sit-to-Stand Test and Machine Learning. Sensors 2024, 24, 7727 . [https://doi.org/10.3390/s24237727](https://doi.org/10.3390/s24237727) Academic Editor: Mehdi Boukallel Received: 14 September 2024 Revised: 23 November 2024 Accepted: 29 November 2024 Published: 3 December 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 School of Computing, Australian National University, Acton, ACT 2601, Australia 2 Human-Centred Technology Research Centre, University of Canberra, Bruce, ACT 2617, Australia; [maryam.ghahramani@canberra.edu.au](maryam.ghahramani@canberra.edu.au) * Correspondence: [iman.hosseini@anu.edu.au](iman.hosseini@anu.edu.au) † This paper is an extended version of our paper published in 2023 IEEE International Symposium on Inertial Sensors and Systems (INERTIAL), Lihue, HI, USA, 28–31 March 2023, titled as “Locomotive Syndrome Assessment in Older Adults Using a Single Inertial Measurement Unit”. ‡ These authors contributed equally to this work. Abstract: Locomotive syndrome (LS) refers to a condition where individuals face challenges in performing activities of daily living. Early detection of such deterioration is crucial to reduce the need for nursing care. The Geriatric Locomotive Function Scale (GLFS-25), a 25-question assessment, has been proposed for categorizing individuals into different stages of LS. However, its subjectivity has prompted interest in technology-based quantitative assessments. In this study, we utilized machine learning and an instrumented five-time sit-to-stand test (FTSTS) to assess LS stages. Younger and older participants were recruited, with older individuals classified into LS stages 0–2 based on their GLFS-25 scores. Equipped with a single inertial measurement unit at the pelvis level, participants performed the FTSTS. Using acceleration data, 144 features were extracted, and seven distinct machine learning models were developed using the features. Remarkably, the multilayer perceptron (MLP) model demonstrated superior performance. Following data augmentation and principal component analysis (PCA), the MLP+PCA model achieved an accuracy of 0.9, a precision of 0.92, a recall of 0.9, and an F1 score of 0.91 . This underscores the efficacy of the approach for LS assessment. This study lays the foundation for the future development of a remote LS assessment system using commonplace devices like smartphones. Keywords: inertial measurement unit; locomotive syndrome; machine learning; sit to stand 1. Introduction The term “locomotive syndrome”(LS) was proposed by the Japanese Orthopaedic Association (JOA) in 2007 to define individuals who are prone to requiring nursing care services due to facing difficulties in performing activities of daily living (ADL) and hence are unable to live independently as the result of the physiological deterioration of locomotive organs [1] . The early diagnosis of any physical deterioration, specifically in such organs, is crucial to diminish the need for nursing care services [2] . The LS concept has thus attracted scientists’ and researchers’ attention around the world [3,4] . While LS was initially presumed to cause musculoskeletal disorder, several studies have also proved that certain psychological disorders result from LS [5,6] . The locomotive system is essential for mobility, and its health is particularly critical for older people. Over the past

FAQs

What is locomotive syndrome (LS) and why is early detection important?

Locomotive syndrome refers to a decline that makes activities of daily living harder. Early detection helps reduce the need for nursing care by identifying deterioration sooner.

How does the study assess LS stages using technology?

Participants perform an instrumented five-time sit-to-stand test while wearing a pelvic inertial measurement unit. Acceleration data are converted into 144 features that feed multiple machine learning models to classify LS stages.

Which machine learning model performed best and what metrics were achieved?

The multilayer perceptron (MLP) showed superior performance. With data augmentation and principal component analysis (PCA), the MLP+PCA model achieved accuracy 0.9, precision 0.92, recall 0.9, and F1 score 0.91.

Aug 4, 2026

Upload by Oliver