Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life

Overview

Journal Biosensors (Basel)

Specialty Biotechnology

Date 2022 Mar 24

PMID 35323437

Authors

Jeong-Kyun Kim

Myung-Nam Bae

Kangbok Lee

Jae-Chul Kim

Sang Gi Hong

Affiliations

Soon will be listed here.

Abstract

Osteopenia and sarcopenia can cause various senile diseases and are key factors related to the quality of life in old age. There is need for portable tools and methods that can analyze osteopenia and sarcopenia risks during daily life, rather than requiring a specialized hospital setting. Gait is a suitable indicator of musculoskeletal diseases; therefore, we analyzed the gait signal obtained from an inertial-sensor-based wearable gait device as a tool to manage bone loss and muscle loss in daily life. To analyze the inertial-sensor-based gait, the inertial signal was classified into seven gait phases, and descriptive statistical parameters were obtained for each gait phase. Subsequently, explainable artificial intelligence was utilized to analyze the contribution and importance of descriptive statistical parameters on osteopenia and sarcopenia. It was found that XGBoost yielded a high accuracy of 88.69% for osteopenia, whereas the random forest approach showed a high accuracy of 93.75% for sarcopenia. Transfer learning with a ResNet backbone exhibited appropriate performance but showed lower accuracy than the descriptive statistical parameter-based identification result. The proposed gait analysis method confirmed high classification accuracy and the statistical significance of gait factors that can be used for osteopenia and sarcopenia management.

Citing Articles

Comparing Stability, Gait, and Functional Score after 40-mm Dual-Mobility Hip Arthroplasty to 36-mm Head Hip Arthroplasty in Elderly Hip Fracture Patients.

Cha Y, Lee S, Bae J, Kang Y, Baek J, Kang J Clin Orthop Surg. 2025; 17(1):62-70.

PMID: 39912063 PMC: 11791493. DOI: 10.4055/cios24148.

The Use of Artificial Intelligence and Wearable Inertial Measurement Units in Medicine: Systematic Review.

Smits Serena R, Hinterwimmer F, Burgkart R, von Eisenhart-Rothe R, Rueckert D JMIR Mhealth Uhealth. 2025; 13:e60521.

PMID: 39880389 PMC: 11822330. DOI: 10.2196/60521.

Gait-Based AI Models for Detecting Sarcopenia and Cognitive Decline Using Sensor Fusion.

Aznar-Gimeno R, Perez-Lasierra J, Perez-Lazaro P, Bosque-Lopez I, Azpiroz-Puente M, Salvo-Ibanez P Diagnostics (Basel). 2025; 14(24.

PMID: 39767247 PMC: 11675090. DOI: 10.3390/diagnostics14242886.

Wearable Fabric System for Sarcopenia Detection.

Huang Z, Ou Q, Li D, Feng Y, Cai L, Hu Y Biosensors (Basel). 2024; 14(12).

PMID: 39727887 PMC: 11674443. DOI: 10.3390/bios14120622.

Exploring the Applications of Explainability in Wearable Data Analytics: Systematic Literature Review.

Abdelaal Y, Aupetit M, Baggag A, Al-Thani D J Med Internet Res. 2024; 26():e53863.

PMID: 39718820 PMC: 11707450. DOI: 10.2196/53863.

References

Sung P . Increased double limb support times during walking in right limb dominant healthy older adults with low bone density. Gait Posture. 2018; 63:145-149. DOI: 10.1016/j.gaitpost.2018.04.036. View

Howcroft J, Kofman J, Lemaire E . Prospective Fall-Risk Prediction Models for Older Adults Based on Wearable Sensors. IEEE Trans Neural Syst Rehabil Eng. 2017; 25(10):1812-1820. DOI: 10.1109/TNSRE.2017.2687100. View

Parsa A, Movahedi A, Taghipour H, Derrible S, Mohammadian A . Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accid Anal Prev. 2019; 136:105405. DOI: 10.1016/j.aap.2019.105405. View

Choi W, Choi J, Chung C, Sung K, Lee K . Can gait kinetic data predict femoral bone mineral density in elderly men and women aged 50 years and older?. J Biomech. 2021; 123:110520. DOI: 10.1016/j.jbiomech.2021.110520. View

Cruz-Jentoft A, Baeyens J, Bauer J, Boirie Y, Cederholm T, Landi F . Sarcopenia: European consensus on definition and diagnosis: Report of the European Working Group on Sarcopenia in Older People. Age Ageing. 2010; 39(4):412-23. PMC: 2886201. DOI: 10.1093/ageing/afq034. View

Stephen W, Janssen I . Sarcopenic-obesity and cardiovascular disease risk in the elderly. J Nutr Health Aging. 2009; 13(5):460-6. DOI: 10.1007/s12603-009-0084-z. View

Bach S, Binder A, Montavon G, Klauschen F, Muller K, Samek W . On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. PLoS One. 2015; 10(7):e0130140. PMC: 4498753. DOI: 10.1371/journal.pone.0130140. View

Baek S, Piao J, Jin Y, Lee S . Validity of the Morse Fall Scale implemented in an electronic medical record system. J Clin Nurs. 2013; 23(17-18):2434-40. DOI: 10.1111/jocn.12359. View

Kim S, Kim M, Won C . Validation of the Korean Version of the SARC-F Questionnaire to Assess Sarcopenia: Korean Frailty and Aging Cohort Study. J Am Med Dir Assoc. 2017; 19(1):40-45.e1. DOI: 10.1016/j.jamda.2017.07.006. View

10.

Taborri J, Palermo E, Rossi S, Cappa P . Gait Partitioning Methods: A Systematic Review. Sensors (Basel). 2016; 16(1). PMC: 4732099. DOI: 10.3390/s16010066. View

11.

Eskofier B, Lee S, Daneault J, Golabchi F, Ferreira-Carvalho G, Vergara-Diaz G . Recent machine learning advancements in sensor-based mobility analysis: Deep learning for Parkinson's disease assessment. Annu Int Conf IEEE Eng Med Biol Soc. 2017; 2016:655-658. DOI: 10.1109/EMBC.2016.7590787. View

12.

Dindorf C, Teufl W, Taetz B, Bleser G, Frohlich M . Interpretability of Input Representations for Gait Classification in Patients after Total Hip Arthroplasty. Sensors (Basel). 2020; 20(16). PMC: 7471970. DOI: 10.3390/s20164385. View

13.

Tatangelo G, Watts J, Lim K, Connaughton C, Abimanyi-Ochom J, Borgstrom F . The Cost of Osteoporosis, Osteopenia, and Associated Fractures in Australia in 2017. J Bone Miner Res. 2019; 34(4):616-625. DOI: 10.1002/jbmr.3640. View

14.

Podsiadlo D, Richardson S . The timed "Up & Go": a test of basic functional mobility for frail elderly persons. J Am Geriatr Soc. 1991; 39(2):142-8. DOI: 10.1111/j.1532-5415.1991.tb01616.x. View

15.

Teufl W, Taetz B, Miezal M, Lorenz M, Pietschmann J, Jollenbeck T . Towards an Inertial Sensor-Based Wearable Feedback System for Patients after Total Hip Arthroplasty: Validity and Applicability for Gait Classification with Gait Kinematics-Based Features. Sensors (Basel). 2019; 19(22). PMC: 6891461. DOI: 10.3390/s19225006. View

16.

Tunca C, Salur G, Ersoy C . Deep Learning for Fall Risk Assessment With Inertial Sensors: Utilizing Domain Knowledge in Spatio-Temporal Gait Parameters. IEEE J Biomed Health Inform. 2019; 24(7):1994-2005. DOI: 10.1109/JBHI.2019.2958879. View

17.

Caramia C, Torricelli D, Schmid M, Munoz-Gonzalez A, Gonzalez-Vargas J, Grandas F . IMU-Based Classification of Parkinson's Disease From Gait: A Sensitivity Analysis on Sensor Location and Feature Selection. IEEE J Biomed Health Inform. 2018; 22(6):1765-1774. DOI: 10.1109/JBHI.2018.2865218. View

18.

Kanis J . Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: synopsis of a WHO report. WHO Study Group. Osteoporos Int. 1994; 4(6):368-81. DOI: 10.1007/BF01622200. View

19.

Intriago M, Maldonado G, Guerrero R, Messina O, Rios C . Bone Mass Loss and Sarcopenia in Ecuadorian Patients. J Aging Res. 2020; 2020:1072675. PMC: 7103045. DOI: 10.1155/2020/1072675. View

20.

Kim J, Bae M, Lee K, Hong S . Identification of Patients with Sarcopenia Using Gait Parameters Based on Inertial Sensors. Sensors (Basel). 2021; 21(5). PMC: 7961754. DOI: 10.3390/s21051786. View