{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T19:42:57Z","timestamp":1791229377376,"version":"4.1.0"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>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\u2019s effectiveness in classifying frail and non-frail stages by capturing spatio-temporal features from raw IMU signals.<\/jats:p>","DOI":"10.1371\/journal.pone.0343402","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:31:10Z","timestamp":1771957870000},"page":"e0343402","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["A deep learning framework for gait-based frailty classification using inertial measurement units"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-4382","authenticated-orcid":true,"given":"Arslan","family":"Amjad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Agnieszka","family":"Szcz\u0119sna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monika","family":"B\u0142aszczyszyn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jerzy","family":"Sacha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magdalena","family":"Sacha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Feusette","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wojciech","family":"Wola\u0144ski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7995-0882","authenticated-orcid":true,"given":"Mariusz","family":"Konieczny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zbigniew","family":"Borysiuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Basheir","family":"khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,2,24]]},"reference":[{"issue":"9868","key":"pone.0343402.ref001","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/S0140-6736(12)62167-9","article-title":"Frailty in elderly people","volume":"381","author":"A Clegg","year":"2013","journal-title":"Lancet"},{"key":"pone.0343402.ref002","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/B978-0-323-84702-5.00054-3","article-title":"What are multimorbidity and frailty and how do they affect the care of older adults?","author":"V Rivera","year":"2023","journal-title":"Evidence-Based Practice of Palliative Medicine. Elsevier"},{"issue":"3","key":"pone.0343402.ref003","doi-asserted-by":"crossref","DOI":"10.1093\/gerona\/56.3.M146","article-title":"Frailty in older adults: Evidence for a phenotype","volume":"56","author":"LP Fried","year":"2001","journal-title":"J Gerontol A Biol Sci Med Sci"},{"issue":"2","key":"pone.0343402.ref004","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1111\/j.1532-5415.1991.tb01616.x","article-title":"The timed \u201cUp & Go\u201d: a test of basic functional mobility for frail elderly persons","volume":"39","author":"D Podsiadlo","year":"1991","journal-title":"J Am Geriatr Soc"},{"issue":"1","key":"pone.0343402.ref005","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.bbe.2019.12.001","article-title":"The repeatability of the instrumented timed Up & Go test: The performance of older adults and parkinson\u2019s disease patients under different conditions","volume":"40","author":"S Viteckova","year":"2020","journal-title":"Biocybernetics and Biomedical Engineering"},{"issue":"1","key":"pone.0343402.ref006","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.jphys.2017.04.002","article-title":"The Short Physical Performance Battery","volume":"64","author":"D Treacy","year":"2018","journal-title":"J Physiother"},{"key":"pone.0343402.ref007","doi-asserted-by":"crossref","first-page":"101833","DOI":"10.1016\/j.pmcj.2023.101833","article-title":"Automated, ecologic assessment of frailty using a wrist-worn device","volume":"95","author":"D Minici","year":"2023","journal-title":"Pervasive and Mobile Computing"},{"issue":"1","key":"pone.0343402.ref008","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1186\/s12877-017-0509-1","article-title":"Frailty assessment in older adults using upper-extremity function: Index development","volume":"17","author":"N Toosizadeh","year":"2017","journal-title":"BMC Geriatr"},{"key":"pone.0343402.ref009","doi-asserted-by":"crossref","DOI":"10.2196\/47346","article-title":"Use of artificial intelligence in the identification and diagnosis of frailty syndrome in older adults: Scoping review","volume":"25","author":"D Velazquez-Diaz","year":"2023","journal-title":"J Med Internet Res"},{"key":"pone.0343402.ref010","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1080\/17434440.2021.1988849","article-title":"Wearable inertial sensors for human movement analysis: A five-year update","volume":"18","author":"P Picerno","year":"2021","journal-title":"Expert Rev Med Devices"},{"issue":"3","key":"pone.0343402.ref011","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1109\/JBHI.2021.3100979","article-title":"Towards Automated Assessment of Frailty Status Using a Wrist-Worn Device","volume":"26","author":"D Minici","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"pone.0343402.ref012","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1016\/j.bbe.2022.05.008","article-title":"The internet of medical things and artificial intelligence: Trends, challenges, and opportunities","volume":"42","author":"K Kakhi","year":"2022","journal-title":"Biocybernetics and Biomedical Engineering"},{"key":"pone.0343402.ref013","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.1052","article-title":"Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models","volume":"8","author":"M Ja\u00e9n-Vargas","year":"2022","journal-title":"PeerJ Comput Sci"},{"issue":"2","key":"pone.0343402.ref014","doi-asserted-by":"crossref","first-page":"149","DOI":"10.3390\/healthcare9020149","article-title":"A deep learning approach for TUG and SPPB score prediction of (Pre-) frail older adults on real-life IMU data","volume":"9","author":"B Friedrich","year":"2021","journal-title":"Healthcare (Basel)"},{"key":"pone.0343402.ref015","first-page":"1874","article-title":"Gait-based frailty assessment using image representation of IMU signals and deep CNN","volume":"2021","author":"MZ Arshad","year":"2021","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"pone.0343402.ref016","doi-asserted-by":"crossref","first-page":"757823","DOI":"10.3389\/fnagi.2021.757823","article-title":"Application of machine vision in classifying gait frailty among older adults","volume":"13","author":"Y Liu","year":"2021","journal-title":"Front Aging Neurosci"},{"issue":"14","key":"pone.0343402.ref017","doi-asserted-by":"crossref","first-page":"3857","DOI":"10.3390\/s20143857","article-title":"Evaluation of vertical ground reaction forces pattern visualization in neurodegenerative diseases identification using deep learning and recurrence plot image feature extraction","volume":"20","author":"C-W Lin","year":"2020","journal-title":"Sensors (Basel)"},{"issue":"13","key":"pone.0343402.ref018","doi-asserted-by":"crossref","first-page":"4273","DOI":"10.3390\/s24134273","article-title":"Research on monitoring assistive devices for rehabilitation of movement disorders through multi-sensor analysis combined with deep learning","volume":"24","author":"Z Xu","year":"2024","journal-title":"Sensors (Basel)"},{"issue":"14","key":"pone.0343402.ref019","doi-asserted-by":"crossref","first-page":"4661","DOI":"10.3390\/s21144661","article-title":"Automated loss-of-balance event identification in older adults at risk of falls during real-world walking using wearable inertial measurement units","volume":"21","author":"J Hauth","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"7","key":"pone.0343402.ref020","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/JBHI.2019.2958879","article-title":"Deep learning for fall risk assessment with inertial sensors: Utilizing domain knowledge in spatio-temporal gait parameters","volume":"24","author":"C Tunca","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0343402.ref021","doi-asserted-by":"crossref","first-page":"106551","DOI":"10.1016\/j.ssci.2024.106551","article-title":"Fall-risk assessment of aged workers using wearable inertial measurement units based on machine learning","volume":"176","author":"J Kou","year":"2024","journal-title":"Safety Science"},{"issue":"3","key":"pone.0343402.ref022","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.3390\/s23031105","article-title":"Transfer learning on small datasets for improved fall detection","volume":"23","author":"N Maray","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"18","key":"pone.0343402.ref023","doi-asserted-by":"crossref","first-page":"5373","DOI":"10.3390\/s20185373","article-title":"Detection of gait abnormalities for fall risk assessment using wrist-worn inertial sensors and deep learning","volume":"20","author":"I Kiprijanovska","year":"2020","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0343402.ref024","doi-asserted-by":"crossref","first-page":"73","DOI":"10.18280\/ts.410106","article-title":"Fusion of dual sensor features for fall risk assessment with improved attention mechanism","volume":"41","author":"C Li","year":"2024","journal-title":"TS"},{"issue":"15","key":"pone.0343402.ref025","doi-asserted-by":"crossref","first-page":"24086","DOI":"10.1109\/JSEN.2024.3407835","article-title":"Unveiling fall origins: Leveraging wearable sensors to detect pre-impact fall causes","volume":"24","author":"S Kiran","year":"2024","journal-title":"IEEE Sensors J"},{"issue":"1","key":"pone.0343402.ref026","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/JBHI.2019.2906499","article-title":"Falls risk classification of older adults using deep neural networks and transfer learning","volume":"24","author":"M Martinez","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0343402.ref027","first-page":"563","article-title":"Time series data augmentation and dropout roles in deep learning applied to fall detection","author":"EG Gonz\u00e1lez","year":"2020","journal-title":"Advances in Intelligent Systems and Computing. Springer International Publishing"},{"issue":"1","key":"pone.0343402.ref028","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1038\/s41597-023-02428-0","article-title":"A database with frailty, functional and inertial gait metrics for the research of fall causes in older adults","volume":"10","author":"S Garc\u00eda-de-Villa","year":"2023","journal-title":"Sci Data"},{"key":"pone.0343402.ref029","unstructured":"Garc\u00eda-Villamil G, Ruiz L, Jim\u00e9nez AR, Granja FS, Rodr\u00edguez-S\u00e1nchez MC. Influence of IMU\u2019s Measurement Noise on the Accuracy of Stride-Length Estimation for Gait Analysis. IPIN-WiP. 2021. https:\/\/api.semanticscholar.org\/CorpusID:247314771"},{"key":"pone.0343402.ref030","unstructured":"Xsens Technologies. MVN user manual. https:\/\/www.xsens.com\/hubfs\/Downloads\/usermanual.%22%0AMVN_User_Manual.pdf. Accessed 2024 January 2."},{"key":"pone.0343402.ref031","doi-asserted-by":"crossref","first-page":"111637","DOI":"10.1016\/j.jbiomech.2023.111637","article-title":"Concurrent validation of the Xsens IMU system of lower-body kinematics in jump-landing and change-of-direction tasks","volume":"154","author":"EM Nijmeijer","year":"2023","journal-title":"J Biomech"},{"issue":"4","key":"pone.0343402.ref032","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.jamda.2014.11.011","article-title":"Instruments to assess sarcopenia and physical frailty in older people living in a community (care) setting: similarities and discrepancies","volume":"16","author":"DM Mijnarends","year":"2015","journal-title":"J Am Med Dir Assoc"},{"issue":"4","key":"pone.0343402.ref033","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1109\/TBME.2014.2368211","article-title":"Inertial sensor-based stride parameter calculation from gait sequences in geriatric patients","volume":"62","author":"A Rampp","year":"2015","journal-title":"IEEE Trans Biomed Eng"},{"issue":"7","key":"pone.0343402.ref034","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.3390\/s24072199","article-title":"A novel framework based on deep learning architecture for continuous human activity recognition with inertial sensors","volume":"24","author":"V Suglia","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0343402.ref035","doi-asserted-by":"crossref","first-page":"1776","DOI":"10.1109\/TNSRE.2022.3186616","article-title":"Can wearable devices and machine learning techniques be used for recognizing and segmenting modified physical performance test items?","volume":"30","author":"Y Zhang","year":"2022","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"2","key":"pone.0343402.ref036","doi-asserted-by":"crossref","first-page":"100046","DOI":"10.1016\/j.jjimei.2021.100046","article-title":"Deep learning based human activity recognition (HAR) using wearable sensor data","volume":"1","author":"S Gupta","year":"2021","journal-title":"International Journal of Information Management Data Insights"},{"key":"pone.0343402.ref037","author":"V Nair","year":"2010","journal-title":"Rectified Linear Units Improve Restricted Boltzmann Machines. International Conference on Machine Learning"},{"issue":"1","key":"pone.0343402.ref038","doi-asserted-by":"crossref","first-page":"115","DOI":"10.3390\/s16010115","article-title":"Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition","volume":"16","author":"FJ Ord\u00f3\u00f1ez","year":"2016","journal-title":"Sensors (Basel)"},{"key":"pone.0343402.ref039","article-title":"Going Deeper with Convolutions","author":"C Szegedy","year":"2014"},{"key":"pone.0343402.ref040","doi-asserted-by":"crossref","first-page":"100548","DOI":"10.1016\/j.softx.2020.100548","article-title":"Mcfly: Automated deep learning on time series","volume":"12","author":"D van Kuppevelt","year":"2020","journal-title":"SoftwareX"},{"issue":"1","key":"pone.0343402.ref041","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/MS.2022.3212033","article-title":"Creating a low-code business process execution platform with python, BPMN, and DMN","volume":"40","author":"D Funk","year":"2023","journal-title":"IEEE Softw"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:31:19Z","timestamp":1771957879000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343402"}},"subtitle":[],"editor":[{"given":"Alessandro","family":"Mengarelli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0343402","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,24]]}}}