{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:01:32Z","timestamp":1777863692459,"version":"3.51.4"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:p>\n                    Falls among older adults pose a major healthcare and social burden, making early identification of high-risk individuals essential for prevention. This study presents a portable, non-invasive AI-based wearable system that predicts fall risk using surface electromyography (sEMG) and plantar-pressure measurements collected during overground walking. sEMG electrodes were placed bilaterally over eight key lower-limb muscles\u2014tibialis anterior, peroneus longus, medial and lateral gastrocnemius, rectus femoris, vastus medialis, vastus lateralis, and biceps femoris\u2014while pressure insoles captured loading at eight anatomical foot regions. Ninety-four older adults (mean age 69.6\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"m1\">\n                        <mml:mrow>\n                          <mml:mo>\u00b1<\/mml:mo>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    10.0 years; 57 females), including 57 non-fallers and 37 individuals who met ICD-10 diagnostic criteria for \u201cpropensity to fall,\u201d participated in the modeling study. The signals from both devices were streamed wirelessly to a central acquisition unit for synchronized processing. Extracted features included muscle activation contribution, mean frequency, mean power frequency, and cumulative plantar-pressure impulses. These features served as model input. To reduce data dimensionality, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were applied. PCA retained a variance structure, whereas LDA maximized class separability. Three machine-learning classifiers\u2014Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGB)\u2014were trained using Leave-One-Out Cross-Validation. LDA substantially improved performance across all models, with LDA + SVM achieving the highest accuracy (0.88), precision (0.92), recall (0.85), and F1-score (0.87). An independent clinical validation study involving ten additional older adults demonstrated that LDA-based models generalized well beyond the original dataset. Compared with existing fall-detection or multimodal EMG-based systems that focus on simulated falls, young participants, or non-portable laboratory equipment, the proposed framework enables physiologically interpretable, clinically deployable fall-risk prediction during natural gait. These findings highlight the promise of dual-modality wearable sensing for proactive fall prevention in geriatric populations.\n                  <\/jats:p>","DOI":"10.3389\/fbioe.2026.1698253","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T05:29:59Z","timestamp":1777526999000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-based wearable system for fall risk prediction in older adults using sEMG and plantar pressure data"],"prefix":"10.3389","volume":"14","author":[{"given":"Xikun","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuandan","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Department of Orthopedics, West China School of Public Health and West China Fourth Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boquan","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohui","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peifang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiali","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Ke","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen Technology University","place":["Shenzhen, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]},{"name":"Med-X Center for Manufacturing, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e36556","DOI":"10.1371\/journal.pone.0036556","article-title":"Fall classification by machine learning using Mobile phones","volume":"7","author":"Albert","year":"2012","journal-title":"PLOS ONE"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2014\/197960","article-title":"Computation and evaluation of features of surface electromyogram to identify the force of muscle contraction and muscle fatigue","volume":"2014","author":"Arjunan","year":"2014","journal-title":"BioMed Res. Int."},{"key":"B3","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1159\/000368655","article-title":"The application of sEMG in aging: a mini review","volume":"61","author":"Boccia","year":"2015","journal-title":"Gerontology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"113","DOI":"10.3233\/SHTI230113","article-title":"Privacy by design solution for robust fall detection","volume":"306","author":"Brandst\u00f6tter","year":"2023","journal-title":"Stud. Health Technol. Inf."},{"key":"B5","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1109\/thms.2023.3287594","article-title":"A layered sEMG\u2013FMG hybrid sensor for hand motion recognition from forearm muscle activities","volume":"53","author":"Chen","year":"2023","journal-title":"IEEE Trans. Human-Machine Syst."},{"key":"B6","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/TITB.2012.2226905","article-title":"A framework for daily activity monitoring and fall detection based on surface electromyography and accelerometer signals","volume":"17","author":"Cheng","year":"2013","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B7","doi-asserted-by":"publisher","first-page":"12431","DOI":"10.3390\/s130912431","article-title":"Others. Surface electromyography signal processing and classification techniques","volume":"13","author":"Chowdhury","year":"2013","journal-title":"Sensors"},{"key":"B8","doi-asserted-by":"publisher","first-page":"105635","DOI":"10.1016\/j.bspc.2023.105635","article-title":"Electromyography and dynamometry in the prediction of risk of falls in the elderly using machine learning tools","volume":"88","author":"da Silva","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B9","first-page":"1624","volume-title":"Semi-supervised learning for surface EMG-Based gesture recognition","author":"Du","year":"2017"},{"key":"B10","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","article-title":"SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary","volume":"61","author":"Fern\u00e1ndez","year":"2018","journal-title":"J. Artificial Intelligence Research"},{"key":"B11","doi-asserted-by":"publisher","first-page":"666458","DOI":"10.3389\/fneur.2021.666458","article-title":"Evaluation of three machine learning algorithms for the automatic classification of EMG patterns in gait disorders","volume":"12","author":"Fricke","year":"2021","journal-title":"Front. Neurology"},{"key":"B12","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-319-67723-1_6","article-title":"Microelectronics for muscle fatigue monitoring through surface EMG","author":"Georgiou","year":"2018","journal-title":"Proc. CMOS Circuits Biol. Sens. Process."},{"key":"B13","doi-asserted-by":"publisher","first-page":"796711","DOI":"10.3389\/fnins.2022.796711","article-title":"Kernel density estimation of electromyographic signals and ensemble learning for highly accurate classification of a large set of hand\/wrist motions","volume":"16","author":"Ghaderi","year":"2022","journal-title":"Front. Neuroscience"},{"key":"B14","doi-asserted-by":"publisher","first-page":"CD007146","DOI":"10.1002\/14651858.CD007146.pub2","article-title":"Interventions for preventing falls in older people living in the community","author":"Gillespie","year":"2009","journal-title":"Cochrane Database Systematic Reviews"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10916-014-0031-3","article-title":"Effect of multiscale PCA de-noising on EMG signal classification for diagnosis of neuromuscular disorders","volume":"38","author":"Gokgoz","year":"2014","journal-title":"J. Med. Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s10916-005-5184-7","article-title":"Classification of EMG signals using PCA and FFT","volume":"29","author":"G\u00fcler","year":"2005","journal-title":"J. Med. Syst."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1109\/TNSRE.2017.2687100","article-title":"Prospective fall-risk prediction models for older adults based on wearable sensors","volume":"25","author":"Howcroft","year":"2017","journal-title":"IEEE Trans. Neural Syst. Rehabilitation Eng."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1184950","DOI":"10.3389\/fpubh.2023.1184950","article-title":"Global population aging\u2013health care, social and economic consequences, volume II","volume":"11","author":"Jakovljevic","year":"2023","journal-title":"Front. Public Health"},{"key":"B19","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.cmpb.2017.10.024","article-title":"Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms","volume":"154","author":"Karthick","year":"2018","journal-title":"Comput. Methods Programs Biomedicine"},{"key":"B20","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3390\/electronics9010043","article-title":"Estimation of knee movement from surface EMG using random forest with principal component analysis","volume":"9","author":"Li","year":"2019","journal-title":"Electronics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"2814","DOI":"10.3390\/s19122814","article-title":"Others. A new approach to fall detection based on improved dual parallel channels convolutional neural network","volume":"19","author":"Liu","year":"2019","journal-title":"Sensors (Basel)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s00198-011-1637-7","article-title":"Relationships between serum vitamin D levels, neuromuscular and neuropsychological function and falls in older men and women","volume":"23","author":"Menant","year":"2012","journal-title":"Osteoporos. Int."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1111\/j.1532-5415.2010.03061.x","article-title":"Foot pain, plantar pressures, and falls in older people: a prospective study","volume":"59","author":"Mickle","year":"2011","journal-title":"J. Am. Geriatrics Soc."},{"key":"B24","doi-asserted-by":"publisher","first-page":"4181","DOI":"10.1109\/jsen.2023.3344605","article-title":"Artificial intelligence and IoT in elderly fall prevention: a review","volume":"24","author":"Mohan","year":"2024","journal-title":"IEEE Sensors J."},{"key":"B25","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1109\/cit.2008.4594760","article-title":"Multi run ICA and surface EMG based signal processing system for recognising hand gestures","author":"Naik","year":"2008","journal-title":"Proc. 8th IEEE Int. Conf. Comput. Inf. Technol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"13926","DOI":"10.3390\/ijerph192113926","article-title":"Associations of gait speed, cadence, gait stability ratio, and body balance with falls in older adults","volume":"19","author":"Nascimento","year":"2022","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B27","doi-asserted-by":"publisher","first-page":"10691","DOI":"10.3390\/s1406106","article-title":"Detecting falls with wearable sensors using machine learning techniques","volume":"14","author":"Ozdemir","year":"2014","journal-title":"Sensors"},{"key":"B28","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.gaitpost.2022.01.009","article-title":"Others. Muscle activation profile is modulated by unexpected balance loss in walking","volume":"93","author":"Rosenblum","year":"2022","journal-title":"Gait Posture"},{"key":"B29","doi-asserted-by":"publisher","first-page":"137489","DOI":"10.1109\/access.2019.2941977","article-title":"Movements classification of multi-channel sEMG based on CNN and stacking ensemble learning","volume":"7","author":"Shen","year":"2019","journal-title":"Ieee Access"},{"key":"B30","doi-asserted-by":"publisher","first-page":"111018","DOI":"10.1016\/j.jbiomech.2022.111018","article-title":"Muscle power is more important than strength in preventing falls in community-dwelling older adults","volume":"134","author":"Simpkins","year":"2022","journal-title":"J. Biomechanics"},{"key":"B31","first-page":"1","article-title":"Fall detection and prediction based on IMU and EMG sensors for elders","author":"Siwadamrongpong","year":"2022"},{"key":"B32","doi-asserted-by":"publisher","first-page":"9546","DOI":"10.3390\/app13179546","article-title":"Review of sEMG for robot control: techniques and applications","volume":"13","author":"Song","year":"2023","journal-title":"Appl. Sci."},{"key":"B33","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1093\/oxfordjournals.aje.a116536","article-title":"Peripheral neuromuscular dysfunction and falls in an elderly cohort","volume":"136","author":"Sorock","year":"1992","journal-title":"Am. J. Epidemiol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"233","DOI":"10.3969\/j.issn.0258-8021.2017.02.015","article-title":"Study on gait characteristics of lower extremities surface electromyography after slips and falls","volume":"36","author":"Su","year":"2017","journal-title":"Chin. J. Biomed. Eng."},{"key":"B35","doi-asserted-by":"publisher","first-page":"107315","DOI":"10.1016\/j.compbiomed.2023.107315","article-title":"Effective fall detection and post-fall breath rate tracking using a low-cost CW doppler radar sensor","volume":"164","author":"Tewari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B36","doi-asserted-by":"publisher","first-page":"810","DOI":"10.3724\/SP.J.1004.2014.00810","article-title":"Multi-channel sEMG time series analysis based human motion recognition method","volume":"40","author":"Tong","year":"2014","journal-title":"Acta Autom. Sin."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.3390\/s23031323","article-title":"Others. Smartphones and threshold-based monitoring methods effectively detect falls remotely: a systematic review","volume":"23","author":"Torres-Guzman","year":"2023","journal-title":"Sensors (Basel)"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1007\/s40520-021-02017-4","article-title":"Aging tsunami coming: the main finding from China\u2019s seventh national population census","volume":"34","author":"Tu","year":"2022","journal-title":"Aging Clin. Exp. Res."},{"key":"B39","doi-asserted-by":"publisher","first-page":"798","DOI":"10.22038\/abjs.2022.59134.2913","article-title":"Others. The efficacy of \u201cAnatomical Posture Control Orthosis\u201d on the activity of erector spinae muscle, risk of falling, balance confidence, and walking speed in osteoporotic hyperkyphotic subjects","volume":"10","author":"Veiskarami","year":"2022","journal-title":"Archives Bone Jt. Surg."},{"key":"B40","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.patrec.2020.05.035","article-title":"Imbalance-XGBoost: leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost","volume":"136","author":"Wang","year":"2020","journal-title":"Pattern Recognition Letters"},{"key":"B41","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/robio.2009.4912988","article-title":"Use of forehead bio-signals for controlling an intelligent wheelchair","author":"Wei","year":"2009","journal-title":"Proc. IEEE Int. Conf. Robot. Biomimetics"},{"key":"B42","doi-asserted-by":"publisher","first-page":"2839","DOI":"10.1016\/j.patcog.2015.03.009","article-title":"Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation","volume":"48","author":"Wong","year":"2015","journal-title":"Pattern Recognition"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.3390\/s17061229","article-title":"Evaluation of feature extraction and recognition for activity monitoring and fall detection based on wearable sEMG sensors","volume":"17","author":"XI","year":"2017","journal-title":"Sensors (Basel)"},{"key":"B44","doi-asserted-by":"publisher","first-page":"9532067","DOI":"10.1155\/2020\/9532067","article-title":"Daily activity monitoring and fall detection based on surface electromyography and plantar pressure","volume":"2020","author":"Xi","year":"2020","journal-title":"Complexity"},{"key":"B45","first-page":"4205","article-title":"Others. Implementation of a real-time fall detection system based on hybrid threshold analysis algorithm and machine learning algorithm","author":"Xu","year":"2022"},{"key":"B46","doi-asserted-by":"publisher","first-page":"722","DOI":"10.20965\/jaciii.2022.p0722","article-title":"Extreme gradient boosting for surface electromyography classification on time-domain features","volume":"26","author":"Zhao","year":"2022","journal-title":"J. Adv. Comput. Intell. Intelligent Inf."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1698253\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T05:30:01Z","timestamp":1777527001000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1698253\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":46,"alternative-id":["10.3389\/fbioe.2026.1698253"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2026.1698253","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]},"article-number":"1698253"}}