{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:46:52Z","timestamp":1776750412932,"version":"3.51.2"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"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. Neurorobot."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Combining machine learning (ML) with gait analysis is widely applicable for diagnosing abnormal gait patterns.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>To analyze gait adaptability characteristics in stroke patients, develop ML models to identify individuals with GAD, and select optimal diagnostic models and key classification features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This study was investigated with 30 stroke patients (mean age 42.69\u2009years, 60% male) and 50 healthy adults (mean age 41.34\u2009years, 58% male). Gait adaptability was assessed using a CMill treadmill on gait adaptation tasks: target stepping, slalom walking, obstacle avoidance, and speed adaptation. The preliminary analysis of variables in both groups was conducted using t-tests and Pearson correlation. Features were extracted from demographics, gait kinematics, and gait adaptability datasets. ML models based on Support Vector Machine, Decision Tree, Multi-layer Perceptron, K-Nearest Neighbors, and AdaCost algorithm were trained to classify individuals with and without GAD. Model performance was evaluated using accuracy (ACC), sensitivity (SEN), F1-score and the area under the receiver operating characteristic (ROC) curve (AUC).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The stroke group showed a significantly decreased gait speed (<jats:italic>p<\/jats:italic>\u2009=\u20090.000) and step length (SL) (<jats:italic>p<\/jats:italic>\u2009=\u20090.000), while the asymmetry of SL (<jats:italic>p<\/jats:italic>\u2009=\u20090.000) and ST (<jats:italic>p<\/jats:italic>\u2009=\u20090.000) was higher compared to the healthy group. The gait adaptation tasks significantly decreased in slalom walking (<jats:italic>p<\/jats:italic>\u2009=\u20090.000), obstacle avoidance (<jats:italic>p<\/jats:italic>\u2009=\u20090.000), and speed adaptation (<jats:italic>p<\/jats:italic>\u2009=\u20090.000). Gait speed (<jats:italic>p<\/jats:italic>\u2009=\u20090.000) and obstacle avoidance (<jats:italic>p<\/jats:italic>\u2009=\u20090.000) were significantly correlated with global F-A score in stroke patients. The AdaCost demonstrated better classification performance with an ACC of 0.85, SEN of 0.80, F1-score of 0.77, and ROC-AUC of 0.75. Obstacle avoidance and gait speed were identified as critical features in this model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Stroke patients walk slower with shorter SL and more asymmetry of SL and ST. Their gait adaptability was decreased, particularly in obstacle avoidance and speed adaptation. The faster gait speed and better obstacle avoidance were correlated with better functional mobility. The AdaCost identifies individuals with GAD and facilitates clinical decision-making. This advances the future development of user-friendly interfaces and computer-aided diagnosis systems.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2024.1421401","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T05:10:29Z","timestamp":1722229829000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning-based gait adaptation dysfunction identification using CMill-based gait data"],"prefix":"10.3389","volume":"18","author":[{"given":"Hang","family":"Yang","sequence":"first","affiliation":[]},{"given":"Zhenyi","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Hailei","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Kuncheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ye","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zhenzhen","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Yajun","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Caiping","family":"Song","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"812","DOI":"10.3390\/s24030812","article-title":"Fall risk assessment in stroke survivors: a machine learning model using detailed motion data from common clinical tests and motor-cognitive dual-tasking","volume":"24","author":"Abdollahi","year":"2024","journal-title":"Sensors"},{"key":"ref2","author":"Alfayeed","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1016\/j.gaitpost.2011.01.004","article-title":"Step length asymmetry is representative of compensatory mechanisms used in post-stroke hemiparetic walking","volume":"33","author":"Allen","year":"2011","journal-title":"Gait Posture"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"7432","DOI":"10.3390\/s22197432","article-title":"Machine learning-based peripheral artery disease identification using laboratory-based gait data","volume":"22","author":"Al-Ramini","year":"2022","journal-title":"Sensors (Basel)"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.csda.2015.12.009","article-title":"High dimensional classifiers in the imbalanced case","volume":"98","author":"Bak","year":"2016","journal-title":"Comput. Stat. Data Anal."},{"key":"ref6","first-page":"560","article-title":"Gait analysis: clinical facts","volume":"52","author":"Baker","year":"2016","journal-title":"Eur. J. Phys. Rehabil. Med."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.apmr.2006.10.004","article-title":"Relationship between step length asymmetry and walking performance in subjects with chronic hemiparesis","volume":"88","author":"Balasubramanian","year":"2007","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"591013","DOI":"10.1155\/2014\/591013","article-title":"Walking adaptability after a stroke and its assessment in clinical settings","volume":"2014","author":"Balasubramanian","year":"2014","journal-title":"Stroke Res. Treat."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2824","DOI":"10.3390\/ijerph19052824","article-title":"Effect of treadmill training interventions on spatiotemporal gait parameters in older adults with neurological disorders: systematic review and Meta-analysis of randomized controlled trials","volume":"19","author":"Bishnoi","year":"2022","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/j.berh.2012.05.007","article-title":"Gait deviations in individuals with inflammatory joint diseases and osteoarthritis and the usage of three-dimensional gait analysis","volume":"26","author":"Brostr\u00f6m","year":"2012","journal-title":"Best Pract. Res. Clin. Rheumatol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1097\/00007632-199210000-00013","article-title":"The natural history of sciatica associated with disc pathology. A prospective study with clinical and independent radiologic follow-up","volume":"17","author":"Bush","year":"1992","journal-title":"Spine (Phila Pa 1976)"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"621977","DOI":"10.3389\/fnhum.2021.621977","article-title":"C-gait for detecting freezing of gait in the early to middle stages of Parkinson's disease: a model prediction study","volume":"15","author":"Chen","year":"2021","journal-title":"Front. Hum. Neurosci."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.artmed.2005.03.002","article-title":"Learning from imbalanced data in surveillance of nosocomial infection","volume":"37","author":"Cohen","year":"2006","journal-title":"Artif. Intell. Med."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1109\/TNSRE.2018.2811415","article-title":"Simultaneous recognition and assessment of post-stroke Hemiparetic gait by fusing kinematic, kinetic, and electrophysiological data","volume":"26","author":"Cui","year":"2018","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1093\/gerona\/glz282","article-title":"Unraveling the association between gait and mortality-one step at a time","volume":"75","author":"Dommershuijsen","year":"2020","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"ref16","volume-title":"Machine intelligence in medical imaging","author":"Erickson","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.2522\/ptj.20120344","article-title":"Tools for observational gait analysis in patients with stroke: a systematic review","volume":"93","author":"Ferrarello","year":"2013","journal-title":"Phys. Ther."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e0252380","DOI":"10.1371\/journal.pone.0252380","article-title":"Computer-aided identification of degenerative neuromuscular diseases based on gait dynamics and ensemble decision tree classifiers","volume":"16","author":"Fraiwan","year":"2021","journal-title":"PLoS One"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"3242","DOI":"10.1080\/09638288.2020.1731852","article-title":"Assessing walking adaptability in stroke patients","volume":"43","author":"Geerse","year":"2021","journal-title":"Disabil. Rehabil."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e12006","DOI":"10.1016\/j.heliyon.2022.e12006","article-title":"Singular value decomposition-based gait characterization","volume":"8","author":"Guzelbulut","year":"2022","journal-title":"Heliyon"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"749274","DOI":"10.3389\/frobt.2021.749274","article-title":"A survey of human gait-based artificial intelligence applications","volume":"8","author":"Harris","year":"2022","journal-title":"Front. Robot. AI"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1177\/154596830101500204","article-title":"Hemiparetic gait parameters in overground versus treadmill walking","volume":"15","author":"Harris-Love","year":"2001","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1186\/s12911-020-01201-2","article-title":"Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences","volume":"20","author":"Hatwell","year":"2020","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1007\/s00202-023-02084-y","article-title":"Improved intelligent methods for power transformer fault diagnosis based on tree ensemble learning and multiple feature vector analysis","volume":"106","author":"Hechifa","year":"2024","journal-title":"Electr. Eng."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"5979","DOI":"10.1038\/s41598-022-09954-8","article-title":"On evaluation metrics for medical applications of artificial intelligence","volume":"12","author":"Hicks","year":"2022","journal-title":"Sci. Rep."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1186\/1745-6215-14-276","article-title":"Visual cue training to improve walking and turning after stroke: a study protocol for a multi-Centre, single blind randomised pilot trial","volume":"14","author":"Hollands","year":"2013","journal-title":"Trials"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"5334","DOI":"10.3390\/s21165334","article-title":"Prediction of myoelectric biomarkers in post-stroke gait","volume":"21","author":"Hussain","year":"2021","journal-title":"Sensors (Basel)"},{"key":"ref28","author":"Jinzhu","year":"2009"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s10916-014-0038-9","article-title":"A clinical decision support system with an integrated EMR for diagnosis of peripheral neuropathy","volume":"38","author":"Kunhimangalam","year":"2014","journal-title":"J. Med. Syst."},{"key":"ref30","author":"Lakshmanarao","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1016\/j.humov.2008.12.003","article-title":"Support vector machine for classification of walking conditions of persons after stroke with dropped foot","volume":"28","author":"Lau","year":"2009","journal-title":"Hum. Mov. Sci."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.3390\/s19071737","article-title":"Gait analysis for post-stroke Hemiparetic patient by multi-features fusion method","volume":"19","author":"Li","year":"2019","journal-title":"Sensors (Basel)"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1109\/TCBB.2019.2952102","article-title":"A hybrid ensemble algorithm combining AdaBoost and genetic algorithm for Cancer classification with gene expression data","volume":"18","author":"Lu","year":"2021","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s11517-019-02079-7","article-title":"Random forest-based classsification and analysis of hemiplegia gait using low-cost depth cameras","volume":"58","author":"Luo","year":"2020","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.13722\/j.cnki.jrme.2019.0924","article-title":"Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses","volume":"39","author":"Mengqi","year":"2020","journal-title":"Chin. J. Rock Mech. Eng."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.pmr.2012.11.007","article-title":"Gait analysis for poststroke rehabilitation: the relevance of biomechanical analysis and the impact of gait speed","volume":"24","author":"Nadeau","year":"2013","journal-title":"Phys. Med. Rehabil. Clin. N. Am."},{"key":"ref37","author":"Park","year":"2003"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1001\/jamaneurol.2024.0190","article-title":"Burden of ischemic and hemorrhagic stroke across the US from 1990 to 2019","volume":"81","author":"Renedo","year":"2024","journal-title":"JAMA Neurol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"e28999","DOI":"10.2196\/28999","article-title":"Exploratory data mining techniques (decision tree models) for examining the impact of internet-based cognitive behavioral therapy for tinnitus: machine learning approach","volume":"23","author":"Rodrigo","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"860","DOI":"10.3969\/j.issn.1006-9771.2013.09.017","article-title":"3D gait analysis for old hemiplegic patients","volume":"19","author":"Sang","year":"2013","journal-title":"Chin. J. Rehabil. Theory Pract."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1186\/s12984-02000787y","article-title":"Characterization of speed adaptation while walking on an omnidirectional treadmill","volume":"18","author":"Soni","year":"2021","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An overview of clinical decision support systems: benefits, risks, and strategies for success","volume":"3","author":"Sutton","year":"2020","journal-title":"NPJ Digit Med."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.gaitpost.2022.06.008","article-title":"Validity and reproducibility of C-mill walking-adaptability assessment in polio survivors","volume":"96","author":"Tuijtelaars","year":"2022","journal-title":"Gait Posture"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.gaitpost.2021.04.031","article-title":"Polio survivors have poorer walking adaptability than healthy individuals","volume":"87","author":"Tuijtelaars","year":"2021","journal-title":"Gait Posture"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1007\/s00221-014-4175-7","article-title":"Improved gait adjustments after gait adaptability training are associated with reduced attentional demands in persons with stroke","volume":"233","author":"Van Ooijen","year":"2015","journal-title":"Exp. Brain Res."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"654","DOI":"10.2522\/ptj.20130108","article-title":"The capacity to restore steady gait after a step modification is reduced in people with poststroke foot drop using an ankle-foot orthosis","volume":"94","author":"Van Swigchem","year":"2014","journal-title":"Phys. Ther."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1016\/j.humov.2008.03.003","article-title":"Exercise training can improve spatial characteristics of time-critical obstacle avoidance in elderly people","volume":"27","author":"Weerdesteyn","year":"2008","journal-title":"Hum. Mov. Sci."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"mzae008","DOI":"10.1093\/intqhc\/mzae008","article-title":"Effects of gait adaptation training on augmented reality treadmill for patients with stroke in community ambulation","volume":"36","author":"Yang","year":"2024","journal-title":"Int. J. Qual. Health Care"},{"key":"ref49","author":"Ye","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/9831252","article-title":"Classification of gait patterns in patients with neurodegenerative disease using adaptive neuro-fuzzy inference system","volume":"2018","author":"Ye","year":"2018","journal-title":"Comput. Math. Methods Med."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"761814","DOI":"10.1155\/2013\/761814","article-title":"An empirical study on the performance of cost-sensitive boosting algorithms with different levels of class imbalance","volume":"2013","author":"Yin","year":"2013","journal-title":"Math. Probl. Eng."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"974985","DOI":"10.3389\/fneur.2022.974985","article-title":"Single-and dual-task gait performance and their diagnostic value in early-stage Parkinson's disease","volume":"13","author":"Zhang","year":"2022","journal-title":"Front. Neurol."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3969\/j.issn.1006-9771.2021.01.008","article-title":"Advance in gait adaptability training for rehabilitation of stroke (review)","volume":"27","author":"Zhong","year":"2021","journal-title":"Chin. J. Rehabil. Theory Pract."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1421401\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T05:10:36Z","timestamp":1722229836000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1421401\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,29]]},"references-count":53,"alternative-id":["10.3389\/fnbot.2024.1421401"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1421401","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,29]]},"article-number":"1421401"}}