{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T04:30:31Z","timestamp":1784694631806,"version":"3.55.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T00:00:00Z","timestamp":1664409600000},"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. Artif. Intell."],"abstract":"<jats:p>Machine learning can discern meaningful information from large datasets. Applying machine learning techniques to raw sensor data from instrumented walkways could automatically detect subtle changes in walking and balance. Multiple sclerosis (MS) is a neurological disorder in which patients report varying degrees of walking and balance disruption. This study aimed to determine whether machine learning applied to walkway sensor data could classify severity of self-reported symptoms in MS patients. Ambulatory people with MS (<jats:italic>n<\/jats:italic> = 107) were asked to rate the severity of their walking and balance difficulties, from 1-No problems to 5-Extreme problems, using the MS-Impact Scale-29. Those who scored less than 3 (moderately) were assigned to the \u201cmild\u201d group (<jats:italic>n<\/jats:italic> = 35), and those scoring higher were in the \u201cmoderate\u201d group (<jats:italic>n<\/jats:italic> = 72). Three machine learning algorithms were applied to classify the \u201cmild\u201d group from the \u201cmoderate\u201d group. The classification achieved 78% accuracy, a precision of 85%, a recall of 90%, and an F1 score of 87% for distinguishing those people reporting mild from moderate walking and balance difficulty. This study demonstrates that machine learning models can reliably be applied to instrumented walkway data and distinguish severity of self-reported impairment in people with MS.<\/jats:p>","DOI":"10.3389\/frai.2022.952312","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T04:38:38Z","timestamp":1664426318000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Machine learning corroborates subjective ratings of walking and balance difficulty in multiple sclerosis"],"prefix":"10.3389","volume":"5","author":[{"given":"Wenting","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Owen","family":"Combden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianta","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syamala","family":"Buragadda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caitlin J.","family":"Newell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria C.","family":"Williams","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amber L.","family":"Critch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle","family":"Ploughman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,9,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1743-0003-2-21","article-title":"Too much or too little step width variability is associated with a fall history in older persons who walk at or near normal gait speed","volume":"2","author":"Brach","year":"2005","journal-title":"J. Neuroeng. Rehabilit"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"Bradley","year":"1997","journal-title":"Pattern Recogn"},{"key":"B3","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.gaitpost.2017.11.024","article-title":"A systematic review of the gait characteristics associated with Cerebellar Ataxia","volume":"60","author":"Buckley","year":"2018","journal-title":"Gait Posture"},{"key":"B4","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.bbr.2018.11.005","article-title":"Asymmetry of brain excitability: a new biomarker that predicts objective and subjective symptoms in multiple sclerosis","volume":"359","author":"Chaves","year":"2019","journal-title":"Behav. Brain Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.gaitpost.2020.03.004","article-title":"Reliability of gait and dual-task measures in multiple sclerosis","volume":"78","author":"Chen","year":"2020","journal-title":"Gait Posture"},{"key":"B6","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A Scalable Tree Boosting System,","author":"Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery Data Mining KDD'16 (ACM)."},{"key":"B7","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"B8","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences","volume":"20","author":"Cox","year":"1958","journal-title":"J. R. Stat. Soc. Series B."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","author":"Delong","year":"1988"},{"key":"B10","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1002\/glia.23576","article-title":"miR-223 promotes regenerative myeloid cell phenotype and function in the demyelinated central nervous system","volume":"67","author":"Galloway","year":"2019","journal-title":"Glia"},{"key":"B11","doi-asserted-by":"publisher","first-page":"114104","DOI":"10.1016\/j.eswa.2020.114104","article-title":"Shapley-Lorenz eXplainable Artificial Intelligence","volume":"167","author":"Giudici","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"B12","first-page":"1322","article-title":"ADASYN: Adaptive synthetic sampling approach for imbalanced learning,","author":"He","year":"2008","journal-title":"Proceedings of the International Joint Conference on Neural Networks"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.50.2.318","article-title":"Parkinsonism : onset, progression, and mortality","author":"Hoehn","year":"1967","journal-title":"Neurology"},{"key":"B14","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s12938-022-00992-x","article-title":"Machine learning classification of multiple sclerosis patients based on raw data from an instrumented walkway","volume":"21","author":"Hu","year":"2022","journal-title":"Biomed. Eng."},{"key":"B15","doi-asserted-by":"publisher","first-page":"650542","DOI":"10.3389\/fneur.2021.650542","article-title":"Artificial neural network analyzing wearable device gait data for identifying patients with stroke unable to return to work","volume":"12","author":"Iosa","year":"2021","journal-title":"Front. Neurol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"106525","DOI":"10.1016\/j.cmpb.2021.106525","article-title":"Detection of ataxia with hybrid convolutional neural network using static plantar pressure distribution model in patients with multiple sclerosis","volume":"214","author":"Kaya","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"B17","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1080\/03091902.2020.1822940","article-title":"Role of machine learning in gait analysis: a review","volume":"44","author":"Khera","year":"2020","journal-title":"J. Med. Eng. Technol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"101005","DOI":"10.1016\/j.jestch.2021.05.009","article-title":"Age-gender specific prediction model for Parkinson's severity assessment using gait biomarkers","volume":"27","author":"Khera","year":"2022","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"B19","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.clinbiomech.2018.04.009","article-title":"Bipedal hopping timed to a metronome to detect impairments in anticipatory motor control in people with mild multiple sclerosis","volume":"55","author":"Kirkland","year":"2018","journal-title":"Clin. Biomech."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1080\/09638288.2020.1820585","article-title":"Bipedal hopping as a new measure to detect subtle sensorimotor impairment in people with multiple sclerosis","volume":"44","author":"Kirkland","year":"2020","journal-title":"Disabil. Rehabil."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2015\/650645","article-title":"Comparing three dual-task methods and the relationship to physical and cognitive impairment in people with multiple sclerosis and controls","volume":"2015","author":"Kirkland","year":"2015","journal-title":"Mult. Scler. Int."},{"key":"B22","doi-asserted-by":"publisher","first-page":"5010","DOI":"10.1109\/EMBC.2012.6347118","article-title":"A novel sensorized shoe system to classify gait severity in children with cerebral palsy,","author":"Mancinelli","year":"2012","journal-title":"Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e0178366","DOI":"10.1371\/journal.pone.0178366","article-title":"A machine learning approach for gait speed estimation using skin-mounted wearable sensors: From healthy controls to individuals with multiple sclerosis","volume":"12","author":"McGinnis","year":"2017","journal-title":"PLoS ONE."},{"key":"B24","doi-asserted-by":"publisher","first-page":"536","DOI":"10.22266\/ijies2021.0430.48","article-title":"ANOVA-SVM for selecting subset features in encrypted internet traffic classification","volume":"14","author":"Megantara","year":"2021","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"B25","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/s10618-012-0295-5","article-title":"Training and assessing classification rules with imbalanced data","volume":"28","author":"Menardi","year":"2014","journal-title":"Data Min. Knowl. Discov"},{"key":"B26","unstructured":"Atlas of MS 3 rd edition. third edit, p. 1\u2212362020"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1177\/1352458514530489","article-title":"Responder definition of the Multiple Sclerosis Impact Scale physical impact subscale for patients with physical worsening","volume":"20","author":"Phillips","year":"2014","journal-title":"Multiple Scler. J."},{"key":"B29","doi-asserted-by":"publisher","first-page":"163","DOI":"10.7224\/1537-2073.2014-052","article-title":"Drawing on related knowledge to advance multiple sclerosis falls-prevention research","volume":"16","author":"Ploughman","year":"2014","journal-title":"Int. J. MS Care."},{"key":"B30","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1056\/NEJMra1401483","article-title":"Multiple sclerosis","volume":"378","author":"Reich","year":"2018","journal-title":"New Engl. J. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"167830","DOI":"10.1109\/ACCESS.2020.3022818","article-title":"Latest research trends in gait analysis using wearable sensors and machine learning: A systematic review","volume":"8","author":"Saboor","year":"2020","journal-title":"IEEE Access"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.3390\/diagnostics11061096","article-title":"Forecasting the walking assistance rehabilitation level of stroke patients using artificial intelligence","volume":"11","author":"Seo","year":"2021","journal-title":"Diagnostics"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.clinbiomech.2017.04.001","article-title":"Evaluation of Clinical Gait Analysis parameters in patients affected by Multiple Sclerosis: Analysis of kinematics","volume":"45","author":"Severini","year":"2017","journal-title":"Clin. Biomech."},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1757-1626-2-187","article-title":"A case of charcot's feet in a patient with parkinson's disease: A case report","volume":"2","author":"Singh","year":"2009","journal-title":"Cases J."},{"key":"B35","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.gaitpost.2012.10.012","article-title":"Gait variability and disability in multiple sclerosis","volume":"38","author":"Socie","year":"2013","journal-title":"Gait Posture"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1109\/LSP.2014.2337313","article-title":"Fast implementation of DeLong's algorithm for comparing the areas under correlated receiver operating characteristic curves","volume":"21","author":"Sun","year":"2014","journal-title":"IEEE Signal Process. Lett."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.3390\/brainsci11081049","article-title":"Using machine learning algorithms for identifying gait parameters suitable to evaluate subtle changes in gait in people with multiple sclerosis","volume":"11","author":"Trentzsch","year":"2021","journal-title":"Brain Sci."},{"key":"B38","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1080\/09638288.2018.1504327","article-title":"Walking activity and its determinants in free-living ambulatory people in a chronic phase after stroke: a cross-sectional study","volume":"42","author":"van de Port","year":"2020","journal-title":"Disabil. Rehabil."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1177\/1352458518783662","article-title":"Five years before multiple sclerosis onset: Phenotyping the prodrome","volume":"25","author":"Wijnands","year":"2019","journal-title":"Multiple Scler. J."},{"key":"B40","doi-asserted-by":"publisher","first-page":"103645","DOI":"10.1016\/j.msard.2022.103645","article-title":"Variability of objective gait measures across the expanded disability status scale in people living with multiple sclerosis: A cross-sectional retrospective analysis","volume":"59","author":"Zanotto","year":"2022","journal-title":"Mult. Scler. Relat. Disord."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2018.03.032","article-title":"A hybrid spatio-temporal model for detection and severity rating of Parkinson's disease from gait data","volume":"315","author":"Zhao","year":"2018","journal-title":"Neurocomputing"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.952312\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T04:38:47Z","timestamp":1664426327000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.952312\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,29]]},"references-count":41,"alternative-id":["10.3389\/frai.2022.952312"],"URL":"https:\/\/doi.org\/10.3389\/frai.2022.952312","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,29]]},"article-number":"952312"}}