{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T18:28:20Z","timestamp":1793903300545,"version":"4.8.0"},"reference-count":41,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T00:00:00Z","timestamp":1583280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T00:00:00Z","timestamp":1583280000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objectives<\/jats:italic>\n                    : Remote assessment of gait in patients\u2019 homes has become a valuable tool for monitoring the progression of Parkinson\u2019s disease (PD). However, these measurements are often not as accurate or reliable as clinical evaluations because it is challenging to objectively distinguish the unique gait characteristics of PD. We explore the inference of patients\u2019 stage of PD from their gait using machine learning analyses of data gathered from their smartphone sensors. Specifically, we investigate supervised machine learning (ML) models to classify the severity of the motor part of the UPDRS (MDS-UPDRS 2.10-2.13). Our goals are to facilitate remote monitoring of PD patients and to answer the following questions: (1) What is the patient PD stage based on their gait? (2) Which features are best for understanding and classifying PD gait severities? (3) Which ML classifier types best discriminate PD patients from healthy controls (HC)? and (4) Which ML classifier types can discriminate the severity of PD gait anomalies?\n                    <jats:italic>Methodology<\/jats:italic>\n                    : Our work uses smartphone sensor data gathered from 9520 patients in the mPower study, of whom 3101 participants uploaded gait recordings and 344 subjects and 471 controls uploaded at least 3 walking activities. We selected 152 PD patients who performed at least 3 recordings before and 3 recordings after taking medications and 304 HC who performed at least 3 walking recordings. From the accelerometer and gyroscope sensor data, we extracted statistical, time, wavelet and frequency domain features, and other lifestyle features were derived directly from participants\u2019 survey data. We conducted supervised classification experiments using 10-fold cross-validation and measured the model precision, accuracy, and area under the curve (AUC).\n                    <jats:italic>Results<\/jats:italic>\n                    : The best classification model, best feature, highest classification accuracy, and AUC were (1) random forest and entropy rate, 93% and 0.97, respectively, for walking balance (\n                    <jats:italic>MDS-UPDRS-<\/jats:italic>\n                    2.12); (2)\n                    <jats:italic>bagged trees<\/jats:italic>\n                    and MinMaxDiff, 95% and 0.92, respectively, for shaking\/tremor (\n                    <jats:italic>MDS-UPDRS-<\/jats:italic>\n                    2.10); (3)\n                    <jats:italic>bagged trees<\/jats:italic>\n                    and entropy rate, 98% and 0.98, respectively, for freeze of gait; and (4) random forest and MinMaxDiff, 95% and 0.99, respectively, for distinguishing PD patients from HC.\n                    <jats:italic>Conclusion<\/jats:italic>\n                    : Machine learning classification was challenging due to the use of data that were subjectively labeled based on patients\u2019 answers to the MDS-UPDRS survey questions. However, with use of a significantly larger number of subjects than in prior work and clinically validated gait features, we were able to demonstrate that automatic patient classification based on smartphone sensor data can be used to objectively infer the severity of PD and the extent of specific gait anomalies.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ab39a8","type":"journal-article","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T18:16:02Z","timestamp":1565288162000},"page":"035005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["Machine learning-based motor assessment of Parkinson\u2019s disease using postural sway, gait and lifestyle features on crowdsourced smartphone data"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7643-4775","authenticated-orcid":false,"given":"Hamza","family":"Abujrida","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Agu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaveh","family":"Pahlavan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2020,3,4]]},"reference":[{"key":"bpexab39a8bib1","first-page":"749","type":"journal-article","article-title":"A systematic review of the worldwide prevalence and incidence of Parkinson\u2019s disease","volume":"94","author":"Muangpaisan","year":"2011","journal-title":"Journal of the Medical Association of Thailand"},{"key":"bpexab39a8bib2","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1136\/jnnp.2007.131045","type":"journal-article","article-title":"Parkinson\u2019s disease: clinical features and diagnosis","volume":"79","author":"Jankovic","year":"2008","journal-title":"Journal of Neurology, Neurosurgery & Psychiatry"},{"key":"bpexab39a8bib3","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1155\/2017\/5932675","type":"journal-article","article-title":"Cost of living with Parkinson\u2019s disease over 12 months in Australia: a prospective cohort study","volume":"2017","author":"Mudiyanselage Shalika","year":"2017","journal-title":"Parkinson\u2019s Disease"},{"key":"bpexab39a8bib4","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1002\/mds.25292","type":"journal-article","article-title":"The current and projected economic burden of Parkinson\u2019s disease in the United States","volume":"28","author":"Kowal","year":"2013","journal-title":"Movement Disorders"},{"key":"bpexab39a8bib5","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.jneumeth.2011.09.019","type":"journal-article","article-title":"Feasibility of home-based automated Parkinson\u2019s disease motor assessment","volume":"203","author":"Mera","year":"2012","journal-title":"J. Neurosci. Methods"},{"key":"bpexab39a8bib6","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1002\/mds.26693","type":"journal-article","article-title":"Machine learning for large\u2010scale wearable sensor data in Parkinson\u2019s disease: Concepts, promises, pitfalls, and futures","volume":"31","author":"Kubota","year":"2016","journal-title":"Movement Disorders"},{"key":"bpexab39a8bib7","author":"Mobile Fact Sheet","year":"2018","type":"web-resource"},{"key":"bpexab39a8bib8","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1109\/TBME.2009.2036000","type":"journal-article","article-title":"Accurate telemonitoring of Parkinson\u2019s disease progression by noninvasive speech tests","volume":"57","author":"Tsanas","year":"2010","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexab39a8bib9","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.csl.2013.12.001","type":"journal-article","article-title":"Fully automated assessment of the severity of Parkinson\u2019s disease from speech","volume":"29","author":"Bayestehtashk","year":"2015","journal-title":"Comput. Speech Lang."},{"key":"bpexab39a8bib10","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1109\/TITB.2009.2033471","type":"journal-article","article-title":"Monitoring motor fluctuations in patients with Parkinson\u2019s disease using wearable sensors","volume":"13","author":"Patel","year":"2009","journal-title":"IEEE Trans. Inf. Technol.Biomed."},{"key":"bpexab39a8bib11","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1002\/mds.25684","type":"journal-article","article-title":"Objective biomarkers of balance and gait for Parkinson\u2019s disease using body-worn sensors","volume":"28","author":"Horak","year":"2013","journal-title":"Mov. Disorders"},{"key":"bpexab39a8bib12","doi-asserted-by":"publisher","first-page":"62","DOI":"10.4236\/apd.2013.22012","type":"journal-article","article-title":"Wireless accelerometer configuration for monitoring Parkinson\u2019s disease hand tremor","volume":"2","author":"LeMoyne","year":"2013","journal-title":"Adv. Parkinson\u2019s Dis."},{"key":"bpexab39a8bib13","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1002\/mdc3.12239","type":"journal-article","article-title":"Developing a tool for remote digital assessment of Parkinson\u2019s disease","volume":"3","author":"Kassavetis","year":"2016","journal-title":"Mov. Disorders Clin. Pract."},{"key":"bpexab39a8bib14","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1002\/mds.22340","type":"journal-article","article-title":"Movement Disorder Society\u2010sponsored revision of the Unified Parkinson\u2019s Disease Rating Scale (MDS\u2010UPDRS): scale presentation and clinimetric testing results","volume":"23","author":"Goetz","year":"2008","journal-title":"Movement disorders: Official Journal of the Movement Disorder Society"},{"key":"bpexab39a8bib15","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.11","type":"journal-article","article-title":"The mPower study, Parkinson disease mobile data collected using Research Kit","volume":"3","author":"Bot","year":"2016","journal-title":"Scientific Data"},{"key":"bpexab39a8bib16","first-page":"12 pages","type":"journal-article","article-title":"High frequency remote monitoring of Parkinson\u2019s disease via smartphone: platform overview and medication response detection","volume":"-","author":"Zhan","year":"2016","journal-title":"arXiv"},{"key":"bpexab39a8bib17","doi-asserted-by":"publisher","DOI":"10.1109\/HIC.2017.8227621","type":"conference-proceedings","article-title":"Smartphone-based gait assessment to infer Parkinson\u2019s disease severity using crowdsourced data","author":"Abujrida","year":"2017"},{"key":"bpexab39a8bib18","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1093\/aje\/kwg068","type":"journal-article","article-title":"Incidence of Parkinson\u2019s disease: variation by age, gender, and race\/ethnicity","volume":"157","author":"Eeden","year":"2003","journal-title":"American journal of epidemiology"},{"key":"bpexab39a8bib19","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/0022-510X(93)90150-W","type":"journal-article","article-title":"Effects of smoking in patients with early-onset Parkinson\u2019s disease","volume":"117","author":"Ishikawa","year":"1993","journal-title":"J. Neurol. Sci."},{"key":"bpexab39a8bib20","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/BF02251206","type":"journal-article","article-title":"Physical activity and sports in patients suffering from Parkinson\u2019s disease in comparison with healthy seniors","volume":"5","author":"Fertl","year":"1993","journal-title":"Journal of Neural Transmission-Parkinson\u2019s Disease and Dementia Section"},{"key":"bpexab39a8bib21","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1097\/00005768-199911000-00008","type":"journal-article","article-title":"Therapeutic value of exercise training in Parkinson\u2019s disease","volume":"31","author":"Reuter","year":"1999","journal-title":"Medicine and Science in Sports and Exercise"},{"key":"bpexab39a8bib22","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1093\/brain\/124.3.558","type":"journal-article","article-title":"Event-related functional magnetic resonance imaging in Parkinson\u2019s disease before and after levodopa","volume":"124","author":"Haslinger","year":"2001","journal-title":"Brain"},{"key":"bpexab39a8bib23","doi-asserted-by":"publisher","DOI":"10.4108\/icst.pervasivehealth.2012.248680","type":"conference-proceedings","article-title":"Online detection of freezing of gait with smartphones and machine learning techniques","author":"Mazilu","year":"2012"},{"key":"bpexab39a8bib24","doi-asserted-by":"publisher","first-page":"180","DOI":"10.3923\/jas.2012.180.185","type":"journal-article","article-title":"Parkinson disease gait classification based on machine learning approach","volume":"12","author":"Tahir","year":"2012","journal-title":"Journal of Applied Sciences"},{"key":"bpexab39a8bib25","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.parkreldis.2015.02.026","type":"journal-article","article-title":"Detecting and monitoring the symptoms of Parkinson\u2019s disease using smartphones: a pilot study","volume":"21","author":"Arora","year":"2015","journal-title":"Parkinsonism & Related Disorders"},{"key":"bpexab39a8bib26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0141694","type":"journal-article","article-title":"A validated smartphone-based assessment of gait and gait variability in Parkinson\u2019s disease","volume":"10","author":"Ellis","year":"2015","journal-title":"PLoS One"},{"key":"bpexab39a8bib27","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2014.6944176","type":"conference-proceedings","article-title":"Smartphone application for classification of motor impairment severity in Parkinson\u2019s disease","author":"Printy","year":"2014"},{"key":"bpexab39a8bib28","article-title":"Unconstrained detection of freezing of Gait in Parkinson\u2019s disease patients using smartphone","author":"Kim","year":"2015","type":"conference-proceedings"},{"key":"bpexab39a8bib29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07635-5_11","type":"book","article-title":"SPARK: personalized parkinson disease interventions through synergy between a smartphone and a smartwatch","author":"Sharma","year":"2014"},{"key":"bpexab39a8bib30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0158852","type":"journal-article","article-title":"A validation study of a smartphone-based finger tapping application for quantitative assessment of bradykinesia in Parkinson\u2019s disease","volume":"11","author":"Lee","year":"2016","journal-title":"PLoS One"},{"key":"bpexab39a8bib31","doi-asserted-by":"publisher","first-page":"16965","DOI":"10.3390\/s131216965","type":"journal-article","article-title":"Automatic and objective assessment of alternating tapping performance in Parkinson\u2019s disease","volume":"13","author":"Memedi","year":"2013","journal-title":"Sensors"},{"key":"bpexab39a8bib32","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1001\/archneur.1992.00530290076015","type":"journal-article","article-title":"A population-based investigation of Parkinson\u2019s disease with and without dementia: relationship to age and gender","volume":"49","author":"Mayeux","year":"1992","journal-title":"Arch. Neurol."},{"key":"bpexab39a8bib33","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","type":"journal-article","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"bpexab39a8bib34","first-page":"18","type":"journal-article","article-title":"Classification and regression by random","volume":"2","author":"Liaw","year":"2002","journal-title":"Forest. R News"},{"key":"bpexab39a8bib35","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1890\/07-0539.1","type":"journal-article","article-title":"Random forests for classification in ecology","volume":"88","author":"Cutler","year":"2007","journal-title":"Ecology"},{"key":"bpexab39a8bib36","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1186\/1471-2105-9-307","type":"journal-article","article-title":"Conditional variable importance for random forests","volume":"9","author":"Strobl","year":"2008","journal-title":"BMC Bioinf."},{"key":"bpexab39a8bib37","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","type":"journal-article","article-title":"Variable selection using random forests","volume":"31","author":"Genuer","year":"2010","journal-title":"Pattern Recognit. Lett."},{"key":"bpexab39a8bib38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-7-3","type":"journal-article","article-title":"Gene selection and classification of microarray data usingrandom forest","volume":"7","author":"D\u00edaz-Uriarte","year":"2006","journal-title":"BMC Bioinform"},{"key":"bpexab39a8bib39","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/S0022-510X(03)00104-7","type":"journal-article","article-title":"Gait dynamics in Parkinson\u2019s disease: relationship to Parkinsonian features, falls and response to levodopa","volume":"212","author":"Schaafsma","year":"2003","journal-title":"J. Neurol. Sci."},{"key":"bpexab39a8bib40","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1038\/506150a","type":"journal-article","article-title":"Scientific method: statistical errors","volume":"506","author":"Nuzzo","year":"2014","journal-title":"Nature News"},{"key":"bpexab39a8bib41","first-page":"17","type":"journal-article","article-title":"A machine learning alternative to P-values","author":"Lu","year":"2017","journal-title":"arxiv"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T15:20:49Z","timestamp":1768663249000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ab39a8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,4]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,3,4]]},"published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ab39a8","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,4]]},"assertion":[{"value":"Machine learning-based motor assessment of Parkinson\u2019s disease using postural sway, gait and lifestyle features on crowdsourced smartphone data","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2020 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2019-03-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2019-08-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-03-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}