{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:33:51Z","timestamp":1789670031724,"version":"4.0.1"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ralf Loddenkemper","award":["CH-270.7.002.704-3"],"award-info":[{"award-number":["CH-270.7.002.704-3"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Neuromotor pathologies often cause motor deficits and deviations from typical locomotion, reducing the quality of life. Clinical gait analysis is used to effectively classify these motor deficits to gain deeper insights into resulting walking behaviours. To allow the ensemble averaging of spatio-temporal metrics across individuals during walking, gait events, such as initial contact (IC) or toe-off (TO), are extracted through either manual annotation based on video data, or through force thresholds using force plates. This study developed a deep-learning long short-term memory (LSTM) approach to detect IC and TO automatically based on foot-marker kinematics of 363 cerebral palsy subjects (age: 11.8 \u00b1 3.2). These foot-marker kinematics, including 3D positions and velocities of the markers located on the hallux (HLX), calcaneus (HEE), distal second metatarsal (TOE), and proximal fifth metatarsal (PMT5), were extracted retrospectively from standard barefoot gait analysis sessions. Different input combinations of these four foot-markers were evaluated across three gait subgroups (IC with the heel, midfoot, or forefoot). For the overall group, our approach detected 89.7% of ICs within 16ms of the true event with a 18.5% false alarm rate. For TOs, only 71.6% of events were detected with a 33.8% false alarm rate. While the TOE|HEE marker combination performed well across all subgroups for IC detection, optimal performance for TO detection required different input markers per subgroup with performance differences of 5-10%. Thus, deep-learning LSTM based detection of IC events using the TOE|HEE markers offers an automated alternative to avoid operator-dependent and laborious manual annotation, as well as the limited step coverage and inability to measure assisted walking for force plate-based detection of IC events.<\/jats:p>","DOI":"10.1371\/journal.pone.0275878","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T17:30:17Z","timestamp":1665682217000},"page":"e0275878","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":20,"title":["A deep-learning approach for automatically detecting gait-events based on foot-marker kinematics in children with cerebral palsy\u2014Which markers work best for which gait patterns?"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8975-5762","authenticated-orcid":true,"given":"Yong Kuk","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-9359","authenticated-orcid":true,"given":"Rosa M. S.","family":"Visscher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elke","family":"Viehweger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Navrag B.","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William R.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6322-4990","authenticated-orcid":true,"given":"Florian","family":"Vogl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"pone.0275878.ref001","first-page":"293","volume":"4","author":"JC Wall","year":"1996","journal-title":"Accuracy and reliability of temporal gait measurement"},{"key":"pone.0275878.ref002","volume-title":"Gait analysis: an introduction","author":"MW Whittle","year":"2008","edition":"4"},{"key":"pone.0275878.ref003","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1016\/j.gaitpost.2013.08.023","article-title":"Automated event detection algorithms in pathological gait","volume":"39","author":"DA Bruening","year":"2014","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref004","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.gaitpost.2021.02.031","article-title":"Towards validation and standardization of automatic gait event identification algorithms for use in paediatric pathological populations","volume":"86","author":"RMS Visscher","year":"2021","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref005","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1242\/jeb.203.2.229","article-title":"The independent effects of gravity and inertia on running mechanics","volume":"203","author":"YH Chang","year":"2000","journal-title":"Journal of Experimental Biology"},{"key":"pone.0275878.ref006","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/j.gaitpost.2012.08.011","article-title":"Detection of swing heel-off event in gait initiation using force-plate data","volume":"37","author":"T Caderby","year":"2013","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref007","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/S0021-9290(00)00014-2","article-title":"Algorithms to determine event timing during normal walking using kinematic data","volume":"33","author":"A Hreljac","year":"2000","journal-title":"Journal of Biomechanics"},{"key":"pone.0275878.ref008","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/BF02345744","article-title":"Phase determination during normal running using kinematic data","volume":"38","author":"A Hreljac","year":"2000","journal-title":"Med Biol Eng Comput"},{"key":"pone.0275878.ref009","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/S0021-9290(01)00174-9","article-title":"A simple method for determination of gait events","volume":"35","author":"AH Hansen","year":"2002","journal-title":"Journal of Biomechanics"},{"key":"pone.0275878.ref010","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.gaitpost.2003.10.001","article-title":"Assessment and validation of a simple automated method for the detection of gait events and intervals","volume":"20","author":"S Ghoussayni","year":"2004","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref011","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.gaitpost.2006.05.016","article-title":"Automatic detection of gait events using kinematic data","volume":"25","author":"CM O\u2019Connor","year":"2007","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref012","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1016\/j.gaitpost.2007.07.007","article-title":"Two simple methods for determining gait events during treadmill and overground walking using kinematic data","volume":"27","author":"JA Zeni","year":"2008","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref013","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.gaitpost.2020.06.019","article-title":"Automated gait event detection for a variety of locomotion tasks using a novel gyroscope-based algorithm","volume":"81","author":"C Fadillioglu","year":"2020","journal-title":"Gait Posture"},{"issue":"21","key":"pone.0275878.ref014","doi-asserted-by":"crossref","DOI":"10.3390\/s20216331","article-title":"Agreement of Gait Events Detection during Treadmill Backward Walking by Kinematic Data and Inertial Motion Units","volume":"20","author":"U Gottlieb","year":"2020","journal-title":"Sensors (Basel)"},{"key":"pone.0275878.ref015","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.gaitpost.2020.06.004","article-title":"Gait event detection using a thigh-worn accelerometer","volume":"80","author":"RD Gurchiek","year":"2020","journal-title":"Gait Posture"},{"key":"pone.0275878.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JBHI.2020.2975361","article-title":"Detection of Gait From Continuous Inertial Sensor Data Using Harmonic Frequencies","author":"M Ullrich","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0275878.ref017","doi-asserted-by":"crossref","first-page":"N1","DOI":"10.1088\/1361-6579\/38\/1\/N1","article-title":"Detecting free-living steps and walking bouts: validating an algorithm for macro gait analysis","volume":"38","author":"A Hickey","year":"2017","journal-title":"Physiol Meas"},{"key":"pone.0275878.ref018","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/S0966-6362(02)00165-0","article-title":"Use of cluster analysis for gait pattern classification of patients in the early and late recovery phases following stroke","volume":"18","author":"S Mulroy","year":"2003","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref019","doi-asserted-by":"crossref","first-page":"S130","DOI":"10.1016\/j.gaitpost.2006.11.090","article-title":"Validity of an automated gait event detection algorithm in children with cerebral palsy and non-impaired children","volume":"24","author":"J-J Salazar-Torres","year":"2006","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref020","doi-asserted-by":"crossref","first-page":"S529","DOI":"10.1016\/S0021-9290(07)70519-5","article-title":"Gait timing event determination using kinematic data for the toe walking children with cerebbreal palsy","volume":"40","author":"BJ Hsue","year":"2007","journal-title":"Journal of Biomechanics"},{"key":"pone.0275878.ref021","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.gaitpost.2008.06.009","article-title":"Foot contact event detection using kinematic data in cerebral palsy children and normal adults gait","volume":"29","author":"E Desailly","year":"2009","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref022","doi-asserted-by":"crossref","first-page":"720699","DOI":"10.3389\/fnhum.2021.720699","article-title":"Impact of the Marker Set Configuration on the Accuracy of Gait Event Detection in Healthy and Pathological Subjects","volume":"15","author":"RMS Visscher","year":"2021","journal-title":"Front Hum Neurosci"},{"issue":"8","key":"pone.0275878.ref023","doi-asserted-by":"crossref","first-page":"882","DOI":"10.1109\/TNSRE.2015.2477720","article-title":"Gait Analysis From a Single Ear-Worn Sensor: Reliability and Clinical Evaluation for Orthopaedic Patients","volume":"24","author":"D Jarchi","year":"2016","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"pone.0275878.ref024","doi-asserted-by":"crossref","first-page":"457","DOI":"10.3389\/fneur.2017.00457","article-title":"Validation of a Step Detection Algorithm during Straight Walking and Turning in Patients with Parkinson\u2019s Disease and Older Adults Using an Inertial Measurement Unit at the Lower Back","volume":"8","author":"MH Pham","year":"2017","journal-title":"Front Neurol"},{"key":"pone.0275878.ref025","doi-asserted-by":"crossref","DOI":"10.3390\/s19112517","article-title":"Real-Time Detection of Seven Phases of Gait in Children with Cerebral Palsy Using Two Gyroscopes","volume":"19","author":"A Behboodi","year":"2019","journal-title":"Sensors"},{"key":"pone.0275878.ref026","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.gaitpost.2016.08.012","article-title":"Gait event detection in laboratory and real life settings: Accuracy of ankle and waist sensor based methods","volume":"50","author":"FA Storm","year":"2016","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref027","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s12984-021-00828-0","article-title":"Validation of IMU-based gait event detection during curved walking and turning in older adults and Parkinson\u2019s Disease patients","volume":"18","author":"R Romijnders","year":"2021","journal-title":"J NeuroEngineering Rehabil"},{"key":"pone.0275878.ref028","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1046\/j.1468-1331.2001.00042.x","article-title":"Classification of gait patterns in spastic hemiplegia and spastic diplegia: a basis for a management algorithm","volume":"8","author":"J Rodda","year":"2001","journal-title":"Eur J Neurol"},{"key":"pone.0275878.ref029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/ijerph2004010001","article-title":"Environmental Research and Public Health","volume":"1","author":"P Tchounwou","year":"2004","journal-title":"IJERPH"},{"key":"pone.0275878.ref030","doi-asserted-by":"crossref","first-page":"e0211466","DOI":"10.1371\/journal.pone.0211466","article-title":"Automatic real-time gait event detection in children using deep neural networks","volume":"14","author":"L Kidzinski","year":"2019","journal-title":"PLoS One"},{"key":"pone.0275878.ref031","doi-asserted-by":"crossref","first-page":"109490","DOI":"10.1016\/j.jbiomech.2019.109490","article-title":"A new deep learning-based method for the detection of gait events in children with gait disorders: Proof-of-concept and concurrent validity","volume":"98","author":"M Lempereur","year":"2020","journal-title":"J Biomech"},{"key":"pone.0275878.ref032","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1111\/j.1469-8749.2004.tb00436.x","article-title":"Gross Motor Function Classification System: impact and utility","volume":"46","author":"C Morris","year":"2007","journal-title":"Developmental Medicine & Child Neurology"},{"key":"pone.0275878.ref033","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.gaitpost.2019.04.015","article-title":"The conventional gait model, an open-source implementation that reproduces the past but prepares for the future","volume":"69","author":"F Leboeuf","year":"2019","journal-title":"Gait & Posture"},{"key":"pone.0275878.ref034","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"pone.0275878.ref035","doi-asserted-by":"crossref","DOI":"10.3390\/s17122735","article-title":"IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion","volume":"17","author":"O Dehzangi","year":"2017","journal-title":"Sensors (Basel)"},{"key":"pone.0275878.ref036","doi-asserted-by":"crossref","DOI":"10.3390\/s21030839","article-title":"Machine-Learning Based Determination of Gait Events from Foot-Mounted Inertial Units","volume":"21","author":"M Zago","year":"2021","journal-title":"Sensors (Basel)"},{"key":"pone.0275878.ref037","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.neunet.2018.12.012","article-title":"Classification of gait patterns between patients with Parkinson\u2019s disease and healthy controls using phase space reconstruction (PSR), empirical mode decomposition (EMD) and neural networks","volume":"111","author":"W Zeng","year":"2019","journal-title":"Neural networks: the official journal of the International Neural Network Society"},{"key":"pone.0275878.ref038","article-title":"A Novel Hybrid Deep Neural Network to Predict Pre-impact Fall for Older People Based on Wearable Inertial Sensors","volume":"8","author":"X Yu","year":"2020","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"key":"pone.0275878.ref039","doi-asserted-by":"crossref","first-page":"3859","DOI":"10.3390\/s22103859","article-title":"A Deep Learning Approach for Gait Event Detection from a Single Shank-Worn IMU: Validation in Healthy and Neurological Cohorts","volume":"22","author":"R Romijnders","year":"2022","journal-title":"Sensors"},{"key":"pone.0275878.ref040","doi-asserted-by":"crossref","first-page":"2981","DOI":"10.1038\/s41598-022-07054-1","article-title":"Explaining the differences of gait patterns between high and low-mileage runners with machine learning","volume":"12","author":"D Xu","year":"2022","journal-title":"Sci Rep"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0275878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T17:31:09Z","timestamp":1665682269000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0275878"}},"subtitle":[],"editor":[{"given":"Yaodong","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"references-count":40,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0275878","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,13]]}}}