{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:35:35Z","timestamp":1776782135506,"version":"3.51.2"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Ministerio de Ciencia, Tecnologia e Innovacion","award":["91934"],"award-info":[{"award-number":["91934"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Parkinson\u2019s Disease (PD) is associated with gait movement disorders, such as bradykinesia, stiffness, tremors and postural instability. Hence, a kinematic gait analysis for PD characterization is key to support diagnosis and to carry out an effective treatment planning. Nowadays, automatic classification and characterization strategies are based on deep learning representations, following supervised rules, and assuming large and stratified data. Nonetheless, such requirements are far from real clinical scenarios. Additionally, supervised rules may introduce bias into architectures from expert\u2019s annotations. This work introduces a self-supervised generative representation to learn gait-motion-related patterns, under the pretext task of video reconstruction. Following an anomaly detection framework, the proposed architecture can avoid inter-class variance, learning hidden and complex kinematics locomotion relationships. In this study, the proposed model was trained and validated with an owner dataset (14 Parkinson and 23 control). Also, an external public dataset (16 Parkinson, 30 control, and 50 Knee-arthritis) was used only for testing, measuring the generalization capability of the method. During training, the method learns from control subjects, while Parkinson subjects are detected as anomaly samples. From owner dataset, the proposed approach achieves a ROC-AUC of 95% in classification task. Regarding the external dataset, the architecture evidence generalization capabilities, achieving a 75% of ROC-AUC (shapeness and homoscedasticity of 66.7%), without any additional training. The proposed model has remarkable performance in detecting gait parkinsonian patterns, recorded in markerless videos, even competitive results with classes non-observed during training.<\/jats:p>","DOI":"10.1007\/s11042-024-19961-8","type":"journal-article","created":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T07:02:15Z","timestamp":1725260535000},"page":"21605-21623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Parkinsonian gait modelling from an anomaly deep representation"],"prefix":"10.1007","volume":"84","author":[{"given":"Edgar","family":"Rangel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Mart\u00ednez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"issue":"4","key":"19961_CR1","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1002\/mdc3.12755","volume":"6","author":"N Afentou","year":"2019","unstructured":"Afentou N, Jarl J, Gerdtham UG et al (2019) Economic evaluation of interventions in parkinson\u2019s disease: a systematic literature review. Movement Disorders Clinical Pract 6(4):282\u2013290","journal-title":"Movement Disorders Clinical Pract"},{"issue":"2","key":"19961_CR2","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1109\/JSEN.2020.3018262","volume":"21","author":"AS Alharthi","year":"2020","unstructured":"Alharthi AS, Casson AJ, Ozanyan KB (2020) Gait spatiotemporal signal analysis for parkinson\u2019s disease detection and severity rating. IEEE Sensors J 21(2):1838\u20131848","journal-title":"IEEE Sensors J"},{"key":"19961_CR3","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.medengphy.2021.03.005","volume":"91","author":"E Balaji","year":"2021","unstructured":"Balaji E, Brindha D, Elumalai VK et al (2021) Data-driven gait analysis for diagnosis and severity rating of parkinson\u2019s disease. Med Eng Phys 91:54\u201364","journal-title":"Med Eng Phys"},{"issue":"1","key":"19961_CR4","first-page":"27","volume":"27","author":"R Balestrino","year":"2020","unstructured":"Balestrino R, Schapira A (2020) Parkinson disease. Euro J Neuro 27(1):27\u201342","journal-title":"Parkinson disease. Euro J Neuro"},{"key":"19961_CR5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/bs.irn.2017.01.001","volume":"132","author":"R Bhidayasiri","year":"2017","unstructured":"Bhidayasiri R, Martinez-Martin P (2017) Clinical assessments in parkinson\u2019s disease: scales and monitoring. Int Rev Neurobiol 132:129\u2013182","journal-title":"Int Rev Neurobiol"},{"issue":"12","key":"19961_CR6","doi-asserted-by":"publisher","first-page":"3529","DOI":"10.3390\/s20123529","volume":"20","author":"L di Biase","year":"2020","unstructured":"di Biase L, Di Santo A, Caminiti ML et al (2020) Gait analysis in parkinson\u2019s disease: An overview of the most accurate markers for diagnosis and symptoms monitoring. Sensors 20(12):3529","journal-title":"Sensors"},{"key":"19961_CR7","doi-asserted-by":"crossref","unstructured":"Chalapathy R, Chawla S (2019) Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407","DOI":"10.1145\/3394486.3406704"},{"issue":"12","key":"19961_CR8","doi-asserted-by":"publisher","first-page":"4463","DOI":"10.3390\/s22124463","volume":"22","author":"JM Chavez","year":"2022","unstructured":"Chavez JM, Tang W (2022) A vision-based system for stage classification of parkinsonian gait using machine learning and synthetic data. Sensors 22(12):4463","journal-title":"Sensors"},{"issue":"1","key":"19961_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1475-925X-10-99","volume":"10","author":"SW Chen","year":"2011","unstructured":"Chen SW, Lin SH, Liao LD et al (2011) Quantification and recognition of parkinsonian gait from monocular video imaging using kernel-based principal component analysis. Biomed Eng Online 10(1):1\u201321","journal-title":"Biomed Eng Online"},{"issue":"3","key":"19961_CR10","doi-asserted-by":"publisher","first-page":"7033","DOI":"10.1016\/j.eswa.2008.08.076","volume":"36","author":"CW Cho","year":"2009","unstructured":"Cho CW, Chao WH, Lin SH et al (2009) A vision-based analysis system for gait recognition in patients with parkinson\u2019s disease. Expert Syst Appl 36(3):7033\u20137039","journal-title":"Expert Syst Appl"},{"key":"19961_CR11","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"key":"19961_CR12","doi-asserted-by":"crossref","unstructured":"Dorsey ER, Bloem BR (2018) The parkinson pandemic\u2014a call to action. JAMA Neuro 75(1):9\u201310","DOI":"10.1001\/jamaneurol.2017.3299"},{"issue":"2","key":"19961_CR13","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/s42979-022-01018-y","volume":"3","author":"\u00c7B Erda\u015f","year":"2022","unstructured":"Erda\u015f \u00c7B, S\u00fcmer E (2022) A deep learning method to detect parkinson\u2019s disease from mri slices. SN Comput Sci 3(2):120","journal-title":"SN Comput Sci"},{"issue":"26","key":"19961_CR14","doi-asserted-by":"publisher","first-page":"37681","DOI":"10.1007\/s11042-022-13506-7","volume":"81","author":"S Fouladi","year":"2022","unstructured":"Fouladi S, Safaei AA, Arshad NI et al (2022) The use of artificial neural networks to diagnose alzheimer\u2019s disease from brain images. Multimed Tools App 81(26):37681\u201337721","journal-title":"Multimed Tools App"},{"key":"19961_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103935","volume":"123","author":"LC Guayac\u00e1n","year":"2021","unstructured":"Guayac\u00e1n LC, Mart\u00ednez F (2021) Visualising and quantifying relevant parkinsonian gait patterns using 3d convolutional network. J Biomed Informat 123:103935","journal-title":"J Biomed Informat"},{"key":"19961_CR16","doi-asserted-by":"crossref","unstructured":"Guo Y, Yang J, Liu Y et\u00a0al (2022) Detection and assessment of parkinson\u2019s disease based on gait analysis: A survey. Frontiers in Aging Neuroscience p 837","DOI":"10.3389\/fnagi.2022.916971"},{"key":"19961_CR17","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1109\/TIP.2019.2946469","volume":"29","author":"K Hu","year":"2019","unstructured":"Hu K, Wang Z, Wang W et al (2019) Graph sequence recurrent neural network for vision-based freezing of gait detection. IEEE Trans Image Process 29:1890\u20131901","journal-title":"IEEE Trans Image Process"},{"key":"19961_CR18","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.jbi.2016.01.014","volume":"60","author":"YN Jane","year":"2016","unstructured":"Jane YN, Nehemiah HK, Arputharaj K (2016) A q-backpropagated time delay neural network for diagnosing severity of gait disturbances in parkinson\u2019s disease. J Biomed Informat 60:169\u2013176","journal-title":"J Biomed Informat"},{"issue":"16","key":"19961_CR19","doi-asserted-by":"publisher","first-page":"4013","DOI":"10.1049\/iet-ipr.2020.1048","volume":"14","author":"H Khachnaoui","year":"2020","unstructured":"Khachnaoui H, Mabrouk R, Khlifa N (2020) Machine learning and deep learning for clinical data and pet\/spect imaging in parkinson\u2019s disease: a review. IET Image Process 14(16):4013\u20134026","journal-title":"IET Image Process"},{"issue":"2","key":"19961_CR20","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3390\/jimaging4020036","volume":"4","author":"BR Kiran","year":"2018","unstructured":"Kiran BR, Thomas DM, Parakkal R (2018) An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos. J Imaging 4(2):36","journal-title":"J Imaging"},{"key":"19961_CR21","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patrec.2020.09.011","volume":"140","author":"N Kleanthous","year":"2020","unstructured":"Kleanthous N, Hussain AJ, Khan W et al (2020) A new machine learning based approach to predict freezing of gait. Pattern Recogn Lett 140:119\u2013126","journal-title":"Pattern Recogn Lett"},{"key":"19961_CR22","doi-asserted-by":"publisher","first-page":"156620","DOI":"10.1109\/ACCESS.2019.2949744","volume":"7","author":"N Kour","year":"2019","unstructured":"Kour N, Arora S et al (2019) Computer-vision based diagnosis of parkinson\u2019s disease via gait: a survey. IEEE Access 7:156620\u2013156645","journal-title":"IEEE Access"},{"key":"19961_CR23","doi-asserted-by":"crossref","unstructured":"Kour N, Arora S et\u00a0al (2022a) A vision-based gait dataset for knee osteoarthritis and parkinson\u2019s disease analysis with severity levels. In: International conference on innovative computing and communications, Springer, pp 303\u2013317","DOI":"10.1007\/978-981-16-3071-2_26"},{"issue":"6","key":"19961_CR24","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12955","volume":"39","author":"N Kour","year":"2022","unstructured":"Kour N, Gupta S, Arora S (2022) A vision-based clinical analysis for classification of knee osteoarthritis, parkinson\u2019s disease and normal gait with severity based on k-nearest neighbour. Expert Syst 39(6):e12955","journal-title":"Expert Syst"},{"key":"19961_CR25","doi-asserted-by":"crossref","unstructured":"Li H, Zhang X, Yang Y et\u00a0al (2023) Abnormal eye movements in parkinson\u2019s disease: From experimental study to clinical application. Parkinsonism & Related Disorders p 105791","DOI":"10.1016\/j.parkreldis.2023.105791"},{"key":"19961_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388","journal-title":"Med Image Anal"},{"issue":"4","key":"19961_CR27","doi-asserted-by":"publisher","first-page":"7798","DOI":"10.1016\/j.eswa.2008.11.041","volume":"36","author":"J Luengo","year":"2009","unstructured":"Luengo J, Garc\u00eda S, Herrera F (2009) A study on the use of statistical tests for experimentation with neural networks: Analysis of parametric test conditions and non-parametric tests. Expert Syst App 36(4):7798\u20137808","journal-title":"Expert Syst App"},{"key":"19961_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s43055-021-00454-9","volume":"52","author":"T Mortezazadeh","year":"2021","unstructured":"Mortezazadeh T, Seyedarabi H, Mahmoudian B et al (2021) Imaging modalities in differential diagnosis of parkinson\u2019s disease: opportunities and challenges. Egypt J Radiol Nuclear Med 52:1\u201312","journal-title":"Egypt J Radiol Nuclear Med"},{"key":"19961_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.inat.2020.100694","volume":"20","author":"SK Mudgal","year":"2020","unstructured":"Mudgal SK, Sharma SK, Chaturvedi J et al (2020) Brain computer interface advancement in neurosciences: Applications and issues. Interdiscip Neurosurg 20:100694","journal-title":"Interdiscip Neurosurg"},{"issue":"19","key":"19961_CR30","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1016\/j.ifacol.2016.10.546","volume":"49","author":"S N\u00f5mm","year":"2016","unstructured":"N\u00f5mm S, Toomela A, Vaske M et al (2016) An alternative approach to distinguish movements of parkinson disease patients. IFAC-PapersOnLine 49(19):272\u2013276","journal-title":"IFAC-PapersOnLine"},{"key":"19961_CR31","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2021.776847","volume":"9","author":"Z Ou","year":"2021","unstructured":"Ou Z, Pan J, Tang S et al (2021) Global trends in the incidence, prevalence, and years lived with disability of parkinson\u2019s disease in 204 countries\/territories from 1990 to 2019. Frontiers Public Health 9:776847","journal-title":"Frontiers Public Health"},{"issue":"1","key":"19961_CR32","first-page":"1","volume":"3","author":"W Poewe","year":"2017","unstructured":"Poewe W, Seppi K, Tanner CM et al (2017) Parkinson disease. Nature Rev Dis Prim 3(1):1\u201321","journal-title":"Parkinson disease. Nature Rev Dis Prim"},{"key":"19961_CR33","doi-asserted-by":"crossref","unstructured":"Rao H, Zeng M, Zhao X et\u00a0al (2024) A survey of artificial intelligence in gait-based neurodegenerative disease diagnosis. arXiv preprint arXiv:2405.13082","DOI":"10.1016\/j.neucom.2025.129533"},{"key":"19961_CR34","doi-asserted-by":"publisher","first-page":"82146","DOI":"10.1109\/ACCESS.2021.3084358","volume":"9","author":"L Schmarje","year":"2021","unstructured":"Schmarje L, Santarossa M, Schr\u00f6der SM et al (2021) A survey on semi-, self-and unsupervised learning for image classification. IEEE Access 9:82146\u201382168","journal-title":"IEEE Access"},{"key":"19961_CR35","doi-asserted-by":"crossref","unstructured":"Soltaninejad S, Rosales-Castellanos A, Ba F et\u00a0al (2018) Body movement monitoring for parkinson\u2019s disease patients using a smart sensor based non-invasive technique. In: 2018 IEEE 20th International conference on e-Health networking, applications and services (Healthcom), IEEE, pp 1\u20136","DOI":"10.1109\/HealthCom.2018.8531197"},{"key":"19961_CR36","doi-asserted-by":"crossref","unstructured":"Sun R, Wang Z, Martens KE et\u00a0al (2018) Convolutional 3d attention network for video based freezing of gait recognition. In: 2018 Digital Image Computing: techniques and applications (DICTA), IEEE, pp 1\u20137","DOI":"10.1109\/DICTA.2018.8615791"},{"issue":"10100","key":"19961_CR37","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1016\/S0140-6736(17)32154-2","volume":"390","author":"T Vos","year":"2017","unstructured":"Vos T, Abajobir AA, Abate KH et al (2017) Global, regional, and national incidence, prevalence, and years lived with disability for 328 diseases and injuries for 195 countries, 1990\u20132016: a systematic analysis for the global burden of disease study 2016. The Lancet 390(10100):1211\u20131259","journal-title":"The Lancet"},{"key":"19961_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2018.03.032","volume":"315","author":"A Zhao","year":"2018","unstructured":"Zhao A, Qi L, Li J et al (2018) A hybrid spatio-temporal model for detection and severity rating of parkinson\u2019s disease from gait data. Neurocomputing 315:1\u20138","journal-title":"Neurocomputing"},{"key":"19961_CR39","doi-asserted-by":"crossref","unstructured":"Zhong C, Ng WW (2022) A robust frequency-domain-based graph adaptive network for parkinson\u2019s disease detection from gait data. IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2022.3217392"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19961-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19961-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19961-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T13:07:07Z","timestamp":1751375227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19961-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":39,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["19961"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19961-8","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,2]]},"assertion":[{"value":"4 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}