{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T22:40:31Z","timestamp":1793054431745,"version":"4.5.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T00:00:00Z","timestamp":1696464000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T00:00:00Z","timestamp":1696464000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP22K20843"],"award-info":[{"award-number":["JP22K20843"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003478","name":"Ministry of Health, Labour and Welfare","doi-asserted-by":"publisher","award":["20FC1049"],"award-info":[{"award-number":["20FC1049"]}],"id":[{"id":"10.13039\/501100003478","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Neurol"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The diagnosis of Parkinson\u2019s disease (PD) and evaluation of its symptoms require in-person clinical examination. Remote evaluation of PD symptoms is desirable, especially during a pandemic such as the coronavirus disease 2019 pandemic. One potential method to remotely evaluate PD motor impairments is video-based analysis. In this study, we aimed to assess the feasibility of predicting the Unified Parkinson\u2019s Disease Rating Scale (UPDRS) score from gait videos using a convolutional neural network (CNN) model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We retrospectively obtained 737 consecutive gait videos of 74 patients with PD and their corresponding neurologist-rated UPDRS scores. We utilized a CNN model for predicting the total UPDRS part III score and four subscores of axial symptoms (items 27, 28, 29, and 30), bradykinesia (items 23, 24, 25, 26, and 31), rigidity (item 22) and tremor (items 20 and 21). We trained the model on 80% of the gait videos and used 10% of the videos as a validation dataset. We evaluated the predictive performance of the trained model by comparing the model-predicted score with the neurologist-rated score for the remaining 10% of videos (test dataset). We calculated the coefficient of determination (<jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup>) between those scores to evaluate the model\u2019s goodness of fit.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the test dataset, the<jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup>values between the model-predicted and neurologist-rated values for the total UPDRS part III score and subscores of axial symptoms, bradykinesia, rigidity, and tremor were 0.59, 0.77, 0.56, 0.46, and 0.0, respectively. The performance was relatively low for videos from patients with severe symptoms.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Despite the low predictive performance of the model for the total UPDRS part III score, it demonstrated relatively high performance in predicting subscores of axial symptoms. The model approximately predicted the total UPDRS part III scores of patients with moderate symptoms, but the performance was low for patients with severe symptoms owing to limited data. A larger dataset is needed to improve the model\u2019s performance in clinical settings.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12883-023-03385-2","type":"journal-article","created":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T06:01:38Z","timestamp":1696485698000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Gait video-based prediction of unified Parkinson\u2019s disease rating scale score: a retrospective study"],"prefix":"10.1186","volume":"23","author":[{"given":"Katsuki","family":"Eguchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ichigaku","family":"Takigawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinichi","family":"Shirai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ikuko","family":"Takahashi-Iwata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaaki","family":"Matsushima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takahiro","family":"Kano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroaki","family":"Yaguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ichiro","family":"Yabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,5]]},"reference":[{"key":"3385_CR1","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1056\/NEJM2003ra020003","volume":"348","author":"RL Nussbaum","year":"2003","unstructured":"Nussbaum RL, Ellis CE. Alzheimer\u2019s disease and Parkinson\u2019s disease. N Engl J Med. 2003;348:1356\u201364.","journal-title":"N Engl J Med"},{"key":"3385_CR2","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1016\/S0140-6736(14)61393-3","volume":"386","author":"LV Kalia","year":"2015","unstructured":"Kalia LV, Lang AE. Parkinson\u2019s disease. Lancet. 2015;386:896\u2013912.","journal-title":"Lancet"},{"key":"3385_CR3","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1001\/jamaneurol.2020.1452","volume":"77","author":"BR Bloem","year":"2020","unstructured":"Bloem BR, Dorsey ER, Okun MS. The coronavirus disease 2019 crisis as catalyst for telemedicine for chronic neurological disorders. JAMA Neurol. 2020;77:927\u201328.","journal-title":"JAMA Neurol"},{"key":"3385_CR4","doi-asserted-by":"publisher","first-page":"e18810","DOI":"10.2196\/18810","volume":"6","author":"R Ohannessian","year":"2020","unstructured":"Ohannessian R, Duong TA, Odone A. Global telemedicine implementation and integration within health systems to fight the COVID-19 pandemic: a call to action. JMIR Public Health Surveill. 2020;6:e18810.","journal-title":"JMIR Public Health Surveill"},{"key":"3385_CR5","doi-asserted-by":"publisher","first-page":"4054","DOI":"10.1038\/s41467-020-17807-z","volume":"11","author":"\u0141 Kidzi\u0144ski","year":"2020","unstructured":"Kidzi\u0144ski \u0141, Yang B, Hicks JL, Rajagopal A, Delp SL, Schwartz MH. Deep neural networks enable quantitative movement analysis using single-camera videos. Nat Commun. 2020;11:4054.","journal-title":"Nat Commun"},{"key":"3385_CR6","doi-asserted-by":"crossref","unstructured":"Zolfaghari M, Singh K, Brox T. ECO: efficient convolutional network for online video understanding. Lecture Notes in Computer Science. Proceedings of the European Conference on Computer Vision (ECCV). 2018:713 \u2013 30.","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"3385_CR7","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1002\/mds.870090112","volume":"9","author":"P Mart\u00ednez-Mart\u00edn","year":"1994","unstructured":"Mart\u00ednez-Mart\u00edn P, Gil-Nagel A, Gracia LM, G\u00f3mez JB, Mart\u00ednez-Sarri\u00e9s J, Bermejo F. Unified Parkinson\u2019s Disease Rating Scale characteristics and structure. The Cooperative Multicentric Group. Mov Disord. 1994;9:76\u201383.","journal-title":"Mov Disord"},{"key":"3385_CR8","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1136\/jnnp.55.3.181","volume":"55","author":"AJ Hughes","year":"1992","unstructured":"Hughes AJ, Daniel SE, Kilford L, Lees AJ. Accuracy of clinical diagnosis of idiopathic Parkinson\u2019s disease: a clinico-pathological study of 100 cases. J Neurol Neurosurg Psychiatry. 1992;55:181\u20134.","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"3385_CR9","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1002\/mds.10459","volume":"18","author":"I Litvan","year":"2003","unstructured":"Litvan I, Bhatia KP, Burn DJ, Goetz CG, Lang AE, McKeith I, et al. Movement Disorders Society scientific issues committee report: SIC Task Force appraisal of clinical diagnostic criteria for parkinsonian disorders. Mov Disord. 2003;18:467\u201386.","journal-title":"Mov Disord"},{"key":"3385_CR10","doi-asserted-by":"publisher","first-page":"2649","DOI":"10.1002\/mds.23429","volume":"25","author":"CL Tomlinson","year":"2010","unstructured":"Tomlinson CL, Stowe R, Patel S, Rick C, Gray R, Clarke CE. Systematic review of levodopa dose equivalency reporting in Parkinson\u2019s disease. Mov Disord. 2010;25:2649\u201353.","journal-title":"Mov Disord"},{"key":"3385_CR11","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1002\/mdc3.12921","volume":"7","author":"S Schade","year":"2020","unstructured":"Schade S, Mollenhauer B, Trenkwalder C. Levodopa equivalent dose conversion factors: an updated proposal including opicapone and safinamide. Mov Disord Clin Pract. 2020;7:343\u20135.","journal-title":"Mov Disord Clin Pract"},{"key":"3385_CR12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.06950","author":"W Kay","year":"2017","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, et al. The kinetics human action video dataset. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1705.06950."},{"key":"3385_CR13","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. Presented at the 32nd International Conference on Machine Learning, Lille, France; vol. 2015; 2015."},{"key":"3385_CR14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1708.05038","author":"D Tran","year":"2017","unstructured":"Tran D, Ray J, Shou Z, Chang SF, Paluri M. ConvNet architecture search for spatiotemporal feature learning. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1708.05038.","journal-title":"arXiv"},{"key":"3385_CR15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703","author":"A Paszke","year":"2019","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: an imperative style, high-performance deep learning library. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1912.01703.","journal-title":"arXiv"},{"key":"3385_CR16","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1002\/mds.24028","volume":"27","author":"E Cubo","year":"2012","unstructured":"Cubo E, Gabriel-Gal\u00e1n JMT, Mart\u00ednez JS, Alcubilla CR, Yang C, Arconada OF, et al. Comparison of office-based versus home web-based clinical assessments for Parkinson\u2019s disease. Mov Disord. 2012;27:308\u201311.","journal-title":"Mov Disord"},{"key":"3385_CR17","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1002\/mds.22340","volume":"23","author":"CG Goetz","year":"2008","unstructured":"Goetz CG, Tilley BC, Shaftman SR, Stebbins GT, Fahn S, Martinez-Martin P, et al. Movement Disorder Society-Sponsored revision of the Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS): scale presentation and clinimetric testing results. Mov Disord. 2008;23:2129\u201370.","journal-title":"Mov Disord"},{"key":"3385_CR18","doi-asserted-by":"crossref","first-page":"4802570","DOI":"10.1155\/2016\/4802570","volume":"2016","author":"T Stillerova","year":"2016","unstructured":"Stillerova T, Liddle J, Gustafsson L, Lamont R, Silburn P. Remotely assessing symptoms of Parkinson\u2019s disease using videoconferencing: a feasibility study. Neurol Res Int. 2016;2016:4802570.","journal-title":"Neurol Res Int"},{"key":"3385_CR19","doi-asserted-by":"publisher","first-page":"2490","DOI":"10.1093\/brain\/awaa181","volume":"143","author":"R Cilia","year":"2020","unstructured":"Cilia R, Cereda E, Akpalu A, Sarfo FS, Cham M, Laryea R, et al. Natural history of motor symptoms in Parkinson\u2019s disease and the long-duration response to levodopa. Brain. 2020;143:2490\u2013501.","journal-title":"Brain"},{"key":"3385_CR20","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/S1353-8020(11)70029-3","volume":"18","author":"CR Baumann","year":"2012","unstructured":"Baumann CR. Epidemiology, diagnosis and differential diagnosis in Parkinson\u2019s disease tremor. Parkinsonism Relat Disord. 2012;18:90\u20132.","journal-title":"Parkinsonism Relat Disord"},{"key":"3385_CR21","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M. Learning spatiotemporal features with 3d convolutional networks. Proceedings of the I.E.E.E. International Conference on Computer Vision. 2015:4489-97.","DOI":"10.1109\/ICCV.2015.510"},{"key":"3385_CR22","doi-asserted-by":"crossref","unstructured":"Carreira J, Andrew Z. Quo vadis, action recognition? a new model and the kinetics dataset. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017:6299 \u2013 308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"3385_CR23","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1186\/s12984-018-0446-z","volume":"15","author":"MH Li","year":"2018","unstructured":"Li MH, Mestre TA, Fox SH, Taati B. Vision-based assessment of parkinsonism and levodopa-induced dyskinesia with pose estimation. J Neuroeng Rehabil. 2018;15:97.","journal-title":"J Neuroeng Rehabil"},{"key":"3385_CR24","doi-asserted-by":"publisher","first-page":"e0223549","DOI":"10.1371\/journal.pone.0223549","volume":"14","author":"K Sato","year":"2019","unstructured":"Sato K, Nagashima Y, Mano T, Iwata A, Toda T. Quantifying normal and parkinsonian gait features from home movies: practical application of a deep learning-based 2D pose estimator. PLoS ONE. 2019;14:e0223549.","journal-title":"PLoS ONE"},{"key":"3385_CR25","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.parkreldis.2020.09.007","volume":"81","author":"JH Shin","year":"2020","unstructured":"Shin JH, Ong JN, Kim R, Park SM, Choi J, Kim HJ, et al. Objective measurement of limb bradykinesia using a marker-less tracking algorithm with 2D-video in PD patients. Parkinsonism Relat Disord. 2020;81:129\u201335.","journal-title":"Parkinsonism Relat Disord"},{"key":"3385_CR26","doi-asserted-by":"publisher","first-page":"e1761","DOI":"10.1212\/WNL.0000000000011654","volume":"96","author":"KW Park","year":"2021","unstructured":"Park KW, Lee EJ, Lee JS, Jeong J, Choi N, Jo S, et al. Machine learning-based automatic rating for cardinal symptoms of Parkinson disease. Neurology. 2021;96:e1761\u20139.","journal-title":"Neurology"},{"key":"3385_CR27","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1002\/mds.27830","volume":"35","author":"AL Silva de Lima","year":"2020","unstructured":"Silva de Lima AL, Smits T, Darweesh SKL, Valenti G, Milosevic M, Pijl M, et al. Home-based monitoring of falls using wearable sensors in Parkinson\u2019s disease. Mov Disord. 2020;35:109\u201315.","journal-title":"Mov Disord"},{"key":"3385_CR28","doi-asserted-by":"publisher","first-page":"555","DOI":"10.3389\/fnins.2017.00555","volume":"11","author":"E Rovini","year":"2017","unstructured":"Rovini E, Maremmani C, Cavallo F. How wearable sensors can support Parkinson\u2019s disease diagnosis and treatment: a systematic review. Front Neurosci. 2017;11:555.","journal-title":"Front Neurosci"},{"key":"3385_CR29","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1002\/mds.26693","volume":"31","author":"KJ Kubota","year":"2016","unstructured":"Kubota KJ, Chen JA, Little MA. Machine learning for large-scale wearable sensor data in Parkinson\u2019s disease: concepts, promises, pitfalls, and futures. Mov Disord. 2016;31:1314\u201326.","journal-title":"Mov Disord"},{"key":"3385_CR30","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1212\/WNL.0b013e3181c34b47","volume":"73","author":"S Hoops","year":"2009","unstructured":"Hoops S, Nazem S, Siderowf AD, Duda JE, Xie SX, Stern MB, et al. Validity of the MoCA and MMSE in the detection of MCI and dementia in Parkinson disease. Neurology. 2009;73:1738\u201345.","journal-title":"Neurology"}],"container-title":["BMC Neurology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12883-023-03385-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12883-023-03385-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12883-023-03385-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T10:40:01Z","timestamp":1703328001000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcneurol.biomedcentral.com\/articles\/10.1186\/s12883-023-03385-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,5]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["3385"],"URL":"https:\/\/doi.org\/10.1186\/s12883-023-03385-2","relation":{"references":[{"id-type":"uri","id":"","asserted-by":"subject"}]},"ISSN":["1471-2377"],"issn-type":[{"value":"1471-2377","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,5]]},"assertion":[{"value":"15 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The study protocol was approved by the institutional review board of the Hokkaido University Hospital (approval number: 020\u20130446), and the requirement for informed consent was waived owing to the retrospective nature of the study. Procedures involving experiments on human participants were performed in accordance with the ethical standards of the Committee on Human Experimentation of the institution in which the experiments were conducted.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"358"}}