{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T11:37:33Z","timestamp":1790422653729,"version":"4.1.0"},"reference-count":48,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003650","name":"National Rehabilitation Center, Ministry of Health and Welfare, Korea","doi-asserted-by":"publisher","award":["NRCTR-EX23002"],"award-info":[{"award-number":["NRCTR-EX23002"]}],"id":[{"id":"10.13039\/501100003650","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Rehabilitation of gait function in post-stroke hemiplegic patients is critical for improving mobility and quality of life, requiring a comprehensive understanding of individual gait patterns. Previous studies on gait analysis using unsupervised clustering often involve manual feature extraction, which introduces limitations such as low accuracy, low consistency, and potential bias due to human intervention. This cross-sectional study aimed to identify and cluster gait patterns using an end-to-end deep learning approach that autonomously extracts features from joint angle trajectories for a gait cycle, minimizing human intervention. A total of 74 sub-acute post-stroke hemiplegic patients with lower limb impairments were included in the analysis. The dataset comprised 219 sagittal plane joint angle and angular velocity trajectories from the hip, knee, and ankle joints during gait cycles. Deep temporal clustering was employed to cluster them in an end-to-end manner by simultaneously optimizing feature extraction and clustering, with hyperparameter tuning tailored for kinematic gait cycle data. Through this method, six optimal clusters were selected with a silhouette score of 0.2831, which is a relatively higher value compared to other clustering algorithms. To clarify the characteristics of the selected groups, in-depth statistics of spatiotemporal, kinematic, and clinical features are presented in the results. The results demonstrate the effectiveness of end-to-end deep learning-based clustering, yielding significant performance improvements without the need for manual feature extraction. While this study primarily utilizes sagittal plane data, future analysis incorporating coronal and transverse planes as well as muscle activity and gait symmetry could provide a more comprehensive understanding of gait patterns.<\/jats:p>","DOI":"10.3390\/bioengineering12010055","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T06:42:15Z","timestamp":1736750535000},"page":"55","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Temporal Clustering of Pathological Gait Patterns in Post-Stroke Patients Using Joint Angle Trajectories: A Cross-Sectional Study"],"prefix":"10.3390","volume":"12","author":[{"given":"Gyeongmin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Intelligent Robotics, Sungkyunkwan University, Suwon 16419, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyungtai","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun-Hee","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Physical and Rehabilitation Medicine, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of Korea"},{"name":"Myongji Choonhey Rehabilitation Hospital, Seoul 07378, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-Jong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, College of Medicine, Korea University, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5025-8785","authenticated-orcid":false,"given":"Mun-Taek","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Intelligent Robotics, Sungkyunkwan University, Suwon 16419, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.1016\/S0140-6736(11)60325-5","article-title":"Stroke rehabilitation","volume":"377","author":"Langhorne","year":"2011","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, F.C., Chen, S.F., Lin, C.H., Shih, C.J., Lin, A.C., Yuan, W., Li, Y.C., and Kuo, T.Y. (2021). Detection and classification of stroke gaits by deep neural networks employing inertial measurement units. Sensors, 21.","DOI":"10.3390\/s21051864"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1177\/15459683231212864","article-title":"Multi-site identification and generalization of clusters of walking behaviors in individuals with chronic stroke and neurotypical controls","volume":"37","author":"Sanchez","year":"2023","journal-title":"Neurorehabilit. Neural Repair"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Horst, F., Lapuschkin, S., Samek, W., M\u00fcller, K.R., and Sch\u00f6llhorn, W.I. (2019). Explaining the unique nature of individual gait patterns with deep learning. Sci. Rep., 9.","DOI":"10.1038\/s41598-019-38748-8"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.jbiomech.2004.05.002","article-title":"A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data","volume":"38","author":"Begg","year":"2005","journal-title":"J. Biomech."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Nutakki, C., Narayanan, J., Anchuthengil, A.A., Nair, B., and Diwakar, S. (2017, January 13\u201316). Classifying gait features for stance and swing using machine learning. Proceedings of the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, Udupi, India.","DOI":"10.1109\/ICACCI.2017.8125896"},{"key":"ref_7","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":"Mulroy","year":"2003","journal-title":"Gait Posture"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.gaitpost.2022.03.007","article-title":"Pathological gait clustering in post-stroke patients using motion capture data","volume":"94","author":"Kim","year":"2022","journal-title":"Gait Posture"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1166\/jmihi.2020.3061","article-title":"Simultaneous clustering and classification of function recovery patterns of ischemic stroke","volume":"10","author":"Kim","year":"2020","journal-title":"J. Med. Imaging Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13721-016-0125-6","article-title":"A review of automatic selection methods for machine learning algorithms and hyper-parameter values","volume":"5","author":"Luo","year":"2016","journal-title":"Netw. Model. Anal. Health Inform. Bioinform."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Hira, Z.M., and Gillies, D.F. (2015). A review of feature selection and feature extraction methods applied on microarray data. Adv. Bioinform., 2015.","DOI":"10.1155\/2015\/198363"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6001","DOI":"10.1109\/ACCESS.2017.2784842","article-title":"Face feature extraction: A complete review","volume":"6","author":"Wang","year":"2017","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Dara, S., and Tumma, P. (2018, January 29\u201331). Feature extraction by using deep learning: A survey. Proceedings of the 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA), IEEE, Coimbatore, India.","DOI":"10.1109\/ICECA.2018.8474912"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rojek, I., Prokopowicz, P., Doro\u017cy\u0144ski, J., and Miko\u0142ajewski, D. (2023). Novel methods of ai-based gait analysis in post-stroke patients. Appl. Sci., 13.","DOI":"10.3390\/app13106258"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Konz, L., Hill, A., and Banaei-Kashani, F. (2022). ST-DeepGait: A spatiotemporal deep learning model for human gait recognition. Sensors, 22.","DOI":"10.3390\/s22208075"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"65579","DOI":"10.1109\/ACCESS.2019.2916648","article-title":"Unsupervised machine learning for networking: Techniques, applications and research challenges","volume":"7","author":"Usama","year":"2019","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.gaitpost.2009.04.004","article-title":"A six degrees-of-freedom marker set for gait analysis: Repeatability and comparison with a modified Helen Hayes set","volume":"30","author":"Collins","year":"2009","journal-title":"Gait Posture"},{"key":"ref_18","unstructured":"Richards, J. (2002). Orthotrak 5.0., Motion Analysis."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Patathong, T., Klaewkasikum, K., Angsnuntsukh, C., Woratanarat, T., Kijkunasathian, C., Sanguantrakul, J., and Woratanarat, P. (2023). The knee kinematic patterns and associated factors in healthy Thai adults. BMC Musculoskelet. Disord., 24.","DOI":"10.1186\/s12891-023-07081-7"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Dunne, J.J., Uchida, T.K., Besier, T.F., Delp, S.L., and Seth, A. (2021). A marker registration method to improve joint angles computed by constrained inverse kinematics. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0254509"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Pignet, A.L., Kranzl, A., Hecker, A., Weigel, G., Kamolz, L.P., and Girsch, W. (2024). Kinematic Effects of Derotational Osteotomy of the Humerus in Patients with Internal Shoulder Contracture Secondary to Erb\u2019s Palsy\u2014A Retrospective Cohort Study. J. Clin. Med., 13.","DOI":"10.3390\/jcm13102759"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2875","DOI":"10.1161\/STROKEAHA.113.001660","article-title":"Vascularization pattern after ischemic stroke is different in control versus diabetic rats: Relevance to stroke recovery","volume":"44","author":"Prakash","year":"2013","journal-title":"Stroke"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"162950","DOI":"10.1109\/ACCESS.2019.2949814","article-title":"A survey on tensor techniques and applications in machine learning","volume":"7","author":"Ji","year":"2019","journal-title":"IEEE Access"},{"key":"ref_24","unstructured":"Madiraju, N.S. (2018). Deep Temporal Clustering: Fully Unsupervised Learning of Time-Domain Features. [Ph.D. Thesis, Arizona State University]."},{"key":"ref_25","first-page":"13","article-title":"Dimensionality reduction: A comparative review","volume":"10","author":"Postma","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1002\/mrm.1910400211","article-title":"A new correlation-based fuzzy logic clustering algorithm for FMRI","volume":"40","author":"Golay","year":"1998","journal-title":"Magn. Reson. Med."},{"key":"ref_27","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","unstructured":"Xie, J., Girshick, R., and Farhadi, A. (2016, January 19\u201324). Unsupervised deep embedding for clustering analysis. Proceedings of the International Conference on Machine Learning, PMLR, New York, NY, USA."},{"key":"ref_29","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"104743","DOI":"10.1016\/j.engappai.2022.104743","article-title":"A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects","volume":"110","author":"Ezugwu","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_31","unstructured":"Nanjundan, S., Sankaran, S., Arjun, C., and Anand, G.P. (2019). Identifying the number of clusters for K-Means: A hypersphere density based approach. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/s10479-008-0371-9","article-title":"Cluster-based outlier detection","volume":"168","author":"Duan","year":"2009","journal-title":"Ann. Oper. Res."},{"key":"ref_33","first-page":"13","article-title":"The post-stroke hemiplegic patient1, a method for evaluation of physical perpormance","volume":"7","author":"Jaasko","year":"1975","journal-title":"Scand. J. Rahabil. Med."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1093\/ptj\/64.1.35","article-title":"Clinical gait assessment in the neurologically impaired: Reliability and meaningfulness","volume":"64","author":"Holden","year":"1984","journal-title":"Phys. Ther."},{"key":"ref_35","first-page":"62","article-title":"Statsmodels: Econometric and statistical modeling with python","volume":"7","author":"Seabold","year":"2010","journal-title":"SciPy"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-de Mariscal, E., Guerrero, V., Sneider, A., Jayatilaka, H., Phillip, J.M., Wirtz, D., and Mu\u00f1oz-Barrutia, A. (2021). Use of the p-values as a size-dependent function to address practical differences when analyzing large datasets. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-00199-5"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1016\/j.ergon.2006.09.013","article-title":"A comparison of gait characteristics between Korean and Western people for establishing Korean gait reference data","volume":"36","author":"Ryu","year":"2006","journal-title":"Int. J. Ind. Ergon."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Paparrizos, J., and Gravano, L. (June, January 31). k-shape: Efficient and accurate clustering of time series. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Australia.","DOI":"10.1145\/2723372.2737793"},{"key":"ref_39","first-page":"1","article-title":"Tslearn, a machine learning toolkit for time series data","volume":"21","author":"Tavenard","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/S0031-3203(02)00060-2","article-title":"The global k-means clustering algorithm","volume":"36","author":"Likas","year":"2003","journal-title":"Pattern Recognit."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1016\/j.patcog.2010.09.013","article-title":"A global averaging method for dynamic time warping, with applications to clustering","volume":"44","author":"Petitjean","year":"2011","journal-title":"Pattern Recognit."},{"key":"ref_42","unstructured":"Cuturi, M., and Blondel, M. (2017, January 6\u201311). Soft-dtw: A differentiable loss function for time-series. Proceedings of the International Conference on Machine Learning. PMLR, Sydney, Australia."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lee, H., Lee, S.H., and Quek, T.Q. (2022, January 16\u201320). Learning multi-objective network optimizations. Proceedings of the 2022 IEEE International Conference on Communications Workshops (ICC Workshops), IEEE, Seoul, Republic of Korea.","DOI":"10.1109\/ICCWorkshops53468.2022.9814461"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: A graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J. Comput. Appl. Math."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Dudek, A. (2020). Silhouette index as clustering evaluation tool. Classification and Data Analysis: Theory and Applications, Springer.","DOI":"10.1007\/978-3-030-52348-0_2"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhou, B., Liu, S., Hooi, B., Cheng, X., and Ye, J. (2019, January 10\u201316). Beatgan: Anomalous rhythm detection using adversarially generated time series. Proceedings of the IJCAI, Macao, China.","DOI":"10.24963\/ijcai.2019\/616"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Kieu, T., Yang, B., Guo, C., and Jensen, C.S. (2019, January 10\u201316). Outlier detection for time series with recurrent autoencoder ensembles. Proceedings of the IJCAI, Macao, China.","DOI":"10.24963\/ijcai.2019\/378"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"110816","DOI":"10.1016\/j.exger.2019.110816","article-title":"Gait analysis with videogrammetry can differentiate healthy elderly, mild cognitive impairment, and Alzheimer\u2019s disease: A cross-sectional study","volume":"131","author":"Ferreira","year":"2020","journal-title":"Exp. Gerontol."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/1\/55\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:26:48Z","timestamp":1759919208000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/1\/55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["bioengineering12010055"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12010055","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,11]]}}}