{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T20:35:23Z","timestamp":1785011723857,"version":"3.55.0"},"reference-count":40,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Legal &amp; General Group"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As gaitpathology assessment systems improve both in accuracy and efficiency, the prospect of using these systems in real healthcare applications is becoming more realistic. Although gait analysis systems have proven capable of detecting gait abnormalities in supervised tasks in laboratories and clinics, there is comparatively little investigation into making such systems explainable to healthcare professionals who would use gait analysis in practice in home-based settings. There is a \u201cblack box\u201d problem with existing machine learning models, where healthcare professionals are expected to \u201ctrust\u201d the model making diagnoses without understanding its underlying reasoning. To address this applicational barrier, an end-to-end pipeline is introduced here for creating graph feature embeddings, generated using a bespoke Spatio-temporal Graph Convolutional Network and per-joint Principal Component Analysis. The latent graph embeddings produced by this framework led to a novel semi-supervised weighting function which quantifies and ranks the most important joint features, which are used to provide a description for each pathology. Using these embeddings with a K-means clustering approach, the proposed method also outperforms the state of the art by between 4.53 and 16% in classification accuracy across three datasets with a total of 14 different simulated gait pathologies from minor limping to ataxic gait. The resulting system provides a workable improvement to at-home gait assessment applications by providing accurate and explainable descriptions of the nature of detected gait abnormalities without need of prior labeled descriptions of detected pathologies.<\/jats:p>","DOI":"10.3390\/s25134106","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T04:04:22Z","timestamp":1751342662000},"page":"4106","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Explainable Graph Embeddings for Gait Assessment Using Per-Cluster Dimensional Weighting"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9046-6784","authenticated-orcid":false,"given":"Chris","family":"Lochhead","sequence":"first","affiliation":[{"name":"University of Edinburgh, Old College, South Bridge, Edinburgh EH8 9YL, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6860-9371","authenticated-orcid":false,"given":"Robert B.","family":"Fisher","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Old College, South Bridge, Edinburgh EH8 9YL, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"102754","DOI":"10.1016\/j.media.2023.102754","article-title":"Vision-based estimation of mds-updrs scores for quantifying parkinson\u2019s disease tremor severity","volume":"85","author":"Liu","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_2","first-page":"264","article-title":"Deep gait recognition: A survey","volume":"45","author":"Etemad","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/TNSRE.2024.3352004","article-title":"Cross-spatiotemporal graph convolution networks for skeleton-based parkinsonian gait mds-updrs score estimation","volume":"32","author":"Tian","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lim, J., Kim, M., Hur, S., and Chung, T. (2023). Wm\u2013stgcn: A novel spatiotemporal modeling method for parkinsonian gait recognition. Sensors, 23.","DOI":"10.3390\/s23104980"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, X., Ellul, J., and Azzopardi, G. (2020). Elderly fall detection systems: A literature survey. Front. Robot. AI, 7.","DOI":"10.3389\/frobt.2020.00071"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yhdego, H., Li, J., Paolini, C., and Audette, M. (2021, January 9\u201312). Wearable sensor gait analysis of fall detection using attention network. Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA.","DOI":"10.1109\/BIBM52615.2021.9669795"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1018","DOI":"10.1109\/TASE.2018.2861382","article-title":"Real-time detection of fall from bed using a single depth camera","volume":"16","author":"Zhao","year":"2018","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Fernandes, C., Fonseca, L., Ferreira, F., Gago, M., Costa, L., Sousa, N., Ferreira, C., Gama, J., Erlhagen, W., and Bicho, E. (2018, January 3\u20136). Artificial neural networks classification of patients with parkinsonism based on gait. Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain.","DOI":"10.1109\/BIBM.2018.8621466"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102871","DOI":"10.1016\/j.media.2023.102871","article-title":"Automatic labeling of parkinson\u2019s disease gait videos with weak supervision","volume":"89","author":"Gholami","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6461","DOI":"10.1109\/TCSVT.2022.3163959","article-title":"A self-supervised metric learning framework for the arising-from-chair assessment of parkinsonians with graph convolutional networks","volume":"32","author":"Guo","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pais, B., Buluschek, P., DuPasquier, G., Nef, T., Sch\u00fctz, N., Saner, H., Gatica-Perez, D., and Santschi, V. (2020). Evaluation of 1-year in-home monitoring technology by home-dwelling older adults, family caregivers, and nurses. Front. Public Health, 8.","DOI":"10.3389\/fpubh.2020.518957"},{"key":"ref_12","unstructured":"Xue, D., Sayana, A., Darke, E., Shen, K., Hsieh, J., Luo, Z., Li, L., Downing, N.L., Milstein, A., and Li, F.F. (2018). Vision-based gait analysis for senior care. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1109\/JBHI.2021.3101549","article-title":"Anomalous gait feature classification from 3-d motion capture data","volume":"26","author":"Jeon","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1550147717703257","DOI":"10.1177\/1550147717703257","article-title":"Fall prediction based on biomechanics equilibrium using kinect","volume":"13","author":"Tao","year":"2017","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"38106","DOI":"10.1109\/ACCESS.2018.2854262","article-title":"3D reconstruction with time-of-flight depth camera and multiple mirrors","volume":"6","author":"Nguyen","year":"2018","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yin, Z., Jiang, Y., Zheng, J., and Yu, H. (2023). Stja-gcn: A multi-branch spatial\u2013temporal joint attention graph convolutional network for abnormal gait recognition. Appl. Sci., 13.","DOI":"10.3390\/app13074205"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Braspenning, A.M., Cranen, K., Snaphaan, L.J.A.E., and Wouters, E.J.M. (2022). A multiple stakeholder perspective on the drivers and barriers for the implementation of lifestyle monitoring using infrared sensors to record movements for vulnerable older adults living alone at home: A qualitative study. Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph19010570"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e24157","DOI":"10.2196\/24157","article-title":"Issues associated with the management and governance of sensor data and information to assist aging in place: Focus group study with health care professionals","volume":"8","author":"Hunter","year":"2020","journal-title":"JMIR mHealth uHealth"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e19641","DOI":"10.2196\/19641","article-title":"Comparison of the mental burden on nursing care providers with and without mat-type sleep state sensors at a nursing home in tokyo, japan: Quasi-experimental study","volume":"5","author":"Itoh","year":"2022","journal-title":"JMIR Aging"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., and Zhu, Z. (2017). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1109\/TMM.2021.3068609","article-title":"Multi-scale sparse graph convolutional network for the assessment of parkinsonian gait","volume":"24","author":"Guo","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12984-022-01025-3","article-title":"Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks","volume":"19","author":"Filtjens","year":"2022","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2288","DOI":"10.1109\/JBHI.2022.3144917","article-title":"Estimating parkinsonism severity in natural gait videos of older adults with dementia","volume":"26","author":"Sabo","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1007\/s11517-018-1795-2","article-title":"Vision-based gait impairment analysis for aided diagnosis","volume":"56","author":"Ortells","year":"2018","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"139881","DOI":"10.1109\/ACCESS.2020.3013029","article-title":"Pathological gait classification using kinect v2 and gated recurrent neural networks","volume":"8","author":"Jun","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1080\/09540091.2022.2026294","article-title":"Multi-stream part-fused graph convolutional networks for skeleton-based gait recognition","volume":"34","author":"Wang","year":"2022","journal-title":"Connect. Sci."},{"key":"ref_27","unstructured":"Yu, S., Tan, D., and Tan, T. (2006, January 20\u201324). A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. Proceedings of the 18th International Conference on Pattern Recognition (ICPR\u201906), Hong Kong."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lochhead, C., and Fisher, R.B. (2025). Lightweight human gait anomaly assessment using single-stream uniform temporal attention. Comput. Biol. Med., 190.","DOI":"10.1016\/j.compbiomed.2025.110076"},{"key":"ref_29","unstructured":"Lundberg, S.M., and Lee, S. (2017). A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cwhy should i trust you?\u201d explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_31","unstructured":"Moshkovitz, M., Dasgupta, S., Rashtchian, C., and Frost, N. (2020, January 12\u201318). Explainable k-means and k-medians clustering. Proceedings of the International Conference on Machine Learning, PMLR 2020, Virtual."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"109239","DOI":"10.1016\/j.patcog.2022.109239","article-title":"Shallow decision trees for explainable k-means clustering","volume":"137","author":"Laber","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1002\/jor.25363","article-title":"Gait biomechanics phenotypes among total knee arthroplasty candidates by machine learning cluster analysis","volume":"41","author":"Roy","year":"2023","journal-title":"J. Orthop. Res."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Tran, L., Yin, X., Atoum, Y., Liu, X., Wan, J., and Wang, N. (2019, January 15\u201320). Gait recognition via disentangled representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00484"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wang, G., Yuan, Y., Chen, X., Li, J., and Zhou, X. (2018, January 22\u201326). Learning discriminative features with multiple granularities for person re-identification. Proceedings of the 26th ACM international conference on Multimedia, Seoul, Republic of Korea.","DOI":"10.1145\/3240508.3240552"},{"key":"ref_36","unstructured":"Duvenaud, D.K., Maclaurin, D., Iparraguirre, J., Bombarell, R., Hirzel, T., Aspuru-Guzik, A., and Adams, R.P. (2015). Convolutional networks on graphs for learning molecular fingerprints. Adv. Neural Inf. Process. Syst., 28, Available online: https:\/\/www.cs.princeton.edu\/~rpa\/pubs\/duvenaud2015fingerprints.pdf."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lu, Z., Du, P., and Nie, J. (2020, January 14\u201317). Vgcn-bert: Augmenting bert with graph embedding for text classification. Proceedings of the Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal. Proceedings, Part I 42.","DOI":"10.1007\/978-3-030-45439-5_25"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.jvcir.2013.02.006","article-title":"The tum gait from audio, image and depth (gaid) database: Multimodal recognition of subjects and traits","volume":"25","author":"Hofmann","year":"2014","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_39","unstructured":"Ismaili, O.A., Lemaire, V., and Cornu\u00e9jols, A. (2014, January 3\u20136). A supervised methodology to measure the variables contribution to a clustering. Proceedings of the Neural Information Processing: 21st International Conference, ICONIP 2014, Kuching, Malaysia. Proceedings, Part I 21."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Z., Xiong, H., Gao, X., and Wu, J. (2010, January 13\u201317). Understanding of internal clustering validation measures. Proceedings of the 2010 IEEE International Conference on Data Mining, Sydney, NSW, Australia.","DOI":"10.1109\/ICDM.2010.35"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/13\/4106\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:01:58Z","timestamp":1760032918000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/13\/4106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":40,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["s25134106"],"URL":"https:\/\/doi.org\/10.3390\/s25134106","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,30]]}}}