{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T12:35:41Z","timestamp":1791462941345,"version":"4.3.4"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T00:00:00Z","timestamp":1712016000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004828","name":"Grand Challenges Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004828","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Quantitative gait analysis is important for understanding the non-typical walking patterns associated with mobility impairments. Conventional linear statistical methods and machine learning (ML) models are commonly used to assess gait performance and related changes in the gait parameters. Nonetheless, explainable machine learning provides an alternative technique for distinguishing the significant and influential gait changes stemming from a given intervention. The goal of this work was to demonstrate the use of explainable ML models in gait analysis for prosthetic rehabilitation in both population- and sample-based interpretability analyses. Models were developed to classify amputee gait with two types of prosthetic knee joints. Sagittal plane gait patterns of 21 individuals with unilateral transfemoral amputations were video-recorded and 19 spatiotemporal and kinematic gait parameters were extracted and included in the models. Four ML models\u2014logistic regression, support vector machine, random forest, and LightGBM\u2014were assessed and tested for accuracy and precision. The Shapley Additive exPlanations (SHAP) framework was applied to examine global and local interpretability. Random Forest yielded the highest classification accuracy (98.3%). The SHAP framework quantified the level of influence of each gait parameter in the models where knee flexion-related parameters were found the most influential factors in yielding the outcomes of the models. The sample-based explainable ML provided additional insights over the population-based analyses, including an understanding of the effect of the knee type on the walking style of a specific sample, and whether or not it agreed with global interpretations. It was concluded that explainable ML models can be powerful tools for the assessment of gait-related clinical interventions, revealing important parameters that may be overlooked using conventional statistical methods.<\/jats:p>","DOI":"10.1371\/journal.pone.0300447","type":"journal-article","created":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T18:09:41Z","timestamp":1712081381000},"page":"e0300447","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Exploration and demonstration of explainable machine learning models in prosthetic rehabilitation-based gait analysis"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4021-9133","authenticated-orcid":true,"given":"Mohammad Pourmahmood","family":"Aghababa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Andrysek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,4,2]]},"reference":[{"issue":"4","key":"pone.0300447.ref001","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.gaitpost.2011.02.003","article-title":"Biomechanics and physiological parameters during gait in lower-limb amputees: A systematic review","volume":"33","author":"Y Sagawa","year":"2011","journal-title":"Gait Posture"},{"issue":"10","key":"pone.0300447.ref002","doi-asserted-by":"crossref","first-page":"1910","DOI":"10.3390\/sym14091910","article-title":"Clinical and demographic factors influencing the asymmetry of gait in lower-limb prosthetic users","volume":"14","author":"M D\u0105browski","year":"2022","journal-title":"Symmetry"},{"key":"pone.0300447.ref003","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3390\/prosthesis4010013","article-title":"Gait performance of friction-based prosthetic knee joint swing-phase controllers in under-resourced settings","volume":"4","author":"J Andrysek","year":"2022","journal-title":"Prosthesis"},{"issue":"9","key":"pone.0300447.ref004","doi-asserted-by":"crossref","first-page":"455","DOI":"10.3390\/medicina56090455","article-title":"Comparison of conventional statistical methods with machine learning in medicine: diagnosis, drug development, and treatment","volume":"56","author":"HSR Rajula","year":"2020","journal-title":"Medicina (Kaunas)"},{"key":"pone.0300447.ref005","doi-asserted-by":"crossref","DOI":"10.4324\/9781315744131","volume-title":"Data analysis: A model comparison approach to regression, ANOVA, and beyond, Third Edition","author":"CM Judd","year":"2017","edition":"3"},{"issue":"9","key":"pone.0300447.ref006","doi-asserted-by":"crossref","first-page":"e01976","DOI":"10.1002\/ecs2.1976","article-title":"Statistically reinforced machine learning for nonlinear patterns and variable interactions","volume":"8","author":"M Ryo","year":"2017","journal-title":"Ecosphere"},{"issue":"4","key":"pone.0300447.ref007","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.3390\/app11041834","article-title":"Severity classification of Parkinson\u2019s Disease based on permutation-variable importance and persistent entropy","volume":"11","author":"J Tong","year":"2021","journal-title":"Appl Sci"},{"issue":"5","key":"pone.0300447.ref008","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1080\/00273171.2019.1671162","article-title":"Testing differential item functioning in small samples","volume":"55","author":"WCM Belzak","year":"2020","journal-title":"Multivariate Behav Res"},{"key":"pone.0300447.ref009","first-page":"1286864","article-title":"Human gait analysis metric for gait retraining","volume":"11","author":"T Ramakrishnan","year":"2019","journal-title":"Appl Bionics Biomech"},{"key":"pone.0300447.ref010","first-page":"202","article-title":"Implementation of machine learning for classifying prosthesis type through conventional gait analysis","author":"R LeMoyne","year":"2015","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"11","key":"pone.0300447.ref011","doi-asserted-by":"crossref","first-page":"e12955","DOI":"10.1111\/exsy.12955","article-title":"A vision-based clinical analysis for classification of knee osteoarthritis, Parkinson\u2019s disease and normal gait with severity based on k-nearest neighbour","volume":"39","author":"N Kour","year":"2022","journal-title":"Expert Syst"},{"issue":"9","key":"pone.0300447.ref012","doi-asserted-by":"crossref","first-page":"4741","DOI":"10.1109\/JSEN.2022.3146617","article-title":"Characterization of knee and gait features from a wearable tele-health monitoring system","volume":"22","author":"AI Faisal","year":"2022","journal-title":"IEEE Sens J"},{"key":"pone.0300447.ref013","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"},{"issue":"6","key":"pone.0300447.ref014","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1002\/widm.1194","article-title":"Scalable machine-learning algorithms for big data analytics: A comprehensive review. Wiley Interdisciplinary Reviews","volume":"6","author":"P Gupta","year":"2016","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"3","key":"pone.0300447.ref015","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/S1470-2045(19)30149-4","article-title":"Big data and machine learning algorithms for health-care delivery","volume":"20","author":"KY Ngiam","year":"2019","journal-title":"Lancet Oncol"},{"issue":"1","key":"pone.0300447.ref016","doi-asserted-by":"crossref","first-page":"95","DOI":"10.36660\/abc.20200596","article-title":"Machine learning in medicine: review and applicability","volume":"118","author":"GMM Paix\u00e3o","year":"2022","journal-title":"Arq Bras Cardiol"},{"key":"pone.0300447.ref017","doi-asserted-by":"crossref","first-page":"205","DOI":"10.3390\/s23010205","article-title":"Systematic review on the applicability of principal component analysis for the study of movement in the older adult population","volume":"23","author":"J Moreira","year":"2023","journal-title":"Sensors"},{"key":"pone.0300447.ref018","doi-asserted-by":"crossref","first-page":"688969","DOI":"10.3389\/fdata.2021.688969","article-title":"Principles and practice of explainable machine learning","volume":"4","author":"V Belle","year":"2021","journal-title":"Front Big Data"},{"key":"pone.0300447.ref019","article-title":"On the explanation of machine learning predictions in clinical gait analysis","author":"DJO Slijepcevic","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0300447.ref020","doi-asserted-by":"crossref","first-page":"6647","DOI":"10.1038\/s41598-022-10666-2","article-title":"Leveraging explainable machine learning to identify gait biomechanical parameters associated with anterior cruciate ligament injury","volume":"12","author":"C Kokkotis","year":"2022","journal-title":"Sci Rep"},{"key":"pone.0300447.ref021","doi-asserted-by":"crossref","first-page":"754477","DOI":"10.3389\/fnetp.2021.754477","article-title":"Comparison of gait speed reserve, usual gait speed, and maximum gait speed of adults aged 50+ in Ireland using explainable machine learning","volume":"1","author":"JRC Davis","year":"2021","journal-title":"Front Netw Physiol"},{"issue":"2","key":"pone.0300447.ref022","doi-asserted-by":"crossref","first-page":"167","DOI":"10.3390\/bios12030167","article-title":"Explainable artificial intelligence and wearable sensor-based gait analysis to identify patients with osteopenia and sarcopenia in daily life","volume":"12","author":"JK Kim","year":"2022","journal-title":"Biosensors"},{"issue":"1","key":"pone.0300447.ref023","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s13246-022-01106-6","article-title":"Explainable machine learning for knee osteoarthritis diagnosis based on a novel fuzzy feature selection methodology","volume":"45","author":"C Kokkotis","year":"2022","journal-title":"Phys Eng Sci Med"},{"key":"pone.0300447.ref024","first-page":"4768","volume-title":"Advances in Neural Information Processing Systems","author":"SM Lundberg","year":"2017"},{"key":"pone.0300447.ref025","article-title":"Identification and interpretation of gait analysis features and foot condition by explainable AI","author":"ME \u00d6zates","year":"2022","journal-title":"Research Square"},{"issue":"1","key":"pone.0300447.ref026","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"pone.0300447.ref027","volume-title":"Hands-on machine learning with Scikit-learn, Keras, and Tensorflow","author":"A G\u00e9ron","year":"2019","edition":"2"},{"key":"pone.0300447.ref028","first-page":"3146","volume-title":"Advances in Neural Information Processing Systems","author":"G Ke","year":"2017"},{"key":"pone.0300447.ref029","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-05127-3","volume-title":"Outlier Detection: Techniques and Applications","author":"NNR Suri","year":"2019"},{"key":"pone.0300447.ref030","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/s42452-021-04148-9","article-title":"Comparison of feature importance measures as explanations for classification models","volume":"3","author":"M Saarela","year":"2021","journal-title":"SN Appl Sci"},{"issue":"3","key":"pone.0300447.ref031","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1177\/0309364620921290","article-title":"Two-dimensional video gait analysis: A systematic review of reliability, validity, and best practice considerations","volume":"44","author":"A Michelini","year":"2020","journal-title":"Prosthet Orthot Int"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0300447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T18:10:00Z","timestamp":1712081400000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0300447"}},"subtitle":[],"editor":[{"given":"Noman","family":"Naseer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,4,2]]},"references-count":31,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0300447","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,2]]}}}