{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:54:01Z","timestamp":1783529641178,"version":"3.55.0"},"reference-count":52,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T00:00:00Z","timestamp":1712707200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100001473","name":"AO North America","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100001473","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal Orthopaedic Research"],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This study aimed to explore the potential of gait analysis coupled with supervised machine learning models as a predictive tool for assessing post\u2010injury complications such as infection, malunion, or hardware irritation among individuals with lower extremity fractures. We prospectively identified participants with lower extremity fractures at a tertiary academic center. These participants underwent gait analysis with a chest\u2010mounted inertial measurement unit device. Using customized software, the raw gait data were preprocessed, emphasizing 12 essential gait variables. The data were standardized, and several machine learning models, including XGBoost, logistic regression, support vector machine, LightGBM, and Random Forest, were trained, tested, and evaluated. Special attention was given to class imbalance, addressed using the synthetic minority oversampling technique (SMOTE). Additionally, we introduced a novel methodology to compute the post\u2010injury recovery rate for gait variables, which operates independently of the time difference between the gait analyses of different participants. XGBoost was identified as the optimal model both before and after the application of SMOTE. Before using SMOTE, the model achieved an average test area under the ROC curve (AUC) of 0.90, with a 95% confidence interval (CI) of [0.79, 1.00], and an average test accuracy of 86%, with a 95% CI of [75%, 97%]. Through feature importance analysis, a pivotal role was attributed to the duration between the occurrence of the injury and the initial gait analysis. Data patterns over time revealed early aggressive physiological compensations, followed by stabilization phases, underscoring the importance of prompt gait analysis. <jats:italic>\u03c7<\/jats:italic><jats:sup>2<\/jats:sup> analysis indicated a statistically significant higher readmission rate among participants with underlying medical conditions (<jats:italic>p<\/jats:italic>\u2009=\u20090.04). Although the complication rate was also higher in this group, the association did not reach statistical significance (<jats:italic>p<\/jats:italic>\u2009=\u20090.06), suggesting a more pronounced impact of medical conditions on readmission rates rather than on complications. This study highlights the transformative potential of integrating advanced machine learning techniques like XGBoost with gait analysis for orthopedic care. The findings underscore a shift toward a data\u2010informed, proactive approach in orthopedics, enhancing patient outcomes through early detection and intervention. The <jats:italic>\u03c7<\/jats:italic><jats:sup>2<\/jats:sup> analysis added crucial insights into the broader clinical implications, advocating for a comprehensive treatment strategy that accounts for the patient's overall health profile. The research paves the way for personalized, predictive medical care in orthopedics, emphasizing the importance of timely and tailored patient assessments.<\/jats:p>","DOI":"10.1002\/jor.25837","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T08:01:10Z","timestamp":1712736070000},"page":"1748-1761","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Employing machine learning to enhance fracture recovery insights through gait analysis"],"prefix":"10.1002","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9569-118X","authenticated-orcid":false,"given":"Mostafa","family":"Rezapour","sequence":"first","affiliation":[{"name":"Center for Artificial Intelligence Research Wake Forest University School of Medicine Winston\u2010Salem North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachel B.","family":"Seymour","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Atrium Health Musculoskeletal Institute and Wake Forest University School of Medicine Charlotte North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen H.","family":"Sims","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Atrium Health Musculoskeletal Institute and Wake Forest University School of Medicine Charlotte North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madhav A.","family":"Karunakar","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Atrium Health Musculoskeletal Institute and Wake Forest University School of Medicine Charlotte North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nahir","family":"Habet","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Atrium Health Musculoskeletal Institute and Wake Forest University School of Medicine Charlotte North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Metin Nafi","family":"Gurcan","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence Research Wake Forest University School of Medicine Winston\u2010Salem North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,4,10]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40719-014-0004-5"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocl.2013.06.005"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/1938640010374121"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.2106\/00004623-200210000-00001"},{"issue":"4","key":"e_1_2_9_6_1","first-page":"427","article-title":"The Ilizarov method in the treatment of pilon fractures","volume":"4","author":"Zarek S","year":"2002","journal-title":"Ortop Traumatol Rehabil"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinbiomech.2007.09.013"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/00003086-199308000-00005"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1097\/00005373-200104000-00019"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.2106\/00004623-199911000-00005"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00264-007-0411-0"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/BOT.0b013e318216b3e3"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.blo.0000119459.00792.c1"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.2106\/00004623-199803000-00007"},{"key":"e_1_2_9_15_1","volume-title":"Gait Analysis: An Introduction","author":"Whittle MW","year":"2014"},{"issue":"2","key":"e_1_2_9_16_1","first-page":"186","article-title":"Human movement analysis using stereophotogrammetry: part 1: theoretical background","volume":"21","author":"Cappozzo A","year":"2005","journal-title":"Gait Posture"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00402-015-2325-4"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1097\/OI9.0000000000000032"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-33222-y"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19314-1"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0276767"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15133428"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107607"},{"key":"e_1_2_9_24_1","unstructured":"SuZ RezapourM SajjadU NiuS GurcanMN NiaziMKK.Cross\u2010attention\u2010based saliency inference for predicting cancer metastasis on whole slide images.arXiv. Preprint posted online September 18 2023.doi:10.48550\/arXiv.2309.09412"},{"key":"e_1_2_9_25_1","volume-title":"Applied Multivariate Statistical Analysis","author":"Johnson RA","year":"2002"},{"key":"e_1_2_9_26_1","volume-title":"Statistics for Business and Economics","author":"Newbold P","year":"2013"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0079945"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2010.12.003"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/33\/11\/1947"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/s140406891"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2009.07.016"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jot.2017.02.003"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2007.08.009"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104309"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.21037\/mhealth-21-17"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1589\/jpts.35.75"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2018.05.014"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2019.12.001"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781412983433"},{"key":"e_1_2_9_40_1","volume-title":"Logistic Regression","author":"Wright RE","year":"1995"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"e_1_2_9_42_1","volume-title":"Support Vector Machine","author":"Steinwart I","year":"2008"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11749-016-0481-7"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_9_45_1","unstructured":"ChenT HeT BenestyM et al.\u00a0Xgboost: extreme gradient boosting.R package version 0.4\u20102 vol. 1 pp. 1\u20104.2015."},{"key":"e_1_2_9_46_1","first-page":"3146","article-title":"Lightgbm: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke G","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00590-021-02927-z"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.injury.2016.05.007"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2014.18614"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e4483"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/0471667196.ess5050"},{"key":"e_1_2_9_53_1","first-page":"508","volume-title":"Encyclopedia of Measurement and Statistics","author":"Abdi H","year":"2007"}],"container-title":["Journal of Orthopaedic Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jor.25837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T08:01:42Z","timestamp":1719993702000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jor.25837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,10]]},"references-count":52,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.1002\/jor.25837"],"URL":"https:\/\/doi.org\/10.1002\/jor.25837","archive":["Portico"],"relation":{},"ISSN":["0736-0266","1554-527X"],"issn-type":[{"value":"0736-0266","type":"print"},{"value":"1554-527X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,10]]},"assertion":[{"value":"2023-09-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-26","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}