{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T05:24:17Z","timestamp":1793165057668,"version":"4.5.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Currently, there is no individualized prediction model for joint function recovery after ankle fracture surgery. This study aims to develop a prediction model for poor recovery following ankle fracture surgery using various machine learning algorithms to facilitate early identification of high-risk patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 750 patients who underwent ankle fracture surgery at Lu\u2019an Hospital Affiliated to Anhui Medical University between January 2018 and December 2023 were followed up. The collected data were chronologically divided into a training set (599 cases) and a test set (151 cases). Feature variables were selected using the Boruta algorithm, and five machine learning algorithms (logistic regression, random forest, extreme gradient boosting, support vector machine, and lasso-stacking) were employed to construct models. The performance of these models was compared on both the training and test sets to select the best-performing model. The decision basis of the optimal model was further analyzed using Shapley Additive Explanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In total, 12 characteristic variables were identified using the Boruta algorithm. Among the five machine learning models, random forest model: AUC (training set: 0.840, test set: 0.779), accuracy (training set: 0.781, test set: 0.742); SVM: AUC (training set: 0.809, test set: 0.768), accuracy (training set: 0.751, test set: 0.728); XGBoost: AUC (training set: 0.734, test set: 0.748), accuracy (training set: 0.668, test set: 0.722); logistic regression: AUC (training set: 0.672, test set: 0.691), accuracy (training set: 0.651, test set: 0.656); lasso-stacking model: AUC (training set: 0.877, test set: 0.791), accuracy (training set: 0.796, test set: 0.762). The PR curve and decision curve of the lasso-stacking model were better than those of other models. The lasso-stacking model had the best performance. SHAP analysis showed that functional exercise compliance, combined ligament injury, and open fracture accounted for the largest proportion of SHAP values and were the most important influencing factors.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Through evaluation and comparison of the developed models, the lasso-stacking model demonstrated the best performance and is more suitable for predicting joint function recovery after ankle surgery. This model can be further validated externally and applied in clinical practice.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1553274","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T05:29:19Z","timestamp":1750915759000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["A risk prediction model for poor joint function recovery after ankle fracture surgery based on interpretable machine learning"],"prefix":"10.3389","volume":"12","author":[{"given":"Congyang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiru","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuezhi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3109\/17453679809002356","article-title":"Epidemiology of ankle fractures: a prospective population-based study of 212 cases in Aalborg, Denmark","volume":"69","author":"Jensen","year":"1998","journal-title":"Acta Orthop Scand"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.cpm.2006.02.001","article-title":"Ankle fractures","volume":"23","author":"Mandi","year":"2006","journal-title":"Clin Podiatr Med Surg"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1053\/j.jfas.2019.09.016","article-title":"Ankle fracture epidemiology in the United States: patient-related trends and mechanisms of injury","volume":"59","author":"Scheer","year":"2020","journal-title":"J Foot Ankle Surg"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e580","DOI":"10.1016\/S2666-7568(21)00172-0","article-title":"Global, regional, and national burden of bone fractures in 204 countries and territories, 1990\u20132019: a systematic analysis from the global burden of disease study 2019","volume":"2","author":"Wu","year":"2021","journal-title":"Lancet Healthy Longevity"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1308\/rcsann.2019.0002","article-title":"Fracture admission trends in England over a ten-year period","volume":"101","author":"Jennison","year":"2019","journal-title":"Ann R College Surg Engl"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11657-023-01353-4","article-title":"The burden of fracture in China from 1990 to 2019","volume":"19","author":"Zhu","year":"2023","journal-title":"Arch Osteoporos"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1186\/s12891-021-04291-9","article-title":"Changing epidemiology of lower extremity fractures in adults over a 15-year period\u2013a National Hospital Discharge Registry study","volume":"22","author":"Hemmann","year":"2021","journal-title":"BMC Musculoskelet Disord"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1016\/s8756-3282(02)00832-3","article-title":"Increasing number and incidence of low-trauma ankle fractures in elderly people: Finnish statistics during 1970\u20132000 and projections for the future","volume":"31","author":"Kannus","year":"2002","journal-title":"Bone"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1186\/s12891-022-06095-x","article-title":"Incidence, costs and post-operative complications following ankle fracture\u2013a US claims database analysis","volume":"23","author":"Vanderkarr","year":"2022","journal-title":"BMC Musculoskelet Disord"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1177\/1071100713519777","article-title":"Economic burden of foot and ankle surgery in the US Medicare population","volume":"35","author":"Belatti","year":"2014","journal-title":"Foot Ankle Int"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1302\/0301-620x.101B5.BJJ-2019-0070","article-title":"Medial malleolar fractures: current treatment concepts","author":"Carter","year":"2019","journal-title":"Bone Joint J"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1177\/1071100716688176","article-title":"Predictors of patient-reported function and pain outcomes in operative ankle fractures","volume":"38","author":"Dean","year":"2017","journal-title":"Foot Ankle Int"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1177\/10711007211003073","article-title":"Patient outcomes following ankle fracture fixation","volume":"42","author":"Chong","year":"2021","journal-title":"Foot Ankle Int"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1177\/1071100720929007","article-title":"Biomechanical effect on joint stability of including deltoid ligament repair in an ankle fracture soft tissue injury model with deltoid and syndesmotic disruption","volume":"41","author":"Mococain","year":"2020","journal-title":"Foot Ankle Int"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"CD005595","DOI":"10.1002\/14651858.CD005595.pub4","article-title":"Rehabilitation for ankle fractures in adults","volume":"9","author":"Lewis","year":"2024","journal-title":"Cochrane Database Syst Rev"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1177\/0269215517724192","article-title":"Active controlled motion in early rehabilitation improves outcome after ankle fractures: a randomized controlled trial","volume":"32","author":"Jansen","year":"2018","journal-title":"Clin Rehabil"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.fcl.2016.09.009","article-title":"Posterior malleolar fractures: changing concepts and recent developments","volume":"22","author":"Barton\u00ed\u010dek","year":"2017","journal-title":"Foot Ankle Clin"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e12011","DOI":"10.1002\/jfa2.12011","article-title":"The effect of early weight-bearing and later weight-bearing rehabilitation interventions on outcomes after ankle fracture surgery: a systematic review and meta-analysis of randomised controlled trials","volume":"17","author":"Chen","year":"2024","journal-title":"J Foot Ankle Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"690","DOI":"10.2519\/jospt.2014.5294","article-title":"Early ankle movement versus immobilization in the postoperative management of ankle fracture in adults: a systematic review and meta-analysis","volume":"44","author":"Keene","year":"2014","journal-title":"J Orthop Sports Phys Ther"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"705","DOI":"10.3390\/jcm13030705","article-title":"Machine learning and deep learning in spinal injury: a narrative review of algorithms in diagnosis and prognosis","volume":"13","author":"Maki","year":"2024","journal-title":"J Clin Med"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"105120","DOI":"10.1016\/j.archger.2023.105120","article-title":"Predictive value of machine learning models in postoperative mortality of older adults patients with hip fracture: a systematic review and meta-analysis","volume":"115","author":"Liu","year":"2023","journal-title":"Arch Gerontol Geriatr"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"106133","DOI":"10.1016\/j.ijsu.2021.106133","article-title":"Perspectives: a surgeon's guide to machine learning","volume":"94","author":"Kuo","year":"2021","journal-title":"Int J Surg"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"e233391","DOI":"10.1001\/jamanetworkopen.2023.3391","article-title":"Artificial intelligence for hip fracture detection and outcome prediction: a systematic review and meta-analysis","volume":"6","author":"Lex","year":"2023","journal-title":"JAMA Netw Open"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1186\/s13018-024-05004-3","article-title":"Machine-learning-based prediction by stacking ensemble strategy for surgical outcomes in patients with degenerative cervical myelopathy","volume":"19","author":"Cai","year":"2024","journal-title":"J Orthop Surg Res"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1016\/j.chest.2021.07.010","article-title":"Point-of-care ultrasound for bedside diagnosis of lower extremity DVT","volume":"160","author":"Barrosse-Antle","year":"2021","journal-title":"Chest"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1161\/CIRCULATIONAHA.117.030687","article-title":"Ultrasound for lower extremity deep venous thrombosis: multidisciplinary recommendations from the Society of Radiologists in ultrasound consensus conference","volume":"137","author":"Needleman","year":"2018","journal-title":"Circulation"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.ajic.2018.01.018","article-title":"Update to the Centers for Disease Control and Prevention and the healthcare infection control practices advisory committee guideline for the prevention of surgical site infection (2017): a summary, review, and strategies for implementation","volume":"46","author":"O'Hara","year":"2018","journal-title":"Am J Infect Control"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1089\/sur.2017.075","article-title":"Introduction to the Centers for Disease Control and Prevention and the healthcare infection control practices advisory committee guideline for the prevention of surgical site infections","volume":"18","author":"Solomkin","year":"2017","journal-title":"Surg Infect"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1097\/ALN.0000000000003947","article-title":"The evolution, current value, and future of the American Society of Anesthesiologists Physical Status Classification System","volume":"135","author":"Horvath","year":"2021","journal-title":"Anesthesiology"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s10916-021-01758-z","article-title":"Reliability of the ASA physical status classification system in predicting surgical morbidity: a retrospective analysis","volume":"45","author":"Li","year":"2021","journal-title":"J Med Syst"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.3969\/j.issn.1672-1756.2019.11.007","article-title":"Development and reliability and validity test of the compliance scale of functional exercise for orthopedic patients","volume":"19","author":"Tan","year":"2019","journal-title":"Chin Nurs Manag"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1177\/107110079401500701","article-title":"Clinical rating systems for the ankle-hindfoot, midfoot, hallux, and lesser toes","volume":"15","author":"Kitaoka","year":"1994","journal-title":"Foot Ankle Int"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e017040","DOI":"10.1136\/bmjopen-2017-017040","article-title":"The American Orthopaedic Foot and Ankle Society ankle-Hindfoot scale; translation and validation of the Dutch language version for ankle fractures","volume":"7","author":"de Boer","year":"2017","journal-title":"BMJ Open"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1053\/j.jfas.2019.08.027","article-title":"Danish language version of the American orthopedic foot and ankle society ankle-Hindfoot scale (AOFAS-AHS) in patients with ankle-related fractures","volume":"59","author":"Erichsen","year":"2020","journal-title":"J Foot Ankle Surg"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","year":"2010","journal-title":"J Stat Softw"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem Med"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3527174","article-title":"Explanation-driven HCI model to examine the mini-mental state for Alzheimer\u2019s disease","volume":"20","author":"Loveleen","year":"2023","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"106156","DOI":"10.1016\/j.compbiomed.2022.106156","article-title":"Explanatory classification of CXR images into COVID-19, pneumonia and tuberculosis using deep learning and XAI","volume":"150","author":"Bhandari","year":"2022","journal-title":"Comput Biol Med"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.aej.2024.04.072","article-title":"An explainable transfer learning framework for multi-classification of lung diseases in chest X-rays","volume":"98","author":"Patel","year":"2024","journal-title":"Alex Eng J"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1186\/s12931-024-02874-3","article-title":"An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease","volume":"25","author":"Huang","year":"2024","journal-title":"Respir Res"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12911-019-1004-8","article-title":"Comparing different supervised machine learning algorithms for disease prediction","volume":"19","author":"Uddin","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1186\/s13098-021-00711-x","article-title":"A potent weighted risk model for evaluating the occurrence and severity of diabetic foot ulcers","volume":"13","author":"Shi","year":"2021","journal-title":"Diabetol Metab Syndr"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1008137","DOI":"10.3389\/fpubh.2022.1008137","article-title":"Construction and validation of nomograms combined with novel machine learning algorithms to predict early death of patients with metastatic colorectal cancer","volume":"10","author":"Zhang","year":"2022","journal-title":"Front Public Health"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"101829","DOI":"10.1016\/j.compmedimag.2020.101829","article-title":"Classification of malignant tumors in breast ultrasound using a pretrained deep residual network model and support vector machine","volume":"87","author":"Shia","year":"2021","journal-title":"Comput Med Imaging Graph"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1302\/0301-620X.106B9.BJJ-2023-1433.R1","article-title":"Early motion and directed exercise (EMADE) following ankle fracture fixation: a pragmatic randomized controlled trial","author":"Matthews","year":"2024","journal-title":"Bone Joint J"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"911471","DOI":"10.3389\/fsurg.2022.911471","article-title":"When is the optimum time for the initiation of early rehabilitative exercise on the postoperative functional recovery of peri-ankle fractures? A network meta-analysis","volume":"9","author":"Zhao","year":"2022","journal-title":"Front Surg"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"e64315","DOI":"10.7759\/cureus.64315","article-title":"Comparative analysis of rehabilitation strategies following ankle fracture surgery: a systematic review","volume":"16","author":"Altuwairqi","year":"2024","journal-title":"Cureus"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"e648","DOI":"10.5435\/JAAOS-D-18-00198","article-title":"Deltoid ligament rupture in ankle fracture: diagnosis and management","volume":"27","author":"Lee","year":"2019","journal-title":"J Am Acad Orthop Surg"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1146\/annurev-nutr-062222-021228","article-title":"Contemporary perioperative nutritional care","volume":"44","author":"Ljungqvist","year":"2024","journal-title":"Annu Rev Nutr"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1002\/jpen.2485","article-title":"Novel nutrition strategies to enhance recovery after surgery","volume":"47","author":"Martindale","year":"2023","journal-title":"J Parenter Enter Nutr"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.ejim.2023.07.003","article-title":"Albumin administration in internal medicine: a journey between effectiveness and futility","volume":"117","author":"Pompili","year":"2023","journal-title":"Eur J Intern Med"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"10318","DOI":"10.3390\/ijms221910318","article-title":"Serum albumin in health and disease: esterase, antioxidant, transporting and signaling properties","volume":"22","author":"Belinskaia","year":"2021","journal-title":"Int J Mol Sci"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"10557","DOI":"10.3390\/ijms231810557","article-title":"Albumin as a biomaterial and therapeutic agent in regenerative medicine","volume":"23","author":"Kuten Pella","year":"2022","journal-title":"Int J Mol Sci"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"pzad074","DOI":"10.1093\/ptj\/pzad074","article-title":"Kinesiophobia is associated with poor function and modifiable through interventions in people with patellofemoral pain: a systematic review with individual participant data correlation meta-analysis","volume":"103","author":"Rethman","year":"2023","journal-title":"Phys Ther"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1553274\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T05:29:20Z","timestamp":1750915760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1553274\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":54,"alternative-id":["10.3389\/fmed.2025.1553274"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1553274","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]},"article-number":"1553274"}}