{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:07:06Z","timestamp":1792598826560,"version":"4.5.0"},"reference-count":47,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Accurate prediction of postoperative metastasis and mortality risks in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction is essential for guiding adjuvant therapies and managing patient expectations. Current prediction methods are limited by variability in patient-specific factors. This study aims to develop and internally validate explainable machine learning (ML) models to predict the 1-year risk of new distant metastases and mortality in these patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We performed a secondary analysis of data from the Prophylactic Antibiotic Regimens in Tumor Surgery trial, which included 604 patients. Candidate features were selected based on availability and clinical relevance and then narrowed using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Boruta algorithms. Six ML classification algorithms were tuned and calibrated: logistic regression, support vector machines, random forest, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), and neural networks. Models were developed with and without including percent tumor necrosis due to its high missing data rate (&gt;30%). Hyperparameters were tuned using Bayesian optimization. Internal validation was conducted using a 30% hold-out set. Model explainability was assessed using permutation-based feature importance and SHapley Additive exPlanations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>LightGBM was identified as the best-performing algorithm for both outcomes. For 1-year mortality prediction without percent necrosis, LightGBM achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.78 (95% confidence interval [CI] 0.70-0.86) during cross-validation and 0.72 on internal validation. For distant metastasis prediction, the LightGBM model without percent necrosis achieved an AUC-ROC of 0.77 (95% CI 0.71-0.84) during cross-validation and 0.77 on internal validation. Including percent necrosis did not significantly improve model performance. The top predictors identified were patient age, largest tumor dimension, and tumor stage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>Explainable ML models can effectively predict the 1-year risk of mortality and new distant metastases in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction. Further external validation and consideration of other data modalities are required before integrating these ML-driven risk assessments into routine clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence:<\/jats:title>\n                    <jats:p>\n                      <jats:underline>Level II<\/jats:underline>\n                      , Prognostic Study. See Instructions for Authors for a complete description of levels of evidence.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.2106\/jbjs.oa.24.00213","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T14:06:54Z","timestamp":1747922814000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":5,"title":["Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors"],"prefix":"10.2106","volume":"10","author":[{"given":"Jiawen","family":"Deng","sequence":"first","affiliation":[{"name":"Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4136-6981","authenticated-orcid":false,"given":"Myron","family":"Moskalyk","sequence":"additional","affiliation":[{"name":"Biostatistics Division, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada"},{"name":"School of Medicine, Faculty of Health Sciences, Queen's University, Kingston, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7502-3475","authenticated-orcid":false,"given":"Madhur","family":"Nayan","sequence":"additional","affiliation":[{"name":"Department of Population Health, NYU Grossman School of Medicine, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Aoude","sequence":"additional","affiliation":[{"name":"Division of Orthopaedic Surgery, McGill University, Montr\u00e9al, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4778-4522","authenticated-orcid":false,"given":"Michelle","family":"Ghert","sequence":"additional","affiliation":[{"name":"Division of Orthopaedic Surgery, McMaster University, Hamilton, Ontario, Canada"},{"name":"Department of Orthopaedics, University of Maryland School of Medicine, University of Maryland, Baltimore, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahir","family":"Bhatnagar","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, McGill University, Montr\u00e9al, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-2086","authenticated-orcid":false,"given":"Anthony","family":"Bozzo","sequence":"additional","affiliation":[{"name":"Division of Orthopaedic Surgery, McGill University, Montr\u00e9al, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,4]]},"reference":[{"issue":"159","key":"R1-20250927","doi-asserted-by":"crossref","first-page":"159","DOI":"10.25259\/JMSR_49_2021","article-title":"Bone tumors distribution in diagnostic and excisional biopsies","volume":"5","author":"Almigdad","year":"2021","journal-title":"J Musculoskelet Surg Res."},{"key":"R2-20250927","doi-asserted-by":"crossref","first-page":"210","DOI":"10.3389\/fonc.2013.00210","article-title":"Quality of life following amputation or limb preservation in patients with lower extremity bone sarcoma","volume":"3","author":"Mason","year":"2013","journal-title":"Front Oncol"},{"issue":"6","key":"R3-20250927","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/S1470-2045(03)01114-8","article-title":"Limb salvage in musculoskeletal oncology","volume":"4","author":"Veth","year":"2003","journal-title":"Lancet Oncol"},{"issue":"2","key":"R4-20250927","first-page":"92","article-title":"Epidemiology and classification of bone tumors","volume":"9","author":"Franchi","year":"2012","journal-title":"Clin Cases Miner Bone Metab"},{"key":"R5-20250927","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-1-4419-0284-9_1","article-title":"The epidemiology of osteosarcoma","volume":"152","author":"Ottaviani","year":"2009","journal-title":"Cancer Treat Res."},{"issue":"3","key":"R6-20250927","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1001\/jamaoncol.2021.6628","article-title":"Comparison of prophylactic intravenous antibiotic regimens after endoprosthetic reconstruction for lower extremity bone tumors: a randomized clinical trial","volume":"8","author":"Ghert","year":"2022","journal-title":"JAMA Oncol"},{"issue":"2","key":"R7-20250927","doi-asserted-by":"crossref","first-page":"94","DOI":"10.7861\/futurehosp.6-2-94","article-title":"The potential for artificial intelligence in healthcare","volume":"6","author":"Davenport","year":"2019","journal-title":"Future Healthc J"},{"key":"R8-20250927","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/RBME.2020.3007816","article-title":"Machine learning for clinical outcome prediction","volume":"14","author":"Shamout","year":"2021","journal-title":"IEEE Rev Biomed Eng"},{"issue":"471","key":"R9-20250927","doi-asserted-by":"crossref","first-page":"eaao5333","DOI":"10.1126\/scitranslmed.aao5333","article-title":"Big data and black-box medical algorithms","volume":"10","author":"Price","year":"2018","journal-title":"Sci Transl Med"},{"key":"R10-20250927","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.inffus.2021.07.016","article-title":"Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: a mini-review, two showcases and beyond","volume":"77","author":"Yang","year":"2022","journal-title":"Inf Fusion"},{"key":"R11-20250927","doi-asserted-by":"crossref","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"issue":"6","key":"R12-20250927","doi-asserted-by":"crossref","first-page":"e002197","DOI":"10.1136\/bmjopen-2012-002197","article-title":"Prophylactic antibiotic regimens in tumour surgery (PARITY): protocol for a multicentre randomised controlled study","volume":"2","author":"Ghert","year":"2012","journal-title":"BMJ Open"},{"issue":"1","key":"R14-20250927","doi-asserted-by":"crossref","first-page":"e092594","DOI":"10.1136\/bmjopen-2024-092594","article-title":"Development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data: a protocol","volume":"15","author":"Deng","year":"2025","journal-title":"BMJ Open"},{"issue":"11","key":"R15-20250927","first-page":"36","article-title":"Feature selection with the Boruta Package","author":"Kursa","year":"2010","journal-title":"J Stat Softw"},{"issue":"3","key":"R16-20250927","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1097\/CORR.0000000000002380","article-title":"Ninety percent or greater tumor necrosis is associated with survival and social determinants of health in patients with osteosarcoma in the National Cancer Database","volume":"481","author":"Richardson","year":"2023","journal-title":"Clin Orthop Relat Res."},{"issue":"12","key":"R17-20250927","doi-asserted-by":"crossref","first-page":"1847","DOI":"10.1007\/s00264-011-1209-7","article-title":"The relation of tumour necrosis and survival in patients with osteosarcoma","volume":"35","author":"Li","year":"2011","journal-title":"Int Orthop"},{"issue":"1","key":"R18-20250927","doi-asserted-by":"crossref","first-page":"11000","DOI":"10.1038\/s41598-019-46721-8","article-title":"Easy-to-use clinical tool for survival estimation in Ewing sarcoma at diagnosis and after surgery","volume":"9","author":"Bosma","year":"2019","journal-title":"Sci Rep"},{"issue":"3","key":"R20-20250927","article-title":"Mice: multivariate imputation by chained equations in R","volume":"45","author":"van Buuren","year":"2011","journal-title":"J Stat Softw"},{"issue":"4","key":"R21-20250927","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1002\/sim.4067","article-title":"Multiple imputation using chained equations: issues and guidance for practice","volume":"30","author":"White","year":"2011","journal-title":"Stat Med"},{"issue":"2065","key":"R23-20250927","first-page":"20150202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos Trans A Math Phys Eng Sci."},{"issue":"3\/4","key":"R24-20250927","doi-asserted-by":"crossref","first-page":"591","DOI":"10.2307\/2333709","article-title":"An analysis of variance test for normality (complete samples)","volume":"52","author":"Shapiro","year":"1965","journal-title":"Biometrika"},{"issue":"2","key":"R25-20250927","doi-asserted-by":"crossref","first-page":"486","DOI":"10.5812\/ijem.3505","article-title":"Normality tests for statistical analysis: a guide for non-statisticians","volume":"10","author":"Ghasemi","year":"2012","journal-title":"Int J Endocrinol Metab"},{"issue":"109924","key":"R26-20250927","doi-asserted-by":"crossref","first-page":"109924","DOI":"10.1016\/j.asoc.2022.109924","article-title":"The choice of scaling technique matters for classification performance","volume":"133","author":"de Amorim","year":"2023","journal-title":"Appl Soft Comput."},{"issue":"4","key":"R29-20250927","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1023\/A:1008306431147","article-title":"Efficient global optimization of expensive black-box functions","volume":"13","author":"Jones","year":"1998","journal-title":"J Glob Optimiz"},{"issue":"3","key":"R30-20250927","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Advances Large Margin Classifiers"},{"issue":"1","key":"R32-20250927","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"issue":"1","key":"R33-20250927","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"issue":"8","key":"R34-20250927","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1016\/j.jclinepi.2009.11.009","article-title":"Use of Brier score to assess binary predictions","volume":"63","author":"Rufibach","year":"2010","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"R35-20250927","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Topic Group \u201cEvaluating diagnostic tests and prediction models\u201d of the STRATOS initiative. Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"issue":"6","key":"R37-20250927","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decis Making"},{"key":"R38-20250927","article-title":"Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"key":"R39-20250927","doi-asserted-by":"crossref","first-page":"e078276","DOI":"10.1136\/bmj-2023-078276","article-title":"Developing clinical prediction models: a step-by-step guide","volume":"386","author":"Efthimiou","year":"2024","journal-title":"BMJ"},{"issue":"1","key":"R40-20250927","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"issue":"1","key":"R42-20250927","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"R44-20250927","doi-asserted-by":"crossref","first-page":"110099","DOI":"10.1016\/j.clinimag.2024.110099","article-title":"Whole-body MRI in oncology: a comprehensive review","volume":"108","author":"Vulasala","year":"2024","journal-title":"Clin Imaging"},{"issue":"4","key":"R45-20250927","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.suc.2022.04.001","article-title":"Radiation therapy for soft tissue sarcoma: indications, timing, benefits, and consequences","volume":"102","author":"Salerno","year":"2022","journal-title":"Surg Clin North Am."},{"issue":"11","key":"R46-20250927","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.3390\/cancers12113242","article-title":"Radiation therapy in adult soft tissue sarcoma-current knowledge and future directions: a review and expert opinion","volume":"12","author":"Roeder","year":"2020","journal-title":"Cancers (Basel)"},{"issue":"22","key":"R47-20250927","doi-asserted-by":"crossref","first-page":"9823","DOI":"10.7314\/APJCP.2014.15.22.9823","article-title":"Comparative outcome of Thai pediatric osteosarcoma treated with two protocols: the role of high-dose methotrexate (HDMTX) in a single institute experience","volume":"15","author":"Choeyprasert","year":"2014","journal-title":"Asian Pac J Cancer Prev"},{"key":"R48-20250927","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.jbo.2018.04.001","article-title":"Does intensified chemotherapy increase survival outcomes of osteosarcoma patients? A meta-analysis","volume":"12","author":"Zhang","year":"2018","journal-title":"J Bone Oncol"},{"issue":"2","key":"R49-20250927","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1097\/CORR.0000000000001969","article-title":"International validation of the SORG machine-learning algorithm for predicting the survival of patients with extremity metastases undergoing surgical treatment","volume":"480","author":"Tseng","year":"2022","journal-title":"Clin Orthop Relat Res."},{"issue":"2","key":"R50-20250927","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1002\/jor.25036","article-title":"Machine learning prediction models in orthopedic surgery: a systematic review in transparent reporting","volume":"40","author":"Groot","year":"2022","journal-title":"J Orthop Res."},{"issue":"suppl 1","key":"R51-20250927","doi-asserted-by":"crossref","first-page":"2","DOI":"10.2106\/JBJS.23.00516","article-title":"Selected Secondary Analyses PARITY Trial: Introduction","volume":"105","author":"Ghert","year":"2023","journal-title":"J Bone Joint Surg Am."},{"issue":"35","key":"R52-20250927","doi-asserted-by":"crossref","first-page":"e2303370120","DOI":"10.1073\/pnas.2303370120","article-title":"Using measures of race to make clinical predictions: decision making, patient health, and fairness","volume":"120","author":"Manski","year":"2023","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"7","key":"R53-20250927","first-page":"10","article-title":"Race and ethnicity: a part of the equation for personalized clinical decision making?","author":"Paulus","year":"2017","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"3","key":"R54-20250927","doi-asserted-by":"crossref","first-page":"173","DOI":"10.3949\/ccjm.91a.23070","article-title":"Artificial intelligence in clinical practice: a look at ChatGPT","volume":"91","author":"Deng","year":"2024","journal-title":"Cleve Clin J Med"},{"issue":"8","key":"R55-20250927","doi-asserted-by":"crossref","first-page":"1706","DOI":"10.1002\/jso.27854","article-title":"Development of machine learning models for predicting the 1-year risk of reoperation after lower limb oncological resection and endoprosthetic reconstruction based on data from the PARITY trial","volume":"130","author":"Deng","year":"2024","journal-title":"J Surg Oncol"},{"issue":"1","key":"R56-20250927","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1038\/s41698-024-00695-7","article-title":"A multimodal neural network with gradient blending improves predictions of survival and metastasis in sarcoma","volume":"8","author":"Bozzo","year":"2024","journal-title":"NPJ Precis Oncol"}],"container-title":["JBJS Open Access"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.OA.24.00213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T13:54:27Z","timestamp":1787752467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.OA.24.00213"}},"subtitle":["A Secondary Analysis of the PARITY Trial"],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.2106\/jbjs.oa.24.00213","relation":{},"ISSN":["2472-7245"],"issn-type":[{"value":"2472-7245","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}