{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T03:30:13Z","timestamp":1791689413142,"version":"4.3.4"},"reference-count":32,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"6","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,3,16]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Statistical models using machine learning (ML) have the potential for more accurate estimates of the probability of binary events than logistic regression. The present study used existing data sets from large musculoskeletal trauma trials to address the following study questions: (1) Do ML models produce better probability estimates than logistic regression models? (2) Are ML models influenced by different variables than logistic regression models?<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We created ML and logistic regression models that estimated the probability of a specific fracture (posterior malleolar involvement in distal spiral tibial shaft and ankle fractures, scaphoid fracture, and distal radial fracture) or adverse event (subsequent surgery [after distal biceps repair or tibial shaft fracture], surgical site infection, and postoperative delirium) using 9 data sets from published musculoskeletal trauma studies. Each data set was split into training (80%) and test (20%) subsets. Fivefold cross-validation of the training set was used to develop the ML models. The best-performing model was then assessed in the independent testing data. Performance was assessed by (1) discrimination (c-statistic), (2) calibration (slope and intercept), and (3) overall performance (Brier score).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The mean c-statistic was 0.01 higher for the logistic regression models compared with the best ML models for each data set (range, \u22120.01 to 0.06). There were fewer variables strongly associated with variation in the ML models, and many were dissimilar from those in the logistic regression models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>The observation that ML models produce probability estimates comparable with logistic regression models for binary events in musculoskeletal trauma suggests that their benefit may be limited in this context.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2106\/jbjs.21.00341","type":"journal-article","created":{"date-parts":[[2021,12,18]],"date-time":"2021-12-18T06:00:09Z","timestamp":1639807209000},"page":"544-551","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":53,"title":["Feasibility of Machine Learning and Logistic Regression Algorithms to Predict Outcome in Orthopaedic Trauma Surgery"],"prefix":"10.2106","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3782-2791","authenticated-orcid":false,"given":"Jacobien H.F.","family":"Oosterhoff","sequence":"first","affiliation":[{"name":"Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"},{"name":"Department of Orthopaedic Surgery, Amsterdam Movement Sciences, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, the Netherlands"},{"name":"Department of Orthopaedic & Trauma Surgery, Flinders Medical Centre, Flinders University, Adelaide, South Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8096-5803","authenticated-orcid":false,"given":"Benjamin Y.","family":"Gravesteijn","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6026-4361","authenticated-orcid":false,"given":"Aditya V.","family":"Karhade","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-7815","authenticated-orcid":false,"given":"Ruurd L.","family":"Jaarsma","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic & Trauma Surgery, Flinders Medical Centre, Flinders University, Adelaide, South Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gino M.M.J.","family":"Kerkhoffs","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Amsterdam Movement Sciences, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6506-4879","authenticated-orcid":false,"given":"David","family":"Ring","sequence":"additional","affiliation":[{"name":"Department of Surgery and Perioperative Care, Dell Medical School, University of Texas, Austin, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph H.","family":"Schwab","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ewout W.","family":"Steyerberg","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1270-2742","authenticated-orcid":false,"given":"Job N.","family":"Doornberg","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic & Trauma Surgery, Flinders Medical Centre, Flinders University, Adelaide, South Australia, Australia"},{"name":"Department of Orthopaedic Surgery, University Medical Centre Groningen, University of Groningen, Groningen, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Machine Learning Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2021,12,17]]},"reference":[{"issue":"5","key":"bib3-20250430","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1097\/SHK.0000000000000898","article-title":"Machine Learning for Predicting Outcomes in Trauma","volume":"48","author":"Liu","year":"2017","journal-title":"Shock."},{"issue":"2","key":"bib4-20250430","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1009715923555","article-title":"A Tutorial on Support Vector Machines for Pattern Recognition","volume":"2","author":"Burges","year":"1998","journal-title":"Data Min Knowl Discov."},{"issue":"3","key":"bib5-20250430","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/2.485891","article-title":"Artificial neural networks: a tutorial","volume":"29","author":"Jain","year":"1996","journal-title":"IEEE Comput Soc."},{"issue":"5","key":"bib6-20250430","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1002\/cem.2790","article-title":"Unsupervised random forest: a tutorial with case studies","volume":"30","author":"Afanador","year":"2016","journal-title":"J Chemometr."},{"key":"bib7-20250430","doi-asserted-by":"crossref","first-page":"21","DOI":"10.3389\/fnbot.2013.00021","article-title":"Gradient boosting machines, a tutorial","volume":"7","author":"Natekin","year":"2013","journal-title":"Front Neurorobot."},{"key":"bib8-20250430","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol."},{"key":"bib9-20250430","doi-asserted-by":"crossref","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ."},{"issue":"12","key":"bib10-20250430","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View","volume":"18","author":"Luo","year":"2016","journal-title":"J Med Internet Res."},{"issue":"12","key":"bib11-20250430","doi-asserted-by":"crossref","first-page":"2567","DOI":"10.2106\/JBJS.G.01694","article-title":"Study to Prospectively Evaluate Reamed Intramedullary Nails in Patients with Tibial Fractures (SPRINT) Investigators. Randomized trial of reamed and unreamed intramedullary nailing of tibial shaft fractures","volume":"90","year":"2008","journal-title":"J Bone Joint Surg Am."},{"issue":"9","key":"bib12-20250430","doi-asserted-by":"crossref","first-page":"2621","DOI":"10.1007\/s11999-010-1737-2","article-title":"Infirmity and injury complexity are risk factors for surgical-site infection after operative fracture care","volume":"469","author":"Bachoura","year":"2011","journal-title":"Clin Orthop Relat Res."},{"issue":"8","key":"bib13-20250430","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1016\/j.jse.2016.02.032","article-title":"Factors associated with adverse events after distal biceps tendon repair or reconstruction","volume":"25","author":"Beks","year":"2016","journal-title":"J Shoulder Elbow Surg."},{"issue":"7","key":"bib14-20250430","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1302\/0301-620X.94B7.28704","article-title":"Predictors of fracture following suspected injury to the scaphoid","volume":"94","author":"Duckworth","year":"2012","journal-title":"J Bone Joint Surg Br."},{"issue":"12","key":"bib15-20250430","doi-asserted-by":"crossref","first-page":"e452","DOI":"10.1097\/BOT.0000000000001605","article-title":"Incidence, Predictors, and Fracture Mapping of (Occult) Posterior Malleolar Fractures Associated with Tibial Shaft Fractures","volume":"33","author":"Hendrickx","year":"2019","journal-title":"J Orthop Trauma."},{"issue":"4","key":"bib16-20250430","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1007\/s00402-020-03383-w","article-title":"Detecting scaphoid fractures in wrist injury: a clinical decision rule","volume":"140","author":"Mallee","year":"2020","journal-title":"Arch Orthop Trauma Surg."},{"key":"bib17-20250430","doi-asserted-by":"crossref","DOI":"10.1177\/21514593211062277","article-title":"Development of machine learning algorithms for prediction of postoperative delirium in elderly hip fracture patients","author":"Oosterhoff","year":"2021","journal-title":"Geriatr Orthop Surg Rehabil."},{"issue":"11","key":"bib18-20250430","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1097\/BOT.0000000000001307","article-title":"The Incidence of Posterior Malleolar Involvement in Distal Spiral Tibia Fractures: Is it Higher than We Think?","volume":"32","author":"Sobol","year":"2018","journal-title":"J Orthop Trauma."},{"issue":"1","key":"bib19-20250430","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1186\/s12891-015-0829-2","article-title":"The Amsterdam wrist rules: the multicenter prospective derivation and external validation of a clinical decision rule for the use of radiography in acute wrist trauma","volume":"16","author":"Walenkamp","year":"2015","journal-title":"BMC Musculoskelet Disord."},{"issue":"6","key":"bib20-20250430","doi-asserted-by":"crossref","first-page":"532","DOI":"10.2106\/JBJS.20.00903","article-title":"A Machine Learning Algorithm to Identify Patients with Tibial Shaft Fractures at Risk for Infection After Operative Treatment","volume":"103","author":"Investigators","year":"2021","journal-title":"J Bone Joint Surg Am."},{"issue":"3","key":"bib21-20250430","first-page":"1","article-title":"mice: Multivariate Imputation by Chained Equations in R","volume":"45","author":"van Buuren","year":"2011","journal-title":"J Stat Software."},{"issue":"13","key":"bib22-20250430","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.1089\/neu.2020.7218","article-title":"Missing Data in Prediction Research: A Five-Step Approach for Multiple Imputation, Illustrated in the CENTER-TBI Study","volume":"38","author":"Gravesteijn","year":"2021","journal-title":"J Neurotrauma."},{"issue":"10","key":"bib23-20250430","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1302\/2058-5241.5.190092","article-title":"Machine Learning Consortium. Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner\u2019s hype cycle","volume":"5","author":"Oosterhoff","year":"2020","journal-title":"EFORT Open Rev."},{"issue":"1","key":"bib24-20250430","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":"3-4","key":"bib25-20250430","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1093\/biomet\/45.3-4.562","article-title":"Two Further Applications of a Model for Binary Regression","volume":"45","author":"Cox","year":"1958","journal-title":"Biometrika."},{"issue":"29","key":"bib26-20250430","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1093\/eurheartj\/ehu207","article-title":"Towards better clinical prediction models: seven steps for development and an ABCD for validation","volume":"35","author":"Steyerberg","year":"2014","journal-title":"Eur Heart J."},{"issue":"2","key":"bib27-20250430","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1177\/0272989X14547233","article-title":"Calibration of risk prediction models: impact on decision-analytic performance","volume":"35","author":"Van Calster","year":"2015","journal-title":"Med Decis Making."},{"issue":"1","key":"bib31-20250430","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/a0018326","article-title":"The epistemology of mathematical and statistical modeling: a quiet methodological revolution","volume":"65","author":"Rodgers","year":"2010","journal-title":"Am Psychol."},{"issue":"1","key":"bib33-20250430","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol."},{"issue":"18","key":"bib34-20250430","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1089\/neu.2019.6708","article-title":"Prognostic Research in Traumatic Brain Injury: Markers, Modeling, and Methodological Principles","volume":"38","author":"Retel Helmrich","year":"2021","journal-title":"J Neurotrauma."},{"issue":"22","key":"bib35-20250430","doi-asserted-by":"crossref","first-page":"3946","DOI":"10.1002\/sim.6195","article-title":"How to interpret a small increase in AUC with an additional risk prediction marker: decision analysis comes through","volume":"33","author":"Baker","year":"2014","journal-title":"Stat Med."},{"issue":"11","key":"bib36-20250430","doi-asserted-by":"crossref","first-page":"3166","DOI":"10.1177\/0962280220921415","article-title":"Regression shrinkage methods for clinical prediction models do not guarantee improved performance: Simulation study","volume":"29","author":"Van Calster","year":"2020","journal-title":"Stat Methods Med Res."},{"key":"bib37-20250430","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.jclinepi.2020.12.005","article-title":"Penalization and shrinkage methods produced unreliable clinical prediction models especially when sample size was small","volume":"132","author":"Riley","year":"2021","journal-title":"J Clin Epidemiol."},{"issue":"10","key":"bib38-20250430","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1016\/j.spinee.2020.06.014","article-title":"SMART on FHIR in spine: integrating clinical prediction models into electronic health records for precision medicine at the point of care","volume":"21","author":"Karhade","year":"2021","journal-title":"Spine J."}],"container-title":["Journal of Bone and Joint Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.21.00341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T13:43:53Z","timestamp":1787751833000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.21.00341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,17]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2106\/jbjs.21.00341","relation":{},"ISSN":["0021-9355","1535-1386"],"issn-type":[{"value":"0021-9355","type":"print"},{"value":"1535-1386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,17]]}}}