{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T07:00:43Z","timestamp":1792393243469,"version":"4.4.0"},"reference-count":61,"publisher":"BMJ","issue":"1","funder":[{"DOI":"10.13039\/100012553","name":"Chang Gung Memorial Hospital","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012553","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2017,11,24]]},"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study aimed to build and test the models of machine learning (ML) to predict the mortality of hospitalised motorcycle riders.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>The study was conducted in a level-1 trauma centre in southern Taiwan.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Motorcycle riders who were hospitalised between January 2009 and December 2015 were classified into a training set (n=6306) and test set (n=946). Using the demographic information, injury characteristics and laboratory data of patients, logistic regression (LR), support vector machine (SVM) and decision tree (DT) analyses were performed to determine the mortality of individual motorcycle riders, under different conditions, using all samples or reduced samples, as well as all variables or selected features in the algorithm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>The predictive performance of the model was evaluated based on accuracy, sensitivity, specificity and geometric mean, and an analysis of the area under the receiver operating characteristic curves of the two different models was carried out.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the training set, both LR and SVM had a significantly higher area under the receiver operating characteristic curve (AUC) than DT. No significant difference was observed in the AUC of LR and SVM, regardless of whether all samples or reduced samples and whether all variables or selected features were used. In the test set, the performance of the SVM model for all samples with selected features was better than that of all other models, with an accuracy of 98.73%, sensitivity of 86.96%, specificity of 99.02%, geometric mean of 92.79% and AUC of 0.9517, in mortality prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ML can provide a feasible level of accuracy in predicting the mortality of motorcycle riders. Integration of the ML model, particularly the SVM algorithm in the trauma system, may help identify high-risk patients and, therefore, guide appropriate interventions by the clinical staff.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2017-018252","type":"journal-article","created":{"date-parts":[[2018,1,6]],"date-time":"2018-01-06T01:56:00Z","timestamp":1515203760000},"page":"e018252","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":34,"title":["Derivation and validation of different machine-learning models in mortality prediction of trauma in motorcycle riders: a cross-sectional retrospective study in southern Taiwan"],"prefix":"10.1136","volume":"8","author":[{"given":"Pao-Jen","family":"Kuo","sequence":"first","affiliation":[{"name":"Department of Plastic and Reconstructive Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao-Chun","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng-Chen","family":"Chien","sequence":"additional","affiliation":[{"name":"Department of Plastic and Reconstructive Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Shyuan","family":"Rau","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Plastic and Reconstructive Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsiao-Yun","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Department of Plastic and Reconstructive Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Hua","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Department of Plastic and Reconstructive Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2018,1,5]]},"reference":[{"key":"2025120519013834000_8.1.e018252.1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2010-0902"},{"key":"2025120519013834000_8.1.e018252.2","unstructured":"National Highway Traffic Safety Administration (NHTSA). 2011 motorcycles traffic safety fact sheet. May 2013. http:\/\/www-nrd.nhtsa.dot.gov\/Pubs\/811765.pdf."},{"key":"2025120519013834000_8.1.e018252.3","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwm064"},{"key":"2025120519013834000_8.1.e018252.4","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.aap.2015.03.023","article-title":"Using travel socialization and underlying motivations to better understand motorcycle usage in Taiwan","volume":"79","author":"Chang","year":"2015","journal-title":"Accid Anal Prev"},{"key":"2025120519013834000_8.1.e018252.5","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1080\/15389588.2011.641166","article-title":"Risk factors in motorcyclist fatalities in Taiwan","volume":"13","author":"Jou","year":"2012","journal-title":"Traffic Inj Prev"},{"key":"2025120519013834000_8.1.e018252.6","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1186\/s12887-015-0419-3","article-title":"Motorcycle-related hospitalization of adolescents in a Level I trauma center in southern Taiwan: a cross-sectional study","volume":"15","author":"Liang","year":"2015","journal-title":"BMC Pediatr"},{"key":"2025120519013834000_8.1.e018252.7","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/1749-7922-10-2","article-title":"Alcohol-related hospitalizations of adult motorcycle riders","volume":"10","author":"Liu","year":"2015","journal-title":"World J Emerg Surg"},{"key":"2025120519013834000_8.1.e018252.8","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.bj.2016.10.005","article-title":"Differences between the sexes in motorcycle-related injuries and fatalities at a Taiwanese level I trauma center","volume":"40","author":"Hsieh","year":"2017","journal-title":"Biomed J"},{"key":"2025120519013834000_8.1.e018252.9","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.bj.2016.10.006","article-title":"Motorcycle-related hospitalizations of the elderly","volume":"40","author":"Hsieh","year":"2017","journal-title":"Biomed J"},{"key":"2025120519013834000_8.1.e018252.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpedsurg.2005.10.013"},{"key":"2025120519013834000_8.1.e018252.11","doi-asserted-by":"publisher","DOI":"10.1097\/TA.0b013e3181f1e9fe"},{"key":"2025120519013834000_8.1.e018252.12","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S2213-2600(14)70268-1","article-title":"Mortality prediction in ICU: a methodological advance","volume":"3","author":"Norrie","year":"2015","journal-title":"Lancet Respir Med"},{"key":"2025120519013834000_8.1.e018252.13","doi-asserted-by":"publisher","DOI":"10.1016\/S1072-7515(01)00993-0"},{"key":"2025120519013834000_8.1.e018252.14","doi-asserted-by":"publisher","DOI":"10.1111\/aas.12256"},{"key":"2025120519013834000_8.1.e018252.15","doi-asserted-by":"publisher","DOI":"10.1097\/01.TA.0000119199.52226.C0"},{"key":"2025120519013834000_8.1.e018252.16","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.injury.2016.12.009","article-title":"Mortality prediction models in the general trauma population: A systematic review","volume":"48","author":"de Munter","year":"2017","journal-title":"Injury"},{"key":"2025120519013834000_8.1.e018252.17","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.amjsurg.2009.08.035","article-title":"Prognostic value of sequential organ failure assessment and simplified acute physiology II Score compared with trauma scores in the outcome of multiple-trauma patients","volume":"200","author":"Fueglistaler","year":"2010","journal-title":"Am J Surg"},{"key":"2025120519013834000_8.1.e018252.18","first-page":"908","article-title":"Base deficit-based predictive modeling of outcome in trauma patients admitted to intensive care units in Dutch trauma centers","volume":"63","author":"Kroezen","year":"2007","journal-title":"J Trauma"},{"key":"2025120519013834000_8.1.e018252.19","first-page":"115","article-title":"Probability of survival scores in different trauma registries: a systematic review","volume":"111","author":"Stoica","year":"2016","journal-title":"Chirurgia"},{"key":"2025120519013834000_8.1.e018252.20","first-page":"121","article-title":"A Prospective evaluation of an automated classification system to support evidence-based medicine and systematic review","volume":"2010","author":"Cohen","year":"2010","journal-title":"AMIA Annu Symp Proc"},{"key":"2025120519013834000_8.1.e018252.21","doi-asserted-by":"crossref","unstructured":"Goldstein BA , Navar AM , Carter RE . Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur Heart J 2016:ehw302.doi:10.1093\/eurheartj\/ehw302","DOI":"10.1093\/eurheartj\/ehw302"},{"key":"2025120519013834000_8.1.e018252.22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.13063\/2327-9214.1222","article-title":"Using machine learning and natural language processing algorithms to automate the evaluation of clinical decision support in electronic medical record systems","volume":"4","author":"Szlosek","year":"2016","journal-title":"EGEMS"},{"key":"2025120519013834000_8.1.e018252.23","doi-asserted-by":"publisher","DOI":"10.1038\/mp.2011.173"},{"key":"2025120519013834000_8.1.e018252.24","first-page":"18","article-title":"An Introduction to Machine Learning","volume":"36","author":"Kotoku","year":"2016","journal-title":"Igaku Butsuri"},{"key":"2025120519013834000_8.1.e018252.25","doi-asserted-by":"crossref","first-page":"2040","DOI":"10.1118\/1.4944738","article-title":"Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods","volume":"43","author":"Yahya","year":"2016","journal-title":"Med Phys"},{"key":"2025120519013834000_8.1.e018252.26","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.cmpb.2016.01.017","article-title":"Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers","volume":"127","author":"","year":"2016","journal-title":"Comput Methods Programs Biomed"},{"key":"2025120519013834000_8.1.e018252.27","unstructured":"VV. Statistical learning theory. New York: John Wiley, 1998."},{"key":"2025120519013834000_8.1.e018252.28","doi-asserted-by":"crossref","first-page":"11065","DOI":"10.1021\/acs.analchem.5b03113","article-title":"Support vector machine classification trees","volume":"87","author":"de Boves Harrington","year":"2015","journal-title":"Anal Chem"},{"key":"2025120519013834000_8.1.e018252.29","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/978-1-60761-580-4_11","article-title":"Support vector machines for classification: a statistical portrait","volume":"620","author":"Lee","year":"2010","journal-title":"Methods Mol Biol"},{"key":"2025120519013834000_8.1.e018252.30","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.aap.2016.02.011","article-title":"Investigating driver injury severity patterns in rollover crashes using support vector machine models","volume":"90","author":"Chen","year":"2016","journal-title":"Accid Anal Prev"},{"key":"2025120519013834000_8.1.e018252.31","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.jpsychires.2014.08.017","article-title":"Quantitative forecasting of PTSD from early trauma responses: a Machine Learning application","volume":"59","author":"Galatzer-Levy","year":"2014","journal-title":"J Psychiatr Res"},{"key":"2025120519013834000_8.1.e018252.32","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1016\/j.aap.2011.08.016","article-title":"Using support vector machine models for crash injury severity analysis","volume":"45","author":"Li","year":"2012","journal-title":"Accid Anal Prev"},{"key":"2025120519013834000_8.1.e018252.33","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.aap.2016.10.014","article-title":"Classifying injury narratives of large administrative databases for surveillance-A practical approach combining machine learning ensembles and human review","volume":"98","author":"Marucci-Wellman","year":"2017","journal-title":"Accid Anal Prev"},{"key":"2025120519013834000_8.1.e018252.34","doi-asserted-by":"crossref","first-page":"1531","DOI":"10.1007\/s10916-010-9430-2","article-title":"A new approach: role of data mining in prediction of survival of burn patients","volume":"35","author":"Patil","year":"2011","journal-title":"J Med Syst"},{"key":"2025120519013834000_8.1.e018252.35","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1007\/s10916-009-9268-7","article-title":"A tree-based decision model to support prediction of the severity of asthma exacerbations in children","volume":"34","author":"Farion","year":"2010","journal-title":"J Med Syst"},{"key":"2025120519013834000_8.1.e018252.36","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1016\/j.compbiomed.2006.06.001","article-title":"A tree-based decision rule for identifying profile groups of cases without predefined classes: application in diffuse large B-cell lymphomas","volume":"37","author":"Zintzaras","year":"2007","journal-title":"Comput Biol Med"},{"key":"2025120519013834000_8.1.e018252.37","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3389\/fendo.2017.00025","article-title":"A decision tree analysis of diabetic foot amputation risk in indian patients","volume":"8","author":"Kasbekar","year":"2017","journal-title":"Front Endocrinol"},{"key":"2025120519013834000_8.1.e018252.38","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1177\/0885066616686924","article-title":"External validation of two classification and regression tree models to predict the outcome of inpatient cardiopulmonary resuscitation","volume":"32","author":"Guilbault","year":"2017","journal-title":"J Intensive Care Med"},{"key":"2025120519013834000_8.1.e018252.39","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1111\/jvh.12617","article-title":"Classification and regression tree analysis of acute-on-chronic hepatitis B liver failure: Seeing the forest for the trees","volume":"24","author":"Shi","year":"2017","journal-title":"J Viral Hepat"},{"key":"2025120519013834000_8.1.e018252.40","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1186\/s12879-016-1839-x","article-title":"Classification and Regression Tree (CART) analysis to predict influenza in primary care patients","volume":"16","author":"Zimmerman","year":"2016","journal-title":"BMC Infect Dis"},{"key":"2025120519013834000_8.1.e018252.41","doi-asserted-by":"publisher","DOI":"10.1089\/cmb.2014.0195"},{"key":"2025120519013834000_8.1.e018252.42","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gni159"},{"key":"2025120519013834000_8.1.e018252.43","doi-asserted-by":"crossref","unstructured":"Vapnik VN . The Nature of Statistical Learning Theory. 2nd ed New York, 2000.","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"2025120519013834000_8.1.e018252.44","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-001815"},{"key":"2025120519013834000_8.1.e018252.45","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1111\/bcpt.12638","article-title":"An effective machine learning approach for prognosis of paraquat poisoning patients using blood routine indexes","volume":"120","author":"Chen","year":"2017","journal-title":"Basic Clin Pharmacol Toxicol"},{"key":"2025120519013834000_8.1.e018252.46","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1016\/j.aap.2006.04.009","article-title":"Analysis of traffic injury severity: an application of non-parametric classification tree techniques","volume":"38","author":"Chang","year":"2006","journal-title":"Accid Anal Prev"},{"key":"2025120519013834000_8.1.e018252.47","unstructured":"Ripley B . Tree: Classification and regression trees. R package version 1.0-34, 2013. http:\/\/CRAN.R-project.org\/package=tree"},{"key":"2025120519013834000_8.1.e018252.48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cmpb.2017.02.011","article-title":"A new survival status prediction system for severe trauma patients based on a multiple classifier system","volume":"142","author":"Sanz","year":"2017","journal-title":"Comput Methods Programs Biomed"},{"key":"2025120519013834000_8.1.e018252.49","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"2025120519013834000_8.1.e018252.50","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwn217"},{"key":"2025120519013834000_8.1.e018252.51","doi-asserted-by":"crossref","first-page":"2786","DOI":"10.1017\/S095026881500014X","article-title":"Use of random forest to estimate population attributable fractions from a case-control study of Salmonella enterica serotype Enteritidis infections","volume":"143","author":"Gu","year":"2015","journal-title":"Epidemiol Infect"},{"key":"2025120519013834000_8.1.e018252.52","doi-asserted-by":"publisher","DOI":"10.1207\/S15324796ABM2603_02"},{"key":"2025120519013834000_8.1.e018252.53","doi-asserted-by":"crossref","first-page":"3808","DOI":"10.1118\/1.2776669","article-title":"Investigation of the support vector machine algorithm to predict lung radiation-induced pneumonitis","volume":"34","author":"Chen","year":"2007","journal-title":"Med Phys"},{"key":"2025120519013834000_8.1.e018252.54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2012.01.004"},{"key":"2025120519013834000_8.1.e018252.55","doi-asserted-by":"crossref","unstructured":"Du Hongle LQ , Jing C . Reduce the samples for svm based on euclidean distance. 3rd International Conference on System Science, Engineering Design and Manufacturing Informatization, 2013.","DOI":"10.1109\/ICSSEM.2012.6340770"},{"key":"2025120519013834000_8.1.e018252.56","first-page":"67","article-title":"Sample reduction using recursive and segmented data structure analysis","volume":"59","author":"Laskar FAT","year":"2011","journal-title":"J Eng Comput Innov"},{"key":"2025120519013834000_8.1.e018252.57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2006.01.014"},{"key":"2025120519013834000_8.1.e018252.58","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-6-57"},{"key":"2025120519013834000_8.1.e018252.59","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(01)00476-0"},{"key":"2025120519013834000_8.1.e018252.60","doi-asserted-by":"crossref","first-page":"186","DOI":"10.4258\/hir.2016.22.3.186","article-title":"Interpretation of clinical data based on C4.5 algorithm for the diagnosis of coronary heart disease","volume":"22","author":"Wiharto","year":"2016","journal-title":"Healthc Inform Res"},{"key":"2025120519013834000_8.1.e018252.61","doi-asserted-by":"crossref","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random Forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J Insur Med"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2017-018252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T03:01:54Z","timestamp":1764990114000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2017-018252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,1,5]]},"published-print":{"date-parts":[[2018,1]]}},"alternative-id":["10.1136\/bmjopen-2017-018252"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2017-018252","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}