{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T22:43:43Z","timestamp":1792622623133,"version":"4.5.0"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:00:00Z","timestamp":1731283200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017954","name":"Fujian Provincial Finance Department","doi-asserted-by":"publisher","award":["Grant No. 2022QH1086"],"award-info":[{"award-number":["Grant No. 2022QH1086"]}],"id":[{"id":"10.13039\/100017954","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>People with traumatic brain injury (TBI) are at high risk for infection and sepsis. The aim of the study was to develop and validate an explainable machine learning(ML) model based on clinical features for early prediction of the risk of sepsis in TBI patients.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We enrolled all patients with TBI in the Medical Information Mart for Intensive Care IV database from 2008 to 2019. All patients were randomly divided into a training set (70%) and a test set (30%). The univariate and multivariate regression analyses were used for feature selection. Six ML methods were applied to develop the model. The predictive performance of different models were determined based on the area under the curve (AUC) and calibration curves in the test cohort. In addition, we selected the eICU Collaborative Research Database version 1.2 as the external validation dataset. Finally, we used the Shapley additive interpretation to account for the effects of features attributed to the model.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Of the 1555 patients enrolled in the final cohort, 834 (53.6%) patients developed sepsis after TBI. Six variables were associated with concomitant sepsis and were used to develop ML models. Of the 6 models constructed, the Extreme Gradient Boosting (XGB) model achieved the best performance with an AUC of 0.807 and an accuracy of 74.5% in the internal validation cohort, and an AUC of 0.762 for the external validation. Feature importance analysis revealed that use mechanical ventilation, SAPSII score, use intravenous pressors, blood transfusion on admission, history of diabetes, and presence of post-stroke sequelae were the top six most influential features of the XGB model.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>As shown in the study, the ML model could be used to predict the occurrence of sepsis in patients with TBI in the intensive care unit.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0313132","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:34:49Z","timestamp":1731350089000},"page":"e0313132","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["Explainable machine learning for early prediction of sepsis in traumatic brain injury: A discovery and validation study"],"prefix":"10.1371","volume":"19","author":[{"given":"Wenchi","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weizhi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6120-8689","authenticated-orcid":true,"given":"Qiaoyi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,11,11]]},"reference":[{"issue":"5","key":"pone.0313132.ref001","doi-asserted-by":"crossref","first-page":"535","DOI":"10.23736\/S0390-5616.18.04532-0","article-title":"Epidemiology of severe traumatic brain injury","volume":"62","author":"C Iaccarino","year":"2018","journal-title":"J Neurosurg Sci"},{"issue":"11","key":"pone.0313132.ref002","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1016\/S1474-4422(22)00309-X","article-title":"Traumatic brain injury: progress and challenges in prevention, clinical care, and research","volume":"21","author":"AIR Maas","year":"2022","journal-title":"Lancet Neurol"},{"key":"pone.0313132.ref003","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.bbi.2019.04.034","article-title":"Infections after a traumatic brain injury: The complex interplay between the immune and neurological systems","volume":"79","author":"R Sharma","year":"2019","journal-title":"Brain, Behavior, and Immunity"},{"issue":"10141","key":"pone.0313132.ref004","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/S0140-6736(18)30696-2","article-title":"Sepsis and septic shock","volume":"392","author":"M Cecconi","year":"2018","journal-title":"Lancet"},{"issue":"8","key":"pone.0313132.ref005","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (Sepsis-3)","volume":"315","author":"M Singer","year":"2016","journal-title":"JAMA"},{"key":"pone.0313132.ref006","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/2046-4053-2-68","article-title":"Incidence, prevalence, and occurrence rate of infection among adults hospitalized after traumatic brain injury: study protocol for a systematic review and meta-analysis","volume":"2","author":"NVS Brittney","year":"2013","journal-title":"Systematic Reviews"},{"issue":"6","key":"pone.0313132.ref007","doi-asserted-by":"crossref","first-page":"355","DOI":"10.5492\/wjccm.v10.i6.355","article-title":"Sequential organ failure assessment score is superior to other prognostic indices in acute pancreatitis","volume":"10","author":"TZJ Teng","year":"2021","journal-title":"World J Crit Care Med"},{"issue":"4","key":"pone.0313132.ref008","first-page":"158","article-title":"Classifying sepsis patients in the emergency department using SIRS, qSOFA or MEWS","volume":"76","author":"SW Woude","year":"2018","journal-title":"Neth J Med"},{"issue":"1","key":"pone.0313132.ref009","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1515\/jomb-2017-0039","article-title":"A new marker to Determine Prognosis of Acute Pancreatitis: PLR and NLR Combination","volume":"37","author":"M Kaplan","year":"2018","journal-title":"J Med Biochem"},{"issue":"1","key":"pone.0313132.ref010","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s13049-017-0399-4","article-title":"Poor performance of quick-SOFA (qSOFA) score in predicting severe sepsis and mortality\u2014a prospective study of patients admitted with infection to the emergency department","volume":"25","author":"\u00c3 Askim","year":"2017","journal-title":"Scand J Trauma Resusc Emerg Med"},{"issue":"26","key":"pone.0313132.ref011","doi-asserted-by":"crossref","first-page":"2588","DOI":"10.1056\/NEJMc1906060","article-title":"Machine learning in medicine","volume":"380","author":"M Fralick","year":"2019","journal-title":"N Engl J Med"},{"issue":"12","key":"pone.0313132.ref012","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.1016\/j.ophtha.2017.08.046","article-title":"Machine learning has arrived","volume":"124","author":"A Lee","year":"2017","journal-title":"Ophthalmology"},{"key":"pone.0313132.ref013","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1007\/s40121-022-00628-6","article-title":"Interpretable Machine Learning for Early Prediction of Prognosis in Sepsis: A Discovery and Validation Study","volume":"11","author":"C Hu","year":"2022","journal-title":"Infect Dis Ther"},{"key":"pone.0313132.ref014","unstructured":"Johnson A, Bulgarelli L, Pollard T, Horng S, Celi LA, Mark R. Mimic-iv. PhysioNet. Available online at: https:\/\/physionet.org\/content\/mimiciv\/1.0\/. (Accessed 23 Aug 2021), 2020."},{"key":"pone.0313132.ref015","doi-asserted-by":"crossref","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative Research Database, a freely available multi-center database for critical care research","volume":"5","author":"TJ Pollard","year":"2018","journal-title":"Scientific Data"},{"issue":"Suppl 1","key":"pone.0313132.ref016","first-page":"67","article-title":"SEPSIS DEFINITION: WHAT\u2019S NEW IN THE TREATMENT GUIDELINES","volume":"61","author":"I Srzi\u0107","year":"2022","journal-title":"Acta Clin Croat"},{"issue":"1","key":"pone.0313132.ref017","doi-asserted-by":"crossref","first-page":"3","DOI":"10.2174\/1574887117666220826164723","article-title":"Invasive Mechanical Ventilation in Traumatic Brain Injured Patients with Acute Respiratory Failure","volume":"18","author":"Fabrizio Racca","year":"2023","journal-title":"Rev Recent Clin Trials"},{"issue":"1","key":"pone.0313132.ref018","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/s12028-019-00773-w","article-title":"Incidence, risk factors, and outcomes of ventilator-associate pneumonia in traumatic brain injury: a meta-analysis","volume":"32","author":"YT Li","year":"2020","journal-title":"Neurocrit Care"},{"issue":"45","key":"pone.0313132.ref019","first-page":"e23151","volume":"99","author":"L Zhao","year":"2020","journal-title":"Platelets as a prognostic marker for sepsis: A cohort study from the MIMIC-III database"},{"issue":"1","key":"pone.0313132.ref020","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1186\/s12874-022-01664-z","article-title":"Machine learning approach for the prediction of 30-day mortality in patients with sepsis-associated encephalopathy [J]","volume":"22","author":"LW Peng","year":"2022","journal-title":"BMC medical research methodology"},{"issue":"1","key":"pone.0313132.ref021","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1186\/s13054-017-1673-6","article-title":"Determinants of the calibration of SAPS II and SAPS 3 mortality scores in intensive care: a European multicenter study","volume":"21","author":"A Poncet","year":"2017","journal-title":"Critical care"},{"issue":"2","key":"pone.0313132.ref022","doi-asserted-by":"crossref","first-page":"107","DOI":"10.5114\/ait.2019.86275","article-title":"Validation of APACHE II and SAPS II scales at the intensive care unit along with assessment of SOFA scale at the admission as an isolated risk of death predictor","volume":"51","author":"I Kadziolka","year":"2019","journal-title":"Anaesthesiology intensive therapy"},{"issue":"2","key":"pone.0313132.ref023","first-page":"95","article-title":"Predicting scores correlations in patients with septic shock\u2014a cohort study","volume":"21","author":"AM Georgescu","year":"2014","journal-title":"Rom J Anaesth Intensive Care"},{"issue":"4","key":"pone.0313132.ref024","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1097\/SLA.0000000000000653","article-title":"Association between gene expression biomarkers of immunosuppression and blood transfusion in severely injured polytrauma patients","volume":"261","author":"HD Torrance","year":"2015","journal-title":"Ann Surg"},{"issue":"2","key":"pone.0313132.ref025","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1007\/s12011-014-0225-z","article-title":"Analysis of blood trace elements and biochemical indexes levels in severe craniocerebral trauma adults with Glasgow Coma Scale and Injury Severity Score","volume":"164","author":"GT Xu","year":"2015","journal-title":"Biol Trace Elem Res"},{"issue":"7","key":"pone.0313132.ref026","doi-asserted-by":"crossref","first-page":"2500","DOI":"10.2337\/db12-1726","article-title":"Concentration and activity of the soluble form of the interleukin-7 receptor \u03b1 in type 1 diabetes identifies an interplay between hyperglycemia and immune function","volume":"62","author":"P Monti","year":"2013","journal-title":"Diabetes"},{"issue":"3","key":"pone.0313132.ref027","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1097\/SHK.0000000000000778","article-title":"Diabetes mellitus and sepsis: a challenging association","volume":"47","author":"SC Trevelin","year":"2017","journal-title":"Shock"},{"issue":"1","key":"pone.0313132.ref028","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1186\/s13054-018-2164-0","article-title":"Focal ischemic stroke leads to lung injury and reduces alveolar macrophage phagocytic capability in rats","volume":"22","author":"CS Samary","year":"2018","journal-title":"Crit Care"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0313132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:35:00Z","timestamp":1731350100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0313132"}},"subtitle":[],"editor":[{"given":"Amirmohammad","family":"Khalaji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,11,11]]},"references-count":28,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,11,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0313132","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,11]]}}}