{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T23:54:25Z","timestamp":1781826865265,"version":"3.54.5"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T00:00:00Z","timestamp":1640304000000},"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:p><jats:bold>Background:<\/jats:bold> There is a high incidence of acute respiratory failure (ARF) in moderate or severe traumatic brain injury (M-STBI), worsening outcomes. This study aimed to design a predictive model for ARF.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> Adult patients with M-STBI [3 \u2264 Glasgow Coma Scale (GCS) \u2264 12] with a definite history of brain trauma and abnormal head on CT images, obtained from September 2015 to May 2017, were included. Patients with age &amp;gt;80 years or &amp;lt;18 years, multiple injuries with TBI upon admission, or pregnancy (in women) were excluded. Two models based on machine learning extreme gradient boosting (XGBoost) or logistic regression, respectively, were developed for predicting ARF within 48 h upon admission. These models were evaluated by out-of-sample validation. The samples were assigned to the training and test sets at a ratio of 3:1.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> In total, 312 patients were analyzed including 132 (42.3%) patients who had ARF. The GCS and the Marshall CT score, procalcitonin (PCT), and C-reactive protein (CRP) on admission significantly predicted ARF. The novel machine learning XGBoost model was superior to logistic regression model in predicting ARF [area under the receiver operating characteristic (AUROC) = 0.903, 95% CI, 0.834\u20130.966 vs. AUROC = 0.798, 95% CI, 0.697\u20130.899; <jats:italic>p<\/jats:italic> &amp;lt; 0.05].<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> The XGBoost model could better predict ARF in comparison with logistic regression-based model. Therefore, machine learning methods could help to develop and validate novel predictive models.<\/jats:p>","DOI":"10.3389\/fmed.2021.793230","type":"journal-article","created":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T06:00:28Z","timestamp":1640325628000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Machine Learning Model for Predicting Acute Respiratory Failure in Individuals With Moderate-to-Severe Traumatic Brain Injury"],"prefix":"10.3389","volume":"8","author":[{"given":"Rui Na","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi Xuan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fu Ping","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi Peng","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming Sheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,12,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s11606-006-0254-1","article-title":"Association of postoperative complications with hospital costs and length of stay in a tertiary care center","volume":"21","author":"Khan","year":"2006","journal-title":"J Gen Intern Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1378\/chest.11-0466","article-title":"Development and validation of a risk calculator predicting postoperative respiratory failure","volume":"140","author":"Gupta","year":"2011","journal-title":"Chest"},{"key":"B3","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1097\/EJA.0000000000000223","article-title":"Development and validation of a score to predict postoperative respiratory failure in a multicentre European cohort: a prospective, observational study","volume":"32","author":"Canet","year":"2015","journal-title":"Eur J Anaesthesiol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1007\/s13304-020-00892-6","article-title":"Predicting primary postoperative pulmonary complications in patients undergoing minimally invasive surgery for colorectal cancer","volume":"72","author":"Abd El Aziz","year":"2020","journal-title":"Updates Surg"},{"key":"B5","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1186\/s13018-018-0975-y","article-title":"Risk factors predicting prognosis and outcome of elderly patients with isolated traumatic brain injury","volume":"13","author":"Ostermann","year":"2018","journal-title":"J Orthop Surg Res"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e0190683","DOI":"10.1371\/journal.pone.0190683","article-title":"Impact of grouping complications on mortality in traumatic brain injury: a nationwide population-based study","volume":"13","author":"Ho","year":"2018","journal-title":"PLoS ONE"},{"key":"B7","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s40560-015-0113-4","article-title":"Demographic and clinical risk factors associated with hospital mortality after isolated severe traumatic brain injury: a cohort study","volume":"3","author":"Krishnamoorthy","year":"2015","journal-title":"J Intensive Care"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1002\/lt.26318","article-title":"Acute graft-versus-host disease following orthotopic liver transplantation: predicting this rare complication using machine learning","author":"Cooper","year":"2021","journal-title":"Liver Transpl."},{"key":"B9","doi-asserted-by":"publisher","first-page":"e2030913","DOI":"10.1001\/jamanetworkopen.2020.30913","article-title":"Development and validation of a machine learning model to predict near-term risk of iatrogenic hypoglycemia in hospitalized patients","volume":"4","author":"Mathioudakis","year":"2021","journal-title":"JAMA Netw Open"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1213\/ANE.0000000000004630","article-title":"Early detection of heart failure with reduced ejection fraction using perioperative data among noncardiac surgical patients: a machine-learning approach","volume":"130","author":"Mathis","year":"2020","journal-title":"Anesth Analg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1213\/ANE.0000000000004988","article-title":"Machine learning applied to registry data: development of a patient-specific prediction model for blood transfusion requirements during craniofacial surgery using the pediatric craniofacial perioperative registry dataset","volume":"132","author":"Jalali","year":"2021","journal-title":"Anesth Analg"},{"key":"B12","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1186\/s13054-019-2411-z","article-title":"Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care","volume":"23","author":"Zhang","year":"2019","journal-title":"Crit Care"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1080\/02699052.2021.1959060","article-title":"Machine learning model to predict ventilator associated pneumonia in patients with traumatic brain injury: the C.5 decision tree approach","volume":"35","author":"Abujaber","year":"2021","journal-title":"Brain Inj"},{"key":"B14","doi-asserted-by":"publisher","first-page":"152","DOI":"10.21037\/atm.2019.03.29","article-title":"Predictive analytics with gradient boosting in clinical medicine","volume":"7","author":"Zhang","year":"2019","journal-title":"Ann Transl Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"E756","DOI":"10.1093\/neuros\/nyz145","article-title":"Machine learning algorithm identifies patients at high risk for early complications after intracranial tumor surgery: registry-based cohort study","volume":"85","author":"van Niftrik","year":"2019","journal-title":"Neurosurgery"},{"key":"B16","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B17","doi-asserted-by":"publisher","first-page":"S400","DOI":"10.1093\/cid\/ciaa1518","article-title":"A ventilator-associated pneumonia prediction model in patients with acute respiratory distress syndrome","volume":"71","author":"Wu","year":"2020","journal-title":"Clin Infect Dis"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-014-0241-z","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement","volume":"13","author":"Collins","year":"2015","journal-title":"BMC Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.2139\/ssrn.3588558","article-title":"Development and validation of a prediction model for severe respiratory failure in hospitalized patients with SARS-CoV-2 infection: a multicentre cohort study (PREDI-CO study)","volume":"26","author":"Bartoletti","year":"2020","journal-title":"Clin Microbiol Infect"},{"key":"B20","doi-asserted-by":"publisher","first-page":"136","DOI":"10.21037\/atm.2016.03.35","article-title":"Variable selection with stepwise and best subset approaches","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann Transl Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.jcrc.2020.07.019","article-title":"Supervised machine learning for the early prediction of acute respiratory distress syndrome (ARDS)","volume":"60","author":"Le","year":"2020","journal-title":"J Crit Care"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1016\/j.chest.2018.01.006","article-title":"Outcomes and mortality prediction model of critically ill adults with acute respiratory failure and interstitial lung disease","volume":"153","author":"Gannon","year":"2018","journal-title":"Chest"},{"key":"B23","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1378\/chest.07-2800","article-title":"Relevance of lung ultrasound in the diagnosis of acute respiratory failure: the BLUE protocol","volume":"134","author":"Lichtenstein","year":"2008","journal-title":"Chest"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1089\/neu.2011.1867","article-title":"Post-traumatic hypoxia exacerbates neuronal cell death in the hippocampus","volume":"29","author":"Feng","year":"2012","journal-title":"J Neurotrauma"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.1097\/CCM.0000000000002619","article-title":"Brain Oxygen optimization in severe traumatic brain injury phase-II: a phase II randomized trial","volume":"45","author":"Okonkwo","year":"2017","journal-title":"Crit Care Med"},{"key":"B26","first-page":"19","article-title":"Prediction of long-term ventilatory support in trauma patients","volume":"62","author":"Ross","year":"1996","journal-title":"Am Surg"},{"key":"B27","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1080\/15563650.2016.1222616","article-title":"The need for ICU admission in intoxicated patients: a prediction model","volume":"55","author":"Brandenburg","year":"2017","journal-title":"Clin Toxicol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1007\/s00508-017-1182-2","article-title":"Non-invasive ventilation for acute hypercapnic respiratory failure in older patients","volume":"129","author":"\u00c7iftci","year":"2017","journal-title":"Wien Klin Wochenschr"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e120","DOI":"10.1016\/j.wneu.2019.09.143","article-title":"Chitinase-3-like protein 1, serum amyloid A1, C-reactive protein, and procalcitonin are promising biomarkers for intracranial severity assessment of traumatic brain injury: relationship with glasgow coma scale and computed tomography volumetry","volume":"134","author":"Carabias","year":"2020","journal-title":"World Neurosurg"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1007\/s12028-021-01298-x","article-title":"A one-day prospective national observational study on sedation-analgesia of patients with brain injury in French Intensive Care Units: the SEDA-BIP-ICU (Sedation-Analgesia in Brain Injury Patient in ICU) Study","author":"Poignant","year":"2021","journal-title":"Neurocrit Care."},{"key":"B31","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1007\/s00415-021-10396-x","article-title":"Clinical features and outcome of patients with primary central nervous system lymphoma admitted to the intensive care unit: a French national expert center experience","volume":"268","author":"Decav\u00e8le","year":"2021","journal-title":"J Neurol"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.793230\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T06:00:31Z","timestamp":1640325631000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.793230\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,24]]},"references-count":31,"alternative-id":["10.3389\/fmed.2021.793230"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2021.793230","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,24]]},"article-number":"793230"}}