{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T14:12:15Z","timestamp":1785161535901,"version":"3.55.0"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop and externally evaluate a machine learning (ML)-based predictive model for incident delirium in patients with traumatic brain injury (TBI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients diagnosed with TBI from the MIMIC-IV and eICU-CRD databases were included. Predictors were selected using Boruta and LASSO regression. Five ML algorithms were developed and compared, with logistic recalibration applied to the external cohort. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). Shapley Additive Explanations (SHAP) was utilized to decode individual risk contributions. Subgroup and sensitivity analyses were conducted to define clinical boundaries and evaluate model robustness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A total of 915 TBI patients from the MIMIC-IV database and 317 from the eICU-CRD database were included. Random Forest (RF) model achieved balanced performance with an internal AUC of 0.819 and an external AUC of 0.706. The model exhibited favorable internal calibration, adequate external recalibration, and positive clinical net benefits (internal: 0.155, external: 0.080). Overall SHAP analysis identified invasive ventilation, Glasgow Coma Scale (GCS), extracranial injury, Acute Physiology Score III (APSIII), hemoglobin and mixed intra-\/extra-axial injury as primary predictors. Crucially, stratified SHAP analysis identified invasive ventilation as the primary driver across all strata, with baseline GCS scores attaining their maximum predictive weight in the medium-risk tier. Subgroup analyses of the external cohort indicated robust generalization in younger patients (AUC = 0.780) and those with extracranial injuries (AUC = 0.762), with expected attenuation in subgroups with higher clinical severity (AUC: 0.578\u20130.589). Sensitivity analyses confirmed the model's stable performance against competing mortality and missing data (all DeLong test\n                      <jats:italic>p<\/jats:italic>\n                      &amp;gt; 0.05).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The RF model demonstrated acceptable discriminative capacity and clinical utility for early delirium prediction in patients with TBI. Supported by SHAP, it translated complex predictions into an actionable three-tiered framework, serving as a valuable adjunct for guiding early monitoring and neuroprotective strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1848730","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:10:16Z","timestamp":1779372616000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Early prediction of incident delirium in traumatic brain injury: a multicenter validated and interpretable machine learning approach"],"prefix":"10.3389","volume":"17","author":[{"given":"Cheng","family":"Li","sequence":"first","affiliation":[{"name":"Graduate School of PLA General Hospital, PLA General Hospital","place":["Beijing, China"]},{"name":"Department of Medical Innovation and Research, PLA General Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Medical Innovation and Research, PLA General Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate School of Capital Medical University, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouli","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Beijing Fangshan District Liangxiang Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Medical Psychology, Ninth Medical Center of PLA General Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixiang","family":"Huan","sequence":"additional","affiliation":[{"name":"Graduate School of PLA General Hospital, PLA General Hospital","place":["Beijing, China"]},{"name":"Department of Medical Innovation and Research, PLA General Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Medical Innovation and Research, PLA General Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Medical Innovation and Research, PLA General Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"16084","DOI":"10.1038\/nrdp.2016.84","article-title":"Traumatic brain injuries","volume":"2","author":"Blennow","year":"2016","journal-title":"Nat Rev Dis Primers."},{"key":"B2","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/S2213-2600(24)00077-8","article-title":"Long-term outcomes after treatment of delirium during critical illness with antipsychotics (MIND-USA): a randomized, placebo-controlled, phase 3 trial","volume":"12","author":"Mart","year":"2024","journal-title":"Lancet Respir Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"632","DOI":"10.23736\/S0375-9393.18.12294-2","article-title":"Delirium and agitation in traumatic brain injury patients: an update on pathological hypotheses and treatment options","volume":"84","author":"Ganau","year":"2018","journal-title":"Minerva Anestesiol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.mayocp.2017.11.005","article-title":"Potentially modifiable risk factors for long-term cognitive impairment after critical illness: a systematic review","volume":"93","author":"Sakusic","year":"2018","journal-title":"Mayo Clin Proc."},{"key":"B5","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/s12028-022-01666-1","article-title":"Prevalence and risk factors for intensive care unit delirium after traumatic brain injury: a retrospective cohort study","volume":"38","author":"Wilson","year":"2023","journal-title":"Neurocrit Care"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1007\/s00701-019-03927-z","article-title":"The predisposing and precipitating risk factors for delirium in neurosurgery: a prospective cohort study of 949 patients","volume":"161","author":"Zipser","year":"2019","journal-title":"Acta Neurochir."},{"key":"B7","doi-asserted-by":"publisher","first-page":"251","DOI":"10.3233\/JAD-170339","article-title":"Prevalence of delirium in a population of elderly outpatients with dementia: a retrospective study","volume":"61","author":"Addesi","year":"2018","journal-title":"J Alzheimers Dis"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e232","DOI":"10.1016\/S2666-7568(22)00013-7","article-title":"The effect of baseline cognition and delirium on long-term cognitive impairment and mortality: a prospective population-based study","volume":"3","author":"Tsui","year":"2022","journal-title":"Lancet Healthy Longev."},{"key":"B9","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s00134-013-3202-7","article-title":"Boogaard, M, Schoonhoven, L, Maseda, E, Plowright, C, Jones, C, Luetz, A, et al. Recalibration of the delirium prediction model for ICU patients (PRE-DELIRIC): a multinational observational study","volume":"40","author":"Van","year":"2014","journal-title":"Intensive Care Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e14690","DOI":"10.1590\/1414-431x2025e14690","article-title":"Retrospective evaluation of the PRE-DELIRIC score in a Chinese mixed ICU: implications for nursing practice","volume":"58","author":"Yuan","year":"2025","journal-title":"Braz J Med Biol Res."},{"key":"B11","doi-asserted-by":"publisher","first-page":"e589","DOI":"10.1002\/ams2.589","article-title":"Utility of a prediction model for delirium in intensive care unit patients (PRE-DELIRIC) in mechanically ventilated patients with sepsis","volume":"7","author":"Miyamoto","year":"2020","journal-title":"Acute Med Surg."},{"key":"B12","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1111\/aas.14363","article-title":"Validation of PRE-DELIRIC and E-PRE-DELIRIC in a Danish population of intensive care unit patients-A prospective observational multicenter study","volume":"68","author":"Anton Joseph","year":"2024","journal-title":"Acta Anaesthesiol Scand."},{"key":"B13","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s40560-025-00800-3","article-title":"Validation of prediction of delirium in ICU patients (PRE-DELIRIC) model for ICU delirium in general ICU and patients with liver disease: a retrospective cohort study","volume":"13","author":"Papadopoulou","year":"2025","journal-title":"J Intensive Care."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.1186\/s12879-024-10380-6","article-title":"Machine learning for the prediction of mortality in patients with sepsis-associated acute kidney injury: a systematic review and meta-analysis","volume":"24","author":"Lv","year":"2024","journal-title":"BMC Infect Dis."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1513732","DOI":"10.3389\/fneur.2025.1513732","article-title":"Interpretable machine learning for early predicting the risk of ventilator-associated pneumonia in ischemic stroke patients in the intensive care unit","volume":"16","author":"Cao","year":"2025","journal-title":"Front Neurol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"106008","DOI":"10.1016\/j.ijmedinf.2025.106008","article-title":"Performance of machine and deep learning models for predicting delirium in adult ICU patients: a systematic review","volume":"203","author":"Al-Jabri","year":"2025","journal-title":"Int J Med Inform."},{"key":"B17","doi-asserted-by":"publisher","first-page":"4968","DOI":"10.1111\/jan.70154","article-title":"Development and validation of a machine learning-based risk prediction model for delirium in older inpatients: a prospective cohort study","volume":"82","author":"Zhou","year":"2025","journal-title":"J Adv Nurs"},{"key":"B18","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1186\/s12888-025-07299-w","article-title":"A Bayesian network-based predictive model for postoperative delirium following coronary artery bypass grafting","volume":"25","author":"Xu","year":"2025","journal-title":"BMC Psychiatry."},{"key":"B19","volume-title":"MIMIC-IV (version 3.1)","author":"Johnson","year":"2024"},{"key":"B20","volume-title":"eICU Collaborative Research Database (version 2.0)","author":"Pollard","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e67258","DOI":"10.2196\/67258","article-title":"Development of a machine learning-based predictive model for postoperative delirium in older adult intensive care unit patients: retrospective study","volume":"27","author":"Li","year":"2025","journal-title":"J Med Internet Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/EMBC46164.2021.9630040","article-title":"ReLearn: a robust machine learning framework in presence of missing data for multimodal stress detection from physiological signals","volume":"2021","author":"Iranfar","year":"2021","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc."},{"key":"B23","doi-asserted-by":"publisher","first-page":"87","DOI":"10.14283\/jpad.2020.7","article-title":"A machine learning framework for assessment of cognitive and functional impairments in alzheimer's disease: data preprocessing and analysis","volume":"7","author":"Vinutha","year":"2020","journal-title":"J Prev Alzheimers Dis."},{"key":"B24","first-page":"00131644251377381","article-title":"An evaluation of the replicable factor analytic solutions algorithm for variable selection: a simulation study","volume":"3","author":"Sass","year":"2025","journal-title":"Educ Psychol Meas Nov."},{"key":"B25","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1111\/ppe.12948","article-title":"Recalibrating prognostic models to improve predictions of in-hospital child mortality in resource-limited settings","volume":"37","author":"Ogero","year":"2023","journal-title":"Paediatr Perinat Epidemiol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.1001\/jamainternmed.2020.2033","article-title":"Development and validation of a clinical risk score to predict the occurrence of critical illness in hospitalized patients with COVID-19","volume":"180","author":"Liang","year":"2020","journal-title":"JAMA Intern Med."},{"key":"B27","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.aucc.2022.01.010","article-title":"Predicting hospital mortality and length of stay: a prospective cohort study comparing the intensive care delirium screening checklist versus confusion assessment method for the intensive care unit","volume":"36","author":"Li","year":"2023","journal-title":"Aust Crit Care."},{"key":"B28","doi-asserted-by":"publisher","first-page":"639","DOI":"10.3390\/brainsci15060639","article-title":"Bridging the gap: missing data imputation methods and their effect on dementia classification performance","volume":"15","author":"Aracri","year":"2025","journal-title":"Brain Sci."},{"key":"B29","doi-asserted-by":"publisher","first-page":"glaf200","DOI":"10.1093\/gerona\/glaf200","article-title":"Development and validation of a machine learning-based risk prediction model for postoperative delirium in older patients with hip fracture","volume":"80","author":"Zhang","year":"2025","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"12697","DOI":"10.1038\/s41598-023-38650-4","article-title":"Development of a machine learning-based prediction model for sepsis-associated delirium in the intensive care unit","volume":"13","author":"Zhang","year":"2023","journal-title":"Sci Rep."},{"key":"B31","doi-asserted-by":"publisher","first-page":"2514186","DOI":"10.1080\/0886022X.2025.2514186","article-title":"A machine learning-based prediction model for sepsis-associated delirium in intensive care unit patients with sepsis-associated acute kidney injury","volume":"47","author":"Yu","year":"2025","journal-title":"Ren Fail."},{"key":"B32","doi-asserted-by":"publisher","first-page":"e73283","DOI":"10.2196\/73283","article-title":"Early prediction of delirium in postcardiac surgery patients: machine learning model development and external validation","volume":"14","author":"Hu","year":"2026","journal-title":"JMIR Med Inform."},{"key":"B33","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1177\/00131644221081867","article-title":"Range restriction affects factor analysis: normality, estimation, fit, loadings, and reliability","volume":"83","author":"Franco-Mart\u00ednez","year":"2023","journal-title":"Educ Psychol Meas."},{"key":"B34","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1007\/s12028-024-02200-1","article-title":"Sedation practices in mechanically ventilated neurocritical care patients from 19 countries: an international cohort study","volume":"43","author":"Feng","year":"2025","journal-title":"Neurocrit Care."},{"key":"B35","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1186\/s12871-025-03202-y","article-title":"Acute hyperammonemic encephalopathy masquerading as postoperative delirium in a patient who underwent lung surgery: a case report","volume":"25","author":"Chen","year":"2025","journal-title":"BMC Anesthesiol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.jaclp.2020.12.005","article-title":"Development and external validation of a delirium prediction model for hospitalized patients with coronavirus disease 2019","volume":"62","author":"Castro","year":"2021","journal-title":"J Acad Consult Liaison Psychiatry"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e6118","DOI":"10.1097\/GOX.0000000000006118","article-title":"Multicenter validation of a novel prediction model for elbow flexion recovery after nerve transfer surgery in brachial plexus injuries","volume":"12","author":"Laohaprasitiporn","year":"2024","journal-title":"Plast Reconstr Surg Glob Open."},{"key":"B38","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1016\/j.eururo.2018.08.038","article-title":"Reporting and interpreting decision curve analysis: a guide for investigators","volume":"74","author":"Van Calster","year":"2018","journal-title":"Eur Urol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"573","DOI":"10.5847\/wjem.j.1920-8642.2025.118","article-title":"Incidence and risk factors for delirium in critically ill patients with severe acute pancreatitis: a multicenter cohort study","volume":"16","author":"Da","year":"2025","journal-title":"World J Emerg Med."},{"key":"B40","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1002\/glia.22350","article-title":"Microglia and neurodegeneration: the role of systemic inflammation","volume":"61","author":"Cunningham","year":"2013","journal-title":"Glia."},{"key":"B41","doi-asserted-by":"publisher","first-page":"4981","DOI":"10.2147\/JIR.S358621","article-title":"Prognostic value of serum procalcitonin based model in moderate to severe traumatic brain injury patients","volume":"15","author":"Wang","year":"2022","journal-title":"J Inflamm Res."},{"key":"B42","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1002\/gps.5086","article-title":"Intraoperative blood transfusion predicts postoperative delirium among older patients undergoing elective orthopedic surgery: a prospective cohort study","volume":"34","author":"Chou","year":"2019","journal-title":"Int J Geriatr Psychiatry."},{"key":"B43","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/s00134-008-1296-0","article-title":"Dexmedetomidine versus propofol\/midazolam for long-term sedation during mechanical ventilation","volume":"35","author":"Ruokonen","year":"2009","journal-title":"Intensive Care Med."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1016\/j.joms.2015.01.011","article-title":"Effect of dexmedetomidine on preventing agitation and delirium after microvascular free flap surgery: a randomized, double-blind, control study","volume":"73","author":"Yang","year":"2015","journal-title":"J Oral Maxillofac Surg."},{"key":"B45","doi-asserted-by":"publisher","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."}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1848730\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:10:17Z","timestamp":1779372617000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1848730\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":45,"alternative-id":["10.3389\/fneur.2026.1848730"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1848730","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]},"article-number":"1848730"}}