{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T22:46:40Z","timestamp":1776725200193,"version":"3.51.2"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Wuxi Science and Technology Association project","award":["KX-23-C165"],"award-info":[{"award-number":["KX-23-C165"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>This study aimed to develop models for predicting the 30-day mortality of sepsis-associated delirium (SAD) by multiple machine learning (ML) algorithms. On the whole, a cohort of 3,197 SAD patients were collected from the Medical Information Mart for Intensive Care (MIMIC)-IV database. Among them, a total of 659 (20.61%) patients died following SAD. The patients who died were about 73.00 (62.00, 82.00) years old and mostly male (56.75%). Recursive feature elimination (RFE) was used to distinguish risk factors. Subsequently, six ML algorithms including artificial neural network (NNET), gradient boosting machine (GBM), adaptive boosting (Ada), random forest (RF), eXtreme Gradient Boosting (XGB) and logistic regression (LR) were employed to establish models to predict the 30-day mortality of SAD. The performance of models was assessed via both discrimination and calibration by cross-validation with 100 resamples. Overall, 10 independent predictors, including Glasgow Coma Scale (GCS), Sequential Organ Failure Assessment (SOFA), anion gap (AG), continuous renal replacement therapy (CRRT), temperature, mean corpuscular hemoglobin concentration (MCHC), vasopressor, blood urea nitrogen (BUN), base excess (BE), and bicarbonate were identified as independent predictors for the 30-day mortality of SAD. The validation cohort demonstrated that all these six models had relatively favorable differentiation, while among them, the GBM model had the highest area under the curve (AUC) of 0.845 (95% Confidence Interval (CI): 0.816, 0.874). Furthermore, the calibration curve of these six models was close to the diagonal line in the validation sets. As for decision curve analysis, the predictive models were clinically useful as well. Based on real-world research, we developed ML models to provide personalized predictions of delirium-related mortality in sepsis patients, potentially enabling clinicians to identify high-risk SAD patients more promptly.<\/jats:p>","DOI":"10.1371\/journal.pone.0319519","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T17:26:20Z","timestamp":1744219580000},"page":"e0319519","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Machine learning approach for the prediction of 30-day mortality in patients with sepsis-associated delirium"],"prefix":"10.1371","volume":"20","author":[{"given":"Xiaoli","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongfeng","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weize","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3104-0362","authenticated-orcid":true,"given":"Shuyan","family":"Ru","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"issue":"10","key":"pone.0319519.ref001","first-page":"S331-6","article-title":"Sepsis-associated encephalopathy and its differential diagnosis","volume":"37","author":"E Iacobone","year":"2009","journal-title":"Crit Care Med"},{"key":"pone.0319519.ref002","doi-asserted-by":"crossref","first-page":"102844","DOI":"10.1016\/j.iccn.2020.102844","article-title":"Risk factors and outcomes of sepsis-associated delirium in intensive care unit patients: a secondary data analysis","volume":"59","author":"Y Kim","year":"2020","journal-title":"Intensive Crit Care Nurs"},{"key":"pone.0319519.ref003","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.jcrc.2019.12.018","article-title":"Incidence, risk factors, and outcomes for sepsis-associated delirium in patients with mechanical ventilation: a sub-analysis of a multicenter randomized controlled trial","volume":"56","author":"T Yamamoto","year":"2020","journal-title":"J Crit Care"},{"issue":"2","key":"pone.0319519.ref004","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1080\/14787210.2020.1812384","article-title":"Sepsis-associated encephalopathy and septic encephalitis: an update","volume":"19","author":"SC Tauber","year":"2021","journal-title":"Expert Rev Anti Infect Ther"},{"issue":"22","key":"pone.0319519.ref005","doi-asserted-by":"crossref","first-page":"2644","DOI":"10.1001\/jama.298.22.2644","article-title":"Effect of sedation with dexmedetomidine vs lorazepam on acute brain dysfunction in mechanically ventilated patients: the MENDS randomized controlled trial","volume":"298","author":"PP Pandharipande","year":"2007","journal-title":"JAMA"},{"issue":"4","key":"pone.0319519.ref006","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.3390\/jcm12041273","article-title":"Sepsis-associated delirium: a narrative review","volume":"12","author":"R Tokuda","year":"2023","journal-title":"J Clin Med"},{"issue":"6","key":"pone.0319519.ref007","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.1007\/s10753-021-01501-3","article-title":"Sepsis-associated encephalopathy and blood-brain barrier dysfunction","volume":"44","author":"Q Gao","year":"2021","journal-title":"Inflammation"},{"key":"pone.0319519.ref008","doi-asserted-by":"crossref","first-page":"h2538","DOI":"10.1136\/bmj.h2538","article-title":"Outcome of delirium in critically ill patients: systematic review and meta-analysis","volume":"350","author":"JIF Salluh","year":"2015","journal-title":"BMJ"},{"issue":"3","key":"pone.0319519.ref009","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1002\/ams2.415","article-title":"Post-intensive care syndrome: its pathophysiology, prevention, and future directions","volume":"6","author":"S Inoue","year":"2019","journal-title":"Acute Med Surg"},{"issue":"13","key":"pone.0319519.ref010","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial intelligence and machine learning in clinical medicine","volume":"388","author":"C Haug","year":"2023","journal-title":"N Engl J Med"},{"issue":"5","key":"pone.0319519.ref011","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1016\/j.arthro.2020.08.009","article-title":"Clinical and research medical applications of artificial intelligence","volume":"37","author":"PN Ramkumar","year":"2021","journal-title":"Arthroscopy"},{"issue":"3","key":"pone.0319519.ref012","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s00134-019-05872-y","article-title":"Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy","volume":"46","author":"LM Fleuren","year":"2020","journal-title":"Intensive Care Med"},{"issue":"12","key":"pone.0319519.ref013","doi-asserted-by":"crossref","first-page":"e086094","DOI":"10.1136\/bmjopen-2024-086094","article-title":"Employing artificial intelligence for optimising antibiotic dosages in sepsis on intensive care unit: a study protocol for a prospective observational study (KI.SEP)","volume":"14","author":"B Marko","year":"2024","journal-title":"BMJ Open"},{"issue":"1","key":"pone.0319519.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"AEW Johnson","year":"2023","journal-title":"Sci Data"},{"issue":"10","key":"pone.0319519.ref015","doi-asserted-by":"crossref","first-page":"e1001885","DOI":"10.1371\/journal.pmed.1001885","article-title":"The REporting of studies Conducted using Observational Routinely-collected health Data (RECORD) statement","volume":"12","author":"EI Benchimol","year":"2015","journal-title":"PLoS Med"},{"issue":"11","key":"pone.0319519.ref016","first-page":"Cd013126","article-title":"Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) for the diagnosis of delirium in adults in critical care settings","volume":"11","author":"F Miranda","year":"2023","journal-title":"Cochrane Database System Rev"},{"issue":"8","key":"pone.0319519.ref017","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.0319519.ref018","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.engappai.2017.01.013","article-title":"Metaheuristic design of feedforward neural networks: a review of two decades of research","volume":"60","author":"VK Ojha","year":"2017","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0319519.ref019","first-page":"1189","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"JH Friedman","year":"2001","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"pone.0319519.ref020","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Y Freund","year":"1997","journal-title":"J Comput Syst Sci"},{"issue":"1","key":"pone.0319519.ref021","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"M Fern\u00e1ndez-Delgado","year":"2014","journal-title":"J Mach Learn Res"},{"issue":"1","key":"pone.0319519.ref022","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1186\/s13075-024-03450-2","article-title":"XGBoost-SHAP-based interpretable diagnostic framework for knee osteoarthritis: a population-based retrospective cohort study","volume":"26","author":"Z Fan","year":"2024","journal-title":"Arthritis Res Ther"},{"key":"pone.0319519.ref023","first-page":"4768","article-title":"A unified approach to interpreting model predictions.","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"S Lundberg","year":"2017"},{"issue":"1","key":"pone.0319519.ref024","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1186\/s12911-023-02282-5","article-title":"A nomogram for predicting sepsis-associated delirium: a retrospective study in MIMIC III","volume":"23","author":"Q Gu","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"pone.0319519.ref025","doi-asserted-by":"crossref","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":"Y Zhang","year":"2023","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0319519.ref026","doi-asserted-by":"crossref","first-page":"18751","DOI":"10.1038\/s41598-024-69332-4","article-title":"Predictive model of risk factors for 28-day mortality in patients with sepsis or sepsis-associated delirium based on the MIMIC-IV database","volume":"14","author":"L Zhang","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0319519.ref027","doi-asserted-by":"crossref","first-page":"e420","DOI":"10.1136\/bmj.e420","article-title":"Development and validation of PRE-DELIRIC (PREdiction of DELIRium in ICu patients) delirium prediction model for intensive care patients: observational multicentre study","volume":"344","author":"M van den Boogaard","year":"2012","journal-title":"BMJ"},{"issue":"3","key":"pone.0319519.ref028","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1097\/ALN.0000000000004478","article-title":"Predicting intensive care delirium with machine learning: model development and external validation","volume":"138","author":"KD Gong","year":"2023","journal-title":"Anesthesiology"},{"issue":"1","key":"pone.0319519.ref029","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","volume":"22","author":"L Peng","year":"2022","journal-title":"BMC Med Res Methodol"},{"issue":"8","key":"pone.0319519.ref030","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1007\/s00134-017-4807-z","article-title":"Potentially modifiable factors contributing to sepsis-associated encephalopathy","volume":"43","author":"R Sonneville","year":"2017","journal-title":"Intensive Care Med"},{"issue":"3","key":"pone.0319519.ref031","article-title":"Enhancing predictions with a stacking ensemble model for ICU mortality risk in patients with sepsis-associated encephalopathy","volume":"52","author":"X Liu","year":"2024","journal-title":"J Int Med Res"},{"issue":"6","key":"pone.0319519.ref032","doi-asserted-by":"crossref","first-page":"120","DOI":"10.21315\/mjms2023.30.6.12","article-title":"Prevalence and outcome of sepsis: mortality and prolonged intensive care unit stay among sepsis patients admitted to a tertiary Centre in Malaysia","volume":"30","author":"KA Kari","year":"2023","journal-title":"Malays J Med Sci"},{"issue":"2","key":"pone.0319519.ref033","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1097\/SHK.0000000000000958","article-title":"Lactate and Immunosuppression in Sepsis","volume":"49","author":"B Nolt","year":"2018","journal-title":"Shock"},{"issue":"6","key":"pone.0319519.ref034","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1016\/S1474-4422(14)70017-1","article-title":"Long-term cerebral consequences of sepsis","volume":"13","author":"CN Widmann","year":"2014","journal-title":"Lancet Neurol"},{"issue":"4","key":"pone.0319519.ref035","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1016\/j.bja.2020.06.063","article-title":"Postoperative delirium: perioperative assessment, risk reduction, and management","volume":"125","author":"Z Jin","year":"2020","journal-title":"Br J Anaesth"},{"key":"pone.0319519.ref036","doi-asserted-by":"crossref","first-page":"111107","DOI":"10.1016\/j.jclinane.2023.111107","article-title":"Association between intraoperative body temperature and postoperative delirium: a retrospective observational study","volume":"87","author":"J-W Ju","year":"2023","journal-title":"J Clin Anesth"},{"issue":"6","key":"pone.0319519.ref037","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1007\/s00134-018-5218-5","article-title":"The relationship between ICU hypotension and in-hospital mortality and morbidity in septic patients","volume":"44","author":"K Maheshwari","year":"2018","journal-title":"Intensive Care Med"},{"key":"pone.0319519.ref038","first-page":"1328729","article-title":"Sepsis-induced brain dysfunction: pathogenesis, diagnosis, and treatment","author":"S Pan","year":"2022","journal-title":"Oxid Med Cell Longev"},{"key":"pone.0319519.ref039","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.jneuroim.2017.02.001","article-title":"Inhibition of indoleamine 2,3-dioxygenase 1\/2 prevented cognitive impairment and energetic metabolism changes in the hippocampus of adult rats subjected to polymicrobial sepsis","volume":"305","author":"CM Comim","year":"2017","journal-title":"J Neuroimmunol"},{"issue":"5","key":"pone.0319519.ref040","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1016\/j.chest.2023.07.009","article-title":"Optimizing vasopressin use and initiation timing in septic shock: a narrative review","volume":"164","author":"GL Sacha","year":"2023","journal-title":"Chest"},{"issue":"1","key":"pone.0319519.ref041","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/s12873-020-00374-3","article-title":"A retrospective study of sepsis-associated encephalopathy: epidemiology, clinical features and adverse outcomes","volume":"20","author":"J Chen","year":"2020","journal-title":"BMC Emerg Med"},{"issue":"4","key":"pone.0319519.ref042","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1016\/j.ahj.2009.07.024","article-title":"Red cell distribution width in heart failure: prediction of clinical events and relationship with markers of ineffective erythropoiesis, inflammation, renal function, and nutritional state","volume":"158","author":"Z F\u00f6rh\u00e9cz","year":"2009","journal-title":"Am Heart J"},{"issue":"2","key":"pone.0319519.ref043","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1191\/0267659105pf793oa","article-title":"Inflammatory cytokine inhibition of erythropoiesis in patients implanted with a mechanical circulatory assist device","volume":"20","author":"CN Pierce","year":"2005","journal-title":"Perfusion"},{"issue":"12 Suppl","key":"pone.0319519.ref044","first-page":"S651-7","article-title":"Red blood cell physiology in critical illness","volume":"31","author":"M Scharte","year":"2003","journal-title":"Crit Care Med"},{"issue":"8","key":"pone.0319519.ref045","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1080\/00365510802213550","article-title":"Relationship between red blood cell distribution width and kidney function tests in a large cohort of unselected outpatients","volume":"68","author":"G Lippi","year":"2008","journal-title":"Scand J Clin Lab Invest"},{"issue":"6","key":"pone.0319519.ref046","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1001\/archinternmed.2009.55","article-title":"Red blood cell distribution width and mortality risk in a community-based prospective cohort","volume":"169","author":"TS Perlstein","year":"2009","journal-title":"Arch Intern Med"},{"issue":"7","key":"pone.0319519.ref047","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1007\/s00134-003-1783-2","article-title":"Red blood cell rheology in sepsis","volume":"29","author":"M Piagnerelli","year":"2003","journal-title":"Intensive Care Med"},{"issue":"3","key":"pone.0319519.ref048","first-page":"307","article-title":"Combined predictive value of the risk factors influencing the short-term prognosis of sepsis","volume":"32","author":"R Chen","year":"2020","journal-title":"Zhonghua Wei Zhong Bing Ji Jiu Yi Xue"},{"issue":"2","key":"pone.0319519.ref049","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1097\/ALN.0000000000002960","article-title":"Artificial intelligence in anesthesiology: current techniques, clinical applications, and limitations","volume":"132","author":"DA Hashimoto","year":"2020","journal-title":"Anesthesiology"},{"issue":"22","key":"pone.0319519.ref050","doi-asserted-by":"crossref","first-page":"2720","DOI":"10.1001\/jama.291.22.2720","article-title":"Participation in cancer clinical trials: race-, sex-, and age-based disparities","volume":"291","author":"VH Murthy","year":"2004","journal-title":"JAMA"},{"issue":"2","key":"pone.0319519.ref051","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.cjca.2021.09.004","article-title":"Opening the black box: the promise and limitations of explainable machine learning in cardiology","volume":"38","author":"J Petch","year":"2022","journal-title":"Can J Cardiol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T17:26:30Z","timestamp":1744219590000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319519"}},"subtitle":[],"editor":[{"given":"Chinh Quoc","family":"Luong,","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0319519","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,9]]}}}