{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:57:17Z","timestamp":1785884237422,"version":"3.56.0"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T00:00:00Z","timestamp":1742428800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"\nBackground and objective<\/jats:title>\nElderly patients with Chronic obstructive pulmonary disease (COPD) and respiratory failure admitted to the intensive care unit (ICU) have a poor prognosis, and the occurrence of delirium further worsens outcomes and increases hospitalization costs. This study aimed to develop a predictive model for delirium in this patient population and identify associated risk factors<\/jats:p>\n<\/jats:sec>\n\nMethods<\/jats:title>\nData for the machine learning model were obtained from the MIMIC-IV database. Feature variable screening was conducted using Lasso regression and the best subset method. Four models\u2014K-nearest neighbor, random forest, logistic regression, and extreme gradient boosting (XGBoost)\u2014were trained and optimized to predict delirium risk. The stability of the model is evaluated using ten-fold cross validation and the effectiveness of the model on the validation set is evaluated using accuracy, F1 score, precision and recall. The SHapley Additive exPlanations (SHAP) method was used to explain the importance of each variable in the model.<\/jats:p>\n<\/jats:sec>\n\nResults<\/jats:title>\nA total of 1,155 patients admitted to the intensive care unit between 2008 and 2019 were included in the study, with a delirium incidence of 12.9% (149\/1,155). Among the four ML models evaluated, the XGBoost model demonstrated the best discriminative ability. In the validation set, it achieved an AUC of 0.932, indicating superior performance with high accuracy, precision, recall, and F1 scores of 0.891, 0.839, 0.795, and 0.810, respectively. Key features identified through SHAP analysis included the Glasgow Coma Scale (GCS) verbal score, length of hospital stay, mean SpO\u2082 on the first day of ICU admission, Modification of Diet in Renal Disease (MDRD) equation score, mean diastolic blood pressure, GCS motor score, gender, and duration of noninvasive ventilation. These findings provide valuable insights for individualized risk management.<\/jats:p>\n<\/jats:sec>\n\nConclusions<\/jats:title>\nThe developed prediction model effectively predicts the occurrence of delirium in elderly COPD patients with respiratory failure in the ICU. This model can assist clinical decision-making, potentially improving patient outcomes and reducing healthcare costs.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0319297","type":"journal-article","created":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T21:19:24Z","timestamp":1742505564000},"page":"e0319297","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: A retrospective study based on MIMIC-IV"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9520-8436","authenticated-orcid":true,"given":"Zong-bi","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6856-5177","authenticated-orcid":true,"given":"You-li","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai-shuai","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5061-9694","authenticated-orcid":true,"given":"Ao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,3,20]]},"reference":[{"key":"pone.0319297.ref001","doi-asserted-by":"crossref","first-page":"2317","DOI":"10.2147\/COPD.S377857","article-title":"Chronic obstructive pulmonary disease prevalence and associated risk factors in adults aged 40 years and older in Southeast China: A cross-sectional study during 2019\u20132020","volume":"17","author":"J Chen","year":"2022","journal-title":"Int J Chron Obstruct Pulmon Dis"},{"issue":"8","key":"pone.0319297.ref002","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1111\/resp.12642","article-title":"COPD and its comorbidities: Impact, measurement and mechanisms","volume":"20","author":"NA Negewo","year":"2015","journal-title":"Respirology"},{"issue":"3","key":"pone.0319297.ref003","first-page":"261","article-title":"COPD: Iron deficiency and clinical characteristics in patients with and without chronic respiratory failure","volume":"11","author":"IM Hardang","year":"2024","journal-title":"Chronic Obstr Pulm Dis"},{"issue":"1","key":"pone.0319297.ref004","first-page":"52","article-title":"Respiratory failure in intensive care unit patients with progressive COPD: Nursing approaches to patient care","volume":"28","author":"L Ai","year":"2022","journal-title":"Altern Ther Health Med"},{"issue":"1","key":"pone.0319297.ref005","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1186\/s12890-022-02052-5","article-title":"Delirium in elderly patients with COPD combined with respiratory failure undergoing mechanical ventilation: a prospective cohort study","volume":"22","author":"X Fu","year":"2022","journal-title":"BMC Pulm Med"},{"issue":"3","key":"pone.0319297.ref006","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s00540-022-03049-4","article-title":"Postoperative delirium is an independent factor influencing the length of stay of elderly patients in the intensive care unit and in hospital","volume":"36","author":"A Kirfel","year":"2022","journal-title":"J Anesth"},{"issue":"11","key":"pone.0319297.ref007","doi-asserted-by":"crossref","DOI":"10.1001\/jamaneurol.2020.2273","article-title":"Association of Delirium With Long-term Cognitive Decline: A Meta-analysis.","volume":"77","author":"TE Goldberg","year":"2020","journal-title":"JAMA Neurol"},{"issue":"6","key":"pone.0319297.ref008","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/j.jaclp.2024.04.005","article-title":"Prognostic implications of delirium after left ventricular assist device implantation: A retrospective study","volume":"65","author":"P Noufi","year":"2024","journal-title":"J Acad Consult Liaison Psychiatry"},{"issue":"5","key":"pone.0319297.ref009","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s00408-024-00725-y","article-title":"Association of delirium with long-term mortality in critically ill patients with COPD who survived to discharge: A retrospective cohort study","volume":"202","author":"H-B Xu","year":"2024","journal-title":"Lung"},{"issue":"2","key":"pone.0319297.ref010","doi-asserted-by":"crossref","first-page":"24","DOI":"10.4037\/ccn2020697","article-title":"Relationship between delirium and ventilatory outcomes in the medical intensive care unit","volume":"40","author":"K Kerber","year":"2020","journal-title":"Crit Care Nurse"},{"issue":"4","key":"pone.0319297.ref011","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1111\/jgs.14076","article-title":"Antipsychotic medication for prevention and treatment of delirium in hospitalized adults: A systematic review and meta-analysis","volume":"64","author":"KJ Neufeld","year":"2016","journal-title":"J Am Geriatr Soc"},{"issue":"1","key":"pone.0319297.ref012","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1055\/s-0040-1710572","article-title":"Prevention and management of delirium in the intensive care unit","volume":"42","author":"MF Mart","year":"2021","journal-title":"Semin Respir Crit Care Med"},{"issue":"2","key":"pone.0319297.ref013","doi-asserted-by":"crossref","first-page":"33","DOI":"10.4037\/ccn2020706","article-title":"Early identification of delirium in intensive care unit patients: Improving the quality of care","volume":"40","author":"J Spiegelberg","year":"2020","journal-title":"Crit Care Nurse"},{"issue":"13","key":"pone.0319297.ref014","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial intelligence and machine learning in clinical medicine","volume":"388","author":"CJ Haug","year":"2023","journal-title":"N Engl J Med"},{"issue":"1","key":"pone.0319297.ref015","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1186\/s12911-024-02504-4","article-title":"Prediction of carbapenem-resistant gram-negative bacterial bloodstream infection in intensive care unit based on machine learning","volume":"24","author":"Q Liang","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0319297.ref016","doi-asserted-by":"crossref","first-page":"103715","DOI":"10.1016\/j.iccn.2024.103715","article-title":"Prediction model of pressure injury occurrence in diabetic patients during ICU hospitalization--XGBoost machine learning model can be interpreted based on SHAP","volume":"83","author":"J Xu","year":"2024","journal-title":"Intensive Crit Care Nurs"},{"issue":"4","key":"pone.0319297.ref017","doi-asserted-by":"crossref","first-page":"e0301014","DOI":"10.1371\/journal.pone.0301014","article-title":"Machine learning for prediction of acute kidney injury in patients diagnosed with sepsis in critical care","volume":"19","author":"J Shi","year":"2024","journal-title":"PLoS One"},{"issue":"6","key":"pone.0319297.ref018","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.1007\/s00134-015-3777-2","article-title":"Multinational development and validation of an early prediction model for delirium in ICU patients","volume":"41","author":"A Wassenaar","year":"2015","journal-title":"Intensive Care Med"},{"issue":"10","key":"pone.0319297.ref019","doi-asserted-by":"crossref","first-page":"2986","DOI":"10.1111\/cns.14237","article-title":"Machine learning for prediction of delirium in patients with extensive burns after surgery","volume":"29","author":"Y Ren","year":"2023","journal-title":"CNS Neurosci Ther"},{"issue":"1","key":"pone.0319297.ref020","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1186\/s12888-023-04768-y","article-title":"Machine learning-based prediction model for postoperative delirium in non-cardiac surgery","volume":"23","author":"DY Lee","year":"2023","journal-title":"BMC Psychiatry"},{"issue":"8","key":"pone.0319297.ref021","first-page":"CD002878","article-title":"Chronic non-invasive ventilation for chronic obstructive pulmonary disease","volume":"8","author":"T Raveling","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"issue":"1","key":"pone.0319297.ref022","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1186\/s12890-021-01517-3","article-title":"Incidence, characteristics, and outcomes of delirium in patients with noninvasive ventilation: a prospective observational study","volume":"21","author":"R Zhang","year":"2021","journal-title":"BMC Pulm Med"},{"issue":"4","key":"pone.0319297.ref023","doi-asserted-by":"crossref","first-page":"100452","DOI":"10.1016\/j.patter.2022.100452","article-title":"Shapley variable importance cloud for interpretable machine learning","volume":"3","author":"Y Ning","year":"2022","journal-title":"Patterns (N Y)"},{"issue":"7","key":"pone.0319297.ref024","doi-asserted-by":"crossref","first-page":"e0288819","DOI":"10.1371\/journal.pone.0288819","article-title":"Dendrogram of transparent feature importance machine learning statistics to classify associations for heart failure: A reanalysis of a retrospective cohort study of the Medical Information Mart for Intensive Care III (MIMIC-III) database","volume":"18","author":"AA Huang","year":"2023","journal-title":"PLoS One"},{"issue":"10","key":"pone.0319297.ref025","doi-asserted-by":"crossref","first-page":"815","DOI":"10.23736\/S0375-9393.22.16511-9","article-title":"Delirium incidence and risk factors in patients undergoing non-invasive ventilation for acute respiratory failure: a multicenter observational trial","volume":"88","author":"L Tabb\u00ec","year":"2022","journal-title":"Minerva Anestesiol"},{"issue":"1","key":"pone.0319297.ref026","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.jcrc.2014.09.010","article-title":"Delirium affects length of hospital stay after lung transplantation","volume":"30","author":"PJ Smith","year":"2015","journal-title":"J Crit Care"},{"key":"pone.0319297.ref027","doi-asserted-by":"crossref","first-page":"886186","DOI":"10.3389\/fpsyt.2022.886186","article-title":"Development and Validation of Simplified Delirium Prediction Model in Intensive Care Unit","volume":"13","author":"M-K Kim","year":"2022","journal-title":"Front Psychiatry"},{"issue":"1","key":"pone.0319297.ref028","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1111\/cns.14002","article-title":"Automated machine learning-based model for the prediction of delirium in patients after surgery for degenerative spinal disease","volume":"29","author":"Y Zhang","year":"2023","journal-title":"CNS Neurosci Ther"},{"issue":"8","key":"pone.0319297.ref029","doi-asserted-by":"crossref","first-page":"983","DOI":"10.3390\/molecules21080983","article-title":"Bioactive Molecule Prediction Using Extreme Gradient Boosting","volume":"21","author":"I Babajide Mustapha","year":"2016","journal-title":"Molecules"},{"issue":"2","key":"pone.0319297.ref030","doi-asserted-by":"crossref","first-page":"e0281922","DOI":"10.1371\/journal.pone.0281922","article-title":"Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations","volume":"18","author":"AA Huang","year":"2023","journal-title":"PLoS One"},{"issue":"6","key":"pone.0319297.ref031","doi-asserted-by":"crossref","first-page":"afad086","DOI":"10.1093\/ageing\/afad086","article-title":"Development and validation of an international preoperative risk assessment model for postoperative delirium","volume":"52","author":"BT Dodsworth","year":"2023","journal-title":"Age Ageing"},{"issue":"1","key":"pone.0319297.ref032","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41398-024-02762-w","article-title":"Prediction models for postoperative delirium in elderly patients with machine-learning algorithms and SHapley Additive exPlanations","volume":"14","author":"Y Song","year":"2024","journal-title":"Transl Psychiatry"},{"key":"pone.0319297.ref033","doi-asserted-by":"crossref","first-page":"111121","DOI":"10.1016\/j.jclinane.2023.111121","article-title":"Early prediction of delirium upon intensive care unit admission: Model development, validation, and deployment","volume":"88","author":"M-L Wang","year":"2023","journal-title":"J Clin Anesth"},{"key":"pone.0319297.ref034","doi-asserted-by":"crossref","first-page":"1290117","DOI":"10.3389\/fneur.2023.1290117","article-title":"Factor analysis based on SHapley Additive exPlanations for sepsis-associated encephalopathy in ICU mortality prediction using XGBoost \u2013 A retrospective study based on two large database","volume":"14","author":"J Guo","year":"2023","journal-title":"Front Neurol"},{"key":"pone.0319297.ref035","doi-asserted-by":"crossref","first-page":"1399848","DOI":"10.3389\/fmed.2024.1399848","article-title":"Interpretable machine learning model for early prediction of delirium in elderly patients following intensive care unit admission: a derivation and validation study","volume":"11","author":"D Tang","year":"2024","journal-title":"Front Med (Lausanne)"},{"issue":"23","key":"pone.0319297.ref036","doi-asserted-by":"crossref","first-page":"3295","DOI":"10.1089\/neu.2021.0199","article-title":"Diagnosing level of consciousness: The limits of the Glasgow Coma Scale Total Score","volume":"38","author":"YG Bodien","year":"2021","journal-title":"J Neurotrauma"},{"issue":"1","key":"pone.0319297.ref037","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1111\/cns.13991","article-title":"Comparison of logistic regression and machine learning methods for predicting postoperative delirium in elderly patients: A retrospective study","volume":"29","author":"Y-X Song","year":"2023","journal-title":"CNS Neurosci Ther"},{"key":"pone.0319297.ref038","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.jcrc.2019.08.010","article-title":"Comparison between logistic regression and machine learning algorithms on survival prediction of traumatic brain injuries","volume":"54","author":"J-Z Feng","year":"2019","journal-title":"J Crit Care"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T21:19:38Z","timestamp":1742505578000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319297"}},"subtitle":[],"editor":[{"given":"Chiara","family":"Lazzeri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,20]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0319297","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,20]]}}}