{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T22:10:21Z","timestamp":1790892621966,"version":"4.1.0"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:00:00Z","timestamp":1749081600000},"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":"<jats:sec id=\"sec019\">\n<jats:title>Introduction<\/jats:title>\n<jats:p>In older patients, postoperative delirium (POD) is a major complication that can result in greater morbidity, longer hospital stays, and higher healthcare expenses. Accurate prediction models for POD can enhance patient outcomes by guiding preventative strategies. This study utilizes advanced machine learning techniques to develop a predictive model for POD using comprehensive perioperative data.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec020\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We examined information from the National Surgical Quality Improvement Program (NSQIP), which included 17,000 patients who were over 65 and undergoing different types of surgery. The dataset included variables such as patient demographics (age, sex), comorbidities (diabetes, cardiovascular diseases, pre-existing dementia), surgical details (type, duration), anesthesia type and dosage, and postoperative outcomes. Categorical variables were encoded numerically, and data standardization was applied to ensure normal distribution. A range of machine learning approaches were assessed such as Decision Trees and Random Forests. Based on the greatest Area Under the Curve (AUC) from Receiver Operating Characteristic (ROC) analysis, the final model was chosen. Hyperparameter tuning was performed using GridSearchCV, optimizing parameters like max_depth, min_child_weight, and gamma for XGBoost model.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec021\">\n<jats:title>Results<\/jats:title>\n<jats:p>The optimized XGBoost model demonstrated superior performance, achieving an AUC of 0.85. Key hyperparameters included min_child_weight\u2009=\u20091, max_depth\u2009=\u20095, gamma\u2009=\u20090.3, subsample\u2009=\u20090.9, colsample_bytree\u2009=\u20090.7, reg_alpha\u2009=\u20090.0007, learning_rate\u2009=\u20090.14, and n_estimators\u2009=\u2009123. The model exhibited an accuracy of 0.926, recall of 0.945, precision of 0.934, and an F1-score of 0.939, depicting a higher level of predictive accuracy &amp; balance between sensitivity and specificity.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec022\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>This study proposes a strong XGBoost-based model to predict POD in older surgical patients, demonstrating the potential of Machine Learning (ML) in clinical risk assessment. With the help of the model\u2019s balanced performance indicators and high accuracy, physicians may identify high-risk patients and promptly execute interventions in clinical settings. Subsequent investigations ought to concentrate on integration into clinical workflows and external validation.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0322032","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T17:31:43Z","timestamp":1749144703000},"page":"e0322032","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["AI-delirium guard: Predictive modeling of postoperative delirium in elderly surgical patients"],"prefix":"10.1371","volume":"20","author":[{"given":"Sri Harsha","family":"Boppana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Divyansh","family":"Tyagi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7431-1040","authenticated-orcid":true,"given":"Sachin","family":"Komati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sri Lasya","family":"Boppana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0300-2886","authenticated-orcid":true,"given":"Ritwik","family":"Raj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9278-4380","authenticated-orcid":true,"given":"C. David","family":"Mintz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,5]]},"reference":[{"issue":"1","key":"pone.0322032.ref001","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1111\/jgs.13281","article-title":"American Geriatrics Society abstracted clinical practice guideline for postoperative delirium in older adults","volume":"63","author":"American Geriatrics Society Expert Panel on Postoperative Delirium in Older Adults","year":"2015","journal-title":"J Am Geriatr Soc"},{"issue":"12","key":"pone.0322032.ref002","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1001\/jamasurg.2015.2606","article-title":"Effect of delirium and other major complications on outcomes after elective surgery in older adults","volume":"150","author":"LJ Gleason","year":"2015","journal-title":"JAMA Surg"},{"issue":"2","key":"pone.0322032.ref003","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1213\/ANE.0b013e3182973650","article-title":"Outcomes of early delirium diagnosis after general anesthesia in the elderly","volume":"117","author":"KJ Neufeld","year":"2013","journal-title":"Anesth Analg"},{"issue":"10","key":"pone.0322032.ref004","doi-asserted-by":"crossref","first-page":"2101","DOI":"10.1111\/jgs.14434","article-title":"Delirium after spine surgery in older adults: incidence, risk factors, and outcomes","volume":"64","author":"CH Brown","year":"2016","journal-title":"J Am Geriatr Soc"},{"key":"pone.0322032.ref005","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1111\/j.1532-5415.2010.02762.x","article-title":"Delirium: an independent predictor of functional decline after cardiac surgery","volume":"58","author":"JL Rudolph","year":"2010","journal-title":"J Am Geriatr Soc"},{"issue":"5","key":"pone.0322032.ref006","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.cmi.2019.09.009","article-title":"Machine learning for clinical decision support in infectious diseases: a narrative review of current applications","volume":"26","author":"N Peiffer-Smadja","year":"2020","journal-title":"Clin Microbiol Infect"},{"key":"pone.0322032.ref007","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.jalz.2016.03.005","article-title":"The short-term and long-term relationship between delirium and cognitive trajectory in older surgical patients","volume":"12","author":"SK Inouye","year":"2016","journal-title":"Alzheimers Dement J Alzheimers Assoc"},{"issue":"4","key":"pone.0322032.ref008","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1001\/jamainternmed.2014.7779","article-title":"Effectiveness of multicomponent nonpharmacological delirium interventions","volume":"175","author":"TT Hshieh","year":"2015","journal-title":"JAMA Intern Med"},{"issue":"10","key":"pone.0322032.ref009","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1016\/j.jagp.2018.06.007","article-title":"Hospital elder life program: systematic review and meta-analysis of effectiveness","volume":"26","author":"TT Hshieh","year":"2018","journal-title":"Am J Geriatr Psychiatry"},{"issue":"5","key":"pone.0322032.ref010","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1046\/j.1532-5415.2001.49108.x","article-title":"Reducing delirium after hip fracture: a randomized trial","volume":"49","author":"ER Marcantonio","year":"2001","journal-title":"J Am Geriatr Soc"},{"issue":"3","key":"pone.0322032.ref011","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1111\/anae.12539","article-title":"The efficacy of peri-operative interventions to decrease postoperative delirium in non-cardiac surgery: a systematic review and meta-analysis","volume":"69","author":"Z Moyce","year":"2014","journal-title":"Anaesthesia"},{"issue":"6","key":"pone.0322032.ref012","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1213\/ANE.0000000000005223","article-title":"An implementation-effectiveness study of a perioperative delirium prevention initiative for older adults","volume":"131","author":"AL Donovan","year":"2020","journal-title":"Anesth Analg"},{"issue":"6","key":"pone.0322032.ref013","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1213\/ANE.0000000000005085","article-title":"Derivation, validation, sustained performance, and clinical impact of an electronic medical record-based perioperative delirium risk stratification tool","volume":"131","author":"EL Whitlock","year":"2020","journal-title":"Anesth Analg"},{"issue":"6","key":"pone.0322032.ref014","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.1213\/ANE.0000000000004641","article-title":"American society for enhanced recovery and perioperative quality initiative joint consensus statement on postoperative delirium prevention","volume":"130","author":"CG Hughes","year":"2020","journal-title":"Anesth Analg"},{"issue":"4","key":"pone.0322032.ref015","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2018.1018","article-title":"Development and validation of an electronic health record-based machine learning model to estimate delirium risk in newly hospitalized patients without known cognitive impairment","volume":"1","author":"A Wong","year":"2018","journal-title":"JAMA Netw Open"},{"issue":"4","key":"pone.0322032.ref016","doi-asserted-by":"crossref","DOI":"10.2196\/14993","article-title":"Exploiting machine learning algorithms and methods for the prediction of agitated delirium after cardiac surgery: models development and validation study","volume":"7","author":"HN Mufti","year":"2019","journal-title":"JMIR Med Inform"},{"issue":"11","key":"pone.0322032.ref017","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1001\/jama.2020.0592","article-title":"Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial","volume":"323","author":"M Wijnberge","year":"2020","journal-title":"JAMA"},{"issue":"10","key":"pone.0322032.ref018","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"SM Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"issue":"6","key":"pone.0322032.ref019","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.bja.2019.07.030","article-title":"An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data","volume":"123","author":"BL Hill","year":"2019","journal-title":"Br J Anaesth"},{"issue":"2","key":"pone.0322032.ref020","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":"12","key":"pone.0322032.ref021","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0113946","article-title":"Performance and agreement of risk stratification instruments for postoperative delirium in persons aged 50 years or older","volume":"9","author":"CJ Jansen","year":"2014","journal-title":"PLoS One"},{"issue":"12","key":"pone.0322032.ref022","doi-asserted-by":"crossref","first-page":"2383","DOI":"10.1111\/jgs.13138","article-title":"Risk prediction models for postoperative delirium: a systematic review and meta-analysis","volume":"62","author":"LCC van Meenen","year":"2014","journal-title":"J Am Geriatr Soc"},{"issue":"1","key":"pone.0322032.ref023","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1093\/ageing\/afv177","article-title":"Delirium risk stratification in consecutive unselected admissions to acute medicine: validation of externally derived risk scores","volume":"45","author":"ST Pendlebury","year":"2016","journal-title":"Age Ageing"},{"issue":"6","key":"pone.0322032.ref024","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1164\/rccm.201404-0716CP","article-title":"Gleaning knowledge from data in the intensive care unit","volume":"190","author":"MR Pinsky","year":"2014","journal-title":"Am J Respir Crit Care Med"},{"key":"pone.0322032.ref025","doi-asserted-by":"crossref","first-page":"11795468221133611","DOI":"10.1177\/11795468221133611","article-title":"XGBoost, a novel explainable AI technique, in the prediction of myocardial infarction: a UK biobank cohort study","volume":"16","author":"A Moore","year":"2022","journal-title":"Clin Med Insights Cardiol"},{"issue":"3","key":"pone.0322032.ref026","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s40266-018-0526-6","article-title":"Do risk prediction models for postoperative delirium consider patients\u2019 preoperative medication use?","volume":"35","author":"GM Kassie","year":"2018","journal-title":"Drugs Aging"},{"issue":"12","key":"pone.0322032.ref027","doi-asserted-by":"crossref","first-page":"941","DOI":"10.7326\/0003-4819-113-12-941","article-title":"Clarifying confusion: the confusion assessment method. A new method for detection of delirium","volume":"113","author":"SK Inouye","year":"1990","journal-title":"Ann Intern Med"},{"issue":"1","key":"pone.0322032.ref028","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s12871-021-01543-y","article-title":"Postoperative delirium prediction using machine learning models and preoperative electronic health record data","volume":"22","author":"A Bishara","year":"2022","journal-title":"BMC Anesthesiol"},{"issue":"11","key":"pone.0322032.ref029","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002701","article-title":"Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): a retrospective, single-site study","volume":"15","author":"KM Corey","year":"2018","journal-title":"PLoS Med"},{"issue":"4","key":"pone.0322032.ref030","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1097\/EJA.0000000000000594","article-title":"European Society of Anaesthesiology evidence-based and consensus-based guideline on postoperative delirium","volume":"34","author":"C Aldecoa","year":"2017","journal-title":"Eur J Anaesthesiol"},{"issue":"5","key":"pone.0322032.ref031","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1016\/j.jamcollsurg.2015.12.026","article-title":"Optimal perioperative management of the geriatric patient: a best practices guideline from the American College of Surgeons NSQIP and the American Geriatrics Society","volume":"222","author":"S Mohanty","year":"2016","journal-title":"J Am Coll Surg"},{"issue":"5","key":"pone.0322032.ref032","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1001\/jamasurg.2014.3176","article-title":"Risk of discharge to postacute care: a patient-centered outcome for the American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator","volume":"150","author":"S Mohanty","year":"2015","journal-title":"JAMA Surg"},{"issue":"2","key":"pone.0322032.ref033","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/s11606-020-06238-7","article-title":"Machine learning to develop and internally validate a predictive model for post-operative delirium in a prospective, observational clinical cohort study of older surgical patients","volume":"36","author":"AM Racine","year":"2021","journal-title":"J Gen Intern Med"},{"key":"pone.0322032.ref034","article-title":"Clarifying confusion: the confusion assessment method.","volume-title":"A new method for detection of delirium","author":"SK Inouye"},{"key":"pone.0322032.ref035","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/1472-6947-12-8","article-title":"Predicting sample size required for classification performance","volume":"12","author":"RL Figueroa","year":"2012","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0322032.ref036","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"T van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"pone.0322032.ref037","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1093\/jamia\/ocw042","article-title":"Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review","volume":"24","author":"BA Goldstein","year":"2017","journal-title":"J Am Med Inform Assoc"},{"issue":"10","key":"pone.0322032.ref038","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.1111\/j.1532-5415.2006.00893.x","article-title":"Preoperative risk assessment for delirium after noncardiac surgery: a systematic review","volume":"54","author":"M Dasgupta","year":"2006","journal-title":"J Am Geriatr Soc"},{"issue":"1","key":"pone.0322032.ref039","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1097\/SLA.0b013e31818e4776","article-title":"Postoperative delirium in the elderly: risk factors and outcomes","volume":"249","author":"TN Robinson","year":"2009","journal-title":"Ann Surg"},{"issue":"1","key":"pone.0322032.ref040","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1097\/SLA.0000000000002436","article-title":"Postoperative delirium as a target for surgical quality improvement","volume":"268","author":"JR Berian","year":"2018","journal-title":"Ann Surg"},{"issue":"9920","key":"pone.0322032.ref041","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1016\/S0140-6736(13)60688-1","article-title":"Delirium in elderly people","volume":"383","author":"SK Inouye","year":"2014","journal-title":"Lancet"},{"key":"pone.0322032.ref042","doi-asserted-by":"crossref","first-page":"104207","DOI":"10.1016\/j.archger.2020.104207","article-title":"Association between lifestyle behaviors and frailty in Atlantic Canadian males and females","volume":"91","author":"V DeClercq","year":"2020","journal-title":"Arch Gerontol Geriatr"},{"issue":"11","key":"pone.0322032.ref043","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1111\/jgs.16082","article-title":"Alcohol consumption and functional limitations in older men: Does muscle strength mediate them?","volume":"67","author":"T Wang","year":"2019","journal-title":"J Am Geriatr Soc"},{"issue":"4","key":"pone.0322032.ref044","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/nrneurol.2009.24","article-title":"Delirium in elderly adults: diagnosis, prevention and treatment","volume":"5","author":"TG Fong","year":"2009","journal-title":"Nat Rev Neurol"},{"issue":"23","key":"pone.0322032.ref045","doi-asserted-by":"crossref","first-page":"2229","DOI":"10.1056\/NEJMsb1503104","article-title":"Precision medicine--personalized, problematic, and promising","volume":"372","author":"JL Jameson","year":"2015","journal-title":"N Engl J Med"},{"issue":"29","key":"pone.0322032.ref046","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1093\/eurheartj\/ehu207","article-title":"Towards better clinical prediction models: seven steps for development and an ABCD for validation","volume":"35","author":"EW Steyerberg","year":"2014","journal-title":"Eur Heart J"},{"key":"pone.0322032.ref047","doi-asserted-by":"crossref","DOI":"10.1186\/cc13084","article-title":"Outcome and quality of life in patients with postoperative delirium during an ICU stay following major surgery","volume":"17","author":"FJ Abelha","year":"2013","journal-title":"Crit Care Lond Engl"},{"issue":"1","key":"pone.0322032.ref048","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1056\/NEJMoa1112923","article-title":"Cognitive trajectories after postoperative delirium","volume":"367","author":"JS Saczynski","year":"2012","journal-title":"N Engl J Med"},{"issue":"3","key":"pone.0322032.ref049","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1097\/ALN.0000000000002253","article-title":"Cognitive decline after delirium in patients undergoing cardiac surgery","volume":"129","author":"CH Brown","year":"2018","journal-title":"Anesthesiology"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0322032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T17:31:53Z","timestamp":1749144713000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0322032"}},"subtitle":[],"editor":[{"given":"Pedro Kallas","family":"Curiati","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,5]]},"references-count":49,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0322032","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,5]]}}}