{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T09:26:04Z","timestamp":1783416364652,"version":"3.54.6"},"reference-count":24,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"21","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,22]]},"abstract":"<jats:sec>\n                    <jats:title\/>\n                    <jats:p>Delirium is a frequent and clinically consequential complication among patients admitted to the intensive care unit (ICU). Early risk stratification in patients with non-ST-segment elevation myocardial infarction (NSTEMI) remains challenging. We aimed to develop and validate prediction models for ICU delirium in NSTEMI patients using Boruta-based feature selection and machine learning (ML) approaches, and to compare ML performance with a nomogram model. We retrospectively identified adult ICU patients (\u2265\u200518 years) diagnosed with NSTEMI in the Medical Information Mart for Intensive Care IV database, and included only those with no delirium within the first 24 hours of admission and no prior history of delirium. A total of 392 patients were included (mean age 72.2\u2005\u00b1\u200512.6 years; 64% male) and categorized into a delirium group (n\u2005=\u2005201) and a non-delirium group (n\u2005=\u2005191). Clinical characteristics and laboratory indices were extracted. Participants were randomly split into a training cohort (70%) and a validation cohort (30%). The Boruta algorithm was applied in the training cohort for feature selection and identification of relevant predictors. A nomogram was constructed using Boruta-selected variables. In parallel, the same features were incorporated into ML models; model discrimination and clinical utility were evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis. SHapley Additive exPlanations were used to quantify and visualize feature contributions for the best-performing model. Boruta identified 9 key variables: systolic blood pressure, serum calcium, pulse oximetry, serum sodium, creatinine, serum chloride, anion gap, blood urea nitrogen, and body temperature. In the validation cohort, CatBoost achieved the best discrimination among ML models, with an area under the receiver operating characteristic curve of 0.743 (95% CI\u2005=\u20050.653\u20130.833). The nomogram demonstrated lower discrimination (validation area under the curve\u2005=\u20050.61). SHapley Additive exPlanations analyses indicated that the Boruta-selected variables contributed differentially to delirium prediction, supporting model interpretability. In ICU patients with NSTEMI, a Boruta-informed CatBoost model showed moderate predictive performance and outperformed a nomogram constructed from the same predictors. This interpretable ML approach may facilitate early identification of patients at high risk of delirium and support timely preventive strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/md.0000000000049062","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:01:28Z","timestamp":1779469288000},"page":"e49062","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Nomogram and machine learning models for predicting the risk of delirium in ICU patients with NSTEMI"],"prefix":"10.1097","volume":"105","author":[{"given":"Dan","family":"Zuo","sequence":"first","affiliation":[{"name":"Department of Mental Health, The First People\u2019s Hospital of Jiande, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8173-6349","authenticated-orcid":false,"given":"Yunpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Respiratory, The First People\u2019s Hospital of Jiande, Hangzhou, Zhejiang, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R2-20260707","doi-asserted-by":"crossref","first-page":"2703","DOI":"10.1001\/jama.286.21.2703","article-title":"Delirium in mechanically ventilated patients: validity and reliability of the confusion assessment method for the intensive care unit (CAM-ICU).","volume":"286","author":"Ely","year":"2001","journal-title":"JAMA"},{"key":"R3-20260707","doi-asserted-by":"crossref","first-page":"103629","DOI":"10.1016\/j.eclinm.2025.103629","article-title":"Delirium after surgery: a retrospective study of predictors, complications, and screening patterns in the national surgical quality improvement program.","volume":"90","author":"Panayi","year":"2025","journal-title":"EClinicalMedicine"},{"key":"R4-20260707","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1177\/08850666241244733","article-title":"Impact of delirium onset and duration on mortality in patients with cancer admitted to the ICU.","volume":"39","author":"Tao","year":"2024","journal-title":"J Intensive Care Med"},{"key":"R5-20260707","first-page":"121","article-title":"Clinical and prognostic implications of delirium in elderly patients with non-ST-segment elevation acute coronary syndromes.","volume":"16","author":"Vives-Borr\u00e1s","year":"2019","journal-title":"J Geriatr Cardiol"},{"key":"R6-20260707","first-page":"1072","article-title":"Incidence and predictors of delirium on the intensive care unit after acute myocardial infarction, insight from a retrospective registry.","volume":"98","author":"J\u00e4ckel","year":"2021","journal-title":"Catheter Cardiovasc Interv"},{"key":"R7-20260707","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1097\/JTN.0000000000000859","article-title":"Delirium in critically ill geriatric surgical patients: a systematic review of screening, risk factors, diagnosis, and management.","volume":"32","author":"Yates","year":"2025","journal-title":"J Trauma Nurs"},{"key":"R8-20260707","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.cger.2024.03.005","article-title":"Update on perioperative delirium.","volume":"41","author":"Schenning","year":"2025","journal-title":"Clin Geriatr Med"},{"key":"R9-20260707","doi-asserted-by":"crossref","first-page":"e70193","DOI":"10.1111\/nicc.70193","article-title":"A data-driven model to predict delirium based on dynamic patterns of clinical deterioration in critically ill patients.","volume":"30","author":"Back","year":"2025","journal-title":"Nurs Crit Care"},{"key":"R10-20260707","doi-asserted-by":"crossref","first-page":"1446523","DOI":"10.3389\/fnagi.2024.1446523","article-title":"Mechanisms underlying delirium in patients with critical illness.","volume":"16","author":"Fan","year":"2024","journal-title":"Front Aging Neurosci"},{"key":"R11-20260707","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1177\/1054773820973123","article-title":"Evaluating pain, opioids, and delirium in critically ill older adults.","volume":"30","author":"Pavone","year":"2021","journal-title":"Clin Nurs Res"},{"key":"R12-20260707","doi-asserted-by":"crossref","first-page":"20","DOI":"10.4037\/ajcc2026815","article-title":"Machine learning-based prediction of subsyndromal delirium in intensive care patients.","volume":"35","author":"Wen","year":"2026","journal-title":"Am J Crit Care"},{"key":"R13-20260707","doi-asserted-by":"crossref","first-page":"e59520","DOI":"10.2196\/59520","article-title":"Development and validation of a machine learning model for early prediction of delirium in intensive care units using continuous physiological data: retrospective study.","volume":"27","author":"Park","year":"2025","journal-title":"J Med Internet Res"},{"key":"R14-20260707","doi-asserted-by":"crossref","first-page":"108748","DOI":"10.1016\/j.rmed.2026.108748","article-title":"A practical and validated nomogram for predicting delirium in critically ill patients: a multicenter prospective observational study.","volume":"255","author":"Chang","year":"2026","journal-title":"Respir Med"},{"key":"R15-20260707","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1016\/j.recesp.2023.12.015","article-title":"Machine learning methods for developing a predictive model of the incidence of delirium in cardiac intensive care units.","volume":"77","author":"Ko","year":"2024","journal-title":"Rev Esp Cardiol (Engl Ed)"},{"key":"R16-20260707","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1016\/j.ijsu.2014.07.013","article-title":"The strengthening the reporting of observational studies in epidemiology (STROBE) statement: guidelines for reporting observational studies.","volume":"12","author":"von Elm","year":"2014","journal-title":"Int J Surg"},{"key":"R17-20260707","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1111\/j.1471-4159.2006.04245.x","article-title":"Alcohol-induced blood-brain barrier dysfunction is mediated via inositol 1,4,5-triphosphate receptor (IP3R)-gated intracellular calcium release.","volume":"100","author":"Haorah","year":"2007","journal-title":"J Neurochem"},{"key":"R18-20260707","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1089\/ars.2010.3359","article-title":"Calcium dysregulation and homeostasis of neural calcium in the molecular mechanisms of neurodegenerative diseases provide multiple targets for neuroprotection.","volume":"14","author":"Z\u00fcndorf","year":"2011","journal-title":"Antioxid Redox Signal"},{"key":"R19-20260707","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s40635-025-00722-2","article-title":"Regional cerebral oxygen saturation during initial mobilization of critically ill patients is associated with clinical outcomes: a prospective observational study.","volume":"13","author":"Imai","year":"2025","journal-title":"Intensive Care Med Exp"},{"key":"R20-20260707","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1177\/08850666241288141","article-title":"Utilization of NIRS monitor to compare the regional cerebral oxygen saturation between dexmedetomidine and propofol sedation in mechanically ventilated critically ill patients with sepsis- a prospective randomized control trial.","volume":"40","author":"Patidar","year":"2025","journal-title":"J Intensive Care Med"},{"key":"R21-20260707","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1186\/s12888-024-05832-x","article-title":"Association between pediatric postoperative delirium and regional cerebral oxygen saturation: a prospective observational study.","volume":"24","author":"Liu","year":"2024","journal-title":"BMC Psychiatry"},{"key":"R22-20260707","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1542\/pir.2021-005438","article-title":"Acute kidney injury.","volume":"44","author":"Menon","year":"2023","journal-title":"Pediatr Rev"},{"key":"R23-20260707","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1177\/10781552241262248","article-title":"Hypokalemia, hypomagnesemia, and hyponatremia are associated with acute kidney injury in patients treated with cisplatin.","volume":"31","author":"Pinard","year":"2025","journal-title":"J Oncol Pharm Pract"},{"key":"R24-20260707","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.34067\/KID.0002402022","article-title":"Associations of metabolic syndrome and abdominal obesity with anion gap metabolic acidosis among US adults.","volume":"3","author":"Lambert","year":"2022","journal-title":"Kidney360"},{"key":"R25-20260707","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1165\/rcmb.2024-0391OC","article-title":"Early sepsis metabolic changes in kidney and liver precede clinical evidence of organ dysfunction.","volume":"73","author":"McCann","year":"2025","journal-title":"Am J Respir Cell Mol Biol"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000049062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T09:01:18Z","timestamp":1783414878000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000049062"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":24,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000049062","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]},"assertion":[{"value":"2026-03-31","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-27","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}