{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:16:31Z","timestamp":1786119391529,"version":"build-2736575974"},"reference-count":43,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"17","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"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":[[2026,4,24]]},"abstract":"<jats:p>Acute rhinosinusitis (ARS) is a heterogeneous catarrhal or purulent inflammatory disease of the sinus mucosa with critical risks in the intensive care unit (ICU). Current mortality models lack specificity for their unique pathophysiology, necessitating tailored prediction tools. We conducted a retrospective analysis of 3 large ICU databases: Medical Information Mart for Intensive Care (MIMIC)-IV-3.1 (n\u2005=\u2005392), MIMIC-III-CareVue (n\u2005=\u200589), and electronic intensive care unit collaborative research database \u22122.0 (n\u2005=\u200578). We employed the Boruta algorithm for feature selection and developed 9 machine learning models using MIMIC-IV as the training dataset, with MIMIC-III-CareVue and the electronic intensive care unit collaborative research database serving as external validation datasets. Model performance was evaluated by multiple metrics, including area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. We implemented L2 regularization and grid-based hyperparameter tuning to prevent overfitting. SHapley Additive exPlanations analysis was used to interpret the best-performing model. This study included 559 patients. The Boruta algorithm identified sequential organ failure assessment scores and platelet counts as potential predictors. Receiver operating characteristic curve analysis showed that the random forest model performed best in 2 external validation sets, with a maximum area under the receiver operating characteristic curve of 0.799, and high sensitivity and accuracy. SHapley Additive exPlanations analysis revealed Oxford acute severity of illness score scores as the core feature affecting model output, with simplified acute physiology score II scores, weight, blood urea nitrogen levels in the first 24 hours, and sequential organ failure assessment scores also showing high contribution. This study constructed an ICU prognostic model for ARS using multi-database clinical data and the top-performing random forest algorithm. It aids in identifying and managing high-risk ARS patients clinically and offers a reliable tool for rational medical resource allocation.<\/jats:p>","DOI":"10.1097\/md.0000000000048376","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T07:02:33Z","timestamp":1777273353000},"page":"e48376","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning-based prediction model for in-hospital mortality in ICU patients with acute rhinosinusitis: A multi-database study using SHAP interpretability"],"prefix":"10.1097","volume":"105","author":[{"given":"Manxiang","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Otolaryngology, The First Affiliated Hospital of Chengdu Medical College, Chengdu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, The First Affiliated Hospital of Chengdu Medical College, Chengdu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6310-8380","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"Experimental Teaching Center of Biotechnology, School of Bioscience and Technology, Chengdu Medical College, Chengdu, China"},{"name":"Key Laboratory of Target Discovery and Protein Drug Development in Major Diseases at Chengdu Medical College of Sichuan Province, Chengdu, China"},{"name":"Irradiation Preservation and Effect Key Laboratory of Sichuan Province, Chengdu, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260622","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1002\/alr.22741","article-title":"International consensus statement on allergy and rhinology: rhinosinusitis 2021.","volume":"11","author":"Orlandi","year":"2021","journal-title":"Int Forum Allergy Rhinol"},{"key":"R2-20260622","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.pop.2024.09.010","article-title":"Sinusitis.","volume":"52","author":"Wilcox","year":"2025","journal-title":"Prim Care"},{"key":"R3-20260622","doi-asserted-by":"crossref","first-page":"2152656721996258","DOI":"10.1177\/2152656721996258","article-title":"Neurological complications of acute rhinosinusitis: meningitis.","volume":"12","author":"Bennett","year":"2021","journal-title":"Allergy Rhinol (Providence)"},{"key":"R4-20260622","doi-asserted-by":"crossref","first-page":"101316","DOI":"10.1016\/j.bjorl.2023.101316","article-title":"Revisiting the orbital complications of acute rhinosinusitis.","volume":"89","author":"Anselmo-Lima","year":"2023","journal-title":"Braz J Otorhinolaryngol"},{"key":"R5-20260622","first-page":"47","article-title":"Acute rhinosinusitis: rapid evidence review.","volume":"111","author":"Butler","year":"2025","journal-title":"Am Fam Physician"},{"key":"R6-20260622","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.wneu.2024.08.127","article-title":"Intracranial hemorrhagic complications of rhinosinusitis: a systematic literature review and case illustration.","volume":"191","author":"Fu","year":"2024","journal-title":"World Neurosurg"},{"key":"R7-20260622","doi-asserted-by":"crossref","first-page":"241","DOI":"10.2500\/ajra.2016.30.4322","article-title":"Complications of sinusitis.","volume":"30","author":"Carr","year":"2016","journal-title":"Am J Rhinol Allergy"},{"key":"R8-20260622","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1159\/000477419","article-title":"Update of sepsis in the intensive care unit.","volume":"9","author":"Genga","year":"2017","journal-title":"J Innate Immun"},{"key":"R9-20260622","doi-asserted-by":"crossref","first-page":"389","DOI":"10.2500\/ajra.2010.24.3512","article-title":"Safety of sphenoid aspiration for diagnosis and treatment of intensive care unit rhinosinusitis.","volume":"24","author":"Jardim Vieira","year":"2010","journal-title":"Am J Rhinol Allergy"},{"key":"R10-20260622","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1177\/08850666231166349","article-title":"Dynamic prediction of patient outcomes in the intensive care unit: a scoping review of the state-of-the-art.","volume":"38","author":"Lapp","year":"2023","journal-title":"J Intensive Care Med"},{"key":"R11-20260622","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s12874-022-01540-w","article-title":"Comparative analysis of explainable machine learning prediction models for hospital mortality.","volume":"22","author":"Stenwig","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"R13-20260622","doi-asserted-by":"crossref","first-page":"427","DOI":"10.4065\/mcp.2010.0392","article-title":"Rhinosinusitis diagnosis and management for the clinician: a synopsis of recent consensus guidelines.","volume":"86","author":"Meltzer","year":"2011","journal-title":"Mayo Clin Proc"},{"key":"R14-20260622","first-page":"101431","article-title":"Is artificial intelligence prepared for the 24-h shifts in the ICU?","volume":"43","author":"Gonzalez","year":"2024","journal-title":"Anaesth Crit Care Pain Med"},{"key":"R15-20260622","doi-asserted-by":"crossref","first-page":"7535","DOI":"10.3390\/jcm13247535","article-title":"Artificial intelligence in the management of patients with respiratory failure requiring mechanical ventilation: a scoping review.","volume":"13","author":"Viderman","year":"2024","journal-title":"J Clin Med"},{"key":"R16-20260622","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1016\/S2213-2600(18)30425-9","article-title":"Opening the black box of machine learning.","volume":"6","year":"2018","journal-title":"Lancet Respir Med"},{"key":"R18-20260622","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1186\/s12931-020-01588-6","article-title":"Five novel clinical phenotypes for critically ill patients with mechanical ventilation in intensive care units: a retrospective and multi database study.","volume":"21","author":"Su","year":"2020","journal-title":"Respir Res"},{"key":"R19-20260622","doi-asserted-by":"crossref","first-page":"688969","DOI":"10.3389\/fdata.2021.688969","article-title":"Principles and practice of explainable machine learning.","volume":"4","author":"Belle","year":"2021","journal-title":"Front Big Data"},{"key":"R20-20260622","doi-asserted-by":"crossref","first-page":"1500326","DOI":"10.3389\/fcimb.2024.1500326","article-title":"Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study.","volume":"14","author":"Shen","year":"2024","journal-title":"Front Cell Infect Microbiol"},{"key":"R21-20260622","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1186\/s12890-024-03252-x","article-title":"Interpretable mortality prediction model for ICU patients with pneumonia: using Shapley additive explanation method.","volume":"24","author":"Li","year":"2024","journal-title":"BMC Pulm Med"},{"key":"R23-20260622","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s11689-025-09612-w","article-title":"Automated extraction of functional biomarkers of verbal and ambulatory ability from multi-institutional clinical notes using large language models.","volume":"17","author":"Kaster","year":"2025","journal-title":"J Neurodev Disord"},{"key":"R24-20260622","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database.","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"key":"R25-20260622","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1093\/toxsci\/kfy166","article-title":"Cadmium activates noncanonical Wnt signaling to impair hematopoietic stem cell function in mice.","volume":"165","author":"Zhao","year":"2018","journal-title":"Toxicol Sci"},{"key":"R26-20260622","first-page":"15","article-title":"Expert consensus on the diagnosis and treatment of thrombocytopenia in adult critical care patients in China.","volume":"7","author":"Song","year":"2020","journal-title":"Mil Med Res"},{"key":"R27-20260622","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1097\/00003246-200208000-00015","article-title":"Thrombocytopenia in patients in the medical intensive care unit: bleeding prevalence, transfusion requirements, and outcome.","volume":"30","author":"Strauss","year":"2002","journal-title":"Crit Care Med"},{"key":"R28-20260622","doi-asserted-by":"crossref","first-page":"109314","DOI":"10.1016\/j.thromres.2025.109314","article-title":"Platelet count trajectory patterns and prognosis in critically ill patients with thrombocytopenia: based on latent growth mixture model analysis.","volume":"249","author":"Li","year":"2025","journal-title":"Thromb Res"},{"key":"R29-20260622","doi-asserted-by":"crossref","first-page":"238","DOI":"10.4103\/1687-8426.165901","article-title":"Impact of C-reactive protein and BMI on patient outcome in respiratory ICU in Abbassia Chest Hospital.","volume":"9","author":"Elnaggara","year":"2015","journal-title":"Egypt J Bronchol"},{"key":"R30-20260622","first-page":"370","article-title":"Body mass index\u00e2\u20ac\u2122s effect on CRSwNP extends to pathological endotype and recurrence.","volume":"62","author":"Chen","year":"2024","journal-title":"Rhinology"},{"key":"R31-20260622","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1016\/j.jaip.2022.01.013","article-title":"A comparison of international guidelines for rhinosinusitis.","volume":"10","author":"Fokkens","year":"2022","journal-title":"J Allergy Clin Immunol Pract"},{"key":"R32-20260622","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/s12028-024-02150-8","article-title":"The predictive validity of the full outline of unresponsiveness score compared to the glasgow coma scale in the intensive care unit: a systematic review.","volume":"43","author":"Schey","year":"2025","journal-title":"Neurocrit Care"},{"key":"R33-20260622","doi-asserted-by":"crossref","first-page":"133201","DOI":"10.1016\/j.ijcard.2025.133201","article-title":"Prognostic value of SAPS II score for 28-day mortality in ICU patients with acute pulmonary embolism.","volume":"430","author":"Liu","year":"2025","journal-title":"Int J Cardiol"},{"key":"R34-20260622","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1186\/s12873-021-00547-8","article-title":"Prognostic scores and early management of septic patients in the emergency department of a secondary hospital: results of a retrospective study.","volume":"21","author":"Colussi","year":"2021","journal-title":"BMC Emerg Med"},{"key":"R35-20260622","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1186\/s13054-021-03582-w","article-title":"Elevated carboxyhaemoglobin as a novel indicator for extracorporeal membrane haemolysis and oxygenator exchange.","volume":"25","author":"Hoffman","year":"2021","journal-title":"Crit Care"},{"key":"R36-20260622","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests.","volume":"45","year":"2001","journal-title":"Mach Learn"},{"key":"R37-20260622","doi-asserted-by":"crossref","first-page":"bbad002","DOI":"10.1093\/bib\/bbad002","article-title":"A review on longitudinal data analysis with random forest.","volume":"24","author":"Hu","year":"2023","journal-title":"Brief Bioinform"},{"key":"R38-20260622","first-page":"44","article-title":"Data mining in clinical big data: the frequently used databases, steps, and methodological models.","volume":"8","author":"Wu","year":"2021","journal-title":"Mil Med Res"},{"key":"R39-20260622","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.3390\/diagnostics11122242","article-title":"Predicting prolonged length of ICU stay through machine learning.","volume":"11","author":"Wu","year":"2021","journal-title":"Diagnostics (Basel)"},{"key":"R40-20260622","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1186\/s12911-021-01688-3","article-title":"Improving random forest predictions in small datasets from two-phase sampling designs.","volume":"21","author":"Han","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"R41-20260622","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1177\/19458924251322081","article-title":"Using machine learning models to diagnose chronic rhinosinusitis: analysis of pre-treatment patient-generated health data to predict cardinal symptoms and sinonasal inflammation.","volume":"39","author":"Raghavan","year":"2025","journal-title":"Am J Rhinol Allergy"},{"key":"R42-20260622","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1002\/alr.22632","article-title":"Machine learning of biomarkers and clinical observation to predict eosinophilic chronic rhinosinusitis: a pilot study.","volume":"11","author":"Thorwarth","year":"2021","journal-title":"Int Forum Allergy Rhinol"},{"key":"R43-20260622","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1159\/000490694","article-title":"From multiple organ support therapy to extracorporeal organ support in critically ill patients.","volume":"48","author":"Ronco","year":"2019","journal-title":"Blood Purif"},{"key":"R44-20260622","doi-asserted-by":"crossref","first-page":"1918","DOI":"10.2215\/CJN.02660221","article-title":"Classification of uremic toxins and their role in kidney failure.","volume":"16","author":"Rosner","year":"2021","journal-title":"Clin J Am Soc Nephrol"},{"key":"R45-20260622","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.aucc.2012.10.004","article-title":"Fever effects and treatment in critical care: literature review.","volume":"26","author":"Kiekkas","year":"2013","journal-title":"Aust Crit Care"},{"key":"R46-20260622","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1186\/s40001-024-01756-0","article-title":"Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers.","volume":"29","author":"Zhang","year":"2024","journal-title":"Eur J Med Res"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000048376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T18:08:12Z","timestamp":1786039692000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000048376"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":43,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000048376","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"2025-10-30","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-01","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}