{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T02:26:19Z","timestamp":1790216779354,"version":"4.1.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study aimed to develop and conduct internal-external validation of a machine learning-based risk prediction model for multidrug-resistant (MDR) infection in mechanically ventilated intensive care unit (ICU) patients with chronic obstructive pulmonary disease (COPD), so as to provide evidence for early identification of high-risk individuals, optimization of antimicrobial strategies, and reduction of infection-related adverse outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 477 mechanically ventilated COPD ICU patients from the MIMIC-IV database, which were divided into a training set (333 cases) and an internal validation set (144 cases) at a ratio of 7:3, with MDR infection as the endpoint. Feature selection was performed using the Boruta algorithm and least absolute shrinkage and selection operator (LASSO). Seven machine learning algorithms were adopted for model training and construction with 10-fold cross-validation. Model performance was evaluated by AUC, accuracy, sensitivity, specificity, F1 score, calibration curve and decision curve analysis. External validation was conducted using 371 independent single-center clinical cases. The optimal model was interpreted by Shapley additive explanations (SHAP) analysis, and a predictive nomogram was established.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Five core predictors were identified, including red blood cell count, hemoglobin, hematocrit, blood urea nitrogen and creatinine. The K-nearest neighbor (KNN) model outperformed other algorithms, with an internal validation AUC of 0.642 (95% CI: 0.518-0.766) and an external validation AUC of 0.639 (95% CI: 0.508-0.769), accompanied by favorable accuracy, calibration and clinical net benefit. SHAP analysis indicated that hematocrit was the primary predictive factor; elevated red blood cell-related indexes increased MDR risk, while elevated blood urea nitrogen and creatinine decreased the risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>MDR infection in mechanically ventilated COPD ICU patients is closely associated with five routine laboratory indicators. The established KNN model and nomogram show favorable predictive value and generalizability, which can achieve rapid individualized risk quantification and serve as an auxiliary tool for early risk stratification and rational antimicrobial selection. It should be emphasized that this model is only used for preliminary screening and cannot replace microbial culture and drug susceptibility testing as the gold standard for definitive diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1899252","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:29:15Z","timestamp":1787203755000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Development and internal-external validation of a machine learning-based risk prediction model for multidrug resistance in mechanically ventilated ICU patients with chronic obstructive pulmonary disease"],"prefix":"10.3389","volume":"13","author":[{"given":"Weimin","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory, Affiliated Hospital of Jiangsu University, Zhenjiang","place":["Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Affiliated Hospital of Jiangsu University, Zhenjiang","place":["Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Affiliated Hospital of Jiangsu University, Zhenjiang","place":["Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Affiliated Hospital of Jiangsu University, Zhenjiang","place":["Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Xin","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy, Baoying People\u2019s Hospital, Baoying Clinical Medical College of Yangzhou University, Yangzhou","place":["Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minxuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Hospital-Acquired Infection Control, Affiliated Hospital of Jiangsu University, Zhenjiang","place":["Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1097\/01.NPR.0000000000000180","article-title":"An update on COPD prevention, diagnosis, and management: The 2024 GOLD Report.","volume":"49","author":"Patel","year":"2024","journal-title":"Nurse Pract"},{"key":"B2","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1186\/s12890-025-03857-w","article-title":"Efficacy of non-invasive ventilation in chronic obstructive pulmonary disease management: a systematic review and meta-analysis of randomized controlled trials.","volume":"25","author":"Li","year":"2025","journal-title":"BMC Pulm Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.2147\/COPD.S531611","article-title":"Acupuncture for chronic obstructive pulmonary disease: a 38-year bibliometric landscape of global research trends and knowledge evolution (1986-2024).","volume":"20","author":"Wu","year":"2025","journal-title":"Int J Chron Obstruct Pulmon Dis"},{"key":"B4","doi-asserted-by":"publisher","first-page":"10045","DOI":"10.21037\/jtd-2025-1180","article-title":"The prevalence of chronic obstructive pulmonary disease in high-altitude areas of China: a systematic review and meta-analysis.","volume":"17","author":"Wei","year":"2025","journal-title":"J Thorac Dis"},{"key":"B5","doi-asserted-by":"publisher","first-page":"S104","DOI":"10.5005\/jp-journals-10071-24677","article-title":"Guidelines for antibiotics prescription in critically Ill Patients.","volume":"28","author":"Khilnani","year":"2024","journal-title":"Indian J Crit Care Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e0106725","DOI":"10.1128\/spectrum.01067-25","article-title":"Epidemiology, clinical characteristics, and outcome of enterococcal bloodstream infections in critically Ill patients in China: a single-center retrospective 10-year analysis.","volume":"13","author":"Jin","year":"2025","journal-title":"Microbiol Spectr"},{"key":"B7","doi-asserted-by":"publisher","first-page":"111","DOI":"10.5492\/wjccm.v5.i2.111","article-title":"Association between infections caused by multidrug-resistant gram-negative bacteria and mortality in critically Ill patients.","volume":"5","author":"Paramythiotou","year":"2016","journal-title":"World J Crit Care Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1186\/s13756-025-01648-w","article-title":"Dutch guideline for the prevention and control of multidrug-resistant organisms in the hospital setting, 2024 update.","volume":"14","author":"Sussenbach","year":"2025","journal-title":"Antimicrob Resist Infect Control"},{"key":"B9","doi-asserted-by":"publisher","first-page":"106388","DOI":"10.1016\/j.jinf.2024.106388","article-title":"Machine learning and clinician predictions of antibiotic resistance in Enterobacterales bloodstream infections.","volume":"90","author":"Yuan","year":"2025","journal-title":"J Infect"},{"key":"B10","doi-asserted-by":"publisher","first-page":"862","DOI":"10.3390\/antibiotics14090862","article-title":"\u201cDusting Off the Cobwebs\u201d: rethinking how we use new antibiotics.","volume":"14","author":"Keck","year":"2025","journal-title":"Antibiotics"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e38571","DOI":"10.7759\/cureus.38571","article-title":"Multidrug resistance urinary tract infection in chronic kidney disease patients: an observational study.","volume":"15","author":"Haque Sumon","year":"2023","journal-title":"Cureus"},{"key":"B12","doi-asserted-by":"publisher","first-page":"300","DOI":"10.3390\/toxins12050300","article-title":"Chronic kidney disease-associated immune dysfunctions: impact of protein-bound uremic retention solutes on immune cells.","volume":"12","author":"Espi","year":"2020","journal-title":"Toxins"},{"key":"B13","doi-asserted-by":"publisher","first-page":"100117","DOI":"10.1016\/j.wroa.2021.100117","article-title":"Periodic chemical cleaning with urea: disintegration of biofilms and reduction of key biofilm-forming bacteria from reverse osmosis membranes.","volume":"13","author":"Sanawar","year":"2021","journal-title":"Water Res X"},{"key":"B14","doi-asserted-by":"publisher","first-page":"100004","DOI":"10.1016\/j.wroa.2018.10.001","article-title":"Enhanced biofilm solubilization by urea in reverse osmosis membrane systems.","volume":"1","author":"Sanawar","year":"2018","journal-title":"Water Res X"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1038\/jid.2012.42","article-title":"Urea uptake enhances barrier function and antimicrobial defense in humans by regulating epidermal gene expression.","volume":"132","author":"Grether-Beck","year":"2012","journal-title":"J Invest Dermatol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1038\/ki.2015.78","article-title":"Urea and protein carbamylation in ESRD: surrogate markers or partners in crime?","volume":"87","author":"Velasquez","year":"2015","journal-title":"Kidney Int"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1016\/j.intimp.2011.04.018","article-title":"Effect of creatine, creatinine, and creatine ethyl ester on TLR expression in macrophages.","volume":"11","author":"Leland","year":"2011","journal-title":"Int Immunopharmacol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e18438","DOI":"10.1371\/journal.pone.0018438","article-title":"Uremic toxins inhibit transport by breast cancer resistance protein and multidrug resistance protein 4 at clinically relevant concentrations.","volume":"6","author":"Mutsaers","year":"2011","journal-title":"PLoS One"},{"key":"B19","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1186\/s12884-025-08030-z","article-title":"Predicting the risk of threatened abortion using machine learning methods: a comparative study.","volume":"25","author":"Zhu","year":"2025","journal-title":"BMC Pregnancy Childbirth"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e42667","DOI":"10.1097\/MD.0000000000042667","article-title":"Predicting thyroid cancer recurrence using supervised CatBoost: A SHAP-based explainable AI approach.","volume":"104","author":"Hanani","year":"2025","journal-title":"Medicine."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1528696","DOI":"10.3389\/fmicb.2025.1528696","article-title":"Integrating sequencing methods with machine learning for antimicrobial susceptibility testing in pediatric infections: current advances and future insights.","volume":"16","author":"Zou","year":"2025","journal-title":"Front Microbiol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3390\/antibiotics12010077","article-title":"Multidrug-resistant acinetobacter baumannii infections in the united kingdom versus egypt: trends and potential natural products solutions.","volume":"12","author":"Elwakil","year":"2023","journal-title":"Antibiotic"},{"key":"B23","doi-asserted-by":"publisher","first-page":"10979","DOI":"10.1038\/s41598-020-67629-8","article-title":"Machine learning-based prediction of acute severity in infants hospitalized for bronchiolitis: a multicenter prospective study.","volume":"10","author":"Raita","year":"2020","journal-title":"Sci Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1788229","DOI":"10.3389\/fcimb.2026.1788229","article-title":"Development and validation of an interpretable machine learning-based model for predicting carbapenem-resistant Acinetobacter baumannii infection in postoperative ICU patients: a retrospective cohort study.","volume":"16","author":"Gao","year":"2026","journal-title":"Front Cell Infect Microbiol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"106244","DOI":"10.1016\/j.ijmedinf.2025.106244","article-title":"Construction and validation of a machine learning-based risk prediction model for invasive mechanical ventilation in AECOPD patients complicated with respiratory failure.","volume":"208","author":"Jiang","year":"2026","journal-title":"Int J Med Inform"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3723","DOI":"10.2147\/IDR.S527114","article-title":"Evaluation of the efficacy of a nomogram to predict multidrug-resistant pulmonary infections based on data from neurosurgery ward patients.","volume":"18","author":"Zhou","year":"2025","journal-title":"Infect Drug Resist"},{"key":"B27","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1177\/08850666261423499","article-title":"Machine learning in the ICU: predicting mortality in patients with carbapenem-resistant gram-negative bacilli bloodstream infections..","volume":"41","author":"G\u00fcler","year":"2026","journal-title":"J Intensive Care Med"},{"key":"B28","doi-asserted-by":"publisher","first-page":"587338","DOI":"10.2147\/IDR.S587338","article-title":"Predicting multidrug-resistant pneumonia: an interpretable machine learning model validated in us and chinese patient cohorts.","volume":"19","author":"Lan","year":"2026","journal-title":"Infect Drug Resist"},{"key":"B29","doi-asserted-by":"publisher","first-page":"7343469","DOI":"10.1155\/jonm\/7343469","article-title":"Mapping the contributing factors to missed nursing care in hospital settings during a global health crisis: a systematic scoping review.","volume":"2025","author":"Pourshaban","year":"2025","journal-title":"J Nurs Manag"},{"key":"B30","doi-asserted-by":"publisher","first-page":"782","DOI":"10.3390\/bioengineering12070782","article-title":"Visual perception and pre-attentive attributes in oncological data visualisation.","volume":"12","author":"Fusco","year":"2025","journal-title":"Bioengineerinng"},{"key":"B31","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1097\/PRS.0b013e318262f4c8","article-title":"The choice of controls for providing validity and evidence in clinical research.","volume":"130","author":"Malay","year":"2012","journal-title":"Plast Reconstr Surg"},{"key":"B32","doi-asserted-by":"publisher","first-page":"3178","DOI":"10.3390\/s25103178","article-title":"Virtual electroencephalogram acquisition: a review on electroencephalogram generative methods.","volume":"25","author":"You","year":"2025","journal-title":"Sensors."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1494","DOI":"10.1038\/s41591-025-03678-8","article-title":"Personalized inhaled bacteriophage therapy for treatment of multidrug-resistant Pseudomonas aeruginosa in cystic fibrosis.","volume":"31","author":"Chan","year":"2025","journal-title":"Nat Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.2147\/IDR.S459830","article-title":"Machine learning-based prediction model for multidrug-resistant organisms infections: performance evaluation and interpretability analysis.","volume":"18","author":"Zhao","year":"2025","journal-title":"Infect Drug Resist"},{"key":"B35","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1111\/j.1469-0691.2005.01148.x","article-title":"Clinical presentation of leptospirosis: a retrospective study of 34 patients admitted to a single institution in metropolitan France.","volume":"11","author":"Jaur\u00e9guiberry","year":"2005","journal-title":"Clin Microbiol Infect"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1899252\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:29:19Z","timestamp":1787203759000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1899252\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":35,"alternative-id":["10.3389\/fmed.2026.1899252"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1899252","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"article-number":"1899252"}}