{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T07:08:47Z","timestamp":1787987327162,"version":"build-2784847793"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T00:00:00Z","timestamp":1758758400000},"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. Public Health"],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To develop and internally validate interpretable machine learning (ML) models for predicting individual central line-associated bloodstream infection (CLABSI) risk in adult ICU patients with central venous catheters (CVCs) using the MIMIC-IV database.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We conducted a retrospective observational cohort study using the MIMIC-IV database. Adult ICU patients with both central venous catheter placement and blood culture evaluation were included. Patients were classified into CLABSI and non-CLABSI cohorts based on central venous catheter tip culture results. A comprehensive set of demographic, physiological, laboratory, therapeutic, and nursing variables was extracted. Feature selection employed Least Absolute Shrinkage and Selection Operator (LASSO) regression. Seven machine learning (ML) models\u2014logistic regression, decision tree, random forest, XGBoost, support vector machine, neural network, and gradient boosting\u2014were developed and compared. Discrimination and calibration were assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F1 score, and Brier score. The optimal model was interpreted with SHAP (SHapley Additive exPlanations) values to elucidate feature contributions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Among 11,999 ICU patients, 519 (4.3%) developed CLABSI. CLABSI patients were younger (61.0 vs. 66.0\u202fyears), had higher rates of multi-lumen catheters (91.3 vs. 63.6%), mechanical ventilation (90.9 vs. 74.0%), and dialysis (34.9 vs. 7.2%; all <jats:italic>p<\/jats:italic>\u202f&amp;lt;\u202f0.001). The random forest model achieved optimal performance (AUC 0.950, 95% CI 0.931\u20130.966; sensitivity 0.904, specificity 0.865), outperforming traditional models. SHAP analysis identified ICU length of stay, unique caregivers, and arterial catheterization as top predictors. CLABSI cases exhibited prolonged ICU stays, increased caregiver exposure, and elevated inflammatory markers. Decision curve analysis confirmed clinical utility, with robust performance maintained in sensitivity analyses.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Machine learning models, particularly the random forest model, accurately predict CLABSI risk in ICU patients. The use of interpretable AI techniques such as SHAP enhances transparency and provides actionable insights for clinical practice. These findings support the development of early warning systems to reduce CLABSI incidence and improve patient outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpubh.2025.1675077","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T05:30:46Z","timestamp":1758778246000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Artificial intelligence-driven prediction and interpretation of central line-associated bloodstream infections in ICU: insights from the MIMIC-IV database"],"prefix":"10.3389","volume":"13","author":[{"given":"Yang","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiali","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaosheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinglan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1056\/NEJMra2213296","article-title":"Prevention of central line\u2013associated bloodstream infections","volume":"389","author":"O\u2019Grady","year":"2023","journal-title":"N Engl J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1017\/ice.2014.86","article-title":"Central line-associated bloodstream infections in non-ICU inpatient wards: a 2-year analysis","volume":"36","author":"Rhee","year":"2015","journal-title":"Infect Control Hosp Epidemiol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"17","DOI":"10.5005\/jp-journals-10071-23325","article-title":"Incidence, microbiological profile, and impact of preventive measures on central line-associated bloodstream infection in liver care intensive care unit","volume":"24","author":"Khodare","year":"2020","journal-title":"Indian J Crit Care Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"6","DOI":"10.31586\/ojms.2024.941","article-title":"Use of chlorhexidine-impregnated dressings and early catheter exchange to reduce the onset of central line-associated bloodstream infections: a case-control study in a cardiac intensive care unit","volume":"4","author":"Kamoshita","year":"2024","journal-title":"Open J Med Sci"},{"key":"ref5","volume-title":"Central line\u2013associated blood stream infections of in StatPearls","author":"Haddadin","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1007\/s12672-025-02685-y","article-title":"XGBoost model for predicting erectile dysfunction risk after radical prostatectomy: development and validation using machine learning","volume":"16","author":"Jiang","year":"2025","journal-title":"Discov Oncol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1186\/s13054-024-04948-6","article-title":"A scoping review of machine learning for sepsis prediction-feature engineering strategies and model performance: a step towards explainability","volume":"28","author":"Bomrah","year":"2024","journal-title":"Crit Care"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1186\/s13054-024-04866-7","article-title":"Real-time machine learning model to predict short-term mortality in critically ill patients: development and international validation","volume":"28","author":"Lim","year":"2024","journal-title":"Crit Care"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"103651","DOI":"10.1016\/j.isci.2021.103651","article-title":"Evaluating machine learning models for sepsis prediction: a systematic review of methodologies","volume":"25","author":"Deng","year":"2022","journal-title":"iScience"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1186\/s12879-025-10854-1","article-title":"Hospital-wide, dynamic, individualized prediction of central line-associated bloodstream infections-development and temporal evaluation of six prediction models","volume":"25","author":"Albu","year":"2025","journal-title":"BMC Infect Dis"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"109276","DOI":"10.1016\/j.thromres.2025.109276","article-title":"Development and validation of machine learning-based prediction model for central venous access device-related thrombosis in children","volume":"247","author":"Fu","year":"2025","journal-title":"Thromb Res"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"102158","DOI":"10.1016\/j.artmed.2021.102158","article-title":"The three ghosts of medical AI: can the black-box present deliver?","volume":"124","author":"Quinn","year":"2022","journal-title":"Artif Intell Med"},{"key":"ref13","author":"Nohara","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"ref15","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s41512-025-00194-8","article-title":"A comparison of modeling approaches for static and dynamic prediction of central line-associated bloodstream infections using electronic health records (part 2): random forest models","volume":"9","author":"Albu","year":"2025","journal-title":"Diagn Progn Res"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1280434","DOI":"10.3389\/fpubh.2023.1280434","article-title":"Drug prescription patterns and their association with mortality and hospitalization duration in COVID-19 patients: insights from big data","volume":"11","author":"Mehrizi","year":"2023","journal-title":"Front Public Health"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3390\/antibiotics14030271","article-title":"Incidence, compliance, and risk factor associated with central line-associated bloodstream infection (CLABSI) in intensive care unit (ICU) patients: a multicenter study in an upper middle-income country","volume":"14","author":"Rajandra","year":"2025","journal-title":"Antibiotics (Basel)"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.jhin.2024.08.002","article-title":"Impact of central-line-associated bloodstream infections and catheter-related bloodstream infections: a systematic review and meta-analysis","volume":"152","author":"Elangovan","year":"2024","journal-title":"J Hosp Infect"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1186\/s13054-015-0993-7","article-title":"Clinical review: intensive care unit acquired weakness","volume":"19","author":"Hermans","year":"2015","journal-title":"Crit Care"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1016\/j.chest.2016.03.045","article-title":"ICU-acquired weakness","volume":"150","author":"Jolley","year":"2016","journal-title":"Chest"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e40954","DOI":"10.7759\/cureus.40954","article-title":"Clinical impacts and risk factors for central line-associated bloodstream infection: a systematic review","volume":"15","author":"Alshahrani","year":"2023","journal-title":"Cureus"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s13756-022-01131-w","article-title":"Duration of central venous catheter placement and central line-associated bloodstream infections after the adoption of prevention bundles: a two-year retrospective study","volume":"11","author":"Pitiriga","year":"2022","journal-title":"Antimicrob Resist Infect Control"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jhin.2023.11.020","article-title":"Central-line-associated bloodstream infection burden among Dutch neonatal intensive care units","volume":"144","author":"Jansen","year":"2024","journal-title":"J Hosp Infect"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.bj.2020.08.007","article-title":"Endothelial glycocalyx damage as a systemic inflammatory microvascular endotheliopathy in COVID-19","volume":"43","author":"Yamaoka-Tojo","year":"2020","journal-title":"Biom J"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1186\/s13054-019-2534-2","article-title":"Intravenous fluid resuscitation is associated with septic endothelial glycocalyx degradation","volume":"23","author":"Hippensteel","year":"2019","journal-title":"Crit Care"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s13613-024-01301-6","article-title":"Managing sepsis and septic shock in an endothelial glycocalyx-friendly way: from the viewpoint of surviving sepsis campaign guidelines","volume":"14","author":"Iba","year":"2024","journal-title":"Ann Intensive Care"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"dlaa002","DOI":"10.1093\/jacamr\/dlaa002","article-title":"The potential for developing new antimicrobial resistance from the use of medical devices containing chlorhexidine, minocycline, rifampicin and their combinations: a systematic review","volume":"2","author":"Reitzel","year":"2020","journal-title":"JAC Antimicrob Resist"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1186\/s12955-025-02398-4","article-title":"Predicting quality of life in people living with HIV: a machine learning model integrating multidimensional determinants","volume":"23","author":"Xie","year":"2025","journal-title":"Health Qual Life Outcomes"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1675077\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T05:30:47Z","timestamp":1758778247000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1675077\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,25]]},"references-count":29,"alternative-id":["10.3389\/fpubh.2025.1675077"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1675077","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,25]]},"article-number":"1675077"}}