{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T02:18:27Z","timestamp":1786501107819,"version":"build-2736575974"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"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. Cell. Infect. Microbiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Intensive care unit\u2013acquired bloodstream infections (ICU-BSIs) are among the most prevalent healthcare-associated infections and a major cause of mortality among ICU patients. We developed a machine learning (ML)\u2013based model to predict the prognosis of ICU-BSIs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Adult patients with blood cultures drawn \u226548 hours after ICU admission were included: the Second Affiliated Hospital of Anhui Medical University (AMU, China) and the Medical Information Mart for Intensive Care IV (MIMIC-IV, USA). The AMU dataset was used for model training and internal validation, and the MIMIC-IV dataset served as the external validation set. The model incorporated routinely collected, easily obtainable clinical variables, including several representing the average rate of change in laboratory indicators. After comparing multiple algorithms, eXtreme Gradient Boosting (XGBoost) was selected and optimized using cross-validation and grid search.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A total of 1,903 patients from AMU and 3,496 from MIMIC-IV were included. In both cohorts, antibiotic duration, platelet count, serum creatinine, duration of invasive mechanical ventilation, and Charlson Comorbidity Index (CCI) were significantly associated with 28-day mortality (\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt;\u00a00.001). The XGBoost model using 33 variables showed strong discrimination, with an AUROC of 0.92 (95% CI 0.90\u20130.94) for training and 0.85 (95% CI 0.80\u20130.90) for internal validation. Shapley Additive Explanations (SHAP) identified the 10 most important variables; a simplified model using these maintained good accuracy, with AUROC values of 0.81 (95% CI 0.76\u20130.85) and 0.71 (95% CI 0.70\u20130.73) for the internal and external validation sets, respectively. In pathogen subgroups, the internal AUROC was 0.91 (95% CI 0.87\u20130.94) and 0.90 (95% CI 0.86\u20130.93) for Gram-positive (Gram+) and Gram-negative (Gram\u2212) infections, with external validation AUROCs of 0.72 (95% CI 0.66\u20130.77) and 0.72 (95% CI 0.62\u20130.82), respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We developed and externally validated a personalized ML-based prognostic model for ICU-BSIs using multicenter time-series data. This model may facilitate early identification of high-risk patients, enabling timely intervention and optimized ICU resource allocation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcimb.2025.1636886","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T06:45:23Z","timestamp":1761720323000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Personalized machine learning\u2013based prognostic model for ICU-acquired bloodstream infections"],"prefix":"10.3389","volume":"15","author":[{"given":"Shijun","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilei","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiujuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanchang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guomei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanjun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jinf.2016.11.001","article-title":"Attributable mortality of ICU-acquired bloodstream infections: impact of the source, causative micro-organism, resistance profile and antimicrobial therapy","volume":"74","author":"Adrie","year":"2017","journal-title":"J. Infect."},{"key":"B2","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/S0140-6736(04)17667-8","article-title":"Septic shock","volume":"365","author":"Annane","year":"2005","journal-title":"Lancet"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.iccn.2022.103227","article-title":"Healthcare-associated infections in adult intensive care unit patients: changes in epidemiology, diagnosis, prevention and contributions of new technologies","volume":"70","author":"Blot","year":"2022","journal-title":"Intensive Crit. Care Nurs."},{"key":"B4","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1007\/s00134-024-07348-0","article-title":"The role of centre and country factors on process and outcome indicators in critically ill patients with hospital-acquired bloodstream infections","volume":"50","author":"Buetti","year":"2024","journal-title":"Intensive Care Med."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.936662","article-title":"Association of longitudinal platelet count trajectory with ICU mortality: a multi-cohort study","volume":"13","author":"Chen","year":"2022","journal-title":"Front. Immunol."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2334-9-115","article-title":"Retrospective analysis of nosocomial infections in the intensive care unit of a tertiary hospital in China during 2003 and 2007","volume":"9","author":"Ding","year":"2009","journal-title":"BMC Infect. Dis."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1086\/500318","article-title":"Excess risk of death from intensive care unit-acquired nosocomial bloodstream infections: a reappraisal","volume":"42","author":"Garrouste-Orgeas","year":"2006","journal-title":"Clin. Infect. Dis."},{"key":"B8","doi-asserted-by":"publisher","first-page":"109666","DOI":"10.1016\/j.engappai.2024.109666","article-title":"Fine-tuning pre-trained networks with emphasis on image segmentation: a multi-network approach for enhanced breast cancer detection","volume":"139","author":"Ghafariasl","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B9","doi-asserted-by":"publisher","first-page":"R31","DOI":"10.1186\/cc13724","article-title":"Platelet mitochondrial membrane depolarization reflects disease severity in patients with sepsis and correlates with clinical outcome","volume":"18","author":"Gr\u00fcndler","year":"2014","journal-title":"Crit. Care"},{"key":"B10","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.ajic.2008.03.002","article-title":"CDC\/NHSN surveillance definition of health care-associated infection and criteria for specific types of infections in the acute care setting","volume":"36","author":"Horan","year":"2008","journal-title":"Am. J. Infect. Control"},{"key":"B11","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1186\/s12967-020-02620-5","article-title":"Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost","volume":"18","author":"Hou","year":"2020","journal-title":"J. Transl. Med."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1186\/s13613-023-01233-7","article-title":"The critically ill older patient with sepsis: a narrative review","volume":"14","author":"Ibarz","year":"2024","journal-title":"Ann. Intensive Care"},{"key":"B13","doi-asserted-by":"publisher","first-page":"5014","DOI":"10.1182\/blood-2012-04-420661","article-title":"Bacteria differentially induce degradation of bcl-xl, a survival protein, by human platelets","volume":"120","author":"Kraemer","year":"2012","journal-title":"Blood"},{"key":"B14","doi-asserted-by":"publisher","first-page":"19377","DOI":"10.1038\/s41598-023-45039-w","article-title":"Skin cancer diagnosis (SCD) using artificial neural network (ANN) and improved gray wolf optimization (IGWO)","volume":"13","author":"Lai","year":"2023","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/S1473-3099(10)70258-9","article-title":"Clinical outcomes of health-care-associated infections and antimicrobial resistance in patients admitted to european intensive-care units: a cohort study","volume":"11","author":"Lambert","year":"2011","journal-title":"Lancet Infect. Dis."},{"key":"B16","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.jhin.2005.12.016","article-title":"Cost of intensive care unit-acquired bloodstream infections","volume":"63","author":"Laupland","year":"2006","journal-title":"J. Hosp. Infect."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04763-5","article-title":"Association of autoimmune diseases with the occurrence and 28-day mortality of sepsis: an observational and mendelian randomization study","volume":"27","author":"Li","year":"2023","journal-title":"Crit. Care"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.2147\/IDR.S373998","article-title":"Predictive value of a quick pitt bacteremia score for prognosis of patients with bloodstream infection secondary to urinary tract infection: a retrospective cohort study","volume":"15","author":"Li","year":"2022","journal-title":"Infect. Drug Resist."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1249695","article-title":"Clinical characteristics and prognosis of pneumonia-related bloodstream infections in the intensive care unit: a single-center retrospective study","volume":"11","author":"Liu","year":"2023","journal-title":"Front. Public Health"},{"key":"B20","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1186\/s12882-020-01974-8","article-title":"Rates, predictors, and mortality of sepsis-associated acute kidney injury: a systematic review and meta-analysis","volume":"21","author":"Liu","year":"2020","journal-title":"BMC Nephrol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1016\/j.cmi.2024.09.011","article-title":"Effect of adequacy of empirical antibiotic therapy for hospital-acquired bloodstream infections on intensive care unit patient prognosis: a causal inference approach using data from the eurobact2 study","volume":"30","author":"Loiodice","year":"2024","journal-title":"Clin. Microbiol. Infect."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1007\/s10096-021-04215-4","article-title":"Attributable mortality of ICU acquired bloodstream infections: a propensity-score matched analysis","volume":"40","author":"Massart","year":"2021","journal-title":"Eur. J. Clin. Microbiol. Infect. Dis."},{"key":"B23","doi-asserted-by":"publisher","first-page":"R161","DOI":"10.1186\/cc7160","article-title":"Evaluation of SOFA-based models for predicting mortality in the ICU: a systematic review","volume":"12","author":"Minne","year":"2008","journal-title":"Crit. Care"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1093\/cid\/civ560","article-title":"Epidemiology, management, and risk-adjusted mortality of ICU-acquired enterococcal bacteremia","volume":"61","author":"Ong","year":"2015","journal-title":"Clin. Infect. Dis."},{"key":"B25","doi-asserted-by":"publisher","first-page":"R100","DOI":"10.1186\/cc10114","article-title":"Acquired bloodstream infection in the intensive care unit: incidence and attributable mortality","volume":"15","author":"Prowle","year":"2011","journal-title":"Crit. Care"},{"key":"B26","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1186\/s12911-024-02655-4","article-title":"Machine learning-based prognostic model for 30-day mortality prediction in sepsis-3","volume":"24","author":"Rahman","year":"2024","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1262","DOI":"10.1002\/sim.7993","article-title":"Minimum sample size for developing a multivariable prediction model: part i - continuous outcomes","volume":"38","author":"Riley","year":"2019","journal-title":"Stat. Med."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1004179","article-title":"Patterns of antibiotic use, pathogens, and prediction of mortality in hospitalized neonates and young infants with sepsis: a global neonatal sepsis observational cohort study (NeoOBS)","volume":"20","author":"Russell","year":"2023","journal-title":"PLoS Med."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0194210","article-title":"ICU mortality following ICU-acquired primary bloodstream infections according to the type of pathogen: a prospective cohort study in 937 Germany ICUs, (2006-2015)","volume":"13","author":"Schwab","year":"2018","journal-title":"PLoS One"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1056\/NEJMoa1703058","article-title":"Time to treatment and mortality during mandated emergency care for sepsis","volume":"376","author":"Seymour","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (sepsis-3)","volume":"315","author":"Singer","year":"2016","journal-title":"JAMA"},{"key":"B32","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/s00134-022-06944-2","article-title":"Epidemiology and outcomes of hospital-acquired bloodstream infections in intensive care unit patients: the EUROBACT-2 international cohort study","volume":"49","author":"Tabah","year":"2023","journal-title":"Intensive Care Med."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0272352","article-title":"Relationship between liver dysfunction, lipoprotein concentration and mortality during sepsis","volume":"17","author":"Tanaka","year":"2022","journal-title":"PloS One"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1578","DOI":"10.1111\/cts.13030","article-title":"Diagnostic and prognostic capabilities of a biomarker and EMR-based machine learning algorithm for sepsis","volume":"14","author":"Taneja","year":"2021","journal-title":"CTS-Clin. Transl. Sci."},{"key":"B35","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.jhin.2008.01.012","article-title":"Estimates of the rate of acquisition of bacteraemia and associated excess mortality in a general intensive care unit: a 10 year study","volume":"69","author":"Thompson","year":"2008","journal-title":"J. Hosp. Infect."},{"key":"B36","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.ijantimicag.2007.10.015","article-title":"Daily cost of antimicrobial therapy in patients with intensive care unit-acquired, laboratory-confirmed bloodstream infection","volume":"31","author":"Vandijck","year":"2008","journal-title":"Int. J. Antimicrob. Agents"},{"key":"B37","doi-asserted-by":"publisher","first-page":"407","DOI":"10.3390\/biom15030407","article-title":"IL-6 baseline values and dynamic changes in predicting sepsis mortality: a systematic review and meta-analysis","volume":"15","author":"Varga","year":"2025","journal-title":"Biomolecules"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1478","DOI":"10.1001\/jama.2020.2717","article-title":"Prevalence and outcomes of infection among patients in intensive care units in 2017","volume":"323","author":"Vincent","year":"2020","journal-title":"JAMA"},{"key":"B39","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1007\/s11739-024-03732-2","article-title":"Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study","volume":"20","author":"Wang","year":"2025","journal-title":"Intern. Emerg. Med."},{"key":"B40","doi-asserted-by":"publisher","first-page":"20187","DOI":"10.1038\/s41598-024-71186-9","article-title":"Subphenotypes of platelet count trajectories in sepsis from multi-center ICU data","volume":"14","author":"Wang","year":"2024","journal-title":"Sci. Rep."},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2023.1167638","article-title":"Microbiology and prognostic prediction model of bloodstream infection in patients with hematological Malignancies","volume":"13","author":"Wang","year":"2023","journal-title":"Front. Cell. Infect. Microbiol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1007\/s00134-023-07138-0","article-title":"Sepsis-associated acute kidney injury in the intensive care unit: incidence, patient characteristics, timing, trajectory, treatment, and associated outcomes. A multicenter, observational study","volume":"49","author":"White","year":"2023","journal-title":"Intensive Care Med."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1093\/burnst\/tkae016","article-title":"Serial platelet count as a dynamic prediction marker of hospital mortality among septic patients","volume":"12","author":"Ye","year":"2024","journal-title":"Burns Trauma"},{"key":"B44","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s12873-022-00582-z","article-title":"Prediction of prognosis in elderly patients with sepsis based on machine learning (random survival forest)","volume":"22","author":"Zhang","year":"2022","journal-title":"BMC Emerg. Med."},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.iccn.2023.103549","article-title":"Machine learning-derived blood culture classification with both predictive and prognostic values in the intensive care unit: a retrospective cohort study","volume":"80","author":"Zhang","year":"2024","journal-title":"Intensive Crit. Care Nurs."},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2020.103081","article-title":"Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values","volume":"62","author":"Zhang","year":"2020","journal-title":"EBioMedicine"},{"key":"B47","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1186\/s12911-023-02383-1","article-title":"Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis","volume":"23","author":"Zhang","year":"2023","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"B48","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s40001-023-01593-7","article-title":"Interpretable machine learning model for early prediction of 28-day mortality in ICU patients with sepsis-induced coagulopathy: development and validation","volume":"29","author":"Zhou","year":"2024","journal-title":"Eur. J. Med. Res."}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2025.1636886\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T06:45:24Z","timestamp":1761720324000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2025.1636886\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":48,"alternative-id":["10.3389\/fcimb.2025.1636886"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2025.1636886","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"article-number":"1636886"}}