{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:07:18Z","timestamp":1780423638008,"version":"3.54.1"},"reference-count":48,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"High-level Medical Team Project in Baoan","award":["202405"],"award-info":[{"award-number":["202405"]}]},{"name":"Medical and Health Scientific Research Project of Shenzhen Bao \u2019an District in 2023","award":["2023JD118"],"award-info":[{"award-number":["2023JD118"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The neutrophil-to-lymphocyte ratio (NLR) has shown inconsistent prognostic value in individuals with sepsis. This study aimed to clarify its ability to predict 28-day mortality via a machine learning-based analysis of a large ICU database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective analysis employed data from the MIMIC-IV database (v3.1). The Boruta algorithm combined with XGBoost was used for two-stage feature selection. Patients were stratified by NLR quartiles into three groups (low:\u2009&lt;4.34, intermediate: 4.34\u201314.70, and high:\u2009&gt;14.70). This study defined 28-day mortality as the primary outcome. Associations between the NLR and mortality were evaluated by using multivariable logistic regression (progressively adjusted for demographic, clinical, and machine learning-derived features), along with restricted cubic splines. Sensitivity analyses included quantifying NLR feature importance via machine learning and performing subgroup analyses across clinical strata.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>This cohort study included 4,376 patients with a 28-day mortality rate of 18.4%. Compared with the SOFA and SAPS II scores, the prediction performance of XGBoost was superior (ROC-AUC 0.875; 95% CI 0.854\u20130.896; PR-AUC 0.603). Although the NLR ranked 14th in SHAP-based feature importance, multivariable analysis confirmed its independent association with elevated mortality risk: 28-day (OR 1.16; 95% CI 1.06\u20131.27; p\u2009&lt;\u20090.001), in-hospital (OR 1.13; 95% CI 1.03\u20131.24; p\u2009&lt;\u20090.001), and ICU (OR 1.14; 95% CI 1.03\u20131.25; p\u2009=\u20090.008). Stratified analyses indicated consistent mortality associations for the NLR, with enhanced predictive value being observed in patients aged &gt;45 years and those with SOFA scores \u22644 or SAPS II scores &gt;29. Specifically, patients \u226565 years of age demonstrated a 17% increase in 28-day mortality risk (p\u2009=\u20090.019), and patients with a SOFA score \u22644 exhibited a greater than 20% elevated risk across all of the endpoints (p\u2009&lt;\u20090.001), whereas no significant association was observed in the SOFA \u22659 subgroup (p\u2009=\u20090.369).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The NLR effectively identifies inflammation-driven mortality risk for early sepsis patients but fails to predict outcomes for patients with terminal organ failure. This biphasic predictive pattern highlights the unique value of the NLR in moderate sepsis risk stratification but cautions against its use in cases of advanced disease. Its value lies in dynamic monitoring rather than static risk assessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0348676","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:34:11Z","timestamp":1780421651000},"page":"e0348676","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["The prognostic value of the early neutrophil-to-lymphocyte ratio for 28-day mortality in sepsis patients: A machine learning-based investigation of the MIMIC database"],"prefix":"10.1371","volume":"21","author":[{"given":"Jiyang","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianwen","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingwang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houwang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijun","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huachu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2790-7468","authenticated-orcid":true,"given":"Jianbo","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"issue":"11","key":"pone.0348676.ref001","doi-asserted-by":"crossref","DOI":"10.1097\/CCM.0000000000005357","article-title":"Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021","volume":"49","author":"L Evans","year":"2021","journal-title":"Crit Care Med"},{"issue":"8","key":"pone.0348676.ref002","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1007\/s00134-020-06151-x","article-title":"Incidence and mortality of hospital- and ICU-treated sepsis: results from an updated and expanded systematic review and meta-analysis","volume":"46","author":"C Fleischmann-Struzek","year":"2020","journal-title":"Intensive Care Med"},{"issue":"3","key":"pone.0348676.ref003","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1164\/rccm.201504-0781OC","article-title":"Assessment of global incidence and mortality of hospital-treated sepsis. Current estimates and limitations","volume":"193","author":"C Fleischmann","year":"2015","journal-title":"Am J Respir Crit Care Med"},{"issue":"4","key":"pone.0348676.ref004","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.jhin.2017.05.005","article-title":"Screening for sepsis in general hospitalized patients: a systematic review","volume":"96","author":"L Alberto","year":"2017","journal-title":"J Hosp Infect"},{"issue":"4","key":"pone.0348676.ref005","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1016\/j.chest.2016.06.020","article-title":"Identifying patients with sepsis on the hospital wards","volume":"151","author":"P Bhattacharjee","year":"2017","journal-title":"Chest"},{"issue":"6","key":"pone.0348676.ref006","article-title":"Automated monitoring compared to standard care for the early detection of sepsis in critically ill patients","volume":"6","author":"S Warttig","year":"2018","journal-title":"Cochrane Database Syst Rev"},{"issue":"6","key":"pone.0348676.ref007","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1002\/jhm.2347","article-title":"Diagnostic accuracy and effectiveness of automated electronic sepsis alert systems: a systematic review","volume":"10","author":"AN Makam","year":"2015","journal-title":"J Hosp Med"},{"issue":"1","key":"pone.0348676.ref008","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1186\/s13054-023-04750-w","article-title":"Prognostic differences in sepsis caused by gram-negative bacteria and gram-positive bacteria: a systematic review and meta-analysis","volume":"27","author":"A Tang","year":"2023","journal-title":"Crit Care"},{"issue":"3","key":"pone.0348676.ref009","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1001\/jama.2016.20328","article-title":"Prognostic accuracy of the SOFA score, SIRS criteria, and qSOFA score for in-hospital mortality among adults with suspected infection admitted to the intensive care unit","volume":"317","author":"EP Raith","year":"2017","journal-title":"JAMA"},{"issue":"5","key":"pone.0348676.ref010","first-page":"224","article-title":"Better prognostic ability of NEWS2, SOFA and SAPS-II in septic patients","volume":"159","author":"V Moreno-Torres","year":"2022","journal-title":"Med Clin (Barc)"},{"issue":"1","key":"pone.0348676.ref011","doi-asserted-by":"crossref","first-page":"122","DOI":"10.3855\/jidc.18526","article-title":"The comparison of scoring systems: SOFA, APACHE-II, LODS, MODS, and SAPS-II in critically ill elderly sepsis patients","volume":"18","author":"B Tekin","year":"2024","journal-title":"J Infect Dev Ctries"},{"issue":"1","key":"pone.0348676.ref012","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1038\/s41598-020-79431-7","article-title":"Neutrophil-to-lymphocyte ratio and mortality in the United States general population","volume":"11","author":"M Song","year":"2021","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0348676.ref013","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1186\/s12964-019-0471-y","article-title":"The regulatory roles of neutrophils in adaptive immunity","volume":"17","author":"Y Li","year":"2019","journal-title":"Cell Commun Signal"},{"issue":"7","key":"pone.0348676.ref014","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1136\/emermed-2014-204071","article-title":"Neutrophil to lymphocyte count ratio as an early indicator of blood stream infection in the emergency department","volume":"32","author":"R Lowsby","year":"2015","journal-title":"Emerg Med J"},{"issue":"7","key":"pone.0348676.ref015","doi-asserted-by":"crossref","first-page":"3636","DOI":"10.3390\/ijms23073636","article-title":"Neutrophil to lymphocyte ratio: an emerging marker of the relationships between the immune system and diseases","volume":"23","author":"A Buonacera","year":"2022","journal-title":"Int J Mol Sci"},{"issue":"8","key":"pone.0348676.ref016","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.3390\/vaccines10081233","article-title":"The role of neutrophil-to-lymphocyte ratio in risk stratification and prognostication of COVID-19: a systematic review and meta-analysis","volume":"10","author":"A Parthasarathi","year":"2022","journal-title":"Vaccines (Basel)"},{"issue":"6","key":"pone.0348676.ref017","doi-asserted-by":"crossref","first-page":"225","DOI":"10.3390\/jpm15060225","article-title":"Novel biomarkers for SARS-CoV-2 infection: a systematic review and meta-analysis","volume":"15","author":"SW Snopkowska Lesniak","year":"2025","journal-title":"J Pers Med"},{"key":"pone.0348676.ref018","doi-asserted-by":"crossref","first-page":"1336456","DOI":"10.3389\/fimmu.2024.1336456","article-title":"Predictive value of the neutrophil-to-lymphocyte ratio in the prognosis and risk of death for adult sepsis patients: a meta-analysis","volume":"15","author":"H Wu","year":"2024","journal-title":"Front Immunol"},{"issue":"5","key":"pone.0348676.ref019","article-title":"The neutrophil-to-lymphocyte-ratio as diagnostic and prognostic tool in sepsis and septic shock","volume":"69","author":"T Schupp","year":"2023","journal-title":"Clin Lab"},{"issue":"23","key":"pone.0348676.ref020","doi-asserted-by":"crossref","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"A Goldberger","year":"2000","journal-title":"Circulation"},{"issue":"1","key":"pone.0348676.ref021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"AEW Johnson","year":"2023","journal-title":"Sci Data"},{"issue":"7","key":"pone.0348676.ref022","doi-asserted-by":"crossref","first-page":"3641","DOI":"10.1007\/s10238-023-01029-w","article-title":"Association between admission systemic immune-inflammation index and mortality in critically ill patients with sepsis: a retrospective cohort study based on MIMIC-IV database","volume":"23","author":"D Jiang","year":"2023","journal-title":"Clin Exp Med"},{"issue":"3","key":"pone.0348676.ref023","first-page":"343","article-title":"Strategies for dealing with missing data in clinical trials: from design to analysis","volume":"86","author":"JD Dziura","year":"2013","journal-title":"Yale J Biol Med"},{"issue":"1","key":"pone.0348676.ref024","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest--non-parametric missing value imputation for mixed-type data","volume":"28","author":"DJ Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"issue":"2","key":"pone.0348676.ref025","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1093\/bib\/bbx124","article-title":"Evaluation of variable selection methods for random forests and omics data sets","volume":"20","author":"F Degenhardt","year":"2019","journal-title":"Brief Bioinform"},{"key":"pone.0348676.ref026","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System","author":"T Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"issue":"1","key":"pone.0348676.ref027","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"pone.0348676.ref028","doi-asserted-by":"crossref","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Y Nohara","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"pone.0348676.ref029","doi-asserted-by":"crossref","first-page":"24081","DOI":"10.1038\/s41598-024-75050-8","article-title":"A retrospective study utilized MIMIC-IV database to explore the potential association between triglyceride-glucose index and mortality in critically ill patients with sepsis","volume":"14","author":"J Lou","year":"2024","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0348676.ref030","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1186\/s12933-023-02041-w","article-title":"Association between triglyceride-glucose index and in-hospital mortality in critically ill patients with sepsis: analysis of the MIMIC-IV database","volume":"22","author":"R Zheng","year":"2023","journal-title":"Cardiovasc Diabetol"},{"key":"pone.0348676.ref031","doi-asserted-by":"crossref","first-page":"1602921","DOI":"10.3389\/fcimb.2025.1602921","article-title":"The non-linear association between creatinine-to-albumin ratio and medium-term mortality in patients with sepsis accompanied by acute kidney injury in the intensive care unit: a retrospective study based on the MIMIC database and external validation","volume":"15","author":"J Lou","year":"2025","journal-title":"Front Cell Infect Microbiol"},{"issue":"3","key":"pone.0348676.ref032","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"T Saito","year":"2015","journal-title":"PLoS One"},{"issue":"12","key":"pone.0348676.ref033","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1016\/j.ajem.2014.09.001","article-title":"Prognostic importance of neutrophil-lymphocyte ratio in critically ill patients: short- and long-term outcomes","volume":"32","author":"NB Akilli","year":"2014","journal-title":"Am J Emerg Med"},{"issue":"30","key":"pone.0348676.ref034","doi-asserted-by":"crossref","DOI":"10.1097\/MD.0000000000029343","article-title":"The association between the neutrophil to lymphocyte ratio and in-hospital mortality among sepsis patients: a prospective study","volume":"101","author":"RB Chebl","year":"2022","journal-title":"Medicine (Baltimore)"},{"issue":"2","key":"pone.0348676.ref035","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.ajem.2016.10.055","article-title":"Neutrophil-to-lymphocyte ratio as a prognostic marker in critically-ill septic patients","volume":"35","author":"SY Hwang","year":"2017","journal-title":"Am J Emerg Med"},{"key":"pone.0348676.ref036","doi-asserted-by":"crossref","first-page":"741015","DOI":"10.3389\/fmed.2021.741015","article-title":"Efficiency of monocyte\/high-density lipoprotein cholesterol ratio combined with neutrophil\/lymphocyte ratio in predicting 28-day mortality in patients with sepsis","volume":"8","author":"J-Y Li","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"pone.0348676.ref037","article-title":"Predictive value of immune cell counts and neutrophil-to-lymphocyte ratio for 28-day mortality in patients with sepsis caused by intra-abdominal infection","volume":"9","author":"S Liu","year":"2021","journal-title":"Burns Trauma"},{"key":"pone.0348676.ref038","doi-asserted-by":"crossref","first-page":"639735","DOI":"10.3389\/fimmu.2021.639735","article-title":"Effects of neutrophil-to-lymphocyte ratio combined with interleukin-6 in predicting 28-day mortality in patients with sepsis","volume":"12","author":"S Liu","year":"2021","journal-title":"Front Immunol"},{"key":"pone.0348676.ref039","doi-asserted-by":"crossref","first-page":"109778","DOI":"10.1016\/j.intimp.2023.109778","article-title":"Neutrophil-to-lymphocyte ratio as a prognostic marker of mortality and disease severity in septic acute kidney injury patients: a retrospective study","volume":"116","author":"W Wei","year":"2023","journal-title":"Int Immunopharmacol"},{"issue":"5","key":"pone.0348676.ref040","doi-asserted-by":"crossref","first-page":"1843","DOI":"10.21037\/jtd-20-1169","article-title":"The association between neutrophil-to-lymphocyte count ratio and mortality in septic patients: a retrospective analysis of the MIMIC-III database","volume":"12","author":"W Ye","year":"2020","journal-title":"J Thorac Dis"},{"key":"pone.0348676.ref041","doi-asserted-by":"crossref","first-page":"1133351","DOI":"10.3389\/fimmu.2023.1133351","article-title":"Blood count derangements after sepsis and association with post-hospital outcomes","volume":"14","author":"SJ Denstaedt","year":"2023","journal-title":"Front Immunol"},{"issue":"1","key":"pone.0348676.ref042","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1186\/s12967-023-04717-z","article-title":"Neutrophil-to-lymphocyte ratio (NLR) predicts mortality in hospitalized geriatric patients independent of the admission diagnosis: a multicenter prospective cohort study","volume":"21","author":"M Di Rosa","year":"2023","journal-title":"J Transl Med"},{"issue":"6","key":"pone.0348676.ref043","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1097\/SLA.0000000000003297","article-title":"Utilizing machine learning methods for preoperative prediction of postsurgical mortality and intensive care unit admission","volume":"272","author":"CJ Chiew","year":"2020","journal-title":"Ann Surg"},{"issue":"3","key":"pone.0348676.ref044","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0092209","article-title":"Area under precision-recall curves for weighted and unweighted data","volume":"9","author":"J Keilwagen","year":"2014","journal-title":"PLoS One"},{"issue":"1","key":"pone.0348676.ref045","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s13054-014-0731-6","article-title":"The association between the neutrophil-to-lymphocyte ratio and mortality in critical illness: an observational cohort study","volume":"19","author":"JD Salciccioli","year":"2015","journal-title":"Crit Care"},{"key":"pone.0348676.ref046","doi-asserted-by":"crossref","first-page":"1603104","DOI":"10.3389\/fcimb.2025.1603104","article-title":"The J-shaped association between the ratio of neutrophil counts to prognostic nutritional index and mortality in ICU patients with sepsis: a retrospective study based on the MIMIC database","volume":"15","author":"J Lou","year":"2025","journal-title":"Front Cell Infect Microbiol"},{"key":"pone.0348676.ref047","doi-asserted-by":"crossref","first-page":"1602016","DOI":"10.3389\/fnut.2025.1602016","article-title":"The V-shaped association between the ratio of neutrophil counts to prognostic nutritional index and 30-, 60-, and 90-day mortality in elderly critically ill patients aged 65 and older with sepsis: a retrospective study based on the MIMIC database","volume":"12","author":"J Cai","year":"2025","journal-title":"Front Nutr"},{"issue":"3","key":"pone.0348676.ref048","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1080\/23744235.2017.1388537","article-title":"Pitfalls in studies of eosinopenia and neutrophil-to-lymphocyte count ratio","volume":"50","author":"S Karakonstantis","year":"2018","journal-title":"Infect Dis (Lond)"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:34:20Z","timestamp":1780421660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348676"}},"subtitle":[],"editor":[{"given":"Chiara","family":"Lazzeri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,2]]},"references-count":48,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348676","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,2]]}}}