{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T06:15:43Z","timestamp":1788156943013,"version":"build-2803163510"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"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. Pediatr."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and internally validate an explainable machine learning model for early mortality prediction in pediatric sepsis using routinely available clinical variables, to support clinical risk stratification and decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 752 children with sepsis admitted to the Pediatric Intensive Care Unit (PICU) at the Children's Hospital of Soochow University between January 1, 2019, and June 30, 2023, were retrospectively enrolled. Twenty-six routinely available clinical variables obtained within 24\u2005h after PICU admission were included. After data preprocessing, variables with excessive missing values, significant multicollinearity, or limited univariate predictive value were excluded. Clinically meaningful ratio-derived variables were constructed, and logarithmic transformation was applied to selected right-skewed continuous variables. Twelve supervised machine learning algorithms were developed and compared for mortality prediction. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), precision\u2013recall (PR) curve, decision curve analysis (DCA), and other performance metrics. Model interpretability was assessed using SHapley Additive exPlanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the 12 machine learning algorithms, extreme gradient boosting (XGBoost) achieved the best overall predictive performance. Following recursive feature elimination based on permutation importance, a simplified XGBoost model incorporating seven variables was established and interpreted using SHAP. In the internal validation cohort, the final model achieved an AUC of 0.803, with a sensitivity of 0.846, specificity of 0.696, accuracy of 0.722, and an F1 score of 0.512. The mean AUCs obtained from 5-fold and 10-fold cross-validation were 0.780\u2009\u00b1\u20090.044 and 0.771\u2009\u00b1\u20090.070, respectively, indicating good model stability. SHAP analysis identified pH, PaO\u2082, glucose, blood urea nitrogen (BUN), lactate dehydrogenase (LDH), international normalized ratio (INR), and the BUN-to-creatinine ratio (BUN\/Cr) as the features that made the greatest contributions to the final model's mortality predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An explainable XGBoost-based prediction model was developed for early mortality prediction in pediatric sepsis using seven routinely available clinical variables collected within 24\u2005h after PICU admission. The model demonstrated good discrimination, stability, and model-based interpretability, suggesting its potential as a practical tool for early risk stratification and individualized clinical management. Further multicenter external validation is warranted before routine clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fped.2026.1933395","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:40:32Z","timestamp":1788154832000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of an explainable XGBoost model for early mortality prediction in pediatric sepsis"],"prefix":"10.3389","volume":"14","author":[{"given":"Hong-mei","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Emergency Medicine, Children's Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-nong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Children's Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-bing","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Children's Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Hua","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Children's Hospital of Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s00134-019-05878-6","article-title":"Surviving sepsis campaign international guidelines for the management of septic shock and sepsis-associated organ dysfunction in children","volume":"46","author":"Weiss","year":"2020","journal-title":"Intensive Care Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/S2213-2600(18)30063-8","article-title":"The global burden of paediatric and neonatal sepsis: a systematic review the","volume":"6","author":"Fleischmann-Struzek","year":"2018","journal-title":"Lancet Respir Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1001\/jama.2024.0196","article-title":"Development and validation of the Phoenix criteria for pediatric sepsis and septic shock","volume":"331","author":"Sanchez-Pinto","year":"2024","journal-title":"JAMA"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e172352","DOI":"10.1001\/jamapediatrics.2017.2352","article-title":"Adaptation and validation of a pediatric sequential organ failure assessment score and evaluation of the sepsis-3 definitions in critically ill children","volume":"171","author":"Matics","year":"2017","journal-title":"JAMA Pediatr"},{"key":"B5","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1097\/00003246-199605000-00004","article-title":"PRISM III: an updated pediatric risk of mortality score","volume":"24","author":"Pollack","year":"1996","journal-title":"Crit Care Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1097\/CCM.0b013e31828a2bbd","article-title":"PELOD-2: an update of the PEdiatric logistic organ dysfunction score.","volume":"41","author":"Leteurtre","year":"2013","journal-title":"Crit Care Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e53","DOI":"10.3346\/jkms.2024.39.e53","article-title":"Early prediction of mortality for septic patients visiting emergency room based on explainable machine learning: a real-world multicenter study.","volume":"39","author":"Park","year":"2024","journal-title":"J Korean Med Sci"},{"key":"B8","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1097\/SHK.0000000000002394","article-title":"Efficacy of a sepsis clinical decision support system in identifying patients with sepsis in the emergency department","volume":"62","author":"Hou","year":"2024","journal-title":"Shock"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.08107","article-title":"Advanced meta-ensemble machine learning models for early and accurate sepsis prediction to improve patient outcomes","author":"Khoushabar","year":"2024","journal-title":"arXiv [Preprint]"},{"key":"B10","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems 30 (NeurIPS 2017)","author":"Lundberg","year":"2017"},{"key":"B11","doi-asserted-by":"publisher","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":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1849727","DOI":"10.3389\/fmed.2026.1849727","article-title":"An interpretable deep concatenated architecture for osteoporosis detection using enhanced knee radiographs","volume":"13","author":"Kaur","year":"2026","journal-title":"Front Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1812486","DOI":"10.3389\/fmed.2026.1812486","article-title":"Optimized deep learning ensemble using fast osprey algorithm for accurate lymphoblastic leukemia detection","volume":"13","author":"Kaur","year":"2026","journal-title":"Front Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1851416","DOI":"10.3389\/fncom.2026.1851416","article-title":"AI-driven neuroanalytic modeling for mental health: multichannel CNN-based autism spectrum disorder detection via facial pattern analysis","volume":"20","author":"Kaur","year":"2026","journal-title":"Front Comput Neurosci"},{"key":"B15","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1001\/jama.2024.0179","article-title":"International consensus criteria for pediatric sepsis and septic shock","volume":"331","author":"Schlapbach","year":"2024","journal-title":"JAMA"},{"key":"B16","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1097\/PCC.0000000000003147","article-title":"Executive summary of the second international guidelines for the diagnosis and management of pediatric acute respiratory distress syndrome (PALICC-2)","volume":"24","author":"Emeriaud","year":"2023","journal-title":"Pediatr Crit Care Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"5595042","DOI":"10.1155\/2021\/5595042","article-title":"Prognostic value of blood urea nitrogen\/creatinine ratio for septic shock: an analysis of the MIMIC-III clinical database","volume":"2021","author":"Han","year":"2021","journal-title":"Biomed Res Int"},{"key":"B18","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.ajem.2019.10.023","article-title":"Prognostic value of neutrophil-to-lymphocyte ratio in sepsis: a meta-analysis","volume":"38","author":"Huang","year":"2020","journal-title":"Am J Emerg Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","article-title":"Mice: multivariate imputation by chained equations in R","volume":"45","author":"Van Buuren","year":"2011","journal-title":"J Stat Softw"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/s11135-006-9018-6","article-title":"A caution regarding rules of thumb for variance inflation factors","volume":"41","author":"O'Brien","year":"2007","journal-title":"Qual Quant"},{"key":"B22","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B23","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach Learn"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B25","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s41512-019-0064-7","article-title":"A simple, step-by-step guide to interpreting decision curve analysis","volume":"3","author":"Vickers","year":"2019","journal-title":"Diagn Progn Res"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1164\/rccm.201412-2323OC","article-title":"Global epidemiology of pediatric severe sepsis: the sepsis prevalence, outcomes, and therapies study","volume":"191","author":"Weiss","year":"2015","journal-title":"Am J Respir Crit Care Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"e002329","DOI":"10.1136\/bmjpo-2023-002329","article-title":"Predictive value of laboratory indicators for in-hospital death in children with community-onset sepsis: a prospective observational study of 266 patients","volume":"8","author":"Liu","year":"2024","journal-title":"BMJ Paediatrics Open"},{"key":"B28","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1186\/cc12514","article-title":"Stress hyperglycemia: an essential survival response!","volume":"17","author":"Marik","year":"2013","journal-title":"Crit Care"},{"key":"B29","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1542\/peds.2005-1819","article-title":"Association of hypoglycemia, hyperglycemia, and glucose variability with morbidity and death in the pediatric intensive care unit","volume":"118","author":"Wintergerst","year":"2006","journal-title":"Pediatrics"},{"key":"B30","doi-asserted-by":"publisher","first-page":"k4891","DOI":"10.1136\/bmj.k4891","article-title":"Sepsis associated acute kidney injury","volume":"364","author":"Poston","year":"2019","journal-title":"Br Med J"},{"key":"B31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1056\/NEJMoa1611391","article-title":"Epidemiology of acute kidney injury in critically ill children and young adults","volume":"376","author":"Kaddourah","year":"2017","journal-title":"N Engl J Med"},{"key":"B32","doi-asserted-by":"publisher","first-page":"11653","DOI":"10.21037\/apm-21-2937","article-title":"Association between blood urea nitrogen and 30-day mortality in patients with sepsis: a retrospective analysis","volume":"10","author":"Li","year":"2021","journal-title":"Ann Palliat Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2192","DOI":"10.1080\/07853890.2021.2004317","article-title":"Higher blood urea nitrogen level is independently linked with the presence and severity of neonatal sepsis","volume":"53","author":"Li","year":"2021","journal-title":"Ann Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.jss.2018.03.035","article-title":"Lactate dehydrogenase is associated with 28-day mortality in patients with sepsis: a retrospective observational study","volume":"228","author":"Lu","year":"2018","journal-title":"J Surg Res"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1097\/ALN.0000000000003122","article-title":"Sepsis-induced coagulopathy and disseminated intravascular coagulation","volume":"132","author":"Iba","year":"2020","journal-title":"Anesthesiology"},{"key":"B36","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1055\/s-0040-1713436","article-title":"Exploration of sepsis-associated coagulopathy severity and pediatric septic shock outcomes","volume":"10","author":"Loberger","year":"2021","journal-title":"J Pediatr Intensive Care"},{"key":"B37","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit Med"},{"key":"B38","doi-asserted-by":"publisher","first-page":"55","DOI":"10.7326\/M14-0697","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"162","author":"Collins","year":"2015","journal-title":"Ann Intern Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e179","DOI":"10.1016\/S2589-7500(20)30018-2","article-title":"Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records","volume":"2","author":"Thorsen-Meyer","year":"2020","journal-title":"Lancet Digit Health"},{"key":"B40","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1933395\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:40:33Z","timestamp":1788154833000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1933395\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":40,"alternative-id":["10.3389\/fped.2026.1933395"],"URL":"https:\/\/doi.org\/10.3389\/fped.2026.1933395","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"article-number":"1933395"}}