{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T18:03:13Z","timestamp":1792173793589,"version":"4.4.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"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>Introduction<\/jats:title>\n                    <jats:p>Sepsis-associated acute kidney injury (S-AKI) is a severe complication in critically ill patients, linked to increased short-term mortality and chronic kidney disease. Existing prognostic tools like SOFA and SAPS II lack full representation of intricate clinical variable interactions. Machine learning (ML) models have potential in intensive care, but few validated and interpretable models focus on the in-hospital mortality rate of patients with S-AKI. This study aims to create and validate ML models for forecasting in-hospital mortality in S-AKI patients, identifying the most effective predictive model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a retrospective analysis of data from the MIMIC-IV 3.0 database to identify adult ICU patients who met theSepsis-3.0(Sepsis-3 was defined as suspected infection with an acute increase in SOFA score \u22652) and KDIGO criteria for S-AKI. Additionally, a prospective cohort study from the General Hospital of Ningxia Medical University spanning 2023 to 2025 was included. Predictors recorded within 24 h of ICU admission included demographic information, comorbidities, vital signs, laboratory results, treatments, and severity scores. Variables with more than 20% missing data were excluded, and the remaining data were processed using interpolation. Feature selection was performed using the Boruta algorithm, and five machine learning models were trained (XGBoost, Random Forest, LightGBM, Decision tree, logistic regression). Model performance evaluation was based on metrics such as AUC, accuracy, sensitivity, specificity, F1 score, and clinical efficacy assessed through decision curve analysis. To enhance model interpretability, the SHapley Additive exPlanations (SHAP) method was employed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 16,800 patients with S-AKI, non-survivors(in-hospital mortality) exhibited older age, higher disease severity scores, more pronounced fluid overload, poorer renal function, metabolic acidosis, coagulation disorders, and heightened inflammatory responses. The XGBoost model demonstrated superior discriminative power (AUC 0.8799 \u7f6e\u4fe1\u533a\u95f4) in internal validation, surpassing other ML models, with exceptional sensitivity, accuracy, and F1 score. Decision curve analysis revealed that LightGBM offered the most significant net clinical benefit across various threshold probabilities. SHAP analysis consistently identified SAPS II score, AKI stage, oxygenation index, and key biochemical markers (e.g., serum sodium and blood urea nitrogen) as primary contributors to mortality risk, while the added value of basic demographic variables was limited. External validation confirmed that the XGBoost model has potential discrimination and robustness, highlighting the robustness and wide applicability of the machine learning-based prognostic framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study established an externally validated and interpretable ML model for riskstratification in S-AKI, enabling early identification of high-risk patients, personalized management strategies, and enhanced clinical outcomes in sepsis care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1756831","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:39:40Z","timestamp":1770964780000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["An interpretable machine-learning model for predicting in-hospital mortality in patients with sepsis-associated acute kidney injury"],"prefix":"10.3389","volume":"13","author":[{"given":"Jian-Zhong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Clinical Medicine, Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Zhang","sequence":"additional","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong-Rong","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Clinical Medicine, Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Clinical Medicine, Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao-Geng","family":"Chen","sequence":"additional","affiliation":[{"name":"Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/S0140-6736(19)32989-7","article-title":"Global, regional, and national sepsis incidence and mortality, 1990\u20132017: analysis for the global burden of disease study","volume":"395","author":"Rudd","year":"2020","journal-title":"Lancet"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"5631","DOI":"10.2147\/IJGM.S320768","article-title":"Epidemiology of Sepsis-associated acute kidney injury in Beijing, China: a descriptive analysis","volume":"14","author":"Wang","year":"2021","journal-title":"Int J Gen Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/s00134-017-4755-7","article-title":"Acute kidney injury in sepsis","volume":"43","author":"Bellomo","year":"2017","journal-title":"Intensive Care Med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1038\/s41581-023-00683-3","article-title":"Sepsis-associated acute kidney injury: consensus report of the 28th acute disease quality initiative workgroup","volume":"19","author":"Zarbock","year":"2023","journal-title":"Nat Rev Nephrol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1080\/0886022x.2022.2027247","article-title":"The predictive value of the Oxford acute severity of illness score for clinical outcomes in patients with acute kidney injury","volume":"44","author":"Wang","year":"2022","journal-title":"Ren Fail"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s41030-020-00110-z","article-title":"Machine learning for pulmonary and critical care medicine: a narrative review","volume":"6","author":"Mlodzinski","year":"2020","journal-title":"Pulm Ther"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s12967-022-03364-0","article-title":"Machine learning for the prediction of acute kidney injury in patients with sepsis","volume":"20","author":"Yue","year":"2022","journal-title":"J Transl Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1200\/cci.20.00072","article-title":"Machine learning in oncology: methods, applications, and challenges","volume":"4","author":"Bertsimas","year":"","journal-title":"JCO Clin Cancer Inform"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1097\/shk.0000000000002065","article-title":"Machine learning models for predicting acute kidney injury in patients with sepsis-associated acute respiratory distress syndrome","volume":"59","author":"Zhou","year":"2023","journal-title":"Shock"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"S117","DOI":"10.1016\/j.kint.2023.10.018","article-title":"KDIGO 2024 clinical practice guideline for the evaluation and management of chronic kidney disease","volume":"105","year":"2024","journal-title":"Kidney Int"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.ajem.2020.02.002","article-title":"Efficacy and safety of corticosteroids for septic shock in immunocompromised patients: a cohort study from MIMIC","volume":"42","author":"Lu","year":"2021","journal-title":"Am J Emerg Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"869499","DOI":"10.3389\/fphar.2022.869499","article-title":"The use of antibiotics for ventilator-associated pneumonia in the MIMIC-IV database","volume":"13","author":"Yang","year":"2022","journal-title":"Front Pharmacol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"379","DOI":"10.2217\/fon-2017-0450","article-title":"Comparison of three prognostic models for predicting cancer-specific survival among patients with gastrointestinal stromal tumors","volume":"14","author":"Oweira","year":"2018","journal-title":"Future Oncol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"30","DOI":"10.3978\/j.issn.2305-5839.2015.12.63","article-title":"Multiple imputation with multivariate imputation by chained equation (MICE) package","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann Transl Med"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1111\/resp.12226","article-title":"Introduction to multiple imputation for dealing with missing data","volume":"19","author":"Lee","year":"2014","journal-title":"Respirology"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"b2393","DOI":"10.1136\/bmj.b2393","article-title":"Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls","volume":"338","author":"Sterne","year":"2009","journal-title":"BMJ"},{"key":"ref18","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive expla- nation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ijcard.2022.09.065","article-title":"Predictive outcomes of APACHE II and expanded SAPS II mortality scoring systems in coronary care unit","volume":"371","author":"Kahraman","year":"","journal-title":"Int J Cardiol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1186\/s12882-021-02611-8","article-title":"Combining renal cell arrest and damage biomarkers to predict progressive AKI in patient with sepsis","volume":"22","author":"Tao","year":"2021","journal-title":"BMC Nephrol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1177\/15357597231225065","article-title":"Tuning Sodium Channel blockers to the near-atomic level","volume":"24","author":"Eyal","year":"2024","journal-title":"Epilepsy Curr"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1097\/MAT.0000000000002409","article-title":"Sepsis-extracorporeal membrane oxygenation score in patients receiving extracorporeal membrane oxygenation support for sepsis","volume":"71","author":"Fu","year":"2025","journal-title":"ASAIO J"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"eAO6828","DOI":"10.31744\/einstein_journal\/2022AO6828","article-title":"Relation between red blood cell distribution width and acute kidney injury in patients with sepsis","volume":"20","author":"Ramires","year":"2022","journal-title":"Einstein (Sao Paulo)"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2194433","DOI":"10.1080\/0886022X.2023.2194433","article-title":"Significance of platelets in the early warning of new-onset AKI in the ICU by using supervise learning: a retrospective analysis","volume":"45","author":"Pan","year":"2025","journal-title":"Ren Fail"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1186\/s12885-025-14693-w","article-title":"Decoding the epigenetic-immune nexus in hepatocellular carcinoma: a Mendelian randomization study reveals BTN3A2, S100A12 and TRIM27 as white blood cell regulators","volume":"25","author":"Qiu","year":"2025","journal-title":"BMC Cancer"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1186\/s12917-020-02450-z","article-title":"Phagocyte activity reflects mammalian homeo- and hetero-thermic physiological states","volume":"16","author":"Pikula","year":"2020","journal-title":"BMC Vet Res"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1111\/jbg.12682","article-title":"Genomic integration to identify molecular biomarkers associated with indicator traits of gastrointestinal nematode resistance in sheep","volume":"139","author":"Berton","year":"2022","journal-title":"J Anim Breed Genet"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"104660","DOI":"10.1016\/j.etap.2025.104660","article-title":"Platelet and IL-33 count as biomarkers for lung function impairment: an 11-year follow-up study on populations exposed to hexavalent chromium","volume":"114","author":"Zheng","year":"","journal-title":"Environ Toxicol Pharmacol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1038\/s41380-022-01905-z","article-title":"Immune cell composition in unipolar depression: a comprehensive systematic review and meta-analysis","volume":"28","author":"S\u00f8rensen","year":"2023","journal-title":"Mol Psychiatry"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.biopsych.2023.06.008","article-title":"Genetic overlap between global cortical brain structure, C-reactive protein, and white blood cell counts","volume":"95","author":"Parker","year":"2024","journal-title":"Biol Psychiatry"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1292\/jvms.23-0261","article-title":"Pathogen and severity-dependent immune responses in bovine mastitis: highlight the dynamics of differential somatic cell count","volume":"86","author":"Huang","year":"2024","journal-title":"J Vet Med Sci"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.cir.101.23","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1756831\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:39:42Z","timestamp":1770964782000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1756831\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":33,"alternative-id":["10.3389\/fmed.2026.1756831"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1756831","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"article-number":"1756831"}}