{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:51:46Z","timestamp":1793987506473,"version":"4.8.0"},"reference-count":40,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"unspecified","delay-in-days":25,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"The Department of Science and Technology in Qinghai Province, China","award":["2021-ZJ-963Q"],"award-info":[{"award-number":["2021-ZJ-963Q"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82160131"],"award-info":[{"award-number":["82160131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,2,5]]},"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study developed and validated a stacked ensemble machine learning model to predict the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A retrospective study based on patient data from public databases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>This study analysed 1295 patients with acute pancreatitis complicated by septicaemia from the US Intensive Care Database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>From the MIMIC database, data of patients with acute pancreatitis and sepsis were obtained to construct machine learning models, which were internally and externally validated. The Boruta algorithm was used to select variables. Then, eight machine learning algorithms were used to construct prediction models for acute kidney injury (AKI) occurrence in intensive care unit (ICU) patients. A new stacked ensemble model was developed using the Stacking ensemble method. Model evaluation was performed using area under the receiver operating characteristic curve (AUC), precision-recall (PR) curve, accuracy, recall and F1 score. The Shapley additive explanation (SHAP) method was used to explain the models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main outcome measures<\/jats:title>\n                    <jats:p>AKI in patients with acute pancreatitis complicated by sepsis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The final study included 1295 patients with acute pancreatitis complicated by sepsis, among whom 893 cases (68.9%) developed acute kidney injury. We established eight base models, including Logit, SVM, CatBoost, RF, XGBoost, LightGBM, AdaBoost and MLP, as well as a stacked ensemble model called Multimodel. Among all models, Multimodel had an AUC value of 0.853 (95% CI: 0.792 to 0.896) in the internal validation dataset and 0.802 (95% CI: 0.732 to 0.861) in the external validation dataset. This model demonstrated the best predictive performance in terms of discrimination and clinical application.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The stack ensemble model developed by us achieved AUC values of 0.853 and 0.802 in internal and external validation cohorts respectively and also demonstrated excellent performance in other metrics. It serves as a reliable tool for predicting AKI in patients with acute pancreatitis complicated by sepsis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2024-087427","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:51:32Z","timestamp":1740574292000},"page":"e087427","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":7,"title":["Predicting the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis using a stacked ensemble machine learning model: a retrospective study based on the MIMIC database"],"prefix":"10.1136","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6183-9792","authenticated-orcid":false,"given":"Fuyuan","family":"Li","sequence":"first","affiliation":[{"name":"Clinical Medical College of Qinghai University, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Clinical Medical College of Qinghai University, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiling","family":"Bian","sequence":"additional","affiliation":[{"name":"Medical School of Qinghai University, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangtuo","family":"Xue","sequence":"additional","affiliation":[{"name":"Clinical Medical College of Qinghai University, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Cai","sequence":"additional","affiliation":[{"name":"Clinical Medical College of Qinghai University, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhou","sequence":"additional","affiliation":[{"name":"Qinghai University Affiliated Hospital, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4225-8136","authenticated-orcid":false,"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Hepatopancreatobiliary Surgery, the Affiliated Hospital of Qinghai University, Qinghai University, Xining, Qinghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,2,26]]},"reference":[{"key":"2025121407052982000_15.2.e087427.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(14)60649-8"},{"key":"2025121407052982000_15.2.e087427.2","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v13.i38.5043"},{"key":"2025121407052982000_15.2.e087427.3","doi-asserted-by":"crossref","DOI":"10.1186\/s12893-023-02151-y","article-title":"Construction and validation of machine learning models for sepsis prediction in patients with acute pancreatitis","volume":"23","author":"Liu","year":"2023","journal-title":"BMC Surg"},{"key":"2025121407052982000_15.2.e087427.4","first-page":"296","article-title":"Septic complications of acute pancreatitis","volume":"107","author":"Mifkovic","year":"2006","journal-title":"Bratisl Lek Listy"},{"key":"2025121407052982000_15.2.e087427.5","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1097\/SHK.0000000000002088","article-title":"Early predictive value of presepsin for secondary sepsis and mortality in intensive care unit patients with severe acute pancreatitis","volume":"59","author":"Wang","year":"2023","journal-title":"Shock"},{"key":"2025121407052982000_15.2.e087427.6","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s10620-020-06172-y","article-title":"Infectious Complications of Acute Pancreatitis Is Associated with Peripheral Blood Phagocyte Functional Exhaustion","volume":"66","author":"Susak","year":"2021","journal-title":"Dig Dis Sci"},{"key":"2025121407052982000_15.2.e087427.7","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.5290"},{"key":"2025121407052982000_15.2.e087427.8","doi-asserted-by":"crossref","DOI":"10.1186\/s12882-023-03369-x","article-title":"Construction and validation of a risk assessment model for acute kidney injury in patients with acute pancreatitis in the intensive care unit","volume":"24","author":"Jiang","year":"2023","journal-title":"BMC Nephrol"},{"key":"2025121407052982000_15.2.e087427.9","doi-asserted-by":"crossref","DOI":"10.1186\/s12911-021-01740-2","article-title":"Machine learning model for predicting acute kidney injury progression in critically ill patients","volume":"22","author":"Wei","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025121407052982000_15.2.e087427.10","doi-asserted-by":"crossref","first-page":"56","DOI":"10.4103\/1319-2442.148734","article-title":"Acute kidney injury in severe acute pancreatitis: an experience from a tertiary care center","volume":"26","author":"Kumar","year":"2015","journal-title":"Saudi J Kidney Dis Transpl"},{"key":"2025121407052982000_15.2.e087427.11","doi-asserted-by":"crossref","first-page":"155","DOI":"10.3109\/03009734.2010.547636","article-title":"Acute renal failure in severe pancreatitis: A population-based study","volume":"116","author":"Lin","year":"2011","journal-title":"Ups J Med Sci"},{"key":"2025121407052982000_15.2.e087427.12","doi-asserted-by":"crossref","first-page":"384","DOI":"10.5935\/0103-507X.20140059","article-title":"Septic versus non-septic acute kidney injury in critically ill patients: characteristics and clinical outcomes","volume":"26","author":"Cruz","year":"2014","journal-title":"Rev Bras Ter Intensiva"},{"key":"2025121407052982000_15.2.e087427.13","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-015-3934-7"},{"key":"2025121407052982000_15.2.e087427.14","doi-asserted-by":"publisher","DOI":"10.2215\/CJN.03681106"},{"key":"2025121407052982000_15.2.e087427.15","doi-asserted-by":"publisher","DOI":"10.1007\/s10157-022-02219-8"},{"key":"2025121407052982000_15.2.e087427.16","doi-asserted-by":"crossref","DOI":"10.1155\/2020\/3431290","article-title":"Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients","volume":"2020","author":"Qu","year":"2020","journal-title":"Gastroenterol Res Pract"},{"key":"2025121407052982000_15.2.e087427.17","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1080\/08941939.2021.1970864","article-title":"The Systemic Immune-Inflammation Index May Be a Novel and Strong Marker for the Accurate Early Prediction of Acute Kidney Injury in Severe Acute Pancreatitis Patients","volume":"35","author":"Lu","year":"2022","journal-title":"J Invest Surg"},{"key":"2025121407052982000_15.2.e087427.18","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.21037\/apm-20-1117","article-title":"A new prediction model for acute kidney injury in patients with sepsis","volume":"10","author":"Fan","year":"2021","journal-title":"Ann Palliat Med"},{"key":"2025121407052982000_15.2.e087427.19","doi-asserted-by":"crossref","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":"2025121407052982000_15.2.e087427.20","article-title":"Introduction to Machine Learning, Neural Networks, and Deep Learning","volume":"9","author":"Choi","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"2025121407052982000_15.2.e087427.21","doi-asserted-by":"crossref","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":"2025121407052982000_15.2.e087427.22","doi-asserted-by":"crossref","DOI":"10.3390\/cancers12102802","article-title":"Comparison of the Tree-Based Machine Learning Algorithms to Cox Regression in Predicting the Survival of Oral and Pharyngeal Cancers: Analyses Based on SEER Database","volume":"12","author":"Du","year":"2020","journal-title":"Cancers (Basel)"},{"key":"2025121407052982000_15.2.e087427.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2019.02.009"},{"key":"2025121407052982000_15.2.e087427.24","doi-asserted-by":"crossref","unstructured":"Sun L , Yang L , Liu X , et al . Optimization of Cervical Cancer Screening: A Stacking-Integrated Machine Learning Algorithm Based on Demographic, Behavioral, and Clinical Factors. Front Oncol 2022;12. doi:10.3389\/fonc.2022.821453","DOI":"10.3389\/fonc.2022.821453"},{"key":"2025121407052982000_15.2.e087427.25","unstructured":"Johnson AEW , Pollard TJ , Shen L , et al . Data from: mimic-iii, a freely accessible critical care database [MIMIC-III Clinical Database]. n.d. Available: https:\/\/doi.org\/10.13026\/C2XW26"},{"key":"2025121407052982000_15.2.e087427.26","doi-asserted-by":"crossref","unstructured":"Johnson AEW , Bulgarelli L , Shen L , et al . Data from:MIMIC-IV, a freely accessible electronic health record dataset [MIMIC-IV]. 2024. Available: https:\/\/doi.org\/10.13026\/kpb9-mt58","DOI":"10.1038\/s41597-023-01945-2"},{"key":"2025121407052982000_15.2.e087427.27","doi-asserted-by":"publisher","DOI":"10.1007\/s10654-018-0390-z"},{"key":"2025121407052982000_15.2.e087427.28","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2021.752558","article-title":"SHAP and LIME: An Evaluation of Discriminative Power in Credit Risk","volume":"4","author":"Gramegna","year":"2021","journal-title":"Front Artif Intell"},{"key":"2025121407052982000_15.2.e087427.29","doi-asserted-by":"crossref","DOI":"10.1186\/cc13161","article-title":"Hemodynamic variables and progression of acute kidney injury in critically ill patients with severe sepsis: data from the prospective observational FINNAKI study","volume":"17","author":"Poukkanen","year":"2013","journal-title":"Crit Care"},{"key":"2025121407052982000_15.2.e087427.30","doi-asserted-by":"crossref","DOI":"10.1186\/s13613-021-00925-2","article-title":"High mean arterial pressure target to improve sepsis-associated acute kidney injury in patients with prior hypertension: a feasibility study","volume":"11","author":"Dewitte","year":"2021","journal-title":"Ann Intensive Care"},{"key":"2025121407052982000_15.2.e087427.31","doi-asserted-by":"crossref","DOI":"10.1186\/cc12495","article-title":"Increasing mean arterial blood pressure in sepsis: effects on fluid balance, vasopressor load and renal function","volume":"17","author":"Corr\u00eaa","year":"2013","journal-title":"Crit Care"},{"key":"2025121407052982000_15.2.e087427.32","doi-asserted-by":"crossref","first-page":"356","DOI":"10.23876\/j.krcp.19.030","article-title":"Optimal systolic blood pressure in noncritically ill patients with acute kidney injury: A retrospective cohort study","volume":"38","author":"Baek","year":"2019","journal-title":"Kidney Res Clin Pract"},{"key":"2025121407052982000_15.2.e087427.33","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.semnephrol.2015.01.003","article-title":"Clinical approach to the patient with AKI and sepsis","volume":"35","author":"Godin","year":"2015","journal-title":"Semin Nephrol"},{"key":"2025121407052982000_15.2.e087427.34","doi-asserted-by":"crossref","DOI":"10.1186\/cc6916","article-title":"Sepsis Occurrence in Acutely Ill Patients (SOAP) Investigators. A positive fluid balance is associated with a worse outcome in patients with acute renal failure","volume":"12","author":"Payen","year":"2008","journal-title":"Crit Care"},{"key":"2025121407052982000_15.2.e087427.35","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.3109\/0886022X.2014.917560","article-title":"Diuretics associated acute kidney injury: clinical and pathological analysis","volume":"36","author":"Wu","year":"2014","journal-title":"Ren Fail"},{"key":"2025121407052982000_15.2.e087427.36","doi-asserted-by":"crossref","first-page":"793","DOI":"10.2147\/RMHP.S361598","article-title":"Association Between the Severity of Early Acute Kidney Injury and Subsequent in-Hospital Complications and 90-Day Mortality in Geriatric Patients Receiving Invasive Mechanical Ventilation","volume":"15","author":"Li","year":"2022","journal-title":"Risk Manag Healthc Policy"},{"key":"2025121407052982000_15.2.e087427.37","doi-asserted-by":"publisher","DOI":"10.1159\/000259585"},{"key":"2025121407052982000_15.2.e087427.38","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1165\/rcmb.2004-0177OC","article-title":"Mechanical Ventilation Alters Airway Nucleotides and Purinoceptors in Lung and Extrapulmonary Organs","volume":"32","author":"Douillet","year":"2005","journal-title":"Am J Respir Cell Mol Biol"},{"key":"2025121407052982000_15.2.e087427.39","doi-asserted-by":"crossref","DOI":"10.1080\/0886022X.2024.2316267","article-title":"Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury","volume":"46","author":"Gao","year":"2024","journal-title":"Ren Fail"},{"key":"2025121407052982000_15.2.e087427.40","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1097\/00005373-200208000-00010","article-title":"Persistent systemic inflammatory response syndrome is predictive of nosocomial infection in trauma","volume":"53","author":"Bochicchio","year":"2002","journal-title":"J Trauma"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2024-087427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T15:05:41Z","timestamp":1765724741000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2024-087427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2,26]]},"published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10.1136\/bmjopen-2024-087427"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2024-087427","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}