{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:50:31Z","timestamp":1791355831088,"version":"4.3.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute kidney injury (AKI) and altered consciousness are common and serious complications following cardiac surgery, both associated with increased morbidity and mortality in the intensive care unit (ICU). Early prediction of these complications is essential for timely intervention. We aimed to develop and validate an interpretable machine learning model for predicting early AKI and altered consciousness risk in this population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively extracted data from the MIMIC-IV database. Adult patients who underwent cardiac surgery within 24\u00a0h before ICU admission were included. The primary outcome was early AKI defined by KDIGO criteria within 48\u00a0h after ICU admission. The secondary outcome was altered consciousness within 24\u00a0h after ICU admission, defined as a Glasgow Coma Scale (GCS) score \u226412. A comprehensive set of candidate variables was screened using four feature selection methods (LassoCV, mRMR, mutual information, and\n                      <jats:italic>F<\/jats:italic>\n                      -test) with a voting strategy. Eight machine learning models were developed and compared. SHapley Additive exPlanations (SHAP) values were used to interpret the best-performing model. External validation was performed using data from cardiac surgery patients at Wuxi No.2 People\u2019s Hospital between 1 January 2020 and 31 December 2025.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>\n                      A total of 5,288 patients were included, with an AKI incidence of 76.2% (4,031\/5,288) and an altered consciousness incidence of 22.8% (1,206\/5,288). For the primary outcome of AKI, the XGBoost model achieved a training AUC of 0.787 (95% CI: 0.770\u20130.804) and an internal test AUC of 0.659 (95% CI: 0.629\u20130.688). For the secondary outcome of altered consciousness, the XGBoost model achieved an internal test AUC of 0.951 (95% CI: 0.936\u20130.963). Calibration curve and decision curve analysis confirmed good calibration and clinical utility for both models. SHAP analysis identified SpO\n                      <jats:sub>2<\/jats:sub>\n                      , age, APSIII score, creatinine, and white blood cell count as the top 5 most important predictors for AKI. External validation was performed in an independent cohort of 395 cardiac surgery ICU patients from Wuxi No.2 People\u2019s Hospital, in whom the incidence of AKI and altered consciousness was 28.1% and 67.3%, respectively. The models retained acceptable discrimination in this external cohort (AKI: AUC 0.764, 95% CI: 0.711\u20130.818; altered consciousness: AUC 0.679, 95% CI: 0.615\u20130.737).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We developed interpretable XGBoost-based prediction models for both early AKI and altered consciousness risk in cardiac surgery patients admitted to the ICU. The models exhibited excellent discrimination, calibration, and clinical utility, which may facilitate early identification of high-risk patients and guide personalized interventions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1959304","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:00:03Z","timestamp":1791352803000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of an interpretable machine learning model for predicting early acute kidney injury and altered consciousness in cardiac surgery patients admitted to the intensive care unit: a retrospective study"],"prefix":"10.3389","volume":"17","author":[{"given":"Shu","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Wuxi No.2 People\u2019s Hospital (Jiangnan University Medical Center)","place":["Wuxi, China"]},{"name":"Wuxi School of Medicine, Jiangnan University","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Affiliated Obstetrics and Gynecology Hospital of Jiangnan University","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianzheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Wuxi School of Medicine, Jiangnan University","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxiao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Wuxi No.2 People\u2019s Hospital (Jiangnan University Medical Center)","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minmin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Wuxi No.2 People\u2019s Hospital (Jiangnan University Medical Center)","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Pain Medicine, Wuxi No.2 People\u2019s Hospital (Jiangnan University Medical Center)","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.106.635573","article-title":"Bedside tool for predicting the risk of postoperative dialysis in patients undergoing cardiac surgery","volume":"114","author":"Mehta","year":"2006","journal-title":"Circulation"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1681\/asn.2004040331","article-title":"A clinical score to predict acute renal failure after cardiac surgery","volume":"16","author":"Thakar","year":"2005","journal-title":"J Am Soc Nephrol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1186\/cc9960","article-title":"Clinical accuracy of RIFLE and Acute Kidney Injury Network (AKIN) criteria for acute kidney injury in patients undergoing cardiac surgery","volume":"15","author":"Englberger","year":"2011","journal-title":"Crit Care"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2010.04.039","article-title":"Duration of acute kidney injury impacts long-term survival after cardiac surgery","volume":"90","author":"Brown","year":"2010","journal-title":"Ann Thorac Surg"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1097\/01.asn.0000130340.93930.dd","article-title":"Minimal changes of serum creatinine predict prognosis in patients after cardiothoracic surgery: a prospective cohort study","volume":"15","author":"Lassnigg","year":"2004","journal-title":"J Am Soc Nephrol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1053\/j.jvca.2018.08.003","article-title":"Acute kidney injury after cardiac surgery: a narrative review of the literature","volume":"33","author":"Chew","year":"2019","journal-title":"J Cardiothorac Vasc Anesth"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-016-4670-3","article-title":"Prevention of cardiac surgery-associated AKI by implementing the KDIGO guidelines in high risk patients identified by biomarkers: the PrevAKI randomized controlled trial","volume":"43","author":"Meersch","year":"2017","journal-title":"Intensive Care Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.297.16.1801","article-title":"Derivation and validation of a simplified predictive index for renal replacement therapy after cardiac surgery","volume":"297","author":"Wijeysundera","year":"2007","journal-title":"JAMA"},{"key":"B9","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1053\/j.jvca.2025.09.045","article-title":"Predicting in-hospital acute kidney injury after cardiac surgery using machine learning","volume":"40","author":"Nezafati","year":"2026","journal-title":"J Cardiothorac Vasc Anesth"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1056\/nejmp1606181","article-title":"Predicting the future - big data, machine learning, and clinical medicine","volume":"375","author":"Obermeyer","year":"2016","journal-title":"N Engl J Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2026.106453","article-title":"Examining user-AI interaction patterns in health-information queries","volume":"215","author":"Wang","year":"2026","journal-title":"Int J Med Inform"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"B13","doi-asserted-by":"publisher","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":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0325151","article-title":"Development and validation of a cardiac surgery-associated acute kidney injury prediction model using the MIMIC-IV database","volume":"20","author":"Xu","year":"2025","journal-title":"PloS One"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.2196\/72349","article-title":"Machine learning for the prediction of acute kidney injury in critically ill patients with coronary heart disease: algorithm development and validation","volume":"27","author":"Li","year":"2025","journal-title":"J Med Internet Res"},{"key":"B16","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":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2014.11.025","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2026.112295","article-title":"Development, validation, and pilot implementation of a prognostic model to predict future foot complications among people with diabetes recently discharged from hospital","volume":"195","author":"Roberts","year":"2026","journal-title":"J Clin Epidemiol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1080\/0886022x.2026.2685354","article-title":"Elevated atherogenic index of plasma is associated with severe acute kidney injury in critically ill patients with cardiovascular disease - a MIMIC-IV analysis with external validation in the eICU-CRD database","volume":"48","author":"Liu","year":"2026","journal-title":"Ren Fail"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1080\/0886022x.2026.2689653","article-title":"Amino acid infusion and acute kidney injury after aortic surgery: a multicenter observational study with target trial emulation","volume":"48","author":"Wang","year":"2026","journal-title":"Ren Fail"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychores.2010.02.009","article-title":"Incidence and predictors of delirium after cardiac surgery: results from the IPDACS Study","volume":"69","author":"Kazmierski","year":"2010","journal-title":"J Psychosom Res"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2022.09.045","article-title":"Machine learning for dynamic and early prediction of acute kidney injury after cardiac surgery","volume":"166","author":"Ryan","year":"2023","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.xjon.2023.09.023","article-title":"Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basis","volume":"16","author":"Lapp","year":"2023","journal-title":"JTCVS Open"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/CBMS55023.2022.00048","article-title":"Predicting the onset of delirium on hourly basis in an intensive care unit following cardiac surgery","author":"Lapp","year":"2022"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1186\/2110-5820-1-13","article-title":"Understanding urine output in critically ill patients","volume":"1","author":"Legrand","year":"2011","journal-title":"Ann Intensive Care"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1097\/ALN.0000000000001006","article-title":"Advance targeted transfusion in anemic cardiac surgical patients for kidney protection: an unblinded randomized pilot clinical trial","volume":"124","author":"Karkouti","year":"2016","journal-title":"Anesthesiology"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2010.08.018","article-title":"Cardiac surgery-associated acute kidney injury: a comparison of two consensus criteria","volume":"90","author":"Robert","year":"2010","journal-title":"Ann Thorac Surg"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1097\/ccm.0b013e318169181a","article-title":"Impact of minimal increases in serum creatinine on outcome in patients after cardiothoracic surgery: do we have to revise current definitions of acute renal failure","volume":"36","author":"Lassnigg","year":"2008","journal-title":"Crit Care Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1080\/10408363.2023.2248992","article-title":"New biomarkers in acute kidney injury","volume":"61","author":"Rossiter","year":"2024","journal-title":"Crit Rev Clin Lab Sci"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2022.1751","article-title":"Predictive accuracy of a perioperative laboratory test-based prediction model for moderate to severe acute kidney injury after cardiac surgery","volume":"327","author":"Demirjian","year":"2022","journal-title":"JAMA"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijnurstu.2022.104340","article-title":"Prediction models for postoperative delirium after cardiac surgery: systematic review and critical appraisal","volume":"136","author":"Cai","year":"2022","journal-title":"Int J Nurs Stud"},{"key":"B32","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1186\/s13054-026-06017-6","article-title":"Beyond binary AKI classification: development and external validation of a distributional model predicting serum creatinine and urine output trajectories in ICU patients","volume":"30","author":"Jonkers","year":"2026","journal-title":"Crit Care"},{"key":"B33","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.bja.2025.08.043","article-title":"Risk factors, outcomes, and early prediction of cardiac surgery-associated acute kidney injury: a post hoc subgroup analysis of the Epidemiology of Surgery Associated Acute Kidney Injury study","volume":"136","author":"Strau\u00df","year":"2026","journal-title":"Br J Anaesth"},{"key":"B34","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s12979-026-00572-w","article-title":"Immunoinflammatory biomarkers for sepsis-associated acute kidney injury: a multicenter prospective cohort study","volume":"23","author":"Ma","year":"2026","journal-title":"Immun Ageing"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107818","article-title":"Postoperative delirium prediction after cardiac surgery using machine learning models","volume":"169","author":"Yang","year":"2024","journal-title":"Comput Biol Med"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1959304\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:00:04Z","timestamp":1791352804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1959304\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":35,"alternative-id":["10.3389\/fendo.2026.1959304"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1959304","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1959304"}}