{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T08:46:24Z","timestamp":1794818784327,"version":"4.9.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Research Program of Medical Science and Technology of Henan Province","award":["LHGJ20190792"],"award-info":[{"award-number":["LHGJ20190792"]}]},{"name":"Research Program of Medical Science and Technology of Henan Province","award":["SBGJ202101005"],"award-info":[{"award-number":["SBGJ202101005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Nephrol"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Objective<\/jats:title>\n                <jats:p>Postoperative acute kidney injury (PO-AKI) is a common complication after cardiac surgery. We aimed to evaluate whether machine learning algorithms could significantly improve the risk prediction of PO-AKI.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>The retrospective cohort study included 2310 adult patients undergoing cardiac surgery in a tertiary teaching hospital, China. Postoperative AKI and severe AKI were identified by the modified KDIGO definition. The sample was randomly divided into a derivation set and a validation set based on a ratio of 4:1. Exploiting conventional logistic regression (LR) and five ML algorithms including decision tree, random forest, gradient boosting classifier (GBC), Gaussian Naive Bayes and multilayer perceptron, we developed and validated the prediction models of PO-AKI. We implemented the interpretation of models using SHapley Additive exPlanation (SHAP) analysis.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Postoperative AKI and severe AKI occurred in 1020 (44.2%) and 286 (12.4%) patients, respectively. Compared with the five ML models, LR model for PO-AKI exhibited the largest AUC (0.812, 95%<jats:italic>CI<\/jats:italic>: 0.756, 0.860, all <jats:italic>P<\/jats:italic>\u2009&lt;\u20090.05), sensitivity (0.774, 95%<jats:italic>CI<\/jats:italic>: 0.719, 0.813), accuracy (0.753, 95%<jats:italic>CI<\/jats:italic>: 0.719, 0.781) and Youden index (0.513, 95%<jats:italic>CI<\/jats:italic>: 0.451, 0.573). Regarding severe AKI, GBC algorithm showed a significantly higher AUC than the other four ML models (all <jats:italic>P<\/jats:italic>\u2009&lt;\u20090.05). Although no significant difference (<jats:italic>P<\/jats:italic>\u2009=\u20090.173) was observed in AUCs between GBC (0.86, 95%<jats:italic>CI<\/jats:italic>: 0.808, 0.902) and conventional logistic regression (0.803, 95%<jats:italic>CI<\/jats:italic>: 0.746, 0.852), GBC achieved greater sensitivity, accuracy and Youden index than conventional LR. Notably, SHAP analyses showed that preoperative serum creatinine, hyperlipidemia, lipid-lowering agents and assisted ventilation time were consistently among the top five important predictors for both postoperative AKI and severe AKI.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Logistic regression and GBC algorithm demonstrated moderate to good discrimination and superior performance in predicting PO-AKI and severe AKI, respectively. Interpretation of the models identified the key contributors to the predictions, which could potentially inform clinical interventions.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12882-023-03324-w","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T13:02:43Z","timestamp":1699362163000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Interpretable machine learning models for early prediction of acute kidney injury after cardiac surgery"],"prefix":"10.1186","volume":"24","author":[{"given":"Jicheng","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianjin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlu","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"issue":"11","key":"3324_CR1","doi-asserted-by":"publisher","first-page":"e8834","DOI":"10.1161\/JAHA.118.008834","volume":"7","author":"MK Nadim","year":"2018","unstructured":"Nadim MK, Forni LG, Bihorac A, et al. Cardiac and vascular Surgery-Associated Acute kidney Injury: the 20th International Consensus Conference of the ADQI (Acute Disease Quality Initiative) Group. J AM HEART ASSOC. 2018;7(11):e8834.","journal-title":"J AM HEART ASSOC"},{"key":"3324_CR2","doi-asserted-by":"publisher","first-page":"153","DOI":"10.2147\/IJNRD.S167477","volume":"12","author":"M Vives","year":"2019","unstructured":"Vives M, Hernandez A, Parramon F, et al. Acute kidney injury after cardiac surgery: prevalence, impact and management challenges. Int J Nephrol Renovasc Dis. 2019;12:153\u201366.","journal-title":"Int J Nephrol Renovasc Dis"},{"issue":"10","key":"3324_CR3","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1001\/jama.2022.1751","volume":"327","author":"S Demirjian","year":"2022","unstructured":"Demirjian S, Bashour CA, Shaw A, et al. Predictive accuracy of a Perioperative Laboratory test\u2013based prediction model for moderate to severe acute kidney Injury after Cardiac surgery. JAMA. 2022;327(10):956.","journal-title":"JAMA"},{"issue":"6","key":"3324_CR4","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1097\/01.ASN.0000130340.93930.DD","volume":"15","author":"A Lassnigg","year":"2004","unstructured":"Lassnigg A, Schmidlin D, Mouhieddine M, et al. Minimal changes of serum creatinine predict prognosis in patients after cardiothoracic surgery: a prospective cohort study. J AM SOC NEPHROL. 2004;15(6):1597\u2013605.","journal-title":"J AM SOC NEPHROL"},{"issue":"5","key":"3324_CR5","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1038\/ki.2011.379","volume":"81","author":"SG Coca","year":"2012","unstructured":"Coca SG, Singanamala S, Parikh CR. Chronic kidney disease after acute kidney injury: a systematic review and meta-analysis. KIDNEY INT. 2012;81(5):442\u20138.","journal-title":"KIDNEY INT"},{"issue":"1","key":"3324_CR6","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.kint.2018.08.036","volume":"95","author":"EJ See","year":"2019","unstructured":"See EJ, Jayasinghe K, Glassford N, et al. Long-term risk of adverse outcomes after acute kidney injury: a systematic review and meta-analysis of cohort studies using consensus definitions of exposure. KIDNEY INT. 2019;95(1):160\u201372.","journal-title":"KIDNEY INT"},{"issue":"1","key":"3324_CR7","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.athoracsur.2011.09.010","volume":"93","author":"SC Huen","year":"2012","unstructured":"Huen SC, Parikh CR. Predicting Acute kidney Injury after Cardiac surgery: a systematic review. Ann Thorac Surg. 2012;93(1):337\u201347.","journal-title":"Ann Thorac Surg"},{"key":"3324_CR8","doi-asserted-by":"crossref","unstructured":"Tseng P, Chen Y, Wang C et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. CRIT CARE. 2020;24(1).","DOI":"10.1186\/s13054-020-03179-9"},{"issue":"10","key":"3324_CR9","doi-asserted-by":"publisher","first-page":"322","DOI":"10.3390\/jcm7100322","volume":"7","author":"H Lee","year":"2018","unstructured":"Lee H, Yoon H, Nam K, et al. Derivation and validation of machine learning approaches to predict acute kidney Injury after Cardiac surgery. J CLIN MED. 2018;7(10):322.","journal-title":"J CLIN MED"},{"issue":"11","key":"3324_CR10","doi-asserted-by":"publisher","first-page":"e1002703","DOI":"10.1371\/journal.pmed.1002703","volume":"15","author":"C Huang","year":"2018","unstructured":"Huang C, Murugiah K, Mahajan S, et al. Enhancing the prediction of acute kidney injury risk after percutaneous coronary intervention using machine learning techniques: a retrospective cohort study. PLOS MED. 2018;15(11):e1002703.","journal-title":"PLOS MED"},{"issue":"12","key":"3324_CR11","doi-asserted-by":"publisher","first-page":"e1916921","DOI":"10.1001\/jamanetworkopen.2019.16921","volume":"2","author":"VJ Lei","year":"2019","unstructured":"Lei VJ, Luong T, Shan E, et al. Risk stratification for postoperative acute kidney Injury in major noncardiac surgery using preoperative and intraoperative data. JAMA Netw Open. 2019;2(12):e1916921.","journal-title":"JAMA Netw Open"},{"issue":"7","key":"3324_CR12","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1002\/clc.23377","volume":"43","author":"Y Li","year":"2020","unstructured":"Li Y, Xu J, Wang Y, et al. A novel machine learning algorithm, bayesian networks model, to predict the high-risk patients with cardiac surgery\u2010associated acute kidney injury. CLIN CARDIOL. 2020;43(7):752\u201361.","journal-title":"CLIN CARDIOL"},{"issue":"6","key":"3324_CR13","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1016\/j.bja.2021.08.015","volume":"127","author":"C Wang","year":"2021","unstructured":"Wang C, Gao Y, Tian Y, et al. Prediction of acute kidney injury after cardiac surgery from preoperative N-terminal pro-B-type natriuretic peptide. BRIT J ANAESTH. 2021;127(6):862\u201370.","journal-title":"BRIT J ANAESTH"},{"key":"3324_CR14","doi-asserted-by":"publisher","first-page":"110664","DOI":"10.1016\/j.jclinane.2022.110664","volume":"78","author":"YS Wang","year":"2022","unstructured":"Wang YS, Chen DX, Yan M, et al. Prediction of the severity of acute kidney injury after on-pump cardiac surgery. J CLIN ANESTH. 2022;78:110664.","journal-title":"J CLIN ANESTH"},{"issue":"6","key":"3324_CR15","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1016\/j.eururo.2014.11.025","volume":"67","author":"GS Collins","year":"2015","unstructured":"Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement. EUR UROL. 2015;67(6):1142\u201351.","journal-title":"EUR UROL"},{"issue":"4","key":"3324_CR16","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1016\/j.athoracsur.2015.09.038","volume":"101","author":"C Rao","year":"2016","unstructured":"Rao C, Zhang H, Gao H, et al. The chinese cardiac surgery Registry: design and data audit. Ann Thorac Surg. 2016;101(4):1514\u201320.","journal-title":"Ann Thorac Surg"},{"issue":"4","key":"3324_CR17","first-page":"c179","volume":"120","author":"A Khwaja","year":"2012","unstructured":"Khwaja A. KDIGO Clinical Practice Guidelines for Acute kidney Injury. NEPHRON. 2012;120(4):c179\u201384.","journal-title":"NEPHRON"},{"issue":"1","key":"3324_CR18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg SM, Erion G, Chen H, et al. From local explanations to Global understanding with explainable AI for trees. Nat Mach Intell. 2020;2(1):56\u201367.","journal-title":"Nat Mach Intell"},{"issue":"5","key":"3324_CR19","doi-asserted-by":"publisher","first-page":"e155705","DOI":"10.1371\/journal.pone.0155705","volume":"11","author":"P Thottakkara","year":"2016","unstructured":"Thottakkara P, Ozrazgat-Baslanti T, Hupf BB, et al. Application of machine learning techniques to high-dimensional Clinical Data to Forecast Postoperative Complications. PLoS ONE. 2016;11(5):e155705.","journal-title":"PLoS ONE"},{"issue":"7767","key":"3324_CR20","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev N, Glorot X, Rae JW, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572(7767):116\u20139.","journal-title":"Nature"},{"issue":"6","key":"3324_CR21","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1186\/s13054-014-0606-x","volume":"18","author":"K Birnie","year":"2014","unstructured":"Birnie K, Verheyden V, Pagano D, et al. Predictive models for kidney disease: improving global outcomes (KDIGO) defined acute kidney injury in UK cardiac surgery. Crit Care (London England). 2014;18(6):606.","journal-title":"Crit Care (London England)"},{"issue":"4","key":"3324_CR22","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1097\/SLA.0000000000002706","volume":"269","author":"A Bihorac","year":"2019","unstructured":"Bihorac A, Ozrazgat-Baslanti T, Ebadi A, et al. MySurgeryRisk: Development and Validation of a machine-learning risk algorithm for major complications and death after surgery. ANN SURG. 2019;269(4):652\u201362.","journal-title":"ANN SURG"},{"issue":"1","key":"3324_CR23","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1038\/s41746-020-00346-8","volume":"3","author":"N Rank","year":"2020","unstructured":"Rank N, Pfahringer B, Kempfert J, et al. Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance. NPJ Digit Med. 2020;3(1):139.","journal-title":"NPJ Digit Med"},{"key":"3324_CR24","doi-asserted-by":"publisher","first-page":"110596","DOI":"10.1016\/j.jclinane.2021.110596","volume":"77","author":"T P\u00e9rez","year":"2022","unstructured":"P\u00e9rez T, Candela-Toha AM, Khalifi L, Muriel A, Pardo MC. Individualized prediction for the occurrence of acute kidney injury during the first postoperative week following cardiac surgery. J CLIN ANESTH. 2022;77:110596.","journal-title":"J CLIN ANESTH"},{"issue":"6","key":"3324_CR25","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s40620-019-00624-z","volume":"32","author":"C Guan","year":"2019","unstructured":"Guan C, Li C, Xu L, et al. Risk factors of cardiac surgery-associated acute kidney injury: development and validation of a perioperative predictive nomogram. J NEPHROL. 2019;32(6):937\u201345.","journal-title":"J NEPHROL"},{"issue":"3","key":"3324_CR26","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1159\/000449235","volume":"134","author":"C Ronco","year":"2016","unstructured":"Ronco C, Chawla LS. Glomerular and tubular kidney stress test: New Tools for a deeper evaluation of kidney function. NEPHRON. 2016;134(3):191\u20134.","journal-title":"NEPHRON"},{"issue":"1\u20134","key":"3324_CR27","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1159\/000363721","volume":"127","author":"A Sharma","year":"2014","unstructured":"Sharma A, Mucino MJ, Ronco C. Renal Functional Reserve and Renal Recovery after Acute kidney Injury. Nephron Clin Pract. 2014;127(1\u20134):94\u2013100.","journal-title":"Nephron Clin Pract"},{"issue":"4","key":"3324_CR28","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1016\/j.athoracsur.2017.12.034","volume":"105","author":"F Husain-Syed","year":"2018","unstructured":"Husain-Syed F, Ferrari F, Sharma A, et al. Preoperative renal Functional Reserve predicts risk of Acute kidney Injury after Cardiac Operation. Ann Thorac Surg. 2018;105(4):1094\u2013101.","journal-title":"Ann Thorac Surg"},{"issue":"2","key":"3324_CR29","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1093\/ndt\/gfy227","volume":"34","author":"F Husain-Syed","year":"2019","unstructured":"Husain-Syed F, Ferrari F, Sharma A, et al. Persistent decrease of renal functional reserve in patients after cardiac surgery-associated acute kidney injury despite clinical recovery. NEPHROL DIAL TRANSPL. 2019;34(2):308\u201317.","journal-title":"NEPHROL DIAL TRANSPL"},{"issue":"6","key":"3324_CR30","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1016\/j.jtcvs.2015.02.005","volume":"149","author":"NR Sodha","year":"2015","unstructured":"Sodha NR, Sellke FW. The effect of statins on perioperative inflammation in cardiac and thoracic surgery. J Thorac Cardiovasc Surg. 2015;149(6):1495\u2013501.","journal-title":"J Thorac Cardiovasc Surg"},{"issue":"8","key":"3324_CR31","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1016\/j.cjca.2015.02.034","volume":"31","author":"J Wang","year":"2015","unstructured":"Wang J, Gu C, Gao M, Yu W, Yu Y. Preoperative statin therapy and renal outcomes after cardiac surgery: a Meta-analysis and Meta-regression of 59,771 patients. CAN J CARDIOL. 2015;31(8):1051\u201360.","journal-title":"CAN J CARDIOL"},{"issue":"2","key":"3324_CR32","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1093\/icvts\/ivt178","volume":"17","author":"I Singh","year":"2013","unstructured":"Singh I, Rajagopalan S, Srinivasan A, et al. Preoperative statin therapy is associated with lower requirement of renal replacement therapy in patients undergoing cardiac surgery: a meta-analysis of observational studies. Interact Cardiovasc Thorac Surg. 2013;17(2):345\u201352.","journal-title":"Interact Cardiovasc Thorac Surg"},{"key":"3324_CR33","doi-asserted-by":"publisher","first-page":"m441","DOI":"10.1136\/bmj.m441","volume":"368","author":"RD Riley","year":"2020","unstructured":"Riley RD, Ensor J, Snell KIE, et al. Calculating the sample size required for developing a clinical prediction model. BMJ. 2020;368:m441\u201353.","journal-title":"BMJ"}],"container-title":["BMC Nephrology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12882-023-03324-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12882-023-03324-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12882-023-03324-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T13:02:58Z","timestamp":1699362178000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcnephrol.biomedcentral.com\/articles\/10.1186\/s12882-023-03324-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["3324"],"URL":"https:\/\/doi.org\/10.1186\/s12882-023-03324-w","relation":{},"ISSN":["1471-2369"],"issn-type":[{"value":"1471-2369","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,7]]},"assertion":[{"value":"7 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The study was approved by the Medical Ethics Committee of Central China Fuwai Hospital of Zhengzhou University. The requirement for informed consent was waived by the Medical Ethics Committee of Central China Fuwai Hospital of Zhengzhou University due to the retrospective design. The study was carried out in accordance with the Helsinki Declaration (WMA Declaration of Helsinki, 2013).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"326"}}