{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T23:53:53Z","timestamp":1783814033441,"version":"3.55.0"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ningbo Medical Health Science Project","award":["2023Y89"],"award-info":[{"award-number":["2023Y89"]}]},{"name":"Project of Ningbo Leading Medical & Health Discipline","award":["2022-S03"],"award-info":[{"award-number":["2022-S03"]}]},{"name":"Zhejiang Medical Health Science and Technology Project","award":["2024KY336"],"award-info":[{"award-number":["2024KY336"]}]},{"name":"Ningbo Major Research and Development Plan Project","award":["2024Z213"],"award-info":[{"award-number":["2024Z213"]}]},{"name":"Ningbo Major Research and Development Plan Project","award":["2023Z177"],"award-info":[{"award-number":["2023Z177"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Introduction<\/jats:title>\n<jats:p>Intradialytic hypotension (IDH) remains a prevalent complication of hemodialysis, which is associated with adverse outcomes for patients. This study seeks to harness machine learning to construct predictive models for IDH based on multiple definitions.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>In this study, a comprehensive approach was employed, leveraging a dataset comprising 26,690 hemodialysis (HD) sessions for training and testing cohort, with an additional 12,293 HD sessions serving as a temporal validation cohort. Five definitions of IDH were employed, and models for each IDH definition were constructed using ten machine learning algorithms. Subsequently, model interpretation was facilitated. Feature simplification ensued, leading to the creation and evaluation of a streamlined machine learning model. Both the most effective machine learning model and its simplified counterpart underwent temporal validation.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Across the five distinct definitions of IDH, the CatBoost model demonstrated superior predictive prowess, generally yielding the highest receiver operating characteristic \u2013 area under the curve (ROC-AUC) (Definition 1\u20135: 0.859, 0.864, 0.880, 0.848, 0.845). Noteworthy is the persistent inclusion of certain features within the top 20 across all definitions, including left ventricular mass index (LVMI), etc. Leveraging these features, we developed robust machine learning models that exhibited good performance (ROC-AUC for Definition 1\u20135: 0.866, 0.858, 0.874, 0.843, 0.838). Both the leading original machine learning model and the refined simplified machine learning model demonstrated robust performance on a temporal validation set.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Machine learning emerged as a reliable tool for predicting IDH in HD patients. Notably, LVMI emerged as a crucial feature for effectively predicting IDH. The simplified models are accessible on the provided website.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0333357","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:40:41Z","timestamp":1759945241000},"page":"e0333357","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Construction and application of machine learning models for predicting intradialytic hypotension"],"prefix":"10.1371","volume":"20","author":[{"given":"Pingping","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningjie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingping","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihui","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijian","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3169-5143","authenticated-orcid":true,"given":"Kedan","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"issue":"10225","key":"pone.0333357.ref001","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/S0140-6736(20)30045-3","article-title":"Global, regional, and national burden of chronic kidney disease, 1990\u20132017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"395","author":"B Bikbov","year":"2020","journal-title":"Lancet"},{"issue":"19","key":"pone.0333357.ref002","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1056\/NEJMra0902710","article-title":"Hemodialysis","volume":"363","author":"J Himmelfarb","year":"2010","journal-title":"N Engl J Med"},{"issue":"9981","key":"pone.0333357.ref003","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1016\/S0140-6736(14)61601-9","article-title":"Worldwide access to treatment for end-stage kidney disease: a systematic review","volume":"385","author":"T Liyanage","year":"2015","journal-title":"Lancet"},{"issue":"6","key":"pone.0333357.ref004","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1016\/j.kint.2021.01.018","article-title":"The time of onset of intradialytic hypotension during a hemodialysis session associates with clinical parameters and mortality","volume":"99","author":"DF Keane","year":"2021","journal-title":"Kidney Int"},{"issue":"8","key":"pone.0333357.ref005","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.2215\/CJN.12141017","article-title":"Mechanisms, Clinical Implications, and Treatment of Intradialytic Hypotension","volume":"13","author":"PB Reeves","year":"2018","journal-title":"Clin J Am Soc Nephrol"},{"issue":"1","key":"pone.0333357.ref006","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1038\/s41591-018-0307-0","article-title":"The practical implementation of artificial intelligence technologies in medicine","volume":"25","author":"J He","year":"2019","journal-title":"Nat Med"},{"issue":"23","key":"pone.0333357.ref007","doi-asserted-by":"crossref","first-page":"2668","DOI":"10.1016\/j.jacc.2018.03.521","article-title":"Artificial Intelligence in Cardiology","volume":"71","author":"KW Johnson","year":"2018","journal-title":"J Am Coll Cardiol"},{"issue":"10","key":"pone.0333357.ref008","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1038\/s41575-020-0327-3","article-title":"Gut microbiome, big data and machine learning to promote precision medicine for cancer","volume":"17","author":"G Cammarota","year":"2020","journal-title":"Nat Rev Gastroenterol Hepatol"},{"issue":"3","key":"pone.0333357.ref009","article-title":"Machine Learning for Antimicrobial Resistance Prediction: Current Practice, Limitations, and Clinical Perspective","volume":"35","author":"JI Kim","year":"2022","journal-title":"Clin Microbiol Rev"},{"issue":"14","key":"pone.0333357.ref010","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine Learning in Medicine","volume":"380","author":"A Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"issue":"6","key":"pone.0333357.ref011","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1111\/sdi.12626","article-title":"Definitions of intradialytic hypotension","volume":"30","author":"MM Assimon","year":"2017","journal-title":"Semin Dial"},{"issue":"3","key":"pone.0333357.ref012","first-page":"269","article-title":"Expert consensus on the prevention and treatment of intradialytic hypotension (2022)","volume":"61","author":"Intradialytic Hypotension Prevention and Treatment Expert Working Group, Renal and Blood Purification Committee, Chinese Medicine Education Society","year":"2022","journal-title":"Zhonghua Nei Ke Za Zhi"},{"key":"pone.0333357.ref013","doi-asserted-by":"crossref","first-page":"105536","DOI":"10.1016\/j.cmpb.2020.105536","article-title":"Predictive modeling of blood pressure during hemodialysis: a comparison of linear model, random forest, support vector regression, XGBoost, LASSO regression and ensemble method","volume":"195","author":"J-C Huang","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"issue":"10","key":"pone.0333357.ref014","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1016\/j.jfma.2018.05.023","article-title":"Intelligent system to predict intradialytic hypotension in chronic hemodialysis","volume":"117","author":"C-J Lin","year":"2018","journal-title":"J Formos Med Assoc"},{"issue":"5","key":"pone.0333357.ref015","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1159\/000531619","article-title":"Construction of an Early Alert System for Intradialytic Hypotension before Initiating Hemodialysis Based on Machine Learning","volume":"9","author":"D Hong","year":"2023","journal-title":"Kidney Dis (Basel)"},{"key":"pone.0333357.ref016","doi-asserted-by":"crossref","first-page":"107698","DOI":"10.1016\/j.cmpb.2023.107698","article-title":"Machine learning-based intradialytic hypotension prediction of patients undergoing hemodialysis: A multicenter retrospective study","volume":"240","author":"J Dong","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"issue":"3","key":"pone.0333357.ref017","first-page":"228","article-title":"Echocardiographic parameters in patients with and without hypotension during dialysis","volume":"13","author":"H Poorzand","year":"2021","journal-title":"J Cardiovasc Thorac Res"},{"issue":"5","key":"pone.0333357.ref018","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1016\/j.kint.2022.01.032","article-title":"Association of cardiac autonomic neuropathy assessed by heart rate response during exercise with intradialytic hypotension and mortality in hemodialysis patients","volume":"101","author":"N Usui","year":"2022","journal-title":"Kidney Int"},{"issue":"4","key":"pone.0333357.ref019","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1007\/s11845-020-02249-9","article-title":"Intradialytic hypotension prevalence, influencing factors, and nursing interventions: prospective results of 744 hemodialysis sessions","volume":"189","author":"N Ozen","year":"2020","journal-title":"Ir J Med Sci"},{"issue":"1","key":"pone.0333357.ref020","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1186\/s12882-019-1426-7","article-title":"Erythrocytosis is associated with intradialytic hypotension: a case series","volume":"20","author":"S Agrawal","year":"2019","journal-title":"BMC Nephrol"},{"issue":"2","key":"pone.0333357.ref021","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1681\/ASN.0000000000000262","article-title":"Effect of Dialysate and Plasma Sodium on Mortality in a Global Historical Hemodialysis Cohort","volume":"35","author":"J Pinter","year":"2023","journal-title":"J Am Soc Nephrol"},{"issue":"3","key":"pone.0333357.ref022","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1159\/000513525","article-title":"Serum Phosphorus Levels are Associated with Intradialytic Hypotension in Hemodialysis Patients","volume":"145","author":"KH Yang","year":"2021","journal-title":"Nephron"},{"issue":"1","key":"pone.0333357.ref023","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s13054-020-03441-0","article-title":"A randomized trial of albumin infusion to prevent intradialytic hypotension in hospitalized hypoalbuminemic patients","volume":"25","author":"E Macedo","year":"2021","journal-title":"Crit Care"},{"key":"pone.0333357.ref024","doi-asserted-by":"crossref","first-page":"105510","DOI":"10.1016\/j.compbiomed.2022.105510","article-title":"An optimized machine learning framework for predicting intradialytic hypotension using indexes of chronic kidney disease-mineral and bone disorders","volume":"145","author":"X Yang","year":"2022","journal-title":"Comput Biol Med"},{"issue":"3","key":"pone.0333357.ref025","doi-asserted-by":"crossref","first-page":"396","DOI":"10.2215\/CJN.09280620","article-title":"Deep Learning Model for Real-Time Prediction of Intradialytic Hypotension","volume":"16","author":"H Lee","year":"2021","journal-title":"Clin J Am Soc Nephrol"},{"key":"pone.0333357.ref026","doi-asserted-by":"crossref","first-page":"878858","DOI":"10.3389\/fmed.2022.878858","article-title":"Deep Learning Model for Predicting Intradialytic Hypotension Without Privacy Infringement: A Retrospective Two-Center Study","volume":"9","author":"HW Kim","year":"2022","journal-title":"Front Med (Lausanne)"},{"issue":"5","key":"pone.0333357.ref027","doi-asserted-by":"crossref","first-page":"2364","DOI":"10.3390\/ijerph18052364","article-title":"Predicting the Appearance of Hypotension during Hemodialysis Sessions Using Machine Learning Classifiers","volume":"18","author":"JA G\u00f3mez-Pulido","year":"2021","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"pone.0333357.ref028","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s12938-022-01044-0","article-title":"Early prediction of hemodialysis complications employing ensemble techniques","volume":"21","author":"M Othman","year":"2022","journal-title":"Biomed Eng Online"},{"key":"pone.0333357.ref029","article-title":"K\/DOQI clinical practice guidelines for cardiovascular disease in dialysis patients","volume":"45","author":"K\/DOQI Workgroup","year":"2005","journal-title":"Am J Kidney Dis"},{"key":"pone.0333357.ref030","article-title":"EBPG guideline on haemodynamic instability","author":"J Kooman","year":"2007","journal-title":"Nephrol Dial Transplant"},{"issue":"5","key":"pone.0333357.ref031","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1111\/j.1744-9987.2012.01088.x","article-title":"Japanese Society for Dialysis Therapy Guidelines for Management of Cardiovascular Diseases in Patients on Chronic Hemodialysis","volume":"16","author":"Japanese Society for Dialysis Therapy","year":"2012","journal-title":"Ther Apher Dial"},{"key":"pone.0333357.ref032","doi-asserted-by":"crossref","first-page":"104975","DOI":"10.1016\/j.ijmedinf.2022.104975","article-title":"A comparative study of the definitions of intradialytic hypotension correlated with increased mortality to identify universal predictors","volume":"173","author":"LSQ N Ngankem","year":"2023","journal-title":"Int J Med Inform"},{"issue":"1","key":"pone.0333357.ref033","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1080\/0886022X.2020.1853570","article-title":"High ultrafiltration rate induced intradialytic hypotension is a predictor for cardiac remodeling: a 5-year cohort study","volume":"43","author":"J Yu","year":"2020","journal-title":"Ren Fail"},{"issue":"1","key":"pone.0333357.ref034","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s40537-020-00369-8","article-title":"CatBoost for big data: an interdisciplinary review","volume":"7","author":"JT Hancock","year":"2020","journal-title":"J Big Data"},{"issue":"7","key":"pone.0333357.ref035","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1093\/ndt\/gfad070","article-title":"Real-time prediction of intradialytic hypotension using machine learning and cloud computing infrastructure","volume":"38","author":"H Zhang","year":"2023","journal-title":"Nephrol Dial Transplant"},{"issue":"11","key":"pone.0333357.ref036","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0278140","article-title":"Preoperative echocardiography predictive analytics for postinduction hypotension prediction","volume":"17","author":"M Yoshimura","year":"2022","journal-title":"PLoS ONE"},{"issue":"1","key":"pone.0333357.ref037","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1186\/s13054-019-2668-2","article-title":"Ultrasound-based clinical profiles for predicting the risk of intradialytic hypotension in critically ill patients on intermittent dialysis: a prospective observational study","volume":"23","author":"R da Hora Passos","year":"2019","journal-title":"Crit Care"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0333357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:40:48Z","timestamp":1759945248000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0333357"}},"subtitle":[],"editor":[{"given":"Nima","family":"Broomand Lomer,","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":37,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0333357","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]}}}