{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:00:00Z","timestamp":1782846000051,"version":"3.54.5"},"reference-count":41,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Postoperative delirium (POD) following cardiac surgery is a severe complication, and early identification of delirium risk remains a challenge in clinical practice. While machine learning (ML) has garnered increasing attention in health care applications, effective early prediction tools remain limited in current clinical practice. Recent investigations have explored the effectiveness of ML-based methods for identifying the risk of POD in patients undergoing cardiac surgery. However, more evidence is required to validate the feasibility of these methods.<\/jats:p>\n <\/jats:sec>\n \n Objectives<\/jats:title>\n This study aims to ascertain the performance of ML in identifying the risk of POD following cardiac surgery, providing evidence for the development or updating of future ML-based assessment tools.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A comprehensive literature search was conducted across 4 databases\u2014PubMed, the Cochrane Library, Embase, and Web of Science\u2014through August 30, 2024, to identify studies investigating individual POD risk prediction using ML approaches and nomograms. The risk of bias of the models in the included studies was assessed leveraging the Prediction Model Bias Risk Assessment Tool. Subgroup analyses were performed based on datasets, validation methods, study types, risk of bias, and model types.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The analysis incorporated 28 original studies comprising 80,143 patients undergoing cardiac surgery, of whom 6326 developed POD. Meta-analysis revealed that, in validation datasets, the c-index, sensitivity, and specificity for delirium prediction reached 0.805 (95% CI 0.759\u20100.852), 0.72 (95% CI 0.65\u20100.79), and 0.78 (95% CI 0.71\u20100.83), respectively. Logistic regression was the primary modeling method. In validation datasets, the c-index, sensitivity, and specificity reached 0.773 (95% CI 0.724\u20100.823), 0.73 (95% CI 0.64\u20100.80), and 0.70 (95% CI 0.65\u20100.74), respectively.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n ML-based prediction tools for POD following cardiac surgery demonstrate promising performance. However, the limited number of studies and validation approaches necessitate cautious interpretation of these findings. Future multicenter studies are warranted to develop more robust ML-based prediction tools, enabling precise risk stratification and targeted preventive interventions for POD.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/72304","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:11:47Z","timestamp":1771881107000},"page":"e72304-e72304","source":"Crossref","is-referenced-by-count":2,"title":["The Predictive Value of Machine Learning for Postoperative Delirium in Cardiac Surgery: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9953-3721","authenticated-orcid":false,"given":"Yi","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4888-6623","authenticated-orcid":false,"given":"Hong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4274-2896","authenticated-orcid":false,"given":"Ankui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0145-5507","authenticated-orcid":false,"given":"Mingming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8890-4838","authenticated-orcid":false,"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5285-0890","authenticated-orcid":false,"given":"Peng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"issue":"8","key":"R1","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1093\/eurheartj\/ehab892","article-title":"European Society of Cardiology: cardiovascular disease statistics 2021","volume":"43","author":"Timmis","journal-title":"Eur Heart J"},{"issue":"9","key":"R2","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1097\/CCM.0000000000001171","article-title":"Postoperative critical care of the adult cardiac surgical patient: part II: procedure-specific considerations, management of complications, and quality improvement","volume":"43","author":"Stephens","journal-title":"Crit Care Med"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1002\/bjs.4823","article-title":"Gastrointestinal complications after cardiac surgery","volume":"92","author":"Andersson","journal-title":"Br J Surg"},{"issue":"6","key":"R4","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1056\/NEJM200102083440601","article-title":"Longitudinal assessment of neurocognitive function after coronary-artery bypass surgery","volume":"344","author":"Newman","journal-title":"N Engl J Med"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1056\/NEJMoa1112923","article-title":"Cognitive trajectories after postoperative delirium","volume":"367","author":"Saczynski","journal-title":"N Engl J Med"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.h2538","article-title":"Outcome of delirium in critically ill patients: systematic review and meta-analysis","volume":"350","author":"Salluh","journal-title":"BMJ"},{"key":"R7","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","journal-title":"Int J Nurs Stud"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1093\/bja\/aew476","article-title":"Risk prediction models for delirium in the intensive care unit after cardiac surgery: a systematic review and independent external validation","volume":"118","author":"Lee","journal-title":"Br J Anaesth"},{"issue":"12","key":"R9","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1016\/j.clinthera.2024.09.013","article-title":"Machine learning for prediction of postoperative delirium in adult patients: a systematic review and meta-analysis","volume":"46","author":"Chen","journal-title":"Clin Ther"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"PROBAST: a tool to assess the risk of bias and applicability of prediction model studies","volume":"170","author":"Wolff","journal-title":"Ann Intern Med"},{"issue":"9","key":"R11","doi-asserted-by":"publisher","first-page":"2768","DOI":"10.1177\/0962280218785504","article-title":"A framework for meta-analysis of prediction model studies with binary and time-to-event outcomes","volume":"28","author":"Debray","journal-title":"Stat Methods Med Res"},{"issue":"10","key":"R12","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1016\/j.jagp.2013.01.061","article-title":"White-matter hyperintensities predict delirium after cardiac surgery","volume":"21","author":"Hatano","journal-title":"Am J Geriatr Psychiatry"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/s00246-023-03297-5","article-title":"Risk factors and nomogram model of postoperative delirium in children with congenital heart disease: a single-center prospective study","volume":"45","author":"Mao","journal-title":"Pediatr Cardiol"},{"issue":"6","key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109932","article-title":"Machine learning with clinical and intraoperative biosignal data for predicting postoperative delirium after cardiac surgery","volume":"27","author":"Han","journal-title":"iScience"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychores.2023.111553","article-title":"Online interpretable dynamic prediction models for postoperative delirium after cardiac surgery under cardiopulmonary bypass developed based on machine learning algorithms: a retrospective cohort study","volume":"176","author":"Zhao","journal-title":"J Psychosom Res"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1016\/j.iccn.2024.103717","article-title":"A nomogram for predicting postoperative delirium in pediatric patients following cardiopulmonary bypass: a prospective observational study","volume":"83","author":"Lin","journal-title":"Intensive Crit Care Nurs"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinane.2020.110158","article-title":"Development and validation of a delirium risk prediction preoperative model for cardiac surgery patients (DELIPRECAS): an observational multicentre study","volume":"69","author":"de la Varga-Mart\u00ednez","journal-title":"J Clin Anesth"},{"issue":"6","key":"R18","doi-asserted-by":"publisher","first-page":"3944","DOI":"10.21037\/jtd-24-578","article-title":"Construction and validation of a risk prediction model for postoperative delirium in patients with off\u2010pump coronary artery bypass grafting","volume":"16","author":"Zhang","journal-title":"J Thorac Dis"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-48418-5","article-title":"Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms","volume":"13","author":"Nagata","journal-title":"Sci Rep"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1186\/s12872-023-03111-3","article-title":"A nomogram model for assessing predictors and prognosis of postoperative delirium in patients receiving acute type A aortic dissection surgery","volume":"23","author":"Lin","journal-title":"BMC Cardiovasc Disord"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2023.1287607","article-title":"Predicting postoperative delirium after cardiovascular surgeries from preoperative portable electroencephalography oscillations","volume":"14","author":"Hata","journal-title":"Front Psychiatry"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1186\/s13019-022-02005-3","article-title":"Prediction model for delirium in patients with cardiovascular surgery: development and validation","volume":"17","author":"Xu","journal-title":"J Cardiothorac Surg"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.2147\/CIA.S350195","article-title":"Prediction of postoperative delirium after cardiac surgery with a quick test of cognitive speed, mini-mental state examination and hospital anxiety and depression scale","volume":"17","author":"Segern\u00e4s","journal-title":"Clin Interv Aging"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezac573","article-title":"Two-stage prediction model for postoperative delirium in patients in the intensive care unit after cardiac surgery","volume":"63","author":"Cai","journal-title":"Eur J Cardiothorac Surg"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.3389\/fsurg.2021.772675","article-title":"Construction and application of a model for predicting the risk of delirium in postoperative patients with type a aortic dissection","volume":"8","author":"He","journal-title":"Front Surg"},{"issue":"11","key":"R26","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci9110308","article-title":"The practical use of white cell inflammatory biomarkers in prediction of postoperative delirium after cardiac surgery","volume":"9","author":"Kotfis","journal-title":"Brain Sci"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1177\/1474515117733365","article-title":"Can we predict a delirium after cardiac surgery? A validation study of a delirium risk checklist","volume":"17","author":"Ten Broeke","journal-title":"Eur J Cardiovasc Nurs"},{"issue":"3","key":"R28","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.3233\/JAD-170380","article-title":"Delayed recall and working memory MMSE domains predict delirium following cardiac surgery","volume":"59","author":"Price","journal-title":"J Alzheimers Dis"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1177\/1474515112450244","article-title":"Prediction of delirium after cardiac surgery and the use of a risk checklist","volume":"12","author":"Koster","journal-title":"Eur J Cardiovasc Nurs"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","DOI":"10.1186\/s12872-024-03723-3","article-title":"A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records","volume":"24","author":"Li","journal-title":"BMC Cardiovasc Disord"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","DOI":"10.1186\/s13019-023-02339-6","article-title":"Dynamic predictive scores for cardiac surgery-associated agitated delirium: a single-center retrospective observational study","volume":"18","author":"Tian","journal-title":"J Cardiothorac Surg"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2022.950188","article-title":"Early alteration of peripheral blood lymphocyte subsets as a risk factor for delirium in critically ill patients after cardiac surgery: a prospective observational study","volume":"14","author":"Li","journal-title":"Front Aging Neurosci"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezab570","article-title":"Risk factors for postoperative delirium after cardiac surgical procedures with cardioplegic arrest","volume":"62","author":"Andr\u00e1si","journal-title":"Eur J Cardiothorac Surg"},{"issue":"2","key":"R34","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1161\/CIRCULATIONAHA.108.795260","article-title":"Derivation and validation of a preoperative prediction rule for delirium after cardiac surgery","volume":"119","author":"Rudolph","journal-title":"Circulation"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2023.1237055","article-title":"Unveiling the nexus of postoperative fever and delirium in cardiac surgery: identifying predictors for enhanced patient care","volume":"10","author":"Wang","journal-title":"Front Cardiovasc Med"},{"key":"R36","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","journal-title":"Comput Biol Med"},{"issue":"7","key":"R37","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1016\/j.jagp.2023.12.017","article-title":"Preoperative delirium risk screening in patients undergoing a cardiac surgery: results from the prospective observational FINDERI study","volume":"32","author":"Sadlonova","journal-title":"Am J Geriatr Psychiatry"},{"issue":"4","key":"R38","doi-asserted-by":"publisher","DOI":"10.2196\/14993","article-title":"Exploiting machine learning algorithms and methods for the prediction of agitated delirium after cardiac surgery: models development and validation study","volume":"7","author":"Mufti","journal-title":"JMIR Med Inform"},{"key":"R39","doi-asserted-by":"crossref","unstructured":"Lapp L Roper M Kavanagh K Schraag S . Predicting the onset of delirium on hourly basis in an intensive care unit following cardiac surgery. Presented at: 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS); Jul 21-23, 2022:234-239; Shenzen, China. [doi: 10.1109\/CBMS55023.2022.00048]","DOI":"10.1109\/CBMS55023.2022.00048"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","first-page":"W1","DOI":"10.7326\/M18-1377","article-title":"PROBAST: a tool to assess risk of bias and applicability of prediction model studies: explanation and elaboration","volume":"170","author":"Moons","journal-title":"Ann Intern Med"},{"issue":"4","key":"R41","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.ejcnurse.2010.09.001","article-title":"Risk factors of delirium after cardiac surgery: a systematic review","volume":"10","author":"Koster","journal-title":"Eur J Cardiovasc Nurs"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e72304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:02:33Z","timestamp":1782842553000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e72304"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":41,"URL":"https:\/\/doi.org\/10.2196\/72304","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]},"article-number":"v28i8e72304"}}