{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T08:40:33Z","timestamp":1792658433903,"version":"4.5.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000133","name":"Agency for Healthcare Research and Quality","doi-asserted-by":"publisher","award":["R01HS029324"],"award-info":[{"award-number":["R01HS029324"]}],"id":[{"id":"10.13039\/100000133","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background and Objective<\/jats:title>\n                    <jats:p>Cardiac surgeries are associated with a range of serious postoperative complications, and current predictive models often rely on static summaries of preoperative and intraoperative data compiled after the case. Such development limits their utility in real-time clinical settings. To address this challenge, we developed TE-Transformer, an end-to-end deep learning framework that continuously ingests heterogeneous electronic health record (EHR) data\u2014including preoperative variables, high-frequency vital signs, medication administration records, and brief surgical notes texts\u2014to provide real-time, multitask predictions of multiple postoperative complications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective cohort of 6416 patients undergoing cardiac surgery was used to develop and evaluate TE-Transformer. The architecture reduced reliance on manually engineered temporal summary features by encoding irregular intraoperative observations as event-level representations. Continuous risk estimates were updated at 30-minute intervals, enabling a dynamic perspective on patient status. Performance was benchmarked against traditional machine learning models (eg, XGBoost, Random Forest) and deep learning comparators (LSTM, GRU, CNN) frequently used in sequential modelling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We analyzed 6416 cardiac surgeries (61% male; median [IQR] age 62 [53-70]). Across classification tasks, TE-Transformer achieved AUROC (area under the receiver operating characteristic curve)\/AUPRC (area under the precision-recall curve) of 0.8461\/0.3994 (mortality), 0.8837\/0.8033 (delirium), and 0.7956\/0.6666 (acute kidney injury). For continuous endpoints, mean absolute error (MAE) was 0.0633 (low SBP [systolic blood pressure] time), 0.0920 (N glucose high), 0.0020 (N glucose low), and 0.9781 (postoperative ventilation duration). Ablation study showed the full multimodal model improved performance over the preoperative-only baseline, most notably for 30-day mortality AUROC (+0.049), postoperative delirium AUPRC (+0.059), and postoperative ventilation MAE (\u22120.082), with intraoperative flowsheet events contributing the largest single increment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>TE-Transformer used routinely collected perioperative data to generate continuously updated risk estimates for multiple postoperative complications and achieved better predictive performance than conventional models. These findings support further evaluation of real-time, multimodal prediction frameworks for intraoperative decision support. This approach highlights the potential of transformer-based, multitask prediction as a foundation for future intraoperative decision support in cardiac surgery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag142","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:42:25Z","timestamp":1785498145000},"page":"2137-2146","source":"Crossref","is-referenced-by-count":0,"title":["A real-time machine learning framework for improved intraoperative risk predictions in cardiac surgery patients"],"prefix":"10.1093","volume":"33","author":[{"given":"Daoyi","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science & Engineering, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]},{"name":"AI for Health Institute, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Engineering, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]},{"name":"AI for Health Institute, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Engineering, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]},{"name":"AI for Health Institute, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]},{"name":"Department of Anesthesiology, Washington University in St. Louis , St. Louis, MO 63110,","place":["United States"]},{"name":"Institute for Informatics, Data Science, and Biostatistics, Washington University in St. Louis , St. Louis, MO 63110,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0235-1632","authenticated-orcid":false,"given":"Joanna","family":"Abraham","sequence":"additional","affiliation":[{"name":"AI for Health Institute, Washington University in St. Louis , St. Louis, MO 63130,","place":["United States"]},{"name":"Department of Anesthesiology, Washington University in St. Louis , St. Louis, MO 63110,","place":["United States"]},{"name":"Institute for Informatics, Data Science, and Biostatistics, Washington University in St. Louis , St. Louis, MO 63110,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"2026102204065780800_ocag142-B1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.15171\/jcvtr.2014.014","article-title":"Predictors of prolonged mechanical ventilation after open heart surgery","volume":"6","author":"Totonchi","year":"2014","journal-title":"J Cardiovasc Thorac Res"},{"key":"2026102204065780800_ocag142-B2","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.athoracsur.2019.09.100","article-title":"The impact of major postoperative complications on long-term survival after cardiac surgery","volume":"110","author":"Seese","year":"2020","journal-title":"Ann Thorac Surg"},{"key":"2026102204065780800_ocag142-B3","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.athoracsur.2019.09.061","article-title":"Out-of-hospital 30-day deaths after cardiac surgery are often underreported","volume":"110","author":"Hannan","year":"2020","journal-title":"Ann Thorac Surg"},{"key":"2026102204065780800_ocag142-B4","doi-asserted-by":"publisher","first-page":"153","DOI":"10.2147\/IJNRD.S167477","article-title":"Acute kidney injury after cardiac surgery: prevalence, impact and management challenges","volume":"12","author":"Vives","year":"2019","journal-title":"Int J Nephrol Renovasc Dis"},{"key":"2026102204065780800_ocag142-B5","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1097\/ACO.0000000000000061","article-title":"Delirium in the cardiac surgical ICU","volume":"27","author":"Brown","year":"2014","journal-title":"Curr Opin Anaesthesiol"},{"key":"2026102204065780800_ocag142-B6","doi-asserted-by":"publisher","first-page":"5285","DOI":"10.3390\/jcm10225285","article-title":"Cardiac surgery associated AKI prevention strategies and medical treatment for CSA-AKI","volume":"10","author":"Ostermann","year":"2021","journal-title":"J Clin Med"},{"key":"2026102204065780800_ocag142-B7","doi-asserted-by":"publisher","first-page":"183","DOI":"10.5935\/0103-507x.20140027","article-title":"[Strategies for prevention of acute kidney injury in cardiac surgery: an integrative review]","volume":"26","author":"Santana-Santos","year":"2014","journal-title":"Rev Bras Ter Intensiva"},{"key":"2026102204065780800_ocag142-B8","doi-asserted-by":"crossref","first-page":"960581","DOI":"10.3389\/fcvm.2022.960581","article-title":"Strategies for post\u2013cardiac surgery acute kidney injury prevention: a network meta-analysis of randomized controlled trials","volume":"9","author":"Chen","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"2026102204065780800_ocag142-B9","doi-asserted-by":"publisher","first-page":"380","DOI":"10.21037\/atm.2018.06.08","article-title":"Mechanical ventilation management during cardiothoracic surgery: an open challenge","volume":"6","author":"Bignami","year":"2018","journal-title":"Ann Transl Med"},{"key":"2026102204065780800_ocag142-B10","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1186\/s12872-023-03315-7","article-title":"Factors associated with long-term mechanical ventilation in patients undergoing cardiovascular surgery","volume":"23","author":"Rahimi","year":"2023","journal-title":"BMC Cardiovasc Disord"},{"key":"2026102204065780800_ocag142-B11","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1053\/j.jvca.2019.09.028","article-title":"Trials focusing on prevention and treatment of delirium after cardiac surgery: a systematic review of randomized evidence","volume":"34","author":"Pieri","year":"2020","journal-title":"J Cardiothorac Vasc Anesth"},{"key":"2026102204065780800_ocag142-B12","volume-title":"StatPearls","author":"Shaydakov","year":"2025"},{"key":"2026102204065780800_ocag142-B13","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.1002\/hec.3933","article-title":"The effect of decision fatigue on surgeons\u2019 clinical decision making","volume":"28","author":"Persson","year":"2019","journal-title":"Health Econ"},{"key":"2026102204065780800_ocag142-B14","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1097\/SLA.0000000000001051","article-title":"The impact of operating room distractions on stress, workload, and teamwork","volume":"261","author":"Wheelock","year":"2015","journal-title":"Ann Surg"},{"key":"2026102204065780800_ocag142-B15","doi-asserted-by":"publisher","first-page":"3838","DOI":"10.1111\/jocs.16842","article-title":"Machine learning to predict adverse outcomes after cardiac surgery: a systematic review and meta-analysis","volume":"37","author":"Penny-Dimri","year":"2022","journal-title":"J Card Surg"},{"key":"2026102204065780800_ocag142-B16","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1016\/j.bja.2024.08.004","article-title":"Effect of machine learning models on clinician prediction of postoperative complications: the perioperative ORACLE randomised clinical trial","volume":"133","author":"Fritz","year":"2024","journal-title":"Br J Anaesth"},{"key":"2026102204065780800_ocag142-B17","doi-asserted-by":"publisher","first-page":"e212240","DOI":"10.1001\/jamanetworkopen.2021.2240","article-title":"Use of machine learning to develop and evaluate models using preoperative and intra-operative data to identify risks of postoperative complications","volume":"4","author":"Xue","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2026102204065780800_ocag142-B18","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s00540-024-03377-7","article-title":"Pediatric cardiac surgery: machine learning models for postoperative complication prediction","volume":"38","author":"Florquin","year":"2024","journal-title":"J Anesth"},{"key":"2026102204065780800_ocag142-B19","doi-asserted-by":"publisher","first-page":"e2322285","DOI":"10.1001\/jamanetworkopen.2023.22285","article-title":"Development and validation of a machine learning model to identify patients before surgery at high risk for postoperative adverse events","volume":"6","author":"Mahajan","year":"2023","journal-title":"JAMA Netw Open"},{"key":"2026102204065780800_ocag142-B20","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1016\/j.jtcvs.2020.07.105","article-title":"Machine learning improves mortality risk prediction after cardiac surgery: systematic review and meta-analysis","volume":"163","author":"Benedetto","year":"2022","journal-title":"J Thorac Cardiovasc Surg"},{"key":"2026102204065780800_ocag142-B21","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1016\/j.bja.2019.01.013","article-title":"Perioperative Quality Initiative consensus statement on intra-operative blood pressure, risk and outcomes for elective surgery","volume":"122","author":"Sessler","year":"2019","journal-title":"Br J Anaesth"},{"key":"2026102204065780800_ocag142-B22","doi-asserted-by":"publisher","first-page":"884144","DOI":"10.3389\/fcvm.2022.884144","article-title":"Outcomes of postoperative delirium in patients undergoing cardiac surgery: a systematic review and meta-analysis","volume":"9","author":"Lin","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"2026102204065780800_ocag142-B23","doi-asserted-by":"publisher","first-page":"e0252209","DOI":"10.1371\/journal.pone.0252209","article-title":"Risk factors for acute kidney injury and mortality in high risk patients undergoing cardiac surgery","volume":"16","author":"Serraino","year":"2021","journal-title":"PLoS One"},{"key":"2026102204065780800_ocag142-B24","doi-asserted-by":"publisher","first-page":"862","DOI":"10.4065\/80.7.862","article-title":"Intra-operative hyperglycemia and perioperative outcomes in cardiac surgery patients","volume":"80","author":"Gandhi","year":"2005","journal-title":"Mayo Clin Proc"},{"key":"2026102204065780800_ocag142-B25","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.ijcard.2018.01.137","article-title":"Association between intra-operative hypotension and 30-day mortality, major adverse cardiac events, and acute kidney injury after non-cardiac surgery: a meta-analysis of cohort studies","volume":"258","author":"Gu","year":"2018","journal-title":"Int J Cardiol"},{"key":"2026102204065780800_ocag142-B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3516367","article-title":"Self-supervised transformer for sparse and irregularly sampled multivariate clinical time-series","volume":"16","author":"Tipirneni","year":"2022","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2026102204065780800_ocag142-B27","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.4330\/wjc.v6.i11.1209","article-title":"Blood glucose management in the patient undergoing cardiac surgery: a review","volume":"6","author":"Reddy","year":"2014","journal-title":"World J Cardiol"},{"key":"2026102204065780800_ocag142-B28","doi-asserted-by":"publisher","first-page":"CD013494","DOI":"10.1002\/14651858.CD013494.pub2","article-title":"High versus low blood pressure targets for cardiac surgery while on cardiopulmonary bypass","volume":"11","author":"Kotani","year":"2022","journal-title":"Cochrane Database Syst Rev"},{"key":"2026102204065780800_ocag142-B29","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1097\/ACO.0000000000001312","article-title":"Initiatives to detect and prevent death from perioperative deterioration","volume":"36","author":"Posthuma","year":"2023","journal-title":"Curr Opin Anaesthesiol"},{"key":"2026102204065780800_ocag142-B30","doi-asserted-by":"publisher","first-page":"100256","DOI":"10.1016\/j.ijnsa.2024.100256","article-title":"The effect of early warning scoring systems on adverse outcome in surgical patients: a systematic review","volume":"7","author":"Stolze","year":"2024","journal-title":"Int J Nurs Stud Adv"},{"key":"2026102204065780800_ocag142-B31","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1016\/j.bja.2020.06.063","article-title":"Postoperative delirium: perioperative assessment, risk reduction, and management","volume":"125","author":"Jin","year":"2020","journal-title":"Br J Anaesth"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag142\/71383426\/ocag142.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/11\/2137\/71383426\/ocag142.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/11\/2137\/71383426\/ocag142.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T08:07:04Z","timestamp":1792656424000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/11\/2137\/8833981"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":31,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,9,24]]},"published-print":{"date-parts":[[2026,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag142","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,11]]},"published":{"date-parts":[[2026,9,24]]}}}