{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T14:37:53Z","timestamp":1790865473234,"version":"4.1.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T00:00:00Z","timestamp":1665705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>In older patients receiving general anesthesia, postoperative delirium (POD) is the most frequent form of cerebral dysfunction. Early identification of patients at higher risk to develop POD could provide the opportunity to adapt intraoperative and postoperative therapy. We, therefore, propose a machine learning approach to predict the risk of POD in elderly patients, using routine intraoperative electroencephalography (EEG) and clinical data that are readily available in the operating room.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We conducted a retrospective analysis of the data of a single-center study at the Charit\u00e9-Universit\u00e4tsmedizin Berlin, Department of Anesthesiology [ISRCTN 36437985], including 1,277 patients, older than 60 years with planned surgery and general anesthesia. To deal with the class imbalance, we used balanced ensemble methods, specifically Bagging and Random Forests and as a performance measure, the area under the ROC curve (AUC-ROC). We trained our models including basic clinical parameters and intraoperative EEG features in particular classical spectral and burst suppression signatures as well as multi-band covariance matrices, which were classified, taking advantage of the geometry of a Riemannian manifold. The models were validated with 10 repeats of a 10-fold cross-validation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Including EEG data in the classification resulted in a robust and reliable risk evaluation for POD. The clinical parameters alone achieved an AUC-ROC score of 0.75. Including EEG signatures improved the classification when the patients were grouped by anesthetic agents and evaluated separately for each group. The spectral features alone showed an AUC-ROC score of 0.66; the covariance features showed an AUC-ROC score of 0.68. The AUC-ROC scores of EEG features relative to patient data differed by anesthetic group. The best performance was reached, combining both the EEG features and the clinical parameters. Overall, the AUC-ROC score was 0.77, for patients receiving Propofol it was 0.78, for those receiving Sevoflurane it was 0.8 and for those receiving Desflurane 0.73. Applying the trained prediction model to an independent data set of a different clinical study confirmed these results for the combined classification, while the classifier on clinical parameters alone did not generalize.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>A machine learning approach combining intraoperative frontal EEG signatures with clinical parameters could be an easily applicable tool to early identify patients at risk to develop POD.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnagi.2022.911088","type":"journal-article","created":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T07:07:04Z","timestamp":1665731224000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Machine-learning model predicting postoperative delirium in older patients using intraoperative frontal electroencephalographic signatures"],"prefix":"10.3389","volume":"14","author":[{"given":"Vera","family":"R\u00f6hr","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Blankertz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Finn M.","family":"Radtke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Spies","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susanne","family":"Koch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,10,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1097\/EJA.0000000000000594","article-title":"European society of anaesthesiology evidence-based and consensus-based guideline on postoperative delirium","volume":"34","author":"Aldecoa","year":"2017","journal-title":"Eur. J. Anaesthesiol"},{"key":"B2","article-title":"The Riemannian potato: an automatic and adaptive artifact detection method for online experiments using Riemannian geometry","volume-title":"TOBI Workshop lV","author":"Barachant","year":"2013"},{"key":"B3","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1109\/TNSRE.2019.2893113","article-title":"The Riemannian potato field: a tool for online signal quality index of EEG","volume":"27","author":"Barth\u00e9lemy","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"},{"key":"B4","unstructured":""},{"key":"B5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s12871-021-01543-y","article-title":"Postoperative delirium prediction using machine learning models and preoperative electronic health record data","volume":"22","author":"Bishara","year":"2022","journal-title":"BMC Anesthesiol"},{"key":"B6","first-page":"1328","article-title":"Threshold based optimization of performance metrics with severely imbalanced big security data","volume-title":"2019 IEEE 31st International Conference on Tools With Artificial Intelligence","author":"Calvert","year":"2019"},{"key":"B7","unstructured":"ChenC.\n            BreimanL.\n          UC BerkeleyDepartment of StatisticsRandom Fore st to Learn Imbalanced Data [Technical Report]2004"},{"key":"B8","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.1109\/TSP.2010.2053029","article-title":"Shrinkage algorithms for MMSE covariance estimation","volume":"58","author":"Chen","year":"2010","journal-title":"IEEE Trans. Signal Process"},{"key":"B9","volume-title":"Non-Parametric Synchronization Measures Used in EEG and MEG","author":"Congedo","year":"2018"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/2326263X.2017.1297192","article-title":"Riemannian geometry for eeg-based brain-computer interfaces; a primer and a review","volume":"4","author":"Congedo","year":"2017","journal-title":"Brain Comput. Interfaces"},{"key":"B11","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1213\/ANE.0000000000005660","article-title":"A processed electroencephalogram-based brain anesthetic resistance index is associated with postoperative delirium in older adults: a dual center study","volume":"134","author":"Cooter Wright","year":"2022","journal-title":"Anesth. Anal"},{"key":"B12","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1097\/ALN.0000000000001859","article-title":"Poor performance on a preoperative cognitive screening test predicts postoperative complications in older orthopedic surgical patients","volume":"127","author":"Culley","year":"2017","journal-title":"Anesthesiology"},{"key":"B13","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1213\/ANE.0000000000000989","article-title":"Intraoperative electroencephalogram suppression predicts postoperative delirium","volume":"122","author":"Fritz","year":"2016","journal-title":"Anesth. Analg"},{"key":"B14","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","article-title":"A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches","volume":"42","author":"Galar","year":"2012","journal-title":"IEEE Trans. Syst. Man Cybern. Part C"},{"key":"B15","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3389\/fnsys.2019.00056","article-title":"Intraoperative low alpha power in the electroencephalogram is associated with postoperative subsyndromal delirium","volume":"13","author":"Gutierrez","year":"2019","journal-title":"Front. Syst. Neurosci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1137\/1.9781611972788.13","article-title":"Roughly balanced bagging for imbalanced data","volume":"2","author":"Hido","year":"2008","journal-title":"Stat. Anal. Data Mining"},{"key":"B17","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s40537-019-0225-0","article-title":"Medicare fraud detection using neural networks","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"B18","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1159\/000502950","article-title":"Cognitive impairment is associated with absolute intraoperative frontal \u03b1-band power but not with baseline \u03b1-band power: a pilot study","volume":"48","author":"Koch","year":"2019","journal-title":"Dement. Geriatr. Cogn. Disord"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1598","DOI":"10.1213\/ANE.0000000000005668","article-title":"Perioperative electroencephalogram spectral dynamics related to postoperative delirium in older patients","volume":"133","author":"Koch","year":"2021","journal-title":"Anesth. Anal"},{"key":"B20","article-title":"Addressing the curse of imbalanced training sets: one-sided selection","volume-title":"ICML","author":"Kub\u00e1t","year":"1997"},{"key":"B21","doi-asserted-by":"publisher","first-page":"7602","DOI":"10.1038\/s41598-018-26030-2","article-title":"Neural predisposing factors of postoperative delirium in elderly patients with femoral neck fracture","volume":"8","author":"Kyeong","year":"2018","journal-title":"Sci. Rep"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5555\/3122009.3122026","article-title":"Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"Lema\u00eetre","year":"2017","journal-title":"J. Mach. Learn. Res"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"SCIKIT-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"B24","doi-asserted-by":"publisher","first-page":"E1142","DOI":"10.1073\/pnas.1221180110","article-title":"Electroencephalogram signatures of loss and recovery of consciousness from propofol","volume":"110","author":"Purdon","year":"2013","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"B25","doi-asserted-by":"publisher","first-page":"i46","DOI":"10.1093\/bja\/aev213","article-title":"The ageing brain: age-dependent changes in the electroencephalogram during propofol and sevoflurane general anaesthesia","volume":"115","author":"Purdon","year":"2015","journal-title":"Br. J. Anaesth"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1093\/bja\/aet055","article-title":"Monitoring depth of anaesthesia in a randomized trial decreases the rate of postoperative delirium but not postoperative cognitive dysfunction","volume":"110","author":"Radtke","year":"2013","journal-title":"Br. J. Anaesth"},{"key":"B27","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/s12871-015-0051-7","article-title":"Intraoperative burst suppression is associated with postoperative delirium following cardiac surgery: a prospective, observational study","volume":"15","author":"Soehle","year":"2015","journal-title":"BMC Anesthesiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e0611","DOI":"10.1097\/CCE.0000000000000611","article-title":"VE-CAM-S: visual EEG-based grading of delirium severity and associations with clinical outcomes","volume":"4","author":"Tesh","year":"2022","journal-title":"Crit. Care Explor"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e11","DOI":"10.1097\/CCM.0000000000005224","article-title":"Physiological assessment of delirium severity: the electroencephalographic confusion assessment method severity score (E-CAM-S)","volume":"50","author":"van Sleuwen","year":"2022","journal-title":"Crit. Care Med"},{"key":"B30","doi-asserted-by":"publisher","first-page":"109896","DOI":"10.1016\/j.jclinane.2020.109896","article-title":"Predicting postoperative delirium after microvascular decompression surgery with machine learning","volume":"66","author":"Wang","year":"2020","journal-title":"J. Clin. Anesth"},{"key":"B31","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TAU.1967.1161901","article-title":"The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms","volume":"15","author":"Welch","year":"1967","journal-title":"IEEE Trans. Audio Electroacoust"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1109\/TBME.2017.2742541","article-title":"Transfer learning: a Riemannian geometry framework with applications to brain-computer interfaces","volume":"65","author":"Zanini","year":"2018","journal-title":"IEEE Trans. Biomed. Eng"},{"key":"B33","first-page":"72","article-title":"Threshold moving approaches for addressing the class imbalance problem and their application to multi-label classification","volume-title":"2020 4th International Conference on Advances in Image Processing, ICAIP 2020","author":"Zhang","year":"2020"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2022.911088\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T07:07:12Z","timestamp":1665731232000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2022.911088\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,14]]},"references-count":33,"alternative-id":["10.3389\/fnagi.2022.911088"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2022.911088","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,14]]},"article-number":"911088"}}