Machine-learning model predicting postoperative delirium in older patients using intraoperative frontal electroencephalographic signatures

Vera Röhr*, Benjamin Blankertz, Finn M. Radtke, Claudia Spies, Susanne Koch


Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

1 Downloads (Pure)


Objective: 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. Methods: We conducted a retrospective analysis of the data of a single-center study at the Charité-Universitätsmedizin 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. Results: 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. Conclusion: 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.

TidsskriftFrontiers in Aging Neuroscience
Antal sider14
StatusUdgivet - 14. okt. 2022

Bibliografisk note

Funding Information:
Author SK is an inventor on patents, sold to Medtronic. She reports a grant during the conduct of the study by the German Research Foundation. Author CS is an inventor on patents, she reports grants during the conduct of a study from the European Commission, from Aridis Pharmaceutical Inc., B. Braun Melsung, Drägerwerk AG & Co. KGaA, German Research Foundation, German Aerospace Center, Einstein Foundation Berlin, European Society of Anaesthesiology, Federal Joint Committee and Inner University grants. Grants promoting Science and Education from WHOCC, Baxter Deutschland GmbH, Cytosorbents Europe GmbH, Edwars Lifesciences Germany GmbH, Fresenius Medical Care, Grünenthal GmbH, Masimo Europe Ltd. Phizer Pharma PFE GmbH. Personal fees from Georg Thieme Verlag, Dr. F. Köhler Chemie GmbH, Sintetica GmbH, European Commission, Stifterverband für die deutsche Wissenschaft e.V./Philips, Stiftung Charite, AGUETTANT Deutschland GmbH, AbbVie Deutschland GmbH & Co. KG, Amomed Pharma GmbH, Touch Health, Copra System GmbH, Correvio GmbH, Max-Planck-Gesellschaft zur Förderung der Wissenschaft e.V., Deutsche Gesellschaft für Anästhesiologie & Intensivmedizin (DGAI), Medtronic, Philips Electronics Nederland BV, BMG, and BMBF. Aspect Medical Systems, now Medtronic, funded the initial SuDoCo study were CS was PI. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Funding Information:
VR and BB acknowledge the introduction to the field of Riemannian geometry for EEG classification, provided by Marco Congedo (University of Grenoble Alpes) in particular during a 2-weeks research stay at TU Berlin and subsequent discussions.

Funding Information:
VR acknowledges the financial support from the Research Training Group (RTG 2433) DAEDALUS (Differential Equation- and Data-driven Models in Life Sciences and Fluid Dynamics) funded by Deutsche Forschungsgemeinschaft (DFG, German Research Foundation, project 384950143). We acknowledge support from the German Research Foundation and the Open Access Publication Fund of TU Berlin.


Dyk ned i forskningsemnerne om 'Machine-learning model predicting postoperative delirium in older patients using intraoperative frontal electroencephalographic signatures'. Sammen danner de et unikt fingeraftryk.