Predicting Intraoperative Burst Suppression Using Preoperative EEG and Patient Characteristics.
Journal:
International journal of neural systems
Published Date:
Apr 16, 2025
Abstract
Burst suppression (BS) is an electroencephalogram (EEG) pattern observed in patients undergoing general anesthesia. The occurrence of BS is associated with adverse outcomes such as postoperative delirium, extended recovery time, and increased postoperative mortality. The detection and prediction of BS can help expedite the evaluation of patient conditions, optimize anesthesia administration, and improve patient safety. This study explores the potential for automatic BS detection using intraoperative EEG and BS prediction using preoperative EEG signals and patient characteristics. A dataset comprising 287 patients who underwent carotid endarterectomy procedures at Maastricht University Medical Center+ was analyzed. An EEG toolbox developed by T. Zhan at the Massachusetts Institute of Technology was utilized for the automatic detection/annotation of BS, while five machine learning classifiers were employed to predict BS occurrence using preoperative data. Based on the 160 patients manually annotated by EEG experts (regarding the presence or absence of BS), the automatic detection tool demonstrated an accuracy of 0.75. For the BS prediction task, an initial subset of 120 patients was evaluated, showing modest performance, with the -nearest neighbors ([Formula: see text]) classifier achieving the best results, with an accuracy of 0.72. Subsequent experiments indicated that increasing the number of patients (by using to annotate the unlabeled instances), applying SMOTE to balance the training set, and enriching the feature set was beneficial. The final experiment demonstrated a significant improvement, with Random Forest and Gradient Boosting outperforming other classifiers, achieving an accuracy of 0.86 and ROC-AUC of 0.94. Patient characteristics, including type of anesthetic agents, symptoms, age, mean absolute delta power, mean absolute theta power, and cognitive impairment, were identified by an xAI method as important features potentially indicating the predisposition to experience BS.
