Abstract
Intraoperative burst suppression (BS) is associated with postoperative neurocognitive disorders, which could lead to increased mortality, morbidity and longer hospitalisation. The main objective of this study is to build a machine learning model capable of predicting the BS pattern between the phases of induction and incision, based on EEG and patient characteristics acquired preoperatively. To this end, several models, namely decision trees, random forest, XGBoost, SVM and logistic regression, were trained on the data with varying window sizes. The performance of the trained models is evaluated using stratified 5-fold cross-validation and a \(5\times 2\)cv t-test was applied to test significance. The main objective is to study, among other factors, the potential impact of the anaesthetic dosage on BS occurrence with the aim of personalising this process. The results obtained indicate that a Logistic Regression approach trained on the data epoched into 7-s windows can achieve a precision score of 0.63 and an ROC-AUC score of 0.61 while predicting future BS occurences. Furthermore, the explanations of the feature importance obtained from the SHapley Additive exPlanations (SHAP) demonstrate that the mean absolute power delta and alpha bands contribute the most to the predictions made as well as the dosage of the anaesthetic agent propofol.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Approval was obtained from the Medical Ethical Board of the Maastricht University Medical Centre (METC 2023–2543) on the 15th of June 2021 for this retrospective study.
References
Alpaydm, E.: Combined \(5\times 2\) cv F test for comparing supervised classification learning algorithms. Neural Comput. 11(8), 1885–1892 (1999)
Awal, M.A., Colditz, P.B., Boashash, B., Azemi, G.: Detection of neonatal EEG burst-suppression using a time-frequency approach, pp. 1–6 (2014)
Brown, E.N., Lydic, R., Schiff, N.D.: General anesthesia, sleep, and coma. N. Engl. J. Med. 363(27), 2638–2650 (2010)
Bruhn, J., Bouillon, T.W., Shafer, S.L.: Bispectral index (BIS) and burst suppression: revealing a part of the bis algorithm. J. Clin. Monit. Comput. 16, 593–596 (2000)
De Faria, W., Schamberg, G., Brown, E.N.: Classifying EEG of propofol-induced unconsciousness in the presence of burst suppression, pp. 1–5 (2020)
Dumermuth, G., Molinari, L.: Spectral analysis of the EEG - some fundamentals revisited and some open problems. Neuropsychobiology 17(1–2), 85–99 (1987)
Evered, L., et al.: Recommendations for the nomenclature of cognitive change associated with anaesthesia and surgery-2018. Anesthesiology 129(5), 872–879 (2018)
Gramfort, A., et al.: MEG and EEG data analysis with MNE-Python. Front. Neurosci. 7(267), 1 (2013)
Gupta, S.D.: Point biserial correlation coefficient and its generalization. Psychometrika 25(4), 393–408 (1960)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 1–10 (2017)
Meghdadi, A.H., et al.: Resting state EEG biomarkers of cognitive decline associated with Alzheimer’s disease and mild cognitive impairment. PloS One 16(2), e0244180 (2021)
Narula, G., Haeberlin, M., Balsiger, J., Strässle, C., Imbach, L., Keller, E.: Detection of EEG burst-suppression in neurocritical care patients using an unsupervised machine learning algorithm. Clin. Neurophysiol. 132(10), 2485–2492 (2021)
Pawar, N., Barreto Chang, O.L.: Burst suppression during general anesthesia and postoperative outcomes: mini review. Front. Syst. Neurosci. 15, 767489 (2022)
Plummer, G.S., et al.: Electroencephalogram dynamics during general anesthesia predict the later incidence and duration of burst-suppression during cardiopulmonary bypass. Clin. Neurophysiol. 130(1), 55–60 (2019)
den Ridder, T., Mess, W., Hortal, E., et. al.: Can baseline EEG predict burst suppression after induction of anesthesia in patients undergoing carotid artery surgery? preliminary results of a retrospective analysis. In: Abstract Dutch Association of Anesthesiology (2022)
Saby, J.N., Marshall, P.J.: The utility of EEG band power analysis in the study of infancy and early childhood. Dev. Neuropsychol. 37(3), 253–273 (2012)
Särkelä, M., Mustola, S., Seppänen, T., Koskinen, M., Lepola, P., Suominen, K., et al.: Automatic analysis and monitoring of burst suppression in anesthesia. J. Clin. Monit. Comput. 17, 125–134 (2002)
Shao, Y.R., et al.: Low frontal alpha power is associated with the propensity for burst suppression: an electroencephalogram phenotype for a “vulnerable brain’’. Anesth. Analg. 131(5), 1529 (2020)
Solomon, O.M., Jr.: PSD computations using welch’s method. NASA STI/Recon Technical Report N 92, 23584 (1991)
Weiner, V.S., et al.: Propofol disrupts alpha dynamics in functionally distinct thalamocortical networks during loss of consciousness. Proc. Natl. Acad. Sci. 120(11), e2207831120 (2023)
Yoshitani, K., Kawaguchi, M., Takahashi, M., Kitaguchi, K., Furuya, H.: Plasma propofol concentration and EEG burst suppression ratio during normothermic cardiopulmonary bypass. Br. J. Anaesth. 90(2), 122–126 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yozkan, E., Hortal, E., Karel, J., Janssen, M.L.F., Vossen, C.J., Gommer, E.D. (2024). Prediction of Burst Suppression Occurrence Under General Anaesthesia Using Pre-operative EEG Signals. In: Ferrández Vicente, J.M., Val Calvo, M., Adeli, H. (eds) Artificial Intelligence for Neuroscience and Emotional Systems. IWINAC 2024. Lecture Notes in Computer Science, vol 14674. Springer, Cham. https://doi.org/10.1007/978-3-031-61140-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-61140-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-61139-1
Online ISBN: 978-3-031-61140-7
eBook Packages: Computer ScienceComputer Science (R0)