Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG

Miikka Ermes; Mika Särkelä; Mark van Gils; Anne Vakkuri; Arvi Yli-Hankala; Ville Jäntti

doi:10.1109/IEMBS.2006.260442

Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG

Miikka Ermes, Mika Särkelä, Mark van Gils, Anne Vakkuri, Arvi Yli-Hankala, Ville Jäntti

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

5 Citations (Scopus)

Abstract

Sevoflurane is a volatile anesthetic which is reported to cause epileptiform EEG changes together with undesired symptoms such as convulsions. In this paper, an algorithm for the automatic detection of these EEG changes is presented which could enable safer induction of anesthesia with sevoflurane by informing the clinicians about the epileptiform EEG. EEG was recorded from 60 healthy female patients during sevoflurane anesthesia. A neurophysiologist classified the EEG waveforms. Each anesthesia period lasted 6 minutes. 48 signal features were extracted from the raw EEG. 5-sec segments of EEG were classified based on the extracted features using a decision tree with a logistic regression based decisions and the classification results were compared to the neurophysiologist's classifications. Awake EEG was recognized with 69% / 96% (sensitivity / specificity), Burst suppression with 56% / 98%, Epileptiform EEG with 83% / 87 %, normal slow anesthesia EEG with 86% / 64 %, slow anesthesia EEG with monophasic pattern with 65% / 80 %, and slow anesthesia EEG with monophasic pattern and spikes with 54% / 84%.

Original language	English
Title of host publication	2006 International Conference of the IEEE Engineering in Medicine and Biology Society
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	6343-6346
ISBN (Print)	978-1-4244-0032-4
DOIs	https://doi.org/10.1109/IEMBS.2006.260442
Publication status	Published - 2006
MoE publication type	A4 Article in a conference publication

Publication series

Series	Annual International Conference of the IEEE Engineering in Medicine and Biology Society
ISSN	1557-170X

Keywords

EEG
Anesthesia
Sevoflurane

Access to Document

10.1109/IEMBS.2006.260442

Cite this

Ermes, M., Särkelä, M., van Gils, M., Vakkuri, A., Yli-Hankala, A., & Jäntti, V. (2006). Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG. In 2006 International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 6343-6346). IEEE Institute of Electrical and Electronic Engineers. https://doi.org/10.1109/IEMBS.2006.260442

Ermes, Miikka ; Särkelä, Mika ; van Gils, Mark et al. / Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG. 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Institute of Electrical and Electronic Engineers, 2006. pp. 6343-6346 (Annual International Conference of the IEEE Engineering in Medicine and Biology Society).

@inproceedings{80913c29107e41a3b25f0922df82f4fb,

title = "Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG",

abstract = "Sevoflurane is a volatile anesthetic which is reported to cause epileptiform EEG changes together with undesired symptoms such as convulsions. In this paper, an algorithm for the automatic detection of these EEG changes is presented which could enable safer induction of anesthesia with sevoflurane by informing the clinicians about the epileptiform EEG. EEG was recorded from 60 healthy female patients during sevoflurane anesthesia. A neurophysiologist classified the EEG waveforms. Each anesthesia period lasted 6 minutes. 48 signal features were extracted from the raw EEG. 5-sec segments of EEG were classified based on the extracted features using a decision tree with a logistic regression based decisions and the classification results were compared to the neurophysiologist's classifications. Awake EEG was recognized with 69% / 96% (sensitivity / specificity), Burst suppression with 56% / 98%, Epileptiform EEG with 83% / 87 %, normal slow anesthesia EEG with 86% / 64 %, slow anesthesia EEG with monophasic pattern with 65% / 80 %, and slow anesthesia EEG with monophasic pattern and spikes with 54% / 84%.",

keywords = "EEG, Anesthesia, Sevoflurane",

author = "Miikka Ermes and Mika S{\"a}rkel{\"a} and {van Gils}, Mark and Anne Vakkuri and Arvi Yli-Hankala and Ville J{\"a}ntti",

year = "2006",

doi = "10.1109/IEMBS.2006.260442",

language = "English",

isbn = "978-1-4244-0032-4",

series = "Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

pages = "6343--6346",

booktitle = "2006 International Conference of the IEEE Engineering in Medicine and Biology Society",

address = "United States",

}

Ermes, M, Särkelä, M, van Gils, M, Vakkuri, A, Yli-Hankala, A & Jäntti, V 2006, Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG. in 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Institute of Electrical and Electronic Engineers, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6343-6346. https://doi.org/10.1109/IEMBS.2006.260442

Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG. / Ermes, Miikka; Särkelä, Mika; van Gils, Mark et al.
2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Institute of Electrical and Electronic Engineers, 2006. p. 6343-6346 (Annual International Conference of the IEEE Engineering in Medicine and Biology Society).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG

AU - Ermes, Miikka

AU - Särkelä, Mika

AU - van Gils, Mark

AU - Vakkuri, Anne

AU - Yli-Hankala, Arvi

AU - Jäntti, Ville

PY - 2006

Y1 - 2006

N2 - Sevoflurane is a volatile anesthetic which is reported to cause epileptiform EEG changes together with undesired symptoms such as convulsions. In this paper, an algorithm for the automatic detection of these EEG changes is presented which could enable safer induction of anesthesia with sevoflurane by informing the clinicians about the epileptiform EEG. EEG was recorded from 60 healthy female patients during sevoflurane anesthesia. A neurophysiologist classified the EEG waveforms. Each anesthesia period lasted 6 minutes. 48 signal features were extracted from the raw EEG. 5-sec segments of EEG were classified based on the extracted features using a decision tree with a logistic regression based decisions and the classification results were compared to the neurophysiologist's classifications. Awake EEG was recognized with 69% / 96% (sensitivity / specificity), Burst suppression with 56% / 98%, Epileptiform EEG with 83% / 87 %, normal slow anesthesia EEG with 86% / 64 %, slow anesthesia EEG with monophasic pattern with 65% / 80 %, and slow anesthesia EEG with monophasic pattern and spikes with 54% / 84%.

AB - Sevoflurane is a volatile anesthetic which is reported to cause epileptiform EEG changes together with undesired symptoms such as convulsions. In this paper, an algorithm for the automatic detection of these EEG changes is presented which could enable safer induction of anesthesia with sevoflurane by informing the clinicians about the epileptiform EEG. EEG was recorded from 60 healthy female patients during sevoflurane anesthesia. A neurophysiologist classified the EEG waveforms. Each anesthesia period lasted 6 minutes. 48 signal features were extracted from the raw EEG. 5-sec segments of EEG were classified based on the extracted features using a decision tree with a logistic regression based decisions and the classification results were compared to the neurophysiologist's classifications. Awake EEG was recognized with 69% / 96% (sensitivity / specificity), Burst suppression with 56% / 98%, Epileptiform EEG with 83% / 87 %, normal slow anesthesia EEG with 86% / 64 %, slow anesthesia EEG with monophasic pattern with 65% / 80 %, and slow anesthesia EEG with monophasic pattern and spikes with 54% / 84%.

KW - EEG

KW - Anesthesia

KW - Sevoflurane

U2 - 10.1109/IEMBS.2006.260442

DO - 10.1109/IEMBS.2006.260442

M3 - Conference article in proceedings

SN - 978-1-4244-0032-4

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology Society

SP - 6343

EP - 6346

BT - 2006 International Conference of the IEEE Engineering in Medicine and Biology Society

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Ermes M, Särkelä M, van Gils M, Vakkuri A, Yli-Hankala A, Jäntti V. Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG. In 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Institute of Electrical and Electronic Engineers. 2006. p. 6343-6346. (Annual International Conference of the IEEE Engineering in Medicine and Biology Society). doi: 10.1109/IEMBS.2006.260442

Method for the Automatic Detection of Epileptiform Waveforms in Sevoflurane-induced Anesthesia EEG

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this