A novel approach for computer assisted EEG monitoring in the adult ICU

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Objective The implementation of a computer assisted system for real-time classification of the electroencephalogram (EEG) in critically ill patients. Methods Eight quantitative features were extracted from the raw EEG and combined into a single classifier. The system was trained with 41 EEG recordings and subsequently evaluated using an additional 20 recordings. Through visual analysis, each recording was assigned to one of the following categories: normal, iso-electric, low voltage, burst suppression, slowing, and EEGs with generalized periodic discharges or seizure activity. Results 36 (88%) recordings from the training set and 17 (85%) recordings from the test set were classified correctly. A user interface was developed to present both trend-curves and a diagnostic output in text form. Implementation in a dedicated EEG monitor allowed real-time analysis in the intensive care unit (ICU) during pilot measurements in four patients. Conclusions We present the first results from a computer assisted EEG interpretation system, based on a combination of eight quantitative features. Our system provided an initial, reasonably accurate interpretation by non-experts of the most common EEG patterns observed in neurological patients in the adult ICU. Significance Computer assisted EEG monitoring may improve early detection of seizure activity and ischemia in critically ill patients.
Original languageEnglish
Pages (from-to)2100-2109
Number of pages9
JournalClinical neurophysiology
Volume122
Issue number10
DOIs
Publication statusPublished - 2011

Fingerprint

Intensive Care Units
Electroencephalography
Critical Illness
Seizures
Computer Systems
Ischemia

Keywords

  • METIS-281881
  • IR-104478

Cite this

@article{81ad2b7ac555464f8f85f588759c94f6,
title = "A novel approach for computer assisted EEG monitoring in the adult ICU",
abstract = "Objective The implementation of a computer assisted system for real-time classification of the electroencephalogram (EEG) in critically ill patients. Methods Eight quantitative features were extracted from the raw EEG and combined into a single classifier. The system was trained with 41 EEG recordings and subsequently evaluated using an additional 20 recordings. Through visual analysis, each recording was assigned to one of the following categories: normal, iso-electric, low voltage, burst suppression, slowing, and EEGs with generalized periodic discharges or seizure activity. Results 36 (88{\%}) recordings from the training set and 17 (85{\%}) recordings from the test set were classified correctly. A user interface was developed to present both trend-curves and a diagnostic output in text form. Implementation in a dedicated EEG monitor allowed real-time analysis in the intensive care unit (ICU) during pilot measurements in four patients. Conclusions We present the first results from a computer assisted EEG interpretation system, based on a combination of eight quantitative features. Our system provided an initial, reasonably accurate interpretation by non-experts of the most common EEG patterns observed in neurological patients in the adult ICU. Significance Computer assisted EEG monitoring may improve early detection of seizure activity and ischemia in critically ill patients.",
keywords = "METIS-281881, IR-104478",
author = "M.C. Cloostermans and {de Vos}, {Cecilia Cecilia Clementine} and {van Putten}, {Michel Johannes Antonius Maria}",
year = "2011",
doi = "10.1016/j.clinph.2011.02.035",
language = "English",
volume = "122",
pages = "2100--2109",
journal = "Clinical neurophysiology",
issn = "1388-2457",
publisher = "Elsevier",
number = "10",

}

A novel approach for computer assisted EEG monitoring in the adult ICU. / Cloostermans, M.C.; de Vos, Cecilia Cecilia Clementine; van Putten, Michel Johannes Antonius Maria.

In: Clinical neurophysiology, Vol. 122, No. 10, 2011, p. 2100-2109.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A novel approach for computer assisted EEG monitoring in the adult ICU

AU - Cloostermans, M.C.

AU - de Vos, Cecilia Cecilia Clementine

AU - van Putten, Michel Johannes Antonius Maria

PY - 2011

Y1 - 2011

N2 - Objective The implementation of a computer assisted system for real-time classification of the electroencephalogram (EEG) in critically ill patients. Methods Eight quantitative features were extracted from the raw EEG and combined into a single classifier. The system was trained with 41 EEG recordings and subsequently evaluated using an additional 20 recordings. Through visual analysis, each recording was assigned to one of the following categories: normal, iso-electric, low voltage, burst suppression, slowing, and EEGs with generalized periodic discharges or seizure activity. Results 36 (88%) recordings from the training set and 17 (85%) recordings from the test set were classified correctly. A user interface was developed to present both trend-curves and a diagnostic output in text form. Implementation in a dedicated EEG monitor allowed real-time analysis in the intensive care unit (ICU) during pilot measurements in four patients. Conclusions We present the first results from a computer assisted EEG interpretation system, based on a combination of eight quantitative features. Our system provided an initial, reasonably accurate interpretation by non-experts of the most common EEG patterns observed in neurological patients in the adult ICU. Significance Computer assisted EEG monitoring may improve early detection of seizure activity and ischemia in critically ill patients.

AB - Objective The implementation of a computer assisted system for real-time classification of the electroencephalogram (EEG) in critically ill patients. Methods Eight quantitative features were extracted from the raw EEG and combined into a single classifier. The system was trained with 41 EEG recordings and subsequently evaluated using an additional 20 recordings. Through visual analysis, each recording was assigned to one of the following categories: normal, iso-electric, low voltage, burst suppression, slowing, and EEGs with generalized periodic discharges or seizure activity. Results 36 (88%) recordings from the training set and 17 (85%) recordings from the test set were classified correctly. A user interface was developed to present both trend-curves and a diagnostic output in text form. Implementation in a dedicated EEG monitor allowed real-time analysis in the intensive care unit (ICU) during pilot measurements in four patients. Conclusions We present the first results from a computer assisted EEG interpretation system, based on a combination of eight quantitative features. Our system provided an initial, reasonably accurate interpretation by non-experts of the most common EEG patterns observed in neurological patients in the adult ICU. Significance Computer assisted EEG monitoring may improve early detection of seizure activity and ischemia in critically ill patients.

KW - METIS-281881

KW - IR-104478

U2 - 10.1016/j.clinph.2011.02.035

DO - 10.1016/j.clinph.2011.02.035

M3 - Article

VL - 122

SP - 2100

EP - 2109

JO - Clinical neurophysiology

JF - Clinical neurophysiology

SN - 1388-2457

IS - 10

ER -