Paper published in a journal (Scientific congresses and symposiums)
Generalized Prediction of Unconsciousness during Propofol Anesthesia using 3D Convolutional Neural Networks
Patlatzoglou, K.; Chennu, S.; Gosseries, Olivia et al.
2020In Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2020-July, p. 134-137
Peer reviewed
 

Files


Full Text
Generalized Prediction of Unconsciousness during Propofol Anesthesia using 3D Convolutional Neural Networks.pdf
Author postprint (825.67 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Anesthesiology; Anesthetics; Brain; Convolution; Deep learning; Deep neural networks; Electroencephalography; Electrophysiology; Altered states of consciousness; Automatic diagnosis; Behavioral measures; Clinical settings; Cross validation; General anesthesias; Generalized pattern; Neural correlates of consciousness; Convolutional neural networks
Abstract :
[en] Neuroscience has generated a number of recent advances in the search for the neural correlates of consciousness, but these have yet to find valuable real-world applications. Electroencephalography under anesthesia provides a powerful experimental setup to identify electrophysiological signatures of altered states of consciousness, as well as a testbed for developing systems for automatic diagnosis and prognosis of awareness in clinical settings. In this work, we use deep convolutional neural networks to automatically differentiate sub-anesthetic states and depths of anesthesia, solely from one second of raw EEG signal. Our results with leave-one-participant-out-cross-validation show that behavioral measures, such as the Ramsay score, can be used to learn generalizable neural networks that reliably predict levels of unconsciousness in unseen transitional anesthetic states, as well as in unseen experimental setups and behaviors. Our findings highlight the potential of deep learning to detect progressive changes in anesthetic-induced unconsciousness with higher granularity than behavioral or pharmacological markers. This work has broader significance for identifying generalized patterns of brain activity that index states of consciousness.Clinical Relevance - In the United States alone, over 100,000 people receive general anesthesia every day, from which up to 1% is affected by unintended intraoperative awareness [1]. Despite this, brain-based monitoring of consciousness is not common in the clinic, and has had mixed success [2]. Given this context, our aim is to develop and explore an automated deep learning model that accurately predicts and interprets the depth and quality of anesthesia from the raw EEG signal. © 2020 IEEE.
Research center :
CHU de Liège-Centre du Cerveau² - ULiège
Disciplines :
Neurology
Author, co-author :
Patlatzoglou, K.;  University of Kent, School of Computing, United Kingdom
Chennu, S.;  University of Kent, School of Computing, United Kingdom
Gosseries, Olivia  ;  Université de Liège - ULiège > GIGA Consciousness-Coma Science Group
BONHOMME, Vincent  ;  Centre Hospitalier Universitaire de Liège - CHU > Département d'Anesthésie et réanimation > Service d'anesthésie - réanimation
Wolff, Audrey ;  Université de Liège - ULiège > GIGA Consciousness-Coma Science Group
Laureys, Steven  ;  Université de Liège - ULiège > GIGA Consciousness-Coma Science Group
Language :
English
Title :
Generalized Prediction of Unconsciousness during Propofol Anesthesia using 3D Convolutional Neural Networks
Publication date :
2020
Event name :
42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020
Event date :
20 July 2020 through 24 July 2020
Audience :
International
Journal title :
Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
ISSN :
1557-170X
Publisher :
Institute of Electrical and Electronics Engineers Inc.
Volume :
2020-July
Pages :
134-137
Peer reviewed :
Peer reviewed
Commentary :
162693 9781728119908
Available on ORBi :
since 07 March 2021

Statistics


Number of views
60 (2 by ULiège)
Number of downloads
223 (1 by ULiège)

Scopus citations®
 
3
Scopus citations®
without self-citations
3
OpenCitations
 
2

Bibliography


Similar publications



Contact ORBi