Analysis of EEG to quantify depth of anesthesia using Hidden Markov Model

Junbeom Kim, Huh Hyub, Seung Z.hoo Yoon, Ho Jin Choi, Kwang M.oo Kim, Sang Hyun Park

Research output: Contribution to journalArticle

Abstract

Real-time quantification of the patient's consciousness level during anesthesia is an important issue to avoid intraoperative awareness and post-operative side effects. A depth-of-anesthesia (DoA) monitoring method called Bispectral Index (BIS) is generally used for this purpose. However, BIS is known to be inaccurate at the transitory state, and also shows a critical time delay in quantifying the patient's consciousness level. This paper introduces a novel method to reduce the response time in the quantification process. This thesis develops a new index called HDoA by analyzing EEG using Hidden Markov Model. The proposed approach is composed by two steps, training and testing. In the training step, two HMM, awakened and anesthetized model are learned based on each training set. In the testing step, by evaluating the probability of producing the testing EEG from two models respectively, the index HDoA is derived. Since the evaluation of DoA using HMM is training based method, it have better performance with more training process. Experiments show that HDoA has a high correlation with BIS at a steady state, and outperforms BIS in two ways: (1) shorter delay time in transition state, and (2) higher Fisher Score. The validity of HDoA has been tested by 8 real clinical data.

Fingerprint

Hidden Markov models
Electroencephalography
Anesthesia
Consciousness
Time delay
Testing
Intraoperative Awareness
Reaction Time
Monitoring
Experiments

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

@article{a4661e6c6e7f46c6a366d4b8ad20275b,
title = "Analysis of EEG to quantify depth of anesthesia using Hidden Markov Model",
abstract = "Real-time quantification of the patient's consciousness level during anesthesia is an important issue to avoid intraoperative awareness and post-operative side effects. A depth-of-anesthesia (DoA) monitoring method called Bispectral Index (BIS) is generally used for this purpose. However, BIS is known to be inaccurate at the transitory state, and also shows a critical time delay in quantifying the patient's consciousness level. This paper introduces a novel method to reduce the response time in the quantification process. This thesis develops a new index called HDoA by analyzing EEG using Hidden Markov Model. The proposed approach is composed by two steps, training and testing. In the training step, two HMM, awakened and anesthetized model are learned based on each training set. In the testing step, by evaluating the probability of producing the testing EEG from two models respectively, the index HDoA is derived. Since the evaluation of DoA using HMM is training based method, it have better performance with more training process. Experiments show that HDoA has a high correlation with BIS at a steady state, and outperforms BIS in two ways: (1) shorter delay time in transition state, and (2) higher Fisher Score. The validity of HDoA has been tested by 8 real clinical data.",
author = "Junbeom Kim and Huh Hyub and Yoon, {Seung Z.hoo} and Choi, {Ho Jin} and Kim, {Kwang M.oo} and Park, {Sang Hyun}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/EMBC.2014.6944642",
language = "English",
volume = "2014",
pages = "4575--4578",
journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
issn = "0589-1019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Analysis of EEG to quantify depth of anesthesia using Hidden Markov Model

AU - Kim, Junbeom

AU - Hyub, Huh

AU - Yoon, Seung Z.hoo

AU - Choi, Ho Jin

AU - Kim, Kwang M.oo

AU - Park, Sang Hyun

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Real-time quantification of the patient's consciousness level during anesthesia is an important issue to avoid intraoperative awareness and post-operative side effects. A depth-of-anesthesia (DoA) monitoring method called Bispectral Index (BIS) is generally used for this purpose. However, BIS is known to be inaccurate at the transitory state, and also shows a critical time delay in quantifying the patient's consciousness level. This paper introduces a novel method to reduce the response time in the quantification process. This thesis develops a new index called HDoA by analyzing EEG using Hidden Markov Model. The proposed approach is composed by two steps, training and testing. In the training step, two HMM, awakened and anesthetized model are learned based on each training set. In the testing step, by evaluating the probability of producing the testing EEG from two models respectively, the index HDoA is derived. Since the evaluation of DoA using HMM is training based method, it have better performance with more training process. Experiments show that HDoA has a high correlation with BIS at a steady state, and outperforms BIS in two ways: (1) shorter delay time in transition state, and (2) higher Fisher Score. The validity of HDoA has been tested by 8 real clinical data.

AB - Real-time quantification of the patient's consciousness level during anesthesia is an important issue to avoid intraoperative awareness and post-operative side effects. A depth-of-anesthesia (DoA) monitoring method called Bispectral Index (BIS) is generally used for this purpose. However, BIS is known to be inaccurate at the transitory state, and also shows a critical time delay in quantifying the patient's consciousness level. This paper introduces a novel method to reduce the response time in the quantification process. This thesis develops a new index called HDoA by analyzing EEG using Hidden Markov Model. The proposed approach is composed by two steps, training and testing. In the training step, two HMM, awakened and anesthetized model are learned based on each training set. In the testing step, by evaluating the probability of producing the testing EEG from two models respectively, the index HDoA is derived. Since the evaluation of DoA using HMM is training based method, it have better performance with more training process. Experiments show that HDoA has a high correlation with BIS at a steady state, and outperforms BIS in two ways: (1) shorter delay time in transition state, and (2) higher Fisher Score. The validity of HDoA has been tested by 8 real clinical data.

UR - http://www.scopus.com/inward/record.url?scp=84942942505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942942505&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6944642

DO - 10.1109/EMBC.2014.6944642

M3 - Article

VL - 2014

SP - 4575

EP - 4578

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SN - 0589-1019

ER -