Electroencephalogram variability analysis for monitoring depth of anesthesia

Chen, Yi-Feng; Fan, Shou-Zen; Abbod, Maysam F.; Shieh, Jiann-Shing; Zhang, Mingming

doi:10.1088/1741-2552/ac3316

Cited by 10 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the EEG spectra have failed due to the non-monotonicity of the linear effects [70]. Existing DOA monitoring indices, such as the Bispectral index, state entropy and response entropy, PE, and the Cerebral State Index provide a scalar ranging from 0-100 to qualify the DOA [33,[71][72][73]. All of these measures are data-driven in that they use mathematical methods to calculate values from EEG signals.…”

Section: The Parameters Of Cnmm Can Track the Doamentioning

confidence: 99%

Tracking the effects of propofol, sevoflurane and (S)-ketamine anesthesia using an unscented Kalman filter-based neural mass model

et al. 2023

View full text Add to dashboard Cite

Objective: Neural mass model (NMM) has been widely used to investigate the neurophysiological mechanisms of anesthestic drugs induced general anesthesia (GA). However, whether the parameters of NMM could track the effects of anesthesia still unknown.Approach: We proposed using the cortical NMM (CNMM) to infer the potential neurophysiological mechanism of three different anesthetic drugs (i.e., propofol, sevoflurane, and (S)-ketamine) induced GA, and we employed unscented Kalman filter (UKF) to track any change in raw electroencephalography (rEEG) in frontal area during GA. We did this by estimating the parameters of population gain [i.e., excitatory/inhibitory postsynaptic potential (EPSP/IPSP, i.e., parameter A/B in CNMM) and the time constant rate of EPSP/IPSP (i.e., parameter a/b in CNMM). We compared the rEEG and simulated EEG (sEEG) from the perspective of spectrum, phase-amplitude coupling (PAC), and permutation entropy (PE). Main results: Under three estimated parameters (i.e., A, B, and a for propofol/sevoflurane or b for (S)-ketamine), the rEEG and sEEG had similar waveforms, time-frequency spectra, and PAC patterns during GA for the three drugs. The PE curves derived from rEEG and sEEG had high correlation coefficients (propofol: 0.97±0.03, sevoflurane: 0.96±0.03, (S)-ketamine: 0.98±0.02) and coefficients of determination (R2) (propofol: 0.86±0.03, sevoflurane: 0.68±0.30, (S)-ketamine: 0.70±0.18). Except for parameter A for sevoflurane, the estimated parameters for each drug in CNMM can differentiate wakefulness and non-wakefulness states. Compared with the simulation of three estimated parameters, the UKF-based CNMM had lower tracking accuracy under the simulation of four estimated parameters (i.e., A, B, a, and b) for three drugs.Significance: The results demonstrate that a combination of CNMM and UKF could track the neural activities during GA. The EPSP/IPSP and their time constant rate can interpert the anesthetic drug’s effect on the brain, and can be used as a new index for depth of anesthesia monitoring.

show abstract

Section: The Parameters Of Cnmm Can Track the Doamentioning

confidence: 99%

Tracking the effects of propofol, sevoflurane and (S)-ketamine anesthesia using an unscented Kalman filter-based neural mass model

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence techniques have been employed to analyze EEG signals to assess DOA [17][18][19][20][21][22][23][24][25][26]. DOA estimation involves two primary tasks.…”

Section: Introductionmentioning

confidence: 99%

SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia

Yu,

Zhou,

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective:Monitoring the depth of anaesthesia (DOA) during surgery is of critical importance. However, accurate and real-time estimation of DOA remains a challenging task. In this paper, we proposed a signal quality index (SQI) network (SQINet) for assessing the electroencephalogram (EEG) signal quality and a DOA network (DOANet) for analyzing EEG signals to precisely estimate DOA. The two networks are termed SQI-DOANet.Approach:The SQINet contained a shallow convolutional neural network to quickly determine the quality of the EEG signal. The DOANet comprised a feature extraction module for extracting features, a dual attention module for fusing multi-channel and multi-scale information, and a gated multilayer perceptron module for extracting temporal information. The performance of the SQI-DOANet model was validated by training and testing the model on the large VitalDB database, with the bispectral index (BIS) as the reference standard.Main results:The proposed DOANet yielded a Pearson correlation coefficient with the BIS score of 0.88 in the 5-fold cross-validation, with a mean absolute error (MAE) of 4.81. The mean Pearson correlation coefficient of SQI-DOANet with the BIS score in the 5-fold cross-validation was 0.82, with an MAE of 5.66.Significance:The SQI-DOANet model outperformed three compared methods. The proposed SQI-DOANet may be used as a new deep learning method for DOA estimation. The code of the SQI-DOANet will be made available publicly at https://github.com/YuRui8879/SQI-DOANet.

show abstract

“…Accordingly, many commercial models for monitoring the DoA have been developed based on electroencephalograms EEG signals. Currently Bispectral Index (BIS) is considered the standard device for prediction the DoA [22][23][24][25]. Although the BIS has been proven to be effective in practice, it has limitations in many aspects [18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Developing a robust model to predict depth of anesthesia from single channel EEG signal

Alsafy

Diykh

2022

Phys Eng Sci Med

View full text Add to dashboard Cite

Monitoring depth of anaesthesia (DoA) from electroencephalograph (EEG) signals is an ongoing challenge for anaesthesiologists. In this study, we propose an intelligence model that predicts the DoA from a single channel electroencephalograph (EEG) signal. A segmentation technique based on a sliding window is employed to partition EEG signals. Hierarchical dispersion entropy (HDE) is applied to each EEG segment. A set of features is extracted from each EEG segment. The extracted features are investigated using a community graph detection approach (CGDA), and the most relevant features are selected to trace the DoA. The proposed model, based on HDE coupled with CGDA, is evaluated in term of BIS index using several statistical metrics such Q-Q plot, regression, and correlation coefficients. In addition, the proposed model is evaluated against the BIS index in the case of the poor signal quality. The results demonstrated that the proposed model showed an earlier reaction compared with the BIS index when patient’s state transits from deep anaesthesia to moderate anaesthesia in the case of poor signal quality. The highest Pearson correlation coefficient obtained by the proposed is 0.96.

show abstract

Electroencephalogram variability analysis for monitoring depth of anesthesia

Cited by 10 publications

References 51 publications

Tracking the effects of propofol, sevoflurane and (S)-ketamine anesthesia using an unscented Kalman filter-based neural mass model

Tracking the effects of propofol, sevoflurane and (S)-ketamine anesthesia using an unscented Kalman filter-based neural mass model

SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia

Developing a robust model to predict depth of anesthesia from single channel EEG signal

Contact Info

Product

Resources

About