Design and Implementation of a Machine Learning Based EEG Processor for Accurate Estimation of Depth of Anesthesia

Saadeh, Wala; Khan, Fatima; Altaf, Muhammad Awais Bin

doi:10.1109/tbcas.2019.2921875

Cited by 59 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our classification models performed favorably in comparison to previous studies involving the use of machine learning to track conscious state. One recent study was able to predict depth of anesthesia in one of four qualitatively defined classes (from “profound unconsciousness” to “awake”) in real time with average accuracy = 0.92 using hand-selected features [ 29 ]. The good average performance of the classifier used in this study is complicated by an unclear clinical/physiological inference of the “true” patient state, which was subjectively assigned in a post-hoc manner.…”

Section: Discussionmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia

et al. 2021

View full text Add to dashboard Cite

In current anesthesiology practice, anesthesiologists infer the state of unconsciousness without directly monitoring the brain. Drug- and patient-specific electroencephalographic (EEG) signatures of anesthesia-induced unconsciousness have been identified previously. We applied machine learning approaches to construct classification models for real-time tracking of unconscious state during anesthesia-induced unconsciousness. We used cross-validation to select and train the best performing models using 33,159 2s segments of EEG data recorded from 7 healthy volunteers who received increasing infusions of propofol while responding to stimuli to directly assess unconsciousness. Cross-validated models of unconsciousness performed very well when tested on 13,929 2s EEG segments from 3 left-out volunteers collected under the same conditions (median volunteer AUCs 0.99-0.99). Models showed strong generalization when tested on a cohort of 27 surgical patients receiving solely propofol collected in a separate clinical dataset under different circumstances and using different hardware (median patient AUCs 0.95—0.98), with model predictions corresponding with actions taken by the anesthesiologist during the cases. Performance was also strong for 17 patients receiving sevoflurane (alone or in addition to propofol) (median AUCs 0.88—0.92). These results indicate that EEG spectral features can predict unconsciousness, even when tested on a different anesthetic that acts with a similar neural mechanism. With high performance predictions of unconsciousness, we can accurately monitor anesthetic state, and this approach may be used to engineer infusion pumps to intelligibly respond to patients’ neural activity.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Machine learning methods can help detect patterns that may otherwise go undetected, and improve performance in predictive tasks ( Bzdok et al, 2018 ). These algorithms have already been applied in similar contexts, such as detecting traumatic brain injury ( Prichep et al, 2014 ), estimating depth of anesthesia ( Saadeh et al, 2019 ), studying Alzheimer’s disease ( Simpraga et al, 2017 ), and studying seizure activity ( Elahian et al, 2017 ). There is also evidence for using EEG data and an SVM method to predict the diagnosis of complex and variable neurodevelopmental conditions, such as autism spectrum disorder ( Bosl, 2018 ; Bosl et al, 2018 ).…”

Section: Discussionmentioning

confidence: 99%

Pain phenotypes classified by machine learning using electroencephalography features

et al. 2020

View full text Add to dashboard Cite

“…The six features including beta ratio, spectral edge frequency, and four bands of spectral energy were extracted from the EEG signal, and then, the decision tree classifier was used to determine the DoA in [ 14 ]. The authors considered the four classes for DoA as deep, moderate, and light versus awake state.…”

Section: Introductionmentioning

confidence: 99%

Time‐Frequency Analysis of EEG Signals and GLCM Features for Depth of Anesthesia Monitoring

Mousavi

Asgharzadeh-Bonab

Ranjbarzadeh

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

One of the important tasks in the operating room is monitoring the depth of anesthesia (DoA) during surgery, and noninvasive techniques are very popular. Hence, we propose a new scheme for DoA monitoring considering the time-frequency analysis of electroencephalography (EEG) signals and GLCM features extracted from them. To this end, at first, the time-frequency map (TFM) of each channel of each EEG is computed by smoothed pseudo-Wigner–Ville distribution (SPWVD), where the EEG signal used in this paper is recorded in 15 channels. After that, we consider the gray-level co-occurrence matrix (GLCM) to obtain the content of TFM, and after that, four features such as homogeneity, correlation, energy, and contrast are obtained for each GLCM. Finally, after the selection of efficient features using the minimum redundancy maximum relevance (MRMR) method, the K-nearest neighbor (KNN) classifier is utilized to determine the DoA. Here, we consider the three states, namely, deep hypnotic, surgical anesthesia, and sedation and awake states according to bispectral index (BIS), and each EEG epoch is classified to these states. We also employ data augmentation to enhance the training phase and increase accuracy. We obtain the accuracy and confusion matrix of the proposed method. We also analyze the effects of a number of gray levels of GLCM, distance measure in KNN classifier, and parameters of data augmentation on the performance of the proposed method. Results indicate the efficiency of the proposed method to determine the DoA during surgery.

show abstract

Design and Implementation of a Machine Learning Based EEG Processor for Accurate Estimation of Depth of Anesthesia

Cited by 59 publications

References 27 publications

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia

Pain phenotypes classified by machine learning using electroencephalography features

Time‐Frequency Analysis of EEG Signals and GLCM Features for Depth of Anesthesia Monitoring

Contact Info

Product

Resources

About