Abstract:Background: Sedation indicators based on a single quantitative EEG (QEEG) feature have been criticised for their limited performance. We hypothesised that integration of multiple QEEG features into a single sedation-level estimator using a machine learning algorithm could reliably predict levels of sedation, independent of the sedative drug used. Methods: In total, 102 subjects receiving propofol (N¼36; 16 male/20 female), sevoflurane (N¼36; 16 male/20 female), or dexmedetomidine (N¼30; 15 male/15 female) were… Show more
“…EEG epochs with absolute amplitude >500 μV (corresponding to movement artifacts) and 0 μV (corresponding to flat EEG artifacts) were excluded for further analysis. Similar to our previous work [ 14 ], we extracted following 44 quantitative EEG (QEEG) features from each 4 s EEG epoch in this study: Time domain – (1) Nonlinear energy operator, (2) Activity (1st Hjorth parameter), (3) Mobility (2nd Hjorth parameter), (4) Complexity (3rd Hjorth parameter) [ 22 ], (5) Root mean square (RMS) amplitude, (6) Kurtosis, (7) Skewness, (8–11) mean, standard deviation, skewness and kurtosis of amplitude modulation (AM) [ 23 ], (12) Burst suppression ratio/min (BSR) [ 24 ]; Frequency domain – (13) P δ =mean power in delta band (0.5–4 Hz), (14) P θ =mean power in theta band (4–8 Hz), (15) P α =mean power in alpha band (8–12 Hz), (16) P σ =mean power in spindle band (12–16 Hz), (17) P β =power in beta band (16–25 Hz), (18) P T =total spectral power (0.5–25 Hz), (19–23) P δ / P T , P θ / P T , P α / P T , P σ / P T , P β / P T , (24–27) P δ / P θ , P α / P θ , P σ / P θ , P β / P θ , (28–30) P α / P θ , P σ / P θ , P β / P θ , (31–34) mean, standard deviation, skewness and kurtosis of frequency modulation (FM) [ 23 ] (35) spectral edge frequency, (36) peak frequency; Entropy domain – (37) Singular value decomposition entropy [ 25 ], (38) spectral entropy [ 26 ], (39) state entropy [ 27 ], (40) sample entropy [ 27 ], (41) Renyi entropy [ 28 ], (42) Shannon entropy [ 29 ], (43) permutation entropy [ 30 ], (44) fractal dimension [ 31 ]. Fig.…”
Section: Methodssupporting
confidence: 81%
“…If the model is not robust in this scenario, it will not be efficient to discriminate multiple levels of sedation. However, we have already developed a method to estimate continuous level of sedation from binary classification via sigmoid transformation in our previous work [ 14 ]. Except for tree based methods, we found that the performance of all other machine learning models was significantly influenced by the addition of remifentanil.…”
Section: Discussionmentioning
confidence: 99%
“…To overcome the limitation of drug specificity, in our preliminary work [ 14 ], we developed a machine learning framework to design a drug-independent sedation level monitoring system using quantitative features derived from the frontal EEG. We developed this framework using a traditional logistic regression model which showed promising results in estimating sedation levels using pooled data from healthy volunteers during propofol, sevoflurane, and dexmedetomidine infusion.…”
Brain monitors which track quantitative electroencephalogram (EEG) signatures to monitor sedation levels are drug and patient specific. There is a need for robust sedation level monitoring systems to accurately track sedation levels across all drug classes, sex and age groups. Forty-four quantitative features estimated from a pooled dataset of 204 EEG recordings from 66 healthy adult volunteers who received either propofol, dexmedetomidine, or sevoflurane (all with and without remifentanil) were used in a machine learning based automated system to estimate the depth of sedation. Model training and evaluation were performed using leave-one-out cross validation methodology. We trained four machine learning models to predict sedation levels and evaluated the influence of remifentanil, age, and sex on the prediction performance. The area under the receiver-operator characteristic curve (AUC) was used to assess the performance of the prediction model. The ensemble tree with bagging outperformed other machine learning models and predicted sedation levels with an AUC = 0.88 (0.81–0.90). There were significant differences in the prediction probability of the automated systems when trained and tested across different age groups and sex. The performance of the EEG based sedation level prediction system is drug, sex, and age specific. Nonlinear machine-learning models using quantitative EEG features can accurately predict sedation levels. The results obtained in this study may provide a useful reference for developing next generation EEG based sedation level prediction systems using advanced machine learning algorithms.Clinical trial registration: NCT 02043938 and NCT 03143972.
“…EEG epochs with absolute amplitude >500 μV (corresponding to movement artifacts) and 0 μV (corresponding to flat EEG artifacts) were excluded for further analysis. Similar to our previous work [ 14 ], we extracted following 44 quantitative EEG (QEEG) features from each 4 s EEG epoch in this study: Time domain – (1) Nonlinear energy operator, (2) Activity (1st Hjorth parameter), (3) Mobility (2nd Hjorth parameter), (4) Complexity (3rd Hjorth parameter) [ 22 ], (5) Root mean square (RMS) amplitude, (6) Kurtosis, (7) Skewness, (8–11) mean, standard deviation, skewness and kurtosis of amplitude modulation (AM) [ 23 ], (12) Burst suppression ratio/min (BSR) [ 24 ]; Frequency domain – (13) P δ =mean power in delta band (0.5–4 Hz), (14) P θ =mean power in theta band (4–8 Hz), (15) P α =mean power in alpha band (8–12 Hz), (16) P σ =mean power in spindle band (12–16 Hz), (17) P β =power in beta band (16–25 Hz), (18) P T =total spectral power (0.5–25 Hz), (19–23) P δ / P T , P θ / P T , P α / P T , P σ / P T , P β / P T , (24–27) P δ / P θ , P α / P θ , P σ / P θ , P β / P θ , (28–30) P α / P θ , P σ / P θ , P β / P θ , (31–34) mean, standard deviation, skewness and kurtosis of frequency modulation (FM) [ 23 ] (35) spectral edge frequency, (36) peak frequency; Entropy domain – (37) Singular value decomposition entropy [ 25 ], (38) spectral entropy [ 26 ], (39) state entropy [ 27 ], (40) sample entropy [ 27 ], (41) Renyi entropy [ 28 ], (42) Shannon entropy [ 29 ], (43) permutation entropy [ 30 ], (44) fractal dimension [ 31 ]. Fig.…”
Section: Methodssupporting
confidence: 81%
“…If the model is not robust in this scenario, it will not be efficient to discriminate multiple levels of sedation. However, we have already developed a method to estimate continuous level of sedation from binary classification via sigmoid transformation in our previous work [ 14 ]. Except for tree based methods, we found that the performance of all other machine learning models was significantly influenced by the addition of remifentanil.…”
Section: Discussionmentioning
confidence: 99%
“…To overcome the limitation of drug specificity, in our preliminary work [ 14 ], we developed a machine learning framework to design a drug-independent sedation level monitoring system using quantitative features derived from the frontal EEG. We developed this framework using a traditional logistic regression model which showed promising results in estimating sedation levels using pooled data from healthy volunteers during propofol, sevoflurane, and dexmedetomidine infusion.…”
Brain monitors which track quantitative electroencephalogram (EEG) signatures to monitor sedation levels are drug and patient specific. There is a need for robust sedation level monitoring systems to accurately track sedation levels across all drug classes, sex and age groups. Forty-four quantitative features estimated from a pooled dataset of 204 EEG recordings from 66 healthy adult volunteers who received either propofol, dexmedetomidine, or sevoflurane (all with and without remifentanil) were used in a machine learning based automated system to estimate the depth of sedation. Model training and evaluation were performed using leave-one-out cross validation methodology. We trained four machine learning models to predict sedation levels and evaluated the influence of remifentanil, age, and sex on the prediction performance. The area under the receiver-operator characteristic curve (AUC) was used to assess the performance of the prediction model. The ensemble tree with bagging outperformed other machine learning models and predicted sedation levels with an AUC = 0.88 (0.81–0.90). There were significant differences in the prediction probability of the automated systems when trained and tested across different age groups and sex. The performance of the EEG based sedation level prediction system is drug, sex, and age specific. Nonlinear machine-learning models using quantitative EEG features can accurately predict sedation levels. The results obtained in this study may provide a useful reference for developing next generation EEG based sedation level prediction systems using advanced machine learning algorithms.Clinical trial registration: NCT 02043938 and NCT 03143972.
“…Power in these bands was estimated from the multitaper power spectral estimate and was given to the ensuing classification model in dB. The bands used were: slow (0-1 Hz), delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), beta (13)(14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25), and gamma (25-50 Hz), as delineated in [2]. Thus, the X (BWP)…”
Section: Classification Modelsmentioning
confidence: 99%
“…Recently, machine learning (ML) and deep learning (DL) techniques have been applied to pattern recognition tasks in medicine with performances similar to human interpretations [18][19][20], and may even improve upon human prediction of adverse events during anesthesia [21]. Previous studies have applied a wide range ML/DL features and models to predict patient unconsciousness in Intensive Care Units [22], during dosing of anesthetics to healthy volunteers [23], or in the operating room [24][25][26]. These studies showed that many methods from machine learning applied to raw or processed EEG data perform well in tracking Modified Observer's Assessment of Alertness/Sedation (MOAA/S) scores or whether a patient had received an anesthetic bolus.…”
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
