Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia

Abstract

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.

Machine learning reveals interhemispheric somatosensory coherence as indicator of anesthetic depth

“…Such work has prominently led to the development of the proprietary Bispectral Index Score (BIS), which makes use of several electroencephalographic parameters to estimate DoA, and has been established as the predominant anesthetic monitor used during human surgeries (Dumont, 2012 ). Other published approaches for human DoA estimation rely on non-linear features extracted from electroencephalographic measurements or evoked potentials (Al-Kadi et al, 2013 ), which are used as inputs to traditional machine learning algorithms or artificial neural networks (Li et al, 2020 ; Abel et al, 2021 ).…”

Do we really measure what we think we are measuring?

“…For example, by combining different resting-state or evoked EEG features, previous studies have improved classification between groups or experimental conditions. 38 , 39 , 40 , 41 , 42 , 43 Similarly, previous studies have reported that a combination of EEG features allowed a better characterization of certain brain processes. 44 , 45 , 46 Our results using PCA also show evidence that, for some cognitive variables, latent dimensions of EEG features might be more informative than single features.…”

Advanced Bioelectrical Signal Processing Methods: Past, Present and Future Approach—Part II: Brain Signals

“…To test the filtering methods, there are databases contaminated with motion artifacts [ 266 ]. There are also plenty of publicly available databases for assessment of neurological status in sleep [ 267 ], or in a specific condition, such as anesthesia [ 268 ]. Special attention is also paid to the research of epilepsy, therefore there are also specific databases containing EEG signals during epileptic seizures in both adults [ 269 , 270 ] or pediatric patients [ 271 ].…”