Machine learning for a combined electroencephalographic anesthesia index to detect awareness under anesthesia

Tacke, Moritz; Kochs, Eberhard; Mueller, Marianne; Krämer, Stefan; Jordan, Denis; Schneider, Gerhard

doi:10.1371/journal.pone.0238249

Cited by 11 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, the hypnotic dose administered has not a linear relationship with DoA, including both volatile and intravenous anesthetics ( 23 ). The field of ML offers many different algorithms that could be used to build a reliable index to monitor the DoA ( 24 ). In this context Afshar et al ( 25 ) proposed a combinatorial DL structure involving CNN, bidirectional long short-term memory (LSTM), and an attention layer.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and anesthesia: a narrative review

Carnà¹,

Russo²,

Vincenzo³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background and Objective The aim of this narrative review is to analyze whether or not artificial intelligence (AI) and its subsets are implemented in current clinical anesthetic practice, and to describe the current state of the research in the field. AI is a general term which refers to all the techniques that enable computers to mimic human intelligence. AI is based on algorithms that gives machines the ability to reason and perform functions such as problem-solving, object and word recognition, inference of world states, and decision-making. It includes machine learning (ML) and deep learning (DL). Methods We performed a narrative review of the literature on Scopus, PubMed and Cochrane databases. The research string comprised various combinations of “artificial intelligence”, “machine learning”, “anesthesia”, “anesthesiology”. The databases were searched independently by two authors. A third reviewer would mediate any disagreement the results of the two screeners. Key Content and Findings The application of AI has shown excellent results in both anesthesia and in operating room (OR) management. In each phase of the perioperative process, pre-, intra- and postoperative ones, it is able to perform different and specific tasks, using various techniques. Conclusions Thanks to the use of these new technologies, even anesthesia, as it is happening for other disciplines, is going through a real revolution, called Anesthesia 4.0. However, AI is not free from limitations and open issues. Unfortunately, the models created, provided they have excellent performance, have not yet entered daily practice. Clinical impact analyzes and external validations are needed before this happens. Therefore, qualitative research will be needed to better understand the ethical, cultural, and societal implications of integrating AI into clinical workflows.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and anesthesia: a narrative review

Carnà¹,

Russo²,

Vincenzo³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

show abstract

“…A common way of quantifying EEG is by calculating the power in pre-defined frequency bands (delta, theta, alpha and beta) [10]. These features are commonly used in EEG analysis for level of anaesthesia classification as they are easy to calculate, and have a physiological meaning as they are known to be related to certain brain states and to be driven by specific brain regions [23][24][25][26][27], making them biologically explainable. Besides frequency, entropy is also commonly used as a feature input for SVM modelling [24,26,[28][29][30].…”

Section: Introductionmentioning

confidence: 99%

“…These features are commonly used in EEG analysis for level of anaesthesia classification as they are easy to calculate, and have a physiological meaning as they are known to be related to certain brain states and to be driven by specific brain regions [23][24][25][26][27], making them biologically explainable. Besides frequency, entropy is also commonly used as a feature input for SVM modelling [24,26,[28][29][30]. SVM classification of the depth of anaesthesia for all kinds of anaesthetics (excluding nitrous oxide) has been compared with other machine-learning algorithms, like random forest classification, regression, and artificial neural networks, with mixed results [26,27,29].…”

Section: Introductionmentioning

confidence: 99%

Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra

Vrijdag

Hallum

Tonks

et al. 2023

J Clin Monit Comput

View full text Add to dashboard Cite

Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In this single-blind, cross-over study, 32-channel EEG was recorded from 12 healthy participants exposed to 0, 20, 30 and 40% end-tidal nitrous oxide. Features of the delta-, theta-, alpha- and beta-band power were used within a 12-fold, participant-wise cross-validation framework to train and test two SVMs: (1) binary SVM classifying EEG during 0 or 40% exposure (chance = 50%); (2) multi-class SVM classifying EEG during 0, 20, 30 or 40% exposure (chance = 25%). Both the binary (accuracy 92%) and the multi-class (accuracy 52%) SVMs classified EEG recordings at rates significantly better than chance (p < 0.001 and p = 0.01, respectively). To determine the relative importance of frequency band features for classification accuracy, we systematically removed features before re-training and re-testing the SVMs. This showed the relative importance of decreased delta power and the frontal region. SVM classification identified that the most important effects of nitrous oxide were found in the delta band in the frontal electrodes that was consistent between participants. Furthermore, support-vector classification of nitrous oxide dosage is a promising method that might be used to improve patient monitoring during nitrous oxide anaesthesia.

show abstract

“…Middle-latency auditory evoked potentials (AEPs) also quantify the action of anesthetic drugs and detect the transition from consciousness to unconsciousness [19][20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

“…e AEP index (AEP) is a dimensionless number scaled from 100 (awake) to 0 and a mathematically derived variable measuring the amplitude and latency of the cortical midlatency auditory evoked potential that occurs in response to sound (a "click") [21,23,24]. Sevoflurane inhalational and propofol intravenous anesthesia are two widely used anesthetic techniques.…”

Section: Introductionmentioning

confidence: 99%

A Crossover Comparison of the Sensitivity and the Specificity between BIS and AEP in Predicting Unconsciousness in General Anesthesia

Huang

Wang

Gao

et al. 2020

Scientific Programming

View full text Add to dashboard Cite

Background. There is an increasing concern of awareness and recall during general anesthesia for both the patient and the anesthetist. The bispectral index (BIS) is used to assess the level of sedation and depth of anesthesia and detect consciousness in different anesthetic drugs. Middle-latency auditory evoked potentials (AEPs) also quantify action of anesthetic drugs and detect the transition from consciousness to unconsciousness. We aim to compare the sensitivity and specificity between BIS and AEP in predicting unconsciousness in inhalational sevoflurane anesthesia and intravenous propofol anesthesia. Methods. Totally, 40 patients were randomly allocated into two groups: propofol or sevoflurane group. In the propofol group, anesthesia was induced with target-controlled infusion propofol. In the sevoflurane group, anesthesia was induced by increasing concentrations of sevoflurane. There were 3 end points during induction: sedation, unconsciousness, and anesthesia. Target and effect-site concentrations of propofol, end-tidal concentration of sevoflurane, and BIS and AEP were recorded at each stage. Results. We obtained good EC50 with both monitors, at which there is a 50% chance that the patient has reached the end point, but the index variation was affected by the anesthetic technique. Propofol had higher correlations with stage of anesthesia, BIS, and AEP than sevoflurane. BIS had higher correlations with depth of anesthesia than AEP, but we did not find an anesthetic depth monitor that had high sensitivity and specificity and is not affected by the anesthetic technique. Conclusions. The prediction powers of BIS and AEP do not seem as good as some papers mentioned.

show abstract

Machine learning for a combined electroencephalographic anesthesia index to detect awareness under anesthesia

Cited by 11 publications

References 28 publications

Artificial intelligence and anesthesia: a narrative review

Artificial intelligence and anesthesia: a narrative review

Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra

A Crossover Comparison of the Sensitivity and the Specificity between BIS and AEP in Predicting Unconsciousness in General Anesthesia

Contact Info

Product

Resources

About