Monitoring depth of anesthesia using combination of EEG measure and hemodynamic variables

Overview and Clinical Applications of Artificial Intelligence and Machine Learning in Cardiac Anesthesiology

Artificial intelligence- (AI) and machine learning (ML)-based applications are becoming increasingly pervasive in the healthcare setting. This has in turn challenged clinicians, hospital administrators, and health policymakers to understand such technologies and develop frameworks for safe and sustained clinical implementation. Within cardiac anesthesiology, challenges and opportunities for AI/ML to support patient care are presented by the vast amounts of electronic health data, which are collected rapidly, interpreted, and acted upon within the periprocedural area. To address such challenges and opportunities, in this article, the authors review 3 recent applications relevant to cardiac anesthesiology, including depth of anesthesia monitoring, operating room resource optimization, and transthoracic/transesophageal echocardiography, as conceptual examples to explore strengths and limitations of AI/ML within healthcare, and characterize this evolving landscape. Through reviewing such applications, the authors introduce basic AI/ML concepts and methodologies, as well as practical considerations and ethical concerns for initiating and maintaining safe clinical implementation of AI/ML-based algorithms for cardiac anesthesia patient care.

How anesthesiology can deal with innovation and new technologies?

Innovation and new technologies have always impacted significantly the anesthesiology practice all along the perioperative course, as it is recognized as one of the most transformative medical specialties specifically regarding patient's safety. Beside a number of major changes in procedures, equipment, training, and organization that aggregated to establish a strong safety culture with effective practices, anesthesiology is also a stakeholder in disruptive innovation. The present review is not exhaustive and aims to provide an overview on how innovation could change and improve anesthesiology practices through some examples as telemedicine (TM), machine learning and artificial intelligence (AI). For example, postoperative complications can be accurately predicted by AI from automated real-time electronic health record data, matching physicians' predictive accuracy. Clinical workflow could be facilitated and accelerated with mobile devices and applications, assuming that these tools should remain at the service of patients and care providers. Care providers and patients connections have improved, thanks to these digital and innovative transformations, without replacing existing relationships between them. It also should give time back to physicians and nurses to better spend it in the perioperative care, and to provide "personalized" medicine keeping a high level of standard of care.

Signal processing and machine learning algorithm to classify anaesthesia depth

BACKGROUND

Poor assessment of anaesthetic depth (AD) has led to overdosing or underdosing of the anaesthetic agent, which requires continuous monitoring to avoid complications. The evaluation of the central nervous system activity and autonomic nervous system could provide additional information on the monitoring of AD during surgical procedures.

METHODS

Observational analytical single-centre study, information on biological signals was collected during a surgical procedure under general anaesthesia for signal preprocessing, processing and postprocessing to feed a pattern classifier and determine AD status of patients. The development of the electroencephalography index was carried out through data processing and algorithm development using MATLAB V.8.1.

RESULTS

A total of 25 men and 35 women were included, with a total time of procedure average of 109.62 min. The results show a high Pearson correlation between the Complexity Brainwave Index and the indices of the entropy module. A greater dispersion is observed in the state entropy and response entropy indices, a partial overlap can also be seen in the boxes associated with deep anaesthesia and general anaesthesia in these indices. A high Pearson correlation might be explained by the coinciding values corresponding to the awake and general anaesthesia states. A high Pearson correlation might be explained by the coinciding values corresponding to the awake and general anaesthesia states.

CONCLUSION

Biological signal filtering and a machine learning algorithm may be used to classify AD during a surgical procedure. Further studies will be needed to confirm these results and improve the decision-making of anaesthesiologists in general anaesthesia.

Inference of Brain States under Anesthesia with Meta Learning Based Deep Learning Models

Monitoring the depth of unconsciousness during anesthesia is beneficial in both clinical settings and neuroscience investigations to understand brain mechanisms. Electroencephalogram (EEG) has been used as an objective means of characterizing brain altered arousal and/or cognition states induced by anesthetics in real-time. Different general anesthetics affect cerebral electrical activities in different ways. However, the performance of conventional machine learning models on EEG data is unsatisfactory due to the low Signal to Noise Ratio (SNR) in the EEG signals, especially in the office-based anesthesia EEG setting. Deep learning models have been used widely in the field of Brain Computer Interface (BCI) to perform classification and pattern recognition tasks due to their capability of good generalization and handling noises. Compared to other BCI applications, where deep learning has demonstrated encouraging results, the deep learning approach for classifying different brain consciousness states under anesthesia has been much less investigated. In this paper, we propose a new framework based on meta-learning using deep neural networks, named Anes-MetaNet, to classify brain states under anesthetics. The Anes-MetaNet is composed of Convolutional Neural Networks (CNN) to extract power spectrum features, and a time consequence model based on Long Short-Term Memory (LSTM) networks to capture the temporal dependencies, and a meta-learning framework to handle large cross-subject variability. We use a multi-stage training paradigm to improve the performance, which is justified by visualizing the high-level feature mapping. Experiments on the office-based anesthesia EEG dataset demonstrate the effectiveness of our proposed Anes-MetaNet by comparison of existing methods.

Electroencephalogram variability analysis for monitoring depth of anesthesia

Objective. In this paper, a new approach of extracting and measuring the variability in electroencephalogram (EEG) was proposed to assess the depth of anesthesia (DOA) under general anesthesia.Approach. The EEG variability (EEGV) was extracted as a fluctuation in time interval that occurs between two local maxima of EEG. Eight parameters related to EEGV were measured in time and frequency domains, and compared with state-of-the-art DOA estimation parameters, including sample entropy, permutation entropy, median frequency and spectral edge frequency of EEG. The area under the receiver-operator characteristics curve (AUC) and Pearson correlation coefficient were used to validate its performance on 56 patients.Main results. Our proposed EEGV-derived parameters yield significant difference for discriminating between awake and anesthesia stages at a significance level of 0.05, as well as improvement in AUC and correlation coefficient on average, which surpasses the conventional features of EEG in detection accuracy of unconscious state and tracking the level of consciousness.Significance. To sum up, EEGV analysis provides a new perspective in quantifying EEG and corresponding parameters are powerful and promising for monitoring DOA under clinical situations.

Quantitative assessment of the relationship between behavioral and autonomic dynamics during propofol-induced unconsciousness

During general anesthesia, both behavioral and autonomic changes are caused by the administration of anesthetics such as propofol. Propofol produces unconsciousness by creating highly structured oscillations in brain circuits. The anesthetic also has autonomic effects due to its actions as a vasodilator and myocardial depressant. Understanding how autonomic dynamics change in relation to propofol-induced unconsciousness is an important scientific and clinical question since anesthesiologists often infer changes in level of unconsciousness from changes in autonomic dynamics. Therefore, we present a framework combining physiology-based statistical models that have been developed specifically for heart rate variability and electrodermal activity with a robust statistical tool to compare behavioral and multimodal autonomic changes before, during, and after propofol-induced unconsciousness. We tested this framework on physiological data recorded from nine healthy volunteers during computer-controlled administration of propofol. We studied how autonomic dynamics related to behavioral markers of unconsciousness: 1) overall, 2) during the transitions of loss and recovery of consciousness, and 3) before and after anesthesia as a whole. Our results show a strong relationship between behavioral state of consciousness and autonomic dynamics. All of our prediction models showed areas under the curve greater than 0.75 despite the presence of non-monotonic relationships among the variables during the transition periods. Our analysis highlighted the specific roles played by fast versus slow changes, parasympathetic vs sympathetic activity, heart rate variability vs electrodermal activity, and even pulse rate vs pulse amplitude information within electrodermal activity. Further advancement upon this work can quantify the complex and subject-specific relationship between behavioral changes and autonomic dynamics before, during, and after anesthesia. However, this work demonstrates the potential of a multimodal, physiologically-informed, statistical approach to characterize autonomic dynamics.

Machine Learning Based Hardware Architecture for DOA Measurement from Mice EEG

OBJECTIVE

This research aims to design a hardware optimized machine learning based Depth of Anesthesia (DOA) measurement framework for mice and its FPGA implementation.

METHODS

Electroencephalography or EEG signal is acquired from 16 mice in the Neural Interface Research (NIR) Laboratory of the City University of Hong Kong. We present a logistic regression based approach with mathematically uncomplicated feature extraction techniques for efficient hardware implementation to estimate the DOA.

RESULTS

With the extraction of only two features, the proposed system can classify the state of consciousness with 94% accuracy for a 1 second EEG epoch, leading to a 100% accurate channel prediction after a 7 second run-time on average.

CONCLUSION

Through performance evaluation and comparative study confirmed the efficacy of the prototype.

SIGNIFICANCE

Traditionally the DOA is estimated by checking biophysical responses of a patient during the surgery. However, the physical symptoms can be misleading for a decisive conclusion due to the patient's health condition or as a side-effect of anesthetic drugs. Recently, several neuroscientific research works are correlating the EEG signal with conscious states, which is likely to have less interference with the patient's medical condition. This research presents the first-of-its-kind hardware implemented automatic DOA computation system for mice.

Dysfunction of the Glymphatic System as a Potential Mechanism of Perioperative Neurocognitive Disorders

Perioperative neurocognitive disorder (PND) frequently occurs in the elderly as a severe postoperative complication and is characterized by a decline in cognitive function that impairs memory, attention, and other cognitive domains. Currently, the exact pathogenic mechanism of PND is multifaceted and remains unclear. The glymphatic system is a newly discovered glial-dependent perivascular network that subserves a pseudo-lymphatic function in the brain. Recent studies have highlighted the significant role of the glymphatic system in the removal of harmful metabolites in the brain. Dysfunction of the glymphatic system can reduce metabolic waste removal, leading to neuroinflammation and neurological disorders. We speculate that there is a causal relationship between the glymphatic system and symptomatic progression in PND. This paper reviews the current literature on the glymphatic system and some perioperative factors to discuss the role of the glymphatic system in PND.

Monitoring anesthesia using simultaneous functional Near Infrared Spectroscopy and Electroencephalography

OBJECTIVE

This study aims to understand the neural and hemodynamic responses during general anesthesia in order to develop a comprehensive multimodal anesthesia depth monitor using simultaneous functional Near Infrared Spectroscopy (fNIRS) and Electroencephalogram (EEG).

METHODS

37 adults and 17 children were monitored with simultaneous fNIRS and EEG, during the complete general anesthesia process. The coupling of fNIRS signals with neuronal signals (EEG) was calculated. Measures of complexity (sample entropy) and phase difference were also quantified from fNIRS signals to identify unique fNIRS based biomarkers of general anesthesia.

RESULTS

A significant decrease in the complexity and power of fNIRS signals characterize the anesthesia maintenance phase. Furthermore, responses to anesthesia vary between adults and children in terms of neurovascular coupling and frontal EEG alpha power.

CONCLUSIONS

This study shows that fNIRS signals could reliably quantify the underlying neuronal activity under general anesthesia and clearly distinguish the different phases throughout the procedure in adults and children (with less accuracy).

SIGNIFICANCE

A multimodal approach incorporating the specific differences between age groups, provides a reliable measure of anesthesia depth.

GABAA receptors in the basal forebrain mediates emergence from propofol anaesthesia in rats

PURPOSE

The aim of the current study was to explore the role of the basal forebrain (BF) in propofol anaesthesia.

METHODS

In the present study, we observed the neural activities of the BF during propofol anaesthesia using calcium fibre photometry recording. Subsequently, ibotenic acid was injected into the BF to verify the role of the BF in propofol anaesthesia. Finally, to test whether GABA_A receptors in the BF were involved in modulating propofol anaesthesia, muscimol (GABA_A receptor agonist) and gabazine (GABA_A receptor antagonist) were microinjected into the BF. Cortical electroencephalogram (EEG), time to loss of righting reflex (LORR), and recovery of righting reflex (RORR) under propofol anaesthesia were recorded and analysed.

RESULTS

The activity of BF neurons was inhibited during induction of propofol anaesthesia and activated during emergence from propofol anaesthesia. In addition, non-specifical lesion of BF neurons significantly prolonged the time to RORR and increased delta power in the frontal cortex under propofol anaesthesia. Next, microinjection of muscimol into the BF delayed emergence from propofol anaesthesia, increased delta power of the frontal cortex, and decreased gamma power under propofol anaesthesia. Conversely, infusion of gabazine accelerated emergence times and decreased EEG delta power.

CONCLUSIONS

The basal forebrain is involved in modulating frontal cortex delta activity and emergence from propofol anaesthesia. Additionally, the GABA_A receptors in the basal forebrain are involved in regulating emergence propofol anaesthesia.

Detecting Loss and Regain of Consciousness during Propofol Anesthesia using Multimodal Indices of Autonomic State

We have traditionally defined `loss of consciousness' (LOC) and `regain of consciousness' (ROC) during general anesthesia in terms of behavioral correlates. We are starting to understand the dynamics in brain activity that may help define those events; however, we have not yet explored the possible autonomic correlates of LOC and ROC. In this study, we investigated the autonomic dynamics immediately surrounding loss and regain of consciousness in nine healthy volunteers under controlled propofol sedation. We used multimodal autonomic indices generated from physiologically accurate models and found that just before and after LOC and ROC could be differentiated with an AUC of 0.80. In addition, we saw that some of the autonomic changes accompanying LOC and ROC verify known information about the mechanism of action of propofol, while others indicate new avenues for exploration of propofol's effect on the autonomic nervous system. Overall, our work suggests that the autonomic dynamics surrounding the events of loss and regain of consciousness are worthy of further investigation.Clinical Relevance-This introduces the possibility of autonomic biomarkers for loss and regain of consciousness during general anesthesia that are more precise than behavioral tracking alone.

Intraoperative Cortical Asynchrony Predicts Abnormal Postoperative Electroencephalogram

BACKGROUND

Postoperative electroencephalograms (EEGs) can identify seizure activity and neurologic dysfunction in high-risk neonates requiring cardiac surgical procedures. Although intraoperative EEG monitoring is uncommon, variations in cerebral blood flow and temperature during antegrade cerebral perfusion (ACP) can manifest as cortical asynchrony during EEG monitoring. We hypothesized that intraoperative EEG cortical asynchrony would identify neonates at risk for abnormal postoperative EEG tracings.

METHODS

Neonates requiring ACP for cardiac repair or palliation had continuous baseline, intraoperative, and postoperative hemodynamic and EEG monitoring. Synchronous and asynchronous cortical bursts were quantified during (1) cooling before ACP, (2) ACP, and (3) rewarming. Asynchronous bursts were defined as interhemispheric variations in electrical voltage or frequency. Neonates were divided into 2 groups, those with and without an abnormal postoperative EEG, which was defined as either persistent asynchrony for more than 2 hours or seizure activity on EEG.

RESULTS

Among 40 neonates, 296 asynchronous bursts were noted, most commonly during rewarming. Eight (20%) neonates had an abnormal postoperative EEG (seizure activity, n = 3; persistent asynchrony, n = 5). Baseline demographics and intraoperative hemodynamics were similar between the groups. However, the total number of intraoperative asynchronous bursts was greater in neonates with an abnormal postoperative EEG (17 [11, IQR:24] vs 3 [IQR:1, 7]; P < .001). Multivariate analysis confirmed that the number of asynchronous bursts was independently associated with an abnormal postoperative EEG (odds ratio,1.35; confidence interval,:1.10, 1.65; P = .004).

CONCLUSIONS

Neonates with a greater number of intraoperative asynchronous cortical bursts had an abnormal postoperative EEG.

Challenges and barriers in finding, forming and performing for network creation

Purpose

The purpose of this paper is as follows: studying a case for technological innovation in Iran; studying the process of network creation; studying different challenges in finding, forming and performing of a collaboration network; studying comprehensive identification and analysis of the challenges in the network creation process; studying an active collaboration network in the field of medical equipment; and studying a network with different partners (consisting of a large company, a small- and medium-sized company, two subcontractors, three universities, a start-up, an accelerator and a venture capital fund).

Design/methodology/approach

The qualitative research method has been used because of a deep and rich analysis of the studied network. The study also provides an overview of finding and forming of partners and details of collaborations in the network, including partner’s goals from network entry, initial negotiations between members, business plan, shared resources and final results are expressed. The data used in this study has been collected by a totally seven semi-structured interviews. To analyze the collected data by open coding, the MAXQDA12 software was used and the basic concepts were identified and were categorized based on their similarities.

Findings

The studied network was identified as a strategic alliance. Details of finding, forming and performing of the studied network were explained. In total, 4 collaboration models and 28 different challenges in the network creation process were identified. In total, 28 different challenges were divided into 7 categories (based on their existence or absence in each of the 4 identified collaboration models). In total, seven categories of challenges were analyzed completely and the relations between challenges and partners of collaboration models were studied.

Originality/value

The collaboration network studied in this research involves several technological collaborations among different actors. Saadat, as the hub of this network, has been involved in all these collaborations, and other members have joined the network in accordance with network requirements and their capabilities. This network has been formed and developed with the aim of developing and producing various modules of vital signs monitoring since 2009. Some of the collaborations in this network, which are for production of a specific module and require long-term collaboration between the partners (such as the production of electrocardiograph or heart attack rapid diagnostic module), continue to be ongoing and some of them that focus on research and development or acquisition of technical knowledge (such as academic collaboration) after the specified result has been ended.

Monitoring the level of hypnosis using a hierarchical SVM system

Monitoring level of hypnosis is a major ongoing challenge for anesthetists to reduce anesthetic drug consumption, avoiding intraoperative awareness and prolonged recovery. This paper proposes a novel automated method for accurate assessing of the level of hypnosis with sevoflurane in 17 patients using the electroencephalogram signal. In this method, a set of distinctive features and a hierarchical classification structure based on support vector machine (SVM) methods, is proposed to discriminate the four levels of anesthesia (awake, light, general and deep states). The first stage of the hierarchical SVM structure identifies the awake state by extracting Shannon Permutation Entropy, Detrended Fluctuation Analysis and frequency features. Then deep state is identified by extracting the sample entropy feature; and finally light and general states are identified by extracting the three mentioned features of the first step. The accuracy of the proposed method of analyzing the brain activity during anesthesia is 94.11%; which was better than previous studies and also a commercial monitoring system (Response Entropy Index).

Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network

Electroencephalogram (EEG) signals contain valuable information about the different physiological states of the brain, with a variety of linear and nonlinear features that can be used to investigate brain activity. Monitoring the depth of anesthesia (DoA) with EEG is an ongoing challenge in anesthesia research. In this paper, we propose a novel method based on Long Short-Term Memory (LSTM) and a sparse denoising autoencoder (SDAE) to combine the hybrid features of EEG to monitor the DoA. The EEG signals were preprocessed using filtering, etc., and then more than ten features including sample entropy, permutation entropy, spectra, and alpha-ratio were extracted from the EEG signal. We then integrated the optional features such as permutation entropy and alpha-ratio to extract the essential structure and learn the most efficient temporal model for monitoring the DoA. Compared with using a single feature, the proposed model could accurately estimate the depth of anesthesia with higher prediction probability (P_k). Experimental results evaluated on the datasets demonstrated that our proposed method provided better performance than the methods using permutation entropy, alpha-ratio, LSTM, and other traditional indices.

Analyzing Electroencephalography (EEG) Waves Provides a Reliable Tool to Assess the Depth of Sevoflurane Anesthesia in Pediatric Patients

BACKGROUND Studies have reported that BIS is unreliable in children because its algorithm provides misleading information about the actual depth of anesthesia. Raw EEG analysis provides direct neurophysiologic measurement of cerebral activity. The relationship between age and EEG has rarely been reported, thus the aim of the present study was to compare raw electroencephalography (EEG) among different age groups of surgical patients under general anesthesia with 1.0 MAC sevoflurane. MATERIAL AND METHODS We enrolled 135 patients aged 0-80 years old (ASA physical status I or II) undergoing surgery, who were divided into 6 groups: 1-12 months old (group 1), 1-3 years old (group 2), 3-6 years old (group 3), 6-18 years old (group 4), 18-65 years old (group 5), and 65-80 years old (group 6). Different raw EEG waves (alpha, delta, and theta) were compared for all subjects. RESULTS The BIS values in groups 1 to 6 were 52.2±12.7, 55.0±8.0, 44.5±7.3, 43.8±7.3, 44.2±6.2, and 49.1±6.2 respectively. Compared with groups 1 and 2 (52.2±12.7, 55.0±8.0), BIS values of groups 3, 4, and 5 (44.5±7.3, 43.8±7.3, 44.2±6.2, respectively) were lower (P<0.05). Theta frequency was observed in the 6 groups. The EEG frequencies in groups 1 to 6 were 6.0 (5.5-6.0), 6.0 (5.5-6.0), 6.0 (5.5-6.0), 6.0 (6.0-7.0), 6.3 (6.0-7.0), and 6.0 (5.1-6.0), respectively. Compared with group 6, EEG frequencies in groups 4 and 5 were higher (P<0.05). BIS value was significantly correlated with EEG frequency (R²=0.063, P<0.01). CONCLUSIONS Analyzing raw EEG waves provides more accurate judgement of depth of anesthesia, especially in pediatric cases in which monitors often provide misleading values.

The Art Is to Extubate, Not to Intubate-Swedish Registered Nurse Anesthetists' Experiences of the Process of Extubation After General Anesthesia

PURPOSE

To describe Registered Nurse Anesthetists' (RNA's) experiences of the process of extubation of the endotracheal tube in patients undergoing general anesthesia.

DESIGN

A descriptive qualitative design.

METHODS

This study was conducted in two hospitals with 20 RNAs in total. Data were generated from focus group interviews. Content analysis was used to analyze data.

FINDINGS

The RNAs' experiences were described within four categories and eight subcategories. The category To be a step ahead includes assessment and preparation, and To be on my toes, their ability to recognize patterns and build a connection. To use situation awareness relates to their use of experience and feelings, and To be alone in a critical moment, to feeling alone in the team and protecting the patient.

CONCLUSIONS

The RNAs make decisions when to extubate by combining theoretical knowledge, clinical experience, and intuition with the uniqueness of each patient.

Non-linear Entropy Analysis in EEG to Predict Treatment Response to Repetitive Transcranial Magnetic Stimulation in Depression

Background: Biomarkers that predict clinical outcomes in depression are essential for increasing the precision of treatments and clinical outcomes. The electroencephalogram (EEG) is a non-invasive neurophysiological test that has promise as a biomarker sensitive to treatment effects. The aim of our study was to investigate a novel non-linear index of resting state EEG activity as a predictor of clinical outcome, and compare its predictive capacity to traditional frequency-based indices.

Methods: EEG was recorded from 62 patients with treatment resistant depression (TRD) and 25 healthy comparison (HC) subjects. TRD patients were treated with excitatory repetitive transcranial magnetic stimulation (rTMS) to the dorsolateral prefrontal cortex (DLPFC) for 4 to 6 weeks. EEG signals were first decomposed using the empirical mode decomposition (EMD) method into band-limited intrinsic mode functions (IMFs). Subsequently, Permutation Entropy (PE) was computed from the obtained second IMF to yield an index named PEIMF2. Receiver Operator Characteristic (ROC) curve analysis and ANOVA test were used to evaluate the efficiency of this index (PEIMF2) and were compared to frequency-band based methods.

Results: Responders (RP) to rTMS exhibited an increase in the PEIMF2 index compared to non-responders (NR) at F3, FCz and FC3 sites (p < 0.01). The area under the curve (AUC) for ROC analysis was 0.8 for PEIMF2 index for the FC3 electrode. The PEIMF2 index was superior to ordinary frequency band measures.

Conclusion: Our data show that the PEIMF2 index, yields superior outcome prediction performance compared to traditional frequency band indices. Our findings warrant further investigation of EEG-based biomarkers in depression; specifically entropy indices applied in band-limited EEG components. Registration in ClinicalTrials.Gov; identifiers NCT02800226 and NCT01887782.

Automated detection of driver fatigue based on EEG signals using gradient boosting decision tree model

Driver fatigue is increasingly a contributing factor for traffic accidents, so an effective method to automatically detect driver fatigue is urgently needed. In this study, in order to catch the main characteristics of the EEG signals, four types of entropies (based on the EEG signal of a single channel) were calculated as the feature sets, including sample entropy, fuzzy entropy, approximate entropy and spectral entropy. All feature sets were used as the input of a gradient boosting decision tree (GBDT), a fast and highly accurate boosting ensemble method. The output of GBDT determined whether a driver was in a fatigue state or not based on their EEG signals. Three state-of-the-art classifiers, k-nearest neighbor, support vector machine and neural network were also employed. To assess our method, several experiments including parameter setting and classification performance comparison were performed on 22 subjects. The results indicated that it is possible to use only one EEG channel to detect a driver fatigue state. The average highest recognition rate in this work was up to 94.0%, which could meet the needs of daily applications. Our GBDT-based method may assist in the detection of driver fatigue.

Sample entropy analysis for the estimating depth of anaesthesia through human EEG signal at different levels of unconsciousness during surgeries

Estimating the depth of anaesthesia (DoA) in operations has always been a challenging issue due to the underlying complexity of the brain mechanisms. Electroencephalogram (EEG) signals are undoubtedly the most widely used signals for measuring DoA. In this paper, a novel EEG-based index is proposed to evaluate DoA for 24 patients receiving general anaesthesia with different levels of unconsciousness. Sample Entropy (SampEn) algorithm was utilised in order to acquire the chaotic features of the signals. After calculating the SampEn from the EEG signals, Random Forest was utilised for developing learning regression models with Bispectral index (BIS) as the target. Correlation coefficient, mean absolute error, and area under the curve (AUC) were used to verify the perioperative performance of the proposed method. Validation comparisons with typical nonstationary signal analysis methods (i.e., recurrence analysis and permutation entropy) and regression methods (i.e., neural network and support vector machine) were conducted. To further verify the accuracy and validity of the proposed methodology, the data is divided into four unconsciousness-level groups on the basis of BIS levels. Subsequently, analysis of variance (ANOVA) was applied to the corresponding index (i.e., regression output). Results indicate that the correlation coefficient improved to 0.72 ± 0.09 after filtering and to 0.90 ± 0.05 after regression from the initial values of 0.51 ± 0.17. Similarly, the final mean absolute error dramatically declined to 5.22 ± 2.12. In addition, the ultimate AUC increased to 0.98 ± 0.02, and the ANOVA analysis indicates that each of the four groups of different anaesthetic levels demonstrated significant difference from the nearest levels. Furthermore, the Random Forest output was extensively linear in relation to BIS, thus with better DoA prediction accuracy. In conclusion, the proposed method provides a concrete basis for monitoring patients’ anaesthetic level during surgeries.

Evaluation of prolonged administration of isoflurane on cerebral blood flow and default mode network in macaque monkeys anesthetized with different maintenance doses

OBJECT

Isoflurane is a commonly used volatile anesthetic agent in clinical anesthesia and biomedical research. Prior study suggested the cerebral blood flow (CBF) and default mode network (DMN) could be changed after prolonged administration of isoflurane. The normal maintenance doses of isoflurane may vary from light (∼0.75%) to deep (∼1.5 or 2%) anesthesia. However, it is not clear how the duration effects are affected by the altered doses. The present study is aimed to examine if the duration effects are affected when isoflurane concentration is altered within normal maintenance doses.

MATERIALS AND METHODS

Adult rhesus monkeys (n=5, 8-12 years old, 8-10kg) were anesthetized and maintained at isoflurane levels 0.89±0.03%, 1.05±0.12%, or 1.19±0.08%. CBF and DMN of monkeys were examined using arterial spin-labeling perfusion and resting state functional MRI techniques.

RESULTS

the functional connectivity (FC) in the dominant DMN (posterior cingulate cortex (PCC) to anterior cingulated cortex (ACC) or media prefrontal cortex (MPFC)) decreased substantially and similarly during 4-h administration of isoflurane at any given maintenance dosage. CBF changes varied with isoflurane dosage. At the low dose (∼0.89%), CBF decreased in most brain regions. In contrast, no obvious changes was seen in those regions (except for the subcortex) when higher doses of isoflurane were applied.

CONCLUSION

FC in DMN was reduced substantially during prolonged administration of isoflurane. The FC reduction was not varying significantly with maintenance doses of isoflurane but the duration effect on CBF was dose-dependent. Such duration effects of isoflurane administration on DMN and CBF should be considered in the interpretation of the outcome in related neuroimaging studies of anesthetized subjects.

Measures of entropy and complexity in altered states of consciousness

Quantification of complexity in neurophysiological signals has been studied using different methods, especially those from information or dynamical system theory. These studies have revealed a dependence on different states of consciousness, and in particular that wakefulness is characterized by a greater complexity of brain signals, perhaps due to the necessity for the brain to handle varied sensorimotor information. Thus, these frameworks are very useful in attempts to quantify cognitive states. We set out to analyze different types of signals obtained from scalp electroencephalography (EEG), intracranial EEG and magnetoencephalography recording in subjects during different states of consciousness: resting wakefulness, different sleep stages and epileptic seizures. The signals were analyzed using a statistical (permutation entropy) and a deterministic (permutation Lempel-Ziv complexity) analytical method. The results are presented in complexity versus entropy graphs, showing that the values of entropy and complexity of the signals tend to be greatest when the subjects are in fully alert states, falling in states with loss of awareness or consciousness. These findings were robust for all three types of recordings. We propose that the investigation of the structure of cognition using the frameworks of complexity will reveal mechanistic aspects of brain dynamics associated not only with altered states of consciousness but also with normal and pathological conditions.

Reprint of "A new approach to analyze data from EEG-based concealed face recognition system"

The purpose of this study is to extend a feature set with non-linear features to improve classification rate of guilty and innocent subjects. Non-linear features can provide extra information about phase space. The Event-Related Potential (ERP) signals were recorded from 49 subjects who participated in concealed face recognition test. For feature extraction, at first, several morphological characteristics, frequency bands, and wavelet coefficients (we call them basic-features) are extracted from each single-trial ERP. Recurrence Quantification Analysis (RQA) measures are then computed as non-linear features from each single-trial. We apply Genetic Algorithm (GA) to select the best feature set and this feature set is used for classification of data using Linear Discriminant Analysis (LDA) classifier. Next, we use a new approach to improve classification results based on introducing an adaptive-threshold. Results indicate that our method is able to correctly detect 91.83% of subjects (45 correct detection of 49 subjects) using combination of basic and non-linear features, that is higher than 87.75% for basic and 79.59% for non-linear features. This shows that combination of non-linear and basic- features could improve classification rate.

An EEG-based machine learning method to screen alcohol use disorder

Screening alcohol use disorder (AUD) patients has been challenging due to the subjectivity involved in the process. Hence, robust and objective methods are needed to automate the screening of AUD patients. In this paper, a machine learning method is proposed that utilized resting-state electroencephalography (EEG)-derived features as input data to classify the AUD patients and healthy controls and to perform automatic screening of AUD patients. In this context, the EEG data were recorded during 5 min of eyes closed and 5 min of eyes open conditions. For this purpose, 30 AUD patients and 15 aged-matched healthy controls were recruited. After preprocessing the EEG data, EEG features such as inter-hemispheric coherences and spectral power for EEG delta, theta, alpha, beta and gamma bands were computed involving 19 scalp locations. The selection of most discriminant features was performed with a rank-based feature selection method assigning a weight value to each feature according to a criterion, i.e., receiver operating characteristics curve. For example, a feature with large weight was considered more relevant to the target labels than a feature with less weight. Therefore, a reduced set of most discriminant features was identified and further be utilized during classification of AUD patients and healthy controls. As results, the inter-hemispheric coherences between the brain regions were found significantly different between the study groups and provided high classification efficiency (Accuracy = 80.8, sensitivity = 82.5, and specificity = 80, F-Measure = 0.78). In addition, the power computed in different EEG bands were found significant and provided an overall classification efficiency as (Accuracy = 86.6, sensitivity = 95, specificity = 82.5, and F-Measure = 0.88). Further, the integration of these EEG feature resulted into even higher results (Accuracy = 89.3 %, sensitivity = 88.5 %, specificity = 91 %, and F-Measure = 0.90). Based on the results, it is concluded that the EEG data (integration of the theta, beta, and gamma power and inter-hemispheric coherence) could be utilized as objective markers to screen the AUD patients and healthy controls.

A new approach to analyze data from EEG-based concealed face recognition system

The purpose of this study is to extend a feature set with non-linear features to improve classification rate of guilty and innocent subjects. Non-linear features can provide extra information about phase space. The Event-Related Potential (ERP) signals were recorded from 49 subjects who participated in concealed face recognition test. For feature extraction, at first, several morphological characteristics, frequency bands, and wavelet coefficients (we call them basic-features) are extracted from each single-trial ERP. Recurrence Quantification Analysis (RQA) measures are then computed as non-linear features from each single-trial. We apply Genetic Algorithm (GA) to select the best feature set and this feature set is used for classification of data using Linear Discriminant Analysis (LDA) classifier. Next, we use a new approach to improve classification results based on introducing an adaptive-threshold. Results indicate that our method is able to correctly detect 91.83% of subjects (45 correct detection of 49 subjects) using combination of basic and non-linear features, that is higher than 87.75% for basic and 79.59% for non-linear features. This shows that combination of non-linear and basic- features could improve classification rate.

Low-Complexity Discriminative Feature Selection From EEG Before and After Short-Term Memory Task

A reliable and unobtrusive quantification of changes in cortical activity during short-term memory task can be used to evaluate the efficacy of interfaces and to provide real-time user-state information. In this article, we investigate changes in electroencephalogram signals in short-term memory with respect to the baseline activity. The electroencephalogram signals have been analyzed using 9 linear and nonlinear/dynamic measures. We applied statistical Wilcoxon examination and Davis-Bouldian criterion to select optimal discriminative features. The results show that among the features, the permutation entropy significantly increased in frontal lobe and the occipital second lower alpha band activity decreased during memory task. These 2 features reflect the same mental task; however, their correlation with memory task varies in different intervals. In conclusion, it is suggested that the combination of the 2 features would improve the performance of memory based neurofeedback systems.

Mechanisms underlying brain monitoring during anesthesia: limitations, possible improvements, and perspectives

Currently, anesthesiologists use clinical parameters to directly measure the depth of anesthesia (DoA). This clinical standard of monitoring is often combined with brain monitoring for better assessment of the hypnotic component of anesthesia. Brain monitoring devices provide indices allowing for an immediate assessment of the impact of anesthetics on consciousness. However, questions remain regarding the mechanisms underpinning these indices of hypnosis. By briefly describing current knowledge of the brain's electrical activity during general anesthesia, as well as the operating principles of DoA monitors, the aim of this work is to simplify our understanding of the mathematical processes that allow for translation of complex patterns of brain electrical activity into dimensionless indices. This is a challenging task because mathematical concepts appear remote from clinical practice. Moreover, most DoA algorithms are proprietary algorithms and the difficulty of exploring the inner workings of mathematical models represents an obstacle to accurate simplification. The limitations of current DoA monitors — and the possibility for improvement — as well as perspectives on brain monitoring derived from recent research on corticocortical connectivity and communication are also discussed.

Aesthetic preference recognition of 3D shapes using EEG

Recognition and identification of aesthetic preference is indispensable in industrial design. Humans tend to pursue products with aesthetic values and make buying decisions based on their aesthetic preferences. The existence of neuromarketing is to understand consumer responses toward marketing stimuli by using imaging techniques and recognition of physiological parameters. Numerous studies have been done to understand the relationship between human, art and aesthetics. In this paper, we present a novel preference-based measurement of user aesthetics using electroencephalogram (EEG) signals for virtual 3D shapes with motion. The 3D shapes are designed to appear like bracelets, which is generated by using the Gielis superformula. EEG signals were collected by using a medical grade device, the B-Alert X10 from advance brain monitoring, with a sampling frequency of 256 Hz and resolution of 16 bits. The signals obtained when viewing 3D bracelet shapes were decomposed into alpha, beta, theta, gamma and delta rhythm by using time-frequency analysis, then classified into two classes, namely like and dislike by using support vector machines and K-nearest neighbors (KNN) classifiers respectively. Classification accuracy of up to 80 % was obtained by using KNN with the alpha, theta and delta rhythms as the features extracted from frontal channels, Fz, F3 and F4 to classify two classes, like and dislike.

Characterizing Awake and Anesthetized States Using a Dimensionality Reduction Method

Distinguishing between awake and anesthetized states is one of the important problems in surgery. Vital signals contain valuable information that can be used in prediction of different levels of anesthesia. Some monitors based on electroencephalogram (EEG) such as the Bispectral (BIS) index have been proposed in recent years. This study proposes a new method for characterizing between awake and anesthetized states. We validated our method by obtaining data from 25 patients during the cardiac surgery that requires cardiopulmonary bypass. At first, some linear and non-linear features are extracted from EEG signals. Then a method called "LLE"(Locally Linear Embedding) is used to map high-dimensional features in a three-dimensional output space. Finally, low dimensional data are used as an input to a quadratic discriminant analyzer (QDA). The experimental results indicate that an overall accuracy of 88.4 % can be obtained using this method for classifying the EEG signal into conscious and unconscious states for all patients. Considering the reliability of this method, we can develop a new EEG monitoring system that could assist the anesthesiologists to estimate the depth of anesthesia accurately.

The discriminatory value of cardiorespiratory interactions in distinguishing awake from anaesthetised states: a randomised observational study

Depth of anaesthesia monitors usually analyse cerebral function with or without other physiological signals; non‐invasive monitoring of the measured cardiorespiratory signals alone would offer a simple, practical alternative. We aimed to investigate whether such signals, analysed with novel, non‐linear dynamic methods, would distinguish between the awake and anaesthetised states. We recorded ECG, respiration, skin temperature, pulse and skin conductivity before and during general anaesthesia in 27 subjects in good cardiovascular health, randomly allocated to receive propofol or sevoflurane. Mean values, variability and dynamic interactions were determined. Respiratory rate (p = 0.0002), skin conductivity (p = 0.03) and skin temperature (p = 0.00006) changed with sevoflurane, and skin temperature (p = 0.0005) with propofol. Pulse transit time increased by 17% with sevoflurane (p = 0.02) and 11% with propofol (p = 0.007). Sevoflurane reduced the wavelet energy of heart (p = 0.0004) and respiratory (p = 0.02) rate variability at all frequencies, whereas propofol decreased only the heart rate variability below 0.021 Hz (p < 0.05). The phase coherence was reduced by both agents at frequencies below 0.145 Hz (p < 0.05), whereas the cardiorespiratory synchronisation time was increased (p < 0.05). A classification analysis based on an optimal set of discriminatory parameters distinguished with 95% success between the awake and anaesthetised states. We suggest that these results can contribute to the design of new monitors of anaesthetic depth based on cardiovascular signals alone.

Power spectral density and coherence analysis of Alzheimer's EEG

In this paper, we investigate the abnormalities of electroencephalograph (EEG) signals in the Alzheimer's disease (AD) by analyzing 16-scalp electrodes EEG signals and make a comparison with the normal controls. The power spectral density (PSD) which represents the power distribution of EEG series in the frequency domain is used to evaluate the abnormalities of AD brain. Spectrum analysis based on autoregressive Burg method shows that the relative PSD of AD group is increased in the theta frequency band while significantly reduced in the alpha2 frequency bands, particularly in parietal, temporal, and occipital areas. Furthermore, the coherence of two EEG series among different electrodes is analyzed in the alpha2 frequency band. It is demonstrated that the pair-wise coherence between different brain areas in AD group are remarkably decreased. Interestingly, this decrease of pair-wise electrodes is much more significant in inter-hemispheric areas than that in intra-hemispheric areas. Moreover, the linear cortico-cortical functional connectivity can be extracted based on coherence matrix, from which it is shown that the functional connections are obviously decreased, the same variation trend as relative PSD. In addition, we combine both features of the relative PSD and the normalized degree of functional network to discriminate AD patients from the normal controls by applying a support vector machine model in the alpha2 frequency band. It is indicated that the two groups can be clearly classified by the combined feature. Importantly, the accuracy of the classification is higher than that of any one feature. The obtained results show that analysis of PSD and coherence-based functional network can be taken as a potential comprehensive measure to distinguish AD patients from the normal, which may benefit our understanding of the disease.