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

Thalamic burst and tonic firing selectively indicate patients' consciousness level and recovery

Patients with disorders of consciousness suffer from severe impairments in arousal and awareness alongside anomalous brain connections and aberrant neuronal activities. The thalamus, a crucial hub in the brain connectome, has been empirically inferred to maintain consciousness and wakefulness. Here, we investigated thalamic spiking, brain connectivity, consciousness states, and recovery outcomes following deep brain stimulation in 29 patients. Our study reveals that thalamic neuronal activity serves as a marker of consciousness state. Patients diagnosed with vegetative state/unresponsive wakefulness syndrome exhibited less-active neurons, with longer and more variable burst discharges, than those in a minimally conscious state. Furthermore, neuronal profiles in the intralaminar thalamus, the direct stimulation site, predicted whether electrostimulation here improved recovery. Stronger tonic firing was correlated with enhanced thalamocortical connectivity and better recovery outcomes in patients. These findings suggest that thalamic spiking signatures, including single-neuron burst discharge and tonic firing, selectively indicate the representation and alteration of consciousness.

Accurate Machine Learning-based Monitoring of Anesthesia Depth with EEG Recording

General anesthesia, pivotal for surgical procedures, requires precise depth monitoring to mitigate risks ranging from intraoperative awareness to postoperative cognitive impairments. Traditional assessment methods, relying on physiological indicators or behavioral responses, fall short of accurately capturing the nuanced states of unconsciousness. This study introduces a machine learning-based approach to decode anesthesia depth, leveraging EEG data across different anesthesia states induced by propofol and esketamine in rats. Our findings demonstrate the model's robust predictive accuracy, underscored by a novel intra-subject dataset partitioning and a 5-fold cross-validation method. The research diverges from conventional monitoring by utilizing anesthetic infusion rates as objective indicators of anesthesia states, highlighting distinct EEG patterns and enhancing prediction accuracy. Moreover, the model's ability to generalize across individuals suggests its potential for broad clinical application, distinguishing between anesthetic agents and their depths. Despite relying on rat EEG data, which poses questions about real-world applicability, our approach marks a significant advance in anesthesia monitoring.

Predicting Treatment Response of Repetitive Transcranial Magnetic Stimulation in Major Depressive Disorder Using an Explainable Machine Learning Model Based on Electroencephalography and Clinical Features

Major depressive disorder (MDD) is highly heterogeneous in response to repetitive transcranial magnetic stimulation (rTMS), and identifying predictive biomarkers is essential for personalized treatment. However, most prior research studies have used either electroencephalography (EEG) or clinical features, lack interpretability, or have small sample sizes. This study included 74 patients with MDD who responded (responders) and 43 patients with MDD who did not respond (nonresponders) to rTMS. Eight baseline EEG metrics and clinical features were sent to 7 machine learning models to classify responders and nonresponders. Shapley additive explanations (SHAP) was used to interpret feature contributions. Combining phase locking value and clinical features with support vector machine achieved optimal classification performance (accuracy = 97.33%). SHAP revealed that delta and beta band functional connectivity (F3-P7, F3-P4, P3-P8, T7-Cz) significantly influenced predictions and differed between groups. This study developed an explainable predictive framework to predict rTMS response in MDD, enhancing the accuracy of rTMS response prediction and supporting personalized treatment in MDD.

Unveiling neural activity changes in mild cognitive impairment using microstate analysis and machine learning

BACKGROUND

Mild cognitive impairment (MCI) is recognized as a condition that may increase the risk of developing Alzheimer's disease (AD). Understanding the neural correlates of MCI is crucial for elucidating its pathophysiology and developing effective interventions. Electroencephalogram (EEG) microstates, reflecting brain activity changes, have shown promise in MCI research. However, current approaches often lack comprehensive characterization of the complex neural dynamics associated with MCI.

OBJECTIVE

This study aims to investigate neurophysiological changes associated with MCI using a comprehensive set of microstate features, including traditional temporal features and entropy measures.

METHODS

Resting-state EEG data were collected from 69 MCI patients and healthy controls (HC). Microstate analysis was performed to extract conventional features (duration, coverage) and entropy measures. Statistical analysis, principal component analysis (PCA), and machine learning (ML) techniques were employed to evaluate neurophysiological patterns associated with MCI.

RESULTS

MCI displayed altered microstate dynamics, with significantly longer coverage and duration in Microstate C but shorter in Microstates A, B, and D compared to HCs. PCA revealed two principal components, primarily composed of microstate dynamics and entropy measures, explaining over 75% of the variance. ML models achieved high accuracy in distinguishing MCI patterns.

CONCLUSIONS

Our comprehensive analysis of EEG microstate features provides new insights into neurophysiological changes associated with MCI, highlighting the potential of EEG microstates for investigating complex neural changes in cognitive decline.

Emergence of multiple spontaneous coherent subnetworks from a single configuration of human connectome coupled oscillators model

Multi-state metastability in neuroimaging signals reflects the brain's flexibility to transition between network configurations in response to changing environments or tasks. We modeled these dynamics with a Kuramoto network of 90 nodes oscillating at an intrinsic frequency of 40 Hz, interconnected using human brain structural connectivity strengths and delays. We simulated this model for 30 min to generate multi-state metastability. We identified global coupling and delay parameters that maximize spectral entropy, a proxy for multi-state metastability. At this operational point, multiple frequency-specific coherent sub-networks spontaneously emerge across oscillatory modes, persisting for periods between 140 and 4300 ms, reflecting flexible and sustained dynamic states. The topography of these sub-networks aligns with empirical resting-state neuroimaging data. Additionally, periodic components of the EEG spectra from young healthy participants correlate with maximal multi-state metastability, while dynamics away from this point correlate with sleep and anesthesia spectra. Our findings suggest that multi-state metastable functional dynamics observed in empirical data emerge from specific interactions of structural topography and connection delays, providing a platform to study mechanisms underlying flexible dynamics of cognition.

Abnormal nonlinear features of EEG microstate sequence in obsessive-compulsive disorder

BACKGROUND

At present, only a few studies have explored electroencephalography (EEG) microstates of patients with obsessive-compulsive disorder (OCD) and the results are inconsistent. Additionally, the nonlinear features of EEG microstate sequences contain rich information about the brain, yet how the nonlinear features of EEG microstate sequences abnormally change in patients with OCD is still unknown.

METHODS

Resting-state EEG data were collected from 48 OCD patients and macheted 48 healthy controls (HC). Subsequently, EEG microstate analysis was used to extract the microstate temporal parameters (duration, occurrence, coverage) and nonlinear features of EEG microstate sequences (sample entropy, Lempel-Ziv complexity, Hurst index). Finally, the temporal parameters and nonlinear features of EEG microstate sequences were sent to three kinds of machine learning models to classify OCD patients.

RESULTS

Both groups obtained four typical EEG microstate topographies. The duration of microstates A, B, and C in OCD patients decreased significantly, while the occurrence of microstate D increased significantly compared to HC. Sample entropy and Lempel-Ziv complexity of microstate sequences in OCD patients increased significantly, while Hurst index decreased significantly compared to HC. The classification accuracy using the nonlinear features of microstate sequences reached up to 85%, significantly higher than that based on microstate temporal parameter models.

CONCLUSION

This study provides supplementary findings on EEG microstates in OCD patients with a larger sample size. We found that the nonlinear features of EEG microstate sequences in OCD patients can serve as potential electrophysiological biomarkers for distinguishing OCD patients.

EEG microstate in people with different degrees of fear of heights during virtual high-altitude exposure

Previous neuroimaging studies based on electroencephalography (EEG) microstate analysis have identified abnormal neural electric activity in patients with psychiatric diseases. However, the microstate information in individuals with different degrees of fear of heights (FoH) remains unknown so far. The aim of the study was therefore to explore the changes of EEG microstate characteristics in different FoH individuals when exposed to high-altitude stimulated by virtual reality (VR). First, acrophobia questionnaire (AQ) before the experiment and 32-channel EEG signals under the virtual high-altitude exposure were collected from 69 subjects. Second, each subject was divided into one of three levels of FoH including no-FoH, mild or moderate FoH (m-FoH) and severe FoH (s-FoH) groups according to their AQ scores. Third, using microstate analysis, we transformed EEG data into sequences of characteristic topographic maps and computed EEG microstate features including microstate basic parameters, microstate sequences complexity and microstate energy. Finally, the extracted features as inputs were sent to train and test an support vector machine (SVM) for classifying different FoH groups. The results demonstrated that five types of microstates (labeled as A, B, C, D and F) were identified across all subjects, of which microstates A-D resembled the four typical microstate classes and microstate F was a non-canonical microstate. Significantly decreased occurrence, coverage and duration of microstate F and transition probabilities from other microstates to microstate F in m-FoH and s-FoH groups were observed compared to no-FoH group. It was also demonstrated that both m-FoH and s-FoH groups showed a notable reduction in sample entropy and Lempel-Ziv complexity. Moreover, energies of microstate D for m-FoH group and microstate B for s-FoH group in right parietal, parietooccipital and occipital regions exhibited prominent decreases as comparison to people without FoH. But, no significant differences were found between m-FoH and s-FoH groups. Additionally, the results indicated that AQ-anxiety scores were negatively correlated with microstate basic metrics as well as microstate energy. For classification, the performance of SVM reached a relatively high accuracy of 89 % for distinguishing no-FoH from m-FoH. In summary, the findings highlight the alterations of EEG microstates in people with fear of heights induced by virtual high-altitude, reflecting potentially underlying abnormalities in the allocation of neural assemblies. Therefore, the combination of EEG microstate analysis and VR may be a potential valuable approach for the diagnosis of fear of heights.

Utilizing Slope Entropy as an Effective Index for Wearable EEG-Based Depth of Anesthesia Monitoring

Based on prior research indicating a decrease in the spectral slope of electroencephalogram (EEG) during anesthesia induction and an increase during recovery, we propose Slope Entropy (SlopEn), which uniquely emphasizes variations in signal slope, as a new index for monitoring the depth of anesthesia (DoA). The performance of SlopEn is investigated on just a single frontal EEG channel and is compared against other well-known entropy metrics utilized in the field. After filtering the EEG signal, four types of entropy, including SlopEn, are derived from all EEG sub-bands and separately inputted to a regressor for estimating DoA index values. Comparing the results obtained using SlopEn with those from the Sample entropy demonstrates the superiority of the former, achieving a higher correlation coefficient (0.75 vs. 0.63) and a lower median absolute error (4.2 vs. 6.2) between the estimated and reference DoA index values. These findings establish that the SlopEn has the potential to become a valuable index for DoA monitoring using single frontal channel EEG systems.

MSE-VGG: A Novel Deep Learning Approach Based on EEG for Rapid Ischemic Stroke Detection

Ischemic stroke is a type of brain dysfunction caused by pathological changes in the blood vessels of the brain which leads to brain tissue ischemia and hypoxia and ultimately results in cell necrosis. Without timely and effective treatment in the early time window, ischemic stroke can lead to long-term disability and even death. Therefore, rapid detection is crucial in patients with ischemic stroke. In this study, we developed a deep learning model based on fusion features extracted from electroencephalography (EEG) signals for the fast detection of ischemic stroke. Specifically, we recruited 20 ischemic stroke patients who underwent EEG examination during the acute phase of stroke and collected EEG signals from 19 adults with no history of stroke as a control group. Afterwards, we constructed correlation-weighted Phase Lag Index (cwPLI), a novel feature, to explore the synchronization information and functional connectivity between EEG channels. Moreover, the spatio-temporal information from functional connectivity and the nonlinear information from complexity were fused by combining the cwPLI matrix and Sample Entropy (SaEn) together to further improve the discriminative ability of the model. Finally, the novel MSE-VGG network was employed as a classifier to distinguish ischemic stroke from non-ischemic stroke data. Five-fold cross-validation experiments demonstrated that the proposed model possesses excellent performance, with accuracy, sensitivity, and specificity reaching 90.17%, 89.86%, and 90.44%, respectively. Experiments on time consumption verified that the proposed method is superior to other state-of-the-art examinations. This study contributes to the advancement of the rapid detection of ischemic stroke, shedding light on the untapped potential of EEG and demonstrating the efficacy of deep learning in ischemic stroke identification.

Artificial Intelligence in Perioperative Planning and Management of Liver Resection

Artificial intelligence (AI) is a speciality within computer science that deals with creating systems that can replicate the intelligence of a human mind and has problem-solving abilities. AI includes a diverse array of techniques and approaches such as machine learning, neural networks, natural language processing, robotics, and expert systems. An electronic literature search was conducted using the databases of "PubMed" and "Google Scholar". The period for the search was from 2000 to June 2023. The search terms included "artificial intelligence", "machine learning", "liver cancers", "liver tumors", "hepatectomy", "perioperative" and their synonyms in various combinations. The search also included all MeSH terms. The extracted articles were further reviewed in a step-wise manner for identification of relevant studies. A total of 148 articles were identified after the initial literature search. Initial review included screening of article titles for relevance and identifying duplicates. Finally, 65 articles were reviewed for this review article. The future of AI in liver cancer planning and management holds immense promise. AI-driven advancements will increasingly enable precise tumour detection, location, and characterisation through enhanced image analysis. ML algorithms will predict patient-specific treatment responses and complications, allowing for tailored therapies. Surgical robots and AI-guided procedures will enhance the precision of liver resections, reducing risks and improving outcomes. AI will also streamline patient monitoring, better hemodynamic management, enabling early detection of recurrence or complications. Moreover, AI will facilitate data-driven research, accelerating the development of novel treatments and therapies. Ultimately, AI's integration will revolutionise liver cancer care, offering personalised, efficient and effective solutions, improving patients' quality of life and survival rates.

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

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.

A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History

In the target-controlled infusion (TCI) of propofol and remifentanil intravenous anesthesia, accurate prediction of the depth of anesthesia (DOA) is very challenging. Patients with different physiological characteristics have inconsistent pharmacodynamic responses during different stages of anesthesia. For example, in TCI, older adults transition smoothly from the induction period to the maintenance period, while younger adults are more prone to anesthetic awareness, resulting in different DOA data distributions among patients. To address these problems, a deep learning framework that incorporates domain adaptation and knowledge distillation and uses propofol and remifentanil doses at historical moments to continuously predict the bispectral index (BIS) is proposed in this paper. Specifically, a modified adaptive recurrent neural network (AdaRNN) is adopted to address data distribution differences among patients. Moreover, a knowledge distillation pipeline is developed to train the prediction network by enabling it to learn intermediate feature representations of the teacher network. The experimental results show that our method exhibits better performance than existing approaches during all anesthetic phases in the TCI of propofol and remifentanil intravenous anesthesia. In particular, our method outperforms some state-of-the-art methods in terms of root mean square error and mean absolute error by 1 and 0.8, respectively, in the internal dataset as well as in the publicly available dataset.

Development of a Bispectral index score prediction model based on an interpretable deep learning algorithm

BACKGROUND

Proper maintenance of hypnosis is crucial for ensuring the safety of patients undergoing surgery. Accordingly, indicators, such as the Bispectral index (BIS), have been developed to monitor hypnotic levels. However, the black-box nature of the algorithm coupled with the hardware makes it challenging to understand the underlying mechanisms of the algorithms and integrate them with other monitoring systems, thereby limiting their use.

OBJECTIVE

We propose an interpretable deep learning model that forecasts BIS values 25 s in advance using 30 s electroencephalogram (EEG) data.

MATERIAL AND METHODS

The proposed model utilized EEG data as a predictor, which is then decomposed into amplitude and phase components using fast Fourier Transform. An attention mechanism was applied to interpret the importance of these components in predicting BIS. The predictability of the model was evaluated on both regression and binary classification tasks, where the former involved predicting a continuous BIS value, and the latter involved classifying a dichotomous status at a BIS value of 60. To evaluate the interpretability of the model, we analyzed the attention values expressed in the amplitude and phase components according to five ranges of BIS values. The proposed model was trained and evaluated using datasets collected from two separate medical institutions.

RESULTS AND CONCLUSION

The proposed model achieved excellent performance on both the internal and external validation datasets. The model achieved a root-mean-square error of 6.614 for the regression task, and an area under the receiver operating characteristic curve of 0.937 for the binary classification task. Interpretability analysis provided insight into the relationship between EEG frequency components and BIS values. Specifically, the attention mechanism revealed that higher BIS values were associated with increased amplitude attention values in high-frequency bands and increased phase attention values in various frequency bands. This finding is expected to facilitate a more profound understanding of the BIS prediction mechanism, thereby contributing to the advancement of anesthesia technologies.

Estimating the Depth of Anesthesia from EEG Signals Based on a Deep Residual Shrinkage Network

The reliable monitoring of the depth of anesthesia (DoA) is essential to control the anesthesia procedure. Electroencephalography (EEG) has been widely used to estimate DoA since EEG could reflect the effect of anesthetic drugs on the central nervous system (CNS). In this study, we propose that a deep learning model consisting mainly of a deep residual shrinkage network (DRSN) and a 1 × 1 convolution network could estimate DoA in terms of patient state index (PSI) values. First, we preprocessed the four raw channels of EEG signals to remove electrical noise and other physiological signals. The proposed model then takes the preprocessed EEG signals as inputs to predict PSI values. Then we extracted 14 features from the preprocessed EEG signals and implemented three conventional feature-based models as comparisons. A dataset of 18 patients was used to evaluate the models' performances. The results of the five-fold cross-validation show that there is a relatively high similarity between the ground-truth PSI values and the predicted PSI values of our proposed model, which outperforms the conventional models, and further, that the Spearman's rank correlation coefficient is 0.9344. In addition, an ablation experiment was conducted to demonstrate the effectiveness of the soft-thresholding module for EEG-signal processing, and a cross-subject validation was implemented to illustrate the robustness of the proposed method. In summary, the procedure is not merely feasible for estimating DoA by mimicking PSI values but also inspired us to develop a precise DoA-estimation system with more convincing assessments of anesthetization levels.

Entropy Information of Pulse Dynamics in Three Stages of Pregnancy

The aim of the present study is to use entropy to explore the change of pulse generated by normal pregnant women with gestational. Firstly, the subjects were divided into early (E), middle (M), and late (L) three stages according to gestational age. Then, pulse signals of the Chi position of 90 pregnant women at different gestational ages were collected. Secondly, the four entropies, namely fuzzy entropy (FuEn), approximate entropy (ApEn), sample entropy (SamEn), and permutation entropy (PerEn), were applied to the analysis of the long-term pulse changes of the pregnancy. Finally, the related information about pulse in different stages of pregnancy is given by the analysis of four kinds of entropy. Furthermore, the statistical tests are conducted for further comparison, and the descriptive statistics and the results are presented. In addition, boxplots are employed to show the distribution of four entropies of pregnancy. This work has studied the changes in pulse during pregnancy from quantitative and qualitative aspects. Our results show that entropy improves the diagnostic value of pulse analysis during pregnancy and could be applied to facilitate noninvasive diagnosis of pregnant women's physiological signals in the future.

Complexity of Brain Dynamics as a Correlate of Consciousness in Anaesthetized Monkeys

The use of anaesthesia is a fundamental tool in the investigation of consciousness. Anesthesia procedures allow to investigate different states of consciousness from sedation to deep anesthesia within controlled scenarios. In this study we use information quantifiers to measure the complexity of electrocorticogram recordings in monkeys. We apply these metrics to compare different stages of general anesthesia for evaluating consciousness in several anesthesia protocols. We find that the complexity of brain activity can be used as a correlate of consciousness. For two of the anaesthetics used, propofol and medetomidine, we find that the anaesthetised state is accompanied by a reduction in the complexity of brain activity. On the other hand we observe that use of ketamine produces an increase in complexity measurements. We relate this observation with increase activity within certain brain regions associated with the ketamine used doses. Our measurements indicate that complexity of brain activity is a good indicator for a general evaluation of different levels of consciousness awareness, both in anesthetized and non anesthetizes states.

Nonlinear Analyses Distinguish Load Carriage Dynamics in Walking and Standing: A Systematic Review

Load carriage experiments are typically performed from a linear perspective that assumes that movement variability is equivalent to error or noise in the neuromuscular system. A complimentary, nonlinear perspective that treats variability as the object of study has generated important results in movement science outside load carriage settings. To date, no systematic review has yet been conducted to understand how load carriage dynamics change from a nonlinear perspective. The goal of this systematic review is to fill that need. Relevant literature was extracted and reviewed for general trends involving nonlinear perspectives on load carriage. Nonlinear analyses that were used in the reviewed studies included sample, multiscale, and approximate entropy; the Lyapunov exponent; fractal analysis; and relative phase. In general, nonlinear tools successfully distinguish between unloaded and loaded conditions in standing and walking, although not in a consistent manner. The Lyapunov exponent and entropy were the most used nonlinear methods. Two noteworthy findings are that entropy in quiet standing studies tends to decrease, whereas the Lyapunov exponent in walking studies tends to increase, both due to added load. Thus, nonlinear analyses reveal altered load carriage dynamics, demonstrating promise in applying a nonlinear perspective to load carriage while also underscoring the need for more research.

On the Spatial Distribution of Temporal Complexity in Resting State and Task Functional MRI

Measuring the temporal complexity of functional MRI (fMRI) time series is one approach to assess how brain activity changes over time. In fact, hemodynamic response of the brain is known to exhibit critical behaviour at the edge between order and disorder. In this study, we aimed to revisit the spatial distribution of temporal complexity in resting state and task fMRI of 100 unrelated subjects from the Human Connectome Project (HCP). First, we compared two common choices of complexity measures, i.e., Hurst exponent and multiscale entropy, and observed a high spatial similarity between them. Second, we considered four tasks in the HCP dataset (Language, Motor, Social, and Working Memory) and found high task-specific complexity, even when the task design was regressed out. For the significance thresholding of brain complexity maps, we used a statistical framework based on graph signal processing that incorporates the structural connectome to develop the null distributions of fMRI complexity. The results suggest that the frontoparietal, dorsal attention, visual, and default mode networks represent stronger complex behaviour than the rest of the brain, irrespective of the task engagement. In sum, the findings support the hypothesis of fMRI temporal complexity as a marker of cognition.

Real-Time Depth of Anaesthesia Assessment Based on Hybrid Statistical Features of EEG

This paper proposed a new depth of anaesthesia (DoA) index for the real-time assessment of DoA using electroencephalography (EEG). In the proposed new DoA index, a wavelet transform threshold was applied to denoise raw EEG signals, and five features were extracted to construct classification models. Then, the Gaussian process regression model was employed for real-time assessment of anaesthesia states. The proposed real-time DoA index was implemented using a sliding window technique and validated using clinical EEG data recorded with the most popular commercial DoA product Bispectral Index monitor (BIS). The results are evaluated using the correlation coefficients and Bland-Altman methods. The outcomes show that the highest and the average correlation coefficients are 0.840 and 0.814, respectively, in the testing dataset. Meanwhile, the scatter plot of Bland-Altman shows that the agreement between BIS and the proposed index is 94.91%. In contrast, the proposed index is free from the electromyography (EMG) effect and surpasses the BIS performance when the signal quality indicator (SQI) is lower than 15, as the proposed index can display high correlation and reliable assessment results compared with clinic observations.

EEG microstate in first-episode drug-naive adolescents with depression

BACKGROUND

A growing number of studies have revealed significant abnormalities in EEG microstate in patients with depression, but these findings may be affected by medication. Therefore, how the EEG microstates abnormally change in patients with depression in the early stage and without the influence of medication has not been investigated so far.

METHODS

Resting-state EEG data and Hamilton Depression Rating Scale (HDRS) were collected from 34 first-episode drug-naïve adolescent with depression and 34 matched healthy controls. EEG microstate analysis was applied and nonlinear characteristics of EEG microstate sequences were studied by sample entropy and Lempel-Ziv complexity (LZC). The microstate temporal parameters and complexity were tried to train a SVM for classification of patients with depression.

RESULTS

Four typical EEG microstate topographies were obtained in both groups, but microstate C topography was significantly abnormal in depression patients. The duration of microstate B, C, D and the occurrence and coverage of microstate B significantly increased, the occurrence and coverage of microstate A, C reduced significantly in depression group. Sample entropy and LZC in the depression group were abnormally increased and were negatively correlated with HDRS. When the combination of EEG microstate temporal parameters and complexity of microstate sequence was used to classify patients with depression from healthy controls, a classification accuracy of 90.9% was obtained.

CONCLUSION

Abnormal EEG microstate has appeared in early depression, reflecting an underlying abnormality in configuring neural resources and transitions between distinct brain network states. EEG microstate can be used as a neurophysiological biomarker for early auxiliary diagnosis of depression.

A novel empirical wavelet SODP and spectral entropy based index for assessing the depth of anaesthesia

The requirement for anaesthesia during modern surgical procedures is unquestionable to ensure a safe experience for patients with successful recovery. Assessment of the depth of anaesthesia (DoA) is an important and ongoing field of research to ensure patient stability during and post-surgery. This research addresses the limitations of current DoA indexes by developing a new index based on electroencephalography (EEG) signal analysis. Empirical wavelet transformation (EWT) methods are employed to extract wavelet coefficients before statistical analysis. The features Spectral Entropy and Second Order Difference Plot are extracted from the wavelet coefficients. These features are used to train a new index, SSE_DoA, utilising a Support Vector Machine (SVM) with a linear kernel function. The new index accurately assesses the DoA to illustrate the transition between different anaesthetic stages. Testing was undertaken with nine patients and an additional four patients with low signal quality. Across the nine patients we tested, an average correlation of 0.834 was observed with the Bispectral (BIS) index. The analysis of the DoA stage transition exhibited a Choen's Kappa of 0.809, indicative of a high agreement.

Multiscale depth of anaesthesia prediction for surgery using frontal cortex electroencephalography

Hypnotic and sedative anaesthetic agents are employed during multiple medical interventions to prevent patient awareness. Careful titration of agent dosing is required to avoid negative side effects; the accuracy thereof may be improved by Depth of Anaesthesia Monitoring. This work investigates the potential of a patient specific depth monitoring prediction using electroencephalography recorded neural oscillation from the frontal lobe of 10 patients during sedation, where a comparison of the prediction accuracy was made across five different approaches to post‐processing; Noise Assisted‐Empirical Mode Decomposition, the Raw Signal, Linear Series Decomposition Learner, Deep Wavelet Scattering and Deep Learning features. These methods towards anaesthesia depth prediction were investigated using the Bispectral Index as ground truth, where it was seen that the Raw Signal, enhanced feature set and a low complexity classification model (Linear Discriminant Analysis) provided the best classification accuracy, in the region of 85.65 % ±10.23 % across the 10 subjects. Subsequent work in this area would now build on these results and validate the best performing methods on a wider cohort of patients, investigate means of continuous DoA estimation using regressions, and also feature optimisation exercises in order to further streamline and reduce the computation complexity of the designed model.

Transient abnormal signal acquisition system based on approximate entropy and sample entropy

In the field of time domain measurement, with increasing complexity of measured signals, the periodic stationarity of signals is destroyed and the transient non-stationarity starts to stand out, specifically manifested as frequent presence of transient abnormal signals, such as burrs, harmonics, noises, and modulating waves in the periodic signals. By applying the entropy estimation of signals to the field of time domain measurement, this paper designs a transient abnormal signal acquisition system based on approximate entropy (ApEn) and sample entropy (SampEn). In the process of data acquisition, the ApEn and SampEn of sampled data are computed in real time and the complexities of measured signals are differentiated, thus realizing abnormal signal detection. The experimental results demonstrate that SampEn generally has a higher sensitivity and wider application than ApEn in the detection process of transient abnormal signals. The study can provide a new method for the design of a time-domain measuring instrument with abnormal signal detection ability.

[An anesthesia depth computing method study based on wavelet transform and artificial neural network]

General anesthesia is an essential part of surgery to ensure the safety of patients. Electroencephalogram (EEG) has been widely used in anesthesia depth monitoring for abundant information and the ability of reflecting the brain activity. The paper proposes a method which combines wavelet transform and artificial neural network (ANN) to assess the depth of anesthesia. Discrete wavelet transform was used to decompose the EEG signal, and the approximation coefficients and detail coefficients were used to calculate the 9 characteristic parameters. Kruskal-Wallis statistical test was made to these characteristic parameters, and the test showed that the parameters were statistically significant for the differences of the four levels of anesthesia: awake, light anesthesia, moderate anesthesia and deep anesthesia ( P < 0.001). The 9 characteristic parameters were used as the input of ANN, the bispectral index (BIS) was used as the reference output, and the method was evaluated by the data of 8 patients during general anesthesia. The accuracy of the method in the classification of the four anesthesia levels of the test set in the 7:3 set-out method was 85.98%, and the correlation coefficient with the BIS was 0.977 0. The results show that this method can better distinguish four different anesthesia levels and has broad application prospects for monitoring the depth of anesthesia.

A Combinatorial Deep Learning Structure for Precise Depth of Anesthesia Estimation From EEG Signals

Electroencephalography (EEG) is commonly used to measure the depth of anesthesia (DOA) because EEG reflects surgical pain and state of the brain. However, precise and real-time estimation of DOA index for painful surgical operations is challenging due to problems such as postoperative complications and accidental awareness. To tackle these problems, we propose a new combinatorial deep learning structure involving convolutional neural networks (inspired by the inception module), bidirectional long short-term memory, and an attention layer. The proposed model uses the EEG signal to continuously predicts the bispectral index (BIS). It is trained over a large dataset, mostly from those under general anesthesia with few cases receiving sedation/analgesia and spinal anesthesia. Despite the imbalance distribution of BIS values in different levels of anesthesia, our proposed structure achieves convincing root mean square error of 5.59 ± 1.04 and mean absolute error of 4.3 ± 0.87, as well as improvement in area under the curve of 15% on average, which surpasses state-of-the-art DOA estimation methods. The DOA values are also discretized into four levels of anesthesia and the results demonstrate strong inter-subject classification accuracy of 88.7% that outperforms the conventional methods.

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.

[Machine learning in anesthesiology]

The application of artificial intelligence (AI) is currently changing very different areas of life. Artificial intelligence involves the emulation of human behavior with the aid of methods from mathematics and informatics. Machine learning (ML) represents a subdivision of AI. Algorithms for ML have the potential to optimize patient care, in that they can be utilized in a supportive way in personalized medicine, decision making and risk prediction. Although the majority of the applications in medicine are still limited to data analysis and research, it is certain that ML will become increasingly more important in scientific and clinical aspects in this supportive function. Therefore, it is necessary for clinicians to have at least a basic understanding of the functional principles, strengths and weaknesses of ML.

Topological analysis of differential effects of ketamine and propofol anaesthesia on brain dynamics

Research has found that the vividness of conscious experience is related to brain dynamics. Despite both being anaesthetics, propofol and ketamine produce different subjective states: we explore the different effects of these two anaesthetics on the structure of dynamic attractors reconstructed from electrophysiological activity recorded from cerebral cortex of two macaques. We used two methods: the first embeds the recordings in a continuous high-dimensional manifold on which we use topological data analysis to infer the presence of higher-order dynamics. The second reconstruction, an ordinal partition network embedding, allows us to create a discrete state-transition network, which is amenable to information-theoretic analysis and contains rich information about state-transition dynamics. We find that the awake condition generally had the 'richest' structure, visiting the most states, the presence of pronounced higher-order structures, and the least deterministic dynamics. By contrast, the propofol condition had the most dissimilar dynamics, transitioning to a more impoverished, constrained, low-structure regime. The ketamine condition, interestingly, seemed to combine aspects of both: while it was generally less complex than the awake condition, it remained well above propofol in almost all measures. These results provide deeper and more comprehensive insights than what is typically gained by using point-measures of complexity.

Depth of anesthesia prediction via EEG signals using convolutional neural network and ensemble empirical mode decomposition

According to a recently conducted survey on surgical complication mortality rate, 47% of such cases are due to anesthetics overdose. This indicates that there is an urgent need to moderate the level of anesthesia. Recently deep learning (DL) methods have played a major role in estimating the depth of Anesthesia (DOA) of patients and has played an essential role in control anesthesia overdose. In this paper, Electroencephalography (EEG) signals have been used for the prediction of DOA. EEG signals are very complex signals which may require months of training and advanced signal processing techniques. It is a point of debate whether DL methods are an improvement over the already existing traditional EEG signal processing approaches. One of the DL algorithms is Convolutional neural network (CNN) which is very popular algorithm for object recognition and is widely growing its applications in processing hierarchy in the human visual system. In this paper, various decomposition methods have been used for extracting the features EEG signal. After acquiring the necessary signals values in image format, several CNN models have been deployed for classification of DOA depending upon their Bispectral Index (BIS) and the signal quality index (SQI). The EEG signals were converted into the frequency domain using and Empirical Mode Decomposition (EMD), and Ensemble Empirical Mode Decomposition (EEMD). However, because of the inter mode mixing observed in EMD method; EEMD have been utilized for this study. The developed CNN models were used to predict the DOA based on the EEG spectrum images without the use of handcrafted features which provides intuitive mapping with high efficiency and reliability. The best trained model gives an accuracy of 83.2%. Hence, this provides further scope and research which can be carried out in the domain of visual mapping of DOA using EEG signals and DL methods.

A novel spectral entropy-based index for assessing the depth of anaesthesia

Anaesthesia is a state of temporary controlled loss of awareness induced for medical operations. An accurate assessment of the depth of anaesthesia (DoA) helps anesthesiologists to avoid awareness during surgery and keep the recovery period short. However, the existing DoA algorithms have limitations, such as not robust enough for different patients and having time delay in assessment. In this study, to develop a reliable DoA measurement method, pre-denoised electroencephalograph (EEG) signals are divided into ten frequency bands (α, β1, β2, β3, β4, β, βγ, γ, δ and θ), and the features are extracted from different frequency bands using spectral entropy (SE) methods. SE from the beta-gamma frequency band (21.5–38.5 Hz) and SE from the beta frequency band show the highest correlation (R-squared value: 0.8458 and 0.7312, respectively) with the most popular DoA index, bispectral index (BIS). In this research, a new DoA index is developed based on these two SE features for monitoring the DoA. The highest Pearson correlation coefficient by comparing the BIS index for testing data is 0.918, and the average is 0.80. In addition, the proposed index shows an earlier reaction than the BIS index when the patient goes from deep anaesthesia to moderate anaesthesia, which means it is more suitable for the real-time DoA assessment. In the case of poor signal quality (SQ), while the BIS index exhibits inflexibility with cases of poor SQ, the new proposed index shows reliable assessment results that reflect the clinical observations.

An Electroencephalogram Metric of Temporal Complexity Tracks Psychometric Impairment Caused by Low-dose Nitrous Oxide

BACKGROUND

Nitrous oxide produces non-γ-aminobutyric acid sedation and psychometric impairment and can be used as scientific model for understanding mechanisms of progressive cognitive disturbances. Temporal complexity of the electroencephalogram may be a sensitive indicator of these effects. This study measured psychometric performance and the temporal complexity of the electroencephalogram in participants breathing low-dose nitrous oxide.

METHODS

In random order, 20, 30, and 40% end-tidal nitrous oxide was administered to 12 participants while recording 32-channel electroencephalogram and psychometric function. A novel metric quantifying the spatial distribution of temporal electroencephalogram complexity, comprised of (1) absolute cross-correlation calculated between consecutive 0.25-s time samples; 2) binarizing these cross-correlation matrices using the median of all channels as threshold; (3) using quantitative recurrence analysis, the complexity in temporal changes calculated by the Shannon entropy of the probability distribution of the diagonal line lengths; and (4) overall spatial extent and intensity of brain complexity, was quantified by calculating median temporal complexity of channels whose complexities were above 1 at baseline. This region approximately overlay the brain's default mode network, so this summary statistic was termed "default-mode-network complexity."

RESULTS

Nitrous oxide concentration correlated with psychometric impairment (r = 0.50, P < 0.001). Baseline regional electroencephalogram complexity at midline was greater than in lateral temporal channels (1.33 ± 0.14 bits vs. 0.81 ± 0.12 bits, P < 0.001). A dose of 40% N2O decreased midline (mean difference [95% CI], 0.20 bits [0.09 to 0.31], P = 0.002) and prefrontal electroencephalogram complexity (mean difference [95% CI], 0.17 bits [0.08 to 0.27], P = 0.002). The lateral temporal region did not change significantly (mean difference [95% CI], 0.14 bits [-0.03 to 0.30], P = 0.100). Default-mode-network complexity correlated with N2O concentration (r = -0.55, P < 0.001). A default-mode-network complexity mixed-effects model correlated with psychometric impairment (r2 = 0.67; receiver operating characteristic area [95% CI], 0.72 [0.59 to 0.85], P < 0.001).

CONCLUSIONS

Temporal complexity decreased most markedly in medial cortical regions during low-dose nitrous oxide exposures, and this change tracked psychometric impairment.

EDITOR’S PERSPECTIVE

State-Dependent Cortical Unit Activity Reflects Dynamic Brain State Transitions in Anesthesia

Understanding the effects of anesthesia on cortical neuronal spiking and information transfer could help illuminate the neuronal basis of the conscious state. Recent investigations suggest that the brain state identified by local field potential spectrum is not stationary but changes spontaneously at a fixed level of anesthetic concentration. How cortical unit activity changes with dynamically transitioning brain states under anesthesia is unclear. Extracellular unit activity was measured with 64-channel silicon microelectrode arrays in cortical layers 5/6 of the primary visual cortex of chronically instrumented, freely moving male rats (n = 7) during stepwise reduction of the anesthetic desflurane (6%, 4%, 2%, and 0%). Unsupervised machine learning applied to multiunit spike patterns revealed five distinct brain states. A novel desynchronized brain state with increased spike rate variability, sample entropy, and EMG activity occurred in 6% desflurane with 40.0% frequency. The other four brain states reflected graded levels of anesthesia. As anesthesia deepened the spike rate of neurons decreased regardless of their spike rate profile at baseline conscious state. Actively firing neurons with wide-spiking pattern showed increased bursting activity along with increased spike timing variability, unit-to-population correlation, and unit-to-unit transfer entropy, despite the overall decrease in transfer entropy. The narrow-spiking neurons showed similar changes but to a lesser degree. These results suggest that (1) anesthetic effect on spike rate is distinct from sleep, (2) synchronously fragmented spiking pattern is a signature of anesthetic-induced unconsciousness, and (3) the paradoxical, desynchronized brain state in deep anesthesia contends the generally presumed monotonic, dose-dependent anesthetic effect on the brain.SIGNIFICANCE STATEMENT Recent studies suggest that spontaneous changes in brain state occur under anesthesia. However, the spiking behavior of cortical neurons associated with such state changes has not been investigated. We found that local brain states defined by multiunit activity had a nonunitary relationship with the current anesthetic level. A paradoxical brain state displaying asynchronous firing pattern and high EMG activity was found unexpectedly in deep anesthesia. In contrast, the synchronous fragmentation of neuronal spiking appeared to be a robust signature of the state of anesthesia. The findings challenge the assumption of monotonic, anesthetic dose-dependent behavior of cortical neuron populations. They enhance the interpretation of neuroscientific data obtained under anesthesia and the understanding of the neuronal basis of anesthetic-induced state of unconsciousness.

High-voltage, diffuse delta rhythms coincide with wakeful consciousness and complexity in Angelman syndrome

Abundant evidence from slow wave sleep, anesthesia, coma, and epileptic seizures links high-voltage, slow electroencephalogram (EEG) activity to loss of consciousness. This well-established correlation is challenged by the observation that children with Angelman syndrome (AS), while fully awake and displaying volitional behavior, display a hypersynchronous delta (1–4 Hz) frequency EEG phenotype typical of unconsciousness. Because the trough of the delta oscillation is associated with down-states in which cortical neurons are silenced, the presence of volitional behavior and wakefulness in AS amidst diffuse delta rhythms presents a paradox. Moreover, high-voltage, slow EEG activity is generally assumed to lack complexity, yet many theories view functional brain complexity as necessary for consciousness. Here, we use abnormal cortical dynamics in AS to assess whether EEG complexity may scale with the relative level of consciousness despite a background of hypersynchronous delta activity. As characterized by multiscale metrics, EEGs from 35 children with AS feature significantly greater complexity during wakefulness compared with sleep, even when comparing the most pathological segments of wakeful EEG to the segments of sleep EEG least likely to contain conscious mentation and when factoring out delta power differences across states. These findings (i) warn against reverse inferring an absence of consciousness solely on the basis of high-amplitude EEG delta oscillations, (ii) corroborate rare observations of preserved consciousness under hypersynchronization in other conditions, (iii) identify biomarkers of consciousness that have been validated under conditions of abnormal cortical dynamics, and (iv) lend credence to theories linking consciousness with complexity.

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

Accurate monitoring of the depth of anesthesia (DoA) is essential for intraoperative and postoperative patient's health. Commercially available electroencephalograph (EEG)-based DoA monitors are recommended only for certain anesthetic drugs and specific age-group patients. This paper presents a machine learning classification processor for accurate DoA estimation irrespective of the patient's age and anesthetic drug. The classification is solely based on six features extracted from EEG signal, i.e., spectral edge frequency (SEF), beta ratio, and four bands of spectral energy (FBSE). A machine learning fine decision tree classifier is adopted to achieve a four-class DoA classification (deep, moderate, and light DoA versus awake state). The feature selection and the classification processor are optimized to achieve the highest classification accuracy for the state of moderate anesthesia required for the surgical operations. The proposed 256-point fast Fourier transform accelerator is implemented to realize SEF, beta ratio, and FBSE that enables minimal latency and high accuracy feature extraction. The proposed DoA processor is implemented using a 65 nm CMOS technology and experimentally verified using field programming gate array (FPGA) based on the EEG recordings of 75 patients undergoing elective surgery with different types of anesthetic agents. The processor achieves an average accuracy of 92.2% for all DoA states, with a latency of 1s The 0.09 mm² DoA processor consumes 140nJ/classification.

Use of Multiple EEG Features and Artificial Neural Network to Monitor the Depth of Anesthesia

The electroencephalogram (EEG) can reflect brain activity and contains abundant information of different anesthetic states of the brain. It has been widely used for monitoring depth of anesthesia (DoA). In this study, we propose a method that combines multiple EEG-based features with artificial neural network (ANN) to assess the DoA. Multiple EEG-based features can express the states of the brain more comprehensively during anesthesia. First, four parameters including permutation entropy, 95% spectral edge frequency, BetaRatio and SynchFastSlow were extracted from the EEG signal. Then, the four parameters were set as the inputs to an ANN which used bispectral index (BIS) as the reference output. 16 patient datasets during propofol anesthesia were used to evaluate this method. The results indicated that the accuracies of detecting each state were 86.4% (awake), 73.6% (light anesthesia), 84.4% (general anesthesia), and 14% (deep anesthesia). The correlation coefficient between BIS and the index of this method was 0.892 (p<0.001). The results showed that the proposed method could well distinguish between awake and other anesthesia states. This method is promising and feasible for a monitoring system to assess the DoA.

Neural Correlates of Anesthesia in Newborn Mice and Humans

Monitoring the hypnotic component of anesthesia during surgeries is critical to prevent intraoperative awareness and reduce adverse side effects. For this purpose, electroencephalographic (EEG) methods complementing measures of autonomic functions and behavioral responses are in use in clinical practice. However, in human neonates and infants existing methods may be unreliable and the correlation between brain activity and anesthetic depth is still poorly understood. Here, we characterized the effects of different anesthetics on brain activity in neonatal mice and developed machine learning approaches to identify electrophysiological features predicting inspired or end-tidal anesthetic concentration as a proxy for anesthetic depth. We show that similar features from EEG recordings can be applied to predict anesthetic concentration in neonatal mice and humans. These results might support a novel strategy to monitor anesthetic depth in human newborns.

Range Entropy: A Bridge between Signal Complexity and Self-Similarity

Approximate entropy (ApEn) and sample entropy (SampEn) are widely used for temporal complexity analysis of real-world phenomena. However, their relationship with the Hurst exponent as a measure of self-similarity is not widely studied. Additionally, ApEn and SampEn are susceptible to signal amplitude changes. A common practice for addressing this issue is to correct their input signal amplitude by its standard deviation. In this study, we first show, using simulations, that ApEn and SampEn are related to the Hurst exponent in their tolerance r and embedding dimension m parameters. We then propose a modification to ApEn and SampEn called range entropy or RangeEn. We show that RangeEn is more robust to nonstationary signal changes, and it has a more linear relationship with the Hurst exponent, compared to ApEn and SampEn. RangeEn is bounded in the tolerance r-plane between 0 (maximum entropy) and 1 (minimum entropy) and it has no need for signal amplitude correction. Finally, we demonstrate the clinical usefulness of signal entropy measures for characterisation of epileptic EEG data as a real-world example.