A Real-Time Depth of Anesthesia Monitoring System Based on Deep Neural Network With Large EDO Tolerant EEG Analog Front-End

Age-dependent Electroencephalogram Characteristics During Different Levels of Anesthetic Depth

Objective The monitoring of anesthetic depth based on electroencephalogram derivation is not currently adjusted for age. Here we analyze the influence of age factors on electroencephalogram characteristics. Methods Frontal electroencephalogram recordings were obtained from 80 adults during routine clinical anesthesia. The characteristics of electroencephalogram with age and anesthesia were observed during four kinds of anesthesia. Results The slow wave power, δ power, Bispectral Index (BIS) and approximate entropy can be used to distinguish different states of anesthesia (P < 0.05). In the deep and very deep anesthesia states, δ power decreased with age (P < 0.0001). In the very deep anesthesia state, θ power decreased with age (P < 0.05). In the deep and very deep anesthesia states, α power decreased with age (P = 0.0002). In the light and deep anesthesia states, β power decreased with age (P = 0.003). In the deep anesthesia state, γ power decreased with age (P = 0.002). In the very deep anesthesia state, permutation entropy increased significantly with age (P = 0.0001). In the very deep anesthesia state, BIS value increased with age (P = 0.006). The slow wave power, approximate entropy, and sample entropy did not show age-dependent changes. Conclusions The influence of age should be considered when using BIS and δ power to monitor the depth of anesthesia, while the influence of age should not be considered when using slow wave power and approximate entropy to monitor the depth of anesthesia.

Personalized anesthesia and precision medicine: a comprehensive review of genetic factors, artificial intelligence, and patient-specific factors

Precision medicine, characterized by the personalized integration of a patient's genetic blueprint and clinical history, represents a dynamic paradigm in healthcare evolution. The emerging field of personalized anesthesia is at the intersection of genetics and anesthesiology, where anesthetic care will be tailored to an individual's genetic make-up, comorbidities and patient-specific factors. Genomics and biomarkers can provide more accurate anesthetic protocols, while artificial intelligence can simplify anesthetic procedures and reduce anesthetic risks, and real-time monitoring tools can improve perioperative safety and efficacy. The aim of this paper is to present and summarize the applications of these related fields in anesthesiology by reviewing them, exploring the potential of advanced technologies in the implementation and development of personalized anesthesia, realizing the future integration of new technologies into clinical practice, and promoting multidisciplinary collaboration between anesthesiology and disciplines such as genomics and artificial intelligence.

A Review of Embedded Machine Learning Based on Hardware, Application, and Sensing Scheme

Machine learning is an expanding field with an ever-increasing role in everyday life, with its utility in the industrial, agricultural, and medical sectors being undeniable. Recently, this utility has come in the form of machine learning implementation on embedded system devices. While there have been steady advances in the performance, memory, and power consumption of embedded devices, most machine learning algorithms still have a very high power consumption and computational demand, making the implementation of embedded machine learning somewhat difficult. However, different devices can be implemented for different applications based on their overall processing power and performance. This paper presents an overview of several different implementations of machine learning on embedded systems divided by their specific device, application, specific machine learning algorithm, and sensors. We will mainly focus on NVIDIA Jetson and Raspberry Pi devices with a few different less utilized embedded computers, as well as which of these devices were more commonly used for specific applications in different fields. We will also briefly analyze the specific ML models most commonly implemented on the devices and the specific sensors that were used to gather input from the field. All of the papers included in this review were selected using Google Scholar and published papers in the IEEExplore database. The selection criterion for these papers was the usage of embedded computing systems in either a theoretical study or practical implementation of machine learning models. The papers needed to have provided either one or, preferably, all of the following results in their studies-the overall accuracy of the models on the system, the overall power consumption of the embedded machine learning system, and the inference time of their models on the embedded system. Embedded machine learning is experiencing an explosion in both scale and scope, both due to advances in system performance and machine learning models, as well as greater affordability and accessibility of both. Improvements are noted in quality, power usage, and effectiveness.

Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System

Despite the growing interest in the use of electroencephalogram (EEG) signals as a potential biometric for subject identification and the recent advances in the use of deep learning (DL) models to study neurological signals, such as electrocardiogram (ECG), electroencephalogram (EEG), electroretinogram (ERG), and electromyogram (EMG), there has been a lack of exploration in the use of state-of-the-art DL models for EEG-based subject identification tasks owing to the high variability in EEG features across sessions for an individual subject. In this paper, we explore the use of state-of-the-art DL models such as ResNet, Inception, and EEGNet to realize EEG-based biometrics on the BED dataset, which contains EEG recordings from 21 individuals. We obtain promising results with an accuracy of 63.21%, 70.18%, and 86.74% for Resnet, Inception, and EEGNet, respectively, while the previous best effort reported accuracy of 83.51%. We also demonstrate the capabilities of these models to perform EEG biometric tasks in real-time by developing a portable, low-cost, real-time Raspberry Pi-based system that integrates all the necessary steps of subject identification from the acquisition of the EEG signals to the prediction of identity while other existing systems incorporate only parts of the whole system.

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.

Real-Time Algorithm for Detrended Cross-Correlation Analysis of Long-Range Coupled Processes

Assessing power-law cross-correlations between a pair - or among a set - of processes is of great significance in diverse fields of analyses ranging from neuroscience to financial markets. In most cases such analyses are computationally expensive and thus carried out offline once the entire signal is obtained. However, many applications - such as mental state monitoring or financial forecasting - call for fast algorithms capable of estimating scale-free coupling in real time. Detrended cross-correlation analysis (DCCA), a generalization of the detrended fluctuation analysis (DFA) to the bivariate domain, has been introduced as a method designed to quantify power-law cross-correlations between a pair of non-stationary signals. Later, in analogy with the Pearson cross-correlation coefficient, DCCA was adapted to the detrended cross-correlation coefficient (DCCC), however as of now no online algorithms were provided for either of these analysis techniques. Here we introduce a new formula for obtaining the scaling functions in real time for DCCA. Moreover, the formula can be generalized via matrix notation to obtain the scaling relationship between not only a pair of signals, but also all possible pairs among a set of signals at the same time. This includes parallel estimation of the DFA scaling function of each individual process as well, thus allowing also for real-time acquisition of DCCC. The proposed algorithm matches its offline variants in precision, while being substantially more efficient in terms of execution time. We demonstrate that the method can be utilized for mental state monitoring on multi-channel electroencephalographic recordings obtained in eyes-closed and eyes-open resting conditions.

Intelligent Method for Real-Time Portable EEG Artifact Annotation in Semiconstrained Environment Based on Computer Vision

As a convenient device for observing neural activity in the natural environment, portable EEG technology (PEEGT) has an extensive prospect in expanding neuroscience research into natural applications. However, unlike in the laboratory environment, PEEGT is usually applied in a semiconstrained environment, including management and engineering, generating much more artifacts caused by the subjects' activities. Due to the limitations of existing artifacts annotation, the problem limits PEEGT to take advantage of portability and low-test cost, which is a crucial obstacle for the potential application of PEEGT in the natural environment. This paper proposes an intelligent method to identify two leading antecedent causes of EEG artifacts, participant's blinks and head movements, and annotate the time segments of artifacts in real time based on computer vision (CV). Furthermore, it changes the original postprocessing mode based on artifact signal recognition to the preprocessing mode based on artifact behavior recognition by the CV method. Through a comparative experiment with three artifacts mark operators and the CV method, we verify the effectiveness of the method, which lays a foundation for accurate artifact removal in real time in the next step. It enlightens us on how to adopt computer technology to conduct large-scale neurotesting in a natural semiconstrained environment outside the laboratory without expensive laboratory equipment or high manual costs.

Time-Frequency Analysis of EEG Signals and GLCM Features for Depth of Anesthesia Monitoring

One of the important tasks in the operating room is monitoring the depth of anesthesia (DoA) during surgery, and noninvasive techniques are very popular. Hence, we propose a new scheme for DoA monitoring considering the time-frequency analysis of electroencephalography (EEG) signals and GLCM features extracted from them. To this end, at first, the time-frequency map (TFM) of each channel of each EEG is computed by smoothed pseudo-Wigner–Ville distribution (SPWVD), where the EEG signal used in this paper is recorded in 15 channels. After that, we consider the gray-level co-occurrence matrix (GLCM) to obtain the content of TFM, and after that, four features such as homogeneity, correlation, energy, and contrast are obtained for each GLCM. Finally, after the selection of efficient features using the minimum redundancy maximum relevance (MRMR) method, the K-nearest neighbor (KNN) classifier is utilized to determine the DoA. Here, we consider the three states, namely, deep hypnotic, surgical anesthesia, and sedation and awake states according to bispectral index (BIS), and each EEG epoch is classified to these states. We also employ data augmentation to enhance the training phase and increase accuracy. We obtain the accuracy and confusion matrix of the proposed method. We also analyze the effects of a number of gray levels of GLCM, distance measure in KNN classifier, and parameters of data augmentation on the performance of the proposed method. Results indicate the efficiency of the proposed method to determine the DoA during surgery.

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.

Smart Portable Pen for Continuous Monitoring of Anaesthetics in Human Serum With Machine Learning

Continuous monitoring of anaesthetics infusion is demanded by anaesthesiologists to help in defining personalized dose, hence reducing risks and side effects. We propose the first piece of technology tailored explicitly to close the loop between anaesthesiologist and patient with continuous drug monitoring. Direct detection of drugs is achieved with electrochemical techniques, and several options are present in literature to measure propofol (widely used anaesthetics). Still, the sensors proposed do not enable in-situ detection, they do not provide this information continuously, and they are based on bulky and costly lab equipment. In this paper, we present a novel smart pen-shaped electronic system for continuous monitoring of propofol in human serum. The system consists of a needle-shaped sensor, a quasi digital front-end, a smart machine learning data processing, in a single wireless battery-operated embedded device featuring Bluetooth Low Energy (BLE) communication. The system has been tested and characterized in real, undiluted human serum, at 37  ^°C. The device features a limit of detection of 3.8  μM, meeting the requirement of the target application, with an electronics system 59% smaller and 81% less power consuming w.r.t. the state-of-the-art, using a smart machine learning classification for data processing, which guarantees up to twenty continuous measure.

Heart rate variability-derived features based on deep neural network for distinguishing different anaesthesia states

Background

Estimating the depth of anaesthesia (DoA) is critical in modern anaesthetic practice. Multiple DoA monitors based on electroencephalograms (EEGs) have been widely used for DoA monitoring; however, these monitors may be inaccurate under certain conditions. In this work, we hypothesize that heart rate variability (HRV)-derived features based on a deep neural network can distinguish different anaesthesia states, providing a secondary tool for DoA assessment.

Methods

A novel method of distinguishing different anaesthesia states was developed based on four HRV-derived features in the time and frequency domain combined with a deep neural network. Four features were extracted from an electrocardiogram, including the HRV high-frequency power, low-frequency power, high-to-low-frequency power ratio, and sample entropy. Next, these features were used as inputs for the deep neural network, which utilized the expert assessment of consciousness level as the reference output. Finally, the deep neural network was compared with the logistic regression, support vector machine, and decision tree models. The datasets of 23 anaesthesia patients were used to assess the proposed method.

Results

The accuracies of the four models, in distinguishing the anaesthesia states, were 86.2% (logistic regression), 87.5% (support vector machine), 87.2% (decision tree), and 90.1% (deep neural network). The accuracy of deep neural network was higher than those of the logistic regression (p < 0.05), support vector machine (p < 0.05), and decision tree (p < 0.05) approaches. Our method outperformed the logistic regression, support vector machine, and decision tree methods.

Conclusions

The incorporation of four HRV-derived features in the time and frequency domain and a deep neural network could accurately distinguish between different anaesthesia states; however, this study is a pilot feasibility study. The proposed method—with other evaluation methods, such as EEG—is expected to assist anaesthesiologists in the accurate evaluation of the DoA.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12871-021-01285-x.