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

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.

Harnessing machine learning for EEG signal analysis: Innovations in depth of anaesthesia assessment

Anaesthesia, crucial to surgical practice, is undergoing renewed scrutiny due to the integration of artificial intelligence in its medical use. The precise control over the temporary loss of consciousness is vital to ensure safe, pain-free procedures. Traditional methods of depth of anaesthesia (DoA) assessment, reliant on physical characteristics, have proven inconsistent due to individual variations. In response, electroencephalography (EEG) techniques have emerged, with indices such as the Bispectral Index offering quantifiable assessments. This literature review explores the current scope and frontier of DoA research, emphasising methods utilising EEG signals for effective clinical monitoring. This review offers a critical synthesis of recent advances, specifically focusing on electroencephalography (EEG) techniques and their role in enhancing clinical monitoring. By examining 117 high-impact papers, the review delves into the nuances of feature extraction, model building, and algorithm design in EEG-based DoA analysis. Comparative assessments of these studies highlight their methodological approaches and performance, including clinical correlations with established indices like the Bispectral Index. The review identifies knowledge gaps, particularly the need for improved collaboration for data access, which is essential for developing superior machine learning models and real-time predictive algorithms for patient management. It also calls for refined model evaluation processes to ensure robustness across diverse patient demographics and anaesthetic agents. The review underscores the potential of technological advancements to enhance precision, safety, and patient outcomes in anaesthesia, paving the way for a new standard in anaesthetic care. The findings of this review contribute to the ongoing discourse on the application of EEG in anaesthesia, providing insights into the potential for technological advancement in this critical area of medical practice.

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.

Consciousness and General Anesthesia: Challenges for Measuring the Depth of Anesthesia

The optimal consciousness level required for general anesthesia with surgery is unclear, but in existing practice, anesthetic oblivion, may be incomplete. This article discusses the concept of consciousness, how it is altered by anesthetics, the challenges for assessing consciousness, currently used technologies for assessing anesthesia levels, and future research directions. Wakefulness is marked by a subjective experience of existence (consciousness), perception of input from the body or the environment (connectedness), the ability for volitional responsiveness, and a sense of continuity in time. Anesthetic drugs may selectively impair some of these components without complete extinction of the subjective experience of existence. In agreement with Sanders et al. (2012), the authors propose that a state of disconnected consciousness is the optimal level of anesthesia, as it likely avoids both awareness and the possible dangers of oversedation. However, at present, there are no reliably tested indices that can discriminate between connected consciousness, disconnected consciousness, and complete unconsciousness.

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.

Comparative analysis of the effect of electromyogram to bispectral index and 95% spectral edge frequency under remimazolam and propofol anesthesia: a prospective, randomized, controlled clinical trial

Background

Bispectral index (BIS), an index used to monitor the depth of anesthesia, can be interfered with by the electromyogram (EMG) signal. The 95% spectral edge frequency (SEF95) also can reflect the sedation depth. Remimazolam in monitored anesthesia care results in higher BIS values than propofol, though in the same sedation level assessed by Modified Observers Assessment of Alertness and Sedation (MOAA/S). Our study aims to illustrate whether EMG is involved in remimazolam causing higher BIS value than propofol preliminarily and to explore the correlations among BIS, EMG, and SEF95 under propofol and remimazolam anesthesia.

Patients and methods

Twenty-eight patients were randomly divided into propofol (P) and remimazolam (RM) groups. Patients in the two groups received alfentanil 10 μg/kg, followed by propofol 2 mg/kg and remimazolam 0.15 mg/kg. Blood pressure (BP), heart rate (HR), and oxygen saturation (SpO2) were routinely monitored. The BIS, EMG, and SEF95 were obtained through BIS VISTATM. The primary outcomes were BIS, EMG, and the correlation between BIS and EMG in both groups. Other outcomes were SEF95, the correlation between BIS and SEF95, and the correlation between EMG and SEF95. And all the statistical and comparative analysis between these signals was conducted with SPSS 26.0 and GraphPad Prism 8.

Results

BIS values, EMG, and SEF95 were significantly higher in the RM group than in the P group (all p < 0.001). There was a strong positive correlation between BIS and EMG in the RM group (r = 0.416). Nevertheless, the BIS in the P group showed a weak negative correlation with EMG (r = -0.219). Both P (r = 0.787) and RM group (r = 0.559) had a reasonably significant correlation coefficient between BIS and SEF95. SEF95 almost did not correlate with EMG in the RM group (r = 0.101).

Conclusion

Bispectral index can be interfered with high EMG intensity under remimazolam anesthesia. However, EMG can hardly affect the accuracy of BIS under propofol anesthesia due to low EMG intensity and a weak negative correlation between EMG and BIS. Moreover, SEF95 may have a great application prospect in predicting the sedation condition of remimazolam.

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.

Photoplethysmography temporal marker-based machine learning classifier for anesthesia drug detection

Anesthesia drug overdose hazards and lack of gold standards in anesthesia monitoring lead to an urgent need for accurate anesthesia drug detection. To investigate the PPG waveform features affected by anesthesia drugs and develop a machine-learning classifier with high anesthesia drug sensitivity. This study used 64 anesthesia and non-anesthesia patient data (32 cases each), extracted from Queensland and MIMIC-II databases, respectively. The key waveform features (total area, rising time, width 75%, 50%, and 25%) were extracted from 16,310 signal recordings (5-s duration). Discriminant analysis, support vector machine (SVM), and K-nearest neighbor (KNN) were evaluated by splitting the dataset into halve training (11 patients, 8570 segments) and halve testing dataset (11 patients, 7740 segments). Significant differences exist between PPG waveform features of anesthesia and non-anesthesia groups (p < 0.05) except total area feature (p > 0.05). The KNN classifier achieved 91.7% (AUC = 0.95) anesthesia detection accuracy with the highest sensitivity (0.88) and specificity (0.90) as compared to other classifiers. Kohen’s kappa also shows almost perfect agreement (0.79) with the KNN classifier. The KNN classifier trained with significant PPG features has the potential to be used as a reliable, non-invasive, and low-cost method for the detection of anesthesia drugs for depth analysis during surgical operations and postoperative monitoring.

Electroencephalogram Features of Perioperative Neurocognitive Disorders in Elderly Patients: A Narrative Review of the Clinical Literature

Postoperative neurocognitive disorder (PND) is a common postoperative complication, particularly in older patients. Electroencephalogram (EEG) monitoring, a non-invasive technique with a high spatial-temporal resolution, can accurately characterize the dynamic changes in brain function during the perioperative period. Current clinical studies have confirmed that the power density of alpha oscillation during general anesthesia decreased with age, which was considered to be associated with increased susceptibility to PND in the elderly. However, evidence on whether general anesthesia under EEG guidance results in a lower morbidity of PND is still contradictory. This is one of the reasons that common indicators of the depth of anesthesia were limitedly derived from EEG signals in the frontal lobe. The variation of multi-channel EEG features during the perioperative period has the potential to highlight the occult structural and functional abnormalities of the subcortical-cortical neurocircuit. Therefore, we present a review of the application of multi-channel EEG monitoring to predict the incidence of PND in older patients. The data confirmed that the abnormal variation in EEG power and functional connectivity between distant brain regions was closely related to the incidence and long-term poor outcomes of PND in older adults.

A Two-Stream Graph Convolutional Network Based on Brain Connectivity for Anesthetized States Analysis

Investigating neural mechanisms of anesthesia process and developing efficient anesthetized state detection methods are especially on high demand for clinical consciousness monitoring. Traditional anesthesia monitoring methods are not involved with the topological changes between electrodes covering the prefrontal-parietal cortices, by investigating electrocorticography (ECoG). To fill this gap, a framework based on the two-stream graph convolutional network (GCN) was proposed, i.e., one stream for extracting topological structure features, and the other one for extracting node features. The two-stream graph convolutional network includes GCN Model 1 and GCN Model 2. For GCN Model 1, brain connectivity networks were constructed by using phase lag index (PLI), representing different structure features. A common adjacency matrix was founded through the dual-graph method, the structure features were expressed on nodes. Therefore, the traditional spectral graph convolutional network can be directly applied on the graphs with changing topological structures. On the other hand, the average of the absolute signal amplitudes was calculated as node features, then a fully connected matrix was constructed as the adjacency matrix of these node features, as the input of GCN Model 2. This method learns features of both topological structure and nodes of the graph, and uses a dual-graph approach to enhance the focus on topological structure features. Based on the ECoG signals of monkeys, results show that this method which can distinguish awake state, moderate sedation and deep sedation achieved an accuracy of 92.75% in group-level experiments and mean accuracy of 93.50% in subject-level experiments. Our work verifies the excellence of the graph convolutional network in anesthesia monitoring, the high recognition accuracy also shows that the brain network may carry neurological markers associated with anesthesia.

Developing a robust model to predict depth of anesthesia from single channel EEG signal

Monitoring depth of anaesthesia (DoA) from electroencephalograph (EEG) signals is an ongoing challenge for anaesthesiologists. In this study, we propose an intelligence model that predicts the DoA from a single channel electroencephalograph (EEG) signal. A segmentation technique based on a sliding window is employed to partition EEG signals. Hierarchical dispersion entropy (HDE) is applied to each EEG segment. A set of features is extracted from each EEG segment. The extracted features are investigated using a community graph detection approach (CGDA), and the most relevant features are selected to trace the DoA. The proposed model, based on HDE coupled with CGDA, is evaluated in term of BIS index using several statistical metrics such Q-Q plot, regression, and correlation coefficients. In addition, the proposed model is evaluated against the BIS index in the case of the poor signal quality. The results demonstrated that the proposed model showed an earlier reaction compared with the BIS index when patient’s state transits from deep anaesthesia to moderate anaesthesia in the case of poor signal quality. The highest Pearson correlation coefficient obtained by the proposed is 0.96.

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.

Biophysical Model: A Promising Method in the Study of the Mechanism of Propofol: A Narrative Review

The physiological and neuroregulatory mechanism of propofol is largely based on very limited knowledge. It is one of the important puzzling issues in anesthesiology and is of great value in both scientific and clinical fields. It is acknowledged that neural networks which are comprised of a number of neural circuits might be involved in the anesthetic mechanism. However, the mechanism of this hypothesis needs to be further elucidated. With the progress of artificial intelligence, it is more likely to solve this problem through using artificial neural networks to perform temporal waveform data analysis and to construct biophysical computational models. This review focuses on current knowledge regarding the anesthetic mechanism of propofol, an intravenous general anesthetic, by constructing biophysical computational models.

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.

Artificial intelligence in perioperative medicine - a narrative review

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. AI models for perioperative risk stratification, intraoperative event prediction, biosignal analyses, and intensive care medicine have been developed in the field of perioperative medicine. Some of these models have been validated using external datasets and randomized controlled trials. Once these models are implemented in electronic health record systems or software medical devices, they could help anesthesiologists improve clinical outcomes by accurately predicting complications and suggesting optimal treatment strategies in real-time. This review provides an overview of the AI techniques used in perioperative medicine and a summary of the studies that have been published using these techniques. Understanding these techniques will aid in their appropriate application in clinical practice.

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.

Age-dependent cross frequency coupling features from children to adults during general anesthesia

BACKGROUND

The frequency coupling characteristics in electroencephalogram (EEG) induced by anesthetics have been well studied in adults, but the investigation of the age-dependent cross frequency coupling features from children to adults is still lacking.

METHODS

We analyzed EEG signals recorded from pediatric to adult patients (n = 131), separated into six age groups: <1 year (n = 15), 1-3 years (n = 23), 3-6 years (n = 19), 6-12 years (n = 18), 12-18 years (n = 16), and 18-45 years (n = 40). Age related EEG power and cross frequency coupling analysis (phase amplitude coupling (PAC) and quadratic phase coupling) of data from maintenance of a surgical state of anesthesia (MOSSA) was conducted. Also, for patients of ages less than 6 years, we analyzed the performance of cross frequency coupling derived indices in distinguishing the states of wakefulness, MOSSA, and recovery of consciousness (ROC).

RESULTS

(1) During MOSSA, EEG power substantially increased with age from infancy to 3-6 years then decreased with age in the theta-gamma frequency bands. The infant group (<1 year) had the highest slow oscillation (SO) power among all age groups. (2) The distinct PAC pattern is absent in patients less than 1 year of age both in SO-alpha and delta-alpha frequency band coupling during propofol induced unconsciousness. The modulation index between delta and alpha oscillations in MOSSA increased with age. (3) Wavelet bicoherence derived indices reach their peaks in the 3-6 years group and then decrease with age growth. (4) The Diag_En index (normalized entropy of the diagonal bicoherence entries of the bicoherence matrix) performed the best at distinguishing different states for ages less than 6 years (p<0.05).

CONCLUSIONS

The combination of propofol induction and sevoflurane maintenance exhibited age-dependent EEG power spectra, PAC, and bicoherence, likely related to brain development. These observations suggest new rules for infant and child brain state monitoring during general anesthesia are needed.

Development and validation of a risk score for predicting postoperative delirium after major abdominal surgery by incorporating preoperative risk factors and surgical Apgar score

STUDY OBJECTIVE

To develop and validate a simple delirium-predicting scoring system in patients undergoing major abdominal surgery by incorporating preoperative risk factors and intraoperative surgical Apgar score (SAS).

DESIGN

Observational retrospective cohort study.

SETTING

A tertiary general hospital in China.

PATIENTS

1055 patients who received major abdominal surgery from January 2015 to December 2019.

MEASUREMENTS

We collected data on preoperative and intraoperative variables, and postoperative delirium. A risk scoring system for postoperative delirium in patients after major open abdominal surgery was developed and validated based on traditional logistic regression model. The elastic net algorithm was further developed and evaluated.

MAIN RESULTS

The incidence of postoperative delirium was 17.8% (188/1055) in these patients. They were randomly divided into the development (n = 713) and validation (n = 342) cohorts. Both the logistic regression model and the elastic net regression model identified that advanced age, arrythmia, hypoalbuminemia, coagulation dysfunction, mental illness or cognitive impairments and low surgical Apgar score are related with increased risk of postoperative delirium. The elastic net algorithm has an area under the receiver operating characteristic curve (AUROC) of 0.842 and 0.822 in the development and validation cohorts, respectively. A prognostic score was calculated using the following formula: Prognostic score = Age classification (0 to 3 points) + arrythmia + 2 * hypoalbuminemia + 2 * coagulation dysfunction + 4 * mental illness or cognitive impairments + (10-surgical Apgar score). The 22-point risk scoring system had good discrimination and calibration with an AUROC of 0.823 and 0.834, and a non-significant Hosmer-Lemeshow test P = 0.317 and P = 0.853 in the development and validation cohorts, respectively. The bootstrapping internal verification method (R = 1000) yielded a C-index of 0.822 (95% CI: 0.759-0.857).

CONCLUSION

The prognostic scoring system, which used both preoperative risk factors and surgical Apgar score, serves as a good first step toward a clinically useful predictive model for postoperative delirium in patients undergoing major open abdominal surgery.

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia

In current anesthesiology practice, anesthesiologists infer the state of unconsciousness without directly monitoring the brain. Drug- and patient-specific electroencephalographic (EEG) signatures of anesthesia-induced unconsciousness have been identified previously. We applied machine learning approaches to construct classification models for real-time tracking of unconscious state during anesthesia-induced unconsciousness. We used cross-validation to select and train the best performing models using 33,159 2s segments of EEG data recorded from 7 healthy volunteers who received increasing infusions of propofol while responding to stimuli to directly assess unconsciousness. Cross-validated models of unconsciousness performed very well when tested on 13,929 2s EEG segments from 3 left-out volunteers collected under the same conditions (median volunteer AUCs 0.99-0.99). Models showed strong generalization when tested on a cohort of 27 surgical patients receiving solely propofol collected in a separate clinical dataset under different circumstances and using different hardware (median patient AUCs 0.95-0.98), with model predictions corresponding with actions taken by the anesthesiologist during the cases. Performance was also strong for 17 patients receiving sevoflurane (alone or in addition to propofol) (median AUCs 0.88-0.92). These results indicate that EEG spectral features can predict unconsciousness, even when tested on a different anesthetic that acts with a similar neural mechanism. With high performance predictions of unconsciousness, we can accurately monitor anesthetic state, and this approach may be used to engineer infusion pumps to intelligibly respond to patients' neural activity.

[Artificial intelligence in neurocritical care]

Artificial intelligence (AI) has been introduced into medicine and an AI-assisted medicine will be the future that we should help to shape. In particular, supervised, unsupervised, and reinforcement learning will be the main methods to play a role in the implementation of AI. Severely ill patients admitted to the intensive care unit (ICU) are closely monitored in order to be able to quickly respond to any changes. These monitoring data can be used to train AI models to predict critical phases in advance, making an earlier reaction possible. To achieve this a large amount of clinical data are needed in order to train models and an external validation on independent cohorts should take place. Prospective studies with treatment of patients admitted to the ICU with AI assistance should show that they provide a benefit for patients. We present the most important resources from de-identified (anonymized) patient data on open-source use for AI research in intensive care medicine. The focus is on neurological diseases in the ICU, therefore, we provide an overview of existing models for prediction of outcome, vasospasms, intracranial pressure and levels of consciousness. To introduce the advantages of AI in the clinical routine, more AI-based models with larger datasets will be needed. To achieve this international cooperation is absolutely necessary. Clinical centers associated with universities are needed to provide a constant validation of applied models as these models can change during use or a bias can develop during the training. A strong commitment to AI research is important for Germany, not only with respect to academic achievements but also in the light of a rapidly growing influence of AI on the economy.

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

In this article, we present a real-time electroencephalogram (EEG) based depth of anesthesia (DoA) monitoring system in conjunction with a deep learning framework, AnesNET. An EEG analog front-end (AFE) that can compensate ±380-mV electrode DC offset using a coarse digital DC servo loop is implemented in the proposed system. The EEG-based MAC, EEGMAC, is introduced as a novel index to accurately predict the DoA, which is designed for applying to patients anesthetized by both volatile and intravenous agents. The proposed deep learning protocol consists of four layers of convolutional neural network and two dense layers. In addition, we optimize the complexity of the deep neural network (DNN) to operate on a microcomputer such as the Raspberry Pi 3, realizing a cost-effective small-size DoA monitoring system. Fabricated in 110-nm CMOS, the prototype AFE consumes 4.33 μW per channel and has the input-referred noise of 0.29 μVrms from 0.5 to 100 Hz with the noise efficiency factor of 2.2. The proposed DNN was evaluated with pre-recorded EEG data from 374 subjects administrated by inhalational anesthetics under surgery, achieving an average squared and absolute errors of 0.048 and 0.05, respectively. The EEGMAC with subjects anesthetized by an intravenous agent also showed a good agreement with the bispectral index value, confirming the proposed DoA index is applicable to both anesthetics. The implemented monitoring system with the Raspberry Pi 3 estimates the EEGMAC within 20 ms, which is about thousand-fold faster than the BIS estimation in literature.

An On-Chip Processor for Chronic Neurological Disorders Assistance Using Negative Affectivity Classification

Chronic neurological disorders (CND's) are lifelong diseases and cannot be eradicated, but their severe effects can be alleviated by early preemptive measures. CND's, such as Alzheimer's, Autism Spectrum Disorder (ASD), and Amyotrophic Lateral Sclerosis (ALS), are the chronic ailment of the central nervous system that causes the degradation of emotional and cognitive abilities. Long term continuous monitoring with neuro-feedback of human emotions for patients with CND's is crucial in mitigating its harmful effect. This paper presents hardware efficient and dedicated human emotion classification processor for CND's. Scalp EEG is used for the emotion's classification using the valence and arousal scales. A linear support vector machine classifier is used with power spectral density, logarithmic interhemispheric power spectral ratio, and the interhemispheric power spectral difference of eight EEG channel locations suitable for a wearable non-invasive classification system. A look-up-table based logarithmic division unit (LDU) is to represent the division features in machine learning (ML) applications. The implemented LDU minimizes the cost of integer division by 34% for ML applications. The implemented emotion's classification processor achieved an accuracy of 72.96% and 73.14%, respectively, for the valence and arousal classification on multiple publicly available datasets. The 2 x 3mm² processor is fabricated using a 0.18 μm 1P6M CMOS process with power and energy utilization of 2.04 mW and 16 μJ/classification, respectively, for 8-channel operation.

A Noninvasive Glucose Monitoring SoC Based on Single Wavelength Photoplethysmography

Conventional glucose monitoring methods for the growing numbers of diabetic patients around the world are invasive, painful, costly and, time-consuming. Complications aroused due to the abnormal blood sugar levels in diabetic patients have created the necessity for continuous noninvasive glucose monitoring. This article presents a wearable system for glucose monitoring based on a single wavelength near-infrared (NIR) Photoplethysmography (PPG) combined with machine-learning regression (MLR). The PPG readout circuit consists of a switched capacitor Transimpedance amplifier with 1 MΩ gain and a 10-Hz switched capacitor LPF. It allows a DC bias current rejection up to 20 μA with an input-referred current noise of 7.3 pA/√Hz. The proposed digital processor eliminates motion artifacts, and baseline drifts from PPG signal, extracts six distinct features and finally predicts the blood glucose level using Support Vector Regression with Fine Gaussian kernel (FGSVR) MLR. A novel piece-wise linear (PWL) approach for the exponential function is proposed to realize the FGSVR on-chip. The overall system is implemented using a 180 nm CMOS process with a chip area of 4.0 mm² while consuming 1.62 mW. The glucose measurements are performed for 200 subjects with R² of 0.937. The proposed system accurately predicts the sugar level with a mean absolute relative difference (mARD) of 7.62%.

Frontal-temporal functional connectivity of EEG signal by standardized permutation mutual information during anesthesia

Quantifying brain dynamics during anesthesia is an important challenge for understanding the neurophysiological mechanisms of anesthetic drug effect. Several single channel Electroencephalogram (EEG) indices have been proposed for monitoring anesthetic drug effect. The most commonly used single channel commercial index is the Bispectral index (BIS). However, this monitor has shown some drawbacks. In this study, a nonlinear functional connectivity measure named Standardized Permutation Mutual Information (SPMI) is proposed to describe communication between two-channel EEG signals at frontal and temporal brain regions during a controlled propofol-induced anesthesia and recovery design from eight subjects. The SPMI index has higher correlation with estimated propofol effect-site concentration and has better ability to distinguish three anesthetic states of patient than the other functional connectivity indexes (cross-correlation, coherence, phase analysis) and also the BIS index. Moreover, the SPMI index has a faster reaction to the effect of drug concentration, less variability at the consciousness state and better robustness to noise than BIS.