Figure 5
Spectrogram comparison of deep hypnosis and N3 sleep stage. Comparison of 5-min EEG power spectrogram from 4 subjects during (A) N3 sleep state in SHHS and (B) dexmedetomidine deep hypnotic state in UMCG. We can clearly see large variability in the slowwave delta band (0-4 Hz) and spindle band (11-16 Hz) across subjects in both SHHS and UMCG data set. The following values were set to perform spectral estimation using multitaper spectral estimation via the chronux toolbox: length of the window T = 4 s with 0.1 s shift, time-bandwidth product TW = 3, number of tapers K = 5, and spectral resolution 2 W of 1.5 Hz. EEG indicates electroencephalogram; SHHS, Sleep Heart Health Study; TW, time-bandwidth product; UMCG, University Medical Center Groningen.
Source publication
Background:
Brain monitors tracking quantitative brain activities from electroencephalogram (EEG) to predict hypnotic levels have been proposed as a labor-saving alternative to behavioral assessments. Expensive clinical trials are required to validate any newly developed processed EEG monitor for every drug and combinations of drugs due to drug-sp...
Context in source publication
Context 1
... recent study by Akeju et al 11 demonstrated that dexmedetomidine infusion significantly increased N3 sleep stage in a dose-dependent manner when compared to natural sleep in 10 healthy volunteers. Though intrasubject variability in these EEG patterns is minimal, there is considerable intersubject variability (for both sleep and dexmedetomidine) due to factors such as sex, 30 age, 31,32 or genetic factors 33,34 ; an example is shown in Figure 5. Using large-scale EEG data and DL, we demonstrate that dexmedetomidine-induced deep hypnotic level is synonymous to N3 sleep stage. ...
Citations
... When the limits of human understanding have been superseded, machine learning can be particularly useful [8,9,[16][17][18]. For example, despite a thorough understanding of pharmacology, normal physiology [19], pathophysiology, and surgical factors [18,20], postinduction hypotension [21] still occurs at a surprisingly high rate, possibly because the number of variables involved is so vast and complex. Thus, such a problem is a prime target for machine learning. ...
Purpose Hypotension is a risk factor for adverse perioperative outcomes. Preoperative transthoracic echocardiography has been extended for preoperative risk assessment before noncardiac surgery. This study aimed to develop a machine learning model to predict postinduction hypotension risk using preoperative echocardiographic data and compared it with conventional statistic models. We also aimed to identify preoperative echocardiographic factors that cause postinduction hypotension. Methods In this retrospective observational study, we extracted data from electronic health records of patients aged >18 years who underwent general anesthesia at a single tertiary care center between April 2014 and September 2019. Multiple supervised machine learning classification techniques were used, with postinduction hypotension (mean arterial pressure
... Research in AI may eliminate the need to perform clinical trials on hypnosis level monitors by the use of deep learning models. [43] Automated closed loop anesthesia delivery (CLAD) involves hypnosis, analgesia, and muscle relaxant delivery systems incorporating hemodynamic feedback mechanisms being studied with promising results. Advances in noninvasive cardiac output monitoring, cerebral oximetry, EEG processing, and nociception assessment form the basis for CLAD. ...
Rapid advances in Artificial Intelligence (AI) have led to diagnostic, therapeutic, and intervention-based applications in the field of medicine. Today, there is a deep chasm between AI-based research articles and their translation to clinical anesthesia, which needs to be addressed. Machine learning (ML), the most widely applied arm of AI in medicine, confers the ability to analyze large volumes of data, find associations, and predict outcomes with ongoing learning by the computer. It involves algorithm creation, testing and analyses with the ability to perform cognitive functions including association between variables, pattern recognition, and prediction of outcomes. AI-supported closed loops have been designed for pharmacological maintenance of anesthesia and hemodynamic management. Mechanical robots can perform dexterity and skill-based tasks such as intubation and regional blocks with precision, whereas clinical-decision support systems in crisis situations may augment the role of the clinician. The possibilities are boundless, yet widespread adoption of AI is still far from the ground reality. Patient-related “Big Data” collection, validation, transfer, and testing are under ethical scrutiny. For this narrative review, we conducted a PubMed search in 2020-21 and retrieved articles related to AI and anesthesia. After careful consideration of the content, we prepared the review to highlight the growing importance of AI in anesthesia. Awareness and understanding of the basics of AI are the first steps to be undertaken by clinicians. In this narrative review, we have discussed salient features of ongoing AI research related to anesthesia and perioperative care.
... Hypnotherapy is to change the physical and mental state of the patient in the hypnotic state under the guidance of the therapist, so as to replace the negative thoughts with positive thoughts. Hypnotic analgesia is effective in childbirth, headache, etc. e key is not the type of pain, but the different hypnotic methods used according to the pain [6,7]. Pain will cause some stress reactions, such as fear, anxiety, and irritability; these reactions stimulate the sympathetic nerve to make it excited, and maternal body will release catecholamine, causing uterine vasoconstriction, which is not conducive to childbirth. ...
The objective of this paper is to study the curative effect of music combined with hypnosis on labor pains during childbirth. Based on the algorithm of data mining, we randomly selected 100 women who delivered babies in obstetric units from October 2020 to June 2021, set the control group and the observation group, obtained the relevant clinical data through comparison, and analyzed the value of music combined with hypnotic analgesia midwifery in obstetrics. The results showed that the number of spontaneous delivery cases in the observation group was higher than that in the control group (P<0.05) and the delivery time in the observation group was better than that in the control group (P<0.05). It is proved that music combined with hypnosis can effectively improve the rate of natural childbirth and shorten the overall labor time, so as to guarantee the health of mother and child.
... Recently, a novel PKPD model for Propofol has been proposed in [62], yet to be seen if applicable for optimizing closed loop control objectives. Furthermore, new evidence that brain activity modulates differently to noxious stimuli than to hypnotic states [63], enable artificial intelligence tools to predict sedation state of patients [64], [65]. ...
We are witnessing a notable rise in the translational use of information technology and control systems engineering tools in clinical practice. This paper empowers the computer based drug dosing optimization of general anesthesia management by means of multiple variables for patient state stabilization. The patient simulator platform is designed through an interdisciplinary combination of medical, clinical practice and systems engineering expertise gathered in the last decades by our team. The result is an open source patient simulator in Matlab/Simulink from Mathworks(R). Simulator features include complex synergic and antagonistic interaction aspects between general anesthesia and hemodynamic stabilization variables. The anesthetic system includes the hypnosis, analgesia and neuromuscular blockade states, while the hemodynamic system includes the cardiac output and mean arterial pressure. Nociceptor stimulation is also described and acts as a disturbance together with predefined surgery profiles from a translation into signal form of most commonly encountered events in clinical practice. A broad population set of pharmacokinetic and pharmacodynamic (PKPD) variables are available for the user to describe both intra- and inter-patient variability. This simulator has some unique features, such as: i) additional bolus administration from anesthesiologist, ii) variable time-delays introduced by data window averaging when poor signal quality is detected, iii) drug trapping from heterogeneous tissue diffusion in high body mass index patients. We successfully reproduced the clinical expected effects of various drugs interacting among the anesthetic and hemodynamic states. Our work is uniquely defined in current state of the art and first of its kind for this application of dose management problem in anesthesia. This simulator provides the research community with accessible tools to allow a systematic design, evaluation and comparison of various control algorithms for multi-drug dosing optimization objectives in anesthesia.
... 431 These robots use complex ML algorithms based on patient data (e.g., EEG monitor, blood pressure, heart rate, etc.) and pharmacokinetic features of drugs to provide the optimal drug dosage. The role of pharmacological robots and even more intelligent autonomous systems (i.e., cognitive robot, which can recognize crucial clinical state that requires human intervention) in the anesthesia field has been comprehensively overviewed by Cédrick et al. 432 Besides the robotic systems, ML applications assisted the clinicians 433 to monitor the drug-specific anesthetic states [434][435][436] and predict the adverse outcomes in anesthesia patients. [437][438][439] Similar to the anesthesia field, AI models have mainly utilized for clinical decision support in pain management. ...
Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML‐driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML‐powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state‐of‐the‐art of AI/ML‐guided CNS drug discovery, focusing on blood–brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.
... Moreover, it has been indicated that deep learning techniques for hypnotic state demonstrated feasibility to validate and verify the robustness of clinical hypothesis using large-scale EEG data instead of visual assessments using traditional EEG spectrogram. It has been also shown that deep learning models generally allows reliable monitoring of hypnosis levels in new patients whose data were not included in the training process, thus the system can be used ''out of the box'' [62]. ...
Automation empowers self-sustainable adaptive processes and personalized services in many industries. The implementation of the integrated healthcare paradigm built on Health 4.0 is expected to transform any area in medicine due to the lightning-speed advances in control, robotics, artificial intelligence, sensors etc. The two objectives of this article, as addressed to different entities, are: i) to raise awareness throughout the anesthesiologists about the usefulness of integrating automation and data exchange in their clinical practice for providing increased attention to alarming situations, ii) to provide the actualized insights of drug-delivery research in order to create an opening horizon towards precision medicine with significantly improved human outcomes. This article presents a concise overview on the recent evolution of closed-loop anesthesia delivery control systems by means of control strategies, depth of anesthesia monitors, patient modelling, safety systems, and validation in clinical trials. For decades, anesthesia control has been in the midst of transformative changes, going from simple controllers to integrative strategies of two or more components, but not achieving yet the breakthrough of an integrated system. However, the scientific advances that happen at high speed need a modern review to identify the current technological gaps, societal implications, and implementation barriers. This article provides a good basis for control research in clinical anesthesia to endorse new challenges for intelligent systems towards individualized patient care. At this connection point of clinical and engineering frameworks through (semi-) automation, the following can be granted: patient safety, economical efficiency, and clinicians’ efficacy.
... Dexmedetomidine sedation is characterized by slow oscillations (0-4 Hz) and spindle oscillations (12)(13)(14)(15)(16) Hz) similar to sleep spindles [2,4]. At clinically recommended doses, dexmedetomidine induces a light state of sedation during which the patient is arousable and has hemodynamic and respiratory stability [9]. ...
... In our previous study [12], we developed a novel datarepurposing framework to predict anesthetic drug-induced deep sedation state from sleep EEG using deep learning algorithms. This framework was designed to eliminate the necessity for new clinical trials for developing automatic sedation level monitors. ...
Study objectives
Dexmedetomidine induced electroencephalogram (EEG) patterns during deep sedation is comparable with natural sleep patterns. Using large scale EEG recordings and machine learning techniques, we investigated whether dexmedetomidine induced deep sedation indeed mimics natural sleep patterns.
Methods
We used EEG recordings from three sources in this study: 8707 overnight sleep EEG and 30 dexmedetomidine clinical trial EEG. Dexmedetomidine induced sedation levels were assessed using the Modified Observer’s Assessment of Alertness/ Sedation (MOAA/S) score. We extracted twenty-two spectral features from each EEG recording using a multitaper spectral estimation method. Elastic-net regularization method was used for feature selection. We compared the performance of several machine learning algorithms (logistic regression, support vector machine and random forest), trained on individual sleep stages, to predict different levels of the MOAA/S sedation state.
Results
The random forest algorithm trained on non-rapid eye movement stage 3 (N3) predicted dexmedetomidine induced deep sedation (MOAA/S = 0) with AUC > 0.8 outperforming other machine learning models. Power in the delta band (0-4Hz) was selected as an important feature for prediction in addition to power in theta (4-8 Hz) and beta (16-30Hz) bands.
Conclusions
Using a large scale EEG data-driven approach and machine learning framework, we show that dexmedetomidine induced deep sedation state mimics N3 sleep EEG patterns.
... Nagaraj et al 7 developed a machine-learning model to predict hypnotic levels using repurposed electroencephalogram data, and then externally validated the model using data collected for a second study. 7 Other articles describe the development of advanced machine-learning models that use continuous vital signs data to predict clinically significant deteriorations including hemorrhage, hypotension, bradycardia, and opioid-induced ataxic breathing. [8][9][10][11][12] Wang et al 13 report a proof-of-concept in manifold learning, an important new technique in the field. ...
Technological innovation has been closely intertwined with the growth of modern anesthesiology as a medical and scientific discipline. Anesthesia & Analgesia, the longest-running physician anesthesiology journal in the world, has documented key technological developments in the specialty over the past 100 years. What began as a focus on the fundamental tools needed for effective anesthetic delivery has evolved over the century into an increasing emphasis on automation, portability, and machine intelligence to improve the quality, safety, and efficiency of patient care.
