Hierarchical rule-based monitoring and fuzzy logic control for neuromuscular block

Applications of artificial intelligence in anesthesia: A systematic review

This review article examines the utility of artificial intelligence (AI) in anesthesia, with a focus on recent developments and future directions in the field. A total of 19,300 articles were available on the given topic after searching in the above mentioned databases, and after choosing the custom range of years from 2015 to 2023 as an inclusion component, only 12,100 remained. 5,720 articles remained after eliminating non-full text. Eighteen papers were identified to meet the inclusion criteria for the review after applying the inclusion and exclusion criteria. The applications of AI in anesthesia after studying the articles were in favor of the use of AI as it enhanced or equaled human judgment in drug dose decision and reduced mortality by early detection. Two studies tried to formulate prediction models, current techniques, and limitations of AI; ten studies are mainly focused on pain and complications such as hypotension, with a P value of <0.05; three studies tried to formulate patient outcomes with the help of AI; and three studies are mainly focusing on how drug dose delivery is calculated (median: 1.1% ± 0.5) safely and given to the patients with applications of AI. In conclusion, the use of AI in anesthesia has the potential to revolutionize the field and improve patient outcomes. AI algorithms can accurately predict patient outcomes and anesthesia dosing, as well as monitor patients during surgery in real time. These technologies can help anesthesiologists make more informed decisions, increase efficiency, and reduce costs. However, the implementation of AI in anesthesia also presents challenges, such as the need to address issues of bias and privacy. As the field continues to evolve, it will be important to carefully consider the ethical implications of AI in anesthesia and ensure that these technologies are used in a responsible and transparent manner.

Artificial intelligence and its clinical application in Anesthesiology: a systematic review

PURPOSE

Application of artificial intelligence (AI) in medicine is quickly expanding. Despite the amount of evidence and promising results, a thorough overview of the current state of AI in clinical practice of anesthesiology is needed. Therefore, our study aims to systematically review the application of AI in this context.

METHODS

A systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We searched Medline and Web of Science for articles published up to November 2022 using terms related with AI and clinical practice of anesthesiology. Articles that involved animals, editorials, reviews and sample size lower than 10 patients were excluded. Characteristics and accuracy measures from each study were extracted.

RESULTS

A total of 46 articles were included in this review. We have grouped them into 4 categories with regard to their clinical applicability: (1) Depth of Anesthesia Monitoring; (2) Image-guided techniques related to Anesthesia; (3) Prediction of events/risks related to Anesthesia; (4) Drug administration control. Each group was analyzed, and the main findings were summarized. Across all fields, the majority of AI methods tested showed superior performance results compared to traditional methods.

CONCLUSION

AI systems are being integrated into anesthesiology clinical practice, enhancing medical professionals' skills of decision-making, diagnostic accuracy, and therapeutic response.

Artificial Intelligence in Anesthesiology: Current Techniques, Clinical Applications, and Limitations

Artificial intelligence has been advancing in fields including anesthesiology. This scoping review of the intersection of artificial intelligence and anesthesia research identified and summarized six themes of applications of artificial intelligence in anesthesiology: (1) depth of anesthesia monitoring, (2) control of anesthesia, (3) event and risk prediction, (4) ultrasound guidance, (5) pain management, and (6) operating room logistics. Based on papers identified in the review, several topics within artificial intelligence were described and summarized: (1) machine learning (including supervised, unsupervised, and reinforcement learning), (2) techniques in artificial intelligence (e.g., classical machine learning, neural networks and deep learning, Bayesian methods), and (3) major applied fields in artificial intelligence.The implications of artificial intelligence for the practicing anesthesiologist are discussed as are its limitations and the role of clinicians in further developing artificial intelligence for use in clinical care. Artificial intelligence has the potential to impact the practice of anesthesiology in aspects ranging from perioperative support to critical care delivery to outpatient pain management.

An Adaptive Monitoring Scheme for Automatic Control of Anaesthesia in dynamic surgical environments based on Bispectral Index and Blood Pressure

During surgical procedures, bispectral index (BIS) is a well-known measure used to determine the patient's depth of anesthesia (DOA). However, BIS readings can be subject to interference from many factors during surgery, and other parameters such as blood pressure (BP) and heart rate (HR) can provide more stable indicators. However, anesthesiologist still consider BIS as a primary measure to determine if the patient is correctly anaesthetized while relaying on the other physiological parameters to monitor and ensure the patient's status is maintained. The automatic control of administering anesthesia using intelligent control systems has been the subject of recent research in order to alleviate the burden on the anesthetist to manually adjust drug dosage in response physiological changes for sustaining DOA. A system proposed for the automatic control of anesthesia based on type-2 Self Organizing Fuzzy Logic Controllers (T2-SOFLCs) has been shown to be effective in the control of DOA under simulated scenarios while contending with uncertainties due to signal noise and dynamic changes in pharmacodynamics (PD) and pharmacokinetic (PK) effects of the drug on the body. This study considers both BIS and BP as part of an adaptive automatic control scheme, which can adjust to the monitoring of either parameter in response to changes in the availability and reliability of BIS signals during surgery. The simulation of different control schemes using BIS data obtained during real surgical procedures to emulate noise and interference factors have been conducted. The use of either or both combined parameters for controlling the delivery Propofol to maintain safe target set points for DOA are evaluated. The results show that combing BIS and BP based on the proposed adaptive control scheme can ensure the target set points and the correct amount of drug in the body is maintained even with the intermittent loss of BIS signal that could otherwise disrupt an automated control system.

Performance analysis of extracted rule-base multivariable type-2 self-organizing fuzzy logic controller applied to anesthesia

We compare type-1 and type-2 self-organizing fuzzy logic controller (SOFLC) using expert initialized and pretrained extracted rule-bases applied to automatic control of anaesthesia during surgery. We perform experimental simulations using a nonfixed patient model and signal noise to account for environmental and patient drug interaction uncertainties. The simulations evaluate the performance of the SOFLCs in their ability to control anesthetic delivery rates for maintaining desired physiological set points for muscle relaxation and blood pressure during a multistage surgical procedure. The performances of the SOFLCs are evaluated by measuring the steady state errors and control stabilities which indicate the accuracy and precision of control task. Two sets of comparisons based on using expert derived and extracted rule-bases are implemented as Wilcoxon signed-rank tests. Results indicate that type-2 SOFLCs outperform type-1 SOFLC while handling the various sources of uncertainties. SOFLCs using the extracted rules are also shown to outperform those using expert derived rules in terms of improved control stability.

MUSCLE RELAXATION CONTROLLED BY AUTOMATED ADMINISTRATION OF CISATRACURIUM

In this paper, the muscle relaxant agent (i.e., cisatracurium) and three clinical control methods (i.e., 13 patients undergoing intermitted bolus control, 15 patients undergoing intensive manual control and 15 patients) undergoing automatic fuzzy logic control (FLC), were used for maintaining depth of muscle relaxation (DOM) during surgery. Cisatracurium, a muscle relaxation drug with long-term effect, low metabolic loading, but long delay time, is widely used in operating rooms and ICUs. Meanwhile, the rules for the FLC were developed from the experimental experience of intensive manual control after learning from 15 patient trials. According to experts' experimental experience, our FLC inputs were chosen from T1% error and trend of T1% which differ from other previous studies on eliminating the effect of time delay from cisatracurium. In individual clinical experimental results, the mean(SD) of the mean T1% error in 13 patients for intermitted bolus control, in 15 patients for intensive manual control, and in 15 patients for automatic control was 8.76(1.46), 1.65(1.67), and 0.48(1.43), respectively. The t test results show that automatic control is not significantly different from intensive manual control. The results show that a simple fuzzy logic controller derived from anesthetists ' clinical trials can provide good accuracy without being affected by the pharmacological time delay problem.

AN ADVISORY SYSTEM FOR PROPOFOL ANAESTHESIA AFTER DETERMINING THE SENSITIVITY OF THE PATIENT DURING THE INDUCTION STAGE

Determining the sensitivity of the patient (SOP) during the induction stage is important because it is related to the confidence of the anaesthetist in controlling this system. Not only does this stage involve no surgical disturbances or artifacts, it is also fast and dynamic and very suitable for identifying the response of the patient to the drug. Eight patients underwent major abdominal surgery during intravenous anaesthesia and were all classified as ASA physical status category 1 or 2. A personal computer was connected via the RS232 ports for the Dinamap (i.e., Critikon, Inc., USA) and the Graseby 3400 syringe pump (i.e., Graseby Medical Limited, UK). All the trials measured patients' systolic arterial pressure (SAP) and heart rate (HR) using a Dinamap instrument. The clinical signs (i.e., sweating (SW), lacrimation (LA), and pupil response (PR)) were observed and input regularly about 5 min by the anaesthetist. A Graseby 3400 syringe pump which can pump from 0.1 to 1200 ml/hr was used to infuse propofol. Fentanyl was injected manually by syringe according to the rule-base. Also, a hierarchical fuzzy logic monitoring and rule-based control advisory system is tested in this paper to assess the determining the patient's sensitivity in the induction stage. The patient sensitivity of the elicited rule-base from anaesthetists' experience has been tested with the 8 patients during induction stage. Therefore, the good recovery time between acceptable and fast was 75 % in 8 patients. And, the mean (SD) of recovery time was 8.13 ± 5.94 min. Furthermore, the monitoring depth of anaesthesia (DOA) in terms of deciding of the confidence of depth of anaesthesia (CDOA) has also been tested with the 8 patients during maintenance stage. The mean (SD) of the mean CDOA in 8 patients was 93.55 ± 5.80 %. We conclude that determining the SOP in the induction stage is important because it is related to the confidence of the anaesthetist in controlling this advisory system. But a longer series of patients is needed to refine the rule-bases of the SOP, and to see how widely they are applicable.

Comparison of the applicability of rule-based and self-organizing fuzzy logic controllers for sedation control of intracranial pressure pattern in a neurosurgical intensive care unit

This paper assesses the controller performance of a self-organizing fuzzy logic controller (SOFLC) in comparison with a routine clinical rule-base controller (RBC) for sedation control of intracranial pressure (ICP) pattern. Eleven patients with severe head injury undergoing different neurosurgeries in a neurosurgical intensive care unit (NICU) were divided into two groups. In all cases the sedation control periods lasted 1 h and assessments of propofol infusion rates were made at a frequency of once per 30 s. In the control group of 10 cases selected from 5 patients, a RBC was used, and in the experimental group of 10 cases selected from 6 patients, a self-organizing fuzzy logic controller was used. A SOFLC was derived from a fuzzy logic controller and allowed to generate new rules via self-learning beyond the initial fuzzy rule-base obtained from experts (i.e., neurosurgeons). The performance of the controllers was analyzed using the ICP pattern of sedation for 1 h of control. The results show that a SOFLC can provide a more stable ICP pattern by administering more propofol and changing the rate of delivery more often when rule-base modifications have been considered.

Fuzzy logic control for intracranial pressure via continuous propofol sedation in a neurosurgical intensive care unit

The major goal of this paper is to provide automatically continuous propofol sedation for patients with severe head injury, unconsciousness, and mechanical ventilation in order to reduce the effect of agitation on intracranial pressure (ICP) using fuzzy logic control in a neurosurgical intensive care unit (NICU). Seventeen patients were divided into three groups in which control was provided with three different controllers. Experimental control periods were of 60min duration in all cases. Group A used a conventional rule-based controller (RBC), Group B a fuzzy logic controller (FLC), and Group C a self-organizing fuzzy logic controller (SOFLC). The performance of the controllers was analyzed by ICP pattern of sedation. The ICP pattern of errors was analyzed for mean and root mean square deviation (RMSD) for the entire duration of control (i.e., 1h). The results indicate that FLC can easily mimic the rule-base of human experts (i.e., neurosurgeons) to achieve stable sedation similar to the RBC group. Furthermore, the results also show that a SOFLC can provide more stable sedation of ICP pattern because it can modify the fuzzy rule-base to compensate for inter-patient variations.

Control of Neuromuscular Blockade in the Presence of Sensor Faults

The problem of embedding sensor fault tolerance in feedback control of neuromuscular blockade is considered. For tackling interruptions of feedback measurements, a structure based upon Bayesian inference as well as a predictive filter is proposed. This algorithm is general and can be applied to different situations. Here, it is incorporated in an adaptive automatic system for feedback control of neuromuscular blockade using continuous infusion of muscle relaxants. A significant contribution consists in the experimental clinical testing of the algorithm in patients undergoing surgery.

Evaluation of a closed-loop muscle relaxation control system

Automatic muscle relaxation control may reduce anesthesiologists' workload freeing them for other patient care requirements. In this report we describe a muscle relaxation controller designed for routine clinical application using rocuronium and the train-of-four count. A muscle relaxation monitor (TOF Watch SX) was connected to a laptop computer running a controller algorithm program that communicates with a syringe pump to form a closed-loop muscle relaxation system. The control algorithm uses proportional-integral and lookup table components and is designed to avoid the usability restrictions of existing controllers. The controller is optimized using an objective method to avoid the uncertainties of ''hand-crafted'' controller algorithms. Controller target was train-of-four count 1 or 2 and controller performance was evaluated in 15 patients. During 39 hours of closed-loop control, 96.1% of all twitches recorded were in the target range. Average rocuronium infusion rate was 0.36 mg.kg(-1).h(-1) (sd 0.18 mg.kg(-1).h(-1)). We show that the controller remains useful even in the presence of disturbances that can arise in routine clinical conditions. The muscle relaxation controller maintained the target train-of-four count values and may serve as a basis for the design of hardware and user interfaces for closed-loop muscle relaxation control in clinical conditions.

Hipocrates: a robust system for the control of neuromuscular blockade

OBJECTIVE

Development of an automatic system (software package Hipocrates) for the control of neuromuscular blockade by continuous infusion of the non-depolarising types of muscle relaxant drugs presently used in anaesthesia, namely atracurium, cisatracurium, vecuronium and rocuronium.

METHODS

Hipocrates incorporates control strategies based upon classical, adaptive and robust control, as well as a wide range of noise reduction techniques and on-line adaptation to patient-specific characteristics. Therefore, the system provides strong robustness to inter- and intra-individual variability of the patients responses or unexpected circumstances and adaptation to the individual requirements.

RESULTS

The control system is easy to set up and to use in a clinical environment. It consists of a portable PC computer, a Datex AS/3 NMT sensor and a B/Braun compact perfusion pump. In the simulation mode the software package incorporates sophisticated generation of pharmacokinetic/pharmacodynamic models driven by simulated drug administration regimes (bolus, continuous infusion and a combination of both).

CONCLUSIONS

Hipocrates is an advanced standalone application for the control of neuromuscular blockade with a friendly graphic interface. It has been extensively validated, and it can be used on patients undergoing surgery as well as for simulation studies. Therefore Hipocrates also provides an excellent environment for education and training purposes.