Search

This study was undertaken to determine whether artificial neural network (ANN) processing of mid-latency auditory evoked potentials (MLAEPs) can identify different anesthetic states during propofol anesthesia, and to determine those parameters that are most useful in the identification process. Twenty-one patients undergoing elective abdominal surgery were studied. To maintain general anesthesia, the patients received propofol (3-5 mgkg(-1) h(-1) intravenously). Epidural analgesia at the level of T4-5 blocked painful stimuli. MLAEP was recorded continuously with patients awake, during induction, during maintenance of general anesthesia, and during emergence until the patients were recovered from anesthesia. Latencies of the 5 MLAEP peaks and three peak to peak amplitudes were measured, along with hemodynamic parameters (heart rate, systolic, and diastolic arterial blood pressure). Four-layer ANNs were used to model the relationship between the parameters of the MLAEP and the four different states (awake, adequate anesthesia, during/before intraoperative movement, and emergence from anesthesia). The best identification accuracy was obtained using only the five latencies. The combination of five latencies and three amplitudes did not improve the identification accuracy. Use of the only the three hemodynamic parameters produced a much poorer identification. This study suggests that the MLAEP has useful information for identifying different anesthetic states, especially in its latencies. A nonlinear discrimination approach, such as the ANN, can effectively capture the relation between the MLAEP patterns and the different states of anesthesia.

A new approach to predicting movement during anaesthesia by using complexity analysis of electroencephalograms (EEG) signals is presented. The raw EEG signal is first decomposed into six consecutive different scaling components by wavelet transform on the basis of its self-similarity. The Lempel-Ziv complexity measures C(n) are extracted from the raw EEG and its corresponding components by complexity analysis. Prediction of movement during anaesthesia is then made by a four-layer artificial neural network (ANN) using the C(n)s. The combination of these three different approaches enables the system to address the non-analytical, non-stationary, non-linear and dynamical properties of the EEG. From 20 dog experiments, 109 distinct EEG recordings are collected under isoflurane anaesthesia. Testing the ANN using the 'drop one dog' method, the performance obtained for the system in detecting movement is: sensitivity 88%, specificity 97% and accuracy 92%. Comparisons with other methods, such as spectral edge frequency, median frequency and principal component analysis, show that the proposed system has a certain advantage. This new method is computationally fast and well suited for realtime clinical implementation.

The objective of this study was to design and evaluate a methodology for estimating the depth of anesthesia in a canine model that integrates electroencephalogram (EEG)-derived autoregressive (AR) parameters, hemodynamic parameters, and the alveolar anesthetic concentration. Using a parameters, and the alveolar anesthetic concentration. Using a parametric approach, two separate AR models of order ten were derived for the EEG, one from the third-order cumulant sequence and the other from the autocorrelation lags of the EEG. Since the anesthetic dose versus depth of anesthesia curve is highly nonlinear, a neural network (NN) was chosen as the basic estimator and a multiple NN approach was conceived which took hemodynamic parameters, EEG derived parameters, and anesthetic concentration as input feature vectors. Since the estimation of the depth of anesthesia involves cognitive as well as statistical uncertainties, a fuzzy integral was used to integrate the individual estimates of the various networks and to arrive at the final estimate of the depth of anesthesia. Data from 11 experiments were used to train the NN's which were then tested on nine other experiments. The fuzzy integral of the individual NN estimates (when tested on 43 feature vectors from seven of the nine test experiments) classified 40 (93%) of them correctly, offering a substantial improvement over the individual NN estimates.

A fully automated system was developed for the depth of anesthesia estimation and control with the intravenous anesthetic, Propofol. The system determines the anesthesia depth by assessing the characteristics of the mid-latency auditory evoked potentials (MLAEP). The discrete time wavelet transformation was used for compacting the MLAEP which localizes the time and the frequency of the waveform. Feature reduction utilizing step discriminant analysis selected those wavelet coefficients which best distinguish the waveforms of those responders from the nonresponders. A total of four features chosen by such analysis coupled with the Propofol effect-site concentration were used to train a four-layer artificial neural network for classifying between the responders and the nonresponders. The Propofol is delivered by a mechanical syringe infusion pump controlled by Stanpump which also estimates the Propofol effect-site and plasma concentrations using a three-compartment pharmacokinetic model with the Tackley parameter set. In the animal experiments on dogs, the system achieved a 89.2% accuracy rate for classifying anesthesia depth. This result was further improved when running in real-time with a confidence level estimator which evaluates the reliability of each neural network output. The anesthesia level is adjusted by scheduled incrementation and a fuzzy-logic based controller which assesses the mean arterial pressure and/or the heart rate for decrementation as necessary. Various safety mechanisms are implemented to safeguard the patient from erratic controller actions caused by external disturbances. This system completed with a friendly interface has shown satisfactory performance in estimating and controlling the depth of anesthesia.

This paper shows the development of a system to control inhalation anesthetic concentration delivered to a patient based upon that patient's midlatency auditory evoked potentials (MLAEP's). It was developed and tested in dogs by determining response to the supramaximal stimulus of tail clamping. Prior to tail clamp, the MLAEP was recorded along with inhalational anesthetic concentration and classified as responders or nonresponders as determined by tail clamping. This was performed at a number of different anesthetic levels to obtain a data training set. The MLAEP's were compacted by means of discrete time wavelet transform (DTWT), and together with anesthetic concentration value, a stepwise discriminant analysis (SDA) was performed to determine those features which could separate responders from nonresponders. It was determined that only three features were necessary for this recognition. These features were then used to train a four-layer artificial neural network (ANN) to separate the responders from nonresponders. The network was tested using a separate set of data, resulting in a 93% recognition rate in the anesthetic transition zone between responders and nonresponders, and 100% recognition rate outside this zone. The anesthetic controller used this ANN combined with fuzzy logic and rule-based control. A set of ten animal experiments were performed to test the robustness of this controller. Acceptable clinical performance was obtained, showing the feasibility of this approach.

The need for a reliable method of predicting movement during anesthesia has existed since the introduction of anesthesia. This paper proposes a recognition system, based on the autoregressive (AR) modeling and neural network analysis of the electroencephalograph (EEG) signals, to predict movement following surgical stimulation. The input to the neural network will be the AR parameters, the hemodynamic parameters blood pressure (BP) and heart rate (HR), and the anesthetic concentration in terms of the minimum alveolar concentration (MAC). The output will be the prediction of movement. Design of the system and results from the preliminary tests on dogs are presented in this paper. The experiments were carried out on 13 dogs at different levels of halothane. Movement prediction was tested by monitoring the response to tail clamping, which is considered to be a supramaximal stimulus in dogs. The EEG data obtained prior to tail clamping was processed using a tenth-order AR model and the parameters obtained were used as input to a three-layer perceptron feedforward neural network. Using only AR parameters the network was able to correctly classify subsequent movement in 85% of the cases as compared to 65% when only hemodynamic parameters were used as the input to the network. When both the measures were combined, the recognition rate rose to greater than 92%. When the anesthetic concentration was added as an input the network could be considerably simplified without sacrificing classification accuracy. This recognition system shows the feasibility of using the EEG signals for movement during anesthesia.