Propofol Anesthesia Depth Monitoring Based on Self-Attention and Residual Structure Convolutional Neural Network

Abstract

Background and Objective. To study the new method of selecting CNN+EEG index values, based on self-attention and residual structure of convolutional neural network, to deeply monitor propofol anesthesia. Methods. We compare nine index values, select CNN+EEG, which has good correlation with BIS index, as an anesthesia state observation index to identify the parameters of the model, and establish a model based on self-attention and dual resistructure convolutional neural network. The data of 93 groups of patients were selected and randomly grouped into three parts: training set, validation set, and test set, and compared the best and worst results predicted by BIS. Result. The best result is that the model’s accuracy of predicting BLS on the test set has an overall upward trend, eventually reaching more than 90%. The overall error shows a gradual decrease and eventually approaches zero. The worst result is that the model’s accuracy of predicting BIS on the test set has an overall upward trend. The accuracy rate is relatively stable without major fluctuations, but the final accuracy rate is above 70%. Conclusion. The prediction of BIS indicators by the deep learning method CNN algorithm shows good results in statistics.

DA-CNN-Driven Innovative Ideological Politics Education Management System

“…Convolutional neural network [22][23][24][25] is a multilayer feedforward neural network composed of input, hidden, and output layers. Suppose the convolutional network's input and output dimensions are m and 1, respectively, and the number of hidden layers is p. en, the mapping mathematical expression of the convolutional neural network is shown in…”

Chinese experts’ consensus on the application of intensive care big data

“…A single-center retrospective study in 2022 used machine learning and cluster analysis to provide guidance on antibiotic management in patients with critical symptoms ( 83 ). Another study in 2022 based on self-attention and residual structure of convolutional neural network (CNN) had a good predictive effect on anesthesia depth monitoring ( 84 ). The examples above illustrate the potential role of AI in guiding critical decisions in patients with critical symptoms.…”

Application of Machine Learning in Predicting Perioperative Outcomes in Patients with Cancer: A Narrative Review for Clinicians

“…ML enables improved predictive analytics throughout the perioperative continuum [12]. ML can incorporate a large number of independent variables from the various phases and domains of care to evaluate dependent variables such as postoperative ileus, surgical site infections, lengths of stay, readmission rates, and other postoperative outcomes [2,3,9,[13][14][15][16][17]. While it is challenging to determine if variables are genuinely independent of historical data collection, many are interdependent.…”

“…ML's value in predicting perioperative outcomes is its ability to train and test large amounts of complex data accurately, efficiently, and autonomously. The domain of artificial intelligence readily identifies patterns, trends, and abnormalities in real time for clinical decision-making support [8,14,[16][17][18][19].…”

“…This technology has been applied to various aspects of anesthesiology and perioperative medicine, such as preoperative assessment and intraoperative monitoring systems [1,13,14]. One example of SL being used in anesthesiology is using ML models for predicting post-surgical complications such as pulmonary compromise, cardiac arrest, or stroke [13,[16][17][18][19]. SL models can also be used for hemodynamic optimization based on individual patients' demographic and physiological parameters, including blood pressure, stroke volume variation, and heart rate variability, among others [13,16].…”