Anesthesia depth monitoring method and system, electronic equipment and storage medium

Abstract

The invention discloses an anesthesia depth monitoring method and system, electronic equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of an original electroencephalogram signal sequence, and obtaining a first smooth signal sequence; calculating according to the first smooth signal sequence to obtain a sample variance, establishing a regression model of the signal sequence according to the sample variance, and calculating the regression model according to a preset likelihood function to obtain a model parameter set; calculating the model parameter set according to a first preset formula to obtain a dynamic volatility index, and normalizing the dynamic volatility index to obtain the anesthesia depth; the electroencephalogram signals are smoothed, so that the smoothness and continuity of the signals are improved, the noise interference is reduced, and the monitoring accuracy is improved; a regression model is established, model parameters are solved, internal fluctuation characteristics of electroencephalogram signals are quantified, a dynamic fluctuation index is calculated to serve as a monitoring index of the anesthesia depth, and the monitoring accuracy and real-time performance are improved. The embodiment of the invention can be widely applied to the technical field of anesthesia monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia monitoring, and in particular to an anesthesia depth monitoring method, system, electronic equipment and storage medium. Background Art

[0002] Anesthesia depth monitoring is very important for anesthesia management. Accurate monitoring of anesthesia depth can effectively reduce the occurrence of anesthesia-related complications. Traditional anesthesia monitoring methods rely on drug dosage, patient physiological indicators and subjective reactions, etc., with low monitoring accuracy and low real-time performance. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide an anesthesia depth monitoring method, system, electronic device and storage medium, which can improve the monitoring accuracy and improve the real-time performance of monitoring.

[0004] To achieve the above object, an embodiment of the present invention provides a method for monitoring depth of anesthesia, the method comprising:

[0005] Preprocessing the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence;

[0006] Calculating a sample variance according to the first smoothed signal sequence, establishing a regression model according to the sample variance, and calculating the regression model according to a preset likelihood function to obtain a model parameter set;

[0007] Calculation is performed according to the first preset formula and the model parameter set to determine the dynamic volatility index; the dynamic volatility index is normalized to obtain the anesthesia depth.

[0008] In some embodiments, the preprocessing of the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence specifically includes:

[0009] Smoothing the original electroencephalogram signal sequence according to a preset window size to obtain a first signal sequence;

[0010] The first signal sequence is subjected to weighted regression processing according to a second preset formula to obtain the first smoothed signal sequence.

[0011] In some embodiments, performing weighted regression processing on the first signal sequence according to a second preset formula to obtain the first smoothed signal sequence specifically includes:

[0012] determining a target smoothing point according to the first signal sequence, and determining a plurality of signal points according to the target smoothing point and the first signal sequence;

[0013] Calculating according to the plurality of signal points and the target smoothing point to obtain a weight set; wherein the weight set includes weight values ​​corresponding to the plurality of signal points;

[0014] A weighted calculation is performed according to the observation values ​​corresponding to the plurality of signal points and the weight set to obtain a response variable value, and the observation value of the target smoothing point is updated according to the response variable value to obtain the first smoothed signal sequence.

[0015] In some embodiments, the calculation is performed based on the plurality of signal points and the target smoothing point to obtain a weight set, specifically including:

[0016] Performing difference calculation based on the target smooth point and the plurality of signal points to obtain a first distance set; wherein the first distance includes distances from the plurality of signal points to the target smooth point;

[0017] The weight set is obtained by performing index calculations according to the first distance set and preset parameters.

[0018] In some embodiments, the calculating the regression model according to a preset likelihood function to obtain a model parameter set specifically includes:

[0019] Determine the observed values ​​and conditional variance values ​​corresponding to a plurality of signal points according to the regression model; calculate according to a third preset formula, the observed values ​​and the conditional variance values ​​to obtain the log-likelihood values ​​corresponding to the plurality of signal points;

[0020] The mean of several log-likelihood values ​​is calculated to determine the overall log-likelihood value, and the baseline volatility parameter and the historical volatility influence parameter of the regression module are determined according to the overall log-likelihood value; the model parameter set is determined according to the baseline volatility parameter and the historical volatility influence parameter of the regression module.

[0021] In some embodiments, the calculating according to the first preset formula and the model parameter set to determine the dynamic volatility index specifically includes:

[0022] Determining a historical fluctuation impact parameter and a baseline volatility parameter according to the model parameter set, and calculating a ratio of the historical fluctuation impact parameter to the baseline volatility parameter;

[0023] The dynamic volatility index is determined by performing a logarithmic operation based on the first preset formula and the ratio.

[0024] In some embodiments, the regression model established according to the sample variance is as follows:

[0025]

[0026] in, is the conditional variance at time t, ω is the constant term, α1 is the coefficient of the standardized residual, is the residual at time t, β1 is the coefficient of conditional variance, is the conditional variance at time t-1.

[0027] To achieve the above object, another aspect of an embodiment of the present invention provides an anesthesia depth monitoring system, the system comprising:

[0028] The first module is used to preprocess the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence;

[0029] A second module is used to calculate the sample variance according to the first smooth signal sequence, establish a regression model according to the sample variance, and calculate the regression model according to a preset likelihood function to obtain a model parameter set;

[0030] The third module is used to calculate according to the first preset formula and the model parameter set to determine the dynamic volatility index; normalize the dynamic volatility index to obtain the anesthesia depth.

[0031] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned method when executing the computer program.

[0032] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0033] Implementation of the embodiments of the present invention includes the following beneficial effects: the embodiments provide a method, system, electronic device and storage medium for monitoring the depth of anesthesia, wherein the scheme obtains a first smoothed signal sequence by preprocessing the acquired original electroencephalogram signal sequence; calculates based on the obtained first smoothed signal sequence to obtain the sample variance corresponding to the signal sequence, establishes a regression model corresponding to the signal sequence based on the calculated sample variance, calculates the established regression model based on a preset likelihood function to obtain a model parameter set of the regression model; calculates the calculated model parameter set based on a first preset formula to obtain a dynamic volatility index, normalizes the obtained dynamic volatility index to obtain anesthesia depth; improves the smoothness and continuity of the signal, reduces noise interference and improves the accuracy of anesthesia depth monitoring by smoothing the electroencephalogram signal; quantifies the intrinsic fluctuation characteristics of the electroencephalogram signal by establishing a regression model and solving the model parameters of the regression model, and then calculates the dynamic volatility index as a monitoring indicator of anesthesia depth, thereby improving the accuracy and real-time performance of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the steps of a method for monitoring depth of anesthesia provided by an embodiment of the present invention;

[0035] Figure 2 This is a schematic flow chart of the steps of preprocessing in a method for monitoring depth of anesthesia provided by an embodiment of the present invention;

[0036] Figure 3 It is a schematic flow chart of the steps of performing local weighted regression processing in a method for monitoring depth of anesthesia provided by an embodiment of the present invention;

[0037] Figure 4 It is a schematic flow chart of the steps of determining a weight set in a method for monitoring depth of anesthesia provided by an embodiment of the present invention;

[0038] Figure 5 It is a schematic flow chart of the steps of determining a model parameter set in a method for monitoring depth of anesthesia provided by an embodiment of the present invention;

[0039] Figure 6 It is a schematic flow chart of the steps of determining a dynamic volatility index in a method for monitoring depth of anesthesia provided by an embodiment of the present invention;

[0040] Figure 7 It is a schematic diagram of a step flow of a specific embodiment provided by an embodiment of the present invention;

[0041] Figure 8(a) to Figure 8(c) A patient's EEG signal waveform diagram, a signal frequency diagram, and a dynamic volatility index change curve diagram provided by an embodiment of the present invention;

[0042] Fig. 9 is a box plot of the dynamic volatility index of sevoflurane anesthetic drug in a specific embodiment provided by an embodiment of the present invention;

[0043] Fig.10 is a structural block diagram of an anesthesia depth monitoring system provided by an embodiment of the present invention;

[0044] Fig.11 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The step numbers in the following embodiments are only provided for the convenience of explanation and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0046] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0047] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0048] Unless otherwise defined, all technical and scientific terms used in the embodiments of the present invention have the same meanings as those commonly understood by those skilled in the art of the present invention. The terms used in the embodiments of the present invention are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0049] Figure 1 is an optional flow chart of a method for monitoring depth of anesthesia provided by an embodiment of the present invention. Figure 1 The method may include but is not limited to steps S101 to S103.

[0050] Step S101, preprocessing the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence;

[0051] Step S102, calculating the sample variance according to the first smoothed signal sequence, establishing a regression model according to the sample variance, and calculating the regression model according to a preset likelihood function to obtain a model parameter set;

[0052] Step S103, calculating according to the first preset formula and the model parameter set to determine the dynamic volatility index; normalizing the dynamic volatility index to obtain the anesthesia depth.

[0053] In steps S101 to S103 shown in the embodiment of the present application, the EEG signal of the patient who needs to monitor the depth of anesthesia is collected by the signal acquisition device. Before the system analyzes the EEG signal and monitors the depth of anesthesia, it performs a series of preprocessing on the collected original EEG signal to reduce the interference caused by environmental factors and improve the smoothness and continuity of the signal, thereby improving the accuracy of the EEG signal; at the same time, by preprocessing the EEG signal, the real change trend of the signal is retained and the interpretability of the signal is improved; after the system preprocesses the collected original EEG signal, a first-order autoregressive variance model is established based on the EEG signal to capture the EEG signal. The fluctuation characteristics in the EEG signal are used to quantify the dynamic change information of the EEG signal. The baseline volatility parameters and historical fluctuation influence parameters of the model are obtained by solving the established first-order autoregressive variance model. The current fluctuation characteristics of the EEG signal and the influence of the historical EEG signal fluctuation on the current EEG signal fluctuation are quantified by the model parameters, and the intrinsic fluctuation characteristics of the current EEG signal are analyzed. The dynamic volatility index is calculated according to the calculated quantification parameters, and the index is used to comprehensively reflect the fluctuation changes of the EEG signal as the anesthesia depth corresponding to the current EEG signal. In some embodiments, the current anesthesia depth of the patient can be quantitatively evaluated by monitoring the dynamic changes of the dynamic volatility index.

[0054] In step S101 of some embodiments, the collected original EEG signal can be segmented according to a certain length, and the segmented original EEG signal can be analyzed to obtain the dynamic volatility index corresponding to each segment of the EEG signal to monitor the fluctuation of the anesthesia depth corresponding to the EEG signal. The EEG signal can also be collected and analyzed at a preset period to achieve regular monitoring of the anesthesia depth, but is not limited thereto.

[0055] See also Figure 2 In some embodiments, step S101 may include but is not limited to steps S201 to S202:

[0056] Step S201, smoothing the original electroencephalogram signal sequence according to a preset window size to obtain a first signal sequence;

[0057] Step S202: Perform weighted regression processing on the first signal sequence according to a second preset formula to obtain a first smoothed signal sequence.

[0058] In step S201 of some embodiments, when the device collects the neural electrical signals of the patient who needs anesthesia monitoring and generates the EEG signal sequence, there is inevitably a mean shift phenomenon, which affects the accuracy of the EEG signal analysis; the system performs moving average smoothing processing on the collected original EEG signal sequence to eliminate the mean shift and improve the accuracy of the EEG signal; in this embodiment, the window size is set to 5, and the collected original EEG signal is subjected to moving average smoothing processing according to the following formula to output a preliminary smoothed EEG signal sequence:

[0059]

[0060] Where N is the window size, t is the current time point, i is the number of steps the current data point is shifted forward, and X is the original EEG signal sequence.

[0061] In step S202 of some embodiments, the EEG signal after eliminating the mean offset is further smoothed or interpolated using the least squares method to reduce the impact of noise on the EEG signal sequence and retain the true change trend of the EEG signal to facilitate the subsequent extraction of the volatility characteristics of the EEG signal. In this embodiment, the target signal point that needs to be smoothed or interpolated in the EEG signal sequence after preliminary smoothing is determined, and the target signal point is subjected to local weighted regression processing to obtain a predicted value of the target signal point. The target signal point is interpolated or smoothed according to the obtained predicted value. The local smoothing processing is extended to a global smoothing processing of the EEG signal sequence to obtain a smoothed signal sequence that can be used for anesthesia depth monitoring.

[0062] See also Figure 3 In some embodiments, step S202 may include but is not limited to steps S301 to S303:

[0063] Step S301, determining a target smoothing point according to a first signal sequence, and determining a plurality of signal points according to the target smoothing point and the first signal sequence;

[0064] Step S302, performing calculations based on a number of signal points and a target smoothing point to obtain a weight set; wherein the weight set includes weight values ​​corresponding to a number of signal points;

[0065] Step S303, performing weighted calculation according to the observation values ​​and weight sets corresponding to the plurality of signal points to obtain a response variable value, and updating the observation value of the target smoothing point according to the response variable value to obtain a first smoothed signal sequence.

[0066] In step S301 of some embodiments, the system performs moving average smoothing on the original EEG signal. After eliminating the mean offset, there are still local fluctuation areas in the EEG signal due to noise interference or the effect of anesthetic drugs. The system processes these local areas, selects target points in the area for smoothing or interpolation, estimates the predicted value of the target point based on the observed values ​​of several points in the local area, and smoothes or interpolates the target point based on the predicted value to reduce the impact of noise interference and extract the signal fluctuation trend to improve signal smoothness and continuity.

[0067] In step S302 of some embodiments, the system selects several signal points for processing in a local area with the selected target point as the center, and adjusts the weight corresponding to each signal point according to the distance from the selected signal point to the target point; by adjusting the weight, the influence of noise interference on the fluctuation of the EEG signal is reduced, while retaining the changing trend of the signal as much as possible to improve the accuracy of anesthesia monitoring.

[0068] In step S303 of some embodiments, the signal value of the target point is estimated according to the weight adjusted by each signal point and the observed value of each signal point; the target point is updated or interpolated according to the estimated signal value to smooth the signal fluctuation in the local area and capture the dynamic characteristics of the EEG signal at this location; in this embodiment, the system performs local weighted regression processing on the EEG signal according to the following formula:

[0069]

[0070] Among them, x0 is the signal point where the signal value needs to be estimated, is the signal estimated value of the signal point where the signal value needs to be estimated, x i is the i-th signal point with a known observed signal value, Y i is the signal value of the i-th signal point with a known observed signal value, W(x0,x i ) is the weight corresponding to the ith signal point of the known observed signal value, and n is the number of signal points of the known observed signal value.

[0071] Or, the above mentioned formula can be adjusted according to the weight of each signal point to obtain the following formula; the system can perform local weighted regression processing according to this formula:

[0072]

[0073] Among them, S is the weighted average, n is the number of signal points with known observed signal values, and W(x0,x i ) is the weight corresponding to the i-th signal point of the known observed signal value, Y i is the signal value of the i-th signal point with a known observed signal value.

[0074] See also Figure 4 In some embodiments, step S302 may include but is not limited to steps S401 to S402:

[0075] Step S401, performing difference calculation based on a target smooth point and a plurality of signal points to obtain a first distance set; wherein the first distance includes distances from a plurality of signal points to the target smooth point;

[0076] Step S402, performing index calculations according to the first distance set and preset parameters to obtain a weight set.

[0077] In step S401 of some embodiments, the system calculates the weight of each signal point selected for weighted regression before performing local weighted regression processing on the EEG signal; in this embodiment, the weight of each signal point is determined based on the distance, and a bandwidth parameter is set to control the speed at which the weight decays with the change of the distance from each signal point to the target point, so as to adjust the weight of each signal point.

[0078] In step S402 of some embodiments, the weight of each signal point is calculated according to the distance from each signal point to the target point and the set bandwidth parameter and the following formula:

[0079]

[0080] Among them, W(x0,x i ) is the weight corresponding to the i-th signal point with known observed signal value, x0 is the signal point whose signal value needs to be estimated, and x i is the ith signal point of the known observed signal value, and τ is the bandwidth parameter.

[0081] See also Figure 5 In some embodiments, step S102 may include but is not limited to steps S501 to S502:

[0082] Step S501, determining the observed values ​​and conditional variance values ​​corresponding to a number of signal points according to the regression model; calculating according to the third preset formula, the observed values ​​and the conditional variance values ​​to obtain the log-likelihood values ​​corresponding to the number of signal points;

[0083] Step S502, calculate the mean based on several log-likelihood values ​​to determine the overall log-likelihood value, determine the baseline volatility parameter and historical volatility impact parameter of the regression module based on the overall log-likelihood value; determine the model parameter set based on the baseline volatility parameter and historical volatility impact parameter of the regression module.

[0084] In step S501 of some embodiments, the system establishes a first-order autoregressive model based on the smoothed EEG signal, and then performs model fitting on the first-order autoregressive model according to a preset log-likelihood function to solve the parameters in the model; in this embodiment, the smoothed signal sequence is input into the following model,

[0085]

[0086] in, is the conditional variance at time t, ω is the constant term, α1 is the coefficient of the standardized residual, is the residual at time t, β1 is the coefficient of conditional variance, is the conditional variance at time t-1; select the starting point of the model analysis, calculate the conditional variance values ​​corresponding to several consecutive moments, and calculate the log-likelihood value corresponding to each moment based on the calculated conditional variance value and the observed values ​​at several consecutive moments based on the following formula:

[0087]

[0088] Among them, l t is the log-likelihood value of the signal sequence at time t, σ t is the conditional variance of the signal sequence at time t, y t is the value of the signal sequence at time t.

[0089] In step S502 of some embodiments, after obtaining the log-likelihood values ​​of several consecutive moments through the above formula, the system processes them according to the maximum likelihood function, calculates the overall log-likelihood value, solves the baseline volatility parameter and the historical volatility influence parameter of the model according to the overall log-likelihood value, and extracts the volatility characteristics of the signal sequence in these several consecutive moments; in this embodiment, the system calculates the overall log-likelihood value according to the following formula:

[0090]

[0091] Among them, L(γ) is the overall log-likelihood value, l t is the log-likelihood value of the signal sequence at time t, γ is the model parameter, including α1 and β1, and T is the number of signal points used for model fitting.

[0092] See also Figure 6 In some embodiments, step S103 may include but is not limited to steps S601 to S602:

[0093] Step S601, determining a historical volatility impact parameter and a baseline volatility parameter according to a model parameter set, and calculating a ratio of the historical volatility impact parameter to the baseline volatility parameter;

[0094] Step S602, performing logarithmic operation according to the first preset formula and the ratio to determine the dynamic volatility index.

[0095] In step S601 of some embodiments, the system extracts the volatility characteristics of the signal sequence in several consecutive moments and quantifies them into two model parameters of a first-order autoregressive model; the system calculates a ratio based on the model parameters, and calculates dynamic volatility changes based on the ratio to capture the dynamic characteristics of the patient's brain activity under anesthesia, and then determines the depth of anesthesia under the action of anesthetic drugs.

[0096] In step S602 of some embodiments, the system calculates the dynamic volatility index according to the following formula, which can quantify the patient's anesthesia state in the current time period. By calculating the dynamic volatility index of several consecutive time periods and monitoring the change trend of the index in real time, the patient's anesthesia state can be determined in real time:

[0097]

[0098] Where DVI is the dynamic volatility index, T is the number of signal points used for model fitting, and α1 and β1 are model parameters.

[0099] The following is a detailed description and explanation of the solution of the embodiment of the present invention in conjunction with a specific application example:

[0100] See also Figure 7 Before the operation, the patient is anesthetized with sevoflurane, and the original EEG signal of the patient is collected by relevant equipment, as shown in Figure 8(a), and sent to the system for analysis; the system receives the original EEG signal sent by the collection device, divides the original EEG signal into several sub-signal sequences of equal length according to a certain length, and then performs moving average processing on the divided sub-signal sequences to smooth the sub-signal sequences to obtain a first signal sequence; performs local weighted regression processing on the first signal sequence, performs interpolation processing on the local signal fluctuation area in the first signal sequence to reduce noise interference and capture signal fluctuation characteristics to obtain a second signal sequence, as shown in Figure 8(b); the system establishes a The first-order autoregressive variance model is established, and based on the user-defined negative log-likelihood function, the quasi-Newton method is used to optimize the estimation of the model parameters of the established first-order autoregressive variance model, and the model parameters of the established model are obtained to quantify the intrinsic characteristics of the signal fluctuations of each sub-signal sequence. The system calculates the dynamic volatility index according to the calculated model parameters, and evaluates the anesthesia depth according to the dynamic volatility index. The dynamic volatility index change curve of the electroencephalogram signal is plotted according to the dynamic volatility index calculated for each sub-signal sequence as shown in Figure 8(c). According to Figure 8(c), the changes in the patient's consciousness state under the action of anesthetic drugs can be obtained. By performing statistical analysis on the change curve of the dynamic volatility index, a plot is made as shown in Figure 8(c). Fig. 9The box plot shown in the figure shows that the dynamic volatility index level of patients under different anesthesia states of sevoflurane is significantly lower in the unconscious and recovery states than in the awake state. The box plot can be used to accurately quantify the anesthesia depth of patients under sevoflurane and can be extended to other patients.

[0101] The implementation of the embodiment of the present invention includes the following beneficial effects: the embodiment provides an anesthesia depth monitoring method, system, electronic device and storage medium, the scheme obtains a first smoothed signal sequence by preprocessing the acquired original electroencephalogram signal sequence; calculates according to the obtained first smoothed signal sequence to obtain the sample variance corresponding to the signal sequence, establishes a regression model corresponding to the signal sequence according to the calculated sample variance, calculates the established regression model according to a preset likelihood function, and obtains a model parameter set of the regression model; calculates the calculated model parameter set according to a first preset formula to obtain a dynamic volatility index, The obtained dynamic volatility index is normalized to obtain the anesthesia depth; the electroencephalogram signal is smoothed to improve the smoothness and continuity of the signal, reduce noise interference, and improve the accuracy of anesthesia depth monitoring; a regression model is established and the model parameters of the regression model are solved to quantify the intrinsic fluctuation characteristics of the electroencephalogram signal, and then the dynamic volatility index is calculated as a monitoring indicator of the anesthesia depth, thereby improving the accuracy and real-time nature of monitoring and reducing the risk of misjudgment; anesthesia depth monitoring is performed based on electroencephalogram signals, thereby improving the objectivity and interpretability of anesthesia monitoring, and at the same time improving the adaptability of the monitoring method, which can be widely used in different scenarios.

[0102] like Fig.10 As shown, an embodiment of the present invention further provides an anesthesia depth monitoring system, which can implement the above-mentioned anesthesia depth monitoring method, and the system includes:

[0103] The first module is used to preprocess the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence;

[0104] A second module is used to calculate the sample variance according to the first smooth signal sequence, establish a regression model according to the sample variance, and calculate the regression model according to a preset likelihood function to obtain a model parameter set;

[0105] The third module is used to calculate according to the first preset formula and the model parameter set to determine the dynamic volatility index; normalize the dynamic volatility index to obtain the anesthesia depth.

[0106] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0107] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned anesthesia depth monitoring method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0108] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0109] See also Fig.11 , Fig.11 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0110] The processor 1101 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0111] The memory 1102 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1102 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1102, and the processor 1101 is called to execute a method for monitoring the depth of anesthesia in the embodiment of this application;

[0112] Input / output interface 1103, used to implement information input and output;

[0113] The communication interface 1104 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0114] A bus 1105 that transmits information between various components of the device (e.g., the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104);

[0115] The processor 1101 , the memory 1102 , the input / output interface 1103 and the communication interface 1104 are connected to each other in communication within the device via the bus 1105 .

[0116] Among them, the memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. The memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a remote memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0117] It can be seen that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0118] In addition, the embodiment of the present application also discloses a computer program product or a computer program, and the computer program product or the computer program is stored in a computer-readable storage medium. The processor of the computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the above method. Similarly, the contents in the above method embodiment are all applicable to the storage medium embodiment, and the functions specifically implemented by the storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method embodiment.

[0119] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned anesthesia depth monitoring method is implemented.

[0120] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0121] It is understood that all or some steps and systems in the disclosed method above can be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0122] The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for monitoring depth of anesthesia, characterized in that: The method comprises: Preprocessing the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence; Calculating a sample variance according to the first smoothed signal sequence, establishing a regression model according to the sample variance, and calculating the regression model according to a preset likelihood function to obtain a model parameter set; Calculation is performed according to the first preset formula and the model parameter set to determine the dynamic volatility index; the dynamic volatility index is normalized to obtain the anesthesia depth.

2. The method according to claim 1, characterized in that The preprocessing of the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence specifically includes: Smoothing the original electroencephalogram signal sequence according to a preset window size to obtain a first signal sequence; The first signal sequence is subjected to weighted regression processing according to a second preset formula to obtain the first smoothed signal sequence.

3. The method according to claim 2, characterized in that The performing weighted regression processing on the first signal sequence according to the second preset formula to obtain the first smoothed signal sequence specifically includes: determining a target smoothing point according to the first signal sequence, and determining a plurality of signal points according to the target smoothing point and the first signal sequence; Calculating according to the plurality of signal points and the target smoothing point to obtain a weight set; wherein the weight set includes weight values ​​corresponding to the plurality of signal points; A weighted calculation is performed according to the observation values ​​corresponding to the plurality of signal points and the weight set to obtain a response variable value, and the observation value of the target smoothing point is updated according to the response variable value to obtain the first smoothed signal sequence.

4. The method according to claim 3, characterized in that The step of calculating according to the plurality of signal points and the target smoothing point to obtain a weight set specifically includes: Performing difference calculation based on the target smooth point and the plurality of signal points to obtain a first distance set; wherein the first distance includes distances from the plurality of signal points to the target smooth point; The weight set is obtained by performing index calculations according to the first distance set and preset parameters.

5. The method according to claim 1, characterized in that The step of calculating the regression model according to a preset likelihood function to obtain a model parameter set specifically includes: Determine the observed values ​​and conditional variance values ​​corresponding to a plurality of signal points according to the regression model; calculate according to a third preset formula, the observed values ​​and the conditional variance values ​​to obtain the log-likelihood values ​​corresponding to the plurality of signal points; The mean of several log-likelihood values ​​is calculated to determine the overall log-likelihood value, and the baseline volatility parameter and the historical volatility influence parameter of the regression module are determined according to the overall log-likelihood value; the model parameter set is determined according to the baseline volatility parameter and the historical volatility influence parameter of the regression module.

6. The method according to claim 1, characterized in that The calculating according to the first preset formula and the model parameter set to determine the dynamic volatility index specifically includes: Determining a historical volatility impact parameter and a baseline volatility parameter according to the model parameter set, and calculating a ratio of the historical volatility impact parameter to the baseline volatility parameter; The dynamic volatility index is determined by performing a logarithmic operation based on the first preset formula and the ratio.

7. The method according to claim 1, characterized in that The regression model established according to the sample variance is as follows: in, is the conditional variance at time t, ω is the constant term, α1 is the coefficient of the standardized residual, is the residual at time t, β1 is the coefficient of conditional variance, is the conditional variance at time t-1.

8. An anesthesia depth monitoring system, characterized in that: include: The first module is used to preprocess the acquired original electroencephalogram signal sequence to obtain a first smoothed signal sequence; A second module is used to calculate the sample variance according to the first smooth signal sequence, establish a regression model according to the sample variance, and calculate the regression model according to a preset likelihood function to obtain a model parameter set; A third module is used to calculate according to the first preset formula and the model parameter set to determine the dynamic volatility index; The dynamic volatility index was normalized to obtain the depth of anesthesia.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to perform the method according to any one of claims 1 to 7 when executed by the processor.

Images