Anesthesia state monitoring method and system

Abstract

The invention provides an anesthesia state monitoring method and system, and the method comprises the steps: obtaining electroencephalogram signal data of a patient, and carrying out the preprocessing of the electroencephalogram signal data, so as to obtain processed signal data; performing de-noising processing on the processed signal data to obtain de-noised signal data; performing first feature extraction on the de-noised signal data to obtain first feature signal data; performing second feature extraction on the de-noised signal data to obtain second feature signal data; according to the method and the device, the data are subjected to denoising processing, features of multiple aspects in the data are extracted, rules in the data and feature data related to the anesthesia state are captured, and the anesthesia state monitoring value is calculated on the basis of the first feature signal data and the second feature signal data, and the current anesthesia state of the patient is determined on the basis of the anesthesia state monitoring value. And the accuracy of anesthesia state monitoring is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of anesthesia state monitoring, and particularly relates to an anesthesia state monitoring method and system. Background Art

[0002] For some surgeries, general anesthesia or local anesthesia of patients needs to be carried out with anesthetic drugs. For the existing process of evaluating the anesthesia state of patients, there are generally two methods. The first is to judge the current anesthesia state of patients based on the experience of anesthesiologists combined with anesthetic drugs, and the second is to judge the current anesthesia state of patients through the electrocardiogram or other physical characteristics of patients. However, the above methods all have inaccurate judgment of the anesthesia state. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention provides an anesthesia state monitoring method and system to solve the technical problems in the prior art.

[0004] On the one hand, the present invention provides the following technical solution. An anesthesia state monitoring method includes: Obtaining electroencephalogram signal data of a patient, and preprocessing the electroencephalogram signal data to obtain processed signal data; Performing denoising processing on the processed signal data to obtain denoised signal data; Performing first feature extraction on the denoised signal data to obtain first feature signal data; Performing second feature extraction on the denoised signal data to obtain second feature signal data; Calculating an anesthesia state monitoring value based on the first feature signal data and the second feature signal data, and determining the current anesthesia state of the patient based on the anesthesia state monitoring value.

[0005] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention first obtains the electroencephalogram signal data of a patient, preprocesses the electroencephalogram signal data to obtain processed signal data; then performs denoising processing on the processed signal data to obtain denoised signal data; then performs first feature extraction on the denoised signal data to obtain first feature signal data; then performs second feature extraction on the denoised signal data to obtain second feature signal data; then calculates an anesthesia state monitoring value based on the first feature signal data and the second feature signal data, and determines the current anesthesia state of the patient based on the anesthesia state monitoring value. The present invention effectively eliminates the noise existing in the data by performing denoising processing on the data to improve the accuracy of subsequent monitoring, and the present invention extracts features in multiple aspects of the data to capture the rules in the data and the feature data related to the anesthesia state, further improving the accuracy of anesthesia state monitoring.

[0006] Preferably, the step of preprocessing the EEG signal data to obtain processed signal data includes: Successively perform baseline drift removal, respiratory artifact removal, singular signal removal, and frequency domain filtering on the target insulator image to obtain processed signal data.

[0007] Preferably, the step of denoising the processed signal data to obtain denoised signal data includes: Calculate the wavelet judgment threshold : ; In the formula, represents the standard deviation of Gaussian noise, represents the length of the processed signal data; Based on the wavelet judgment threshold Calculate the wavelet transform coefficient : ; In the formula, represents the wavelet coefficient of the high-frequency part; Based on the wavelet transform coefficient Perform wavelet denoising on the processed signal data to obtain denoised signal data.

[0008] Preferably, the step of extracting the first feature from the denoised signal data to obtain the first feature signal data includes: Select any two sets of denoised signal data, and convert the two sets of denoised signal data into a first data matrix and a second data matrix : ; ; In the formula, , respectively represent two sets of denoised signal data, represents the common source signal of the two sets of denoised signal data, , respectively represent the spatial patterns related to , , represents , 's common source spatial pattern; Calculate the first covariance matrix of the first data matrix and the second covariance matrix of the second data matrix: ; ; In the formula, Denote the sum of the elements on the diagonal of the matrix; Perform eigenvalue decomposition on the first covariance matrix and the second covariance matrix respectively to obtain the first eigenvector and the second eigenvector, and perform descending order arrangement of the eigenvalues based on the first eigenvector and the second eigenvector to obtain the first sorting matrix and the second sorting matrix; Perform principal component decomposition on the first sorting matrix and the second sorting matrix respectively to obtain the first decomposed eigenvector and the second decomposed eigenvector, and determine the first eigen-signal data based on the first decomposed eigenvector and the second decomposed eigenvector : ; In the formula, and represent the first decomposed eigenvector and the second decomposed eigenvector respectively, and represent the diagonal matrices composed of the eigenvalues of the first covariance matrix and the second covariance matrix respectively, represent the first eigenvector and the second eigenvector respectively, represents variance calculation.

[0009] Preferably, the step of performing second feature extraction on the denoised signal data to obtain the second eigen-signal data includes: Embed the denoised signal data into -dimensional space to obtain the embedded signal data, calculate the data distance between any two data in the embedded signal data, and determine the number of data whose data distance between any two data is less than the preset distance , and calculate the data ratio based on the number of data : ; In the formula, represents the number of data in the embedded signal data; Calculate the data ratio Calculate the eigenvalue under the -dimensional space : ; Repeat the process of eigenvalue calculation until the eigenvalue under the -dimensional space is obtained , and determine the first undetermined feature based on the eigenvalue and the eigenvalue : ; Based on the quantity of the data calculate the quantity mean value in the - dimensional space : ; Repeat the process of calculating the data mean value until obtaining the quantity mean value in the - dimensional space , and based on the quantity mean value and the quantity mean value calculate the second undetermined feature : ; Construct a phase space, determine the arrangement order of the embedded signal data in the phase space, and based on the arrangement order, determine the value set of the embedded signal. The value set includes values, and calculate the arrangement frequency of each arrangement order : ; In the formula, represents the frequency at which the arrangement order appears in the time series; Based on the arrangement frequency determine the third undetermined feature : ; Integrate the first undetermined feature , the second undetermined feature , and the third undetermined feature to obtain the second feature signal data.

[0010] Preferably, the steps of calculating the anesthesia state monitoring value based on the first feature signal data and the second feature signal data, and determining the current anesthesia state of the patient based on the anesthesia state monitoring value include: Determine the distribution value based on the denoised signal data ; Based on the distribution value , the first feature signal data, and the second feature signal data, calculate the anesthesia state monitoring value : ; In the formula, , are the first weight and the second weight respectively, is the first feature signal data, are the first undetermined feature, the second undetermined feature, and the third undetermined feature in the second feature signal data respectively; If the anesthesia state monitoring value is not greater than the first threshold, the current anesthesia state is the first state. If the anesthesia state monitoring value is greater than the first threshold and less than the second threshold, the current anesthesia state is the second state. If the anesthesia state monitoring value is not less than the second threshold, the current anesthesia state is the third state.

[0011] Preferably, the step of determining the distribution value based on the denoised signal data includes: Determining the correlation coefficient between the denoised signal data of different channels : ; In the formula, respectively represent the auto-power spectra of the denoised signal data of the th channel, represents the cross-power spectrum between the denoised signal data of the th channel; Based on the correlation coefficient determine the correlation matrix : ; In the formula, represents the correlation coefficient at frequency , represents the frequency band range, represents the element in the th row and th column of the correlation matrix, represents the number of correlation coefficients within ; Perform eigenvalue decomposition on the correlation matrix to obtain correlation eigenvalues; Use the amplitude-modulated Fourier algorithm to perform iterative resampling on the denoised signal data of different channels for several times to obtain several sampling matrices, perform eigenvalue decomposition on the several sampling matrices to obtain several sampling eigenvalues, and determine the average eigenvalue between the several sampling eigenvalues; Based on the correlation eigenvalues and the average eigenvalue, determine the final eigenvalue : ; In the formula, , respectively represent the correlation eigenvalue and the average eigenvalue of the th channel; Calculate the distribution value based on the final eigenvalue : .

[0012] In a second aspect, the present invention provides the following technical solution. An anesthesia state monitoring system, the system comprising: A processing module, configured to obtain electroencephalogram signal data of a patient, and preprocess the electroencephalogram signal data to obtain processed signal data; A denoising module, configured to perform denoising processing on the processed signal data to obtain denoised signal data; A first extraction module, configured to perform first feature extraction on the denoised signal data to obtain first feature signal data; A second extraction module, configured to perform second feature extraction on the denoised signal data to obtain second feature signal data; A monitoring module, configured to calculate an anesthesia state monitoring value based on the first feature signal data and the second feature signal data, and determine the current anesthesia state of the patient based on the anesthesia state monitoring value.

[0013] In a third aspect, the present invention provides the following technical solution. A computer, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the anesthesia state monitoring method as described above is implemented.

[0014] In a fourth aspect, the present invention provides the following technical solution. A storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the anesthesia state monitoring method as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of the anesthesia state monitoring method provided in Embodiment 1 of the present invention; Figure 2 It is a structural block diagram of the anesthesia state monitoring system provided in Embodiment 2 of the present invention; Figure 3 It is a schematic hardware structure diagram of a computer provided in another embodiment of the present invention.

[0017] The following will further describe the embodiments of the present invention with reference to the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0019] In the description of the embodiments of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.

[0020] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0021] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific situations.

[0022] Embodiment 1 In Embodiment 1 of the present invention, as Figure 1 shown, an anesthesia state monitoring method includes: S1. Obtain the electroencephalogram signal data of the patient, and preprocess the electroencephalogram signal data to obtain processed signal data; Among them, step S1 is specifically: Successively perform baseline drift removal, respiratory artifact removal, singular signal removal, and frequency domain filtering on the target insulator image to obtain processed signal data; Specifically, the above preprocessing process is a common method for electroencephalogram signal data processing, so it will not be elaborated here.

[0023] S2. Denoise the processed signal data to obtain denoised signal data; Among them, step S2 includes: S21. Calculate the wavelet judgment threshold : ; In the formula, represents the standard deviation of Gaussian noise, represents the length of the processed signal data.

[0024] S22. Based on the wavelet judgment threshold calculate the wavelet transform coefficients : ; In the formula, represents the wavelet coefficients of the high-frequency part.

[0025] S23. Based on the wavelet transform coefficients perform wavelet denoising on the processed signal data to obtain denoised signal data; Specifically, the wavelet denoising algorithm is a commonly used algorithm in the prior art, so it will not be elaborated here. However, the present invention improves the wavelet transform coefficients therein. For the wavelet transform denoising algorithm in the prior art, its coefficients are generally fixed coefficients. However, since the noise does not have the correlation of wavelets, the noise energy after transformation does not have a concentrated characteristic, which may lead to signal data being prone to oscillation. The improved wavelet transform coefficients provided by the present invention have a continuous derivative at the threshold point, which does not limit the normal operation of the wavelet algorithm and is convenient for processing, effectively improving the denoising effect.

[0026] S3. Perform first feature extraction on the denoised signal data to obtain first feature signal data; Among them, step S3 includes: S31. Select any two sets of denoised signal data and convert the two sets of denoised signal data into a first data matrix and a second data matrix : ; ; In the formula, , respectively represent two sets of denoised signal data, represents the common source signal of the two sets of denoised signal data, , respectively represent the spatial patterns related to , , represents , Common source space pattern.

[0027] S32. Calculate the first covariance matrix of the first data matrix and the second covariance matrix of the second data matrix : ; ; In the formula, represents the sum of the diagonal elements of the matrix.

[0028] S33. Respectively perform eigenvalue decomposition on the first covariance matrix , the second covariance matrix to obtain the first eigenvector and the second eigenvector, and perform eigenvalue descending order arrangement based on the first eigenvector and the second eigenvector to obtain the first sorting matrix and the second sorting matrix.

[0029] S34. Respectively perform principal component decomposition on the first sorting matrix and the second sorting matrix to obtain the first decomposed eigenvector and the second decomposed eigenvector, and determine the first eigen signal data based on the first decomposed eigenvector and the second decomposed eigenvector : ; In the formula, , respectively represent the first decomposed eigenvector and the second decomposed eigenvector, , respectively represent the diagonal matrices composed of the eigenvalues of the first covariance matrix and the second covariance matrix, respectively represent the first eigenvector and the second eigenvector, represents variance calculation; Specifically, the purpose of the first feature extraction is to extract the most discriminative and representative eigenvalues to improve the accuracy of anesthesia state monitoring.

[0030] S4. Perform second feature extraction on the denoised signal data to obtain second eigen signal data; Among them, the step S4 includes: S41. Embed the denoised signal data into -dimensional space to obtain embedded signal data, calculate the data distance between any two data in the embedded signal data, and determine the number of data whose data distance between any two data is less than the preset distance , and calculate the data ratio based on the number of data : ; In the formula, Indicates the number of data in the embedded signal data; S42. Calculate the data ratio Calculate The eigenvalues in the -dimensional space: ; S43. Repeat the process of eigenvalue calculation until obtaining the eigenvalues in the -dimensional space. Based on the eigenvalues and the eigenvalues determine the first undetermined feature : ; Specifically, the first undetermined feature is specifically a feature regarding the sequence information entropy.

[0031] S44. Based on the data quantity calculate the quantity mean value in the -dimensional space: ; S45. Repeat the process of data mean value calculation until obtaining the quantity mean value in the -dimensional space. Based on the quantity mean value and the quantity mean value calculate the second undetermined feature : ; Specifically, the second undetermined feature is specifically a feature regarding the difference relationship between the data in the sequence.

[0032] S46. Construct a phase space, determine the arrangement order of the embedded signal data in the phase space, and based on the arrangement order, determine the value set of the embedded signal. The value set includes values. Calculate the arrangement frequency of each arrangement order : ; In the formula, represents the frequency of the arrangement order appearing in the time series; S47. Based on the arrangement frequency determine the third undetermined feature : ; Specifically, the third undetermined feature is specifically a feature regarding the arrangement relationship and order of the data in the sequence.

[0033] S48. Synthesize the first undetermined feature , the second undetermined feature , and the third undetermined feature to obtain the second feature signal data.

[0034] S5. Calculate the anesthesia state monitoring value based on the first feature signal data and the second feature signal data, and determine the current anesthesia state of the patient based on the anesthesia state monitoring value.

[0035] Among them, the step S5 includes: S51. Determine the distribution value based on the denoised signal data ; Among them, the step S51 includes: S511. Determine the correlation coefficient between the denoised signal data of different channels : ; In the formula, respectively represent the auto-power spectrum of the denoised signal data of the th channel, represents the cross-power spectrum between the denoised signal data of the th channel.

[0036] S512. Determine the correlation matrix based on the correlation coefficient : : ; In the formula, represents the correlation coefficient at frequency , represents the frequency band range, represents the element in the th row and th column of the correlation matrix, represents the number of correlation coefficients within .

[0037] S513. Perform eigenvalue decomposition on the correlation matrix to obtain the correlation eigenvalues; Specifically, for all eigenvalue decomposition processes in the present invention, the EVD algorithm can be used.

[0038] S514. Use the amplitude-modulated Fourier algorithm to perform iterative resampling on the denoised signal data of different channels for several times to obtain several sampling matrices, perform eigenvalue decomposition on the several sampling matrices to obtain several sampling eigenvalues, and determine the average eigenvalue between the several sampling eigenvalues.

[0039] S515. Determine the final eigenvalue based on the correlation eigenvalue and the average eigenvalue : ; In the formula, and respectively represent the correlation eigenvalue and the average eigenvalue of the th channel.

[0040] S516. Calculate the distribution value based on the final eigenvalue : ; Specifically, the distribution value can reflect the synchronization of the data.

[0041] S52. Calculate the anesthesia state monitoring value based on the distribution value , the first characteristic signal data and the second characteristic signal data : ; In the formula, and are the first weight and the second weight respectively, is the first characteristic signal data, are the first undetermined characteristic, the second undetermined characteristic, and the third undetermined characteristic in the second characteristic signal data respectively; And before calculating the anesthesia state monitoring value, it is necessary to perform normalization processing on the distribution value, the first characteristic signal data, and the second characteristic signal data.

[0042] Specifically, in this embodiment, the first weight is 0.4 and the second weight is 0.3.

[0043] S53. If the anesthesia state monitoring value is not greater than the first threshold, the current anesthesia state is the first state. If the anesthesia state monitoring value is greater than the first threshold and less than the second threshold, the current anesthesia state is the second state. If the anesthesia state monitoring value is not less than the second threshold, the current anesthesia state is the third state; Specifically, when the anesthesia state monitoring value is not greater than the first threshold, it indicates that the patient is in a relatively clear state at this time. Therefore, the first state is the awake state. When the anesthesia state monitoring value is greater than the first threshold and less than the second threshold, it indicates that the patient is in an unconscious state at this time. Therefore, the second state is the deep anesthesia state. When the anesthesia state monitoring value When it is not less than the second threshold, it indicates that the patient is in a state of slow awakening after anesthesia at this time. Therefore, the third state is the recovery state, and the first threshold and the second threshold can be set according to actual parameters.

[0044] For the anesthesia state monitoring method provided in Embodiment 1 of the present invention, first, the electroencephalogram signal data of the patient is acquired, and the electroencephalogram signal data is preprocessed to obtain processed signal data; then, the processed signal data is denoised to obtain denoised signal data; then, the denoised signal data is subjected to first feature extraction to obtain first feature signal data; then, the denoised signal data is subjected to second feature extraction to obtain second feature signal data; then, an anesthesia state monitoring value is calculated based on the first feature signal data and the second feature signal data, and the current anesthesia state of the patient is determined based on the anesthesia state monitoring value. By denoising the data, the present invention effectively eliminates the noise existing in the data to improve the accuracy of subsequent monitoring, and the present invention extracts features in multiple aspects of the data to capture the rules in the data and the feature data related to the anesthesia state, further improving the accuracy of anesthesia state monitoring.

[0045] Embodiment 2 As Figure 2 shown, Embodiment 2 of the present invention provides an anesthesia state monitoring system, and the system includes: Processing module 1, configured to acquire the electroencephalogram signal data of the patient, and preprocess the electroencephalogram signal data to obtain processed signal data; Denoising module 2, configured to denoise the processed signal data to obtain denoised signal data; First extraction module 3, configured to perform first feature extraction on the denoised signal data to obtain first feature signal data; Second extraction module 4, configured to perform second feature extraction on the denoised signal data to obtain second feature signal data; Monitoring module 5, configured to calculate an anesthesia state monitoring value based on the first feature signal data and the second feature signal data, and determine the current anesthesia state of the patient based on the anesthesia state monitoring value; The processing module 1 is specifically configured to: Successively perform baseline drift removal, respiratory artifact removal, singular signal removal, and frequency domain filtering processing on the target insulator image to obtain processed signal data.

[0046] The denoising module 2 includes: Threshold calculation sub-module, configured to calculate the wavelet judgment threshold : ; In the formula, represents the standard deviation of Gaussian noise, represents the length of the processed signal data; The coefficient calculation sub-module is used to calculate the wavelet transform coefficient based on the wavelet judgment threshold : : ; In the formula, represents the wavelet coefficients of the high-frequency part; The denoising sub-module is used to perform wavelet denoising on the processed signal data based on the wavelet transform coefficient to obtain the denoised signal data.

[0047] The first extraction module 3 includes: The conversion sub-module is used to select any two sets of denoised signal data and convert the two sets of denoised signal data into a first data matrix and a second data matrix : ; ; In the formula, , respectively represent two sets of denoised signal data, represents the common source signal of the two sets of denoised signal data, , respectively represent the spatial patterns related to , ; represents , the common source spatial pattern of; The covariance sub-module is used to calculate the first covariance matrix of the first data matrix and the second covariance matrix of the second data matrix : ; ; In the formula, represents the sum of the elements on the diagonal of the matrix; The first decomposition sub-module is used to perform eigenvalue decomposition on the first covariance matrix , the second covariance matrix respectively, to obtain the first eigenvector and the second eigenvector, and perform eigenvalue descending order arrangement based on the first eigenvector and the second eigenvector to obtain the first sorting matrix and the second sorting matrix; The second decomposition sub-module is used to perform principal component decomposition on the first sorting matrix and the second sorting matrix respectively to obtain a first decomposition eigenvector and a second decomposition eigenvector, and determine first eigen-signal data based on the first decomposition eigenvector and the second decomposition eigenvector : ; In the formula, and respectively represent the first decomposition eigenvector and the second decomposition eigenvector, and respectively represent diagonal matrices composed of eigenvalues of the first covariance matrix and the second covariance matrix, respectively represent the first eigenvector and the second eigenvector, represents variance calculation.

[0048] The second extraction module 4 includes: An embedding sub-module for embedding the denoised signal data into a dimensional space to obtain embedded signal data, calculating the data distance between any two data in the embedded signal data, and determining the number of data whose data distance between any two data is less than a preset distance , and calculating a data ratio based on the number of data : : ; In the formula, represents the number of data in the embedded signal data; A first calculation sub-module for calculating the data ratio Calculate the eigenvalue in the dimensional space : ; A second calculation sub-module for repeating the process of eigenvalue calculation until obtaining the eigenvalue in the dimensional space , and determining a first undetermined eigenvalue based on the eigenvalue and the eigenvalue : : ; A third calculation sub-module for calculating the quantity mean in the dimensional space based on the number of data : ; A fourth calculation sub-module for repeating the process of data mean calculation until obtaining ​Quantity mean value in the n-dimensional space , based on the quantity mean value and the quantity mean value calculate the second undetermined feature : ; The fifth calculation sub-module is used to construct a phase space, determine the arrangement order of the embedded signal data in the phase space, and determine the value set of the embedded signal based on the arrangement order. The value set includes values, and calculate the arrangement frequency of each arrangement order : ; In the formula, represents the arrangement order appearing frequency in the time series; The sixth calculation sub-module is used to determine the third undetermined feature based on the arrangement frequency : ; The comprehensive calculation sub-module is used to comprehensively calculate the first undetermined feature , the second undetermined feature , and the third undetermined feature to obtain the second feature signal data.

[0049] The monitoring module 5 includes: The distribution sub-module is used to determine the distribution value based on the denoised signal data; The monitoring sub-module is used to calculate the anesthesia state monitoring value based on the distribution value , the first feature signal data, and the second feature signal data: ; In the formula, , are the first weight and the second weight respectively, is the first feature signal data, are the first undetermined feature, the second undetermined feature, and the third undetermined feature in the second feature signal data respectively; The state sub-module is used to determine that if the anesthesia state monitoring value is not greater than the first threshold, the current anesthesia state is the first state. If the anesthesia state monitoring value is greater than the first threshold and less than the second threshold, the current anesthesia state is the second state. If the anesthesia state monitoring value is not less than the second threshold, the current anesthesia state is the third state.

[0050] The distribution sub-module includes: A coefficient unit for determining the correlation coefficient between the denoised signal data of different channels : ; In the formula, respectively represent the auto-power spectra of the denoised signal data of the th channel, represents the cross-power spectrum between the denoised signal data of the th channel; A matrix unit for determining a correlation matrix based on the correlation coefficient : : ; In the formula, represents the correlation coefficient at frequency , represents the frequency band range, represents the element in the th row and th column of the correlation matrix, represents the number of correlation coefficients within ; An eigen-decomposition unit for performing eigen-value decomposition on the correlation matrix to obtain correlation eigen-values; An iteration unit for iteratively resampling the denoised signal data of different channels several times using the amplitude-modulated Fourier algorithm to obtain several sampling matrices, performing eigen-value decomposition on the several sampling matrices to obtain several sampling eigen-values, and determining the average eigen-value among the several sampling eigen-values; An eigen-value unit for determining the final eigen-value based on the correlation eigen-value and the average eigen-value : ; In the formula, , respectively represent the correlation eigen-value and the average eigen-value of the th channel; A calculation unit for calculating a distribution value based on the final eigen-value : .

[0051] In some other embodiments of the present invention, the present invention provides the following technical solution. A computer includes a memory 102, a processor 101, and a computer program stored on the memory 102 and executable on the processor 101. When the processor 101 executes the computer program, the anesthesia state monitoring method described above is implemented.

[0052] Specifically, the above-mentioned processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present invention.

[0053] Among them, the memory 102 may include a mass storage for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In appropriate cases, the memory 102 may include removable or non-removable (or fixed) media. In appropriate cases, the memory 102 may be internal or external to the data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes a read-only memory (ROM) and a random access memory (RAM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these. In appropriate cases, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM may be a fast page mode dynamic random access memory (FPMDRAM), an extended data out dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0054] The memory 102 can be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 101.

[0055] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the above-mentioned anesthesia state monitoring method.

[0056] In some of these embodiments, the computer may further include a communication interface 103 and a bus 100. Among them, as Figure 3 shown, the processor 101, the memory 102, and the communication interface 103 are connected through the bus 100 and complete communication with each other.

[0057] The communication interface 103 is used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present invention. The communication interface 103 can also implement data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations, etc.

[0058] Bus 100 includes hardware, software, or both, and couples components of a computer device to each other. Bus 100 includes, but is not limited to, at least one of the following: Data Bus, Address Bus, Control Bus, Expansion Bus, Local Bus. By way of example and not limitation, Bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. In suitable cases, Bus 100 may include one or more buses. Although embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0059] The computer can execute the anesthesia state monitoring method of the present invention based on the acquired anesthesia state monitoring system, thereby realizing anesthesia state monitoring.

[0060] In still some other embodiments of the present invention, in combination with the above-mentioned anesthesia state monitoring method, embodiments of the present invention provide the following technical solution: a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned anesthesia state monitoring method is realized.

[0061] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus or device and execute the instructions), or used in combination with these instruction execution systems, apparatus or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by or in combination with an instruction execution system, apparatus or device.

[0062] More specific examples (a non-exhaustive list) of the readable medium include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation or other appropriate processing as necessary, and then stored in a computer memory.

[0063] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0064] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0065] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A method for monitoring anesthesia status, characterized in that: include: Acquiring electroencephalogram (EEG) signal data of a patient, and preprocessing the EEG signal data to obtain processed signal data; Performing denoising on the processed signal data to obtain denoised signal data; Performing a first feature extraction on the denoised signal data to obtain first feature signal data; Performing a second feature extraction on the denoised signal data to obtain second feature signal data; An anesthesia state monitoring value is calculated based on the first characteristic signal data and the second characteristic signal data, and a current anesthesia state of the patient is determined based on the anesthesia state monitoring value.

2. The method for monitoring anesthesia status according to claim 1, characterized in that: The step of preprocessing the EEG signal data to obtain processed signal data comprises: The target insulator image is processed in sequence by baseline drift removal, breathing artifact removal, singular signal removal, and frequency domain filtering to obtain processed signal data.

3. The method for monitoring anesthesia status according to claim 1, characterized in that: The step of performing denoising on the processed signal data to obtain denoised signal data comprises: Calculate the wavelet judgment threshold : ； In the formula, represents the standard deviation of Gaussian noise, Indicates the length of the processed signal data; Based on the wavelet judgment threshold Calculate wavelet transform coefficients : ； In the formula, Represents the wavelet coefficients of the high-frequency part; Based on the wavelet transform coefficients The processed signal data is subjected to wavelet denoising to obtain denoised signal data.

4. The method for monitoring anesthesia status according to claim 1, characterized in that: The step of performing first feature extraction on the denoised signal data to obtain first feature signal data comprises: Select any two sets of denoised signal data and convert the two sets of denoised signal data into the first data matrix respectively With the second data matrix : ； ； In the formula, , Represent two sets of denoised signal data respectively, represents the common source signal of the two sets of denoised signal data, , Respectively represent , The spatial pattern of the correlation, express , The common source space pattern of Compute the first covariance matrix of the first data matrix The second covariance matrix with the second data matrix : ； ； In the formula, represents the sum of the elements on the diagonal of the matrix; For the first covariance matrix , the second covariance matrix Performing eigenvalue decomposition respectively to obtain a first eigenvector and a second eigenvector, and arranging the eigenvalues ​​in descending order based on the first eigenvector and the second eigenvector to obtain a first sorting matrix and a second sorting matrix; The first sorting matrix and the second sorting matrix are respectively subjected to principal component decomposition to obtain a first decomposition eigenvector and a second decomposition eigenvector, and the first characteristic signal data is determined based on the first decomposition eigenvector and the second decomposition eigenvector. : ； In the formula, , denote the first decomposition eigenvector and the second decomposition eigenvector respectively, , Respectively represent the diagonal matrices composed of the eigenvalues ​​of the first covariance matrix and the second covariance matrix, denote the first eigenvector and the second eigenvector respectively, Represents variance calculation.

5. The method for monitoring anesthesia status according to claim 1, characterized in that: The step of performing second feature extraction on the denoised signal data to obtain second feature signal data comprises: The denoised signal data is embedded into dimensional space to obtain embedded signal data, calculate the data distance between any two data in the embedded signal data, and determine the number of data whose data distance between any two data is less than a preset distance , based on the amount of data Calculate data ratio : ； In the formula, Indicates the amount of data embedded in the signal data; Calculate the data ratio calculate Eigenvalues ​​in dimensional space : ； Repeat the process of eigenvalue calculation until you get Eigenvalues ​​in dimensional space , based on the eigenvalue With eigenvalue Determine the first feature to be determined : ； Based on the amount of data calculate The number mean in dimensional space : ； Repeat the process of calculating the mean value until you get The number mean in dimensional space , based on the number mean and the number mean Calculate the second undetermined feature : ； Constructing a phase space, determining the arrangement order of the embedded signal data in the phase space and determining a value set of the embedded signal based on the arrangement order, wherein the value set includes values, calculate the frequency of each arrangement order : ； In the formula, Indicates the order of sorting frequency of occurrence in a time series; Based on the frequency of the arrangement Determine the third undetermined feature : ； Comprehensive first undetermined feature , the second undetermined feature , the third undetermined feature , to obtain the second characteristic signal data.

6. The method for monitoring anesthesia status according to claim 1, characterized in that: The step of calculating the anesthesia state monitoring value based on the first characteristic signal data and the second characteristic signal data, and determining the current anesthesia state of the patient based on the anesthesia state monitoring value comprises: Determining a distribution value based on the denoised signal data ; Based on the distribution value , the first characteristic signal data and the second characteristic signal data calculate the anesthesia state monitoring value : ； In the formula, , are the first weight and the second weight respectively. is the first characteristic signal data, They are respectively the first undetermined feature, the second undetermined feature, and the third undetermined feature in the second feature signal data; If the anesthesia status monitoring value is not greater than the first threshold, the current anesthesia state is the first state. If the anesthesia state monitoring value is greater than the first threshold and less than the second threshold, the current anesthesia state is the second state, and the anesthesia state monitoring value If the value is not less than the second threshold, the current anesthesia state is the third state.

7. The method for monitoring anesthesia status according to claim 6, characterized in that: determining a distribution value based on the denoised signal data The steps include: Determine the correlation coefficient between the denoised signal data of different channels : ； In the formula, Respectively represent The autopower spectrum of the denoised signal data of the channels, Indicates The cross power spectrum between the denoised signal data of the channels; Based on the correlation coefficient Determine the correlation matrix : ； In the formula, Indicates the frequency The correlation coefficient when Indicates the frequency band range, Indicates the correlation matrix Line The elements of the column, Indicated in the number of intracorrelation coefficients; Performing eigenvalue decomposition on the correlation matrix to obtain relevant eigenvalues; The denoised signal data of different channels are iteratively resampled several times using the amplitude modulation Fourier algorithm to obtain several sampling matrices, the eigenvalue decomposition of the several sampling matrices is performed to obtain several sampling eigenvalues, and the average eigenvalue between the several sampling eigenvalues ​​is determined; Determine the final eigenvalue based on the correlation eigenvalue and the average eigenvalue : ； In the formula, , Respectively represent The relevant eigenvalues ​​and average eigenvalues ​​of each channel; Calculate the distribution value based on the final feature value : 。 8. An anesthesia status monitoring system, characterized in that: The system comprises: A processing module, used to obtain the patient's EEG signal data and pre-process the EEG signal data to obtain processed signal data; A denoising module, used for performing denoising on the processed signal data to obtain denoised signal data; A first extraction module, used for performing a first feature extraction on the denoised signal data to obtain first feature signal data; A second extraction module, used for performing a second feature extraction on the denoised signal data to obtain second feature signal data; A monitoring module is used to calculate an anesthesia status monitoring value based on the first characteristic signal data and the second characteristic signal data, and determine the patient's current anesthesia status based on the anesthesia status monitoring value.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the anesthesia status monitoring method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the anesthesia status monitoring method according to any one of claims 1 to 7 is implemented.

Images