Nursing monitoring system and method for neurology department

Abstract

The invention discloses a nursing monitoring system and method for the neurology department, and particularly relates to the field of neural signal abnormal pattern recognition, and the method comprises the steps: carrying out the time axis synchronization adjustment of MRS and EEG sampling data, and building a mapping relation with a stimulation input trigger event; feature dimension reduction is carried out on set target tracking metabolite concentration data, energy distribution features of EEG signals are extracted through a time-frequency distribution algorithm, and correlation features of metabolism and neural electrical activity are established; establishing a correlation driving path of the real-time metabolite concentration change and the neural electrical activity of the patient, and quantifying the causal effect of the correlation driving path; establishing an abnormal mode recognition reference of the metabolism-nerve electrical activity signal, and judging whether the patient is in a pathological abnormal state or not by calculating a deviation index of pathological characteristics; when it is judged that the patient is in the metabolic-neural electrical activity signal abnormal state, according to direction calibration in the causal relationship network, the abnormal mode of the metabolic-neural electrical activity signal of the patient is recognized and classified.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal neural signal pattern recognition, and more specifically, to a nursing monitoring system and method for neurology. Background Art

[0002] In the field of neurology nursing, the dynamic association and causal relationship between brain metabolism and neural electrical activity signals are important pathological features of many neurological diseases, such as the association between the sudden increase in lactate concentration and abnormal delta waves during epileptic seizures, or the change in NAA reduction and abnormal synchronization of theta waves after stroke. The abnormal patterns of these signals can reflect the occurrence and development of the disease and provide an important reference for clinical intervention. However, traditional analysis methods mostly rely on static correlation analysis, ignoring the dynamic changes of metabolic and neural electrical activity signals in the time dimension and the causal driving relationship between the two. It is difficult to accurately locate lesions or identify pathological driving patterns, resulting in a high rate of missed detection and misjudgment in the diagnosis and pattern classification of pathological states.

[0003] Therefore, how to implement a comprehensive processing solution based on multimodal signal dynamic analysis, causal relationship modeling, and abnormal pattern classification to provide accurate abnormality detection and pattern classification capabilities, thereby supporting real-time monitoring and personalized intervention in neurological care, is an urgent problem to be solved.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a nursing monitoring method for neurology to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: S1: Synchronize the time axis of MRS and EEG sampling data and establish a mapping relationship with the stimulus input trigger event; S2: Extract the concentration value changes of the set target tracking metabolites, and extract the energy distribution characteristics of the EEG signal through the time-frequency distribution algorithm, calculate the correlation coefficient describing the characteristic correlation between metabolism and neural electrical activity, and construct the correlation matrix; S3: According to the mapping relationship between MRS and EEG signals and the stimulus input triggering events, the correlation coefficient sequence in the correlation matrix is ​​divided into multiple time window data, and the time series distribution sequence of the correlation coefficient is established. The time series distribution sequence of the correlation coefficient is brought into the causal analysis model to establish the association driving path between the patient's real-time metabolite concentration changes and neural electrical activity, and quantify its causal effect to construct a causal relationship network; S4: Retrieve and analyze historical healthy individual sample data, establish a reference association matrix for abnormal pattern recognition of metabolic-neuroelectric activity signals, calculate the deviation index of the patient's pathological characteristics by analyzing the deviation between the association matrix of the patient's real-time metabolite concentration changes and the neuroelectric signal activity characteristic data and the reference association matrix, and judge whether the patient is in an abnormal state of metabolic-neuroelectric activity signals based on the deviation index of the pathological characteristics; S5: When it is determined that the patient is in an abnormal state of metabolic-neural electrical activity signals, the abnormal patterns of the patient's metabolic-neural electrical activity signals are identified and classified according to the direction calibration in the causal relationship network.

[0007] In a preferred embodiment, in S1, the time axis synchronization of the MRS and EEG sampling data is adjusted, and a mapping relationship with the stimulus input triggering event is established, which specifically includes: The sampling frequencies of the MRS and EEG devices were set respectively, and calibration pulses were injected into the MRS and EEG devices through the synchronous trigger signal to synchronously adjust the signal acquisition time axis of the two sets of devices; Monitor and capture external stimulus input trigger events in real time, bind the event time nodes with the sampled data, and form a mapping relationship between multimodal data and trigger events at a unified time scale; The synchronized MRS and EEG signals are time-stamped and each acquisition time point is time-calibrated to form a unified time series data format.

[0008] In a preferred embodiment, in S2, the concentration value change of the set target tracking metabolite is extracted, and the energy distribution characteristics of the EEG signal are extracted by the time-frequency distribution algorithm, and the correlation coefficient describing the characteristic correlation between metabolism and neural electrical activity is calculated. The construction of the correlation matrix specifically includes: Analyze the signal intensity of the MRS signal, extract the concentration value of the set target metabolite, calibrate the concentration change trend and the temporal and spatial distribution of the peak characteristics based on the time series, and construct the time series distribution matrix of the metabolite concentration change; Perform fast Fourier transform on EEG signals, extract the energy distribution characteristics of the set frequency band, remove high-frequency artifacts and low-frequency drift signals, and construct a neural electrical signal feature matrix that describes a specific band; Combining the concentration change time points of metabolic signals with the brain region localization of neural electrical signals, the dynamic time warping algorithm is used to achieve time domain alignment, and the neural electrical signal characteristics are mapped to the brain region map according to spatial distribution; The correlation analysis is performed on the metabolite concentration change time series distribution matrix and the neural electrical signal feature matrix to generate the correlation matrix R. Each element in the correlation matrix represents the Pearson correlation coefficient between the dynamic concentration of the metabolite and the neural electrical signal energy distribution in a specific band. The correlation coefficient is used to describe the correlation strength. Dynamic range compression technology is used to normalize the values ​​of the correlation matrix, and the correlation expressions of metabolite concentrations and neural electrical signal characteristics are uniformly mapped to the standardized interval.

[0009] In a preferred embodiment, in S3, according to the mapping relationship between MRS and EEG signals and the stimulus input triggering event, the correlation coefficient sequence in the correlation matrix is ​​divided into multiple time window data, the time series distribution sequence of the correlation coefficient is established, the time series distribution sequence of the correlation coefficient is brought into the causal analysis model, the association driving path between the patient's real-time metabolite concentration change and the neural electrical activity is established, and the causal effect is quantified. The construction of the causal relationship network specifically includes: Extract the correlation coefficient sequence corresponding to the metabolite concentration and the neural electrical signal characteristics from the correlation matrix R, and divide the correlation coefficient sequence into multiple time window data based on the mapping relationship between MRS and EEG signals according to the time starting node of the triggering event of the captured stimulus input, and construct the time series distribution sequence of the correlation coefficient; The causal model was used to analyze the time-lag response of metabolite concentration and neural electrical signal activity, quantify the causal strength of metabolite concentration and neural electrical signal activity in each lag time period, and generate a causal sequence matrix, where the causal strength judgment formula is: In the formula, is the causal value, indicating that the variable and quantifies the strength of the causal effect of a variable, is the correlation coefficient value of the i-th row and j-th column of the correlation matrix R, which indicates the correlation strength of the power of the j-th frequency band in the EEG signal corresponding to the i-th target metabolite type. is the concentration change value of the i-th target metabolite extracted from the MRS signal, is the target variable The historical sequence is the target variable and causal variables The historical sequence represents the variance of the causal model prediction error residual; The causal strengths in multiple time windows are summarized according to the lag time to generate a dynamic causal matrix G. Each element in the matrix represents the cumulative causal strength of metabolite changes on neural electrical signal activity in a specific band in all segmented time windows. The causal relationship network is constructed based on the dynamic causal matrix G.

[0010] In a preferred embodiment, in S4, historical healthy individual sample data is retrieved and analyzed, and a reference association matrix for abnormal pattern recognition of metabolic-neuroelectric activity signals is established. By analyzing the deviation between the association matrix of the patient's real-time metabolite concentration changes and the neural electrical signal activity characteristic data and the reference association matrix, the deviation index of the patient's pathological characteristics is calculated. Judging whether the patient is in an abnormal state of metabolic-neuroelectric activity signals based on the deviation index of the pathological characteristics specifically includes: Retrieve the metabolic and neural electrical activity data of historical healthy individual samples, and generate a reference correlation matrix by calculating the correlation between changes in metabolite concentrations and neural electrical signal activity characteristics; The correlation matrix of the patient's real-time metabolite concentration changes and neural electrical signal activity characteristic data is used to perform element difference calculation with the reference correlation matrix to generate a correlation deviation matrix. The pathological deviation index is calculated comprehensively through the correlation deviation matrix. The calculation formula is as follows: In the formula, is the pathological deviation index, is the correlation coefficient of the i-th row and j-th column of the reference correlation matrix, m and n are the total number of target metabolite species and the number of EEG signal frequency bands, respectively; A pathological deviation index abnormal threshold is set. When the pathological deviation index exceeds the pathological deviation index abnormal threshold, the patient is judged to be in an abnormal metabolic-neuroelectric activity signal state; otherwise, the patient is judged to be in a normal metabolic-neuroelectric activity signal state.

[0011] In a preferred embodiment, in S5, when it is determined that the patient is in an abnormal state of metabolic-neural electrical activity signals, identifying and classifying abnormal patterns of the patient's metabolic-neural electrical activity signals according to the direction calibration in the causal relationship network specifically includes: When the patient is judged to be in an abnormal state of metabolic-neuroelectric activity signals, the deviation rate of each element in the correlation deviation matrix is ​​calculated, and the elements with a deviation rate greater than the set threshold are screened and marked as dynamic correlation abnormal points; Extract matrix elements from the same position in the causal matrix G according to the dynamic correlation abnormal points, calibrate the direction of the nodes in the causal relationship network corresponding to the elements, and generate causal paths for abnormal driving pattern recognition of metabolic-neural electrical activity signals; If the dynamic correlation abnormal point shows that the metabolic signal is the causal starting point in the causal relationship network, the abnormal pattern of the patient's metabolic-neuroelectric activity signal is calibrated as the metabolic abnormality driving pattern; If the dynamic correlation abnormal point shows that the neural electrical activity signal is the causal starting point in the causal relationship network, the abnormal pattern of the patient's metabolism-neural electrical activity signal is calibrated as the abnormal neural activity driving pattern; If the dynamic correlation abnormal point appears as a two-way interaction between metabolic signals and neural electrical activity signals in the causal network, the abnormal pattern of metabolic-neural electrical activity signals of the patient is calibrated as a metabolic-neural composite abnormality.

[0012] On the other hand, the present invention provides a nursing monitoring system for neurology, including a signal synchronization module, a signal feature analysis module, a causal relationship analysis module, a pathological abnormality judgment module, and an abnormal pattern recognition module: Signal synchronization module: Through the synchronous trigger calibration mechanism, the sampling time axes of the MRS and EEG devices are aligned, external stimulus trigger events are captured in real time and time nodes are bound to generate a unified time series data format; Signal feature analysis module: extract the target metabolite concentration value by analyzing the MRS signal intensity, generate a concentration change time series matrix, extract the spectral features of the EEG signal, and construct a spectral feature matrix after removing artifacts and drifts. Use correlation analysis to generate a standardized multimodal feature correlation expression.

[0013] Causal relationship analysis module: Use causal models to analyze the delayed response of metabolic signals to EEG signals, quantify the causal strength in each time period, and generate a causal sequence matrix. Summarize the causal results of multiple time windows by lag time, construct a dynamic causal matrix and build a causal relationship network; Pathological abnormality judgment module: retrieve healthy individual data to generate a reference association matrix, perform difference calculation with the patient's real-time collected association matrix to generate an association deviation matrix, and comprehensively calculate the pathological deviation index; set an abnormal threshold, and when the pathological deviation index exceeds the threshold, the patient's metabolic-neuroelectric activity signal is judged to be abnormal, otherwise it is judged to be normal; Abnormal pattern recognition module: calculates the deviation rate of the correlation deviation matrix to screen dynamic correlation abnormal points, generates causal paths based on the direction of the causal relationship network, calibrates metabolic or neural signals as causal starting points based on the paths, and classifies abnormal patterns into metabolic-driven, neural-driven, or metabolic-neural combined abnormalities.

[0014] The technical effects and advantages of the neurology nursing monitoring system and method of the present invention are as follows: The present invention adopts a causal analysis model to establish the association driving path between the patient's metabolite concentration and neural electrical activity, and quantify its causal effect. At the same time, based on the historical data of healthy individuals, it constructs an abnormal pattern recognition reference for metabolic-neural electrical activity signals, calculates the deviation index of the patient's pathological characteristics, and determines whether the patient is in an abnormal state. When the signal is determined to be abnormal, the directional calibration of the causal relationship network is used to identify the abnormal patterns of the patient's metabolic and neural electrical activity signals, and classify them into metabolic-driven, neural activity-driven, or metabolic-neural combined abnormalities.

[0015] In summary, the present invention provides accurate signal analysis and pattern recognition capabilities for neurology nursing, supports personalized diagnosis and treatment decisions, realizes real-time monitoring and dynamic evaluation of complex neuropathological states, and provides a scientific basis for disease intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a nursing monitoring method for neurology of the present invention; Figure 2 The present invention is a structural schematic diagram of a nursing monitoring system for neurology. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1 Figure 1 The present invention provides a nursing monitoring method for neurology, which comprises the following steps: S1: Synchronize the time axis of MRS and EEG sampling data and establish a mapping relationship with the stimulus input trigger event; S2: Extract the concentration value changes of the set target tracking metabolites, and extract the energy distribution characteristics of the EEG signal through the time-frequency distribution algorithm, calculate the correlation coefficient describing the characteristic correlation between metabolism and neural electrical activity, and construct the correlation matrix; S3: According to the mapping relationship between MRS and EEG signals and the stimulus input triggering events, the correlation coefficient sequence in the correlation matrix is ​​divided into multiple time window data, and the time series distribution sequence of the correlation coefficient is established. The time series distribution sequence of the correlation coefficient is brought into the causal analysis model to establish the association driving path between the patient's real-time metabolite concentration changes and neural electrical activity, and quantify its causal effect to construct a causal relationship network; S4: Retrieve and analyze historical healthy individual sample data, establish a reference association matrix for abnormal pattern recognition of metabolic-neuroelectric activity signals, calculate the deviation index of the patient's pathological characteristics by analyzing the deviation between the association matrix of the patient's real-time metabolite concentration changes and the neuroelectric signal activity characteristic data and the reference association matrix, and judge whether the patient is in an abnormal state of metabolic-neuroelectric activity signals based on the deviation index of the pathological characteristics; S5: When it is determined that the patient is in an abnormal state of metabolic-neural electrical activity signals, the abnormal patterns of the patient's metabolic-neural electrical activity signals are identified and classified according to the direction calibration in the causal relationship network.

[0019] In S1, the MRS and EEG sampling data are time-synchronized and adjusted, and a mapping relationship with the stimulus input triggering event is established.

[0020] Select the target metabolite type (such as lactate, NAA, glutamate, etc.). In the MRS device, preset the chemical shift range of the corresponding metabolite (such as lactate at 1.3ppm), and adjust the spectrum resolution to cover the accurate acquisition of the peak signal of the target metabolite. At the same time, in the EEG device, set the sampling frequency to 2000Hz according to the target frequency band (such as δ wave 0.5-4Hz or γ wave>30Hz) to ensure the integrity of the signal characteristics.

[0021] Start the MRS and EEG devices respectively, set the trigger signal receiving mode, inject calibration pulses into the MRS and EEG through the external stimulation control device, the calibration signal is triggered at a fixed frequency (such as 1Hz), and each calibration pulse is marked with a unique timestamp on the time axis.

[0022] Start the external stimulation device and send a trigger event (such as visual or auditory stimulation). Record the time node of the trigger event in real time and bind it to the sampling data of MRS and EEG. Embed the synchronized MRS and EEG signals with unified timestamp information according to the sampling point, save the multimodal data file with embedded timestamp in CSV format, and attach the mapping table of external stimulation time node and signal window to form a complete time series data format.

[0023] In S2, feature dimension reduction is performed on the set target tracking metabolite concentration data, the energy distribution characteristics of the EEG signal are extracted through the time-frequency distribution algorithm, and the correlation characteristics between metabolism and neural electrical activity are established.

[0024] The dynamic change signals of the target metabolites were recorded by MRS equipment, and the water suppression technology was used to remove the interference of the 4.7ppm water peak to ensure the clarity of the metabolite signal. The collected MRS spectra were baseline corrected, and the low-frequency drift was eliminated using a smoothing algorithm. For lactic acid and NAA, the chemical shift range was set, the corresponding peak areas were extracted respectively, and the peak signals were integrated to calculate the metabolite concentration. The obtained concentration values ​​were calibrated on the time axis according to the time point to generate a metabolite concentration time series data matrix .

[0025] EEG signals are collected synchronously through a 64-channel device. After collection, high-frequency artifacts (such as electromyographic interference) and low-frequency drift (such as electrode offset) are removed using bandpass filtering technology. Fast Fourier transform (FFT) is performed on the signal to convert the time domain signal into frequency domain features, and the energy of the corresponding band (such as δ, γ, θ, etc.) of the set frequency band (specifically set based on the monitored pathological band) is calculated to form the spectrum feature matrix of the EEG signal. .

[0026] Combining the concentration change time points of metabolic signals with the brain area positioning of neural electrical signals, time domain alignment is achieved through a dynamic time warping algorithm, and the neural electrical signal characteristics are mapped to the brain area map according to spatial distribution. Through spatial distribution and feature analysis, the activity pattern, functional state and possible abnormal behavior of specific brain regions are revealed, providing a visual observation model for nursing monitoring.

[0027] The correlation matrix R is generated by performing correlation analysis on the metabolite concentration change time series distribution matrix and the neural electrical signal feature matrix. Each element in the correlation matrix represents the Pearson correlation coefficient between the dynamic concentration of the metabolite and the energy distribution of the neural electrical signal in a specific band. The correlation coefficient is used to describe the strength of the correlation and is updated in real time based on the calibration of the synchronous time axis time point. The correlation coefficient calculation expression is: In the formula, is the correlation strength of the power of the jth frequency band in the EEG signal corresponding to the i-th target metabolite type, , is the mean of the concentration of the i-th target metabolite and the power of the j-th frequency band of the EEG signal, , The matrices are The concentration of the ith metabolite at time point t in the time series, and the matrix The j-th frequency band power at time point t in the time series, T is the length of the time series.

[0028] Dynamic range compression technology is used to normalize the values ​​of the correlation matrix, and the correlation expressions of metabolite concentrations and neural electrical signal characteristics are uniformly mapped to the standardized interval.

[0029] In S3, based on the causal analysis model, the association driving pathway between the patient's real-time metabolite concentration changes and neural electrical activity is established, and its causal effect is quantified.

[0030] The correlation coefficient sequence corresponding to the metabolite concentration and the neural electrical signal characteristics is extracted from the correlation matrix R. According to the time starting node of the stimulus input triggering event, the correlation coefficient sequence is divided into multiple time window data according to the mapping relationship of the signal, and the correlation coefficient time series distribution sequence is constructed.

[0031] The causal model (such as the Granger causality analysis model) is used to analyze the time lag response of metabolite concentration and neural electrical signal activity, quantify the causal strength of metabolite concentration and neural electrical signal activity in each lag time period (the lag time period uses multiple time windows as the time axis reference benchmark), and generate a causal sequence matrix, where the causal strength judgment formula is: In the formula, is the causal value, indicating that the variable and quantifies the strength of the causal effect of a variable, is the correlation coefficient value of the i-th row and j-th column of the correlation matrix R, which indicates the correlation strength of the power of the j-th frequency band in the EEG signal corresponding to the i-th target metabolite type. is the concentration change value of the i-th target metabolite extracted from the MRS signal, is the target variable The historical sequence is the target variable and causal variables The historical sequence Represents the variance of the causal model prediction error residuals.

[0032] if , explaining the introduction After significantly reducing the prediction error, there is a causal relationship, if Description Introduction There was no significant improvement in prediction and the causal relationship was not significant.

[0033] When adding causal variables The specific process of recalculating the residuals at each time point using historical sequence data in the model is as follows: In the formula, Predict the target variable for the model at the ath time point (the latest time point) in the time series, is the lag order of the target variable, that is The number of lag time steps when predicting the historical sequence value itself (the step size is determined by the time axis scale of multiple time windows), is the lag order of the causal variable, that is, the causal variable The number of time steps behind the historical values ​​when making predictions, , , In the time series model, the linear influence coefficient of historical values ​​on current values, The error between the model's predicted value and the actual value of the target variable at time t is calculated by adjusting the lag orders p and q to minimize the model error. The variance is .

[0034] The causal sequence matrix is ​​expressed as: is the causal strength distribution in the k-th time window, yes The complete representation of the z time points in the time window.

[0035] The causal strengths in multiple time windows are summarized according to the lag time to obtain an average matrix, the dynamic causal matrix G. Each element in the matrix represents the cumulative causal strength of metabolite changes on neural electrical signal activities in a specific band in all segmented time windows. A causal relationship network is constructed based on the dynamic causal matrix G, and the edge weights are determined by the causal strength of the dynamic causal matrix.

[0036] In S4, an abnormal pattern recognition reference of metabolic-neuroelectric activity signals is established based on historical healthy individual sample data, and by calculating the deviation index of pathological characteristics, it is determined whether the patient is in a pathologically abnormal state.

[0037] The metabolic and neural electrical activity data of historical healthy individual samples were retrieved, and the correlation between the changes in metabolite concentrations and the characteristics of neural electrical signal activity was calculated to generate a reference correlation matrix (consistent with the process in S2).

[0038] The correlation matrix of the patient's real-time metabolite concentration changes and neural electrical signal activity characteristic data is used to perform element difference calculation with the reference correlation matrix to generate a correlation deviation matrix. The pathological deviation index is calculated comprehensively through the correlation deviation matrix. The calculation formula is as follows: In the formula, is the pathological deviation index, is the correlation coefficient of the i-th row and j-th column of the reference correlation matrix, and m and n are the total number of target metabolite species and the number of EEG signal frequency bands, respectively.

[0039] An abnormal threshold of the pathology deviation index is set (set by the medical monitoring staff based on the patient's pathology data level and monitoring sensitivity requirements). When the pathology deviation index exceeds the abnormal threshold of the pathology deviation index, it is determined that the patient's metabolic-neuroelectrical activity signal is in an abnormal state; otherwise, it is determined that the patient is in a normal metabolic-neuroelectrical activity signal state.

[0040] In S5, when it is determined that the patient is in an abnormal state of metabolic-neural electrical activity signals, the abnormal pattern of the patient's metabolic-neural electrical activity signals is identified and classified according to the direction calibration in the causal relationship network.

[0041] When the patient is judged to be in an abnormal state of metabolic-neuroelectric activity signal, the deviation rate (numerical deviation ratio) of each element in the correlation deviation matrix is ​​calculated, and the elements with deviation rate greater than the set threshold are screened and marked as dynamic correlation abnormality points. The dynamic correlation abnormality points contain significantly abnormal metabolite-neuroelectric activity signal feature pairs.

[0042] Extract matrix elements from the same position in the causal matrix G according to the dynamic correlation abnormal points, calibrate the direction of the nodes in the causal relationship network corresponding to the elements, and generate causal paths for abnormal driving pattern recognition of metabolic-neural electrical activity signals; If the dynamic correlation abnormal point shows that the metabolic signal is the causal starting point in the causal network, the abnormal pattern of the patient's metabolic-neuroelectric activity signal is calibrated as a metabolic abnormality driven pattern. For example, if a patient's lactate concentration increases abnormally (metabolic signal) resulting in a significant abnormality in delta wave intensity, then the abnormal pattern is calibrated as metabolic abnormality driven.

[0043] If the dynamic correlation abnormal point shows that the neural electrical activity signal is the causal starting point in the causal network, the abnormal pattern of the patient's metabolism-neural electrical activity signal is calibrated as the abnormal neural activity driven mode. For example, if the patient's gamma wave frequency is too high (abnormal neural activity) and causes glutamate metabolism disorder, then the abnormal pattern is calibrated as abnormal neural activity driven.

[0044] If the dynamic correlation abnormal points appear as two-way interactions between metabolic signals and neural electrical activity signals in the causal network, then the abnormal pattern of the patient's metabolic-neural electrical activity signals is calibrated as a metabolic-neural composite abnormality. This method can effectively analyze the driving mechanism of the patient's metabolic and neural electrical activity abnormalities, providing a basis for precise intervention.

[0045] Example 2 The difference between Example 2 of the present invention and Example 1 is that this example introduces a nursing monitoring method for neurology.

[0046] Figure 2 A structural diagram of a nursing monitoring system for neurology of the present invention is given, which includes a signal synchronization module, a signal feature analysis module, a causal relationship analysis module, a pathological abnormality judgment module, and an abnormal pattern recognition module: Signal synchronization module: Through the synchronous trigger calibration mechanism, the sampling time axes of the MRS and EEG devices are aligned, external stimulus trigger events are captured in real time and time nodes are bound to generate a unified time series data format; Signal feature analysis module: extract the target metabolite concentration value by analyzing the MRS signal intensity, generate a concentration change time series matrix, extract the spectral features of the EEG signal, and construct a spectral feature matrix after removing artifacts and drifts. Use correlation analysis to generate a standardized multimodal feature correlation expression.

[0047] Causal relationship analysis module: Use causal models to analyze the delayed response of metabolic signals to EEG signals, quantify the causal strength in each time period, and generate a causal sequence matrix. Summarize the causal results of multiple time windows by lag time, construct a dynamic causal matrix and build a causal relationship network; Pathological abnormality judgment module: retrieve healthy individual data to generate a reference association matrix, perform difference calculation with the patient's real-time collected association matrix to generate an association deviation matrix, and comprehensively calculate the pathological deviation index; set an abnormal threshold, and when the pathological deviation index exceeds the threshold, the patient's metabolic-neuroelectric activity signal is judged to be abnormal, otherwise it is judged to be normal; Abnormal pattern recognition module: calculates the deviation rate of the correlation deviation matrix to screen dynamic correlation abnormal points, generates causal paths based on the direction of the causal relationship network, calibrates metabolic or neural signals as causal starting points based on the paths, and classifies abnormal patterns into metabolic-driven, neural-driven, or metabolic-neural combined abnormalities.

[0048] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0049] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0050] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0051] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0052] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0053] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0054] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0055] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0056] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0057] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A nursing monitoring method for neurology, characterized in that: The steps include: S1: Synchronize the time axis of MRS and EEG sampling data and establish a mapping relationship with the stimulus input trigger event; S2: Extract the concentration value changes of the set target tracking metabolites, and extract the energy distribution characteristics of the EEG signal through the time-frequency distribution algorithm, calculate the correlation coefficient describing the characteristic correlation between metabolism and neural electrical activity, and construct the correlation matrix; S3: According to the mapping relationship between MRS and EEG signals and the stimulus input triggering events, the correlation coefficient sequence in the correlation matrix is ​​divided into multiple time window data, and the time series distribution sequence of the correlation coefficient is established. The time series distribution sequence of the correlation coefficient is brought into the causal analysis model to establish the association driving path between the patient's real-time metabolite concentration changes and neural electrical activity, and quantify its causal effect to construct a causal relationship network; S4: Retrieve and analyze historical healthy individual sample data, establish a reference association matrix for abnormal pattern recognition of metabolic-neuroelectric activity signals, calculate the deviation index of the patient's pathological characteristics by analyzing the deviation between the association matrix of the patient's real-time metabolite concentration changes and the neuroelectric signal activity characteristic data and the reference association matrix, and judge whether the patient is in an abnormal state of metabolic-neuroelectric activity signals based on the deviation index of the pathological characteristics; S5: When it is determined that the patient is in an abnormal state of metabolic-neural electrical activity signals, the abnormal patterns of the patient's metabolic-neural electrical activity signals are identified and classified according to the direction calibration in the causal relationship network.

2. A nursing monitoring method for neurology according to claim 1, characterized in that: In S1, the MRS and EEG sampling data are synchronized in time axis and the mapping relationship with the stimulus input triggering event is established, including: Set the target metabolite type and set the sampling frequency of MRS and EEG equipment respectively; The sampling frequencies of the MRS and EEG devices were set respectively, and calibration pulses were injected into the MRS and EEG devices through the synchronous trigger signal to synchronously adjust the signal acquisition time axis of the two sets of devices; Monitor and capture external stimulus input trigger events in real time, bind the event time nodes with the sampled data, and form a mapping relationship between multimodal data and trigger events at a unified time scale; The synchronized MRS and EEG signals are time-stamped and each acquisition time point is time-calibrated to form a unified time series data format.

3. A nursing monitoring method for neurology according to claim 2, characterized in that: In S2, the concentration value changes of the set target tracking metabolites are extracted, and the energy distribution characteristics of the EEG signal are extracted through the time-frequency distribution algorithm. The correlation coefficient describing the characteristic correlation between metabolism and neural electrical activity is calculated, and the correlation matrix is ​​constructed, which specifically includes: Analyze the signal intensity of the MRS signal, extract the concentration value of the set target metabolite, calibrate the concentration change trend and the temporal and spatial distribution of the peak characteristics based on the time series, and construct the time series distribution matrix of the metabolite concentration change; Perform fast Fourier transform on EEG signals, extract the energy distribution characteristics of the set frequency band, remove high-frequency artifacts and low-frequency drift signals, and construct a neural electrical signal feature matrix that describes a specific band; Combining the concentration change time points of metabolic signals with the brain region localization of neural electrical signals, the dynamic time warping algorithm is used to achieve time domain alignment, and the neural electrical signal characteristics are mapped to the brain region map according to spatial distribution; The correlation matrix R is generated by performing correlation analysis on the metabolite concentration change time series distribution matrix and the neural electrical signal feature matrix. Each element in the correlation matrix represents the Pearson correlation coefficient between the dynamic concentration of the metabolite and the neural electrical signal energy distribution in a specific band. The correlation coefficient is used to describe the correlation strength. Dynamic range compression technology was used to normalize the values ​​of the correlation matrix, and the correlation expressions of metabolite concentrations and neural electrical signal characteristics were uniformly mapped to a standardized interval.

4. A nursing monitoring method for neurology according to claim 3, characterized in that: In S3, according to the mapping relationship between MRS and EEG signals and stimulus input triggering events, the correlation coefficient sequence in the correlation matrix is ​​divided into multiple time window data, and the time series distribution sequence of the correlation coefficient is established. The time series distribution sequence of the correlation coefficient is brought into the causal analysis model, and the association driving path between the patient's real-time metabolite concentration changes and neural electrical activity is established, and its causal effect is quantified. The construction of the causal relationship network specifically includes: Extract the correlation coefficient sequence corresponding to the metabolite concentration and the neural electrical signal characteristics from the correlation matrix R, and divide the correlation coefficient sequence into multiple time window data based on the mapping relationship between MRS and EEG signals according to the time starting node of the captured stimulus input trigger event, and construct the time series distribution sequence of the correlation coefficient; The causal model was used to analyze the time-lag response of metabolite concentration and neural electrical signal activity, quantify the causal strength of metabolite concentration and neural electrical signal activity in each lag time period, and generate a causal sequence matrix, where the causal strength judgment formula is: In the formula, is the causal value, indicating that the variable and quantifies the strength of the causal effect of a variable, is the correlation coefficient value of the i-th row and j-th column of the correlation matrix R, which indicates the correlation strength of the power of the j-th frequency band in the EEG signal corresponding to the i-th target metabolite type. is the concentration change value of the i-th target metabolite extracted from the MRS signal, is the target variable The historical sequence is the target variable and causal variables The historical sequence represents the variance of the causal model prediction error residual; The causal strengths in multiple time windows are summarized according to the lag time to generate a dynamic causal matrix G. Each element in the matrix represents the cumulative causal strength of metabolite changes on neural electrical signal activity in a specific band in all segmented time windows. The causal relationship network is constructed based on the dynamic causal matrix G.

5. A nursing monitoring method for neurology according to claim 4, characterized in that: In S4, historical healthy individual sample data is retrieved and analyzed to establish a reference association matrix for abnormal pattern recognition of metabolic-neuroelectric activity signals. By analyzing the deviation between the association matrix of the patient's real-time metabolite concentration changes and the characteristic data of neuroelectric signal activity and the reference association matrix, the deviation index of the patient's pathological characteristics is calculated. Based on the deviation index of the pathological characteristics, it is determined whether the patient is in an abnormal state of metabolic-neuroelectric activity signals, including: Retrieve the metabolic and neural electrical activity data of historical healthy individual samples, and generate a reference correlation matrix by calculating the correlation between changes in metabolite concentrations and neural electrical signal activity characteristics; The correlation matrix of the patient's real-time metabolite concentration changes and neural electrical signal activity characteristic data is used to perform element difference calculation with the reference correlation matrix to generate a correlation deviation matrix. The pathological deviation index is calculated comprehensively through the correlation deviation matrix. The calculation formula is as follows: In the formula, is the pathological deviation index, is the correlation coefficient of the i-th row and j-th column of the reference correlation matrix, m and n are the total number of target metabolite species and the number of EEG signal frequency bands, respectively; A pathological deviation index abnormal threshold is set. When the pathological deviation index exceeds the pathological deviation index abnormal threshold, the patient is judged to be in an abnormal metabolic-neuroelectric activity signal state; otherwise, the patient is judged to be in a normal metabolic-neuroelectric activity signal state.

6. A nursing monitoring method for neurology according to claim 5, characterized in that: In S5, when it is determined that the patient is in an abnormal state of metabolic-neuroelectric activity signals, the abnormal pattern of the metabolic-neuroelectric activity signals of the patient is identified and classified according to the direction calibration in the causal relationship network, specifically including: When the patient is judged to be in an abnormal state of metabolic-neuroelectric activity signals, the deviation rate of each element in the correlation deviation matrix is ​​calculated, and the elements with a deviation rate greater than the set threshold are screened and marked as dynamic correlation abnormal points; Extract matrix elements from the same position in the causal matrix G according to the dynamic correlation abnormal points, calibrate the direction of the nodes in the causal relationship network corresponding to the elements, and generate causal paths for abnormal driving pattern recognition of metabolic-neural electrical activity signals; If the dynamic correlation abnormal point shows that the metabolic signal is the causal starting point in the causal relationship network, the abnormal pattern of the patient's metabolic-neuroelectric activity signal is calibrated as the metabolic abnormality driving pattern; If the dynamic correlation abnormal point shows that the neural electrical activity signal is the causal starting point in the causal relationship network, the abnormal pattern of the patient's metabolism-neural electrical activity signal is calibrated as the abnormal neural activity driving pattern; If the dynamic correlation abnormal point appears as a two-way interaction between metabolic signals and neural electrical activity signals in the causal network, the abnormal pattern of metabolic-neural electrical activity signals of the patient is calibrated as a metabolic-neural composite abnormality.

7. A nursing monitoring system for neurology, used to implement a nursing monitoring method for neurology according to any one of claims 1 to 6, characterized in that: It includes signal synchronization module, signal feature analysis module, causal relationship analysis module, pathological abnormality judgment module and abnormal pattern recognition module: Signal synchronization module: Through the synchronous trigger calibration mechanism, the sampling time axes of the MRS and EEG devices are aligned, external stimulus trigger events are captured in real time and time nodes are bound to generate a unified time series data format; Signal feature analysis module: extract the target metabolite concentration value by analyzing the MRS signal intensity, generate a concentration change time series matrix, extract the spectral features of the EEG signal, and construct a spectral feature matrix after removing artifacts and drifts. Use correlation analysis to generate a standardized multimodal feature correlation expression. Causal relationship analysis module: Use causal models to analyze the delayed response of metabolic signals to EEG signals, quantify the causal strength in each time period, and generate a causal sequence matrix. Summarize the causal results of multiple time windows by lag time, construct a dynamic causal matrix and build a causal relationship network; Pathological abnormality judgment module: retrieve healthy individual data to generate a reference association matrix, perform difference calculation with the patient's real-time collected association matrix to generate an association deviation matrix, and comprehensively calculate the pathological deviation index; Set an abnormal threshold. When the pathological deviation index exceeds the threshold, the patient's metabolic-neural electrical activity signal is judged to be abnormal, otherwise it is judged to be normal. Abnormal pattern recognition module: calculates the deviation rate of the correlation deviation matrix to screen dynamic correlation abnormal points, generates causal paths based on the direction of the causal relationship network, calibrates metabolic or neural signals as causal starting points based on the paths, and classifies abnormal patterns into metabolic-driven, neural-driven, or metabolic-neural combined abnormalities.

Images