Brain damage early warning device based on electroencephalogram monitoring

Abstract

The invention discloses a brain damage early warning device based on electroencephalogram monitoring, and relates to the technical field of medical instruments. In order to solve the problems that abnormal modes and types of electroencephalogram signals cannot be accurately recognized, so that the early warning and processing capacity is low, medical staff still need to conduct judgment and processing, and postoperative cognitive impairment or brain injury is difficult to predict. The brain damage early warning device based on electroencephalogram monitoring comprises an electroencephalogram data acquisition device and a processing display terminal, the electroencephalogram sensor is attached to the head of a patient to collect electroencephalogram data, the collected electroencephalogram data are transmitted to the signal amplifier through the processing display terminal, the processing display terminal generates an electroencephalogram spectrogram to conduct signal analysis, feature extraction is conducted on processed electroencephalogram signals, and then the electroencephalogram signals are obtained. According to the method, feature extraction and recognition are carried out on a patient, feature changes related to postoperative cognitive impairment and brain injury are recognized, whether the patient has the risk of postoperative cognitive impairment or brain injury or not is automatically judged according to feature extraction and recognition results, and an early warning report is generated.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a brain damage early warning device based on electroencephalogram monitoring. Background Art

[0002] Surgery and anesthesia are the main risk factors for perioperative neurocognitive dysfunction. Regarding brain damage early warning devices, a patent application with publication number CN112842364A discloses a brain damage early warning device based on remote EEG monitoring, including an acquisition system for acquiring EEG signals, an EEG amplification analog-to-digital conversion system, a wireless transceiver system, a terminal system, and a remote EEG processing and analysis system; wherein the EEG amplification analog-to-digital conversion system is used to amplify the collected EEG signals and convert them into data, the wireless transceiver system is used to transmit the data converted by the EEG amplification analog-to-digital conversion system to the terminal system, and the remote EEG processing and analysis system is used to process and analyze the data received by the terminal system. This patent conducts EEG signal analysis on patients with severe heatstroke brain damage, which can detect brain damage early to provide early warning, and continuously monitor the degree of brain damage to guide effective intervention.

[0003] Although the above patent can detect brain damage early and provide early warning, it cannot accurately identify abnormal patterns and types of EEG signals, resulting in low warning and processing capabilities. Medical staff still need to make judgments and handle the problem, and it is difficult to predict postoperative cognitive dysfunction or brain damage. Summary of the invention

[0004] The purpose of the present invention is to provide a brain damage warning device based on EEG monitoring, which can comprehensively and accurately monitor the patient's EEG signals, timely warn of potential postoperative cognitive dysfunction or brain damage risks, provide strong support for clinical anesthesia management and postoperative care, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A brain damage early warning device based on electroencephalogram monitoring includes an electroencephalogram data acquisition device and a processing and display terminal. The electroencephalogram data acquisition device includes an electrode cap, an air bag, an electroencephalogram sensor and a connecting wire. The air bag is arranged in the electrode cap, and the electroencephalogram sensor is arranged inside the air bag. One side of the electroencephalogram sensor is electrically connected to a signal amplifier through a connecting wire, and one side of the signal amplifier is electrically connected to the processing and display terminal.

[0007] Further, processing the display terminal includes:

[0008] The EEG signal acquisition unit is used to collect the patient's EEG signals in real time based on the EEG sensor, transmit the signals collected by the EEG sensor to the signal amplifier for amplification processing, and transmit the processed signals to the signal processing and analysis unit to ensure the continuity and accuracy of data acquisition;

[0009] A signal processing and analysis unit is used to standardize the acquired signal, extract the features of the patient's EEG signal based on spectrum analysis, and quantify the extracted target feature data;

[0010] The early warning unit is used to build an early warning model for identifying postoperative cognitive dysfunction and brain damage, perform early warning identification based on the feature extraction results after quantification processing, determine whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage, and issue an early warning based on the judgment results;

[0011] The display unit is used to provide an intuitive user interface, display real-time EEG spectrum, characteristic parameters and warning information, and support medical staff to view, analyze and record monitoring results.

[0012] Furthermore, the EEG signal acquisition unit comprises:

[0013] The sensor control module is used to calibrate and adjust the data parameters of the EEG sensor, monitor the working status of the EEG sensor in real time, and manage the start, stop, calibration and multi-channel synchronous acquisition of the EEG sensor;

[0014] A signal conversion module, used to convert the continuous analog EEG signals collected by the EEG sensor into digital signals;

[0015] The filtering and amplifying module is used to filter the converted digital signal and amplify the filtered signal.

[0016] Furthermore, the filtering and amplification module also includes signal quality evaluation of the digital signal after filtering and amplification:

[0017] Determine the sampling rate, sampling time and range parameters according to the characteristics of the measured signal, and collect the filtered and amplified digital signal data from the output end of the signal amplifier;

[0018] Further filtering the collected digital signal data to remove possible noise or interference, calculating the mean of the digital signal based on the time series, and identifying the DC component in the digital signal;

[0019] Subtracting the mean value of the digital signal from each data point of the digital signal based on the recognition result to obtain a digital signal after the DC component is removed;

[0020] The signal-to-noise ratio and distortion of the digital signal after the DC component is removed are calculated, and the calculation results are compared with the preset thresholds to evaluate whether the signal quality meets the standards and whether the signal distortion is too large;

[0021] Based on the evaluation results, a comprehensive diagnosis is made as to whether the signal quality of the digital signal meets the standards, and parameter optimization and adjustment are performed according to the diagnosis results.

[0022] Furthermore, the signal processing and analysis unit comprises:

[0023] The analog-to-digital standardization module is used to standardize the processed and qualified digital signals to ensure that the amplitude and range of the signals are suitable for subsequent analysis, including normalization processing, so that the signals are within a certain numerical range, which is convenient for comparison and analysis, and calibrating the signals to eliminate system errors introduced by hardware or environmental factors, and improve the accuracy and reliability of the data;

[0024] The EEG spectrum analysis module is used to divide the digital signal into multiple continuous time periods based on the time series, and perform frequency domain signal conversion on the digital signal of each time period, wherein the length of the divided time period is adaptively adjusted according to the characteristics of the signal, and a shorter time period is used for the part with a larger signal change, and a longer time period is used otherwise, so as to improve the analysis accuracy;

[0025] Calculate the amplitude and phase of each frequency component in each time period, obtain the target spectrum value of the digital signal in each time period, and draw a spectrum diagram based on the target spectrum value;

[0026] Divide the spectrum graph into different frequency bands according to the spectrum characteristics of each time period in the spectrum graph, and analyze the activity of EEG signals in each frequency band, including power changes, frequency distribution, etc., and analyze the frequency characteristics of digital signals changing over time;

[0027] The target feature extraction module is used to extract features based on the activity of EEG signals in each frequency band and the frequency characteristics of digital signals changing over time, and to screen feature parameters related to brain damage and cognitive dysfunction from the spectrum features based on the feature extraction results, such as power changes in specific frequency bands, waveform complexity, etc.

[0028] Furthermore, the EEG spectrum analysis module also includes:

[0029] Obtaining the patient's brain acquisition position corresponding to each digital signal in the digital signal of each time period;

[0030] Obtain the initial signal of the same brain acquisition position and the frequency amplitude and phase corresponding to each time period to establish the frequency characteristics of the position;

[0031] Generating a change feature corresponding to each brain acquisition position according to the change of the frequency characteristic over time, and extracting a position attribute of each brain acquisition position;

[0032] According to the position attributes and change characteristics corresponding to each brain acquisition position, the relationship between the change characteristics of different brain acquisition positions is established and analyzed;

[0033] Based on the relationship between the changing characteristics of different brain sampling locations, the patient's corresponding brain activity markers are generated, such as cognitive state, emotional changes, disease markers, etc.

[0034] Furthermore, the early warning unit includes:

[0035] The early warning model building module is used to combine historical data and professional knowledge database to build an early warning model for predicting postoperative cognitive dysfunction and brain damage;

[0036] The warning instruction driving module is used to input the feature parameters extracted by the target feature extraction module into the constructed warning model, determine the warning category according to the output results of the warning model, match the corresponding warning signal and issue a warning such as sound alarm, screen display of warning information, etc. At the same time, send an alarm notification to medical staff.

[0037] Furthermore, the display unit comprises:

[0038] Real-time signal display module, used to display real-time collected EEG waveforms and spectrograms, making it easier for medical staff to observe signal changes;

[0039] The processing result display module is used to display the output results of the signal processing and analysis unit, such as characteristic parameters, analysis result charts, etc.

[0040] The warning information display module is used to highlight the warning information when potential risks are detected, including the warning type, risk level and recommended intervention measures.

[0041] Furthermore, early warning identification is performed based on the feature extraction results after quantification processing to determine whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage, including:

[0042] Determine the patient's brain activity feature measurement matrix based on the feature extraction result after quantization processing, and calculate the corresponding covariance matrix according to the brain activity feature measurement matrix;

[0043] Determine the eigenvalue of the covariance matrix, determine the principal component eigenvector of the patient's brain activity according to the eigenvalue, and obtain the representation parameter corresponding to the principal component eigenvector of the brain activity;

[0044] Determine the distribution structure of the patient's postoperative brain activity variability and its structural characteristics over time based on the characterization parameters;

[0045] The postoperative brain activity waveform of the patient is obtained according to the distribution structure of the postoperative brain activity variability and its structural characteristics that change over time, and the postoperative brain activity waveform is converted into a time series related brain activity variation spatiotemporal scatter plot using scatter plot technology;

[0046] The dynamic characteristics of the patient's postoperative brain activity and its related plane characteristics were extracted based on the spatiotemporal scatter plot of the time series-related brain activity variation;

[0047] Determine the critical state cutoff value of the patient's postoperative brain activity based on the patient's postoperative brain activity dynamics characteristics and its related plane characteristics;

[0048] The patient's brain damage attributes are determined based on the critical state dividing value of brain activity, and based on the brain damage attributes, it is judged whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage.

[0049] Furthermore, an adjusting device is provided between the electrode cap (11) and the air bag (12) for adjusting the internal pressure of the air bag, specifically:

[0050] Collecting a head image of the patient wearing the cap, determining the patient's brain shape curve based on the head image, and superimposing the brain shape curve with the internal space shape curve of the electrode cap;

[0051] Determine the space gap between the head of the patient and the electrode cap when the patient wears the electrode cap according to the processing result;

[0052] Determine the contact index between the airbag and the head of the patient wearing the airbag according to the preset position parameters and shape parameters of the space gap and the airbag in the electrode cap;

[0053] Determine the static load increment and static deformation increment of the airbag on the head of the patient wearing the airbag according to the contact index and the preset pressure of the airbag;

[0054] The comfort index of the patient wearing the airbag at the preset pressure is calculated based on the static load increment and static deformation increment:

[0055]

[0056] Wherein, Q represents the comfort index of the patient under the preset pressure, P represents the adjustable space ratio of the electrode cap when the patient wears the electrode cap, δ represents the Poisson's ratio of the airbag, μ represents the comfort gain factor of the material of the airbag for human skin, F represents the static load increment of the airbag for the head of the patient, E represents the static deformation increment of the airbag for the head of the patient, G represents the sum of the load and deformation that the user can bear under the best comfort, θ represents the matching factor between the electrode cap and the head of the patient,

[0057] The airbag pressure adjustment method is determined according to the comfort index of the patient wearing the airbag at a preset pressure, and the airbag pressure is increased or decreased according to the adjustment method.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The EEG sensor is attached to the patient's head to collect EEG data, and the collected EEG data is transmitted to the signal amplifier through the processing and display terminal. The collected raw EEG signals are amplified, filtered, analog-to-digital converted, and converted into digital signals. The processing and display terminal generates an EEG spectrum diagram for signal analysis, and features are extracted from the processed EEG signals to identify characteristic changes related to postoperative cognitive dysfunction and brain damage. Based on the feature extraction and recognition results, it is automatically determined whether the patient is at risk of postoperative cognitive dysfunction or brain damage, and an early warning report is generated to notify medical staff through sound, light or wireless transmission. This not only reduces the workload of medical staff, but also improves their data-based decision-making ability, which helps to more accurately assess the patient's condition and take appropriate intervention measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is an axonometric diagram of the EEG data acquisition device of the present invention;

[0061] Figure 2 It is a schematic diagram of the brain damage early warning device for EEG monitoring of the present invention;

[0062] Figure 3 This is a diagram of a processing and display terminal module of the present invention.

[0063] In the figure: 1. EEG data acquisition device; 11. Electrode cap; 12. Air bag; 13. EEG sensor; 14. Connecting wires; 2. Signal amplifier; 3. Processing and display terminal. DETAILED DESCRIPTION

[0064] 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.

[0065] In order to solve the technical problem that the abnormal patterns and types of EEG signals cannot be accurately identified, resulting in low early warning and processing capabilities, medical staff are still required to make judgments and handle them, and it is difficult to predict postoperative cognitive dysfunction or brain damage, please refer to Figure 1-3 , this embodiment provides the following technical solutions:

[0066] A brain damage early warning device based on electroencephalogram monitoring includes an electroencephalogram data acquisition device 1 and a processing and display terminal 3. The electroencephalogram data acquisition device 1 includes an electrode cap 11, an air bag 12, an electroencephalogram sensor 13 and a connecting wire 14. The air bag 12 is arranged in the electrode cap 11. The electroencephalogram sensor 13 is arranged inside the air bag 12. One side of the electroencephalogram sensor 13 is electrically connected to a signal amplifier 2 through the connecting wire 14. One side of the signal amplifier 2 is electrically connected to the processing and display terminal 3.

[0067] In this embodiment, by arranging the airbag 12 in the electrode cap 11 and adaptively adjusting it according to the patient's head shape, the close fit between the EEG sensor 13 and the patient's scalp is ensured, and the signal interference and distortion caused by movement or head shape difference is reduced. At the same time, the wearing comfort of the patient is improved, and the discomfort that may be caused by long-term monitoring is reduced;

[0068] In this embodiment, processing the display terminal 3 includes:

[0069] The EEG signal acquisition unit is used to acquire the patient's EEG signal in real time based on the EEG sensor 13, transmit the signal acquired by the EEG sensor 13 to the signal amplifier 2 for amplification, and transmit the processed signal to the signal processing and analysis unit to ensure the continuity and accuracy of data acquisition;

[0070] A signal processing and analysis unit is used to standardize the acquired signal, extract the features of the patient's EEG signal based on spectrum analysis, and quantify the extracted target feature data;

[0071] The early warning unit is used to build an early warning model for identifying postoperative cognitive dysfunction and brain damage, perform early warning identification based on the feature extraction results after quantification processing, determine whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage, and issue an early warning based on the judgment results;

[0072] The display unit is used to provide an intuitive user interface, display real-time EEG spectrograms, characteristic parameters and warning information, and support medical staff to view, analyze and record monitoring results, including:

[0073] The real-time signal display module is used to display the real-time collected EEG waveform and spectrum diagram, which is convenient for medical staff to observe signal changes; the processing result display module is used to display the output results of the signal processing and analysis unit, such as characteristic parameters, analysis result charts, etc.; the early warning information display module is used to highlight the early warning information when potential risks are detected, including the warning type, risk level and recommended intervention measures.

[0074] In this embodiment, the EEG sensor 13 is attached to the patient's head to collect EEG data, and the collected EEG data is transmitted to the signal amplifier 2 through the processing and display terminal 3. The collected original EEG signal is amplified, filtered, analog-to-digital converted, and converted into a digital signal. The processing and display terminal 3 generates an EEG spectrum diagram for signal analysis, and performs feature extraction on the processed EEG signal to identify characteristic changes related to postoperative cognitive dysfunction and brain damage, such as frequency changes, amplitude changes, and complexity changes in specific bands. Based on the feature extraction and recognition results, it is automatically determined whether the patient has the risk of postoperative cognitive dysfunction or brain damage, and a warning report is generated to notify medical staff through sound, light or wireless transmission.

[0075] In this embodiment, the EEG signal acquisition unit includes:

[0076] The sensor control module is used to calibrate and adjust the data parameters of the EEG sensor 13 to ensure the accuracy and stability of the EEG sensor 13, monitor the working status of the EEG sensor 13 in real time, including signal quality, power, etc., to ensure the normal operation of the EEG sensor 13, manage the start, stop, calibration and multi-channel synchronous acquisition of the EEG sensor 13, and ensure that the sensor works stably and accurately captures EEG signals;

[0077] A signal conversion module, used to convert the continuous analog EEG signal collected by the EEG sensor 13 into a digital signal;

[0078] The filter amplification module is used to filter the converted digital signal, remove noise and interference, improve signal quality, and amplify the filtered signal to reach an amplitude suitable for subsequent processing;

[0079] The filtering and amplifying module further includes performing signal quality evaluation on the digital signal after filtering and amplification:

[0080] Determine the sampling rate, sampling time and range parameters according to the characteristics of the measured signal, and collect the filtered and amplified digital signal data from the output end of the signal amplifier 2;

[0081] Further filtering the collected digital signal data to remove possible noise or interference, calculating the mean of the digital signal based on the time series, and identifying the DC component in the digital signal;

[0082] Subtracting the mean value of the digital signal from each data point of the digital signal based on the recognition result to obtain a digital signal after the DC component is removed;

[0083] The signal-to-noise ratio and distortion of the digital signal after the DC component is removed are calculated, and the calculation results are compared with the preset thresholds to evaluate whether the signal quality meets the standards and whether the signal distortion is too large;

[0084] Based on the evaluation results, a comprehensive diagnosis is made as to whether the signal quality of the digital signal meets the standards, and parameter optimization and adjustment are performed according to the diagnosis results.

[0085] In this embodiment, the sensor management and control module ensures the accuracy and stability of the sensor during the acquisition process by calibrating and adjusting the data parameters of the EEG sensor 13, promptly discovers and solves problems that may arise in the operation of the sensor, and ensures the validity and continuity of the data. The filtering and amplification module filters and amplifies the converted digital signal, which significantly improves the quality and clarity of the signal, and evaluates the signal quality to promptly discover potential problems in the signal, thereby ensuring the reliability and validity of the signal for subsequent analysis.

[0086] In this embodiment, the signal processing and analysis unit includes:

[0087] The analog-to-digital standardization module is used to standardize the processed and qualified digital signals to ensure that the amplitude and range of the signals are suitable for subsequent analysis, including normalization processing, so that the signals are within a certain numerical range, which is convenient for comparison and analysis, and calibrating the signals to eliminate system errors introduced by hardware or environmental factors, and improve the accuracy and reliability of the data;

[0088] The EEG spectrum analysis module is used to divide the digital signal into multiple continuous time periods based on the time series, and perform frequency domain signal conversion on the digital signal of each time period, wherein the length of the divided time period is adaptively adjusted according to the characteristics of the signal, and a shorter time period is used for the part with a larger signal change, and a longer time period is used otherwise, so as to improve the analysis accuracy;

[0089] Calculate the amplitude and phase of each frequency component in each time period, obtain the target spectrum value of the digital signal in each time period, and draw a spectrum diagram based on the target spectrum value;

[0090] Divide the spectrum graph into different frequency bands according to the spectrum characteristics of each time period in the spectrum graph, and analyze the activity of EEG signals in each frequency band, including power changes, frequency distribution, etc., and analyze the frequency characteristics of digital signals changing over time;

[0091] The EEG spectrum analysis module further includes:

[0092] Obtaining the patient's brain acquisition position corresponding to each digital signal in the digital signal of each time period;

[0093] Obtain the initial signal of the same brain acquisition position and the frequency amplitude and phase corresponding to each time period to establish the frequency characteristics of the position;

[0094] Generating a change feature corresponding to each brain acquisition position according to the change of the frequency characteristic over time, and extracting a position attribute of each brain acquisition position;

[0095] According to the position attributes and change characteristics corresponding to each brain acquisition position, the relationship between the change characteristics of different brain acquisition positions is established and analyzed;

[0096] Generate the patient's corresponding brain activity markers based on the relationship between the change characteristics of different brain acquisition locations, such as cognitive state, emotional changes, disease markers, etc.

[0097] The target feature extraction module is used to extract features based on the activity of EEG signals in each frequency band and the frequency characteristics of digital signals changing over time, and to screen feature parameters related to brain damage and cognitive dysfunction from the spectrum features based on the feature extraction results, such as power changes in specific frequency bands, waveform complexity, etc.

[0098] In this embodiment, the digital signal is standardized and normalized by the analog-to-digital standardization module, which improves the quality and comparability of the signal, reduces system errors, and ensures the accuracy and reliability of subsequent analysis. The EEG spectrum analysis module can more accurately capture signal changes by adaptively adjusting the length of the time period, thereby improving the accuracy of spectrum analysis, understanding the activity of EEG signals in different frequency bands in detail, and establishing the relationship between the changing characteristics of different brain acquisition positions. This allows a deeper understanding of the spatial distribution and changes of brain activity, and generates a patient's brain activity marker based on the changing characteristics of the brain acquisition position, which is helpful for diagnosing cognitive states, emotional changes, and disease markers.

[0099] In this embodiment, the early warning unit includes:

[0100] The early warning model building module is used to combine historical data and professional knowledge database to build an early warning model for predicting postoperative cognitive dysfunction and brain damage;

[0101] The warning instruction driving module is used to input the feature parameters extracted by the target feature extraction module into the constructed warning model, determine the warning category according to the output results of the warning model, match the corresponding warning signal and issue a warning such as sound alarm, screen display of warning information, etc. At the same time, send an alarm notification to medical staff.

[0102] In this embodiment, by utilizing historical data and a professional knowledge database, the risk of postoperative cognitive dysfunction and brain damage can be effectively predicted, so that preventive measures can be taken before symptoms appear, thereby improving the preventive nature of medical care. Feature parameters related to brain damage and cognitive dysfunction are screened out from spectral features according to the target feature extraction module. The early warning model can identify potential risks in advance before the patient's postoperative cognitive function becomes significantly impaired, providing the possibility for early intervention and helping to improve the patient's prognosis. Through various methods such as sound alarms and screen displays of early warning information, the effective communication of early warning information is ensured, thereby reducing misdiagnosis and missed diagnosis due to poor information transmission.

[0103] Furthermore, early warning identification is performed based on the feature extraction results after quantification processing to determine whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage, including:

[0104] Determine the patient's brain activity feature measurement matrix based on the feature extraction result after quantization processing, and calculate the corresponding covariance matrix according to the brain activity feature measurement matrix;

[0105] Determine the eigenvalue of the covariance matrix, determine the principal component eigenvector of the patient's brain activity according to the eigenvalue, and obtain the representation parameter corresponding to the principal component eigenvector of the brain activity;

[0106] Determine the distribution structure of the patient's postoperative brain activity variability and its structural characteristics over time based on the characterization parameters;

[0107] The postoperative brain activity waveform of the patient is obtained according to the distribution structure of the postoperative brain activity variability and its structural characteristics that change over time, and the postoperative brain activity waveform is converted into a time series related brain activity variation spatiotemporal scatter plot using scatter plot technology;

[0108] The dynamic characteristics of the patient's postoperative brain activity and its related plane characteristics were extracted based on the spatiotemporal scatter plot of the time series-related brain activity variation;

[0109] Determine the critical state cutoff value of the patient's postoperative brain activity based on the patient's postoperative brain activity dynamics characteristics and its related plane characteristics;

[0110] The patient's brain damage attributes are determined based on the critical state dividing value of brain activity, and based on the brain damage attributes, it is judged whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage.

[0111] The beneficial effects of the above technical solution are: by characterizing and deeply analyzing the patient's brain activity to determine the patient's brain activity state and then evaluating the brain damage properties to determine whether the patient has cognitive dysfunction after surgery, the patient can be quickly and accurately evaluated through feature analysis, thereby improving the evaluation efficiency and accuracy.

[0112] In one embodiment, an adjusting device is further provided between the electrode cap (11) and the airbag (12) for adjusting the internal pressure of the airbag, specifically:

[0113] Collecting a head image of the patient wearing the cap, determining the patient's brain shape curve based on the head image, and superimposing the brain shape curve with the internal space shape curve of the electrode cap;

[0114] Determine the space gap between the head of the patient and the electrode cap when the patient wears the electrode cap according to the processing result;

[0115] Determine the contact index between the airbag and the head of the patient wearing the airbag according to the preset position parameters and shape parameters of the space gap and the airbag in the electrode cap;

[0116] Determine the static load increment and static deformation increment of the airbag on the head of the patient wearing the airbag according to the contact index and the preset pressure of the airbag;

[0117] The comfort index of the patient wearing the airbag at the preset pressure is calculated based on the static load increment and static deformation increment:

[0118]

[0119] Wherein, Q represents the comfort index of the patient under the preset pressure, P represents the adjustable space ratio of the electrode cap when the patient wears the electrode cap, δ represents the Poisson's ratio of the airbag, μ represents the comfort gain factor of the material of the airbag for human skin, F represents the static load increment of the airbag for the head of the patient, E represents the static deformation increment of the airbag for the head of the patient, G represents the sum of the load and deformation that the user can bear under the best comfort, θ represents the matching factor between the electrode cap and the head of the patient,

[0120] The airbag pressure adjustment method is determined according to the comfort index of the patient wearing the airbag at a preset pressure, and the airbag pressure is increased or decreased according to the adjustment method.

[0121] The beneficial effects of the above technical solution are: by calculating the comfort of the patient when wearing the electrode cap based on the static deformation increment and the static load increment as reference conditions, the comfort of the patient when wearing the electrode cap can be intuitively and clearly determined through mapping indicators, and then the airbag pressure can be reasonably adjusted to ensure the patient's wearing experience, thereby improving practicality and comfort.

[0122] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A brain damage early warning device based on electroencephalogram monitoring, comprising an electroencephalogram data acquisition device (1) and a processing and display terminal (3), characterized in that: The electroencephalogram data acquisition device (1) comprises an electrode cap (11), an air bag (12), an electroencephalogram sensor (13) and a connecting wire (14); the air bag (12) is arranged in the electrode cap (11); the electroencephalogram sensor (13) is arranged inside the air bag (12); one side of the electroencephalogram sensor (13) is electrically connected to a signal amplifier (2) via the connecting wire (14); and one side of the signal amplifier (2) is electrically connected to a processing and display terminal (3).

2. A brain damage early warning device based on EEG monitoring as claimed in claim 1, characterized in that: Processing display terminal (3), including: An electroencephalogram signal acquisition unit, used to acquire the patient's electroencephalogram signal in real time based on the electroencephalogram sensor (13), transmit the signal acquired by the electroencephalogram sensor (13) to the signal amplifier (2) for amplification processing, and transmit the processed signal to the signal processing and analysis unit; A signal processing and analysis unit is used to standardize the acquired signal, extract the features of the patient's EEG signal based on spectrum analysis, and quantify the extracted target feature data; The early warning unit is used to build an early warning model for identifying postoperative cognitive dysfunction and brain damage, perform early warning identification based on the feature extraction results after quantification processing, determine whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage, and issue an early warning based on the judgment results; The display unit is used to provide an intuitive user interface, display real-time EEG spectrum, characteristic parameters and warning information, and support medical staff to view, analyze and record monitoring results.

3. A brain damage early warning device based on EEG monitoring as claimed in claim 2, characterized in that: Based on the feature extraction results after quantification processing, early warning identification is performed to determine whether the patient's EEG signals have trend characteristics of postoperative cognitive dysfunction and brain damage, including: Determine the patient's brain activity feature measurement matrix based on the feature extraction result after quantization processing, and calculate the corresponding covariance matrix according to the brain activity feature measurement matrix; Determine the eigenvalue of the covariance matrix, determine the principal component eigenvector of the patient's brain activity according to the eigenvalue, and obtain the representation parameter corresponding to the principal component eigenvector of the brain activity; Determine the distribution structure of the patient's postoperative brain activity variability and its structural characteristics over time based on the characterization parameters; The postoperative brain activity waveform of the patient is obtained according to the distribution structure of the postoperative brain activity variability and its structural characteristics that change over time, and the postoperative brain activity waveform is converted into a time series related brain activity variation spatiotemporal scatter plot using scatter plot technology; The dynamic characteristics of the patient's postoperative brain activity and its related plane characteristics were extracted based on the spatiotemporal scatter plot of the time series-related brain activity variation; Determine the critical state cutoff value of the patient's postoperative brain activity based on the patient's postoperative brain activity dynamics characteristics and its related plane characteristics; The patient's brain damage attributes are determined based on the critical state dividing value of brain activity, and based on the brain damage attributes, it is judged whether the patient's EEG signal has trend characteristics of postoperative cognitive dysfunction and brain damage.

4. A brain damage early warning device based on EEG monitoring as claimed in claim 2, characterized in that: The EEG signal acquisition unit comprises: A sensor control module, used to calibrate and adjust data parameters of the EEG sensor (13), monitor the working status of the EEG sensor (13) in real time, and manage the start, stop, calibration and multi-channel synchronous acquisition of the EEG sensor (13); A signal conversion module, used for converting the continuous analog EEG signal collected by the EEG sensor (13) into a digital signal; The filtering and amplifying module is used to filter the converted digital signal and amplify the filtered signal.

5. A brain damage early warning device based on EEG monitoring as claimed in claim 4, characterized in that: The filtering and amplification module also includes signal quality evaluation of the digital signal after filtering and amplification: Determine the sampling rate, sampling time and range parameters according to the characteristics of the measured signal, and collect the digital signal data after filtering and amplification from the output end of the signal amplifier (2); Performing further filtering processing on the collected digital signal data, calculating the mean value of the digital signal based on the time series, and identifying the DC component in the digital signal; Subtracting the mean value of the digital signal from each data point of the digital signal based on the recognition result to obtain a digital signal after the DC component is removed; The signal-to-noise ratio and distortion of the digital signal after the DC component is removed are calculated, and the calculation results are compared with the preset thresholds to evaluate whether the signal quality meets the standards and whether the signal distortion is too large; Based on the evaluation results, a comprehensive diagnosis is made as to whether the signal quality of the digital signal meets the standards, and parameter optimization and adjustment are performed according to the diagnosis results.

6. A brain damage early warning device based on EEG monitoring as claimed in claim 5, characterized in that: Signal processing and analysis unit, including: The analog-to-digital standardization module is used to standardize the processed digital signals with qualified quality; The EEG spectrum analysis module is used to divide the digital signal into multiple continuous time periods based on the time series, and perform frequency domain signal conversion on the digital signal of each time period, wherein the length of the divided time period is adaptively adjusted according to the characteristics of the signal; Calculate the amplitude and phase of each frequency component in each time period, obtain the target spectrum value of the digital signal in each time period, and draw a spectrum diagram based on the target spectrum value; Divide the spectrum graph into different frequency bands according to the spectrum characteristics of each time period in the spectrum graph, analyze the activity of EEG signals in each frequency band, and analyze the frequency characteristics of digital signals changing over time; The target feature extraction module is used to extract features based on the activity of EEG signals in each frequency band and the frequency characteristics of digital signals changing over time, and to screen feature parameters related to brain damage and cognitive dysfunction from the spectrum features based on the feature extraction results.

7. A brain damage early warning device based on EEG monitoring as claimed in claim 6, characterized in that: The EEG spectrum analysis module also includes: Obtaining the patient's brain acquisition position corresponding to each digital signal in the digital signal of each time period; Obtain the initial signal of the same brain acquisition position and the frequency amplitude and phase corresponding to each time period to establish the frequency characteristics of the position; Generating a change feature corresponding to each brain acquisition position according to the change of the frequency characteristic over time, and extracting a position attribute of each brain acquisition position; According to the position attributes and change characteristics corresponding to each brain acquisition position, the relationship between the change characteristics of different brain acquisition positions is established and analyzed; The patient's corresponding brain activity signature is generated based on the relationship between the changing characteristics of different brain acquisition locations.

8. The brain damage early warning device based on EEG monitoring as claimed in claim 7, characterized in that: Early warning unit, including: The early warning model building module is used to combine historical data and professional knowledge database to build an early warning model for predicting postoperative cognitive dysfunction and brain damage; The early warning instruction driving module is used to input the feature parameters extracted by the target feature extraction module into the constructed early warning model, determine the early warning category according to the output results of the early warning model, match the corresponding early warning signal and issue an early warning, and at the same time, send an alarm notification to medical staff.

9. A brain damage early warning device based on EEG monitoring as claimed in claim 8, characterized in that: Display unit, comprising: Real-time signal display module, used to display the real-time collected EEG waveform and spectrum; A processing result display module is used to display the output results of the signal processing and analysis unit; The warning information display module is used to highlight the warning information when potential risks are detected, including the warning type, risk level and recommended intervention measures.

10. The brain damage early warning device based on EEG monitoring as claimed in claim 1, characterized in that: An adjusting device is also provided between the electrode cap (11) and the air bag (12) for adjusting the internal pressure of the air bag, specifically: Collecting a head image of the patient wearing the cap, determining the patient's brain shape curve based on the head image, and superimposing the brain shape curve with the internal space shape curve of the electrode cap; Determine the space gap between the head of the patient and the electrode cap when the patient wears the electrode cap according to the processing result; Determine the contact index between the airbag and the head of the patient wearing the airbag according to the preset position parameters and shape parameters of the space gap and the airbag in the electrode cap; Determine the static load increment and static deformation increment of the airbag on the head of the patient wearing the airbag according to the contact index and the preset pressure of the airbag; The comfort index of the patient wearing the airbag at the preset pressure is calculated based on the static load increment and static deformation increment: Wherein, Q represents the comfort index of the patient under the preset pressure, P represents the adjustable space ratio of the electrode cap when the patient wears the electrode cap, δ represents the Poisson's ratio of the airbag, μ represents the comfort gain factor of the material of the airbag for human skin, F represents the static load increment of the airbag for the head of the patient, E represents the static deformation increment of the airbag for the head of the patient, G represents the sum of the load and deformation that the user can bear under the best comfort, θ represents the matching factor between the electrode cap and the head of the patient, The airbag pressure adjustment method is determined according to the comfort index of the patient wearing the airbag at a preset pressure, and the airbag pressure is increased or decreased according to the adjustment method.

Images