Vagus nerve stimulation parameter closed-loop adjustment method and system based on electroencephalogram characteristics

Abstract

The invention discloses a vagus nerve stimulation parameter closed-loop adjustment method and system based on electroencephalogram characteristics. The method comprises the steps that real-time electroencephalogram signals of a patient are obtained, and time domain information and frequency domain information of the electroencephalogram signals of all frequency bands in the real-time electroencephalogram signals are extracted; on the basis of the time domain information and the frequency domain information of the electroencephalogram signals of all the frequency bands, electroencephalogram signal index features are calculated, and the electroencephalogram signal index features comprise an electroencephalogram signal power spectrum, a brain dynamic symmetry feature, a brain function connection feature and a rhythm feature; determining the state type of the patient according to the electroencephalogram signal index characteristics; determining parameter configuration information of vagus nerve stimulation according to the state type of the patient; and adjusting parameters of the vagus nerve electrical stimulation equipment according to the parameter configuration information of vagus nerve stimulation. According to the invention, timely and accurate electrical stimulation can be applied to a patient, the treatment accuracy is improved, the stimulation efficiency and the treatment effect are enhanced, side effects are reduced, and more accurate and individualized treatment management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of neural stimulation systems, and in particular to a closed-loop adjustment method and system for vagus nerve stimulation parameters based on electroencephalographic characteristics. Background Art

[0002] Traditional vagus nerve stimulation (VNS) is a neuroelectric regulation technology with low trauma and wide application range. However, traditional vagus nerve stimulation is not only invasive and expensive, but also requires battery replacement through surgery every 10 years. In addition, it can cause adverse reactions such as arrhythmia, dyspnea, indigestion, nausea and vomiting during the stimulation process, and these reactions cannot completely disappear as the treatment progresses.

[0003] The transcutaneous auricular VNS (ta-VNS) technology has most of the above disadvantages. By stimulating the auricular branch of the vagus nerve, ta-VNS can avoid invasive surgery while retaining the effectiveness of traditional vagus nerve stimulation, and it also brings fewer adverse reactions. Auricular vagus nerve stimulation can be widely used in the treatment of epilepsy, stroke rehabilitation, depression, insomnia, etc.

[0004] However, the existing parameter adjustment method of ta-VNS technology is generally for doctors to set a stimulation parameter range, and patients adjust it by themselves. This adjustment method is a passive and very inaccurate adjustment method, and the actual effect is not ideal. This method also cannot accurately match the changes in the patient's physiological state, the stimulation effect is poor, the accuracy of treatment is low, and the probability of side effects is also high. Therefore, it is necessary to design a closed-loop adjustment method for vagus nerve stimulation parameters based on EEG characteristics to overcome the shortcomings of the existing technology. Summary of the invention

[0005] In view of the above problems, the purpose of this application is to provide a closed-loop adjustment method, system, device and storage medium for vagus nerve stimulation parameters based on EEG characteristics. By detecting and analyzing the patient's status through EEG, timely and accurate electrical stimulation can be automatically applied to the patient when the patient's status changes, so that the patient can obtain a more ideal stimulation effect.

[0006] The purpose of this application is achieved by the following technical solutions: In a first aspect, the present invention provides a closed-loop adjustment method for vagus nerve stimulation parameters based on EEG characteristics, comprising: Obtain the patient's real-time EEG signal and extract the time domain information and frequency domain information of the EEG signal in each frequency band; Based on the time domain information and frequency domain information of the EEG signals in each frequency band, the EEG signal index features are calculated, wherein the EEG signal index features include the EEG signal power spectrum, brain dynamic symmetry features, brain functional connection features, and rhythm features; Determine the patient's condition type based on the EEG signal index characteristics; Determining parameter configuration information for vagus nerve stimulation according to the patient's condition type; The parameters of the vagus nerve electrical stimulation device are adjusted according to the parameter configuration information of the vagus nerve stimulation.

[0007] In a preferred embodiment, the EEG signal power spectrum includes power spectral density, the ratio of delta waves and alpha waves; the brain dynamic symmetry characteristics include brain symmetry index and laterality coefficient; the brain functional connection characteristics include coherence analysis results, functional connection characteristics, and cortical-muscle coherence characteristics; the rhythm characteristics include phase locking value and phase synchronization index.

[0008] In a preferred embodiment, the parameter configuration information includes: stimulation amplitude, stimulation frequency, single stimulation duration, pulse width, stimulation time interval, start mode, and stimulation mode. The start mode is a bidirectional waveform start mode or a unidirectional waveform start mode. The stimulation mode is a monaural stimulation mode or a binaural stimulation mode.

[0009] In a preferred embodiment, the parameter configuration information of vagus nerve stimulation is determined according to the patient's state type. Specifically, it is determined whether the latest patient's state type is consistent with the patient's state type obtained last time. If they are inconsistent, the parameter configuration information of vagus nerve stimulation is determined according to the latest patient's state type.

[0010] In a preferred embodiment, determining the parameter configuration information of vagus nerve stimulation according to the patient's state type specifically includes the following steps: Acquire a first training data set, wherein the first training data set includes a patient's state type and parameter configuration information of vagus nerve stimulation corresponding to each state type; Using the first training data set to train parameter configuration model; The most recently determined patient's state type is input into the parameter configuration model to obtain parameter configuration information corresponding to the patient's state type.

[0011] In a preferred embodiment, the adjusting the parameters of the vagus nerve electrical stimulation device according to the parameter configuration information of the vagus nerve stimulation is specifically: based on the parameter configuration information corresponding to the state type of the patient, the parameters of the vagus nerve electrical stimulation device are adjusted using the programmable device so that the vagus nerve electrical stimulation device applies corresponding electrical stimulation to the patient.

[0012] In a preferred embodiment, the use of the programmable device to adjust the parameters of the stimulator so that the stimulator applies corresponding electrical stimulation to the patient is specifically as follows: the programmable device obtains the parameter configuration information of the vagus nerve stimulation, generates adjustment parameters based on the information and sends them to the vagus nerve electrical stimulation device, and the adjustment parameters automatically take effect when the vagus nerve electrical stimulation device performs the next stimulation.

[0013] In a preferred embodiment, the method further comprises the step of obtaining a status type of the patient.

[0014] In a second aspect, the present invention provides a closed-loop adjustment system for vagus nerve stimulation parameters based on EEG characteristics, which is used to automatically adjust the parameters of a vagus nerve electrical stimulation device applied to a patient, and the device comprises: A data acquisition module, used to obtain the patient's real-time EEG signal; An information extraction module is used to extract the time domain information and frequency domain information of the EEG signals in each frequency band in the EEG signals; A calculation module, used to calculate the EEG signal index characteristics based on the time domain information and frequency domain information of the EEG signals in each frequency band, wherein the EEG signal index characteristics include the EEG signal power spectrum, brain dynamic symmetry characteristics, brain functional connection characteristics, and rhythm characteristics; A type determination module, used to determine the patient's state type based on the EEG signal index characteristics; A parameter determination module, used to determine parameter configuration information of vagus nerve stimulation according to the patient's state type; The adjustment module is used to adjust the parameters of the vagus nerve electrical stimulation device according to the parameter configuration information of the vagus nerve stimulation.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics described in the first aspect are implemented.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for closed-loop adjustment of vagus nerve stimulation parameters based on EEG characteristics described in the first aspect.

[0017] The closed-loop adjustment method and system of vagus nerve stimulation parameters based on EEG characteristics of the present invention extracts the time domain and frequency domain information of EEG signals in each frequency band based on the patient's EEG signals, further calculates the EEG signal index characteristics, and determines the real-time patient state type accordingly, and finally determines the new parameters of vagus nerve electrical stimulation, and sends the new parameters to the vagus nerve electrical stimulation device. Such a design can adjust the stimulation parameters according to the real-time EEG signals, does not require manual adjustment, and can apply timely and accurate electrical stimulation to the patient, thereby improving the accuracy of treatment, enhancing the stimulation efficiency and treatment effect, reducing the occurrence of side effects, and achieving more accurate and individualized treatment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 The flowchart is a closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics; Figure 2 It is a flow chart of a closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics in a specific embodiment; Figure 3 is a flow chart of a closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics in another specific embodiment; Figure 4 Schematic diagram of the framework of the closed-loop adjustment system of vagus nerve stimulation parameters based on EEG characteristics. DETAILED DESCRIPTION

[0020] Below, the present application is further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0021] The following embodiments of the present invention may be executed separately or in combination with each other, and the embodiments of the present invention do not impose any specific restrictions on this. In the embodiments of the present invention, "first", "second", etc. are used to describe, and the terms "first", "second", etc. are only used to distinguish names, and do not indicate a sequence, a difference in importance, or the same structure. The "and / or" mentioned in the present invention refers to any and all combinations of one or more of the related listed items.

[0022] See also Figure 1The present application embodiment provides a closed-loop adjustment method for vagus nerve stimulation parameters based on EEG characteristics, comprising the following steps: Obtain the patient's real-time EEG signal and extract the time domain information and frequency domain information of the EEG signal in each frequency band; Based on the time domain information and frequency domain information of the EEG signals in each frequency band, calculating the EEG signal index features, the EEG signal index features including EEG signal power spectrum, brain dynamic symmetry features, brain functional connection features, and rhythm features; Determine the patient's state type based on the (most recently calculated) EEG signal index characteristics; Determining parameter configuration information for vagus nerve stimulation according to the (most recently determined) patient state type; Adjust the parameters of the vagus nerve electrical stimulation device according to the (most recently determined) vagus nerve stimulation parameter configuration information.

[0023] This method is described in detail below.

[0024] The closed-loop adjustment method is used to calculate and close-loop adjust the vagus nerve stimulation parameters through the results of EEG signal detection and analysis. In this embodiment, the vagus nerve electrical stimulation device is adjusted by this method, wherein the stimulator is a transcutaneous ear vagus nerve stimulator, and the action site is the position of the cymba of the left and right ears. The parameters of the stimulator include: the amplitude of vagus nerve electrical stimulation (0.1mA~50mA), the stimulation frequency (0.1Hz~100Hz), the duration of a single stimulation (1 second~24 hours), the time interval between two adjacent stimulations (1 second~24 hours), the start mode (including two modes of bidirectional waveform and unidirectional waveform), the pulse width (μs), and the stimulation mode (monaural stimulation mode or binaural stimulation mode). In specific applications, the various parameters of the stimulator can be adjusted in the current mode or the voltage mode. The bidirectional waveform start mode is to generate a bidirectional square wave of equal size, opposite direction and adjustable frequency, which can be called a bidirectional square wave mode, and the unidirectional waveform start mode is to generate a unidirectional square wave by the stimulator, which can be called a unidirectional square wave mode.

[0025] The patients in the embodiments of the present application may be patients suffering from epilepsy, stroke rehabilitation, depression and / or insomnia disorders.

[0026] For epilepsy, the most commonly used initial setting parameters are 20Hz, pulse width 200μs, about 2mA current (the patient can feel the current stimulation, but no discomfort), single stimulation duration 0.5 hours, two stimulation intervals 24 hours, start mode bidirectional waveform, pulse waveform alternate stimulation in both ears at the same time. For stroke patients, the initial setting parameters can be set at 30Hz, unilateral stimulation of the right ear, and the other configuration parameters are the same as before.

[0027] See also Figure 2A closed-loop adjustment method for vagus nerve stimulation parameters based on EEG characteristics is used to automatically adjust the parameters of a vagus nerve electrical stimulation device applied to a patient, comprising the following steps: Step S101: collecting multi-channel scalp EEG signals from the patient, and extracting time domain information and frequency domain information of the EEG signals in each frequency band.

[0028] The device used to collect brain electrical signals is a dedicated electroencephalograph, which can be a medical device or a wearable device. As an embodiment, the brain electrical signals are obtained by a scalp electroencephalograph, which records the electrical signals of electrodes and reference electrodes on the scalp to obtain information about brain activity.

[0029] The time domain information and frequency domain information of the EEG signals in each frequency band are extracted through a program-controlled device, which is referred to as a program-controlled device. The program-controlled device can adopt a program controller existing in the prior art, that is, a program controller arranged outside the patient's body; or, the program-controlled device can also be a separate hardware device, which is an electronic device that can interact with the stimulator or the program controller for data, such as a tablet computer, a computer, a mobile phone or a smart wearable device, etc. The patient or caregiver can use this program-controlled device to perform marking operations. In general, the program-controlled device is equipped with a computer program (i.e., software), and when the computer program is executed by the processor, the steps of the parameter adjustment method in the embodiment of the present application can be implemented.

[0030] The first deep learning model is trained using the data set 1 to obtain a signal time domain and frequency domain feature extraction model. The first deep learning model is, for example, a given neural network or a rebuilt neural network. The data set 1 includes a number of EEG signals, time domain information of EEG signals in each frequency band, and frequency domain information of EEG signals in each frequency band.

[0031] By inputting the patient's EEG signal into the trained first deep learning model, the time domain information and frequency domain information of the output EEG signals in each frequency band can be obtained.

[0032] As a specific embodiment, when the training data of each model is collected, the data set may include the patient's state type, and the patient's state type is associated with the EEG signal. The patient's state type is also associated with the parameters of the vagus nerve electrical stimulation device. According to this, the parameters of the vagus nerve electrical stimulation device are determined according to the EEG signal index characteristics, that is, the EEG signal index characteristics are determined according to the EEG signal, and the patient's state type can be determined according to the EEG signal index characteristics, and the parameters of the ideal stimulator corresponding to the patient's state type are determined according to the patient's state type. It can be understood that the data set 1 used to train the first deep learning model includes the patient's state type associated with the EEG signal.

[0033] The patient's state type refers to the patient's living state and / or the type of the patient's physiological state. The state type is determined according to the patient's diet, medication, sleep, etc., and each state type has corresponding parameter configuration information for vagus nerve stimulation. For example, the state type may include at least one of the following: before going to bed, after getting up (may include after getting up and before breakfast), after taking medicine (may include the first period, second period, third period, etc. after medication), after meal (may include which period after breakfast, which period after lunch, which period after dinner, after meal but before medication, etc.), during exercise (may be specific to the intensity level of exercise). The state type can also be determined according to the patient's physiological state, such as a state of mental distress, a state of hunger and hypoglycemia. These state types can be pre-set options, and you can select one of them when marking, or they can be customized by the user of the programmable device.

[0034] Step S102: Based on all the time domain information and all the frequency domain information obtained in step S101, further calculate the EEG signal index features. The EEG signal index features include but are not limited to the EEG signal power spectrum, brain dynamic symmetry features, brain functional connectivity features, and rhythm features. The brain dynamic symmetry features are features about symmetry in brain dynamics. For example, the waveforms, frequencies, and amplitudes of the EEG activities in the corresponding regions of the two hemispheres of the brain are roughly the same, which is symmetrical.

[0035] In this embodiment, specific extraction parameters of the EEG signal index feature include: The power spectrum of EEG signals includes the calculation formula of power spectral density (PSD): Among them, is the Fourier transform of a single EEG channel signal, is the recording time of the signal segment. By traversing the frequency band, for example, traversing 0.1~70Hz, the PSD values ​​of the EEG signals of all channels in the frequency band can be obtained.

[0036] The power spectrum of EEG signals includes the calculation formula of delta / alpha ratio (DAR) of delta waves and alpha waves: in, Yes Frequency band (0.5~4Hz) Numerical summation, Yes Frequency band (8~14Hz) sum of values; The brain dynamic symmetry characteristics include the calculation formula of the brain symmetry index (BSI): BSI = (|Average power of left hemisphere channel - average power of right hemisphere channel|) / (Average power of left hemisphere channel + average power of right hemisphere channel) Among them, the average power of the left hemisphere channel is the EEG signal of the left hemisphere of the brain Average value, the average power of the right hemisphere channel is the EEG signal of the right hemisphere of the brain Average. EEG hemispheric signal of the brain axis Values ​​can be attributed to the left hemisphere, right hemisphere, or not counted.

[0037] The dynamic symmetry characteristics of the brain include the calculation formula of the laterality coefficient (LC): LC= (Total power of the contralateral hemisphere - total power of the ipsilateral hemisphere) / (Total power of the contralateral hemisphere + total power of the ipsilateral hemisphere).

[0038] Among them, the average power of the left hemisphere channel is the EEG signal of the left hemisphere of the brain The sum value, the average power of the right hemisphere channel is the EEG signal of the right hemisphere of the brain Total value. EEG hemispheric signal of the brain axis Values ​​can be attributed to the left hemisphere, right hemisphere, or not counted.

[0039] The brain functional connectivity features include: The calculation formula of the coherence analysis (CA) results is: in, represents the coherence analysis results, Indicates the frequency f Place x The cross power spectrum between the EEG signal of the channel and the EEG signal of the yth channel, Indicates the frequency f Place x The power spectrum of the channel EEG signal, Indicates the frequency f Place y Power spectrum of channel EEG signal.

[0040] Brain functional connectivity features include: The calculation formula of functional connectivity (FC) features is: in, For the a The time domain segment of the channel EEG signal, For the a The time domain segment of the channel EEG signal, corr is the Pearson correlation coefficient.

[0041] The calculation formula of brain functional connectivity features includes the cortico-muscular coherence (CMC) feature: Rhythm characteristics include: Phase locking value (PLV) is calculated as: in, For the a The phase value of the channel EEG signal, For the b The phase value of the channel EEG signal, j Is the imaginary part.

[0042] Rhythm characteristics include: Phase synchrony index (PSI) is calculated as: in, sign is the threshold function. For any real number x , if x is greater than 0, then sign ( x )=1; if x is equal to 0, then sign ( x )=0; if x Less than 0, then sign ( x )=-1 Step S103: input the calculated EEG signal index features as parameters into the machine learning and deep learning classifiers to calculate new parameters for vagus nerve electrical stimulation.

[0043] The machine learning and deep learning classifiers first determine the patient's state type, and then determine the parameter configuration information of the vagus nerve stimulation according to the patient's state type.

[0044] Specifically, the patient's state type is first obtained, and then it is determined whether the latest obtained (this time obtained) patient's state type is consistent with the patient's state type obtained last time. If they are inconsistent, the parameter configuration information of vagus nerve stimulation is determined according to the latest obtained patient's state type.

[0045] The patient's EEG power spectrum, brain dynamic symmetry characteristics, brain functional connectivity characteristics, and rhythm characteristics are associated and stored in Dataset 2, so that Dataset 2 includes the patient's multiple EEG signals and the EEG signal index characteristics corresponding to each EEG signal, where each state type corresponds to an EEG signal. It can be understood that Dataset 2 includes EEG signal index characteristics, state types, and parameter configuration information for vagus nerve stimulation.

[0046] The second deep learning model is trained using data set 2 to obtain a vagus nerve stimulation parameter configuration model.

[0047] In a specific embodiment, the following steps are included: obtaining a first training data set, the first training data set including the patient's state type and parameter configuration information of vagus nerve stimulation corresponding to each state type; training a parameter configuration model using the first training data set; inputting the most recently determined patient's state type into the trained parameter configuration model to obtain parameter configuration information corresponding to the patient's state type.

[0048] Furthermore, the method also comprises the following steps: obtaining a second training data set, wherein the second training data set includes the patient's state type and the EEG signal index feature corresponding to each state type; training a state type model using the second training data set; and inputting the latest determined EEG signal index feature into the trained state type model to obtain the patient's state type.

[0049] Here, the parameter configuration information of vagus nerve stimulation can be directly output according to the EEG signal index characteristics, and the parameter configuration information of vagus nerve stimulation can also be output according to the patient's state type on this basis. In this embodiment, on the one hand, the real-time state type can be input to obtain new parameter configuration information corresponding to the real-time state type, so as to stimulate the patient using the new parameter configuration information; on the other hand, multiple real-time state types can be identified, with a wide range of applications and a high level of intelligence.

[0050] Step S104: The program-controlled device sends the new parameters to the vagus nerve electrical stimulation device via wireless or cable communication. The program-controlled device obtains the parameter configuration information of the vagus nerve stimulation, generates adjustment parameters based on the information and sends them to the vagus nerve electrical stimulation device. The adjustment parameters automatically take effect when the vagus nerve electrical stimulation device performs the next stimulation, so that the stimulation device applies corresponding electrical stimulation to the patient. This wireless communication method can be a communication method such as Bluetooth, WIFI, etc., and the cable communication method can be a USB interface, etc.

[0051] In summary, this method can identify the patient's state based on the patient's EEG signals when the patient's physiological state changes, and automatically apply timely and accurate vagus nerve stimulation parameters to the patient according to the parameter configuration information corresponding to the state, so that the patient can obtain a more ideal stimulation effect.

[0052] See also Figure 3 , in some embodiments, as Figure 2 The detailed S101~S104 scheme describes the steps S201~S210 of extracting features based on EEG signals and calculating new parameters for vagus nerve regulation. S201 uses an electroencephalograph to collect data; S202~210 uses a program-controlled device for calculation, storage, and distribution.

[0053] Step S201: Use a typical 10-20 lead system to collect continuous EEG signals from the patient. In this step, the EEG signals may be filtered, for example, by performing 0.1-70 Hz bandpass filtering and 50 Hz power frequency notch filtering.

[0054] Step S202: Slice the patient's EEG signal in the time domain according to 5 seconds and 50% overlap rate before and after to obtain the time domain EEG data of each channel of the slice.

[0055] Step S203: Perform Fourier transform on the time domain EEG data of each channel of the slice to obtain frequency domain EEG data of the corresponding channel.

[0056] Step S204: Calculate the coherence analysis CA and functional connectivity FC features based on the time-domain EEG data of each channel.

[0057] Step S205: Calculate the power spectral density PSD, the ratio of delta waves to alpha waves DAR, the brain symmetry index BSI, the laterality coefficient LC, the cortical-muscle coherence CMC, the phase locking value PLV, and the phase synchronization index PSI features according to the frequency domain EEG data of each channel.

[0058] Step S206: Fuse the time domain features calculated in step S204 and the frequency domain features calculated in step S205, and use them as the first data set, that is, obtain the first data set, which includes the EEG signal index features, that is, the first data set includes the EEG signal power spectrum, brain dynamic symmetry features, brain functional connection features, and rhythm features.

[0059] Step S207: Use the historical vagus nerve stimulation parameters as configuration samples to establish a second data set. The data in the first data set and the data in the second data set have a corresponding relationship. The vagus nerve stimulation parameters include: the amplitude of vagus nerve electrical stimulation (0.1mA~50mA), stimulation frequency (0.1Hz~100Hz), single stimulation duration (1 second~24 hours), pulse width (μs), time interval between two stimulations (1 second~24 hours), start mode (bidirectional waveform or single waveform), monaural or binaural stimulation mode.

[0060] Step S208: Use the first data set in step S206 and the second data set in step S207 as learning data, input the deep learning classifier for calculation, and output the new configuration parameters of vagus nerve stimulation.

[0061] Step S209: The new parameters of vagus nerve stimulation are calculated by the deep learning classifier, including: the amplitude of vagus nerve electrical stimulation (0.1mA~50mA), stimulation frequency (0.1Hz~100Hz), single stimulation duration (1 second~24 hours), pulse width (μs), time interval between two stimulations (1 second~24 hours), start mode (bidirectional waveform with alternating waveform +- or unidirectional waveform with only + direction), monaural or binaural stimulation mode. The new parameters are packaged as new configuration parameters and wait to be sent to the vagus nerve stimulation device.

[0062] Step 210: Send the new parameters to the vagus nerve electrical stimulation device via wireless or cable communication, such as Bluetooth, WIFI, etc., and the cable communication may be a USB interface, etc.

[0063] In a preferred embodiment, the closed-loop adjustment method further includes the step of obtaining the patient's state type. The patient or a doctor or other personnel directly inputs the patient's state type (by keystroke, voice, typing, etc.), that is, the input patient's state type is directly obtained without calculating the EEG signal index feature, and the parameter configuration information of the vagus nerve stimulation is determined according to the externally input patient's state type, and then the parameters of the vagus nerve electrical stimulation device are determined and adjusted accordingly.

[0064] The method of closed-loop adjustment of vagus nerve electrical stimulation signal parameters based on EEG characteristics in this embodiment is based on the EEG signals collected from the patient, and the time domain and frequency domain information of the EEG signals in each frequency band are extracted, and the EEG signal index characteristics are further calculated, thereby determining the real-time patient state type, and finally determining the new parameters of vagus nerve electrical stimulation, and sending the new parameters to the vagus nerve electrical stimulation device. This method adjusts the stimulation parameters according to the real-time EEG signals, and adjusts the stimulation mode according to the feedback of the patient's state changes. It does not require manual participation in the adjustment, and realizes automatic closed-loop adjustment (i.e., closed-loop adjustment is realized). It can apply timely and accurate electrical stimulation to the patient, improve the accuracy of treatment, thereby reducing the occurrence of side effects, and realize more accurate and individualized treatment management, and enhance stimulation efficiency and treatment effects.

[0065] This embodiment collects and analyzes EEG signals and adjusts the feedback parameter adjustment cycle of the vagus nerve electrical stimulation device on a time scale of several minutes to several weeks to achieve real-time closed-loop control and long-term closed-loop adjustment of vagus nerve electrical stimulation parameter solutions.

[0066] See also Figure 4 This embodiment provides a closed-loop adjustment system for vagus nerve stimulation parameters based on EEG characteristics, which is used to automatically adjust the parameters of a vagus nerve electrical stimulation device applied to a patient. The device includes: A data acquisition module 10 is used to obtain the patient's real-time EEG signal; The information extraction module 20 is used to extract the time domain information and frequency domain information of the EEG signals in each frequency band in the EEG signals; A calculation module 30, for calculating the EEG signal index characteristics based on the time domain information and frequency domain information of the EEG signal in each frequency band, wherein the EEG signal index characteristics include the EEG signal power spectrum, brain dynamic symmetry characteristics, brain functional connection characteristics, and rhythm characteristics; A type determination module 40, for determining the patient's state type according to the EEG signal index characteristics; A parameter determination module 50, for determining parameter configuration information of vagus nerve stimulation according to the patient's state type; The adjustment module 60 is used to adjust the parameters of the vagus nerve electrical stimulation device according to the parameter configuration information of the vagus nerve stimulation.

[0067] When the system for closed-loop adjustment of vagus nerve stimulation parameters based on EEG characteristics is implemented, the closed-loop adjustment of stimulation parameters can be achieved by referring to the closed-loop adjustment method for vagus nerve stimulation parameters based on EEG characteristics in any of the above embodiments, and the specific implementation steps will not be repeated here.

[0068] In one embodiment, the patient's EEG signal and state type are associated and stored in a data set, so that the data set includes the patient's EEG signal and the state type corresponding to the EEG signal. This data set is used for model training to simultaneously determine the information extraction module 20, the calculation module 30 and the type determination module 40, so as to extract the time domain information and frequency domain information of the EEG signal in each frequency band in the EEG signal, calculate the EEG signal index feature based on the time domain information and frequency domain information of the EEG signal in each frequency band, and determine the patient's state type according to the EEG signal index feature.

[0069] According to the method of the present invention, an electronic device can be implemented, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics are implemented.

[0070] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for closed-loop adjustment of vagus nerve stimulation parameters based on EEG characteristics.

[0071] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0072] The memory may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage. In addition, the memory may include any combination of computer-readable storage media, such as semiconductor memory chips, magnetic disks, and optical disks.

[0073] The memory stores executable codes, and when the executable codes are processed by the processor, the processor can execute part or all of the methods described above.

[0074] Those skilled in the art to which the present invention belongs can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0075] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may also be combined, the steps may be implemented in any order, and there are many other changes in different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A closed-loop adjustment method for vagus nerve stimulation parameters based on EEG characteristics, characterized in that: include: Obtain the patient's real-time EEG signal and extract the time domain information and frequency domain information of the EEG signal in each frequency band; Based on the time domain information and frequency domain information of the EEG signals in each frequency band, the EEG signal index features are calculated, wherein the EEG signal index features include the EEG signal power spectrum, brain dynamic symmetry features, brain functional connection features, and rhythm features; Determine the patient's condition type based on the EEG signal index characteristics; Determining parameter configuration information for vagus nerve stimulation according to the patient's condition type; The parameters of the vagus nerve electrical stimulation device are adjusted according to the parameter configuration information of the vagus nerve stimulation.

2. The closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics according to claim 1, characterized in that: The power spectrum of the EEG signal includes power spectrum density and the ratio of delta waves to alpha waves; the brain dynamic symmetry characteristics include brain symmetry index and laterality coefficient; the brain functional connection characteristics include coherence analysis results, functional connection characteristics, and cortical-muscle coherence characteristics; the rhythm characteristics include phase locking value and phase synchronization index.

3. The closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics according to claim 1, characterized in that: The parameter configuration information includes: stimulation amplitude, stimulation frequency, single stimulation duration, pulse width, stimulation time interval, start mode, and stimulation mode. The start mode is a bidirectional waveform start mode or a unidirectional waveform start mode. The stimulation mode is a monaural stimulation mode or a binaural stimulation mode.

4. The closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics according to claim 1, characterized in that: The method of determining the parameter configuration information of vagus nerve stimulation according to the patient's state type is specifically as follows: determining whether the latest patient's state type is consistent with the last patient's state type; if not, determining the parameter configuration information of vagus nerve stimulation according to the latest patient's state type.

5. The closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics according to claim 1, characterized in that: Determining the parameter configuration information of vagus nerve stimulation according to the patient's state type specifically includes the following steps: Acquire a first training data set, wherein the first training data set includes a patient's state type and parameter configuration information of vagus nerve stimulation corresponding to each state type; Using the first training data set to train parameter configuration model; The most recently determined patient's state type is input into the parameter configuration model to obtain parameter configuration information corresponding to the patient's state type.

6. The closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics according to claim 1, characterized in that: The method of using the programmable device to adjust the parameters of the stimulator so that the stimulator applies corresponding electrical stimulation to the patient is as follows: the programmable device obtains the parameter configuration information of the vagus nerve stimulation, generates adjustment parameters based on the information and sends them to the vagus nerve electrical stimulation device, and the adjustment parameters automatically take effect when the vagus nerve electrical stimulation device performs the next stimulation.

7. The closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics according to claim 1, characterized in that: The method further comprises the step of obtaining a status type of the patient.

8. A closed-loop adjustment system for vagus nerve stimulation parameters based on EEG characteristics, characterized in that: The apparatus is used to automatically adjust the parameters of a vagus nerve electrical stimulation device applied to a patient, the apparatus comprising: A data acquisition module, used to obtain the patient's real-time EEG signal; An information extraction module is used to extract the time domain information and frequency domain information of the EEG signals in each frequency band in the EEG signals; A calculation module, used to calculate the EEG signal index characteristics based on the time domain information and frequency domain information of the EEG signals in each frequency band, wherein the EEG signal index characteristics include the EEG signal power spectrum, brain dynamic symmetry characteristics, brain functional connection characteristics, and rhythm characteristics; A type determination module, used to determine the patient's state type based on the EEG signal index characteristics; A parameter determination module, used to determine parameter configuration information of vagus nerve stimulation according to the patient's state type; The adjustment module is used to adjust the parameters of the vagus nerve electrical stimulation device according to the parameter configuration information of the vagus nerve stimulation.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the closed-loop adjustment method of vagus nerve stimulation parameters based on EEG characteristics as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for closed-loop adjustment of vagus nerve stimulation parameters based on EEG characteristics according to any one of claims 1 to 7 are implemented.

Images