Method and device for adjusting nerve regulation parameters and nerve regulation instrument

By acquiring and analyzing brain wave signals, dynamically adjusting the parameters of physical therapy, the problem of poor matching of regulatory parameters with patients in the prior art is solved, and the neuroregulatory effect of Alzheimer's disease is improved.

CN115779226BActive Publication Date: 2024-12-03SHEN ZHEN MING SI YI LIAO KE JI YOU XIAN GONG SI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211724401.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-30
Publication Date
2024-12-03
Estimated Expiration
2042-12-30

AI Technical Summary

Technical Problem

When treating Alzheimer's disease, existing physical therapy methods cannot detect brain changes in real time, resulting in poor matching of regulatory parameters with the patient's condition, which in turn affects the effect of nerve regulation.

Method used

By obtaining the brain wave signal of the target person, inputting the disease classification prediction model, predicting the disease category, and comparing it with the disease category obtained by the questionnaire evaluation, adjusting the light source driving power and other regulatory parameters to match the patient's condition.

Benefits of technology

It realizes dynamic adjustment of regulatory parameters based on the patient's real-time brain wave signal, improves the matching degree and effect of neural regulation, and improves the targetedness and effectiveness of treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115779226B_ABST
    Figure CN115779226B_ABST
Patent Text Reader

Abstract

The present application is applicable to the field of neuroregulation technology, and provides a method, device and neuroregulator for adjusting neuroregulation parameters. The method includes obtaining the brain wave signal of the target person under the current regulation parameters; inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person; comparing the predicted disease category with the pre-acquired disease category to obtain a comparison result; adjusting the current regulation parameters according to the comparison result to obtain new regulation parameters; wherein the pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new regulation parameters are used to perform neuroregulation on the target person. The new regulation parameters obtained in the regulation method provided in the present application are more closely matched with the disease of the target person, so that the effect of neuroregulation on the target person according to the new regulation parameters is better.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of neuromodulation, and in particular, relates to a method and device for adjusting neuromodulation parameters and a neuromodulator. Background Art

[0002] Alzheimer's disease, commonly known as senile dementia, is a persistent neurological disorder that progresses slowly and worsens over time.

[0003] Studies have shown that physical therapy can reverse the progression of Alzheimer's disease. As a neuromodulatory method, physical therapy usually uses an irradiation source to stimulate the human brain and change brain parameters to treat Alzheimer's disease. Current physical therapy methods generally use the same control parameters for brain stimulation and are unable to detect and perceive changes in the patient's brain in real time, resulting in poor matching between the control parameters and the patient's condition, which in turn leads to poor neuromodulatory effects. Summary of the invention

[0004] In view of the above background, the embodiments of the present application provide a method and device for adjusting neural regulation parameters and a neural regulation instrument to solve the technical problem of poor neural regulation effect in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for adjusting a neural regulation parameter, the method comprising:

[0006] Obtain the brain wave signal of the target person under the current control parameters;

[0007] Inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person;

[0008] Comparing the predicted disease category with the previously obtained disease category to obtain a comparison result;

[0009] Adjust the current control parameters according to the comparison result to obtain new control parameters;

[0010] The pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameter is used to perform neurological control on the target person.

[0011] In a possible implementation manner of the first aspect, the control parameter includes at least one of a light source driving power, a light source wavelength, a light source frequency, and a light source light emitting mode.

[0012] In a possible implementation manner of the first aspect, the regulation parameter includes a light source driving power;

[0013] The adjusting the current control parameter according to the comparison result includes:

[0014] If the severity of the predicted disease category does not match the severity of the pre-acquired disease category, adjusting the light source driving power according to a mapping relationship; the mapping relationship is used to describe the corresponding relationship between the light source driving power and the disease category;

[0015] If the severity of the predicted disease condition category matches the severity of the pre-acquired disease condition category, the light source driving power is kept unchanged.

[0016] In a possible implementation of the first aspect, inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person includes:

[0017] Extracting frequency domain features and time domain features of the brain wave signal respectively; wherein the time domain features include the amplitude and period of the brain wave signal, and the frequency domain features include the distribution of delta wave, theta wave, alpha wave, and beta wave;

[0018] Combining the frequency domain feature and the time domain feature to generate a disease condition feature;

[0019] The predicted condition classification of the target person is determined according to the condition characteristics.

[0020] In a possible implementation of the first aspect, before inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person, the method further includes:

[0021] Acquire multiple training samples; wherein each training sample includes a brain wave signal of a sample person at a certain moment and the disease category of the sample person at the same moment; wherein the sample persons include normal persons who are not ill and patients;

[0022] The deep learning model is trained according to the multiple training samples to obtain the disease classification prediction model.

[0023] In a possible implementation manner of the first aspect, the deep learning model includes an input layer, a fully connected layer, and an output layer;

[0024] The input layer includes a long short-term memory network and a convolutional neural network processed in parallel;

[0025] The long short-term memory network is used to extract the time domain features of the brain wave signal;

[0026] The convolutional neural network is used to extract frequency domain features of the brain wave signal;

[0027] The fully connected layer is used to combine the time domain features and the frequency domain features;

[0028] The output layer includes a softmax function for classifying the disease condition.

[0029] In a possible implementation manner of the first aspect, before acquiring the brain wave signal of the target person under the current control parameters, the method includes:

[0030] Acquiring the location of the target person's key tissues; wherein the key tissues include brain tissues that affect disease treatment;

[0031] The implantation position of the electrode is determined according to the position of the key tissue; wherein the implantation position is the position in the intracranial artery closest to the key tissue.

[0032] The embodiment of the present application provides a method for adjusting neural control parameters, which obtains the brain wave signal of the target person under the current control parameters, inputs the brain wave signal into a disease classification prediction model, obtains the predicted disease category of the target person, compares the predicted disease category with the pre-acquired disease category, obtains a comparison result, and adjusts the current control parameters according to the comparison result to obtain new control parameters; wherein the pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameters are used to perform neural control on the target person.

[0033] It can be seen that the predicted disease category in the above method is the disease category determined based on the brain wave signal, which is used to describe the disease category of the target person at the current moment under the current control parameters. The pre-obtained disease category is the disease category obtained based on the questionnaire evaluation, which can describe the real disease category of the target person at the current moment.

[0034] The predicted disease category is compared with the previously obtained disease category to obtain a comparison result. If the predicted disease category matches the previously obtained disease category, it indicates that the current regulation parameters are reasonable and can be continuously used for subsequent neuroregulation, and better neuroregulation effects can be obtained.

[0035] If the predicted disease category does not match the pre-obtained disease category, it indicates that the current control parameters are unreasonable and poorly match the target person's disease category. By adjusting the current control parameters, new control parameters are obtained so that the new control parameters better match the target person's disease category, and subsequent neural control of the target person is performed according to the new control parameters, better neural control effects can be obtained.

[0036] In a second aspect, an embodiment of the present application provides a device for adjusting a neural regulation parameter, the device comprising:

[0037] An acquisition module is used to acquire the brain wave signal of the target person under the current control parameters;

[0038] A disease prediction module, used to input the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person;

[0039] A comparison module, used for comparing the predicted disease category with the pre-acquired disease category to obtain a comparison result;

[0040] A parameter adjustment module, used to adjust the current control parameters according to the comparison result to obtain new control parameters;

[0041] The pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameter is used to perform neurological control on the target person.

[0042] In a third aspect, an embodiment of the present application provides a neuromodulator, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods of the first aspect when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any one of the methods in the first aspect.

[0045] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 A schematic diagram of the composition of a physical therapy-based neuromodulation device provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of an application of a neuromodulatory device provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a flow chart of a method for adjusting a neural regulation parameter provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of a flow chart of a method for adjusting a neural regulation parameter provided in another embodiment of the present application;

[0051] Figure 5 A functional block diagram of a deep learning model provided in an embodiment of the present application;

[0052] Figure 6 It is a schematic diagram of the structure of a device for adjusting nerve regulation parameters provided in one embodiment of the present application;

[0053] Figure 7 is a schematic diagram of the structure of a device for adjusting nerve regulation parameters provided in another embodiment of the present application;

[0054] Figure 8 It is a schematic diagram of the hardware composition of a neuromodulator provided in one embodiment of the present application. DETAILED DESCRIPTION

[0055] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0056] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0057] Alzheimer's disease, commonly known as senile dementia, is a persistent neurological disorder that progresses slowly and worsens over time.

[0058] Studies have shown that physical therapy can reverse the progression of Alzheimer's disease. As a neuromodulatory method, physical therapy usually uses radiation sources to stimulate the human brain and change brain parameters to treat Alzheimer's disease.

[0059] Figure 1A schematic diagram of the composition of a physical therapy-based neuromodulation device provided in an embodiment of the present application. Figure 1 As shown, the neural regulation device includes a brain wave signal acquisition module 10, a stimulation light source generation module 20, a circuit control module 30 and a neural regulation module 40.

[0060] In this embodiment, the brain wave signal acquisition module 10 is implanted in the patient's skull to collect the patient's brain wave signals. For example, the brain wave signal acquisition module may include a plurality of electrodes and a support component for mounting the plurality of electrodes. The plurality of electrodes are evenly arranged on the support component to obtain brain wave signals at different positions.

[0061] Exemplarily, the electrode is mounted on a support member and implanted into a blood vessel within the skull via the support member.

[0062] Optionally, the support component is implanted at a position in the intracranial artery that is closest to brain tissue that affects treatment.

[0063] In this embodiment, the circuit control module 30 is implanted in the patient's body and connected to the brain wave signal acquisition module, and is used to feed back the brain wave signal collected by the brain wave signal acquisition module 10 to the neural regulation module 40.

[0064] The circuit control module 30 may include at least one signal sensor and a wireless communication unit. In practical applications, the signal sensor is connected to the electrodes, and then the brain wave signals collected by each electrode are transmitted to the neural regulation module 40 through the wireless communication unit.

[0065] In this embodiment, multiple electrodes and signal sensors can be connected in series or in parallel. If connected in series, multiple electrodes and signal sensors can be powered by only one powered cable, reducing the number of powered cables and signal sensors; if multiple electrodes and signal sensors are connected in parallel, each electrode corresponds to a signal sensor, ensuring that there is no interference between the electrodes, thereby improving safety.

[0066] In this embodiment, the signal sensor is connected to the electrode and fixed on the support component. The wireless communication unit is placed in the subcutaneous tissue of the target person, for example, in the chest, under the clavicle, behind the ear, etc.

[0067] In this embodiment, the stimulation light source generation module 20 includes a light source and an optical fiber, wherein the light source is implanted in the body, one end of the optical fiber is connected to the light source, and the other end is implanted in the skull through a supporting component. The illumination light emitted by the light source is transmitted to the skull through the optical fiber, and the brain tissue that affects the treatment of the disease is stimulated by light, thereby changing brain parameters, thereby achieving the effect of treating Alzheimer's disease.

[0068] In this embodiment, the neuroregulatory device also includes a power module, which is implanted in the body and supplies power to the electrodes and signal sensors through a powered cable.

[0069] For example, the power module may be a battery.

[0070] Exemplarily, one end of the power cable is connected to the battery, and the other end is connected to the signal sensor located in the brain. The power cable located in the intracranial blood vessel is wound around the support component, and the power cable located in the blood vessel can be wound around the optical fiber.

[0071] In this embodiment, the neuroregulatory module 40 is an extracorporeal control module for receiving brain wave signals and performing subsequent processing based on the brain wave signals. The processing results can be provided to medical staff so that they can evaluate the patient's treatment progress based on the processing results of the brain wave signals and make corresponding adjustments.

[0072] Optionally, the neural regulation module 40 includes but is not limited to mobile terminals such as smart phones, tablet computers, wearable devices, etc., and can also be desktop computers, robots, servers, etc.

[0073] In this embodiment, the neuroregulatory module 40 can also receive the control parameters input by the medical staff, and send the control parameters input by the medical staff to the stimulation light source generation module 20 through the wireless communication unit, so as to control the stimulation light source generation module 20 to generate the corresponding stimulation light source according to the adjusted control parameters. Alternatively, the neuroregulatory module 40 can also adjust the control parameters according to a preset mode, and control the stimulation light source generation module 20 to generate the corresponding stimulation light source according to the adjusted control parameters.

[0074] Optionally, the neuroregulatory module 40 is also used to display control parameters of the neuroregulatory device, for example, battery power, light source emission wavelength, light source driving power, etc. When the battery power is too low, the neuroregulatory module 40 can also remind medical staff to charge.

[0075] For a clearer description of this embodiment, please refer to Figure 2 . Figure 2 A schematic diagram of the application of the neuromodulation device provided in an embodiment of the present application.

[0076] like Figure 2 As shown, the neural regulation device includes a brain wave signal acquisition module, a stimulation light source generation module, a circuit control module, a neural regulation module and a power supply module.

[0077] Among them, the brain wave signal acquisition module includes multiple electrodes 101 and a supporting component 102 for installing multiple electrodes; the stimulation light source generation module includes an optical fiber 103 and a light source 104; the circuit control module includes a signal sensor 105 and a wireless communication unit 106; the power supply module includes a battery 107 and a power cable 108.

[0078] like Figure 2 As shown, multiple electrodes 101 are connected in series and then connected to a signal sensor 105. The multiple electrodes 101 and the signal sensor 105 are fixed on a support component 102 and implanted into a human intracranial blood vessel through the support component 102. A light source 104, a wireless communication unit 106 and a battery 107 are fixed together and implanted into the subcutaneous tissue of the human chest cavity.

[0079] One end of the optical fiber 103 is connected to the light source 104, and the other end enters the skull through the human blood vessels and is fixed on the support component 102; one end of the power cable 108 is connected to the battery 107, and the other end is connected to the signal sensor 105 located in the skull. The power cable 108 located in the intracranial blood vessels is wound around the support component 102, and the power cable 108 located in the blood vessels is wound around the optical fiber 103.

[0080] The neuroregulatory module 40 is located outside the body, and can receive brain wave signals fed back by the wireless communication unit 106 , and send neuroregulatory parameters to the light source 104 through the wireless communication unit 106 .

[0081] In actual applications, after the implantation of the supporting components (on which electrodes, signal sensors, powered cables and optical fibers are arranged), light sources, wireless communication units and batteries, the neuroregulatory module receives the control parameters input by medical staff, and sends the control parameters to the light source through the wireless communication unit. The light source generates corresponding irradiation light according to the current control parameters. The irradiation light emitted by the light source is transmitted to the skull through optical fibers to perform light stimulation on brain tissues that affect the treatment of the disease. Multiple electrodes collect the patient's brain wave signals under the current irradiation light, and feed the above brain wave signals back to the neuroregulatory module through the signal sensor and wireless communication unit.

[0082] After receiving the brain wave signal, the neuroregulatory module can process the brain wave signal and generate processing results, for example, obtaining the patient's condition category, etc., and display the processing results to medical staff so that they can evaluate the patient's treatment progress based on the processing results of the brain wave signal and make corresponding adjustments to obtain better neuroregulatory effects.

[0083] In the existing neuroregulatory methods, the same control parameters are used for brain stimulation, and it is impossible to detect and perceive the changes in the patient's brain state in real time. The control parameters are poorly matched with the patient's condition, which leads to poor neuroregulatory effects. After receiving the brain wave signal, the neuroregulatory module in the embodiment of the present application can obtain the predicted condition category of the target person, compare the predicted condition category with the pre-acquired condition category, and adjust the current control parameters according to the comparison result to obtain new control parameters, so that the new control parameters better match the condition of the target person, thereby performing subsequent neuroregulation on the target person according to the new control parameters, and obtaining better neuroregulatory effects.

[0084] The following is an illustrative description of the technical solution of the present application and how the technical solution of the present application solves the above technical problems with specific embodiments. It is worth noting that the specific embodiments listed below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0085] Figure 3 A flowchart of a method for adjusting a neural control parameter provided in an embodiment of the present application is provided. The execution subject of this embodiment is Figure 1 The neural regulation module in the embodiment, such as Figure 3 As shown, the method for adjusting the neural regulation parameters includes:

[0086] S10. Obtaining the brain wave signal of the target person under the current control parameters.

[0087] In this embodiment, the target person is a patient to be treated, including a patient who is undergoing neuromodulation for the first time and a patient who has undergone neuromodulation for a period of time.

[0088] Accordingly, for patients undergoing neuroregulation for the first time, the current regulation parameters are the regulation parameters determined according to the target person's condition category during the first neuroregulation; for patients who have undergone neuroregulation for a period of time, the current regulation parameters are the regulation parameters for the target person undergoing neuroregulation.

[0089] In this embodiment, the control parameters include at least one of the light source driving power, the light source wavelength, the light source frequency and the light source light emission mode.

[0090] In this embodiment, the stimulation light source generation module generates corresponding irradiation light according to the current control parameters, and the electrodes collect brain wave signals under the stimulation of the irradiation light, which are brain wave signals under the current control parameters.

[0091] In this embodiment, the neural regulation module acquiring the brain wave signal of the target person under the current regulation parameters may refer to the neural regulation module receiving the brain wave signal sent by the circuit control module.

[0092] Optionally, after receiving the brain wave signal fed back by the circuit control module, the neural regulation module may pre-process the brain wave signal to remove obvious noise interference, wherein the pre-processing includes low-pass filtering, time window interception, etc.

[0093] S20, inputting the brain wave signal into the disease classification prediction model to obtain the predicted disease category of the target person.

[0094] In this embodiment, the disease classification prediction model is obtained based on deep learning network model training, the input of the disease classification prediction model is the brain wave signal, and the output of the disease classification prediction model is the predicted disease category.

[0095] In this embodiment, the predicted disease categories include asymptomatic, mild dementia, moderate dementia and severe dementia, wherein the severity of asymptomatic, mild dementia, moderate dementia and severe dementia increases in sequence, and asymptomatic means no symptoms of Alzheimer's disease, that is, the target person has returned to normal.

[0096] In this embodiment, the brain wave signal may include α wave, δ wave, θ wave, β wave, spike wave, and spike-slow wave.

[0097] If the alpha wave, delta wave, theta wave, and beta wave in the brain wave signal change evenly and regularly, the predicted disease category of the target person is asymptomatic;

[0098] If the alpha wave rhythm in the EEG signal is irregular, for example, the alpha wave rhythm slows down, and there are moderate amounts of theta waves and small amounts of delta waves, then the predicted condition of the target person is mild dementia;

[0099] If the alpha wave rhythm disappears in the EEG signal, the theta wave and delta wave increase significantly and appear paroxysmically, and contain a small amount or a moderate amount of spike waves or spike-slow waves, then the predicted condition of the target person is moderate dementia;

[0100] If the EEG signal is dominated by theta waves or delta waves, for example, there are a large number of high-amplitude theta waves and delta waves, and at the same time contain a large number of spike waves and spike-slow waves, then the predicted disease category of the target person is severe dementia.

[0101] In this embodiment, inputting the brain wave signal into the disease classification prediction model to obtain the predicted disease category of the target person may include the following steps:

[0102] Step 1: Extract the frequency domain features and time domain features of the brain wave signal respectively; wherein the time domain features include the amplitude and period of the brain wave signal, and the frequency domain features include the distribution of delta wave, theta wave, alpha wave, and beta wave.

[0103] In this step, power spectrum density estimation can be performed on the brain wave signal to obtain frequency domain features; wherein the power spectrum density estimation includes parameter estimation and non-parameter estimation.

[0104] Step 2: Combine the frequency domain features and time domain features to generate disease characteristics.

[0105] In this step, the frequency domain features and time domain features of each EEG signal can be connected through a fully connected layer to generate disease characteristics.

[0106] Step 3: Determine the predicted condition classification of the target person based on the condition characteristics.

[0107] In this step, the disease characteristics may be input into a classifier to obtain the predicted disease category of the target person, wherein the classifier is the output layer of the disease classification prediction model.

[0108] S30: Compare the predicted disease category with the pre-acquired disease category to obtain a comparison result.

[0109] In this embodiment, the condition category obtained in advance is the condition category obtained based on questionnaire evaluation. For example, the condition category of the target person can be determined by conducting a questionnaire evaluation on the target person using a simplified mental status examination scale (hereinafter referred to as the scale).

[0110] For example, the total score of this scale is 30 points, and the degree of dementia is divided into 4 degrees, namely asymptomatic, mild dementia, moderate dementia and severe dementia. If the score obtained based on the questionnaire assessment of this scale is greater than or equal to 24 points, it can be determined as asymptomatic; if the score obtained based on the questionnaire assessment of this scale is greater than or equal to 18 points and less than 24 points, it can be determined as mild dementia; if the score obtained based on the questionnaire assessment of this scale is greater than or equal to 16 points and less than 17 points, it can be determined as moderate dementia; if the score obtained based on the questionnaire assessment of this scale is less than or equal to 15 points, it can be determined as severe dementia.

[0111] In this embodiment, in order to ensure the credibility of the comparison result, the predicted disease category and the pre-acquired disease category are obtained respectively when the target person is in the same time period.

[0112] The same time period may refer to the time period between two adjacent courses of treatment, that is, the time period between the completion of one course of neuroregulation and the initiation of the next course of neuroregulation.

[0113] In this embodiment, the comparison result includes that the predicted condition category matches the pre-acquired condition category, and that the predicted condition category does not match the pre-acquired condition category.

[0114] The mismatch includes that the severity of the predicted condition category is greater than the severity of the pre-acquired condition category, and the severity of the predicted condition category is less than the severity of the pre-acquired condition category.

[0115] For example, if the predicted condition category is moderate dementia and the previously obtained condition category is severe dementia, it means that the severity of the predicted condition category is less than the severity of the previously obtained condition category. On the contrary, it means that the severity of the predicted condition category is greater than the severity of the previously obtained condition category.

[0116] S40. Adjust the current control parameters according to the comparison result to obtain new control parameters; wherein the new control parameters are used to perform neural control on the target person.

[0117] In this embodiment, adjusting the current control parameters includes adjusting according to a preset mode, or receiving input from medical personnel, and adjusting the current control parameters according to the input from the medical personnel.

[0118] Among them, the preset modes include step adjustment and linear adjustment.

[0119] In this embodiment, the current control parameters include at least one of the light source driving power, the light source wavelength, the light source frequency and the light source light emitting mode.

[0120] For example, in a feasible implementation manner, taking the current control parameter as the light source driving power as an example, adjusting the current control parameter according to the comparison result may include:

[0121] If the severity of the predicted disease category does not match the severity of the disease category acquired in advance, the light source driving power is adjusted according to the mapping relationship.

[0122] The mismatch between the severity of the predicted condition category and the severity of the pre-acquired condition category includes that the severity of the predicted condition category is greater than the severity of the pre-acquired condition category, and the severity of the predicted condition category is less than the severity of the pre-acquired condition category.

[0123] In this embodiment, the mapping relationship is used to describe the corresponding relationship between the light source driving power and the disease category. For example, the magnitude of the light source driving power is positively correlated with the severity of the disease category. That is, the greater the severity of the disease category, the greater the corresponding light source driving power should be.

[0124] In this implementation, the goal of adjusting the light source driving power is to make the adjusted light source driving power match the severity of the disease category acquired in advance. Therefore, adjusting the light source driving power according to the mapping relationship may include:

[0125] Case 1: If the severity of the predicted disease category is greater than the severity of the disease category acquired in advance, the light source driving power is reduced.

[0126] Case 2: If the severity of the predicted disease category is less than the severity of the disease category acquired in advance, the light source driving power is increased.

[0127] In another feasible implementation manner, taking the current control parameter as the light source driving power as an example, adjusting the current control parameter according to the comparison result may include:

[0128] If the predicted severity of the disease category matches the severity of the disease category acquired in advance, the light source driving power is kept unchanged.

[0129] In this embodiment, after obtaining new control parameters, the neural control module can send the new control parameters to the stimulation light source generation module, so that the stimulation light source generation module generates illumination light corresponding to the new control parameters, thereby performing brain light stimulation on the target person based on the illumination light to improve the effect of neural control.

[0130] Optionally, if the predicted severity of the disease category matches the pre-acquired disease category and both are asymptomatic, it means that the target person has recovered to a normal person and no subsequent neurological regulation is required.

[0131] In this embodiment, the acquisition of the brain wave signal of the target person may be real-time monitoring or periodic monitoring.

[0132] Exemplarily, the target person is treated for Alzheimer's disease based on the neuroregulatory method, with a course of two weeks. In the same course, neuroregulation can be performed based on the same regulation parameters. Medical staff obtain the treatment progress of the target person once during the time period between two adjacent courses (every two weeks), that is, obtain the comparison results of the predicted disease category and the pre-acquired disease category, and then determine whether to adjust the current regulation parameters based on the comparison results.

[0133] For example, the neuromodulation module is executed every two weeks. Figure 3 The method in the embodiment obtains the comparison results of the predicted disease category and the pre-acquired disease category and displays them to the medical staff. On the one hand, the medical staff can obtain the treatment progress of the target person; on the other hand, the medical staff can also input new control parameters by themselves, or instruct the neural control module to adjust according to the preset mode to ensure the control effect of the target person in the next treatment course.

[0134] The method for adjusting the neural control parameters provided in the embodiment of the present application predicts the disease category as the disease category determined based on the brain wave signal, which is used to describe the disease category of the target person at the current moment under the current control parameters. The pre-acquired disease category is the disease category obtained based on the questionnaire evaluation, which can describe the actual disease category of the target person at the current moment.

[0135] The predicted disease category is compared with the previously obtained disease category. If the predicted disease category matches the previously obtained disease category, it indicates that the current regulation parameters are reasonable and can be continuously used for subsequent neuroregulation, and better neuroregulation effects can be obtained.

[0136] If the predicted disease category does not match the pre-acquired disease category, it indicates that the current control parameters are unreasonable and poorly match the target person's disease category. By adjusting the current control parameters so that the new control parameters better match the target person's disease category, subsequent neural control of the target person can be performed according to the new control parameters, thereby obtaining a better neural control effect.

[0137] Figure 4 A flowchart of a method for adjusting a neural control parameter provided in another embodiment of the present application is provided, which describes a flowchart of a method for obtaining a disease classification prediction model, such as Figure 4 As shown, before step 10, the method further includes:

[0138] S50, obtaining a plurality of training samples; wherein each training sample includes a brain wave signal of a sample person at a certain moment and the disease category of the sample person at the same moment; wherein the sample persons include normal persons who are not ill and patients.

[0139] In this embodiment, normal people who are not sick may include multiple groups of normal people who are over 60 years old and have similar education levels. For example, normal people with a master's degree form one group, normal people with a college degree form one group, normal people with a high school degree form one group, etc. Correspondingly, patients may also be classified according to their education levels.

[0140] In this embodiment, the brain wave signal and disease category of each sample person need to be obtained at the same time.

[0141] The brain wave signals of the sample personnel are collected based on the electrodes set outside the skull. Specifically, the electrode setting position is the position outside the skull and closest to the intracranial electrode placement position.

[0142] The intracranial electrode placement site may include a location in the intracranial artery closest to the hippocampus.

[0143] It should be understood that the environment should be kept quiet during the EEG signal collection process.

[0144] The condition category of the sample personnel is determined based on a questionnaire assessment method. For example, a simple mental status examination scale can be used to conduct a questionnaire assessment on the sample personnel to determine the condition category of the sample personnel.

[0145] S60: Train the deep learning model according to multiple training samples to obtain the disease classification prediction model.

[0146] In this embodiment, after obtaining multiple training samples, the training samples are preprocessed to obtain a data set that can be input into a deep learning model.

[0147] Among them, preprocessing includes filtering, time window interception, etc.

[0148] In this embodiment, the deep learning model includes an input layer, a fully connected layer and an output layer.

[0149] Among them, the input layer includes a long short-term memory network and a convolutional neural network processed in parallel. The long short-term memory network is used to extract the time domain features of the brain wave signals; the convolutional neural network is used to extract the frequency domain features of the brain wave signals; the fully connected layer is used to combine the time domain features and the frequency domain features; the output layer includes a softmax function, which is used to classify the disease.

[0150] To more clearly explain the deep learning model in this embodiment, please refer to Figure 5 , Figure 5 This is a functional block diagram of the deep learning model provided in the embodiment of the present application. Figure 5 As shown, the deep learning model includes an input layer, a fully connected layer, and an output layer.

[0151] Among them, the input layer includes a time domain feature extraction module and a frequency domain feature extraction module running in parallel. Since the brain wave signal is a time domain signal, a time domain to frequency domain conversion module is provided between the frequency domain feature extraction modules.

[0152] Optionally, the time domain feature extraction module is a long short-term memory network, the time domain to frequency domain conversion module is a Fourier transform module, and the frequency domain feature extraction module is a first-order convolutional neural network.

[0153] A time domain and frequency domain feature merging module is provided after the time domain feature extraction module and the frequency domain feature extraction module, and is specifically implemented by providing a fully connected layer.

[0154] The fully connected layer is connected to the output layer, which includes a disease category classification module for realizing disease category classification.

[0155] Optionally, the disease classification module can be implemented by, for example, a softmax classifier.

[0156] Optionally, training the deep learning model according to the multiple training samples may include the following steps:

[0157] Step 1: Preprocess each training sample to obtain the preprocessed data set.

[0158] Step 2: The preprocessed data set is used as the input of the long short-term memory network and the Fourier transform module respectively. The Fourier transform module transforms the data set and then inputs it into the first-order convolutional neural network.

[0159] Step 3: Set the number of time steps of the LSTM network, build a fully connected layer and a softmax classifier after the last time step of the LSTM network and after the first-order convolutional neural network, and set the loss function.

[0160] The loss function may be a cross entropy loss function.

[0161] During the training process, the forward propagation algorithm is used to calculate the output layer results of the LSTM network, and the back propagation algorithm transmitted over time is used to update the parameters of the LSTM network. After the preset conditions are met, the training is completed and the disease classification prediction model is obtained.

[0162] The method for obtaining a disease classification prediction model provided in the embodiment of the present application, on the one hand, obtains a combined disease feature by fully connecting the frequency domain features and time domain features of the EEG signal, and obtains the final disease classification based on the combined disease feature, which has high credibility. On the other hand, the long short-term memory network and the convolutional neural network have simple results and strong generalization ability, and can obtain a disease classification prediction model relatively quickly.

[0163] In order to ensure the accuracy of brain wave signals and achieve a higher treatment effect, before the brain wave acquisition module is implanted into the skull, the implantation position can be determined based on the nuclear magnetic resonance method. In a feasible implementation, the method for determining the implantation position of the brain wave acquisition module includes the following steps:

[0164] Step 1: Obtain the location of the target person's critical tissues, including brain tissues that affect disease treatment.

[0165] Exemplarily, the key tissue includes the hippocampus, and the location of the hippocampus inside the target person's brain can be determined based on the MRI (nuclear magnetic resonance imaging) method. The neuroregulatory module receives the location and displays the location of the key tissue in the target person's brain to medical staff in a graphical manner.

[0166] Step 2: Determine the implantation position of the electrode according to the position of the critical tissue; wherein the implantation position is the position in the intracranial artery that is closest to the critical tissue.

[0167] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0168] Based on the method for adjusting the neural regulation parameters provided in the above embodiment, the embodiment of the present invention further provides an embodiment of a device for implementing the above method embodiment.

[0169] Figure 6 A schematic diagram of the structure of a device for adjusting neural control parameters provided in an embodiment of the present application. Figure 3 For details of the steps in the corresponding embodiments, please refer to Figure 3 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 6 , the neural control parameter adjustment device 50 includes:

[0170] An acquisition module 501 is used to acquire the brain wave signal of the target person under the current control parameters;

[0171] The disease prediction module 502 is used to input the brain wave signal into the disease classification prediction model to obtain the predicted disease category of the target person;

[0172] A comparison module 503 is used to compare the predicted disease category with the pre-acquired disease category to obtain a comparison result;

[0173] A parameter adjustment module 504 is used to adjust the current control parameters according to the comparison result to obtain new control parameters;

[0174] The pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameter is used to perform neurological control on the target person.

[0175] Optionally, the control parameters include at least one of a light source driving power, a light source wavelength, a light source frequency, and a light source light emitting mode.

[0176] Optionally, the control parameter includes the light source driving power. Then the parameter adjustment module 504 adjusts the current control parameter according to the comparison result, including:

[0177] If the severity of the predicted disease category does not match the severity of the pre-acquired disease category, adjusting the light source driving power according to a mapping relationship; the mapping relationship is used to describe the corresponding relationship between the light source driving power and the disease category;

[0178] If the severity of the predicted disease condition category matches the severity of the pre-acquired disease condition category, the light source driving power is kept unchanged.

[0179] Optionally, the disease prediction module 502 inputs the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person, including:

[0180] Extracting frequency domain features and time domain features of the brain wave signal respectively; wherein the time domain features include the amplitude and period of the brain wave signal, and the frequency domain features include the distribution of delta wave, theta wave, alpha wave, and beta wave;

[0181] Combining the frequency domain feature and the time domain feature to generate a disease condition feature;

[0182] The predicted condition classification of the target person is determined according to the condition characteristics.

[0183] In the neural regulation parameter adjustment device provided in the embodiment of the present application, the predicted disease category is the disease category determined based on the brain wave signal, which is used to describe the disease category of the target person at the current moment under the current regulation parameters. The pre-acquired disease category is the disease category obtained based on the questionnaire evaluation, which can describe the actual disease category of the target person at the current moment.

[0184] The predicted disease category is compared with the previously obtained disease category to obtain a comparison result. If the predicted disease category matches the previously obtained disease category, it indicates that the current regulation parameters are reasonable and can be continuously used for subsequent neuroregulation, and better neuroregulation effects can be obtained.

[0185] If the predicted disease category does not match the pre-obtained disease category, it indicates that the current control parameters are unreasonable and poorly match the target person's disease category. By adjusting the current control parameters, new control parameters are obtained so that the new control parameters better match the target person's disease category, and subsequent neural control of the target person is performed according to the new control parameters, better neural control effects can be obtained.

[0186] Figure 7 A schematic diagram of a structure of a device for adjusting a neural control parameter provided in another embodiment of the present application. Figure 4 For details of the steps in the corresponding embodiments, please refer to Figure 4 The relevant description in the corresponding embodiment. Figure 7 The neural regulation parameter adjustment device 50 also includes a sample acquisition module 505 and a training module 506 .

[0187] The sample acquisition module 505 is used to acquire a plurality of training samples; each training sample includes a brain wave signal of a sample person at a certain moment and the disease category of the sample person at the same moment; the sample persons include normal persons who are not ill and patients;

[0188] The training module 506 is used to train the deep learning model according to the multiple training samples to obtain the disease classification prediction model.

[0189] Optionally, the deep learning model includes an input layer, a fully connected layer and an output layer;

[0190] The input layer includes a long short-term memory network and a convolutional neural network processed in parallel;

[0191] The long short-term memory network is used to extract the time domain features of the brain wave signal;

[0192] The convolutional neural network is used to extract frequency domain features of the brain wave signal;

[0193] The fully connected layer is used to combine the time domain features and the frequency domain features;

[0194] The output layer includes a softmax function for classifying the disease condition.

[0195] Optionally, the neuroregulatory parameter adjustment device 50 also includes a determination module for obtaining the position of the key tissue of the target person and determining the electrode implantation position according to the position of the key tissue; wherein the key tissue includes brain tissue that affects the treatment of the disease; and the implantation position is the position in the intracranial artery that is closest to the key tissue.

[0196] Figure 6 and Figure 7 The device for adjusting the neural regulation parameters provided in the illustrated embodiment can be used to execute the technical solution in the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail in this embodiment.

[0197] Figure 8 Schematic diagram of a neuromodulator provided in one embodiment of the present application. Figure 8 As shown, the neuroregulator 70 of this embodiment includes: at least one processor 701, a memory 702, and a computer program stored in the memory 702 and executable on the processor 701. The neuroregulator 70 also includes a communication component 703, wherein the processor 701, the memory 702, and the communication component 703 are connected via a bus 704.

[0198] When the processor 701 executes the computer program, Figure 3 or Figure 4The steps in the embodiment of the neural regulation method in the embodiment. Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 702 and executed by the processor 701 to complete the present application.

[0199] Those skilled in the art will understand that Figure 8 These are merely examples of neuroregulators and do not constitute limitations on neuroregulatory devices, which may include more or fewer components than those shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0200] Exemplarily, the neuromodulator can be Figure 1 Neuromodulatory devices.

[0201] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned welding parameter setting method embodiment can be implemented.

[0202] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0203] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0204] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0205] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0206] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A device for adjusting neural control parameters, characterized in that: The device comprises: An acquisition module is used to acquire the brain wave signal of the target person under the current control parameters; A disease prediction module, used to input the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person; A comparison module, used for comparing the predicted disease category with the pre-acquired disease category to obtain a comparison result; A parameter adjustment module, used to adjust the current control parameters according to the comparison result to obtain new control parameters; Wherein, the pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameter is used to perform neurological control on the target person; the predicted disease category and the pre-acquired disease category are obtained in the same time period; The control parameter includes the light source driving power; and adjusting the current control parameter according to the comparison result includes: If the severity of the predicted disease category does not match the severity of the pre-acquired disease category, adjusting the light source driving power according to a mapping relationship; the mapping relationship is used to describe the corresponding relationship between the light source driving power and the disease category; If the severity of the predicted disease condition category matches the severity of the pre-acquired disease condition category, the light source driving power is kept unchanged.

2. The device for adjusting the neural control parameters according to claim 1, characterized in that: The control parameters also include at least one of the wavelength of the light source, the frequency of the light source, and the light emission mode of the light source.

3. The device for adjusting the neural control parameters according to claim 1, characterized in that: The step of inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person includes: Extracting frequency domain features and time domain features of the brain wave signal respectively; wherein the time domain features include the amplitude and period of the brain wave signal, and the frequency domain features include the distribution of delta wave, theta wave, alpha wave, and beta wave; Combining the frequency domain feature and the time domain feature to generate a disease condition feature; The predicted condition classification of the target person is determined according to the condition characteristics.

4. The device for adjusting the neural control parameters according to any one of claims 1 to 3, characterized in that: The device also includes a sample acquisition module and a training module; The sample acquisition module is used to acquire a plurality of training samples before inputting the brain wave signal into the disease classification prediction model to acquire the predicted disease category of the target person; wherein each training sample includes the brain wave signal of the sample person at a certain moment and the disease category of the sample person at the same moment; wherein the sample persons include normal persons who are not ill and patients; The training module is used to train the deep learning model according to the multiple training samples to obtain the disease classification prediction model; The deep learning model includes an input layer, a fully connected layer and an output layer; The input layer includes a long short-term memory network and a convolutional neural network processed in parallel; The long short-term memory network is used to extract the time domain features of the brain wave signal; The convolutional neural network is used to extract frequency domain features of the brain wave signal; The fully connected layer is used to combine the time domain features and the frequency domain features; The output layer includes a softmax function for classifying the disease condition.

5. The device for adjusting the neural control parameters according to any one of claims 1 to 3, characterized in that: The device also includes a determining module, configured to: Before obtaining the brain wave signal of the target person under the current control parameters, obtaining the location of the key tissue of the target person; wherein the key tissue includes the brain tissue that affects the treatment of the disease; The implantation position of the electrode is determined according to the position of the key tissue; wherein the implantation position is the position in the intracranial artery closest to the key tissue.

6. A neuromodulator, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the following steps are implemented: Obtain the brain wave signal of the target person under the current control parameters; Inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person; Comparing the predicted disease category with the previously obtained disease category to obtain a comparison result; Adjust the current control parameters according to the comparison result to obtain new control parameters; Wherein, the pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameter is used to perform neurological control on the target person; the predicted disease category and the pre-acquired disease category are obtained in the same time period; The control parameter includes the light source driving power; and adjusting the current control parameter according to the comparison result includes: If the severity of the predicted disease category does not match the severity of the pre-acquired disease category, adjusting the light source driving power according to a mapping relationship; the mapping relationship is used to describe the corresponding relationship between the light source driving power and the disease category; If the severity of the predicted disease condition category matches the severity of the pre-acquired disease condition category, the light source driving power is kept unchanged.

7. The neuromodulator according to claim 6, characterized in that: The control parameters also include at least one of the wavelength of the light source, the frequency of the light source, and the light emission mode of the light source; The step of inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person includes: Extracting frequency domain features and time domain features of the brain wave signal respectively; wherein the time domain features include the amplitude and period of the brain wave signal, and the frequency domain features include the distribution of delta wave, theta wave, alpha wave, and beta wave; Combining the frequency domain feature and the time domain feature to generate a disease condition feature; Determining the predicted condition classification of the target person according to the condition characteristics; Before inputting the brain wave signal into the disease classification prediction model to obtain the predicted disease category of the target person, the neuroregulator is further used to: Acquire multiple training samples; wherein each training sample includes a brain wave signal of a sample person at a certain moment and the disease category of the sample person at the same moment; wherein the sample persons include normal persons who are not ill and patients; Training the deep learning model according to the multiple training samples to obtain the disease classification prediction model; The deep learning model includes an input layer, a fully connected layer and an output layer; The input layer includes a long short-term memory network and a convolutional neural network processed in parallel; The long short-term memory network is used to extract the time domain features of the brain wave signal; The convolutional neural network is used to extract frequency domain features of the brain wave signal; The fully connected layer is used to combine the time domain features and the frequency domain features; The output layer includes a softmax function for classifying the condition; Before obtaining the brain wave signal of the target person under the current control parameters, the neuroregulator is further used to: Before obtaining the brain wave signal of the target person under the current control parameters, obtaining the location of the key tissue of the target person; wherein the key tissue includes the brain tissue that affects the treatment of the disease; The implantation position of the electrode is determined according to the position of the key tissue; wherein the implantation position is the position in the intracranial artery closest to the key tissue.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the following steps are implemented: Obtain the brain wave signal of the target person under the current control parameters; Inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person; Comparing the predicted disease category with the previously obtained disease category to obtain a comparison result; Adjust the current control parameters according to the comparison result to obtain new control parameters; Wherein, the pre-acquired disease category is a disease category obtained based on a questionnaire assessment, and the new control parameter is used to perform neurological control on the target person; the predicted disease category and the pre-acquired disease category are obtained in the same time period; The control parameter includes the light source driving power; and adjusting the current control parameter according to the comparison result includes: If the severity of the predicted disease category does not match the severity of the pre-acquired disease category, adjusting the light source driving power according to a mapping relationship; the mapping relationship is used to describe the corresponding relationship between the light source driving power and the disease category; If the severity of the predicted disease condition category matches the severity of the pre-acquired disease condition category, the light source driving power is kept unchanged.

9. The computer-readable storage medium of claim 8, wherein: The control parameters also include at least one of the wavelength of the light source, the frequency of the light source, and the light emission mode of the light source; The step of inputting the brain wave signal into a disease classification prediction model to obtain the predicted disease category of the target person includes: Extracting frequency domain features and time domain features of the brain wave signal respectively; wherein the time domain features include the amplitude and period of the brain wave signal, and the frequency domain features include the distribution of delta wave, theta wave, alpha wave, and beta wave; Combining the frequency domain feature and the time domain feature to generate a disease condition feature; Determining the predicted condition classification of the target person according to the condition characteristics; Before inputting the brain wave signal into the disease classification prediction model to obtain the predicted disease category of the target person, the computer program further implements the following steps when executed by the processor: Acquire multiple training samples; wherein each training sample includes a brain wave signal of a sample person at a certain moment and the disease category of the sample person at the same moment; wherein the sample persons include normal persons who are not ill and patients; Training the deep learning model according to the multiple training samples to obtain the disease classification prediction model; The deep learning model includes an input layer, a fully connected layer and an output layer; The input layer includes a long short-term memory network and a convolutional neural network processed in parallel; The long short-term memory network is used to extract the time domain features of the brain wave signal; The convolutional neural network is used to extract frequency domain features of the brain wave signal; The fully connected layer is used to combine the time domain features and the frequency domain features; The output layer includes a softmax function for classifying the condition; Before obtaining the brain wave signal of the target person under the current control parameters, the computer program further implements the following steps when executed by the processor: Before obtaining the brain wave signal of the target person under the current control parameters, obtaining the location of the key tissue of the target person; wherein the key tissue includes the brain tissue that affects the treatment of the disease; The implantation position of the electrode is determined according to the position of the key tissue; wherein the implantation position is the position in the intracranial artery closest to the key tissue.