A dual-path stimulation intelligent control system for brain nerves in Parkinson's disease

Abstract

The present invention discloses a brain nerve dual-path stimulation intelligent control system for Parkinson's disease, which relates to the fields of medical and neuroengineering technology, including: obtaining neural electrical signals of a target patient based on a stimulation electrode, and determining neural activity characteristics based on the neural electrical signals; the stimulation electrode includes a first stimulation electrode and a second stimulation electrode; determining a neural evaluation value based on the neural activity characteristics, and generating a co-stimulation parameter based on the neural evaluation value; adjusting the initial stimulation parameters of the stimulation electrode based on the co-stimulation parameter, and stimulating the target patient through the stimulation electrode, so as to complete the brain nerve dual-path stimulation intelligent control for Parkinson's disease. The present invention realizes the comprehensive quantification of neural activities in the deep brain and vagus nerve regions by introducing real-time evaluation of abnormal oscillation patterns and neural network synchronization characteristics, and improves the accuracy of neural control; by generating co-stimulation parameters, the mutual influence of the two stimulation pathways is comprehensively considered, and intelligent co-control is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical treatment and neural engineering technology, and in particular to a brain nerve dual-path stimulation intelligent control system for Parkinson's disease. Background Art

[0002] Parkinson's disease is a common neurodegenerative disease, whose main characteristics include motor symptoms such as resting tremor, muscle rigidity and bradykinesia. In the past few decades, deep brain stimulation (DBS) has become one of the effective methods for treating Parkinson's disease. Traditional DBS mainly targets the subthalamic nucleus (STN) or the globus pallidus internus (GPi) for single-site stimulation. Although this method has achieved remarkable results in alleviating motor symptoms, it still has some limitations. First, single-site stimulation may not be able to fully regulate the complex neural network involved in Parkinson's disease. Second, traditional DBS systems usually use an open-loop stimulation mode, which cannot dynamically adjust the stimulation parameters according to the patient's real-time neural activity state, resulting in the possibility that the treatment effect will decrease over time. In addition, long-term continuous stimulation may cause some side effects, such as speech disorders and balance problems.

[0003] In recent years, researchers have begun to explore multi-target stimulation and closed-loop stimulation strategies to improve the therapeutic effect of DBS. Vagus nerve stimulation has been shown to regulate the activity of multiple brain regions related to Parkinson's disease, including the substantia nigra, striatum, and cortical areas. However, the existing technology lacks effective methods to evaluate and quantify the characteristics of neural activity at two stimulation sites in real time, especially in terms of abnormal oscillation patterns and neural network synchronization. Secondly, it is difficult for existing technologies to achieve coordinated regulation between the two stimulation pathways, and they often simply superimpose the two stimulation effects rather than truly intelligent coordination. Finally, the existing stimulation parameter adjustment algorithms usually rely on fixed thresholds or preset rules, lack sufficient flexibility and individual characteristics, and are difficult to adapt to the dynamic changes and individual differences in symptoms of Parkinson's patients. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: How to solve the problems of the existing Parkinson's disease brain nerve stimulation technology, such as insufficient real-time evaluation of dual-path neural activity, lack of coordinated regulation mechanism, and lack of flexibility and individualization in stimulation parameter adjustment?

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a brain nerve dual-path stimulation intelligent control system for Parkinson's disease, comprising: obtaining neural electrical signals of a target patient based on stimulation electrodes, and determining neural activity characteristics based on the neural electrical signals; the stimulation electrodes include a first stimulation electrode and a second stimulation electrode; the neural electrical signals include a first neural electrical signal and a second neural electrical signal; determining a neural evaluation value based on the neural activity characteristics, and generating a synergistic stimulation parameter based on the neural evaluation value; the neural evaluation value includes a first neural evaluation value and a second neural evaluation value; adjusting the initial stimulation parameters of the stimulation electrode based on the synergistic stimulation parameters, and stimulating the target patient through the stimulation electrode, thereby completing the brain nerve dual-path stimulation intelligent control for Parkinson's disease.

[0007] As a preferred solution of the brain nerve dual-path stimulation intelligent control system for Parkinson's disease described in the present invention, wherein: the neural activity characteristics include abnormal oscillation patterns and neural network synchronization characteristics; the neural electrical signals of the target patient are obtained based on the stimulation electrodes, and the neural activity characteristics are determined according to the neural electrical signals, including the following steps: obtaining the first neural electrical signal of the target patient based on the first stimulation electrode, and determining the abnormal oscillation pattern in the first neural electrical signal; obtaining the second neural electrical signal of the target patient based on the second stimulation electrode, and determining the neural network synchronization characteristics in the second neural electrical signal.

[0008] As a preferred solution of the brain nerve dual-path stimulation intelligent control system for Parkinson's disease described in the present invention, wherein: based on the first stimulation electrode, the first neural electrical signal of the target patient is obtained, and the abnormal oscillation pattern in the first neural electrical signal is determined, including the following steps: collecting the first neural electrical signal of the first stimulation electrode within a preset time period; performing wavelet transform on the first neural electrical signal to obtain the time-frequency energy distribution of the β frequency band, the α frequency band and the θ frequency band; calculating the energy ratio β / α of the β frequency band to the α frequency band, and the energy ratio θ / α of the θ frequency band to the α frequency band; based on a pre-established individualized database, obtaining a historical energy ratio data set of the target patient; wherein the historical energy ratio data set The data set includes historical energy ratio β / α and historical energy ratio θ / α ratios of the target patient in a predefined time window in the past; based on the historical energy ratio data set, the historical means and historical standard deviations of the energy ratio β / α and the energy ratio θ / α ratio are calculated respectively; based on the historical means and historical standard deviations, the Z scores of the energy ratio β / α and the energy ratio θ / α are calculated respectively; if the Z score of the energy ratio β / α is greater than a preset positive threshold and the Z score of the energy ratio θ / α is less than a preset negative threshold, the coefficient of variation of the β-band energy is calculated; if the coefficient of variation of the β-band energy exceeds a preset multiple of its historical mean, it is determined that the first neural electrical signal has an abnormal oscillation pattern.

[0009] The second neural electrical signal of the target patient is acquired based on the second stimulation electrode, and the neural network synchronization feature in the second neural electrical signal is determined, including the following steps: collecting the second neural electrical signal of the second stimulation electrode within a preset time period; performing wavelet transform on the second neural electrical signal to obtain the time-frequency energy distribution of the δ frequency band, the θ frequency band, the α frequency band, the β frequency band and the γ frequency band; calculating the phase locking value between the δ frequency band, the θ frequency band, the α frequency band, the β frequency band and the γ frequency band, and when any two frequency bands meet the first preset condition, they are marked as highly synchronized; based on the phase locking value, a phase synchronization matrix is ​​constructed; the eigenvalues ​​of the phase synchronization matrix are calculated to obtain the maximum eigenvalue and the second largest eigenvalue; according to the maximum eigenvalue, the second largest eigenvalue, and the number of frequency band pairs marked as highly synchronized, a neural network synchronization feature index is determined, and the neural network synchronization feature index is used as a mathematical representation of the neural network synchronization feature.

[0010] As a preferred solution of the brain nerve dual-path stimulation intelligent control system for Parkinson's disease described in the present invention, wherein: determining the neural evaluation value according to the neural activity characteristics includes the following steps: determining the first neural evaluation value based on the abnormal oscillation pattern and the initial stimulation parameters of the first stimulation electrode; determining the second neural evaluation value based on the mathematical representation of the neural network synchronization characteristics, that is, the neural network synchronization characteristic index.

[0011] As a preferred solution of the brain nerve dual-path stimulation intelligent control system for Parkinson's disease described in the present invention, wherein: based on the abnormal oscillation pattern and the initial stimulation parameters of the first stimulation electrode, the first nerve evaluation value is determined, including the following steps: calculating the ratio of the coefficient of variation of the β-band energy in the abnormal oscillation pattern to its historical mean to obtain an abnormal oscillation intensity index; comparing the stimulation frequency, stimulation amplitude and pulse width in the initial stimulation parameters of the first stimulation electrode with preset standard parameters respectively to obtain a stimulation parameter deviation value; performing weighted summation of the abnormal oscillation intensity index and the stimulation parameter deviation value to obtain a first nerve evaluation value.

[0012] Based on the mathematical representation of the neural network synchronization characteristics, that is, the neural network synchronization characteristic index, a second neural evaluation value is determined, including the following steps: based on the neural network synchronization characteristic index, the degree of synchronization abnormality is obtained; the ratio of the number of highly synchronized frequency band pairs to the total number of frequency band pairs is calculated to obtain a high synchronization ratio; and the degree of synchronization abnormality and the high synchronization ratio are weighted averaged to obtain a second neural evaluation value.

[0013] As a preferred solution of the brain nerve dual-path stimulation intelligent control system for Parkinson's disease described in the present invention, wherein: generating a synergistic stimulation parameter based on the nerve evaluation value includes the following steps: substituting the first nerve evaluation value into a sigmoid function to obtain a stimulation intensity adjustment coefficient of the first stimulation electrode; substituting the second nerve evaluation value into an inverse tangent function to obtain a stimulation frequency adjustment coefficient of the second stimulation electrode, and calculating new stimulation parameters of the first stimulation electrode and the second stimulation electrode respectively according to the stimulation intensity adjustment coefficient and the stimulation frequency adjustment coefficient to obtain a synergistic stimulation parameter, specifically: calculating the new stimulation parameter of the first stimulation electrode:

[0014] New stimulation amplitude 1 = current stimulation amplitude 1*(1+γ1*stimulation intensity adjustment coefficient);

[0015] New pulse width 1 = current pulse width 1*(1+γ2*stimulation intensity adjustment coefficient);

[0016] New stimulation frequency 1 = current stimulation frequency 1*(1+γ3*stimulation frequency adjustment coefficient);

[0017] Calculate new stimulation parameters for the second stimulation electrode:

[0018] New stimulation amplitude 2 = current stimulation amplitude 2*(1+γ4*stimulation intensity adjustment coefficient);

[0019] New pulse width 2 = current pulse width 2*(1+γ5*stimulation intensity adjustment coefficient);

[0020] New stimulation frequency 2 = current stimulation frequency 2*(1+γ6*stimulation frequency adjustment coefficient);

[0021] The new stimulation parameters of the first stimulation electrode are combined with the new stimulation parameters of the second stimulation electrode to form synergistic stimulation parameters.

[0022] Among them, the current stimulation amplitude 1, the current pulse width 1, and the current stimulation frequency 1 are the initial stimulation parameters of the first stimulation electrode; the current stimulation amplitude 2, the current pulse width 2, and the current stimulation frequency 2 are the initial stimulation parameters of the second stimulation electrode; γ1, γ2, γ3, γ4, γ5, and γ6 are adjustment coefficients used to control the adjustment amplitude of each parameter.

[0023] As a preferred solution of the intelligent control system for dual-path stimulation of cranial nerves for Parkinson's disease described in the present invention, wherein: adjusting the initial stimulation parameters of the stimulation electrode based on the synergistic stimulation parameters includes the following steps: receiving the synergistic stimulation parameters and parsing them into new stimulation parameters of the first stimulation electrode and new stimulation parameters of the second stimulation electrode; comparing the new stimulation parameters of the first stimulation electrode with the initial stimulation parameters of the first stimulation electrode, comparing the new stimulation parameters of the second stimulation electrode with the initial stimulation parameters of the second stimulation electrode, and calculating the parameter adjustment amount; according to the parameter adjustment amount, updating the stimulation parameters of the first stimulation electrode and the second stimulation electrode respectively, and completing the adjustment of the initial stimulation parameters of the stimulation electrodes.

[0024] To further solve the above technical problems, the present invention provides the following technical solutions: A brain nerve dual-path stimulation intelligent control system for Parkinson's disease, comprising: an acquisition unit, including a neural electrical signal acquisition module and a neural activity feature determination module; the neural electrical signal acquisition module is used to obtain neural electrical signals of a target patient based on stimulation electrodes; the neural activity feature determination module is used to determine neural activity features according to the neural electrical signals; an evaluation generation unit, including a neural evaluation value determination module and a co-stimulation parameter generation module; the neural evaluation value determination module is used to determine a neural evaluation value according to the neural activity features, and the neural evaluation value includes a first neural evaluation value and a second neural evaluation value; the co-stimulation parameter generation module is used to generate co-stimulation parameters based on the neural evaluation value; an adjustment execution unit, including a stimulation parameter adjustment module and a stimulation execution module; the stimulation parameter adjustment module is used to adjust the initial stimulation parameters of the stimulation electrode based on the co-stimulation parameters; the stimulation execution module is used to stimulate the target patient through the stimulation electrode to complete the brain nerve dual-path stimulation intelligent control for Parkinson's disease.

[0025] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the above-mentioned brain nerve dual-path stimulation intelligent control system for Parkinson's disease are implemented.

[0026] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned intelligent control system for dual-path stimulation of cranial nerves for Parkinson's disease are implemented.

[0027] Beneficial effects of the present invention: The present invention realizes comprehensive quantification of neural activity in the deep brain and vagus nerve regions and improves the accuracy of neural regulation by introducing real-time evaluation of abnormal oscillation patterns and neural network synchronization characteristics. Secondly, the present invention realizes intelligent collaborative regulation by generating co-stimulation parameters and comprehensively considering the mutual influence of the two stimulation pathways. In addition, the present invention can more flexibly adapt to the dynamic changes of patient symptoms and provide highly individualized treatment plans. Finally, the introduction of a closed-loop feedback mechanism significantly improves the stability and long-term effectiveness of the stimulation effect, while potentially reducing the occurrence of side effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0029] Figure 1 This is an overall flow chart of a brain nerve dual-path stimulation intelligent control system for Parkinson's disease provided by one embodiment of the present invention.

[0030] Figure 2 This is a computer device diagram of the brain nerve dual-path stimulation intelligent control system for Parkinson's disease of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0033] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a brain nerve dual-path stimulation intelligent control system for Parkinson's disease.

[0034] The existing technology lacks effective methods to evaluate and quantify the characteristics of neural activity at two stimulation sites in real time, especially in terms of abnormal oscillation patterns and neural network synchronization. Secondly, it is difficult for the existing technology to achieve coordinated regulation between the two stimulation pathways, and it often simply superimposes the two stimulation effects rather than truly intelligent coordination. Finally, the existing stimulation parameter adjustment algorithms usually rely on fixed thresholds or preset rules, lack sufficient flexibility and individual characteristics, and are difficult to adapt to the dynamic changes and individual differences in symptoms of Parkinson's patients.

[0035] The present application provides a method that can effectively solve the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the brain nerve dual-path stimulation intelligent control system for Parkinson's disease.

[0036] Figure 1 The overall flow chart of an execution method of a brain nerve dual-path stimulation intelligent control system for Parkinson's disease is shown, including:

[0037] S1: Obtain the neural electrical signals of the target patient based on the stimulation electrodes, and determine the neural activity characteristics based on the neural electrical signals;

[0038] S2: determining a neural evaluation value according to the neural activity characteristics, and generating a co-stimulation parameter based on the neural evaluation value;

[0039] S3: The initial stimulation parameters of the stimulation electrodes are adjusted based on the synergistic stimulation parameters, and stimulation is implemented on the target patient through the stimulation electrodes to complete the intelligent regulation of dual-path stimulation of cranial nerves for Parkinson's disease.

[0040] Next, each step will be explained in detail:

[0041] S1: Obtain the target patient's neural electrical signals based on the stimulation electrodes, and determine the neural activity characteristics based on the neural electrical signals.

[0042] Specifically, the stimulation electrode includes a first stimulation electrode and a second stimulation electrode. In an embodiment of the present application, the deep brain stimulation electrode is used as the first stimulation electrode to obtain the first neural electrical signal and implement stimulation, thereby directly affecting the neural activity pattern of the brain. The deep brain stimulation electrode is an implantable medical device used for the treatment of Parkinson's disease, and is often implanted in a specific area of ​​the brain, such as the subthalamic nucleus or the globus pallidus. The deep brain stimulation electrode can send precisely controlled electrical pulses to regulate abnormal neural activity. The vagus nerve stimulation electrode is used as the second stimulation electrode to obtain the second neural electrical signal and implement stimulation, thereby indirectly affecting the synchronization of brain function and neural networks. The vagus nerve stimulation electrode is also an implantable device, usually implanted in the neck area, for stimulating the vagus nerve. In the treatment of Parkinson's disease, vagus nerve stimulation can assist in treatment by regulating the activity of the central nervous system. The target patient specifically refers to Parkinson's patients.

[0043] Specifically, the neural electrical signal includes a first neural electrical signal and a second neural electrical signal. Neural activity characteristics include abnormal oscillation patterns and neural network synchronization characteristics. In the present invention, the first neural electrical signal refers to the neural electrical activity signal collected by deep brain stimulation electrodes, which mainly reflects the deep brain structures, such as the neuronal discharge patterns and rhythmic activities of the basal ganglia. In the present invention, the first neural electrical signal is used to analyze abnormal oscillation patterns. The second neural electrical signal is a neural electrical activity signal collected by vagus nerve stimulation electrodes, which is used to reflect the activity state of the vagus nerve and indirectly reflect the overall regulation of the central nervous system. In the present invention, the second neural electrical signal is mainly used to analyze the synchronization characteristics of the neural network, which helps to evaluate the regulatory effect of vagus nerve stimulation on the overall neural network function.

[0044] Abnormal oscillation patterns refer to abnormal neuronal firing patterns observed in the first neural electrical signals collected by deep brain stimulation electrodes. In patients with Parkinson's disease, neurons in deep brain structures (such as the subthalamic nucleus or globus pallidus) exhibit abnormal synchronized activity, resulting in excessive rhythmic firing, which can be directly captured by deep brain stimulation electrodes.

[0045] In an optional embodiment, a first neural electrical signal of a Parkinson's patient is obtained based on a deep brain stimulation electrode, and an abnormal oscillation pattern in the first neural electrical signal is determined. A second neural electrical signal of a Parkinson's patient is obtained based on a vagus nerve stimulation electrode, and a neural network synchronization feature in the second neural electrical signal is determined.

[0046] Further, S1.1: acquiring a first neural electrical signal of a target patient (i.e., a Parkinson's patient) based on a first stimulation electrode (i.e., a deep brain stimulation electrode), and determining an abnormal oscillation pattern in the first neural electrical signal, comprises the following steps:

[0047] S1.1.1: Collecting a first neural electrical signal from a first stimulation electrode within a preset time period.

[0048] S1.1.2: Perform wavelet transform on the first neural electrical signal to obtain the time-frequency energy distribution of the β frequency band (13-30 Hz), α frequency band (8-12 Hz) and θ frequency band (4-7 Hz).

[0049] S1.1.3: Calculate the energy ratio β / α between the β band and the α band, and the energy ratio θ / α between the θ band and the α band.

[0050] S1.1.4: Based on a pre-established individualized database, a historical energy ratio data set of the target patient is obtained; wherein the historical energy ratio data set includes the historical energy ratio β / α and the historical energy ratio θ / α ratios of the target patient within a predefined time window in the past.

[0051] S1.1.5: Based on the historical energy ratio data set, calculate the historical mean and historical standard deviation of the energy ratio β / α and the energy ratio θ / α respectively.

[0052] S1.1.6: Calculate the Z scores of the energy ratio β / α and the energy ratio θ / α based on the historical mean and historical standard deviation.

[0053] S1.1.7: If the Z score of the energy ratio β / α is greater than the preset positive threshold and the Z score of the energy ratio θ / α is less than the preset negative threshold, then calculate the coefficient of variation of the β band energy.

[0054] S1.1.8: If the coefficient of variation of the beta frequency band energy exceeds a preset multiple of its historical mean, it is determined that the first neural electrical signal has an abnormal oscillation pattern.

[0055] It should be noted that the preset positive threshold may be set to 2, the preset negative threshold may be set to -1, and the preset multiple may be set to 1.5 times.

[0056] Preferably, the method for determining abnormal oscillation patterns provided by the present invention makes full use of the strategic implantation position of deep brain stimulation electrodes to achieve direct acquisition of neural electrical activity in the core pathological area of ​​Parkinson's disease. Unlike traditional methods that rely only on clinical symptom assessment, the present invention performs high-precision spectrum analysis on the acquired neural electrical signals, focusing on the quantitative assessment of abnormal enhancement of β-band power, thereby achieving real-time, objective identification and quantification of abnormal oscillation patterns. This method based on neuroelectrophysiology not only provides highly objective quantitative indicators for the assessment of Parkinson's disease, but also provides a theoretical basis and practical guidance for the dynamic adjustment of stimulation parameters. Specifically, the present invention accurately captures the abnormal synchronization phenomenon of neural networks under pathological conditions by dynamically monitoring the energy ratio β / α between the β band and the α band, and the energy ratio θ / α between the θ band and the α band, combined with individualized historical data comparison. Compared with the prior art, the present invention not only takes into account the absolute energy level, but also effectively controls the variability between individuals and measurements through the calculation of relative ratios and standardized scores (Z scores), thereby significantly improving the specificity and sensitivity of abnormal oscillation pattern recognition. In addition, the present invention introduces the analysis of the energy variation coefficient of the β frequency band, which further enhances the detection capability of transient abnormal activities and provides a more fine-grained neurophysiological basis for the precise regulation of stimulation parameters.

[0057] Further, S1.2: obtaining a second neural electrical signal of a target patient (i.e., a Parkinson's patient) based on a second stimulation electrode (i.e., a vagus nerve stimulation electrode), and determining a neural network synchronization feature in the second neural electrical signal, comprising the following steps:

[0058] S1.2.1: collecting a second neural electrical signal from the vagus nerve stimulation electrode within a preset time period;

[0059] S1.2.2: Perform wavelet transform on the second neural electrical signal to obtain the time-frequency energy distribution of the δ frequency band (0.5-4Hz), θ frequency band (4-8Hz), α frequency band (8-13Hz), β frequency band (13-30Hz) and γ frequency band (30-100Hz). The wavelet transform adopts the continuous wavelet transform (CWT) method, which will not be described in detail here.

[0060] S1.2.3: Calculate the phase locking value (PLV) between the δ band, θ band, α band, β band and γ band.

[0061] It should be noted that, compared with the prior art, the phase lock value (PLV) calculation in this embodiment introduces a phase difference variance term, because:

[0062] a) Increased robustness: By taking into account the variance of the phase difference, it is able to better handle noise and fluctuations in the signal.

[0063] b) Reflecting synchronization stability: The phase difference variance term reflects the stability of the phase difference. A smaller variance indicates more stable synchronization, resulting in a higher PLV value.

[0064] c) Distinguishing between persistent and transient synchronization: Traditional PLV calculation may overestimate the importance of transient synchronization, while the improved PLV calculation better distinguishes persistent, stable synchronization from transient, unstable synchronization through the phase difference variance term.

[0065] Specifically, for two frequency bands i and j, the phase difference Δφ at sampling point n is ij (n) is calculated as follows:

[0066] Δφ ij (n) = φ i (n)-φ j (n);

[0067] Furthermore, the variance of the phase difference is calculated The following steps are involved:

[0068] 1. Calculate the average phase difference of the entire time series

[0069]

[0070] 2. Calculate the variance of the phase difference

[0071]

[0072] Substituting this variance into the existing phase lock value (PLV) calculation formula, we get the improved phase lock value (PLV) calculation formula:

[0073]

[0074] Among them, i and j are different frequency bands; N is the number of sampling points; φ i (n) and φ j (n) are the phases of the i-th frequency band and the j-th frequency band at the n-th sampling point; is the variance of the phase difference; is the phase difference between the two frequency bands. The PLV value will be reduced when the phase difference fluctuates greatly, thereby better reflecting the actual synchronization status.

[0075] Preferably, the improved phase lock value (PLV) can also realize multi-band synchronization evaluation compared with the prior art, and can be used to calculate the PLV between any two frequency bands, rather than being limited to synchronization evaluation within a single frequency band. This enables the present invention to comprehensively evaluate the interaction between different brain wave frequency bands.

[0076] If any two frequency bands satisfy the first preset condition, the two frequency bands are marked as highly synchronized; wherein the first preset condition is:

[0077]

[0078] in, and It refers to the entropy of the phase sequence, which is generally expressed as The calculation formula is as follows:

[0079]

[0080] p k is the probability that the phase value falls into the kth bin (bin refers to an interval or grouping), and K is the total number of bins.

[0081] S1.2.4: Based on the phase lock value calculated in S1.2.3, construct a 5×5 phase synchronization matrix M:

[0082] M ij =PLV ij ·(1+α·H ij );

[0083] Among them, H ij is the indicator function. When bands i and j are marked as highly synchronized, H ij =1, otherwise H ij = 0. α is a small positive constant (such as 0.1) with a value range of 0 to 1, and is used to adjust the weight of the highly synchronized frequency band pair in the phase synchronization matrix.

[0084] Calculate the eigenvalues ​​of the phase synchronization matrix M:

[0085] det(M-λI)=0;

[0086] Among them, λ is the eigenvalue; I is the 5×5 identity matrix.

[0087] Get the maximum eigenvalue λ max and the second largest eigenvalue λ sub .

[0088] The neural network synchronization characteristic index S is calculated and used as a mathematical representation of the neural network synchronization characteristic. The neural network synchronization characteristic index S is calculated by the following formula:

[0089]

[0090] Among them, N high is the number of band pairs marked as highly synchronized; β is a small positive constant (such as 0.05, it should be understood that the β here is different from the β band mentioned above) used to consider the number of highly synchronized band pairs. 10 is the total number of possible band pairs (5 bands, a total of 10 different band pairs).

[0091] Preferably, by constructing a matrix containing comprehensive inter-band phase synchronization information and introducing weight adjustment of highly synchronized frequency band pairs, accurate quantification of the overall synchronization state of the neural network is achieved. In addition, the eigenvalue analysis method of the matrix can not only capture the strength of the dominant synchronization mode, but also reflect the contribution of the secondary synchronization mode, thereby providing a multi-dimensional, highly sensitive neural network synchronization evaluation index. Compared with the traditional single frequency band or frequency band pair analysis, this embodiment significantly improves the ability to characterize the dynamic characteristics of complex neural networks, and can more comprehensively reflect the changes in abnormal synchronous activity in the brains of Parkinson's patients. At the same time, this embodiment compresses high-dimensional synchronization information into a few key eigenvalues ​​through mathematical dimensionality reduction, greatly simplifies the subsequent data processing and decision-making process, and provides a solid mathematical foundation for realizing fast and accurate intelligent regulation.

[0092] S2: Determine a neural evaluation value according to the neural activity characteristics, and generate a co-stimulation parameter based on the neural evaluation value.

[0093] Specifically, the nerve evaluation value includes a first nerve evaluation value and a second nerve evaluation value. In the embodiment of the present application, the first nerve evaluation value is a nerve activity state evaluation value, and the second nerve evaluation value is a nerve regulation effect evaluation value.

[0094] In an optional embodiment, based on the abnormal oscillation pattern and the initial stimulation parameters of the deep brain stimulation electrode, the neural activity state evaluation value of the deep brain region is determined; at the same time, based on the mathematical representation of the neural network synchronization characteristics, that is, the neural network synchronization characteristic index, the neuromodulation effect evaluation value of the vagus nerve region is determined; finally, based on the neural activity state evaluation value and the neuromodulation effect evaluation value, the synergistic stimulation parameters of the deep brain stimulation electrode and the vagus nerve stimulation electrode are dynamically generated.

[0095] Further, S2.1: based on the abnormal oscillation pattern and the initial stimulation parameters of the first stimulation electrode (ie, the deep brain stimulation electrode), a first neural evaluation value (ie, a neural activity state evaluation value) is determined.

[0096] S2.1.1: Calculate the ratio of the coefficient of variation of the β-band energy in the abnormal oscillation mode to its historical mean to obtain the abnormal oscillation intensity index.

[0097] S2.1.2: Compare the stimulation frequency, stimulation amplitude and pulse width in the initial stimulation parameters of the first stimulation electrode with the preset standard parameters respectively to obtain the stimulation parameter deviation value.

[0098] It should be noted that the preset standard parameters refer to a reference parameter set for deep brain stimulation for the treatment of Parkinson's disease based on a large amount of clinical data and expert consensus. These parameters include, but are not limited to, stimulation frequency (usually in the range of 130-180Hz), stimulation amplitude (generally 1-3.5V or 1-3.5mA), and pulse width (typical value is 60-90μs). The preset standard parameters take into account the neurophysiological characteristics of the target brain area, symptom relief effects, and adverse reaction risks, and provide a benchmark for individualized regulation. In actual applications, the preset standard parameters need to be dynamically adjusted according to the specific circumstances of the patient to achieve the best therapeutic effect.

[0099] S2.1.3: Perform a weighted summation of the abnormal oscillation intensity index and the stimulation parameter deviation value to obtain the first neural assessment value of the deep brain area.

[0100] S2.2: Based on the mathematical representation of the neural network synchronization characteristics, that is, the neural network synchronization characteristic index, determine the second neural evaluation value (that is, the neural regulation effect evaluation value).

[0101] S2.2.1: Based on the neural network synchronization characteristic index, the degree of synchronization anomaly is obtained.

[0102] Specifically, first, set three thresholds T1, T2, and T3, where T1 < T2 < T3, and these thresholds are determined based on a large amount of clinical data and the neural network synchronization feature index distribution of the normal population.

[0103] Secondly, compare the neural network synchronization feature index S with these three thresholds:

[0104] If S ≤ T1, define the synchronization abnormality degree as 0;

[0105] If T1 < S ≤ T2, define the synchronization abnormality degree as 1;

[0106] If T2 < S ≤ T3, define the synchronization abnormality degree as 2;

[0107] If S > T3, define the synchronization abnormality degree as 3;

[0108] Finally, output the synchronization abnormality degree as the result of this step for use in the subsequent calculation of the second neural evaluation value.

[0109] S2.2.2: Calculate the ratio of the number of highly synchronized frequency band pairs to the total number of frequency band pairs to obtain the high synchronization ratio.

[0110] S2.2.3: Perform a weighted average of the synchronization abnormality degree and the high synchronization ratio to obtain the second neural evaluation value of the vagus nerve region.

[0111] S2.3: Generate the coordinated stimulation parameters of the first stimulation electrode (i.e., the deep brain stimulation electrode) and the second stimulation electrode (i.e., the vagus nerve stimulation electrode) according to the first neural evaluation value (i.e., the neural activity state evaluation value) and the second neural evaluation value (i.e., the neural regulation effect evaluation value).

[0112] S2.3.1: Compare the first neural evaluation value with a first preset threshold to determine the stimulation intensity adjustment coefficient of the first stimulation electrode;

[0113] S2.3.2: Compare the second neural evaluation value with a second preset threshold to determine the stimulation frequency adjustment coefficient of the second stimulation electrode;

[0114] S2.3.3: Calculate the new stimulation parameters of the first stimulation electrode and the second stimulation electrode respectively according to the stimulation intensity adjustment coefficient and the stimulation frequency adjustment coefficient to obtain the coordinated stimulation parameters.

[0115] First, calculate the new stimulation parameters of the first stimulation electrode:

[0116] New stimulation amplitude 1 = current stimulation amplitude 1 * (1 + γ1 * stimulation intensity adjustment coefficient);

[0117] New pulse width 1 = current pulse width 1*(1+γ2*stimulation intensity adjustment coefficient);

[0118] New stimulation frequency 1 = current stimulation frequency 1*(1+γ3*stimulation frequency adjustment coefficient);

[0119] Next, calculate the new stimulation parameters for the second stimulation electrode:

[0120] New stimulation amplitude 2 = current stimulation amplitude 2*(1+γ4*stimulation intensity adjustment coefficient);

[0121] New pulse width 2 = current pulse width 2*(1+γ5*stimulation intensity adjustment coefficient);

[0122] New stimulation frequency 2 = current stimulation frequency 2*(1+γ6*stimulation frequency adjustment coefficient);

[0123] Finally, the new stimulation parameters of the first stimulation electrode and the new stimulation parameters of the second stimulation electrode are combined to form synergistic stimulation parameters.

[0124] Among them, the current stimulation amplitude 1, the current pulse width 1, and the current stimulation frequency 1 are the initial stimulation parameters of the first stimulation electrode; the current stimulation amplitude 2, the current pulse width 2, and the current stimulation frequency 2 are the initial stimulation parameters of the second stimulation electrode; γ1, γ2, γ3, γ4, γ5, and γ6 are adjustment coefficients used to control the adjustment amplitude of each parameter.

[0125] Preferably, step S2 introduces a dual-path evaluation mechanism in the present invention, taking into account the neural activity state of the deep brain region and the vagus nerve region at the same time, and realizing a comprehensive evaluation of the nervous system of patients with Parkinson's disease. By introducing multidimensional indicators such as abnormal oscillation intensity index, stimulation parameter deviation value, neural network synchronization characteristic index, and combining the dynamic threshold classification method, the present invention significantly improves the personalization and accuracy of the evaluation, which not only takes into account the individual differences of patients, but also integrates clinical experience, and can more finely capture the abnormal pattern of the neural network. In addition, step S2 constructs a closed-loop feedback mechanism to dynamically generate synergistic stimulation parameters. This collaborative regulation strategy comprehensively considers the mutual influence of the two stimulation areas of the deep brain and the vagus nerve, and realizes a more refined and comprehensive optimization of the stimulation effect by adjusting multiple stimulation parameters (such as stimulation amplitude, pulse width and stimulation frequency) at the same time. Compared with the single stimulation or simple superposition stimulation in the prior art, the method of the present invention can better adapt to the complexity and variability of Parkinson's disease symptoms, and is expected to significantly improve the accuracy, effectiveness and quality of life of patients with treatment.

[0126] S3: The initial stimulation parameters of the stimulation electrodes are adjusted based on the synergistic stimulation parameters, and stimulation is implemented on the target patient through the stimulation electrodes to complete the intelligent regulation of dual-path stimulation of cranial nerves for Parkinson's disease.

[0127] Adjusting the initial stimulation parameters of the stimulation electrode based on the co-stimulation parameters includes the following steps:

[0128] receiving the co-stimulation parameters and parsing them into new stimulation parameters for the first stimulation electrode and the second stimulation electrode;

[0129] Compare the new stimulation parameters with the initial stimulation parameters of the respective stimulation electrodes and calculate the parameter adjustment amount;

[0130] According to the parameter adjustment amount, the stimulation parameters of the first stimulation electrode and the second stimulation electrode are updated respectively, and the adjustment of the initial stimulation parameters of the stimulation electrodes is completed.

[0131] In summary, the present invention achieves comprehensive quantification of neural activity in the deep brain and vagus nerve regions and improves the accuracy of neural regulation by introducing real-time evaluation of abnormal oscillation patterns and neural network synchronization characteristics. Secondly, the present invention achieves intelligent collaborative regulation by generating co-stimulation parameters, taking into account the mutual influence of the two stimulation pathways. In addition, the present invention can more flexibly adapt to the dynamic changes of patient symptoms and provide highly individualized treatment plans. Finally, the introduction of a closed-loop feedback mechanism significantly improves the stability and long-term effectiveness of the stimulation effect, while potentially reducing the occurrence of side effects.

[0132] Embodiment 2 is an embodiment of the present invention, which provides a brain nerve dual-path stimulation intelligent control system for Parkinson's disease, comprising:

[0133] The acquisition unit includes a neural electrical signal acquisition module and a neural activity feature determination module. The neural electrical signal acquisition module is used to acquire the neural electrical signal of the target patient based on the stimulation electrode; the neural activity feature determination module is used to determine the neural activity feature based on the neural electrical signal;

[0134] The evaluation generation unit includes a neural evaluation value determination module and a synergistic stimulation parameter generation module. The neural evaluation value determination module is used to determine a neural evaluation value according to neural activity characteristics, wherein the neural evaluation value includes a first neural evaluation value and a second neural evaluation value; and the synergistic stimulation parameter generation module is used to generate synergistic stimulation parameters based on the neural evaluation value.

[0135] The regulation execution unit includes a stimulation parameter regulation module and a stimulation execution module. The stimulation parameter regulation module is used to adjust the initial stimulation parameters of the stimulation electrode based on the synergistic stimulation parameters; the stimulation execution module is used to stimulate the target patient through the stimulation electrode to complete the intelligent regulation of the cranial nerve dual-path stimulation for Parkinson's disease.

[0136] Example 3, reference Figure 2, is an embodiment of the present invention, which is different from the previous embodiment in that: if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0137] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0138] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0139] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0140] Example 4 is an embodiment of the present invention, which provides a brain nerve dual-path stimulation intelligent control system for Parkinson's disease. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0141] In order to compare and analyze the performance of the present invention with the prior art in multiple aspects, 60 Parkinson's patients were randomly divided into an experimental group and a control group, with 30 people in each group. The experimental group received the dual-channel intelligent regulation stimulation treatment of the present invention, and the control group received the traditional single-site open-loop stimulation treatment. The treatment cycle was 6 months, and evaluations were performed before treatment, 3 months after treatment, and 6 months after treatment. The evaluation indicators included the Unified Parkinson's Disease Rating Scale (UPDRS), daily living activities (ADL) score, beta band energy ratio, neural network synchronization index, and patient-reported side effect incidence.

[0142] The experiment also compared and analyzed the stability and adjustment frequency of stimulation parameters of the two groups of patients, and recorded the number of stimulation parameter adjustments for each patient within 6 months, as well as the amplitude of changes in stimulation parameters. In addition, through electroencephalogram (EEG) and neuroimaging examinations, this embodiment evaluated the functional connectivity changes of the brain neural network of the two groups of patients. All data were statistically analyzed, and paired t-tests and repeated measures analysis of variance were used to evaluate the significance of differences between and within groups.

[0143] Table 1: Comparison of UPDRS scores and ADL scores

[0144] Group Evaluation time UPDRS-III score (mean ± standard deviation) ADL score (mean ± standard deviation) Experimental Group Before treatment 42.3±5.7 62.5±8.2 Experimental Group 3 months later 28.6±4.9 75.8±7.5 Experimental Group 6 months later 22.1±4.2 82.3±6.8 Control group Before treatment 41.9±5.5 63.1±7.9 Control group 3 months later 33.7±5.2 70.2±7.7 Control group 6 months later 30.5±4.8 72.8±7.4

[0145] As shown in Table 1, there was no significant difference in the UPDRS-III scores and ADL scores between the experimental group and the control group before treatment. However, after 3 and 6 months of treatment, the UPDRS-III scores of the experimental group were significantly lower than those of the control group (p<0.01), indicating that motor symptoms were better improved. At the same time, the ADL scores of the experimental group were also significantly higher than those of the control group (p<0.01), indicating that the patients' daily living ability was improved to a greater extent. It is particularly noteworthy that the UPDRS-III scores of the experimental group at 6 months still decreased significantly compared to those at 3 months (p<0.05), while the improvement of the control group during the 3-6 month period was smaller, indicating that the present invention has a more lasting therapeutic effect.

[0146] Table 2: Comparison of neurophysiological parameters

[0147]

[0148]

[0149] Table 2 shows the changes in neurophysiological indicators of the two groups of patients before and after treatment. The β-band energy ratio reflects the degree of abnormal brain oscillation in Parkinson's patients, while the neural network synchronization index reflects the degree of excessive synchronization of the neural network. The data showed that the β-band energy ratio and the neural network synchronization index of the experimental group were significantly reduced after treatment (p<0.001), and the reduction was greater than that of the control group. This shows that the present invention can not only effectively inhibit abnormal oscillations, but also better regulate the synchronization of the neural network. In particular, at the 6-month point, the two indicators of the experimental group continued to improve, while the control group tended to stabilize, further confirming the advantages of this method in long-term treatment.

[0150] Table 3: Comparison of stimulation parameter stability and side effects

[0151]

[0152] Table 3 reflects the stability of stimulation parameters and the occurrence of side effects in the two groups of patients during the 6-month treatment period. The number of stimulation parameter adjustments in the experimental group was significantly less than that in the control group (p<0.001), and the changes in stimulation amplitude and frequency were also significantly less than those in the control group (p<0.01). This shows that the present invention can find the optimal stimulation parameters more quickly and that the parameters have better stability. More importantly, the incidence of side effects in the experimental group (12.5%) was significantly lower than that in the control group (28.3%), and the difference was statistically significant (p<0.05). These data strongly prove that the present invention can not only provide a more stable and individualized stimulation scheme, but also significantly reduce the incidence of side effects, thereby improving patients' treatment compliance and quality of life.

[0153] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A brain nerve dual-path stimulation intelligent control system for Parkinson's disease, characterized in that: include: A collection unit, including a neural electrical signal collection module and a neural activity feature determination module; The neural electrical signal acquisition module is used to acquire the neural electrical signal of the target patient based on the stimulation electrode; the neural activity feature determination module is used to determine the neural activity feature according to the neural electrical signal; An evaluation generation unit, comprising a neural evaluation value determination module and a synergistic stimulation parameter generation module; the neural evaluation value determination module is used to determine a neural evaluation value according to the neural activity characteristics, the neural evaluation value comprising a first neural evaluation value and a second neural evaluation value; the synergistic stimulation parameter generation module is used to generate synergistic stimulation parameters based on the neural evaluation value; The regulation execution unit includes a stimulation parameter regulation module and a stimulation execution module; the stimulation parameter regulation module is used to adjust the initial stimulation parameters of the stimulation electrode based on the synergistic stimulation parameters; the stimulation execution module is used to stimulate the target patient through the stimulation electrode to complete the intelligent regulation of cranial nerve dual-path stimulation for Parkinson's disease; The neural activity characteristics include abnormal oscillation patterns and neural network synchronization characteristics; Acquiring a neural electrical signal of a target patient based on a stimulation electrode and determining neural activity characteristics according to the neural electrical signal include the following steps: acquiring the first neural electrical signal of the target patient based on the first stimulation electrode, and determining an abnormal oscillation pattern in the first neural electrical signal; Acquire the second neural electrical signal of the target patient based on the second stimulation electrode, and determine the neural network synchronization feature in the second neural electrical signal; Acquiring the first neural electrical signal of the target patient based on the first stimulation electrode and determining an abnormal oscillation pattern in the first neural electrical signal includes the following steps: collecting the first neural electrical signal of the first stimulation electrode within a preset time period; Performing wavelet transform on the first neural electrical signal to obtain time-frequency energy distribution of β frequency band, α frequency band and θ frequency band; Calculate the energy ratio β / α between the β band and the α band, and the energy ratio θ / α between the θ band and the α band; Based on a pre-established individualized database, a historical energy ratio data set of the target patient is obtained; wherein the historical energy ratio data set includes the historical energy ratio β / α and the historical energy ratio θ / α ratio of the target patient within a predefined time window in the past; Based on the historical energy ratio data set, respectively calculating the historical mean and historical standard deviation of the energy ratio β / α and the energy ratio θ / α; Based on the historical mean and the historical standard deviation, respectively calculating the Z scores of the energy ratio β / α and the energy ratio θ / α; If the Z score of the energy ratio β / α is greater than a preset positive threshold and the Z score of the energy ratio θ / α is less than a preset negative threshold, then calculating the coefficient of variation of the β-band energy; If the coefficient of variation of the beta frequency band energy exceeds a preset multiple of its historical mean, it is determined that the first neural electrical signal has an abnormal oscillation pattern; Acquiring the second neural electrical signal of the target patient based on the second stimulation electrode and determining the neural network synchronization feature in the second neural electrical signal comprises the following steps: collecting a second neural electrical signal from the second stimulation electrode within a preset time period; Performing wavelet transformation on the second neural electrical signal to obtain the time-frequency energy distribution of the δ frequency band, the θ frequency band, the α frequency band, the β frequency band and the γ frequency band; Calculating the phase locking values ​​between the δ frequency band, the θ frequency band, the α frequency band, the β frequency band and the γ frequency band, and marking any two frequency bands as being highly synchronized when the first preset condition is satisfied; Based on the phase locking value, construct a phase synchronization matrix; Calculating the eigenvalues ​​of the phase synchronization matrix to obtain the maximum eigenvalue and the second largest eigenvalue; According to the maximum eigenvalue, the second largest eigenvalue, and the number of frequency band pairs marked as highly synchronized, a neural network synchronization characteristic index is determined, and the neural network synchronization characteristic index is used as a mathematical representation of the neural network synchronization characteristic.

2. The brain nerve dual-path stimulation intelligent control system for Parkinson's disease according to claim 1, characterized in that: Determining a neural assessment value according to the neural activity characteristics comprises the following steps: determining the first nerve evaluation value based on the abnormal oscillation pattern and the initial stimulation parameters of the first stimulation electrode; A second neural assessment value is determined based on a mathematical representation of the neural network synchronization feature, namely a neural network synchronization feature index.

3. The brain nerve dual-path stimulation intelligent control system for Parkinson's disease according to claim 2, characterized in that: Determining the first nerve evaluation value based on the abnormal oscillation pattern and the initial stimulation parameters of the first stimulation electrode comprises the following steps: Calculating the ratio of the coefficient of variation of the β-band energy in the abnormal oscillation mode to its historical mean value to obtain an abnormal oscillation intensity index; Compare the stimulation frequency, stimulation amplitude and pulse width in the initial stimulation parameters of the first stimulation electrode with the preset standard parameters respectively to obtain a stimulation parameter deviation value; Performing a weighted summation of the abnormal oscillation intensity index and the stimulation parameter deviation value to obtain a first nerve assessment value; Determining a second neural evaluation value based on the mathematical representation of the neural network synchronization characteristic, that is, the neural network synchronization characteristic index, comprises the following steps: Based on the neural network synchronization characteristic index, obtaining the degree of synchronization abnormality; Calculating the ratio of the number of highly synchronized frequency band pairs to the total number of frequency band pairs to obtain a high synchronization ratio; The synchronization abnormality degree and the high synchronization ratio are weighted averaged to obtain a second nerve assessment value.

4. The brain nerve dual-path stimulation intelligent control system for Parkinson's disease as claimed in claim 3, characterized in that: Generating a co-stimulation parameter based on the neural evaluation value comprises the following steps: Substituting the first nerve evaluation value into a sigmoid function to obtain a stimulation intensity adjustment coefficient of the first stimulation electrode; Substituting the second nerve evaluation value into the arctangent function, the stimulation frequency adjustment coefficient of the second stimulation electrode is obtained. According to the stimulation intensity adjustment coefficient and the stimulation frequency adjustment coefficient, new stimulation parameters of the first stimulation electrode and the second stimulation electrode are calculated respectively to obtain synergistic stimulation parameters, which are specifically: Calculate new stimulation parameters for the first stimulation electrode: New stimulation amplitude 1 = current stimulation amplitude 1*(1+γ1*stimulation intensity adjustment coefficient); New pulse width 1 = current pulse width 1*(1+γ2*stimulation intensity adjustment coefficient); New stimulation frequency 1 = current stimulation frequency 1*(1+γ3*stimulation frequency adjustment coefficient); Calculate new stimulation parameters for the second stimulation electrode: New stimulation amplitude 2 = current stimulation amplitude 2*(1+γ4*stimulation intensity adjustment coefficient); New pulse width 2 = current pulse width 2*(1+γ5*stimulation intensity adjustment coefficient); New stimulation frequency 2 = current stimulation frequency 2*(1+γ6*stimulation frequency adjustment coefficient); Combining the new stimulation parameters of the first stimulation electrode and the new stimulation parameters of the second stimulation electrode to form synergistic stimulation parameters; Among them, the current stimulation amplitude 1, the current pulse width 1, and the current stimulation frequency 1 are the initial stimulation parameters of the first stimulation electrode; the current stimulation amplitude 2, the current pulse width 2, and the current stimulation frequency 2 are the initial stimulation parameters of the second stimulation electrode; γ1, γ2, γ3, γ4, γ5, and γ6 are adjustment coefficients used to control the adjustment amplitude of each parameter.

5. The brain nerve dual-path stimulation intelligent control system for Parkinson's disease according to claim 4, characterized in that: Adjusting the initial stimulation parameters of the stimulation electrode based on the synergistic stimulation parameters comprises the following steps: receiving the co-stimulation parameters and parsing them into new stimulation parameters for the first stimulation electrode and new stimulation parameters for the second stimulation electrode; comparing the new stimulation parameters of the first stimulation electrode with the initial stimulation parameters of the first stimulation electrode, comparing the new stimulation parameters of the second stimulation electrode with the initial stimulation parameters of the second stimulation electrode, and calculating the parameter adjustment amount; According to the parameter adjustment amount, the stimulation parameters of the first stimulation electrode and the second stimulation electrode are updated respectively, so as to complete the adjustment of the initial stimulation parameters of the stimulation electrodes.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the intelligent control system for dual-path stimulation of cranial nerves for Parkinson's disease described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent control system for dual-path stimulation of cranial nerves for Parkinson's disease described in any one of claims 1 to 5 are implemented.

Images