Equipment, method and device for intelligently adjusting implantable electrical stimulation

Abstract

The invention provides a device, method and device for intelligently adjusting implantable electrical stimulation, and the device comprises a controller, a stimulation circuit, a switching circuit, and an acquisition circuit. The controller is configured to: when a characteristic value of a waveform of a first ECAP signal of a to-be-stimulated patient in a first posture is not matched with a sample, the characteristic value of which is the same as the characteristic value of the waveform of the first ECAP signal, in a target sample selected from a sample library; taking the stimulation parameter adjustment function corresponding to the sample with the minimum deviation between the characteristic value of the ECAP signal waveform in the target sample and the characteristic value of the waveform of the first ECAP signal as a first stimulation parameter adjustment function, so as to reduce the matched data volume, and further adjusting the first stimulation parameter adjustment function through a stimulation parameter adjustment model. The method obtains the stimulation parameter adjustment function suitable for the current patient, adjusts the stimulation parameter according to the stimulation parameter adjustment function, achieves the self-adaptive adjustment of the stimulation parameter value, improves the accuracy of the adjustment of the stimulation parameter, and further improves the stability of the treatment effect.

Description

Technical Field

[0001] The present application relates to the field of medical electronic equipment, and in particular to a device, method and apparatus for intelligently regulating implantable electrical stimulation. Background Art

[0002] An implantable electrical stimulation device is an implantable medical device that can generate electrical stimulation pulses and deliver them to various tissue parts of the patient to treat a variety of diseases. It has significant therapeutic effects and is therefore widely used in treatment processes such as pain relief and tissue damage repair.

[0003] However, in actual applications, when the patient's movements change, the position of the implantable electrical stimulation device in the patient's body may change accordingly, and the therapeutic effect produced by the corresponding electrical stimulation pulse will also change, resulting in unstable treatment effects, which affects the patient's treatment effect and experience.

[0004] Therefore, how to improve the stability of the therapeutic effect of implantable electrical stimulation devices is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] In view of this, the embodiments of the present application provide a device, method and apparatus for intelligently adjusting implantable electrical stimulation to achieve adaptive adjustment of stimulation parameter values, improve the stability of electrical stimulation treatment effects, and improve the accuracy and efficiency of adjusting stimulation parameters.

[0006] In a first aspect, the present application provides a device for intelligently regulating implantable electrical stimulation, which includes: a controller, a stimulation circuit, configured to generate pulses and output pulses through electrode leads; a switching circuit, connected between the controller and the electrode leads, configured to, under the control of the controller, connect the electrode contacts to the stimulation circuit and output pulses through the electrode contacts; an acquisition circuit, electrically connected to the controller, configured to receive an evoked compound action potential (ECAP) signal generated by the pulse emitted by the stimulation circuit to stimulate the body after the controller controls the stimulation circuit and the acquisition circuit to connect to the electrode contacts. The controller is configured to perform the following steps: obtaining the characteristic value of the waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture; determining at least one target sample in the sample library, each target sample including the waveform information of the ECAP signal of the sample patient and the stimulation parameter adjustment function, the stimulation parameter adjustment function being used to characterize the functional relationship between the change of the waveform and the stimulation parameter increment; matching with at least one target sample according to the characteristic value of the waveform of the first ECAP signal, and determining that there is no sample in the at least one target sample with the same characteristic value of the waveform of the first ECAP signal; taking the stimulation parameter adjustment function corresponding to the sample with the smallest deviation between the characteristic value of the waveform of the ECAP signal in at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function; adjusting the first stimulation parameter adjustment function through the trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function; adjusting the stimulation parameter value based on the second stimulation parameter adjustment function to obtain the adjusted stimulation parameter value; and sending the adjusted stimulation parameter value to the body of the patient to be stimulated through the stimulation circuit.

[0007] In one embodiment provided by the present invention, determining at least one target sample in the sample library includes: obtaining category information of the body of the patient to be stimulated; matching the category information of the body of the patient to be stimulated with the category information of the sample body in the sample library; and taking at least one target sample in the sample library whose category information is the same as the category information of the body of the patient to be stimulated as at least one target sample.

[0008] In one embodiment provided by the present invention, the controller is further configured to: match the characteristic value of the waveform of the first ECAP signal with at least one target sample, and determine whether there is a sample with the same characteristic value as the waveform of the first ECAP signal in the at least one target sample; select the stimulation parameter adjustment function of the sample with the smallest deviation between the characteristic value of the ECAP signal waveform and the characteristic value of the first ECAP signal waveform among the samples with the same characteristic value as the waveform of the first ECAP signal in the at least one target sample as the target stimulation parameter adjustment function; adjust the stimulation parameter value based on the target stimulation parameter adjustment function; and emit the stimulation parameter value to the patient's body based on the adjusted stimulation parameter value.

[0009] In one embodiment provided by the present invention, according to the characteristic value of the waveform of the first ECAP signal, matching is performed with at least one target sample to determine whether there is a sample with the same characteristic value as the waveform of the first ECAP signal in the at least one target sample, including: selecting any sample from the at least one target sample as the first target sample, calculating the deviation value between the characteristic value of the ECAP signal waveform in the first target sample and the characteristic value of the waveform of the first ECAP signal; comparing the deviation value with a preset threshold; and when the deviation value is less than the preset threshold, determining that there is a sample with the same characteristic value as the first ECAP waveform in the target sample.

[0010] In one embodiment provided by the present invention, matching is performed with at least one target sample based on the characteristic value of the waveform of the first ECAP signal, and determining that no sample in the at least one target sample has the same characteristic value as the waveform of the first ECAP signal, includes: selecting any sample in the at least one target sample as the first target sample, calculating the deviation value between the characteristic value of the waveform of the ECAP signal in the first target sample and the characteristic value of the waveform of the first ECAP signal; comparing the deviation value with a preset threshold; and when it is determined that the deviation value is not less than the preset threshold, selecting any sample in the at least one target sample except the first target sample as the second target sample, repeating the above steps, and when all samples in the at least one target sample have been selected, stopping repeating the above steps, and determining that no sample in the target sample has the same characteristic value as the first ECAP waveform.

[0011] In one embodiment provided by the present invention, the controller is further configured to: when the patient's posture is changed to a second posture, adjust the first stimulation parameter value according to the second stimulation parameter adjustment function to obtain a second stimulation parameter value, wherein the first stimulation parameter value is the stimulation parameter value corresponding to the patient's first ECAP signal; based on the patient's feedback, confirm whether the stimulation pulse based on the second stimulation parameter value makes the patient feel comfortable; if not, adjust the currently determined stimulation parameter adjustment function through the trained adjustment model to obtain an adjusted stimulation parameter adjustment function; based on the patient's feedback, confirm whether the stimulation pulse based on the adjusted stimulation parameter value makes the patient feel comfortable; if not, repeatedly adjust the currently determined stimulation parameter adjustment function through the trained adjustment model until the patient feedback indicates that the stimulation pulse based on the adjusted stimulation parameter value feels comfortable, and adjust the current stimulation parameter value based on the adjusted stimulation parameter adjustment function.

[0012] In one embodiment provided by the present invention, after confirming whether the stimulation pulse based on the second stimulation parameter value makes the patient feel comfortable based on the patient's feedback, the controller is further configured to: if so, when the patient's posture continues to change to the third posture, adjust the second stimulation parameter according to the second stimulation parameter adjustment function to obtain the third stimulation parameter value; confirm whether the stimulation pulse corresponding to the third stimulation parameter value makes the patient feel comfortable based on the patient's feedback; if so, determine to use the second stimulation parameter adjustment function to adjust the stimulation parameter value when the patient's posture changes; if not, repeatedly adjust the currently determined stimulation parameter adjustment function through the trained adjustment model until the patient feedback feels comfortable with the stimulation pulse based on the adjusted stimulation parameter value, and adjust the current stimulation parameter value based on the adjusted stimulation parameter adjustment function.

[0013] In one embodiment provided by the present invention, the controller is further configured to: when the patient to be stimulated feeds back that the current stimulation pulse makes him feel uncomfortable, automatically update the stimulation parameter adjustment function through the trained stimulation parameter adjustment model; adjust the stimulation parameter value based on the updated stimulation parameter adjustment function; based on the feedback from the patient to be stimulated, confirm whether the stimulation pulse corresponding to the adjusted stimulation parameter value makes the patient feel comfortable; if not, repeat the above steps until the patient to be stimulated feeds back that the current stimulation pulse makes him feel comfortable.

[0014] In one embodiment provided by the present invention, the controller is further configured to: upload the updated stimulation parameter adjustment function, the corresponding ECAP signal waveform information and the category information of the patient to be stimulated to the sample library as a new sample in the sample library; and update the sample library based on the new sample.

[0015] In one embodiment provided by the present invention, obtaining the characteristic value of the waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture includes: determining the waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture; and extracting the characteristic value of the waveform of the first ECAP signal based on a deep learning algorithm.

[0016] In one embodiment provided by the present invention, determining the waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture includes: sending a pulse to the body of the patient to be stimulated based on the initial stimulation parameter value, and sending an induced pulse to the body of the patient to be stimulated, wherein the induced pulse is used to induce the body of the patient to be stimulated to send an ECAP signal corresponding to the initial stimulation parameter value; judging whether the initial stimulation parameter value makes the patient to be stimulated feel comfortable based on feedback from the body of the patient to be stimulated; if so, determining that the waveform of the ECAP signal corresponding to the initial stimulation parameter value is the first ECAP signal waveform; if not, adjusting the initial stimulation parameter value, and repeating the above steps.

[0017] In one embodiment of the present invention, the controller is further configured to: collect ECAP signals and corresponding stimulation parameter adjustment functions from multiple treated patients to construct a sample library; classify the samples in the sample library and label the sample categories in the sample library; and train a stimulation parameter adjustment model based on the ECAP signals of the treated patients, the corresponding stimulation parameter adjustment functions, and the labeled category information for each sample in the sample library.

[0018] In a second aspect, the present application provides a method for intelligently adjusting implantable electrical stimulation, the method comprising: obtaining a characteristic value of a waveform of a first ECAP signal of a patient to be stimulated in a first posture; determining at least one target sample in a sample library, each target sample comprising waveform information of the ECAP signal of the sample patient and a stimulation parameter adjustment function, the stimulation parameter adjustment function being used to characterize the functional relationship between the change in the ECAP signal waveform and the stimulation parameter increment; matching at least one target sample based on the characteristic value of the waveform of the first ECAP signal, and determining that no sample in at least one target sample has the same characteristic value as the waveform of the first ECAP signal; using the stimulation parameter adjustment function corresponding to the sample having the smallest deviation between the characteristic value of the waveform of the ECAP signal in at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function; adjusting the first stimulation parameter adjustment function through a trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function; adjusting the stimulation parameter value based on the second stimulation parameter adjustment function when the patient's posture changes; and sending a pulse to the patient's body based on the adjusted stimulation parameter value.

[0019] In a third aspect, the present application provides a device for intelligently adjusting implantable electrical stimulation, including an acquisition module for acquiring a characteristic value of a waveform of a first ECAP signal of a patient to be stimulated in a first posture; a determination module for determining at least one target sample in a sample library, each target sample including waveform information of the ECAP signal of the sample patient and a stimulation parameter adjustment function, the stimulation parameter adjustment function being used to characterize the functional relationship between the change in the waveform of the ECAP signal and the stimulation parameter increment; a matching module for matching at least one target sample based on the characteristic value of the waveform of the first ECAP signal, and determining that no sample in the at least one target sample has the same characteristic value as the waveform of the first ECAP signal; a selection module for using the stimulation parameter adjustment function corresponding to the sample with the smallest deviation between the characteristic value of the waveform of the ECAP signal in at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function; an adjustment module for adjusting the first stimulation parameter adjustment function through a trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function, and adjusting the stimulation parameter value based on the second stimulation parameter adjustment function to obtain the adjusted stimulation parameter value; and a stimulation module for emitting a pulse to the body of the patient to be stimulated based on the adjusted stimulation parameter value.

[0020] The embodiments of the present application provide an intelligently adjustable implantable electrical stimulation device, method, and apparatus. The device includes: a controller, a stimulation circuit, a switching circuit, and an acquisition circuit. The controller is configured to: when the characteristic value of the waveform of the first ECAP signal of the patient to be stimulated in the first posture does not match a sample with the same characteristic value as the waveform of the first ECAP signal in the target sample selected from the sample library, use the stimulation parameter adjustment function corresponding to the sample with the smallest deviation between the characteristic value of the waveform of the ECAP signal in the target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function to reduce the amount of matching data, further adjust the first stimulation parameter adjustment function through a stimulation parameter adjustment model to obtain a stimulation parameter adjustment function suitable for the current patient, adjust the stimulation parameters according to the stimulation parameter adjustment function, realize adaptive adjustment of the stimulation parameter value, improve the accuracy of adjusting the stimulation parameter, and further improve the stability of the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 This is a structural diagram of an implantable electrical stimulation system provided in one embodiment of the present application.

[0023] Figure 2 This is a structural diagram of an implantable electrical stimulation device provided in one embodiment of the present application.

[0024] Figure 3 This is a flow chart of a method for intelligently regulating implantable electrical stimulation provided in one embodiment of the present application.

[0025] Figure 4 This is a flow chart of adjusting stimulation parameter values ​​provided by an embodiment of the present application.

[0026] Figure 5 This is a flow chart of another method for intelligently regulating implantable electrical stimulation provided in one embodiment of the present application.

[0027] Figure 6 This is a flow chart of a method for verifying a stimulation parameter adjustment function provided in one embodiment of the present application.

[0028] Figure 7 This is a structural diagram of an implantable electrical stimulation device provided in one embodiment of the present application.

[0029] Figure 8 This is a structural diagram of an implantable electrical stimulation device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] Figure 1 This is a schematic diagram of the structure of a system for regulating electrical stimulation provided by an exemplary embodiment of the present application. Figure 1 In the figure, the reference numeral SC is used to indicate the patient's spinal cord, and the reference numeral SK is used to indicate the patient's skin. In addition, the adjustable electrical stimulation system provided in this application can also be used for electrical stimulation treatment of other parts of the body besides the spinal cord, such as the brain, waist, legs, etc. This embodiment is only used as an example to illustrate the adjustable stimulation parameter system for the spinal cord, and does not mean that the adjustable stimulation parameter system provided in this disclosure is limited to use for the spinal cord.

[0032] In related technologies, implantable electrical stimulators can use a closed-loop regulation stimulation method, that is, when the position of the implantable electrical stimulator relative to the stimulated part of the patient's body changes, causing the current stimulation parameters to make the patient feel uncomfortable, the stimulation parameter value is adaptively adjusted. For example, when the patient's body posture changes (from lying to sitting, from sitting to standing, bending over, squatting, or even coughing, sneezing, etc.), the distance and relative position between the electrode lead and the patient's body nerve fibers may change. Correspondingly, the degree of stimulation of the patient's body nerve fibers by the electrical stimulation pulse will also change, thereby affecting the patient's feelings and treatment effect.

[0033] To address the above issues, sensors can be configured in the implantable electrical stimulation system, and stimulation parameter values ​​corresponding to different postures can be set in advance. The sensors detect the patient's posture in real time, so that when the patient's posture changes, the stimulation parameter values ​​corresponding to the posture are matched, maintaining the stimulation effect basically unchanged to avoid causing discomfort to the patient. However, the above method may have the following problems:

[0034] During actual application, the changes in the patient's posture may be subtle. By pre-setting the stimulation parameter values ​​suitable for the patient's body in different postures, it may be difficult to cover the stimulation parameter values ​​under all angle changes, resulting in the inability to accurately adjust the stimulation parameter values ​​under the corresponding posture. In addition, as the use time increases, the patient's body's perception and reaction to electrical stimulation at the same stimulation intensity may change, that is, the same patient's stimulation perception under the same stimulation parameter value may change. Based on the above method, it is impossible to adaptively adjust the stimulation parameter value according to the patient's perception of the electrical stimulation of the current real-time feedback.

[0035] Based on the above problems, the present application creatively adds a deep learning model to the adjustment process of the stimulation parameter values, realizes the adaptive adjustment of the stimulation parameter values, and improves the accuracy and efficiency of the overall adjustment of the electrical stimulation parameter values.

[0036] The following will refer to the attached Figures 1 to 8 Various non-limiting embodiments of the present application will be described in detail.

[0037] The method for intelligently adjusting implantable electrical stimulation provided in the present application can be applied to an implantable electrical stimulation system, which can adaptively adjust stimulation parameter values ​​for patients in a closed-loop manner, and provide electrical stimulation therapy based on the adjusted stimulation parameter values, so that the pulses generated by the electrical stimulation system always make the patient feel comfortable.

[0038] In order to further illustrate the implantable electrical stimulation system, the present application also provides a structural diagram of the implantable electrical stimulation system ( Figure 1 ).

[0039] like Figure 1 As shown, the implantable electrical stimulation system 100 may include an electrode lead 10, an implantable electrical stimulation device 20, and a server 30. Figure 2 As shown, the implantable electrical stimulation device 20 includes: a controller 21, a stimulation circuit 22, an acquisition circuit 23 and a switching circuit 24.

[0040] The electrode lead 10 is configured to be implanted in a patient's body to deliver electrical stimulation pulses (including therapeutic pulses and induced pulses) to the patient's body. For example, the stimulation electrodes on the electrode lead can output one or more electrical stimulation signals (e.g., waveforms), i.e., therapeutic pulses; and the sensing electrodes on the electrode lead sense one or more neural responses and / or one or more muscle activation / contraction reactions induced by the induced pulses and sense them as one or more electrical stimulation induced signals.

[0041] The controller 21 can be configured to be connected to the electrode lead 10 and the server 30 in a wired or wireless manner, so as to deliver stimulation pulses to the patient's body through the electrode lead 10 and transmit the acquired relevant data to the server 30. It should be understood that an electrode can always serve as a stimulation electrode or a sensing electrode, or can serve as a stimulation electrode at one moment and a sensing electrode at another moment, or can serve as a stimulation electrode in one case and a sensing electrode in another case.

[0042] The controller 21 can be configured to be implanted in the patient's body or located outside the patient's body to generate electrical stimulation pulses. The controller 21 can be electrically connected to the electrode lead 10 via the switch circuit 24, and the electrical stimulation pulses can be delivered to the patient's body through the electrode lead 10 to achieve the purpose of treatment.

[0043] The switch circuit 24 is connected between the controller 21 and the electrode lead 10 , and is configured to, under the control of the controller 21 , connect the electrode contacts to the stimulation circuit 22 and output pulses through the electrode contacts.

[0044] The stimulation circuit 23 is electrically connected to the controller 21 and is configured to receive the evoked compound action potential (ECAP) signal generated by the electrical stimulation pulse emitted by the stimulation circuit 22 to stimulate the body when the controller 21 controls the stimulation circuit 22 and the stimulation circuit 23 is connected to the corresponding electrode contacts.

[0045] The server 30 may be one or more servers in a cloud computing environment. The server 30 may be connected to the network through a network access point ( Figure 1 The controller 21 and / or the electrode lead 10 are communicated with the controller 21 and / or the electrode lead 10 via wireless communication to obtain and store relevant information of the patient.

[0046] In some embodiments, the server 30 can be used to train and provide a stimulation parameter adjustment model, which is used to characterize the functional relationship between the change in the waveform of the ECAP signal and the stimulation parameter increment, so that when the patient's posture changes, causing the waveform of the ECAP signal to change, the stimulation parameter value can be adaptively adjusted according to the stimulation parameter adjustment model.

[0047] In the implantable electrical stimulation system 10 provided in the present application, the controller 21 can be configured to: send therapeutic pulses to the body of the patient to be stimulated based on the corresponding stimulation parameter values ​​through the electrode lead 10, and send induction pulses to the patient's body, wherein the induction pulses are used to induce the patient's body to emit ECAP signals corresponding to the corresponding stimulation parameter values.

[0048] In this application, an electrical stimulation pulse (including a therapeutic pulse and / or an induced pulse) may refer to a current pulse or a voltage pulse. Stimulation parameters of an electrical stimulation pulse may include pulse amplitude and / or pulse width. Accordingly, a stimulation parameter value may include specific values ​​of the pulse amplitude and / or pulse width.

[0049] Therapeutic pulses are used to treat symptoms, such as pain relief. Therefore, their stimulation parameters (including parameters other than pulse amplitude and pulse width, such as frequency) must ensure that the therapeutic pulses effectively affect the symptoms and achieve a therapeutic effect. Evoked pulses are used to stimulate ECAP signals. Therefore, their stimulation parameters only need to induce the patient's nerve fibers to emit ECAP signals; they do not need to have a therapeutic effect.

[0050] like Figure 2 As shown, the electrode lead 11 may include a first electrode contact 111 and a second electrode contact 112, and is configured to stimulate a human body, for example, the spinal cord SC, or other parts of the human body, without specific limitation herein. The stimulation circuit 22 is configured to generate a first pulse signal and apply the first pulse signal to the first electrode contact to stimulate the human body.

[0051] Corresponding to the above system, this specification provides a method for intelligently regulating implantable electrical stimulation applied to the above system. Figure 3 Shown is a flow chart of a method for intelligently regulating implantable electrical stimulation provided by an exemplary embodiment of the present application.

[0052] In some embodiments, Figure 3 The exemplary process shown may be executed by the controller 21 .

[0053] like Figure 3 As shown, the method may include the following steps:

[0054] S210, obtaining a characteristic value of a waveform of a first ECAP signal of a body of a patient to be stimulated in a first posture;

[0055] S220, determining at least one target sample in the sample library;

[0056] S230: Match the characteristic value of the waveform of the first ECAP signal with at least one target sample, and determine that no sample in the at least one target sample has the same characteristic value as the waveform of the first ECAP signal;

[0057] S240, using the stimulation parameter adjustment function corresponding to the sample having the smallest deviation between the characteristic value of the ECAP signal waveform in at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function;

[0058] S250, adjusting the first stimulation parameter adjustment function using the trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function;

[0059] S260, adjusting the stimulation parameter value based on the second stimulation parameter adjustment function to obtain an adjusted stimulation parameter value;

[0060] S270: Send stimulation parameters based on the adjusted values ​​to the patient's body to be stimulated.

[0061] Specifically, the first posture may be the initial posture of the patient to be stimulated. For example, the initial posture may be a lying position, a sitting position, etc. This is not specifically limited herein. Accordingly, the first ECAP signal may be an ECAP signal corresponding to a stimulation pulse generated based on stimulation parameters suitable for the patient in the first posture (i.e., the initial posture).

[0062] In some embodiments, a therapeutic pulse can be emitted to the body of the patient to be stimulated based on the initial stimulation parameter value (random stimulation parameter value), and an induction pulse can be emitted to the body of the patient to be stimulated, wherein the induction pulse is used to induce the patient's body to emit an ECAP signal corresponding to the initial stimulation parameter value; based on the feedback from the body of the patient to be stimulated, it is judged whether the initial stimulation parameter value makes the patient feel comfortable; and the waveform of the ECAP signal corresponding to the stimulation parameter value that makes the patient feel comfortable is set as the first ECAP signal waveform.

[0063] The at least one target sample may be a sample used for matching characteristic values ​​of an ECAP signal waveform. Each target sample includes ECAP signal information of a sample patient and a stimulation parameter adjustment function, wherein the stimulation parameter adjustment function is used to characterize the functional relationship between changes in the ECAP signal waveform and stimulation parameter increments. The ECAP signal information may be an ECAP signal waveform or characteristic values ​​extracted from the ECAP signal waveform.

[0064] Exemplarily, the process of adjusting the stimulation parameters based on the stimulation parameter adjustment function can be: the stimulation parameter adjustment function is f(ΔECAP), the stimulation parameter increment is Δx, the initial stimulation parameter is x1, and the adjusted stimulation parameter is x2, then f(ΔECAP)=Δx, x2=x1+Δx, where Δx can be a positive number or a negative number, and f can be a stimulation parameter adjustment function determined according to the stimulation parameter adjustment function of the sample patient in the target sample. Specifically, f can be a linear function, a multi-time function, or a multi-segment function.

[0065] In some embodiments, when a first ECAP signal from the patient's body to be stimulated is collected, the ECAP signal may be subject to noise interference. Therefore, the collected ECAP signal may be preprocessed. For example, the ECAP signal collected by the electrode may be amplified and then further processed using adaptive filtering to reduce noise in the ECAP signal. For example, the signal of the sound source may be detected and the signal of the noise source may be filtered out from the original ECAP signal using an adaptive filtering algorithm. Alternatively, the original ECAP signal may be subtracted from the signal of the noise source and the noise signal may be filtered out using a minimum mean square error algorithm or a recursive least squares algorithm to obtain a preprocessed ECAP signal.

[0066] In some embodiments, in order to facilitate subsequent further processing of the waveform of the ECAP signal, the preprocessed ECAP signal can be standardized. For example, the characteristic values ​​of the waveform of the first ECAP signal can be extracted based on a deep learning algorithm, wherein the characteristic values ​​of the waveform of the ECAP signal generally include a peak value P1, a peak value P2, and a valley value N1.

[0067] Taking into account that in actual applications, the amount of data compared with all the samples in the sample library is relatively large, and the stimulation parameter adjustment functions applicable to patients of the same type may be similar, therefore, in order to improve the efficiency of the overall determination of the stimulation parameter adjustment function and reduce the time cost, in the aforementioned S220, the category information of the patient to be stimulated can be obtained, and the category information of the sample body in the sample library can be matched according to the category information of the patient to be stimulated; at least one target sample in the sample library whose category information is the same as the category information of the patient to be stimulated is used as at least one target sample, and on this basis, the characteristic values ​​of the waveform of the ECAP signal are further matched, which greatly narrows the matching range and improves the efficiency of the overall adjustment of the stimulation parameter value.

[0068] In some embodiments, the category information of the patient's body to be stimulated may be the patient's age, height, weight, gender, and imaging data, such as spinal segment images, which is not specifically limited here.

[0069] In some embodiments, considering that the waveform of the ECAP signal can reflect the patient's perception of the stimulation to a certain extent, that is, whether it is comfortable, that is, if the waveforms of the ECAP signals are similar, the patient's perception of the stimulation is also similar. If there is no characteristic value of the waveform of the first ECAP signal in the target sample, the target sample with the smallest deviation between the characteristic value of the waveform of the ECAP signal and the characteristic value of the waveform of the first ECAP signal can be used as the initial sample, and adjustment can be started based on the stimulation parameter adjustment function in the initial sample to reduce the number of times the stimulation parameter adjustment function is adjusted and improve the efficiency of the overall adjustment of the stimulation parameter value.

[0070] In some embodiments, to improve the accuracy of stimulation parameter adjustment, the first stimulation parameter adjustment function (i.e., the initial stimulation parameter adjustment function) determined in S240 can be adjusted based on the trained stimulation parameter adjustment model. Exemplarily, the stimulation parameter adjustment model can be a machine learning model, such as a neural network model, a support vector machine model, a decision tree model, etc. This application does not limit the type of stimulation parameter adjustment model.

[0071] In some embodiments, ECAP signals and corresponding stimulation parameter adjustment functions from multiple treated patients can be collected to construct a sample library to provide data support for implementing the above method. The samples in the sample library can be further classified and labeled with category information. The sample library can be stored on the server 30 or in the cloud.

[0072] In some embodiments, a stimulation parameter adjustment model can be trained based on the ECAP signal of a treated patient, the corresponding stimulation parameter adjustment function, and the annotated category information for each sample in the sample library. Exemplarily, the trained stimulation parameter adjustment model can include a functional relationship between changes in the ECAP signal, i.e., ΔECAP, and changes in the patient's posture.

[0073] In some embodiments, the patient's updated treatment data can be updated to the sample library in real time, and the stimulation parameter adjustment model can be iteratively trained based on the samples in the updated sample library to optimize the trained stimulation parameter adjustment model to improve the generalization ability and accuracy of the stimulation parameter adjustment model.

[0074] According to the implantable electrical stimulation system provided in the embodiment of the present application, when the characteristic value of the waveform of the first ECAP signal of the patient to be stimulated in the first posture is not matched with a sample with the same characteristic value as the waveform of the first ECAP signal in the target sample selected from the sample library, the stimulation parameter adjustment function corresponding to the sample with the smallest deviation between the characteristic value of the ECAP signal waveform in the target sample and the characteristic value of the waveform of the first ECAP signal is used as the first stimulation parameter adjustment function to reduce the amount of matching data, and the first stimulation parameter adjustment function is further adjusted through the stimulation parameter adjustment model to obtain a stimulation parameter adjustment function suitable for the current patient, and the stimulation parameters are adaptively adjusted according to the stimulation parameter adjustment function, and a treatment pulse is sent to the patient based on the adjusted stimulation parameters, thereby improving the efficiency and accuracy of adjusting the stimulation parameter values ​​and further improving the stability of the electrical stimulation treatment effect.

[0075] In order to further illustrate the process of determining the stimulation parameter adjustment function and the process of adjusting the stimulation parameter value according to the corresponding stimulation parameter adjustment function, the present application also provides a method for adjusting the stimulation parameter value.

[0076] Figure 4 FIG. 1 is a flow chart of a method for adjusting stimulation parameter values ​​provided by an exemplary embodiment of the present application. In some embodiments, Figure 4 The illustrated method may be executed by the controller 21 .

[0077] like Figure 4 As shown, S230 may include the following sub-steps:

[0078] S231 : Select any one of the at least one target sample as a first target sample, and calculate a deviation between a characteristic value of the ECAP signal waveform in the first target sample and a characteristic value of the waveform of the first ECAP signal.

[0079] S232: Compare the deviation value with a preset threshold.

[0080] S233. When it is determined that the deviation value is not less than a preset threshold, select any sample other than the first target sample from at least one target sample as the second target sample, repeat the above steps, and stop repeating when all samples from at least one target sample have been selected, and determine that there is no sample in the target sample with the same characteristic value as the first ECAP waveform.

[0081] The first target sample may be one of the at least one target sample determined in the aforementioned S220 .

[0082] In some embodiments, based on the characteristic values ​​(peak value P1, peak value P2, and valley value N1) of the waveform of the first ECAP signal extracted above and the characteristic values ​​of the waveform of the ECAP signal of the first target sample, (P2-N1) can be calculated as the characteristic difference value, which can represent the ECAP signal to a certain extent. Further, the deviation value of the characteristic values ​​of the waveforms of the two ECAP signals is calculated based on the characteristic difference value. For example, the characteristic values ​​of the waveform of the first ECAP signal are (P1)1, (P2)1, and (N1)1, and the characteristic values ​​of the waveform of the ECAP signal of the first target sample are (P1)2, (P2)2, and (N1)2, then the characteristic difference value X1 of the waveform of the first ECAP signal is (P2)1-(N1)1, and correspondingly, the characteristic difference value X2 of the waveform of the ECAP signal of the first target sample is (P2)2-(N1)2, and the deviation value between the characteristic values ​​of the waveforms of the two ECAP signals is X2-X1.

[0083] In some embodiments, the waveform of a first ECAP signal of the patient to be stimulated in a first posture can be determined, and then, based on a deep learning algorithm, characteristic values ​​of the waveform of the first ECAP signal can be extracted. Exemplarily, the deep learning algorithm can be a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), etc. This application does not specifically limit the type of deep learning algorithm.

[0084] The preset threshold can be used as a benchmark for determining whether the waveform features of two ECAP signals are identical. In some embodiments, when the characteristic difference between the waveform features of the two ECAP signals is less than the preset threshold, the waveform features of the two ECAP signals are determined to be identical; otherwise, the waveform features of the two ECAP signals are determined to be different. In other words, the preset threshold can be understood as a tolerance, which defines the allowable error range of the ECAP signal waveforms.

[0085] In some embodiments, the method for determining the preset threshold value may be: based on the range of stimulation changes that the patient can receive, determine the difference in the characteristic waveform of the ECAP signal corresponding to the stimulation change, and further determine the preset threshold value based on the difference. For example, if the difference in the characteristic waveform of the ECAP signal corresponding to the stimulation change that the patient can receive is 5, the tolerance range of the preset threshold value can be pre-set in the system to ±20% of the characteristic difference, that is, 4 to 6, and the corresponding tolerance range of the voltage of the stimulation pulse is also ±20%. If the deviation value obtained in the aforementioned S231 is not within the preset threshold range, that is, the error range, it is determined that the characteristic value of the ECAP signal waveform in the first target sample is different from the characteristic value of the waveform of the first ECAP signal, and S233 is executed; if the deviation value obtained in the aforementioned S231 is within the preset threshold range, it is determined that the characteristic value of the ECAP signal waveform in the first target sample is the same as the characteristic value of the waveform of the first ECAP signal.

[0086] Figure 5 FIG. 1 is a flow chart of another method for intelligently regulating implantable electrical stimulation provided by an exemplary embodiment of the present application. In some embodiments, Figure 5 The illustrated method may be executed by the controller 21 . Figure 5 yes Figure 3 Example of the method.

[0087] like Figure 5 As shown, before the above S230, the method may further include the following steps:

[0088] S310 : Match at least one target sample according to a characteristic value of the waveform of the first ECAP signal, and determine whether there is a sample in the at least one target sample having the same characteristic value as the waveform of the first ECAP signal.

[0089] S320 , selecting the stimulation parameter adjustment function of the sample having the smallest deviation between the characteristic value of the ECAP signal waveform and the characteristic value of the first ECAP signal waveform among the samples having the same characteristic value as the waveform of the first ECAP signal in at least one target sample as the target stimulation parameter adjustment function.

[0090] S330 , adjusting the stimulation parameter value based on the target stimulation parameter adjustment function.

[0091] S340: Send stimulation to the patient's body based on the adjusted stimulation parameter value.

[0092] Taking into account that in actual applications, after executing S232, there may be multiple samples in the target sample that are smaller than the preset threshold, that is, multiple samples in the target sample are judged to be the same as the characteristic value of the first ECAP waveform. In this application, the stimulation parameter adjustment function of the sample with the smallest deviation between the characteristic value of the ECAP signal waveform in the sample with the same characteristic value as the waveform of the first ECAP signal in the target sample and the characteristic value of the first ECAP signal waveform is used as the target stimulation parameter adjustment function to adjust the stimulation parameters.

[0093] In another embodiment of the present invention, in S310, S231 and S232 can be executed to compare the deviation value of the characteristic value of the waveform of the first ECAP signal with a preset threshold. Unlike the aforementioned S233, in this embodiment, the deviation value is less than the preset threshold, and it is determined that there is a sample in the target sample with the same characteristic value as the first ECAP waveform.

[0094] It should be understood that the specific working process and functions in the above embodiments can refer to the above Figure 4 To avoid repetition, the relevant descriptions of the method for adjusting the stimulation parameter value provided in the embodiment will not be repeated here.

[0095] In order to further confirm whether the corresponding stimulation parameter adjustment function determined by the above method is suitable for the current patient, it is necessary to further verify the determined corresponding stimulation parameter adjustment function. Figure 6 It is a flowchart of a stimulation parameter adjustment function verification method provided by an exemplary embodiment of the present application.

[0096] like Figure 6 As shown, after S270, the method may further include the following steps:

[0097] S410 . When the patient's posture changes to a second posture, adjust the first stimulation parameter value according to a second stimulation parameter adjustment function to obtain a second stimulation parameter value.

[0098] S420: Determine, based on the patient's feedback, whether the stimulation pulse based on the second stimulation parameter value makes the patient feel comfortable. If so, execute S430; otherwise, execute S460.

[0099] S430: When the patient's posture continues to change to the third posture, adjust the second stimulation parameter according to the second stimulation parameter adjustment function to obtain a third stimulation parameter value.

[0100] S440: Based on the patient's feedback, determine whether the stimulation pulse based on the third stimulation parameter value makes the patient feel comfortable. If yes, execute S450; otherwise, execute S460.

[0101] S450: Adjust the stimulation parameter value based on the second stimulation parameter adjustment function.

[0102] S460 , adjusting the currently determined stimulation parameter adjustment function through the trained adjustment model to obtain an adjusted stimulation parameter adjustment function.

[0103] S470: Based on the patient's feedback, confirm whether the stimulation pulse based on the adjusted stimulation parameter value makes the patient feel comfortable. If so, execute S480; otherwise, execute S460.

[0104] S480 , adjusting the current stimulation parameter value based on the adjusted stimulation parameter adjustment function.

[0105] The second posture may be a posture of the patient transformed based on the first posture, and the third posture may be a posture transformed based on the second posture.

[0106] Taking into account that there may be multiple postures of the patient, that is, there may be multiple possibilities for the angle between the patient's body and the horizontal direction, in some embodiments, in order to provide stimulation parameter values ​​that are more suitable for the patient, the postures of some key points can be selected to verify the stimulation parameter adjustment function. Exemplarily, the postures at two key points can be selected to verify the stimulation parameter adjustment function. For example, the postures at 90° and 180° to the horizontal direction are respectively selected as the second posture and the third posture to verify the stimulation parameter adjustment function. The postures at five key points can also be selected to verify the stimulation parameter adjustment function, and the number of key points selected is not specifically limited here.

[0107] In some embodiments, after the patient changes to different postures for verification, the finalized patient-related data and ECAP waveform information and stimulation parameter adjustment function can be uploaded to the sample library to expand the sample library.

[0108] Considering that the degree of stimulation a patient experiences in response to the same therapeutic pulse may vary over time, the stimulation parameter adjustment function determined based on the above method may no longer be applicable to the current patient over time and may require further adjustment. In some embodiments, when the patient provides feedback that the current stimulation pulse causes discomfort, the stimulation parameter adjustment function is adaptively updated using a trained stimulation parameter adjustment model, and the stimulation parameter values ​​are adjusted based on the updated stimulation parameter adjustment function, thereby forming a closed-loop control and achieving adaptive adjustment of the stimulation parameter values.

[0109] In some embodiments, in order to make the sample data in the sample library accurate, the updated stimulation parameter adjustment function, the corresponding ECAP signal waveform information and the patient category information are uploaded to the sample library as new samples in the sample library to update the sample library.

[0110] Figure 7 This is a schematic diagram of the system modules of an implantable electrical stimulation device shown in some embodiments of the present application.

[0111] like Figure 7 As shown, the implantable electrical stimulation device 500 may include an acquisition module 510 , a determination module 520 , a matching module 530 , a selection module 540 , an adjustment module 550 and a stimulation module 560 .

[0112] The acquisition module 510 may be configured to acquire characteristic values ​​of a waveform of a first ECAP signal of a body of a patient to be stimulated in a first posture.

[0113] The determination module 520 can be used to determine at least one target sample in the sample library, each target sample includes the waveform information of the ECAP signal of the sample patient and a stimulation parameter adjustment function, and the stimulation parameter adjustment function is used to characterize the functional relationship between the change in the waveform of the ECAP signal and the stimulation parameter increment.

[0114] The matching module 530 may be configured to match the characteristic value of the waveform of the first ECAP signal with at least one target sample, and determine that no sample having the same characteristic value as the waveform of the first ECAP signal exists in the at least one target sample.

[0115] The selection module 540 may be configured to use the stimulation parameter adjustment function corresponding to the sample having the smallest deviation between the characteristic value of the ECAP signal waveform and the characteristic value of the first ECAP signal waveform in at least one target sample as the first stimulation parameter adjustment function.

[0116] The adjustment module 550 can be used to adjust the first stimulation parameter adjustment function through the trained stimulation parameter adjustment model to obtain the second stimulation parameter adjustment function, and adjust the stimulation parameter value based on the second stimulation parameter adjustment function to obtain the adjusted stimulation parameter value.

[0117] The stimulation module 560 may be configured to send stimulation to the patient's body based on the adjusted stimulation parameter values.

[0118] In some embodiments, the acquisition module can be used to obtain category information of the body of the patient to be stimulated. For example, the category information can be the patient's age, height, weight, gender, and imaging data, such as spinal segment images, which is not specifically limited here.

[0119] In some embodiments, the matching module 530 is also used to match the category information of the patient to be stimulated with the category information of the sample body in the sample library; at least one target sample in the sample library whose category information is the same as the category information of the patient to be stimulated is used as at least one target sample, and on this basis, the characteristic values ​​of the waveform of the ECAP signal are further matched, which greatly narrows the matching range and improves the efficiency of the overall adjustment of the stimulation parameter value.

[0120] In some embodiments, the matching module 530 can also be used to match at least one target sample based on the characteristic value of the waveform of the first ECAP signal, and determine whether there is a sample with the same characteristic value as the waveform of the first ECAP signal in the at least one target sample. Accordingly, the selection module 540 is also used to select the stimulation parameter adjustment function of the sample with the smallest deviation between the characteristic value of the ECAP signal waveform and the characteristic value of the first ECAP signal waveform among the samples with the same characteristic value as the waveform of the first ECAP signal in the at least one target sample as the target stimulation parameter adjustment function. The adjustment module 550 is used to adjust the stimulation parameter value based on the target stimulation parameter adjustment function. The stimulation module 560 can also be used to emit the stimulation parameter value to the patient's body based on the adjusted stimulation parameter value.

[0121] In some embodiments, the selection module 540 can be used to select any one of at least one target sample as the first target sample, calculate the deviation value between the characteristic value of the ECAP signal waveform in the first target sample and the characteristic value of the waveform of the first ECAP signal; compare the deviation value with a preset threshold; and when the deviation value is less than the preset threshold, determine that there is a sample in the target sample with the same characteristic value as the first ECAP waveform.

[0122] In some embodiments, the selection module 540 can also be used to select any sample from at least one target sample as a first target sample, calculate the deviation value between the characteristic value of the ECAP signal waveform in the first target sample and the characteristic value of the waveform of the first ECAP signal; compare the deviation value with a preset threshold; when it is judged that the deviation value is not less than the preset threshold, select any sample from at least one target sample except the first target sample as a second target sample, repeat the above steps, and stop repeating when all samples in at least one target sample have been selected, and determine that there is no sample in the target sample with the same characteristic value as the first ECAP waveform.

[0123] In some embodiments, the intelligently adjustable implantable electrical stimulation device may further include a verification module, which is used to adjust the first stimulation parameter value according to the second stimulation parameter adjustment function to obtain the second stimulation parameter value when the patient's posture changes to the second posture, wherein the first stimulation parameter value is the stimulation parameter value corresponding to the patient's first ECAP signal; based on the patient's feedback, confirm whether the stimulation pulse based on the second stimulation parameter value makes the patient feel comfortable; if not, adjust the currently determined stimulation parameter adjustment function through the trained adjustment model to obtain the adjusted stimulation parameter adjustment function, adjust the second stimulation parameter value based on the adjusted stimulation parameter adjustment function, and repeat the above steps until the patient feedbacks that the stimulation pulse based on the adjusted stimulation parameter value feels comfortable.

[0124] In some embodiments, the verification module is also used to adjust the second stimulation parameter according to the second stimulation parameter adjustment function to obtain a third stimulation parameter value when the patient's posture continues to change to a third posture; based on the patient's feedback, confirm whether the stimulation pulse corresponding to the third stimulation parameter value makes the patient feel comfortable; if so, determine to use the second stimulation parameter adjustment function to adjust the stimulation parameter value when the patient's posture changes.

[0125] In some embodiments, the intelligently adjustable implantable electrical stimulation device may further include an update module. When the patient feedbacks that the current stimulation pulse makes him feel uncomfortable, the update module is used to automatically update the stimulation parameter adjustment function through the trained stimulation parameter adjustment model; based on the updated stimulation parameter adjustment function, the stimulation parameter value is adjusted; based on the patient's feedback, whether the stimulation pulse corresponding to the adjusted stimulation parameter value makes the patient feel comfortable; if not, repeat the above steps until the patient feedbacks that the current stimulation pulse makes him feel comfortable.

[0126] In some embodiments, the update module can also be used to upload the updated stimulation parameter adjustment function, the corresponding ECAP signal waveform information and the patient category information to the sample library as a new sample in the sample library; and update the sample library based on the new sample.

[0127] It should be understood that the specific working processes and functions of the acquisition module 510, determination module 520, matching module 530, selection module 540, adjustment module 550, stimulation module 560, verification module and update module in the above embodiment can refer to the above Figures 3 to 5 To avoid repetition, the description of the method for intelligently regulating implantable electrical stimulation provided in the embodiment will not be repeated here.

[0128] Figure 8An implantable electrical stimulation device 600 provided in one embodiment of the present application includes: a processor 610, and a storage medium 620, wherein the storage medium 620 stores a program, which, when executed by the processor 610, enables the processor 610 to execute the intelligent adjustment implantable electrical stimulation method provided in the above embodiment.

[0129] An embodiment of the present disclosure further provides a storage medium storing a program, which, when executed by a processor, causes the processor to execute the intelligent adjustment implantable electrical stimulation method provided by the above embodiment.

[0130] It should be understood that the term “including” and its variations used in the present disclosure are open inclusions, that is, “including but not limited to.” The term “one embodiment” means “at least one embodiment,” and the term “another embodiment” means “at least one additional embodiment.”

[0131] It should be noted that the various specific technical features (elements) described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0132] Those skilled in the art will appreciate that the units or modules of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0133] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems and devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units or modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or modules 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, and the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0134] In addition, each functional unit or module in each embodiment of the present disclosure may be integrated into one processing unit or module, or each unit or module may exist physically separately, or two or more units or modules may be integrated into one unit or module.

[0135] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A device for intelligently regulating implantable electrical stimulation, characterized in that: include: Controller, a stimulation circuit configured to generate pulses and output the pulses through electrode leads; A switch circuit, connected between the controller and the electrode lead, configured to connect the electrode contact to the stimulation circuit and output pulses through the electrode contact under the control of the controller; The acquisition circuit is electrically connected to the controller and is configured to receive an evoked compound action potential (ECAP) signal generated by the pulse emitted by the stimulation circuit to stimulate the body after the controller controls the stimulation circuit and the acquisition circuit to be connected to the electrode contact. Wherein, the controller is configured to perform the following steps: Acquire a characteristic value of a waveform of a first ECAP signal of a body of a patient to be stimulated in a first posture; Determine at least one target sample in the sample library, each target sample includes waveform information of an ECAP signal of a sample patient and a stimulation parameter adjustment function, wherein the stimulation parameter adjustment function is used to characterize a functional relationship between a change in the waveform and an increment of a stimulation parameter; Matching the at least one target sample according to the characteristic value of the waveform of the first ECAP signal, and determining that there is no sample in the at least one target sample having the same characteristic value as the waveform of the first ECAP signal; taking the stimulation parameter adjustment function corresponding to the sample having the smallest deviation between the characteristic value of the ECAP signal waveform in the at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function; Adjust the first stimulation parameter adjustment function by using the trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function; adjusting the stimulation parameter value based on the second stimulation parameter adjustment function to obtain an adjusted stimulation parameter value; The adjusted stimulation parameter value is sent to the body of the patient to be stimulated through the stimulation circuit.

2. The device for intelligently regulating implantable electrical stimulation according to claim 1, characterized in that: The determining at least one target sample in the sample library comprises: Acquiring the body type information of the patient to be stimulated; Matching the category information of the body of the patient to be stimulated with the category information of the sample body in the sample library; At least one target sample in the sample library whose category information is the same as the category information of the body of the patient to be stimulated is used as the at least one target sample.

3. The device for intelligently regulating implantable electrical stimulation according to claim 1, characterized in that: The controller is also configured to: Matching the at least one target sample according to the characteristic value of the waveform of the first ECAP signal, and determining that there is a sample in the at least one target sample having the same characteristic value as the waveform of the first ECAP signal; Selecting the stimulation parameter adjustment function of the sample having the smallest deviation between the characteristic value of the ECAP signal waveform and the characteristic value of the first ECAP signal waveform among the samples having the same characteristic value as the waveform of the first ECAP signal in the at least one target sample as the target stimulation parameter adjustment function; adjusting the stimulation parameter value based on the target stimulation parameter adjustment function; The adjusted stimulation parameter values ​​are emitted to the patient's body.

4. The device for intelligently regulating implantable electrical stimulation according to claim 3, wherein: The matching, according to the characteristic value of the waveform of the first ECAP signal, with the at least one target sample to determine whether there is a sample in the at least one target sample having the same characteristic value as the waveform of the first ECAP signal, comprises: Selecting any one of the at least one target sample as a first target sample, and calculating a deviation value between a characteristic value of an ECAP signal waveform in the first target sample and a characteristic value of a waveform of the first ECAP signal; comparing the deviation value with a preset threshold; When the deviation value is less than a preset threshold, it is determined that there is a sample having the same characteristic value as the first ECAP waveform in the target samples.

5. The device for intelligently regulating implantable electrical stimulation according to claim 1, characterized in that: The matching, according to the characteristic value of the waveform of the first ECAP signal, with the at least one target sample to determine that no sample having the same characteristic value as the waveform of the first ECAP signal exists in the at least one target sample, comprises: Selecting any one of the at least one target sample as a first target sample, and calculating a deviation value between a characteristic value of an ECAP signal waveform in the first target sample and a characteristic value of a waveform of the first ECAP signal; Comparing the deviation value with the preset threshold value; When it is determined that the deviation value is not less than the preset threshold, any sample except the first target sample in the at least one target sample is selected as the second target sample, and the above steps are repeated. When all samples in the at least one target sample have been selected, the above steps are stopped and it is determined that there is no sample in the target sample with the same characteristic value as the first ECAP waveform.

6. The device for intelligently regulating implantable electrical stimulation according to claim 1, characterized in that: The controller is also configured to: When the patient's posture changes to a second posture, adjusting the first stimulation parameter value according to a second stimulation parameter adjustment function to obtain a second stimulation parameter value, wherein the first stimulation parameter value is a stimulation parameter value corresponding to the first ECAP signal of the patient; confirming, based on feedback from the patient, whether the stimulation pulse based on the second stimulation parameter value makes the patient feel comfortable; If not, adjusting the currently determined stimulation parameter adjustment function by using the trained adjustment model to obtain an adjusted stimulation parameter adjustment function; According to the patient's feedback, confirm whether the stimulation pulse based on the adjusted stimulation parameter value makes the patient feel comfortable; If not, repeatedly adjust the currently determined stimulation parameter adjustment function through the trained adjustment model until the patient feedbacks that the stimulation pulse based on the adjusted stimulation parameter value feels comfortable, and adjust the current stimulation parameter value based on the adjusted stimulation parameter adjustment function.

7. The device for intelligently regulating implantable electrical stimulation according to claim 6, characterized in that: After confirming, based on the patient's feedback, whether the stimulation pulse based on the second stimulation parameter value makes the patient feel comfortable, the controller is further configured to: If yes, when the patient's posture continues to change to a third posture, adjusting the second stimulation parameter according to a second stimulation parameter adjustment function to obtain a third stimulation parameter value; confirming, according to the patient's feedback, whether the stimulation pulse corresponding to the third stimulation parameter value makes the patient feel comfortable; If so, determining to use a second stimulation parameter adjustment function to adjust the stimulation parameter value when the patient's posture changes; If not, repeatedly adjust the currently determined stimulation parameter adjustment function through the trained adjustment model until the patient feedbacks that the stimulation pulse based on the adjusted stimulation parameter value feels comfortable, and adjust the current stimulation parameter value based on the adjusted stimulation parameter adjustment function.

8. The device for intelligently regulating implantable electrical stimulation according to claim 7, characterized in that: The controller is also configured to: When the patient to be stimulated feedbacks that the current stimulation pulse makes him feel uncomfortable, the stimulation parameter adjustment function is automatically updated by the trained stimulation parameter adjustment model; adjusting the stimulation parameter value based on the updated stimulation parameter adjustment function; According to the feedback of the patient to be stimulated, confirm whether the stimulation pulse corresponding to the adjusted stimulation parameter value makes the patient feel comfortable; If not, repeat the above steps until the patient to be stimulated provides feedback on the current stimulation pulse that makes him feel comfortable.

9. The device for intelligently regulating implantable electrical stimulation according to claim 8, characterized in that: The controller is also configured to: Uploading the updated stimulation parameter adjustment function, the corresponding waveform information of the ECAP signal and the category information of the patient to be stimulated to the sample library as a new sample in the sample library; Based on the new sample, the sample library is updated.

10. The device for intelligently regulating implantable electrical stimulation according to claim 1, characterized in that: The step of obtaining the characteristic value of the waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture comprises: determining a waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture; Based on a deep learning algorithm, characteristic values ​​of the waveform of the first ECAP signal are extracted.

11. The device for intelligently regulating implantable electrical stimulation according to claim 9, characterized in that: The step of determining the waveform of the first ECAP signal of the body of the patient to be stimulated in the first posture comprises: Sending a pulse to the body of the patient to be stimulated based on the initial stimulation parameter value, and sending an induced pulse to the body of the patient to be stimulated, wherein the induced pulse is used to induce the body of the patient to be stimulated to emit an ECAP signal corresponding to the initial stimulation parameter value; judging whether the initial stimulation parameter value makes the patient to be stimulated feel comfortable according to the feedback of the body of the patient to be stimulated; If so, determining that the waveform of the ECAP signal corresponding to the initial stimulation parameter value is the first ECAP signal waveform; If not, adjust the initial stimulation parameter value and repeat the above steps.

12. The device for intelligently regulating implantable electrical stimulation according to claim 1, characterized in that: The controller is also configured to: Collecting ECAP signals and corresponding stimulation parameter adjustment functions of a plurality of treated patients to construct the sample library; Classifying the samples in the sample library and marking the category information of the samples in the sample library; The stimulation parameter adjustment model is trained based on the ECAP signal of the treated patient in each sample in the sample library, the corresponding stimulation parameter adjustment function and the annotated category information.

13. A method for intelligently regulating implantable electrical stimulation, characterized in that: include: Acquire a characteristic value of a waveform of a first ECAP signal of a body of a patient to be stimulated in a first posture; Determine at least one target sample in the sample library, each target sample includes waveform information of an ECAP signal of a sample patient and a stimulation parameter adjustment function, wherein the stimulation parameter adjustment function is used to characterize a functional relationship between a change in the waveform of the ECAP signal and an increment of the stimulation parameter; Matching the at least one target sample according to the characteristic value of the waveform of the first ECAP signal, and determining that there is no sample in the at least one target sample having the same characteristic value as the waveform of the first ECAP signal; taking the stimulation parameter adjustment function corresponding to the sample having the smallest deviation between the characteristic value of the ECAP signal waveform in the at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function; Adjust the first stimulation parameter adjustment function by using the trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function; adjusting the stimulation parameter value based on the second stimulation parameter adjustment function to obtain an adjusted stimulation parameter value; A pulse is emitted to the body of the patient to be stimulated based on the adjusted stimulation parameter value.

14. A device for intelligently regulating implantable electrical stimulation, comprising: An acquisition module, used for acquiring a characteristic value of a waveform of a first ECAP signal of a body of a patient to be stimulated in a first posture; A determination module, used to determine at least one target sample in the sample library, each target sample including waveform information of an ECAP signal of a sample patient and a stimulation parameter adjustment function, wherein the stimulation parameter adjustment function is used to characterize a functional relationship between a change in the waveform of the ECAP signal and an increment of the stimulation parameter; a matching module, configured to match the at least one target sample according to a characteristic value of the waveform of the first ECAP signal, and determine that no sample having the same characteristic value as the waveform of the first ECAP signal exists in the at least one target sample; A selection module, configured to use the stimulation parameter adjustment function corresponding to the sample having the smallest deviation between the characteristic value of the ECAP signal waveform in the at least one target sample and the characteristic value of the waveform of the first ECAP signal as the first stimulation parameter adjustment function; an adjustment module, configured to adjust the first stimulation parameter adjustment function through the trained stimulation parameter adjustment model to obtain a second stimulation parameter adjustment function, and adjust the stimulation parameter value based on the second stimulation parameter adjustment function to obtain an adjusted stimulation parameter value; A stimulation module is used to send pulses to the body of the patient to be stimulated based on the adjusted stimulation parameter value.

Images