Sacral nerve stimulation control model construction method, sacral nerve stimulation control model adaptive control method, medium and equipment

Abstract

The invention provides a sacral nerve stimulation control model construction method, a sacral nerve stimulation control model self-adaptive control method, a medium and equipment, and relates to the technical field of biological signal analysis and medical instruments.The method comprises the steps that electrical stimulation testing is conducted on multiple tested patients in different postures, and sacral evoked response signals of the tested patients under each stimulation condition are collected; selecting data in the sacral evoked response signal within a set time period after the electrical stimulation is finished as an effective signal; preprocessing the effective signal to remove power frequency noise and stimulus artifacts; extracting feature data from the processed signal; and according to the feature data obtained by all the electrical stimulation test samples and the stimulation amplitude of the corresponding electrical stimulation, establishing a corresponding relation model between the feature data of the sacral evoked response and the stimulation amplitude. The method can cope with the influence of various factors such as electrode change and patient state change, the stimulation effect is improved, the number of doctor seeing times of the patient is reduced, and the convenience and effectiveness of treatment are improved.

Description

Technical Field

[0001] The present invention relates to the field of biological signal analysis and medical device technology, and in particular to a sacral nerve stimulation control model construction, an adaptive control method, a medium and a device. Background Art

[0002] Sacral neuromodulation (SNM) is an effective treatment for overactive bladder (OAB), nonobstructive urinary retention (NOUR) and fecal incontinence (FI). Currently, doctors usually choose appropriate stimulation parameters based on the patient's motor response or the patient's subjective feedback.

[0003] However, the same patient may feel different stimulation in different postures, so setting stimulation parameters based solely on the visual-motor response at the time of implantation or the fixed posture at the time may not meet the patient's needs in real life. In addition, after implantation, doctors cannot adjust stimulation parameters in real time based on the patient's perceptual feedback, making existing treatment options lack flexibility and personalized regulation. Therefore, how to achieve adaptive stimulation control and adjust stimulation parameters in real time based on the patient's physical condition has become a bottleneck problem currently facing sacral neuromodulation technology.

[0004] At present, the parameter settings of sacral nerve stimulation are usually adjusted by doctors according to the sensory threshold felt by the patient during the implantation process, and a fixed stimulation amplitude is generally used. However, as the implantation time goes by, hyperplasia reactions or electrode offset problems may occur around the implanted electrodes, and changes in the patient's posture will also lead to different reactions under the same stimulation amplitude (overstimulation or understimulation). These factors mean that fixed-amplitude stimulation schemes may not always meet the actual needs of patients. In addition, when the stimulation effect is not ideal, patients usually need to go to the hospital and have the doctor manually adjust the stimulation parameters, which not only wastes time but also increases the burden on patients. Summary of the invention

[0005] The purpose of the present invention is to provide a sacral nerve stimulation control model construction, adaptive control method, medium and equipment, aiming to automatically optimize the stimulation amplitude according to real-time feedback, realize adaptive dynamic adjustment of the stimulation amplitude, so as to cope with the influence of various factors such as electrode changes and patient status changes, thereby improving the stimulation effect, reducing the number of patient visits, and improving the convenience and effectiveness of treatment. The specific technical solution is as follows: A method for constructing a sacral nerve stimulation control model, the method comprising the following steps: S100, data collection: performing electrical stimulation tests on multiple test patients in different postures, and collecting sacral evoked response signals of the test patients under each stimulation condition; S200, data clipping: selecting data in a set time period after the end of electrical stimulation in the sacral evoked response signal as a valid signal; S300, data preprocessing: preprocessing the effective signal to remove power frequency noise and stimulation artifacts; S400, feature extraction: extracting feature data from the processed signal; S500, modeling: establishing a corresponding relationship model between the characteristic data of sacral evoked response and the stimulation amplitude according to the characteristic data obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude.

[0006] Furthermore, in step S100, the number of the tested patients is more than 15, the postures of the tested patients include lying down, standing and sitting still, and the stimulation amplitude includes the motor threshold, the sensory threshold and the maximum tolerance threshold.

[0007] Further, in step S200, the sacral evoked response signal after the electrical stimulation is selected Time to The data between the times is taken as the effective signal, and the calculation formula of the effective signal is as follows:

[0008] in, is a valid signal, is the end time of electrical stimulation, is the sampling rate.

[0009] Furthermore, in step S300, a notch filter is used to filter out the power frequency noise, and the calculation formula is as follows:

[0010] in, is the filtered signal, is the filter function.

[0011] Removing the stimulation artifact includes the following steps: using an exponential function to fit the stimulation artifact, the exponential function fitting model is:

[0012] in, is the initial amplitude, indicating the strength of the artifact signal; is the time constant, controlling how quickly the signal decays; is a constant that represents the baseline or offset of the signal; Solution Error The minimum value of , , ,error The calculation formula is as follows:

[0013] in, is the sampling time point; According to the best , , Calculate the artifact signal , from the filtered signal Subtract artifact signal Get the processed signal , in order to eliminate the influence of artifacts, the processed signal The calculation formula is as follows: .

[0014] Furthermore, in step S400, the characteristic data includes peak-to-peak value, latency and number of peaks, the peak-to-peak value is the difference between the maximum positive peak and the maximum negative peak in the processed signal, the latency is the delay of the occurrence time of the maximum peak in the processed signal relative to the starting point of the effective signal, and the number of peaks is the total number of peaks and troughs in the processed signal.

[0015] Furthermore, in step S500, the three extracted feature data are combined into a feature vector X1=(peak-to-peak value, latency, number of peaks), and then the feature vector is standardized to obtain an input feature vector X; for the input feature vector X obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude Y, a linear regression model is used to establish a corresponding relationship model between the feature data of the sacral evoked response and the stimulation amplitude, and the linear regression model calculation formula is as follows:

[0016] in, is the slope, is the intercept; determined by the least squares method and , the formula is as follows:

[0017] in, The serial number is i The input feature vector of the electrical stimulation test sample, The serial number is i The stimulation amplitude of the electrical stimulation test sample, is the average value of the input feature vectors of all electrical stimulation test samples, is the average value of the stimulation amplitude of all electrical stimulation test samples, n The number of samples tested for electrical stimulation.

[0018] The present invention also provides a sacral nerve stimulation adaptive control method, the method comprising the following steps: S1000, data acquisition: real-time acquisition of sacral evoked response signals under electrical stimulation of the patient; S2000, data clipping: selecting data in a set time period after the end of electrical stimulation in the sacral evoked response signal as a valid signal; S3000, data preprocessing: preprocess the effective signal to remove power frequency noise and stimulation artifacts; S4000, feature extraction: extracting feature data from the processed signal; S5000, model prediction: input the extracted feature data into the corresponding relationship model obtained by the sacral nerve stimulation control model construction method as described above to calculate the predicted stimulation amplitude ; S6000, Stimulation Amplitude Adjustment: Compare predicted stimulation amplitudes The actual stimulation amplitude of the electrical stimulation ,if , then reduce the stimulus amplitude; if , then increase the stimulus amplitude; if , the stimulus amplitude remains unchanged.

[0019] Furthermore, in step S6000, the stimulation amplitude is adjusted using the following linear modification formula:

[0020] in, is the adjusted stimulus amplitude, To adjust the step size, is the error value.

[0021] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the sacral nerve stimulation adaptive control method as described above are implemented.

[0022] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned sacral nerve stimulation adaptive control method when executing the program.

[0023] The invention provides a sacral nerve stimulation control model construction, adaptive control method, medium and device, which have the following beneficial effects: The embodiment of the present invention only needs one sacral nerve electrode to collect sacral evoked responses of different stimulation thresholds under different patient postures, and construct a corresponding relationship model between sacral evoked responses and stimulation amplitudes, so that the current stimulation amplitude can be predicted according to the patient's real-time sacral evoked response, and the actual stimulation intensity can be dynamically adjusted to determine whether it meets the requirements, and the treatment effect under the patient's posture state and electrode changes can be applied. At the same time, patients do not need to go back and forth to the hospital many times, reducing the number of visits for patients and improving the convenience and effectiveness of treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a schematic diagram of sacral evoked responses; Figure 2 is a flow chart of a method for constructing a sacral nerve stimulation control model provided by an embodiment of the present invention; Figure 3 It is a schematic diagram showing the meaning of feature data; Figure 4 is a flow chart of a sacral nerve stimulation adaptive control method provided by an embodiment of the present invention; Figure 5 It is a structural block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the accompanying drawings provided by the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. According to the following description, the advantages and features of the present invention will be more clear. It should be noted that the accompanying drawings are all in a very simplified form and are not in precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.

[0026] At present, the parameter settings of sacral nerve stimulation are usually adjusted by doctors according to the sensory threshold felt by the patient during the implantation process, and a fixed stimulation amplitude is generally used. However, as the implantation time goes by, hyperplasia reactions or electrode offset problems may occur around the implanted electrodes, and changes in the patient's posture will also lead to different responses under the same stimulation amplitude (overstimulation or understimulation). These factors mean that fixed-amplitude stimulation schemes may not always meet the actual needs of patients. In addition, when the stimulation effect is not ideal, patients usually need to go to the hospital and have the doctor manually adjust the stimulation parameters, which not only wastes time but also increases the burden on patients. Therefore, how to achieve adaptive dynamic adjustment of the stimulation amplitude to cope with multiple factors such as electrode changes and patient status changes has become an urgent problem to be solved. The dynamic adjustment mechanism can automatically optimize the stimulation amplitude based on real-time feedback, thereby improving the stimulation effect, reducing the number of patient visits, and improving the convenience and effectiveness of treatment.

[0027] In order to solve this problem, the present invention proposes a new adaptive control method, which is mainly to adaptively adjust the stimulation amplitude of sacral nerve stimulation by measuring sacral evoked responses (SERs) generated by sacral nerve stimulation.

[0028] Sacral evoked responses refer to the electrophysiological responses recorded from the S3 nerve after stimulation, such as Figure 1 As shown. It mainly includes the following two types of electrophysiological responses: (1) Neural Responses: Evoked Compound Action Potentials (ECAPs), which are electrical signals recorded from near the electrode when the nerve fiber is stimulated. (2) Myoelectric Responses: Electrical signals generated by muscle activation, usually muscle contraction caused by nerve stimulation.

[0029] This method is mainly divided into a construction phase and a use phase. The construction phase refers to the process of surgical implantation and the observation period after implantation. In the construction phase, a large number of patients' sacral evoked response signals are collected, and the model is obtained through processing and analysis. The use phase refers to the use of the model obtained in the construction phase after implantation is completed, and the real-time collected sacral evoked response signals are analyzed and predicted for the stimulation amplitude, and compared with the initially set stimulation amplitude, so as to adaptively adjust the stimulation parameters and achieve the effect of adaptive control.

[0030] Example 1: This example provides a method for constructing a sacral nerve stimulation control model. Figure 2 As shown, the method comprises the following steps: S100, data collection: performing electrical stimulation tests on multiple test patients in different postures, and collecting sacral evoked response signals of the test patients under each stimulation condition.

[0031] During the electrical stimulation test, the sacral nerve electrode is implanted into the third sacral foramen (S3) of the sacrum. The implanted sacral nerve electrode is generally 4-channel, and both have the functions of stimulation and acquisition. Generally, two channels are used for current stimulation, and two channels are used for data acquisition. Electrical stimulation will cause the activation of the sacral nerve and the corresponding muscles, and there will be electrical signals, which are collected. After the sacral nerve electrode is implanted into the S3 sacral foramen, two of the four channels are set to stimulation mode, and then electrical stimulation can be applied. The commonly used stimulation frequency is 14Hz, and the range can be set to 5HZ-20HZ; the stimulation current can be increased from 0.5mA in increments of 0.1mA, but it cannot exceed the maximum tolerance threshold; the pulse width is generally set to 210us; repeated stimulation is required during the model construction phase to ensure that the test time is more than 10s.

[0032] Specifically, a large number of patients in different postures (such as lying down, standing and sitting) are collected and electrical stimulation tests are performed on the patients. The number of patients tested is more than 15. The stimulation amplitude is divided into the following three types: (1) Motor threshold: The minimum current intensity at which the stimulus amplitude first causes muscle movement. Generally, during the implantation procedure, the muscle contraction threshold is recorded, which is the motor threshold.

[0033] (2) Sensory threshold: The threshold at which the patient first perceives the electrical stimulation. The current intensity is adjusted based on patient feedback.

[0034] (3) Maximum tolerance threshold: The highest current intensity at which the patient can feel the stimulation without feeling discomfort. The stimulation intensity is adjusted based on patient feedback.

[0035] Under each stimulation condition, the corresponding sacral evoked response signal recorded and collected is ,in Represents a point in time.

[0036] S200, data clipping: selecting data in a set time period after the end of electrical stimulation in the sacral evoked response signal as a valid signal.

[0037] In one embodiment, the sacral evoked response signal after the electrical stimulation is selected Time to The data between the two moments are taken as valid signals for subsequent analysis. Assuming that the end time of electrical stimulation is , then the effective signal time range is The effective signal calculation formula is as follows:

[0038] in, is a valid signal, is the sampling rate.

[0039] In a preferred embodiment, data between 1.25 milliseconds and 30 milliseconds after the end of electrical stimulation in the sacral evoked response signal is selected as a valid signal.

[0040] S300, data preprocessing: preprocessing the effective signal to remove power frequency noise and stimulation artifacts.

[0041] In a preferred embodiment, a notch filter is used to filter out 50 Hz power frequency noise, and the calculation formula is as follows:

[0042] in, is the filtered signal, is the filter function.

[0043] In a preferred embodiment, removing the stimulation artifact comprises the following steps: fitting the stimulation artifact using an exponential function, wherein the exponential function fitting model is:

[0044] in, is the initial amplitude, indicating the strength of the artifact signal; is the time constant, controlling how quickly the signal decays; is a constant that represents the baseline or offset of the signal; Solution Error The minimum value of , , ,error The calculation formula is as follows:

[0045] in, Sampling time point; According to the best , , Calculate the artifact signal , from the filtered signal Subtract artifact signal Get the processed signal , in order to eliminate the influence of artifacts, the processed signal The calculation formula is as follows: .

[0046] S400, feature extraction: extracting feature data from the processed signal.

[0047] In one embodiment, the characteristic data includes peak-to-peak value, latency and number of peaks, see Figure 3 As shown, the peak-to-peak value is the difference between the largest positive peak and the largest negative peak in the processed signal, and the calculation formula is as follows:

[0048] in, is the peak-to-peak value; The latency is the delay between the maximum peak time in the processed signal and the starting point of the effective signal. The calculation formula is as follows:

[0049] in, For the incubation period, is the time of occurrence of the maximum peak in the processed signal; The peak count is the total number of peaks and troughs in the processed signal, calculated as follows:

[0050] in, is the number of peaks, As a function, Returns 1 if it is a local maximum, otherwise returns 0.

[0051] S500, modeling: establishing a corresponding relationship model between the characteristic data of sacral evoked response and the stimulation amplitude according to the characteristic data obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude.

[0052] Optionally, one or more methods including correlation coefficient, regression, variance, covariance, and machine learning can be used to process and analyze the characteristic data obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude, so as to establish a corresponding relationship model between the characteristic data of sacral evoked responses and the stimulation amplitude.

[0053] In one embodiment, the three extracted feature data are combined into a feature vector X1=(peak-to-peak value, latency, number of peaks), and then the feature vector is standardized to obtain an input feature vector X, so that the mean of each feature is 0 and the standard deviation is 1, so as to eliminate the dimensional difference between the features; for the input feature vector X obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude Y, a linear regression model is used to establish a corresponding relationship model between the feature data of the sacral evoked response and the stimulation amplitude, and the linear regression model calculation formula is as follows:

[0054] in, is the slope, is the intercept; determined by the least squares method and , the formula is as follows:

[0055] in, The serial number is i The input feature vector of the electrical stimulation test sample, The serial number is i The stimulation amplitude of the electrical stimulation test sample, is the average value of the input feature vectors of all electrical stimulation test samples, is the average value of the stimulation amplitude of all electrical stimulation test samples, n The number of samples tested for electrical stimulation.

[0056] Embodiment 2: This embodiment provides a sacral nerve stimulation adaptive control method, see Figure 4 As shown, the method comprises the following steps: S1000, data acquisition: real-time acquisition of sacral evoked response signals under electrical stimulation of the patient.

[0057] After the sacral nerve electrode is implanted into the third sacral foramen (S3) of the sacrum, when in use, two of the four channels are set to stimulation mode, and then electrical stimulation is applied. The commonly used stimulation frequency is 14Hz, and the range can be set to 5HZ-20HZ; the stimulation current can be increased from 0.5mA in increments of 0.1mA, but it cannot exceed the maximum tolerance threshold; the pulse width is generally set to 210us. The corresponding sacral evoked response signal recorded and collected is ,in Represents a point in time.

[0058] S2000, data clipping: selecting data in a set time period after the end of electrical stimulation in the sacral evoked response signal as a valid signal.

[0059] In one embodiment, the sacral evoked response signal after the electrical stimulation is selected Time to The data between the two moments are taken as valid signals for subsequent analysis. Assuming that the end time of electrical stimulation is , then the effective signal time range is The effective signal calculation formula is as follows:

[0060] in, is the sampling rate.

[0061] In a preferred embodiment, data between 1.25 milliseconds and 30 milliseconds after the end of electrical stimulation in the sacral evoked response signal is selected as a valid signal.

[0062] S3000, data preprocessing: preprocess the effective signal to remove power frequency noise and stimulation artifacts.

[0063] In a preferred embodiment, a notch filter is used to filter out 50 Hz power frequency noise, and the calculation formula is as follows:

[0064] in, is the filtered signal, is the filter function.

[0065] In a preferred embodiment, removing the stimulation artifact comprises the following steps: fitting the stimulation artifact using an exponential function, wherein the exponential function fitting model is:

[0066] in, is the initial amplitude, indicating the strength of the artifact signal; is the time constant, controlling how quickly the signal decays; is a constant that represents the baseline or offset of the signal; Solution Error The minimum value of , , ,error The calculation formula is as follows:

[0067] in, is the sampling time point; According to the best , , Calculate the artifact signal , from the filtered signal Subtract artifact signal Get the processed signal , in order to eliminate the influence of artifacts, the processed signal The calculation formula is as follows: .

[0068] S4000, feature extraction: extract feature data from the processed signal.

[0069] In one embodiment, the characteristic data includes peak-to-peak value, latency and number of peaks, see Figure 3 As shown, the peak-to-peak value is the difference between the largest positive peak and the largest negative peak in the processed signal, and the calculation formula is as follows:

[0070] in, is the peak-to-peak value; The latency is the delay between the maximum peak time in the processed signal and the starting point of the effective signal. The calculation formula is as follows:

[0071] in, For the incubation period, is the time of occurrence of the maximum peak in the processed signal; The peak count is the total number of peaks and troughs in the processed signal, calculated as follows:

[0072] in, is the number of peaks, As a function, Returns 1 if it is a local maximum, otherwise returns 0.

[0073] S5000, model prediction: input the extracted feature data into the corresponding relationship model obtained in Example 1 to calculate the predicted stimulation amplitude .

[0074] S6000, Stimulation Amplitude Adjustment: Compare predicted stimulation amplitudes The actual stimulation amplitude of the electrical stimulation ,if , then reduce the stimulus amplitude; if , then increase the stimulus amplitude; if , the stimulus amplitude remains unchanged.

[0075] In a preferred embodiment, the stimulation amplitude is adjusted using the following linear modification formula:

[0076] in, is the adjusted stimulus amplitude, To adjust the step size, is the error value.

[0077] Controls the speed of adjusting the amplitude. If If it is larger, the adjustment will be more drastic, if it is smaller, the adjustment will be more stable. The maximum sensory threshold must not be exceeded.

[0078] The embodiment of the present invention only needs one sacral nerve electrode to collect sacral evoked responses of different stimulation thresholds under different patient postures, and construct a corresponding relationship model between sacral evoked responses and stimulation amplitudes, so that the current stimulation amplitude can be predicted according to the patient's real-time sacral evoked response, and the actual stimulation intensity can be dynamically adjusted to determine whether it meets the requirements, and the treatment effect under the patient's posture state and electrode changes can be applied. At the same time, patients do not need to go back and forth to the hospital many times, reducing the number of visits for patients and improving the convenience and effectiveness of treatment.

[0079] Embodiment 3: This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the sacral nerve stimulation adaptive control method described above are implemented.

[0080] The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.

[0081] Embodiment 4: This embodiment provides a computer device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the sacral nerve stimulation adaptive control method described above when executing the program.

[0082] like Figure 5 As shown, the computer device 70 may include: at least one processor 71, such as a CPU (Central Processing Unit), at least one communication interface 73, a memory 74, and at least one communication bus 72. The communication bus 72 is used to realize the connection and communication between these components. The communication interface 73 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 73 may also include a standard wired interface and a wireless interface. The memory 74 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 74 may also be at least one storage device located away from the aforementioned processor 71. The memory 74 stores application programs, and the processor 71 calls the program code stored in the memory 74 to execute any of the above method steps.

[0083] The communication bus 72 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 72 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0084] Among them, the memory 74 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 74 may also include a combination of the above types of memory.

[0085] The processor 71 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

[0086] The processor 71 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0087] Optionally, the memory 74 is also used to store program instructions. The processor 71 can call the program instructions to implement the sacral nerve stimulation adaptive control method of the present invention.

[0088] Those skilled in the art should understand that the present invention can be implemented in many other specific forms without departing from the spirit and scope of the present invention. Based on the embodiments of the present invention, any changes and modifications made by ordinary technicians in the field of the present invention according to the above disclosure are within the scope of protection of the claims.

Claims

1. A method for constructing a sacral nerve stimulation control model, characterized in that: The method comprises the following steps: S100, data collection: performing electrical stimulation tests on multiple test patients in different postures, and collecting sacral evoked response signals of the test patients under each stimulation condition; S200, data clipping: selecting data in a set time period after the end of electrical stimulation in the sacral evoked response signal as a valid signal; S300, data preprocessing: preprocessing the effective signal to remove power frequency noise and stimulation artifacts; S400, feature extraction: extracting feature data from the processed signal; S500, modeling: establishing a corresponding relationship model between the characteristic data of sacral evoked response and the stimulation amplitude according to the characteristic data obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude.

2. The method for constructing a sacral nerve stimulation control model according to claim 1, characterized in that: In step S100, the number of patients tested is more than 15, the postures of the patients tested include lying down, standing and sitting, and the stimulation amplitude includes the motor threshold, the sensory threshold and the maximum tolerance threshold.

3. The method for constructing a sacral nerve stimulation control model according to claim 1, characterized in that: In step S200, the sacral evoked response signal after the electrical stimulation is selected. Time to The data between the times is taken as the effective signal, and the calculation formula of the effective signal is as follows: ； in, is a valid signal, For the collected sacral evoked response signals, Represents a point in time, is the end time of electrical stimulation, is the sampling rate.

4. The method for constructing a sacral nerve stimulation control model according to claim 3, characterized in that: In step S300, a notch filter is used to filter out power frequency noise, and the calculation formula is as follows: ； in, is the filtered signal, is the filter function; Removing the stimulation artifact includes the following steps: using an exponential function to fit the stimulation artifact, the exponential function fitting model is: ； in, is the initial amplitude, indicating the strength of the artifact signal; is the time constant, controlling how quickly the signal decays; is a constant that represents the baseline or offset of the signal; Solution Error The minimum value of , , ,error The calculation formula is as follows: ； in, is the sampling time point; According to the best , , Calculate the artifact signal , from the filtered signal Subtract artifact signal Get the processed signal , in order to eliminate the influence of artifacts, the processed signal The calculation formula is as follows: 。 5. The method for constructing a sacral nerve stimulation control model according to claim 4, characterized in that: In step S400, the characteristic data includes peak-to-peak value, latent period and number of peaks, wherein the peak-to-peak value is the difference between the maximum positive peak and the maximum negative peak in the processed signal, the latent period is the delay of the occurrence time of the maximum peak in the processed signal relative to the starting point of the effective signal, and the number of peaks is the total number of peaks and troughs in the processed signal.

6. The method for constructing a sacral nerve stimulation control model according to claim 5, characterized in that: In step S500, the three extracted feature data are combined into a feature vector X1=(peak-to-peak value, latency, number of peaks), and then the feature vector is standardized to obtain an input feature vector X; for the input feature vector X obtained from all electrical stimulation test samples and the corresponding electrical stimulation amplitude Y, a linear regression model is used to establish a corresponding relationship model between the feature data of the sacral evoked response and the stimulation amplitude, and the linear regression model calculation formula is as follows: ； in, is the slope, is the intercept; determined by the least squares method and , the formula is as follows: ； in, The serial number is i The input feature vector of the electrical stimulation test sample, The serial number is i The stimulation amplitude of the electrical stimulation test sample, is the average value of the input feature vectors of all electrical stimulation test samples, is the average value of the stimulation amplitude of all electrical stimulation test samples, n The number of samples tested for electrical stimulation.

7. A sacral nerve stimulation adaptive control method, characterized in that: The method comprises the following steps: S1000, data acquisition: real-time acquisition of sacral evoked response signals under electrical stimulation of the patient; S2000, data clipping: selecting data in a set time period after the end of electrical stimulation in the sacral evoked response signal as a valid signal; S3000, data preprocessing: preprocess the effective signal to remove power frequency noise and stimulation artifacts; S4000, feature extraction: extracting feature data from the processed signal; S5000, model prediction: input the extracted feature data into the corresponding relationship model obtained by the sacral nerve stimulation control model construction method according to any one of claims 1 to 6 to calculate the predicted stimulation amplitude ; S6000, Stimulus Amplitude Adjustment: Compare predicted stimulation amplitudes The actual stimulation amplitude of the electrical stimulation ,if , then reduce the stimulus amplitude; if , then increase the stimulus amplitude; if , the stimulus amplitude remains unchanged.

8. The sacral nerve stimulation adaptive control method according to claim 7, characterized in that: In step S6000, the stimulation amplitude is adjusted using the following linear modification formula: ； in, is the adjusted stimulus amplitude, To adjust the step size, is the error value.

9. 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 sacral nerve stimulation adaptive control method according to any one of claims 7 to 8 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the sacral nerve stimulation adaptive control method according to any one of claims 7 to 8 are implemented.

Images