A method and system for evaluating the correctness of sacral nerve implantation points

Abstract

The present invention discloses a method and system for evaluating the correctness of sacral nerve implantation points. The method comprises: collecting a first sacral evoked response signal when the sacral nerve electrode is implanted in the correct point, and a second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct point; performing data processing and feature extraction on the sacral evoked response signal to obtain data features; using the data features as input and whether the sacral nerve electrode is implanted in the correct point as the output result to construct a decision tree model; collecting a target sacral evoked response signal when the sacral nerve electrode to be detected is implanted in the target point, and detecting whether the target point is the correct point based on the target sacral evoked response signal and the decision tree model for identifying the implantation point. The method disclosed in the embodiment of the present invention can automatically determine whether the sacral nerve electrode is in the correct point.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of biological signal analysis, and in particular to a method and system for evaluating the correctness of sacral nerve implantation points. Background Art

[0002] Sacral neuromodulation (SNM) is an established treatment modality for patients with symptoms such as overactive bladder (OAB), non-obstructive urinary retention (NOUR), and fecal incontinence (FI) who are unresponsive to conservative treatment. In the current standard of care for SNM, physicians rely on visually observed motor responses (motor thresholds) or patient-reported sensory responses (sensory thresholds) to determine if the correct implant site is in place and to determine the treatment schedule based on this information.

[0003] Motor threshold is defined as the stimulus amplitude required to elicit the first observable motor response, such as contraction of the external sphincter, abdomen, or toes. Sensory threshold is the stimulus amplitude at which a patient first reports a sensation of stimulation.

[0004] Currently, the evaluation of whether the implantation site is correct and the setting of the stimulation program for treatment mainly relies on the motor threshold or sensory threshold, but both methods have disadvantages. The motor threshold relies on visual observation of motor reactions, and slight motor reactions may be difficult to distinguish. It is also related to the doctor's subjective judgment, which may lead to inaccurate judgment results. In addition, after implantation, the sacral nerve electrodes may be displaced due to the patient's movement and other reasons, affecting the treatment effect. Currently, the only way to judge whether the electrode has been displaced and whether the treatment is effective is based on the patient's feeling, and the patient's perception of stimulation may be unreliable. Therefore, the process of judging whether the implantation site is correct, whether the electrode has been displaced after implantation, and whether the treatment effect is effective is cumbersome and lacks clear evidence. Using these methods, it is impossible to correctly and objectively evaluate the correctness of the electrode implantation site or predict the effectiveness of the treatment. Summary of the Invention

[0005] The present invention aims to address, at least to some extent, one of the problems in the related art. Embodiments of the present invention provide a method and system for assessing the accuracy of sacral nerve implant placement. By measuring and characterizing the sacral evoked response produced by sacral nerve stimulation, the method reduces human variability and allows for a more reliable assessment of implant placement and treatment efficacy.

[0006] In a first aspect, an embodiment of the present invention provides a method for evaluating the correctness of sacral nerve implantation points, comprising:

[0007] Collect the first sacral evoked response signal when the sacral nerve electrode is implanted in the correct position, and the second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct position;

[0008] performing data processing on the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in a correct location; performing data processing on the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in a correct location;

[0009] Performing feature extraction on the first processed data to obtain a first data feature when the sacral nerve electrode is implanted in the correct location; performing feature extraction on the second processed data to obtain a second data feature when the sacral nerve electrode is not implanted in the correct location;

[0010] Taking the first data feature as input and the correct implantation location of the sacral nerve electrode as output; and taking the second data feature as input and the incorrect implantation location of the sacral nerve electrode as output; constructing a decision tree model for identifying the implantation location and completing model training;

[0011] A target sacral evoked response signal is collected when the sacral nerve electrode to be detected is implanted at the target point, and whether the target point is a correct point is detected based on the target sacral evoked response signal and the decision tree model for identifying the implantation point.

[0012] Furthermore, the data processing method includes: data clipping and data preprocessing;

[0013] The data clipping process is specifically as follows:

[0014] Through the time window, the sacral evoked response signal within the preset time period after the stimulation is intercepted as the effective signal data, and the formula is:

[0015]

[0016] in, is the valid signal data, is the sacral evoked response signal, is the stimulation end time, is the start time of the preset time period, The end time of the preset time period. is the sampling rate.

[0017] Furthermore, the data preprocessing process specifically includes: filtering the effective signal data; using the recursive least squares method to remove stimulation artifacts from the filtered data to obtain processed data.

[0018] Further, the first data feature includes peak-to-peak amplitude, latency, and number of peaks in the first processed data; the second data feature includes peak-to-peak amplitude, latency, and number of peaks in the second processed data;

[0019] The peak-to-peak amplitude is the difference between the maximum positive peak and the maximum negative peak in the data following the maximum negative peak;

[0020] The incubation period is the time delay from the start time of the preset time period to the appearance time of the maximum negative peak;

[0021] The peak number is the number of peaks in the data after the maximum negative peak.

[0022] Furthermore, the decision tree generation algorithm adopts the ID3 information gain algorithm or the CART Gini index algorithm.

[0023] Furthermore, after the decision tree is built, cross-validation is used to test the accuracy of the model.

[0024] Furthermore, a target sacral evoked response signal is collected when the sacral nerve electrode to be detected is implanted at the target location, and whether the target location is a correct location is detected based on the target sacral evoked response signal and the decision tree model for identifying the implantation location, including:

[0025] Stimulation is applied to the target point where the sacral nerve electrode to be detected is implanted, and a target sacral evoked response signal after the target point is stimulated is collected; data processing is performed on the target sacral evoked response signal to obtain target processed data; feature extraction is performed on the target processed data to obtain target data features; the target data features are input into the decision tree model for identifying the implantation point to obtain a detection result of whether the target point is a correct point.

[0026] In a second aspect, an embodiment of the present invention provides a sacral nerve implant location correctness assessment system, comprising:

[0027] Data acquisition module: used to collect the first sacral evoked response signal when the sacral nerve electrode is implanted in the correct position, and the second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct position;

[0028] A data processing module is configured to process the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in the correct location; and to process the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in the correct location.

[0029] A feature extraction module is configured to extract features from the first processed data to obtain first data features when the sacral nerve electrode is implanted in the correct location; and to extract features from the second processed data to obtain second data features when the sacral nerve electrode is not implanted in the correct location.

[0030] a model construction module configured to take the first data feature as input and the correct implantation location of the sacral nerve electrode as output; and take the second data feature as input and the incorrect implantation location of the sacral nerve electrode as output; construct a decision tree model for identifying the implantation location, and complete model training;

[0031] The evaluation module is used to collect the target sacral evoked response signal when the sacral nerve electrode to be tested is implanted in the target point, and detect whether the target point is the correct point based on the target sacral evoked response signal and the decision tree model for identifying the implantation point.

[0032] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising:

[0033] at least one processor; and

[0034] a memory communicatively connected to the at least one processor; wherein,

[0035] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for assessing the correctness of sacral nerve implantation position according to any embodiment of the present invention.

[0036] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the sacral nerve implant position correctness assessment method described in any embodiment of the present invention when executed.

[0037] An embodiment of the present invention provides a method and system for evaluating the correctness of sacral nerve implantation sites. The method collects sacral evoked response signals from different patients, performs preprocessing and feature extraction on the signals, and finally performs statistics and analysis on the extracted features to determine the relationship between the sacral evoked response and the electrode implantation site. In subsequent use, the sacral evoked response is used as an objective evaluation basis for the implantation site and therapeutic effect. This method does not rely on the patient's subjective feedback or the doctor's subjective observation, and can provide objective feedback for the implantation site and therapeutic effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a schematic diagram of a sacral evoked response provided by the present invention;

[0039] Figure 2 This is a flow chart of the method for evaluating the correctness of sacral nerve implantation points in Example 1 of the present invention;

[0040] Figure 3 is a characteristic example diagram of the sacral evoked response in Example 1 of the present invention;

[0041] Figure 4 is a flowchart of the training phase in the first embodiment of the present invention;

[0042] Figure 5 This is a flow chart of the use phase in the first embodiment of the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0044] Before introducing the embodiments of the present invention, it is necessary to explain that:

[0045] Sacral evoked responses refer to the electrophysiological responses recorded from the S3 sacral nerve after stimulation of the representative sacral nerve. Figure 1 Schematic diagram of the sacral evoked response provided by the present invention, such as Figure 1 As shown in the figure, the horizontal axis represents time and the vertical axis represents the amplitude of the electrical signal. At the moment of stimulation, the amplitude of the electrical signal reaches its maximum. After the stimulation ends, the amplitude of the electrical signal begins to gradually decrease, and neural reactions and myoelectric reactions occur successively, and then tend to be stable. In addition, Figure 1 The amplitude of the CEC signal represents the intensity of the response of the sacral nerve after stimulation compared to the non-stimulated state. Figure 1 The electrical signal amplitude in the non-stimulation state is not shown in the figure. The values ​​above this amplitude represent positive stimulation responses, and the values ​​below this amplitude represent negative stimulation responses.

[0046] After stimulation, sacral evoked responses mainly include the following two electrophysiological responses: (1) Neural Responses: Evoked Compound Action Potentials (ECAPs), which are electrical signals recorded from near the electrodes when nerve fibers are stimulated; (2) Myoelectric Responses: electrical signals generated by muscle activation, usually muscle contraction caused by nerve stimulation.

[0047] Example 1: Figure 2 This is a flow chart of a method for evaluating the correctness of sacral nerve implantation point location provided in Example 1 of the present invention. This embodiment is applicable to evaluating the correctness of electrode location in sacral nerve modulation therapy. This method can be executed by a sacral nerve implantation point location accuracy evaluation system, such as Figure 2 As shown, the method specifically includes the following steps:

[0048] Step 210 , collecting a first sacral evoked response signal when the sacral nerve electrode is implanted at the correct location, and a second sacral evoked response signal when the sacral nerve electrode is not implanted at the correct location.

[0049] Specifically, during surgery, sacral evoked response signals were collected from different patients after stimulation, both when the sacral nerve electrodes were correctly implanted and when they were not. Different sacral evoked response signals were labeled differently depending on whether the sacral nerve electrodes were correctly implanted. The labels were then used to distinguish whether the data corresponding to different features belonged to data from correct or incorrect implantation.

[0050] Step 220 , data processing is performed on the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in the correct location; data processing is performed on the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in the correct location.

[0051] Data processing methods include data cropping and data preprocessing. Preprocessing mainly includes filtering and recursive least squares method artifact removal.

[0052] In the embodiment of the present invention, the data clipping process is specifically as follows:

[0053] Through the time window, the sacral evoked response signal within the preset time period after the stimulation is intercepted as the effective signal data, and the formula is:

[0054]

[0055] in, is the valid signal data, is the sacral evoked response signal, is the stimulation end time, is the start time of the preset time period, The end time of the preset time period. is the sampling rate.

[0056] In a preferred embodiment, Select 1.25 milliseconds, 30 milliseconds was selected. That is, the data between 1.25 milliseconds and 30 milliseconds after the end of the stimulus were used as valid signal data for subsequent analysis.

[0057] In the embodiment of the present invention, the data preprocessing process is specifically as follows:

[0058] Filter the valid signal data to remove power frequency noise. Use a notch filter to filter out 50Hz power frequency noise.

[0059]

[0060] in, is the filter function.

[0061] Furthermore, the recursive least squares method (RLS) is used to remove stimulation artifacts from the filtered data to obtain processed data.

[0062] The core idea of ​​the RLS algorithm is to recursively update the filter coefficients to minimize the error between the output signal and the desired signal.

[0063] Assuming the input signal , expected output signal , output signal is the input signal and the filter weight The weighted sum of:

[0064]

[0065] The error is the difference between the expected output and the actual data:

[0066]

[0067] The goal of RLS is to adjust the filter coefficients by , making the error Minimize. RLS adopts the least squares criterion and updates the filter through a recursive formula.

[0068] The filter is updated as follows:

[0069]

[0070] in, is the gain vector:

[0071]

[0072] The signal after removing the stimulation artifact is used as the processed data: .

[0073] In an embodiment of the present invention, filtering is performed on the effective signal data to remove noise, and a recursive least squares method is used to remove stimulation artifacts to ensure that the signal quality is suitable for subsequent analysis.

[0074] Step 230 , feature extraction is performed on the first processed data to obtain first data features when the sacral nerve electrode is implanted in the correct location; feature extraction is performed on the second processed data to obtain second data features when the sacral nerve electrode is not implanted in the correct location.

[0075] Feature extraction was performed on the pre-processed data to obtain key physiological features, such as peak-to-peak amplitude, peak latency, and the total number of peaks in each sacral evoked response.

[0076] Specifically, the sacral evoked response signal when the sacral nerve electrode is implanted in the correct position and the sacral evoked response signal when the sacral nerve electrode is not implanted in the correct position are collected. Both signals include the neural response process and the electromyographic response process. By comparing the characteristics of the neural response process and the electromyographic response process, features that can distinguish the two types of data are obtained.

[0077] The first data feature includes the peak-to-peak amplitude, latency, and number of peaks in the first processed data; the second data feature includes the peak-to-peak amplitude, latency, and number of peaks in the second processed data.

[0078] Figure 3 This is a characteristic diagram of the sacral evoked response in Example 1 of the present invention, combined with Figure 1 and Figure 3 , Figure 1 The starting time is the end time of stimulation: , Figure 3 The starting time is the starting time of the valid signal data time: .

[0079] In the embodiment of the present invention, the peak-to-peak amplitude is the difference between the maximum positive peak and the maximum negative peak in the data following the maximum negative peak:

[0080]

[0081] by Figure 3 For example, the peak-to-peak amplitude is collected from the time when the largest negative peak appears. The largest negative peak is the first marked point, and the largest positive peak is the second marked point. The peak-to-peak amplitude is the difference between the two.

[0082] In an embodiment of the present invention, the incubation period is the time delay from the start time of the preset time period to the occurrence time of the maximum negative peak:

[0083] Figure 3 The starting time is the starting time of the valid signal data time: , as the starting time of the incubation period, and the end time of the incubation period is the time when the maximum negative peak occurs.

[0084] In the embodiment of the present invention, the peak number is the number of peaks in the data after the maximum negative peak:

[0085] by Figure 3 For example, the peak count also starts from the time when the largest negative peak appears, including two positive peaks and two negative peaks, where Figure 3 The first negative peak in the graph is the maximum negative peak.

[0086] Step 240: Using the first data feature as input and the correct implantation location of the sacral nerve electrode as output, and using the second data feature as input and the incorrect implantation location of the sacral nerve electrode as output, construct a decision tree model for identifying the implantation location and complete model training.

[0087] In an embodiment of the present invention, the relationship between sacral evoked responses and electrode placement is determined by analyzing the characteristics of sacral evoked responses when implanted at the correct location and when not implanted at the correct potential. Specifically, the extracted feature data is input into a decision tree model for training to generate a classification model. This model can automatically determine whether the sacral nerve electrode is in the correct location based on different sacral evoked response signals.

[0088] Specifically, the peak-to-peak amplitude, latency, and number of peaks of the sacral evoked response (EVR) signal when the sacral nerve electrodes were correctly implanted, as well as the peak-to-peak amplitude, latency, and number of peaks when the sacral nerve electrodes were not correctly implanted, were input into a decision tree model. Based on the different labels assigned to the EVR signals, the decision tree recursively selects features for classification and continuously optimizes the tree structure, ultimately generating a decision tree capable of classifying the different EVR signals.

[0089] Furthermore, after the decision tree is built, cross-validation is used to test the accuracy of the model. Based on the evaluation results, the structure of the tree is further optimized to avoid overfitting or underfitting.

[0090] In an embodiment of the present invention, a decision tree is constructed using features extracted from electrophysiological signals (such as peak-to-peak amplitude, latency, and number of peaks). The core of decision tree generation is to select the optimal features to split the dataset, maximizing the purity of each subset. Decision tree generation algorithms employ the ID3 information gain algorithm or the CART Gini index algorithm, which typically select the optimal splitting features based on information gain or the Gini index.

[0091] For ID3 information gain algorithm:

[0092] There is a feature A and a data set D, information gain Calculated as:

[0093]

[0094] Among them, is the entropy of the data set D, which represents the uncertainty of the data.

[0095]

[0096] in, is the probability of the i-th class in the data set, It is the entropy of the subset after the data set is divided by the value v of feature A.

[0097] For the CART Gini Index algorithm, the split selection is based on the Gini Index. The Gini Index is defined as:

[0098]

[0099] in, is the probability of the i-th class in the data set. For each feature A, the Gini index is calculated, and the feature with the smallest Gini index is selected to split the data set.

[0100] The decision tree generation process is as follows:

[0101] Input features: The signal features collected in each test are used as data input. Each data point contains these feature values, which serve as the basis for decision tree training.

[0102] Training Dataset: Whether or not the data is in the correct location is used as the class label to train the decision tree. Based on the different signal characteristics of the two types of data, the decision tree learns to classify them into different categories based on these characteristics.

[0103] Decision tree generation: By recursively selecting features for division and continuously optimizing the tree structure, a decision tree is eventually generated that can classify whether the sacral evoked response signal is in the correct position.

[0104] Evaluation and Optimization: After the decision tree is built, cross-validation is used to test the accuracy of the model. Based on the evaluation results, the tree structure is further optimized to avoid overfitting or underfitting.

[0105] Step 250 , collecting a target sacral evoked response signal when the sacral nerve electrode to be tested is implanted at the target location, and detecting whether the target location is a correct location based on the target sacral evoked response signal and the decision tree model for identifying the implantation location.

[0106] In an embodiment of the present invention, during actual implantation, whether the implantation point is correct is evaluated based on the sacral evoked response characteristics; preferably, whether the electrode is displaced can also be determined based on the sacral evoked response characteristics; further, whether the treatment effect is effective can also be determined.

[0107] Specifically, stimulation is applied to the target point where the sacral nerve electrode to be tested is implanted, and the target sacral evoked response signal after the target point is stimulated is collected; data processing is performed on the target sacral evoked response signal to obtain target processed data; feature extraction is performed on the target processed data to obtain target data features; the target data features are input into a decision tree model for identifying the implantation point to obtain a detection result of whether the target point is a correct point.

[0108] In an embodiment of the present invention, the implementation of the entire scheme includes two phases: a training phase and a usage phase. The training phase involves collecting sacral evoked response signals from a large number of subjects at different implantation sites, performing statistics and analysis after preprocessing and feature extraction, determining the relationship between sacral evoked responses and electrode site locations, and then establishing a decision tree model. The usage phase refers to the phase after modeling is completed, during which the patient enters the implantation process, assessing the correctness of the implantation site based on the sacral evoked response data, and assessing whether the electrode has shifted and whether the treatment is effective during subsequent treatment.

[0109] Figure 4 4 is a flow chart of the training phase in an embodiment of the present invention. The training phase targets the detected sacral nerve electrode implantation sites, and the sacral evoked response signals of these sites are used as training data sets.

[0110] Specifically, the sacral evoked response signals of these points are first collected; then the sacral evoked response signals are subjected to data clipping and data preprocessing; then the processed data are subjected to feature extraction; finally, a decision tree is generated based on the different features of different data.

[0111] Figure 5 This is a flow chart of the use phase in an embodiment of the present invention, which is directed to the sacral nerve electrode implantation site to be detected.

[0112] Data acquisition: real-time collection of patients' physiological signal data.

[0113] Data trimming: Data between 1.25 milliseconds and 30 milliseconds after the end of stimulation were selected as valid signal data for subsequent analysis.

[0114] Data preprocessing: Valid signal data were filtered to remove noise, and recursive least squares method was used to remove stimulation artifacts to ensure that the signal quality was suitable for subsequent analysis.

[0115] Feature extraction: Extract key features from the processed signal, including peak-to-peak amplitude, latency, and number of peaks.

[0116] Effect evaluation: The extracted feature data is input into a pre-trained decision tree model to determine whether the implantation point of the electrode is correct; during use, it is determined whether the electrode is displaced and whether the therapeutic effect is effective.

[0117] Specifically, during the usage phase, the sacral evoked response signals of the sacral nerve implantation point to be tested are first collected; then the sacral evoked response signals are subjected to data clipping and data preprocessing; then, feature extraction is performed on the processed data; then, these features are statistically analyzed and input into a trained decision tree model; finally, based on the classification results of the decision tree model, the effect of the sacral nerve implantation point to be tested is evaluated.

[0118] The technical solution of this embodiment collects sacral evoked response signals from different patients, preprocesses them, extracts features, and then statistically analyzes the extracted features to determine the relationship between sacral evoked responses and electrode implantation sites. Subsequent use uses sacral evoked responses as an objective basis for evaluating implantation sites and therapeutic efficacy, eliminating the need for subjective feedback from users and subjective observations by doctors. Furthermore, the elimination of redundant electrodes reduces patient trauma and overall system power consumption.

[0119] Embodiment 2: This embodiment of the present invention provides a sacral nerve implant position accuracy assessment system configured to implement the method described in any embodiment of the present invention. This embodiment is applicable to assessing the accuracy of electrode position during sacral nerve modulation therapy. The system can be implemented using software and / or hardware. The sacral nerve implant position accuracy assessment system specifically includes:

[0120] Data acquisition module: used to collect the first sacral evoked response signal when the sacral nerve electrode is implanted in the correct position, and the second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct position;

[0121] Data processing module: used to process the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in the correct position; and to process the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in the correct position;

[0122] Feature extraction module: used to extract features from the first processed data to obtain first data features when the sacral nerve electrode is implanted in the correct location; and to extract features from the second processed data to obtain second data features when the sacral nerve electrode is not implanted in the correct location;

[0123] a model building module configured to take the first data feature as input and the correct implantation location of the sacral nerve electrode as output; and take the second data feature as input and the incorrect implantation location of the sacral nerve electrode as output; build a decision tree model for identifying the implantation location, and complete model training;

[0124] The evaluation module is used to collect the target sacral evoked response signal when the sacral nerve electrode to be tested is implanted in the target point, and detect whether the target point is the correct point based on the target sacral evoked response signal and the decision tree model for identifying the implantation point.

[0125] The technical solution of this embodiment does not require complex models and calculations, and has high operational efficiency. It uses data as an evaluation indicator, making implantation point judgment more accurate, and the judgment standards of different doctors or patients are consistent. It does not rely on the patient's subjective feedback or the doctor's subjective observation, and can provide objective feedback for implantation point and efficacy evaluation.

[0126] Embodiment 3: An embodiment of the present invention further provides an electronic device, comprising:

[0127] at least one processor; and

[0128] a memory communicatively connected to the at least one processor; wherein,

[0129] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for assessing the correctness of sacral nerve implantation position according to any embodiment of the present invention.

[0130] Electronic devices are intended to refer to various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also refer to various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are intended to be examples only and are not intended to limit the implementation of the inventions described and / or claimed herein.

[0131] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processing device, implements the sacral nerve implant position accuracy assessment method described in the embodiments of the present invention. The computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or convey a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0132] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0133] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0134] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: collects a first sacral evoked response signal when the sacral nerve electrode is implanted in the correct position, and a second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct position; performs data processing on the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in the correct position; performs data processing on the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in the correct position; performs feature extraction on the first processed data to obtain a first processed data when the sacral nerve electrode is implanted in the correct position. The invention discloses a method for detecting a first data feature of a sacral nerve electrode when the sacral nerve electrode is not implanted at the correct location; extracting features from the second processed data to obtain a second data feature when the sacral nerve electrode is not implanted at the correct location; taking the first data feature as input and the sacral nerve electrode being implanted at the correct location as output; and taking the second data feature as input and the sacral nerve electrode not being implanted at the correct location as output; constructing a decision tree model for identifying the implantation location and completing model training; collecting a target sacral evoked response signal when the sacral nerve electrode to be detected is implanted at the target location, and detecting whether the target location is the correct location based on the target sacral evoked response signal and the decision tree model for identifying the implantation location.

[0135] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0136] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0137] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0138] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0139] In the context of the present disclosure, a computer-readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for evaluating the correctness of sacral nerve implantation points, characterized in that: include: The first sacral evoked response signal when the sacral nerve electrode is implanted in the correct location, and the second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct location are collected. The sacral evoked response includes the following two electrophysiological responses: neural response and electromyographic response. The neural response refers to the evoked compound action potential, which is the electrical signal recorded from the vicinity of the electrode when the nerve fiber is stimulated. The electromyographic response refers to the electrical signal generated by muscle activation, which is the muscle contraction caused by nerve stimulation. performing data processing on the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in a correct location; performing data processing on the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in a correct location; Performing feature extraction on the first processed data to obtain a first data feature when the sacral nerve electrode is implanted in the correct location; performing feature extraction on the second processed data to obtain a second data feature when the sacral nerve electrode is not implanted in the correct location; Taking the first data feature as input and the correct implantation location of the sacral nerve electrode as output; and taking the second data feature as input and the incorrect implantation location of the sacral nerve electrode as output; constructing a decision tree model for identifying the implantation location and completing model training; collecting a target sacral evoked response signal when the sacral nerve electrode to be tested is implanted at a target location, and detecting whether the target location is a correct location based on the target sacral evoked response signal and the decision tree model for identifying the implantation location; The data processing method includes: data clipping and data preprocessing; The data clipping process is specifically as follows: Through the time window, the sacral evoked response signal within the preset time period after the stimulation is intercepted as the effective signal data, and the formula is: ； in, is the valid signal data, is the sacral evoked response signal, is the stimulation end time, is the start time of the preset time period, The end time of the preset time period. is the sampling rate; The data preprocessing process specifically includes: filtering the effective signal data; using the recursive least squares method to remove stimulation artifacts from the filtered data to obtain processed data; The first data feature includes the peak-to-peak amplitude, latency, and number of peaks in the first processed data; the second data feature includes the peak-to-peak amplitude, latency, and number of peaks in the second processed data; The peak-to-peak amplitude is the difference between the maximum positive peak and the maximum negative peak in the data following the maximum negative peak; The incubation period is the time delay from the start time of the preset time period to the appearance time of the maximum negative peak; The peak number is the number of peaks in the data after the maximum negative peak.

2. The method according to claim 1, characterized in that The decision tree generation algorithm uses the ID3 information gain algorithm or the CART Gini index algorithm.

3. The method according to claim 1, characterized in that After the decision tree is built, cross-validation is used to test the accuracy of the model.

4. The method according to claim 1, wherein Acquiring a target sacral evoked response signal when the sacral nerve electrode to be tested is implanted at a target location, and detecting whether the target location is a correct location based on the target sacral evoked response signal and the decision tree model for identifying the implantation location, including: Stimulation is applied to the target point where the sacral nerve electrode to be detected is implanted, and a target sacral evoked response signal after the target point is stimulated is collected; data processing is performed on the target sacral evoked response signal to obtain target processed data; feature extraction is performed on the target processed data to obtain target data features; the target data features are input into the decision tree model for identifying the implantation point to obtain a detection result of whether the target point is a correct point.

5. A sacral nerve implantation point correctness assessment system, characterized in that: The system is configured to implement the method according to any one of claims 1 to 4, and the system comprises: Data acquisition module: used to collect the first sacral evoked response signal when the sacral nerve electrode is implanted in the correct location, and the second sacral evoked response signal when the sacral nerve electrode is not implanted in the correct location. Among them, the sacral evoked response includes the following two electrophysiological responses: neural response and electromyographic response. The neural response refers to the evoked compound action potential, which is the electrical signal recorded from the vicinity of the electrode when the nerve fiber is stimulated. The electromyographic response refers to the electrical signal generated by muscle activation and is the muscle contraction caused by nerve stimulation. A data processing module is configured to process the first sacral evoked response signal to obtain first processed data when the sacral nerve electrode is implanted in the correct location; and to process the second sacral evoked response signal to obtain second processed data when the sacral nerve electrode is not implanted in the correct location. A feature extraction module is configured to extract features from the first processed data to obtain first data features when the sacral nerve electrode is implanted in the correct location; and to extract features from the second processed data to obtain second data features when the sacral nerve electrode is not implanted in the correct location. a model construction module configured to take the first data feature as input and the correct implantation location of the sacral nerve electrode as output; and take the second data feature as input and the incorrect implantation location of the sacral nerve electrode as output; construct a decision tree model for identifying the implantation location, and complete model training; An evaluation module is used to collect a target sacral evoked response signal when the sacral nerve electrode to be tested is implanted at a target location, and detect whether the target location is a correct location based on the target sacral evoked response signal and the decision tree model for identifying the implantation location; The data processing method includes: data clipping and data preprocessing; The data clipping process is specifically as follows: Through the time window, the sacral evoked response signal within the preset time period after the stimulation is intercepted as the effective signal data, and the formula is: ； in, is the valid signal data, is the sacral evoked response signal, is the stimulation end time, is the start time of the preset time period, The end time of the preset time period. is the sampling rate; The data preprocessing process specifically includes: filtering the effective signal data; using the recursive least squares method to remove stimulation artifacts from the filtered data to obtain processed data; The first data feature includes the peak-to-peak amplitude, latency, and number of peaks in the first processed data; the second data feature includes the peak-to-peak amplitude, latency, and number of peaks in the second processed data; The peak-to-peak amplitude is the difference between the maximum positive peak and the maximum negative peak in the data following the maximum negative peak; The incubation period is the time delay from the start time of the preset time period to the appearance time of the maximum negative peak; The peak number is the number of peaks in the data after the maximum negative peak.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for assessing the correctness of sacral nerve implantation position according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium Computer instructions are stored, and the computer instructions are used to enable a processor to implement the sacral nerve implant point correctness assessment method according to any one of claims 1 to 4 when executed.

Images