An intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor

Abstract

The present application discloses an intra-bladder cavity and pelvic floor intelligent interactive electrical stimulation system, including: an electromyographic acquisition module, an intelligent diagnosis module, a display interaction module and an electrical stimulation module; through the intelligent diagnosis module, the original electromyographic signal sent by the electromyographic acquisition module is received and characteristic information is obtained, the characteristic information and a pre-configured intelligent fitting model are used to generate a first treatment plan, and the characteristic information and a pre-configured intelligent classification model are used to generate a classification result of abnormal bladder activity; when a change in the patient's bladder activity is identified, the dynamic switching from the first treatment mode to the second treatment mode is automatically completed; through the display interaction module, the first treatment plan and the second treatment plan are received and sent to the electrical stimulation module to apply electrical stimulation pulses. On the one hand, the present application can autonomously evaluate the patient's symptoms and dynamically switch the treatment mode to adopt the corresponding treatment plan, and on the other hand, it can reduce the burden on medical staff and effectively improve the accuracy and effect of treatment.

Description

Technical Field

[0001] The present application relates to the technical field of neural electrical stimulation, and in particular to an intelligent interactive electrical stimulation system for the bladder cavity and the pelvic floor. Background Art

[0002] Intravesical electrical stimulation is a treatment method that inserts a catheter with a stimulating electrode into the bladder, uses saline as a medium to stimulate the detrusor muscle, and induces the bladder to produce a sense of urination through the existing afferent nerve connection pathway between the detrusor muscle and the central nervous system, thereby increasing the outflow of nerve impulses, promoting urination or improving urine control. At present, this type of electrical stimulation therapy has been clinically proven to be an effective method for treating symptoms of underactive bladder (UAB). At the same time, it has been found in clinical practice that this method, in combination with other related accessories, can have a certain therapeutic effect on patients with overactive bladder (OAB) and some patients with multiple system atrophy (MSA) who present with detrusor hyperactivity and impaired contractility (DHIC).

[0003] However, due to the variety of different indications and individual changes in short-term urine dynamics, the original electrical stimulation treatment plan is difficult to achieve closed-loop regulation and precise control of electrical stimulation in the bladder cavity. Therefore, the existing plan needs to be adjusted in a timely manner to better cope with the individual differences of different patients. Summary of the invention

[0004] The embodiment of the present application provides an intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor, so as to achieve the technical effect of autonomously evaluating the patient's current clinical characteristic information, judging the patient's abnormal bladder symptoms, automatically realizing dynamic switching between different treatment modes, and timely adopting corresponding treatment plans, thereby improving the accuracy of the treatment plan and reducing the burden on doctors.

[0005] The present application embodiment adopts the following technical solutions:

[0006] Provided is a bladder cavity and pelvic floor intelligent interactive electrical stimulation system, the system comprising: an electromyographic acquisition module, an intelligent diagnosis module, a display interaction module and an electrical stimulation module, the electrical stimulation module comprising a first electrical stimulation unit and a second electrical stimulation unit, the electromyographic acquisition module being connected to the intelligent diagnosis module and the display interaction module, the electrical stimulation module being connected to the display interaction module, wherein the electromyographic acquisition module at least comprises a first patch electrode attached to the periphery of the anus, the first electrical stimulation unit comprises an electrode inserted into the bladder cavity, and the second electrical stimulation unit comprises a second patch electrode attached to the periphery of the anus; the intelligent diagnosis module is used to receive the original electromyographic signal acquired by the electromyographic acquisition module; based on the original electromyographic signal, a signal for characterizing the electromyographic activity of the bladder during underactive bladder and / or overactive bladder is obtained. Characteristic information of changes in electrical signals; using the characteristic information and a pre-configured intelligent fitting model to generate a first treatment plan, and using the characteristic information and a pre-configured intelligent classification model to generate a classification result of abnormal bladder activity; when changes in the patient's bladder activity are identified, automatically completing the dynamic switching from the first treatment mode to the second treatment mode, wherein the first treatment mode includes: when it is judged as a symptom of underactive bladder, based on the first treatment plan received or the second treatment plan input by the doctor, using electrodes inserted into the bladder cavity to apply corresponding electrical stimulation pulses; the second treatment mode includes: when it is judged as a symptom of overactive bladder, based on the first treatment plan received or the second treatment plan input by the doctor, using a second patch electrode attached to the periphery of the anus to apply corresponding electrical stimulation pulses.

[0007] Optionally, the display interaction module is used to receive the first treatment plan and send the first treatment plan to the electrical stimulation module to apply corresponding electrical stimulation pulses;

[0008] Alternatively, the display interaction module is also used to receive the second treatment plan input by the doctor based on the original electromyographic signal, the characteristic information and the classification result received by the display interaction module, and send the second treatment plan to the electrical stimulation module to apply corresponding electrical stimulation pulses.

[0009] Optionally, the system further comprises: a server module, the server module is connected to the display interaction module, the server module is used to construct an intelligent fitting model and / or an intelligent classification model, and send the trained intelligent fitting model and / or intelligent classification model to the display interaction module;

[0010] Among them, the intelligent fitting model and / or the intelligent classification model are obtained by using a training sample set and training through a machine learning algorithm, and the training data in the training sample set at least includes the following clinical collection data: the original electromyographic signal sent by the display interaction module and the characteristic information of the original electromyographic signal obtained by a preset processing algorithm.

[0011] Optionally, the server module is further used to filter the original electromyographic signals of normal people, the original electromyographic signals of OAB patients, the original electromyographic signals of UAB patients, and the original electromyographic signals of DHIC patients during the model training stage;

[0012] According to the preset processing algorithm, the characteristic information corresponding to the original electromyographic signal during active contraction and inactive contraction is obtained respectively as the input of the machine learning algorithm.

[0013] Optionally, the server module is also used to use the diagnosis results and optimal treatment plans made by the doctor based on each set of training data as the output of the machine learning algorithm during the model training stage, wherein the diagnosis results are used to train the intelligent classification model, and the optimal treatment plan is used to train the intelligent fitting model.

[0014] Optionally, the intelligent diagnosis module includes an intelligent classification model unit and an intelligent fitting model unit, and the display interaction module includes an algorithm configuration unit.

[0015] The algorithm configuration unit is used to select and adjust the model parameters of the intelligent classification model and the intelligent fitting model; send the intelligent classification model to the intelligent classification model unit, and send the intelligent fitting model to the intelligent fitting model unit to realize the model configuration of the intelligent diagnosis module.

[0016] Optionally, the display interaction module also includes a treatment plan configuration unit, which is used to receive a first treatment plan sent by the intelligent fitting model unit, and send the first treatment plan to the electrical stimulation module to apply corresponding electrical stimulation pulses; or, the treatment plan configuration unit is also used to receive and display the classification result sent by the intelligent classification model unit, and send the second treatment plan input by the doctor to the electrical stimulation module to apply corresponding electrical stimulation pulses.

[0017] Optionally, the intelligent diagnostic module is also used to filter and Fourier transform the original electromyographic signal to obtain characteristic information for characterizing the change of the electromyographic signal when the bladder is underactive and / or overactive; wherein the filtering process is used to extract the electromyographic signal in the 20Hz-500Hz frequency band of the original electromyographic signal, and calculate the instantaneous RMS value of the signal according to a preset sampling rate to perform window smoothing, and the RMS change curve after the window smoothing process is used to extract the characteristic information.

[0018] Optionally, the original electromyographic signal includes at least one of the following: an electromyographic signal of the patient's vagina, an electromyographic signal of the anal sphincter and anus periphery, and an electromyographic signal of the abdominal muscle surface.

[0019] Optionally, the first treatment plan and the second treatment plan include at least one of the following basic parameters: stimulation waveform, amplitude, pulse width, frequency, rising cycle, falling cycle, continuous cycle, treatment duration, variable frequency / constant frequency, high frequency, low frequency, voltage / current source.

[0020] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0021] First, the intelligent interactive electrical stimulation system for the bladder cavity and the pelvic floor of the embodiment of the present application receives the original electromyographic signal and obtains characteristic information for characterizing the change of the electromyographic signal through the intelligent diagnosis module, generates a first treatment plan using the characteristic information and a pre-configured intelligent fitting model, and generates a classification result of abnormal bladder activity using the characteristic information and a pre-configured intelligent classification model; when it is recognized that the patient's bladder activity has changed, it automatically completes the dynamic switching from the first treatment mode to the second treatment mode, which can not only autonomously evaluate the patient's current clinical characteristic information, realize the adaptive dynamic switching between the treatment modes of underactive bladder symptoms and overactive bladder symptoms, and take corresponding treatment plans in time, but also does not require doctors to monitor the patient's condition in real time, greatly reducing the burden on medical staff.

[0022] Second, the intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor of the embodiment of the present application receives the first treatment plan through the display interaction module, and sends the first treatment plan to the first electrical stimulation unit or the second electrical stimulation unit to apply corresponding electrical stimulation pulses, without the need for frequent manual adjustments, thereby effectively improving the treatment efficiency and effect.

[0023] Third, the intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor of the embodiment of the present application displays the interactive interface information through the display interaction module and receives the second treatment plan input by the doctor, so as to send the second treatment plan to the first electrical stimulation unit or the second electrical stimulation unit and apply corresponding electrical stimulation pulses, so that the doctor can make a comprehensive judgment and give a customized second treatment plan through the display interaction module, thereby improving the effectiveness and accuracy of the treatment.

[0024] Fourth, the intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor of the embodiment of the present application can output two treatment plans respectively by adopting an automatic adjustment mechanism and a semi-automatic adjustment mechanism. Therefore, it is possible to select a more appropriate treatment plan for treatment according to the dynamic switching of the treatment mode, making the treatment for different patients more intelligent, precise and personalized, further improving the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 It is a schematic diagram of the structure of the bladder cavity and pelvic floor intelligent interactive electrical stimulation system in the embodiment of the present application;

[0027] Figure 2 This is one of the waveform diagrams of urodynamic measurement with synchronous electromyography acquisition;

[0028] Figure 3 The second waveform diagram of urodynamic measurement with synchronous electromyography acquisition;

[0029] Figure 4 The third waveform diagram of urodynamic measurement with synchronous electromyography acquisition;

[0030] In the figure: 1. EMG acquisition module; 2. Intelligent diagnosis module; 3. Display interaction module; 4. Electrical stimulation module; 41. First electrical stimulation unit; 42. Second electrical stimulation unit; 5. Server module; 21. Intelligent classification model unit; 22. Intelligent fitting model unit; 31. Original signal unit; 32. EMG signal unit; 33. Feature information unit; 34. Algorithm configuration unit; 35. Treatment plan configuration unit. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0032] To facilitate understanding of the technical solution of the intelligent interactive electrical stimulation system for the bladder cavity and the pelvic floor of the embodiment of the present application, the technical principle of the embodiment of the present application is first explained.

[0033] Combination Figures 2 to 3 As shown, a schematic diagram of the waveform of urodynamic measurement under different conditions is provided; the horizontal axis in the figure represents time (min), and the vertical axis represents urine output (ml), urine flow rate (ml / s), bladder pressure (cmH2O), abdominal pressure (cmH2O), detrusor pressure (cmH2O), perfusion volume (ml), and electromyographic signal intensity (uV) from top to bottom.

[0034] refer to Figure 2 As shown in the figure, under normal circumstances, during the urine storage period, as the bladder capacity increases, the bladder pressure does not increase significantly or increases slightly, and the pelvic floor electromyographic signals recorded from the perianal area remain stable at a certain amplitude and do not change significantly; during the urination period, the detrusor muscle contracts autonomously, and the pelvic floor electromyographic signals recorded from the perianal area will be significantly weakened to allow urine to be discharged smoothly. Figure 3 and Figure 4 As shown in the figure, when patients have lower urinary tract dysfunction, they can be divided into the following two situations: In the first situation, during the storage period, the patient has uninhibited detrusor contraction, and the pelvic floor myoelectric signal recorded from the perianal area is synchronously enhanced, which is manifested as overactivity of the detrusor during the storage period. For details, please refer to Figure 3 As shown in the figure; In the second case, during the urination period, when the detrusor muscle contracts spontaneously, the pelvic floor electromyographic signal recorded from the anus is synchronously enhanced, resulting in the inability to discharge urine smoothly, manifested as dysuria. For details, please refer to Figure 4 shown.

[0035] Therefore, the technical concept of the present application is to utilize the correlation between pelvic floor electromyographic signals and detrusor muscle activity based on electromyographic feedback technology to collect and identify the intensity changes of the patient's pelvic floor electromyographic signals and their clinical characteristic information in real time. When it is identified that the patient's bladder activity has changed, the dynamic switching from the first treatment mode to the second treatment mode is automatically completed, that is, the dynamic switching of different treatment modes is automatically completed according to the changes in the patient's underactive bladder symptoms and overactive bladder symptoms; and by establishing an intelligent diagnostic model, the automatic adjustment and semi-automatic adjustment functions of the electrical stimulation system are realized, so as to output the automatically generated first treatment plan or the second treatment plan input by the doctor to the electrical stimulation module, thereby realizing closed-loop regulation and precise control of electromyographic signal acquisition and electrical stimulation in the bladder cavity, so as to achieve the technical effect of improving the accuracy of the treatment plan, enhancing the intelligence and flexibility of the system, and reducing the burden on doctors.

[0036] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0037] The present application embodiment provides a bladder cavity and pelvic floor intelligent interactive electrical stimulation system, such as Figure 1 As shown, a structural schematic diagram of an intelligent interactive electrical stimulation system for the bladder cavity and the pelvic floor is provided. The intelligent interactive electrical stimulation system for the bladder cavity and the pelvic floor in an embodiment of the present application includes: an electromyography acquisition module 1, an intelligent diagnosis module 2, a display interaction module 3 and an electrical stimulation module 4, wherein the electrical stimulation module 4 includes a first electrical stimulation unit 41 and a second electrical stimulation unit 42, wherein the electromyography acquisition module 1 is connected to the intelligent diagnosis module 2 and the display interaction module 3, and the electrical stimulation module 4 is connected to the display interaction module 3; wherein the electromyography acquisition module 1 includes at least a first patch electrode attached to the periphery of the anus, the first electrical stimulation unit includes an electrode inserted into the bladder cavity, and the second electrical stimulation unit includes a second patch electrode attached to the periphery of the anus; that is, the two electrodes attached to the periphery of the anus can be respectively set as an electrode with a signal acquisition function and a stimulation electrode, and an insertable stimulation electrode is also provided in the bladder; of course, the electrical stimulation module 4 of the present embodiment can also include stimulation electrodes arranged at other positions, so as to apply electrical stimulation pulses at different positions according to different symptoms of the patient, which is not limited here.

[0038] The intelligent diagnosis module 2 is used to receive the original electromyographic signal collected by the electromyographic acquisition module 1; obtain characteristic information for characterizing the change of the electromyographic signal when the bladder is underactive and / or overactive according to the original electromyographic signal; generate a first treatment plan using the characteristic information and a pre-configured intelligent fitting model, and generate a classification result of abnormal bladder activity using the characteristic information and a pre-configured intelligent classification model;

[0039] When changes in the patient's bladder activity are identified, the intelligent diagnosis module 2 can automatically complete the dynamic switching from the first treatment mode to the second treatment mode, wherein the first treatment mode includes: when it is judged to be a symptom of underactive bladder, based on the first treatment plan received or the second treatment plan input by the doctor, using electrodes inserted into the bladder cavity to apply corresponding electrical stimulation pulses; the second treatment mode includes: when it is judged to be a symptom of overactive bladder, based on the first treatment plan received or the second treatment plan input by the doctor, using a second patch electrode attached to the periphery of the anus to apply corresponding electrical stimulation pulses.

[0040] Specifically, this embodiment can realize dynamic switching of two treatment modes according to the change of the patient's bladder activity. For example, when it is determined through the intelligent diagnosis module 2 that the patient exhibits symptoms of underactive bladder, the first treatment mode can be adopted, that is, electrical stimulation treatment can be performed by inserting electrodes into the patient's bladder. When it is identified that the patient's electromyographic activity has changed (for example, electromyographic signal enhancement, characteristic information change, etc.), it is considered that the patient has changed from the current underactive bladder symptoms to overactive bladder symptoms. At this time, it is necessary to automatically switch the treatment mode, that is, adopt the second treatment mode, turn off the electrical stimulation pulse of the electrode inserted into the bladder cavity, and turn on the second patch electrode attached to the periphery of the anus of the patient to apply the corresponding electrical stimulation pulse; thereafter, when the patient's electromyographic activity changes again (for example, returns to the original signal state), it is considered that the patient has changed from overactive bladder symptoms to underactive bladder symptoms. At this time, it is necessary to adopt the first treatment mode again, turn off the second patch electrode attached to the periphery of the anus, and turn on the electrode inserted into the bladder cavity and apply the corresponding electrical stimulation pulse; thereby realizing the dynamic switching between the two different treatment modes for underactive bladder symptoms and overactive bladder symptoms, and improving the level of intelligent and precise treatment.

[0041] It can be seen that, different from the technical solution in the prior art that uses ultrasonic technology to monitor bladder pressure and volume to apply electrical stimulation pulses and cannot achieve dynamic switching, the bladder cavity and pelvic floor intelligent interactive electrical stimulation system of the embodiment of the present application can collect the patient's original electromyographic signals in real time and process and identify them, autonomously evaluate and monitor the patient's current clinical characteristic information, and automatically complete the dynamic switching from the first treatment mode to the second treatment mode when it is identified that the patient's bladder activity has changed, and then timely adopt targeted treatment plans to achieve precise treatment. In this way, closed-loop regulation and precise control between electromyographic signal acquisition and electrical stimulation modules can be achieved, effectively improving treatment efficiency and treatment effects, and making the treatment of different patients more intelligent and personalized, greatly reducing the burden on doctors.

[0042] In some embodiments, the display interaction module 3 is used to receive the first treatment plan and send the first treatment plan to the first electrical stimulation unit 41 or the second electrical stimulation unit 42 to apply corresponding electrical stimulation pulses; or, the display interaction module 3 is also used to receive a second treatment plan input by a doctor based on the received original electromyographic signal, the characteristic information and the classification result, and send the second treatment plan to the first electrical stimulation unit 41 or the second electrical stimulation unit 42 to apply corresponding electrical stimulation pulses.

[0043] The treatment plans in the embodiments of the present application can be specifically divided into two types. The first treatment plan, also known as the fully automatic adjustment plan, means that the intelligent diagnosis module 2 can use the characteristic information and the pre-configured intelligent fitting model to automatically generate a first treatment plan, and send the first treatment plan to the display interaction module 3. Thereafter, the treatment plan configuration unit 35 of the display interaction module 3 sends the first treatment plan to the first electrical stimulation unit 41 or the second electrical stimulation unit 42 to apply corresponding electrical stimulation pulses. That is to say, when the patient exhibits symptoms of underactive bladder, the first treatment mode is adopted, the first treatment plan is sent to the first electrical stimulation unit 41, and the corresponding electrical stimulation pulses are applied using electrodes inserted into the bladder cavity; when the patient exhibits symptoms of overactive bladder, the second treatment mode is adopted, the first treatment plan is sent to the second electrical stimulation unit 42, and the corresponding electrical stimulation pulses are applied using the second patch electrode attached to the periphery of the anus.

[0044] The second treatment plan, i.e., the semi-automatic adjustment plan, is to generate classification results related to abnormal bladder activity of the patient through the intelligent diagnosis module 2, such as overactive bladder (OAB symptoms), underactive bladder (UAB symptoms), or detrusor hyperactivity and impaired contractility. The intelligent diagnosis module 2 classifies various urinary tract dysfunction symptoms such as underactive bladder, urinary tract dysfunction symptoms such as urinary tract contractility, DHIC symptoms, and sends the original electromyographic signal, characteristic information and classification results to the display interaction module 3. The doctor makes a comprehensive judgment based on the information displayed by the display interaction module 3 and gives a second treatment plan. Then, the treatment plan configuration unit 35 of the display interaction module 3 sends the second treatment plan to the first electrical stimulation unit 41 or the second electrical stimulation unit 42 to apply corresponding electrical stimulation pulses; that is, when the patient shows symptoms of underactive bladder, the first treatment mode is adopted, the second treatment plan is sent to the first electrical stimulation unit 41, and the corresponding electrical stimulation pulses are applied by the electrodes inserted into the bladder cavity; when the patient shows symptoms of overactive bladder, the second treatment mode is adopted, the second treatment plan is sent to the second electrical stimulation unit 42, and the corresponding electrical stimulation pulses are applied by the second patch electrode attached to the periphery of the anus.

[0045] It can be understood that the difference between the two treatment plans is that the treatment parameters of the first treatment plan are automatically generated by the system, while the treatment parameters of the second treatment plan are manually input by the doctor. At the same time, the first treatment plan and the second treatment plan both contain relevant symptom treatment parameters of the first treatment mode and the second treatment mode. Therefore, when generating the first treatment plan, there is no need for the doctor to participate and make decisions. The bladder cavity and pelvic floor intelligent interactive electrical stimulation system can automatically monitor and analyze the patient's electromyographic signals, complete the dynamic switching between treatment modes, and automatically output the treatment parameters to ensure that the system outputs the best first treatment plan. The second treatment plan depends to a certain extent on the doctor's intervention and decision-making. The bladder cavity and pelvic floor intelligent interactive electrical stimulation system can automatically monitor and analyze the patient's electromyographic signals and automatically output the diagnosis results, complete the dynamic switching between treatment modes, but when outputting the treatment parameters, the doctor still needs to make a comprehensive judgment through the displayed information. Of course, no matter which treatment plan is adopted, its core goal is to improve the intelligence and personalization level of the entire system, thereby reducing the burden on medical staff, improving treatment capabilities and treatment effects.

[0046] Of course, the above descriptions about the two treatment modes and the two treatment plans are only exemplary embodiments and cannot be understood as limitations on the present application. Relevant technical personnel in this field may also combine the above two treatment plans according to specific usage scenarios, or improve them; for example, pre-store the treatment parameters entered by the doctor in the intelligent classification model to directly output the second treatment plan when used offline or the doctor is not present, that is, directly output the pre-stored standardized treatment plan; for example, after the intelligent fitting model automatically outputs the first treatment plan, the doctor fine-tunes the first treatment plan, etc., which will not be elaborated here.

[0047] It should be noted that the technical solution of this application is particularly suitable for monitoring, symptom identification, evaluation and treatment of UAB patients (patients with underactive bladder), OAB patients (patients with overactive bladder), and DHIC patients (patients with overactive detrusor with impaired contractility); it can be understood that DHIC patients refer to patients with both OAB symptoms and UAB symptoms. The clinical characteristics of DHIC patients are mainly detrusor overactivity during the storage period, causing frequent urination, urgency and urge incontinence, and weak detrusor contraction during the urination period, resulting in increased residual urine volume. Of course, the technical solution of this application can also be extended to the monitoring and treatment of other urinary tract dysfunction symptoms, which are not limited here.

[0048] In some embodiments, the original electromyographic signal may specifically include at least one of the electromyographic signals of the patient's vagina, anal sphincter, anal periphery, and abdominal muscle surface, that is, electromyographic acquisition units are respectively set at the patient's vagina, anal sphincter, anal periphery, and abdominal muscle surface and perform signal acquisition. Preferably, the original electromyographic signal is divided into active contraction electromyographic signal and inactive contraction electromyographic signal, that is, electromyographic signal collected during active contraction period and electromyographic signal collected during inactive contraction period; active contraction period refers to the electromyographic signal characteristics of the pelvic floor muscle contraction collected at the above-mentioned different parts of the patient under the guidance and command of the doctor, and inactive contraction period refers to the electromyographic signal characteristics of the pelvic floor muscle collected at the above-mentioned different parts of the patient during the urination cycle. Further, active contraction electromyographic signals are divided into electromyographic signals of four different periods, namely, resting period, fast muscle contraction, slow muscle continuous contraction (5~10 seconds) and slow muscle endurance contraction (60 seconds). It can be seen that by collecting the original electromyographic signals during the above periods, the accuracy and precision of the system signal recognition and judgment are further improved.

[0049] In some embodiments, the intelligent diagnostic module 2 is also used to filter and Fourier transform the original electromyographic signal to obtain characteristic information for characterizing the change of the electromyographic signal during underactive bladder and / or overactive bladder; wherein the filtering process is used to extract the electromyographic signal in the 20Hz-500Hz frequency band of the original electromyographic signal, and calculate the instantaneous RMS value of the signal according to a preset sampling rate for window smoothing, and the RMS change curve after window smoothing is used to extract the characteristic information.

[0050] Specifically, in this embodiment, the characteristic information of the electromyographic signal during the active contraction period includes, but is not limited to, the average value of the electromyographic signal during the resting period, the maximum value of the electromyographic signal of the fast muscle contraction, the contraction time and the average rate of change, the relaxation time and the average rate of change, the mean and the normalized mean square error of the electromyographic signal of the slow muscle continuous contraction, the overall mean value of the electromyographic signal of the slow muscle endurance contraction, the normalized mean square error and the average value of the last 20 seconds, etc. The average rate of change is the average slope from the contraction start point to the contraction peak signal. The characteristic information of the electromyographic signal during the non-active contraction period includes, but is not limited to, the rise time, the maximum value, the fall time and the average value of the resting stage, the surface electromyographic mean value of the abdominal muscles, the electromyographic change rate, etc.

[0051] It can be seen from the above that the original electromyographic signal and its characteristic information of the embodiment of the present application can characterize the abnormal bladder activity to a certain extent. That is to say, by processing the original electromyographic signal, characteristic information that can characterize the changes in the electromyographic signal during underactive bladder (UAB) and / or overactive bladder (OAB) can be obtained, thereby realizing accurate identification and autonomous assessment of the patient's symptoms; for example, when collecting the electromyographic signal around the patient's anus, if the electromyographic signal collected during the urine storage period is enhanced for a certain period of time, it means that detrusor overactivity has occurred; on the contrary, if the electromyographic signal collected during the urination period is not significantly reduced compared with that before urination, it means that the detrusor contraction is weak or the detrusor contraction force is low.

[0052] Of course, the above content about the original electromyographic signal and its characteristic information is only for the convenience of understanding and simplified description, and cannot be regarded as a limitation of the present application.

[0053] In some embodiments of the present application, the system also includes: a server module 5, which is connected to the display interaction module 3, and the server module 5 is used to construct an intelligent fitting model and / or an intelligent classification model, and send the trained intelligent fitting model and / or intelligent classification model to the display interaction module 3; wherein the intelligent fitting model and / or the intelligent classification model is obtained by using a training sample set and training through a machine learning algorithm, and the training data in the training sample set includes at least the following clinical collection data: the original electromyographic signal sent by the display interaction module and the characteristic information of the original electromyographic signal obtained by a preset processing algorithm.

[0054] Specifically, the server module 5 in this embodiment can not only receive the original electromyographic signal sent by the display interaction module 3, extract the characteristic information of the original electromyographic signal and form a training sample set to train the intelligent fitting model and the intelligent classification model respectively, but also send the constructed intelligent fitting model and intelligent classification model to the display interaction module 3. Furthermore, the intelligent classification model and the intelligent fitting model are both based on machine learning algorithms and are trained using clinically collected data as training sample sets. The machine learning algorithm model can adopt a neural network model, or other models such as a Bayesian polynomial fitting model, which are not limited here.

[0055] In some embodiments of the present application, the server module 5 is also used to filter the original electromyographic signals of normal people, the original electromyographic signals of OAB patients, the original electromyographic signals of UAB patients, and the original electromyographic signals of DHIC patients during the model training stage; according to a preset processing algorithm, characteristic information corresponding to the original electromyographic signals during active contraction and inactive contraction is obtained respectively, as input to the machine learning algorithm.

[0056] Specifically, during the model training and construction process, the original electromyographic signals can also be divided into active contraction electromyographic signals and inactive contraction electromyographic signals. At the same time, the data dimensions of the electromyographic signals and their characteristic information in the model training stage are the same as the data dimensions of the signals and the characteristic information obtained by processing in the aforementioned intelligent diagnosis module 2, which will not be repeated here.

[0057] For example, the peak value and average RMS value of the electromyographic signal can be used as reference values ​​during the inactive contraction period; for another example, taking the active contraction period as a reference, when the peak value or RMS value of the inactive contraction period reaches 50% of the active contraction period, it can be considered that the patient has symptoms such as detrusor contraction, and then the characteristic information during the active contraction period and the inactive contraction period can be used to judge different symptoms. Of course, the above content about the active contraction period and the inactive contraction period is only an exemplary description, and the specific values ​​such as the reference value and the threshold value need to be set and adjusted according to the actual situation of the patient, and there is no limitation here.

[0058] In some embodiments of the present application, the server module 5 is also used to use the diagnosis results and optimal treatment plans made by the doctor based on each set of training data as the output of the machine learning algorithm during the model training stage, wherein the diagnosis results are used to train the intelligent classification model, and the optimal treatment plan is used to train the intelligent fitting model.

[0059] It can be understood that the inputs of the intelligent classification model and the intelligent fitting model can be the same, that is, both can use the patient's clinical collection data as a training sample set. For example, the training sample set can contain information such as the amplitude of the change of the electromyographic signal, the electromyographic intensity, the electromyographic frequency, and the discharge time. However, the output results of the intelligent classification model and the intelligent fitting model are different. The intelligent classification model outputs a diagnosis result with a classification label, which is to classify the different symptoms of the patient, while the intelligent fitting model outputs a treatment plan with treatment parameters. Specifically, the diagnosis result and the best treatment plan given by the doctor according to each sample situation need to be used as the output of the machine learning algorithm, that is, the diagnosis result is used to train the intelligent classification model, and the best treatment plan is used to train the intelligent fitting model. Preferably, the diagnosis result includes asymptomatic, OAB symptoms and / or UAB symptoms, and the best treatment plan includes relevant content such as electrode selection and the numerical value of the electrical stimulation treatment parameters.

[0060] For example, when it is determined to be an OAB symptom, the second patch electrode attached to the periphery of the anus can be used for electrical stimulation therapy; when it is determined to be a UAB symptom, the electrode inserted into the bladder cavity can be used for electrical stimulation therapy; when it is determined to be a DHIC symptom (both OAB symptoms and UAB symptoms), the first treatment mode can be dynamically switched to the second treatment mode according to the changes in the patient's bladder activity, and then the electrode in the bladder cavity or the second patch electrode attached to the periphery of the anus can be used for electrical stimulation therapy, and there is no restriction here. Of course, the data dimensions of the diagnosis results or the best treatment plan output in the model training stage are the same as the data dimensions of the classification results output in the intelligent diagnosis module 2, the first treatment plan, and the second treatment plan input by the doctor, and will not be repeated here.

[0061] In some embodiments of the present application, the intelligent diagnosis module 2 includes an intelligent classification model unit 21 and an intelligent fitting model unit 22, and the display interaction module 3 includes an algorithm configuration unit 34, and the algorithm configuration unit 34 is used to select and adjust the model parameters of the intelligent classification model and the intelligent fitting model; send the intelligent classification model to the intelligent classification model unit 21, and send the intelligent fitting model to the intelligent fitting model unit 22, so as to realize the model configuration of the intelligent diagnosis module 2.

[0062] In some embodiments, the display interaction module 3 further includes an original signal unit 31, an electromyographic signal unit 32, and a characteristic information unit 33. The original signal unit 31 is used to display the signal graph of the original electromyographic signal collected by the electromyographic acquisition module 1; the electromyographic signal unit 32 is used to display and mark the time domain and frequency domain graphs of the original electromyographic signal after filtering; the characteristic information unit 33 is used to display the characteristic information extracted from the original electromyographic signal, including but not limited to the rise time, maximum value and fall time of the electromyographic signal during active contraction and inactive contraction, the average value of the resting stage, the mean value of the surface electromyography of the abdominal muscles, and the rate of change of these values. The algorithm configuration unit 34 is used to send the intelligent fitting model and / or the intelligent classification model to the intelligent diagnosis module 2, that is, the user can select which model to use through the algorithm configuration unit 34, and adjust the model-related parameters according to the actual situation displayed, so that the intelligent diagnosis module 2 can obtain the intelligent fitting model and / or intelligent classification model configured by the display interaction module 3.

[0063] In some embodiments, the display interaction module 3 also includes a treatment plan configuration unit 35, which is used to receive a first treatment plan sent by the intelligent fitting model unit 22, and send the first treatment plan to the electrical stimulation module 4 to apply a corresponding electrical stimulation pulse; or, the treatment plan configuration unit 35 is also used to receive and display the classification result sent by the intelligent classification model unit 21, and send the second treatment plan input by the doctor to the electrical stimulation module 4 to apply a corresponding electrical stimulation pulse.

[0064] Specifically, the treatment plan configuration unit 35 can receive the first treatment plan transmitted by the intelligent fitting model unit 22. The doctor can also fine-tune the first treatment plan through the treatment plan configuration unit 35 and then transmit it to the electrical stimulation module 4 for treatment. For example, the doctor can make fine adjustments based on the strength and changes of the electromyographic signal and the differences in the characteristic information. At the same time, the treatment plan configuration unit 35 can also receive the second treatment plan input by the doctor, that is, the treatment plan configuration unit 35 is used to display the classification results transmitted by the intelligent diagnosis module 2. After that, the doctor comprehensively determines and inputs the second treatment plan based on the original electromyographic signal, characteristic information, and classification results, and outputs the second treatment plan to the electrical stimulation module 4.

[0065] In some preferred embodiments, the first treatment plan and the second treatment plan include at least one of the following basic parameters: stimulation waveform, amplitude, pulse width, frequency, rising cycle, falling cycle, continuous cycle, treatment duration, variable frequency / constant frequency, high frequency, low frequency, voltage / current source. Thus, the user can adjust the basic parameters and select a suitable treatment plan for treatment, and has the ability of precise personalized treatment. Regardless of which treatment mode is adopted, the intelligent treatment is realized, reducing the burden on medical staff.

[0066] In some embodiments of the present application, the electrical stimulation module 4 is used to receive the first treatment plan and / or the second treatment plan sent by the display interaction module 3, and apply corresponding electrical stimulation pulses according to the first treatment plan and / or the second treatment plan.

[0067] Preferably, in the first treatment mode, the first stimulation unit 41 is used to apply corresponding electrical stimulation pulses using electrodes inserted into the bladder cavity based on the received first treatment plan or the second treatment plan when it is judged as underactive bladder symptoms (UAB symptoms); in the second treatment mode, the second electrical stimulation unit 42 is used to apply corresponding electrical stimulation pulses using a second patch electrode attached to the periphery of the anus when it is judged as overactive bladder symptoms (OAB symptoms) based on the received first treatment plan or the second treatment plan; of course, when it is judged as detrusor overactivity with impaired contractility (DHIC symptoms), dynamic switching from the first treatment mode to the second treatment mode can be automatically achieved according to changes in the patient's bladder activity, and then electrical stimulation treatment can be performed using electrodes in the bladder cavity or second patch electrodes attached to the periphery of the anus, and there is no limitation here.

[0068] It should be noted that the myoelectric acquisition module 1 and the electrical stimulation module 4 use a universal interface, which can be connected to vaginal, rectal, body surface, anal peripheral patch electrodes and bladder cavity electrodes, so that doctors can arbitrarily combine the myoelectric acquisition module 1 and the electrical stimulation module 4 according to actual needs, which will not be described in detail here. Of course, the above content about the connection, combination, number and stimulation position of the electrodes is only an exemplary description and cannot be understood as a limitation of this application.

[0069] In summary, this application has achieved at least the following technical effects:

[0070] First, the bladder cavity and pelvic floor intelligent interactive electrical stimulation system of the embodiment of the present application can autonomously evaluate the patient's current clinical characteristic information by collecting the patient's original electromyographic signal and processing and identifying it, realize adaptive dynamic switching between the treatment modes of underactive bladder symptoms and overactive bladder symptoms, and take corresponding treatment plans in time. The system does not require doctors to monitor the patient's status in real time, which greatly reduces the burden on doctors.

[0071] Second, the intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor of the embodiment of the present application directly outputs the first treatment plan by adopting an intelligent fitting model, and transmits it to the electrical stimulation module through the display interaction module; by automatically generating the first treatment plan for electrical stimulation, there is no need for frequent manual adjustments, which effectively improves the treatment efficiency and treatment effect.

[0072] Third, the intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor of the embodiment of the present application obtains corresponding classification results based on the intelligent classification model and the characteristic information characterizing bladder activity. The doctor makes a comprehensive judgment and gives a second treatment plan by displaying the original electromyographic signals, characteristic information, and classification results displayed by the interactive module, thereby being able to perform electrical stimulation therapy more effectively and accurately.

[0073] Fourth, the bladder cavity and pelvic floor intelligent interactive electrical stimulation system of the embodiment of the present application adopts two methods to obtain two treatment plans, and can select the appropriate treatment plan for treatment according to the dynamic switching of the treatment mode, and has the ability of more precise and personalized treatment. No matter which treatment method is adopted, intelligent treatment is realized, reducing the burden on medical staff.

[0074] It should be noted that in this application, unless otherwise clearly specified and limited, the terms such as "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or communication with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0075] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0076] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An intelligent interactive electrical stimulation system for the bladder cavity and pelvic floor, wherein: The system comprises: an electromyographic acquisition module, an intelligent diagnosis module, a display interaction module and an electrical stimulation module, wherein the electrical stimulation module comprises a first electrical stimulation unit and a second electrical stimulation unit, the electromyographic acquisition module is connected to the intelligent diagnosis module and the display interaction module, and the electrical stimulation module is connected to the display interaction module, wherein the electromyographic acquisition module comprises at least a first patch electrode attached to the periphery of the anus, the first electrical stimulation unit comprises an electrode inserted into the bladder cavity, and the second electrical stimulation unit comprises a second patch electrode attached to the periphery of the anus; The intelligent diagnosis module is used to Receiving the original electromyographic signal collected by the electromyographic acquisition module; According to the original electromyographic signal, characteristic information for characterizing changes in the electromyographic signal when the bladder is underactive and / or overactive; generating a first treatment plan using the feature information and a preconfigured intelligent fitting model, and generating a classification result of abnormal bladder activity using the feature information and a preconfigured intelligent classification model; When changes in the patient's bladder activity are detected, the dynamic switch from the first treatment mode to the second treatment mode is automatically completed, wherein: The first treatment mode includes: when it is determined to be a symptom of underactive bladder, based on the first treatment plan received or the second treatment plan input by the doctor, applying corresponding electrical stimulation pulses using electrodes inserted into the bladder cavity; The second treatment mode includes: when it is determined to be an overactive bladder symptom, based on the first treatment plan received or the second treatment plan input by the doctor, using a second patch electrode attached to the periphery of the anus to apply a corresponding electrical stimulation pulse; The intelligent diagnosis module is also used to When it is determined that the patient exhibits symptoms of underactive bladder, the first treatment mode is used to perform electrical stimulation treatment through electrodes inserted into the patient's bladder; When it is identified that the patient's electromyographic activity has changed, it is considered that the patient's current underactive bladder symptoms have changed to overactive bladder symptoms, and the second treatment mode is automatically switched to use, the electrical stimulation pulse of the electrode inserted into the bladder cavity is turned off, and the second patch electrode attached to the patient's anus is turned on to apply the corresponding electrical stimulation pulse; When the patient's electromyographic activity changes again, it is considered that the patient has changed from overactive bladder symptoms to underactive bladder symptoms. At this time, the first treatment mode is automatically switched again, the second patch electrode attached to the periphery of the anus is turned off, and the electrode inserted into the bladder cavity is turned on to apply the corresponding electrical stimulation pulse.

2. The system of claim 1, wherein: The display interaction module is used to receiving the first treatment plan, and sending the first treatment plan to the electrical stimulation module to apply corresponding electrical stimulation pulses; Alternatively, the display interaction module is also used to Based on the original electromyographic signal, the characteristic information and the classification result received by the display interaction module, the second treatment plan input by the doctor is received, and the second treatment plan is sent to the electrical stimulation module to apply corresponding electrical stimulation pulses.

3. The system of claim 1, wherein: The system further comprises: a server module, the server module being connected to the display interaction module, the server module being used to Constructing an intelligent fitting model and / or an intelligent classification model, and sending the trained intelligent fitting model and / or intelligent classification model to the display interaction module; Among them, the intelligent fitting model and / or the intelligent classification model are obtained by using a training sample set and training through a machine learning algorithm, and the training data in the training sample set at least includes the following clinical collection data: the original electromyographic signal sent by the display interaction module and the characteristic information of the original electromyographic signal obtained by a preset processing algorithm.

4. The system of claim 3, wherein: The server module is also used to In the model training stage, the original electromyographic signals of normal people, the original electromyographic signals of OAB patients, the original electromyographic signals of UAB patients, and the original electromyographic signals of DHIC patients are filtered; According to the preset processing algorithm, the characteristic information corresponding to the original electromyographic signal during active contraction and inactive contraction is obtained respectively as the input of the machine learning algorithm.

5. The system of claim 4, wherein: The server module is also used to During the model training phase, the diagnosis results and optimal treatment plans made by the doctor based on each set of training data are used as the output of the machine learning algorithm, where the diagnosis results are used to train the intelligent classification model, and the optimal treatment plan is used to train the intelligent fitting model.

6. The system of claim 1, wherein: The intelligent diagnosis module includes an intelligent classification model unit and an intelligent fitting model unit, and the display interaction module includes an algorithm configuration unit. The algorithm configuration unit is used to Selecting and adjusting model parameters of the intelligent classification model and the intelligent fitting model; The intelligent classification model is sent to the intelligent classification model unit, and the intelligent fitting model is sent to the intelligent fitting model unit to implement the model configuration of the intelligent diagnosis module.

7. The system of claim 6, wherein: The display interaction module also includes a treatment plan configuration unit, which is used to receiving a first treatment plan sent by the intelligent fitting model unit, and sending the first treatment plan to the electrical stimulation module to apply a corresponding electrical stimulation pulse; Alternatively, the treatment plan configuration unit is further configured to The classification result sent by the intelligent classification model unit is received and displayed, and the second treatment plan input by the doctor is sent to the electrical stimulation module to apply corresponding electrical stimulation pulses.

8. The system of claim 1, wherein: The intelligent diagnosis module is also used to Performing filtering and Fourier transform processing on the original electromyographic signal to obtain characteristic information for characterizing changes in the electromyographic signal when the bladder is underactive and / or overactive; The filtering process is used to extract the electromyographic signal in the frequency band of 20Hz-500Hz from the original electromyographic signal, and calculate the instantaneous RMS value of the signal according to the preset sampling rate to perform window smoothing processing, and the RMS change curve after the window smoothing processing is used to extract the characteristic information.

9. The system of claim 1, wherein: The original electromyographic signal includes at least one of the following: an electromyographic signal of the patient's vagina, an electromyographic signal of the anal sphincter and anus periphery, and an electromyographic signal of the abdominal muscle surface.

10. The system of claim 1, wherein: The first treatment plan and the second treatment plan include at least one of the following basic parameters: stimulation waveform, amplitude, pulse width, frequency, rising cycle, falling cycle, continuous cycle, treatment duration, variable frequency / constant frequency, high frequency, low frequency, voltage / current source.

Images