A pelvic floor muscle early screening training method based on data analysis

Abstract

The application discloses a pelvic floor muscle early screening training method based on data analysis, which comprises the following steps: a user completes a specified rating action, and surface electromyography (SEMG) data is acquired; raw data of the surface electromyography signal is processed first, evaluation indexes of the electromyography signal are calculated, index information is acquired in the time domain, and the index information comprises a mean absolute value (MAV), a root mean square (RMS), a maximum peak time (t1) and an integral electromyography value (iEMG); secondly, fast Fourier transform is performed on the signal to obtain frequency domain related information, and the related information comprises a median frequency (MF) and an average power frequency (MPF); the acquired signal indexes are compared with expected indexes, and screening is performed; a pelvic floor muscle state report is generated according to comparison with preset values through a rating result; and data is uploaded to the cloud to generate a data set. The application has the technical characteristics that subjectivity and uncertainty possibly existing in a traditional evaluation method can be avoided, and the real function state of the pelvic floor muscle can be comprehensively reflected.

Description

TECHNICAL FIELD

[0001] The application relates to a pelvic floor muscle early screening training method, in particular to a pelvic floor muscle early screening training method based on data analysis, and belongs to the medical system field. BACKGROUND

[0002] As an important supporting structure of pelvic organs, the pelvic floor muscle is like an invisible "elastic net" that holds the bladder, uterus, rectum and other organs firmly and maintains their normal position and physiological function. However, under the influence of many factors in modern life, the problem of pelvic floor muscle dysfunction is becoming more and more common. Postpartum women go through the "ordeal" of pregnancy and childbirth, and the pelvic floor muscle is subjected to great traction and damage; as the body ages, the muscle elasticity decreases and the fascia relaxes, and the pelvic floor muscle function gradually degenerates; people who sit for a long time, are obese or engage in high-intensity physical labor, the pelvic floor muscle is under long-term pressure and overfatigue, and they also face the risk of pelvic floor muscle function impairment.

[0003] Early and accurate screening of the pelvic floor muscle function state and the matching of scientific and effective training methods are key measures to prevent and treat pelvic floor muscle dysfunction and improve the quality of life of patients. The pelvic floor muscle early screening system and training method based on data analysis emerge as the times require, which integrates advanced sensing technology, complex data processing algorithms and professional medical knowledge to open up a new path for pelvic floor muscle health management.

[0004] Currently, there are mainly two ways for the main pelvic floor muscle evaluation scheme: one is the traditional way of relying solely on the observation of doctors, which feels the movement of the pelvic floor muscle by fingers, and grades the muscle strength according to the contraction state of the muscle. The other is to use the Glazer scheme, which requires the patient to complete the specified action according to the doctor's instructions, and analyzes and grades the muscle electrical signals taken by the pelvic floor muscle during the movement. Patent application publication No. CN117275667A discloses a pelvic floor muscle fatigue degree optimization training system and method based on big data, which comprises a reading module, a data recognition module, a data calculation module, a decision processing module, a scheme adjustment module and a log recording module. The application obtains the template data of the contraction stage according to the component information by reading the scheme data, judges the abdominal muscle detection function, collects the pelvic floor muscle electromyographic signal and abdominal muscle electromyographic signal of the patient through the vaginal electrode and processes them to obtain the corresponding pelvic floor muscle data and abdominal muscle data, judges whether the pelvic floor muscle is in a fatigue state according to the template data of the contraction stage, the pelvic floor muscle data and the abdominal muscle data, processes the subsequent training scheme data according to the judgment of the pelvic floor muscle fatigue state, so that the training scheme data of the patient reaches the template value, and finally records and saves the data flow in the whole process one by one. However, the evaluation of the pelvic floor muscle often depends not only on the fatigue evaluation index, but also on more comprehensive evaluation. SUMMARY

[0005] In order to solve the above prior art problems, the application provides a pelvic floor muscle early screening training method based on data analysis, which has the technical characteristics of being able to avoid the subjectivity and uncertainty that may exist in the traditional evaluation method and being able to comprehensively reflect the real functional state of the pelvic floor muscle.

[0006] In order to achieve the above-mentioned purpose, the application is realized by the following technical scheme:

[0007] The application is a pelvic floor muscle early screening training method based on data analysis, which comprises the following steps:

[0008] Step a: the user uses the connected pelvic floor muscle non-invasive detection equipment to complete the specified rating action, and obtains the real-time value of the surface pelvic floor muscle surface electromyography (SEMG) in the action process;

[0009] Step b: the original data of the surface electromyography signal is first processed, the evaluation index of the electromyography signal is calculated, the index information is obtained in the time domain, the index information includes the mean absolute value MAV, the root mean square RMS, the maximum peak time t1 and the integral electromyography value iEMG, and secondly, the signal is subjected to fast Fourier transform to obtain the frequency domain related information, the related information includes the median frequency MF and the average power frequency MPF;

[0010] Step c: the obtained signal index is compared with the expected index, and multi-aspect screening is performed, including muscle strength, muscle endurance, reaction speed, coordination and fatigue;

[0011] Step d: according to the comparison with the preset value, the pelvic floor muscle state report is produced through the rating result; if an abnormality occurs, the targeted recovery training guidance is performed according to the comparison between the signal index and the expected index;

[0012] Step e: upload the data to the cloud to generate a data set, so as to facilitate the user to more accurately realize the pelvic floor muscle early screening training based on data analysis.

[0013] Preferably, the pelvic floor muscle non-invasive detection equipment comprises a signal acquisition module, a signal processing module, a signal detection and judgment module, a report generation module and a data storage module connected in communication, the signal processing module comprises a signal amplifier, the signal acquisition module comprises disposable gel electrodes, the signal amplifier is connected with nine disposable gel electrodes, and the nine electrodes are divided into three groups, each group comprising one positive electrode, one negative electrode and one reference electrode.

[0014] Preferably, the specified rating action in step a includes a rapid contraction action, a slow and continuous contraction action and an intermittent contraction action; the user collects the signal under the guidance of a professional medical staff when completing the specified action using the original equipment;

[0015] Among them, the rapid contraction action requires the user to tighten the pelvic floor muscle to the maximum contraction in an instant, lasting about 3-5 seconds, just like simulating the emergency response of the pelvic floor muscle in the sudden cough and sneeze scene in daily life, thereby capturing the high-intensity electromyographic signal corresponding to the instantaneous explosive force of the muscle, and accurately evaluating the nerve conduction velocity and rapid activation ability of the pelvic floor muscle;

[0016] The slow sustained contraction action requires the user to gradually exert force, and gradually reach the maximum contraction degree for 5-10 seconds, and then maintain for 10-15 seconds, which is similar to the working state of the pelvic floor muscle under sustained pressure when standing for a long time or walking under load, and is used to measure muscle endurance and the foundation of maintaining stable tension;

[0017] The intermittent contraction action is set as a cycle rhythm of "contraction for 3 seconds and relaxation for 2 seconds", repeated 8-10 times, which accurately maps the dynamic cooperation situation of the pelvic floor muscle in the process of daily walking and climbing stairs, and tests its coordination and flexibility.

[0018] Preferably, the original surface electromyography SEMG data obtained in step a includes:

[0019] Firstly, 50HZ notch processing is performed to eliminate power frequency interference; then, the original signal is processed through an infinite long unit impulse response system; and finally, the characteristic value of the user's surface pelvic floor muscle surface electromyography SEMG signal is extracted.

[0020] Preferably, the original SEMG signal processing obtains {x{i}|(i=1.2.3…N)} in the time domain, wherein N represents the number of sample points, and the characteristic extraction calculation formula of the one-dimensional signal is as follows:

[0021] 1) The average absolute value MAV in the index information is:

[0022] In the formula, N is the number of surface electromyography signal data points collected, and x(i) is the i-th data in the signal data sequence, that is, the absolute value of the electromyography signal amplitude is calculated point by point, the absolute values are accumulated and summed, and then divided by the total number of sample points, so that the average level of the electromyography signal amplitude in the period can be obtained;

[0023] 2) The root mean square RMS in the index information is:

[0024] When calculating, the amplitude of each sampling point in the electromyography signal sequence is squared, all square values are accumulated and averaged, and then the square root is taken to obtain the RMS value;

[0025] 3) The integral electromyography value iEMG in the index information is: That is, the absolute values of the electromyography signal amplitudes are directly accumulated and summed;

[0026] 4) Maximum peak time t1: In the time domain waveform, the time when the amplitude of the electromyographic signal first reaches the maximum value is accurately locked, that is, the maximum peak time t1; it measures the time from the moment when the pelvic floor muscle receives the contraction instruction to the full burst and reaches the maximum contraction force from the time dimension.

[0027] Preferably, the original SEMG signal is subjected to fast Fourier transform in the frequency domain to obtain the frequency component and amplitude information of the signal, and the power spectral density of the user's surface electromyographic signal is set as PSD(f), and the two indicators of the median frequency MF and the average power frequency MPF are used to characterize the characteristics of the user's SEMG spectrum or power spectrum:

[0028] 1) Median frequency MF: The median frequency refers to the frequency at which the power spectral density function PSD of the electromyographic signal is divided into two equal area parts.

[0029] 2) Average power frequency MPF, which represents the average distribution position of the electromyographic signal power on the frequency axis.

[0030] Preferably, the multi-aspect screening in step c is specifically:

[0031] 1) Muscle strength screening: Obtain the data of pelvic floor muscle contraction strength, and reflect it by obtaining the three indicators of average absolute value MAV, root mean square RMS, and integral electromyographic value iEMG of the user in completing the specified process;

[0032] The average absolute value MAV reflects the average contraction force, the root mean square RMS highlights the energy release intensity, and the integral electromyographic value iEMG presents the total amount of electrical activity; and compared with the normal muscle strength interval generated by large sample statistics of the same age and gender population, if the measured average absolute value MAV and root mean square RMS of the patient are lower than the lower limit, and the integral electromyographic value iEMG is small, it indicates that the pelvic floor muscle contraction strength is severely insufficient;

[0033] 2) Muscle endurance screening: Muscle endurance considers the sustained working capacity of the pelvic floor muscle, and evaluates it by the median frequency MF and average power frequency MPF indicators generated by the user's movement; if the median frequency MF decreases slowly and the average power frequency MPF is stable, it is determined that the healthy pelvic floor muscle is long-time contraction; if MF decreases sharply and MPF shifts greatly, it is determined that the endurance is poor; such as long-distance drivers sitting for a long time, the pelvic floor muscle is chronically fatigued, MF continuously decreases, and MPF drifts to low frequency;

[0034] 3) Reaction speed screening: Reaction speed is related to the emergency ability of the pelvic floor muscle. The maximum peak time t1 is taken as the basis. According to a large number of healthy people samples, different motion modes are set to adapt to the reaction time threshold. Coughing and sneezing can instantly increase abdominal pressure, and the pelvic floor muscle should quickly contract. Normally, it takes tens of milliseconds. Set the normal threshold. If it is far beyond the threshold, such as hundreds of milliseconds, it indicates abnormal nerve conduction and muscle activation.

[0035] 4) Coordination screening: The coordination of the pelvic floor muscle is judged by observing the parameters, including the waveform, frequency and amplitude of the electromyographic signal.

[0036] Under normal circumstances, when the pelvic floor muscle contracts in coordination, the starting time, peak time and ending time of the electromyographic signal recorded by each channel corresponding to different electrode positions should be relatively synchronized. If the signal of a certain channel is significantly delayed or advanced, it indicates that the pelvic floor muscle at that position is not well coordinated with other parts.

[0037] 5) Fatigue screening: Comprehensive time domain and frequency domain indicators are used to achieve fatigue screening. Time domain observes the mean absolute value MAV, root mean square RMS and integral electromyographic value iEMG attenuation slope, and frequency domain observes the median frequency MF and average power frequency MPF drift direction and speed. If the index line attenuates linearly, it is a normal pelvic floor muscle fatigue progression. If the index line decreases exponentially, it indicates abnormal fatigue.

[0038] Preferably, step d specifically includes: integrating the detailed results of multi-dimensional screening to realize the close integration of user key information, including age, BMI, and psychological health status. The system generates a pelvic floor muscle status report, which includes user basic information, measured values of each indicator, comparison details with expected indicators, health rating, and intuitive charts and professional interpretation, allowing users to understand at a glance. The health rating is subdivided into multiple levels, and from "excellent" to "severe abnormality" to accurately anchor the pelvic floor muscle function level.

[0039] If the screening determines that there is an abnormality in the pelvic floor muscle status, the system will implement a customized recovery training guidance program based on the built-in intelligent algorithm and the knowledge base of rehabilitation experts. The training program fully considers the physiological and psychological rehabilitation needs, carefully designs exclusive movements, covers multiple projects such as modified Kegel exercise and pelvic floor yoga, reasonably plans the training frequency (recommended 3-5 times a week) and duration (20-30 minutes each time), recommends appropriate training aids (such as biofeedback instrument and yoga brick), and carries a real-time feedback mechanism. Real-time monitoring of electromyographic signals through portable devices, real-time prompting of action accuracy through voice and images, and full-process training protection. At the same time, great attention is paid to the psychological health of users. For patients with high stress and anxiety, relaxation training and psychological counseling are incorporated to promote rehabilitation in line with the concept of physical and mental rehabilitation.

[0040] Step e: with the wide application of the system and the continuous influx of massive user data, the system uploads the data to the cloud, can more intelligently optimize the training guidance strategy, realize the individualization and precision customization of the training scheme, help the user further understand the pelvic floor muscle state, and meet the unique rehabilitation demands of each user.

[0041] Preferably, the recovery training guidance in step d includes Kegel exercise and pelvic floor muscle yoga.

[0042] The pelvic floor muscle non-invasive detection device further comprises a voice module, a graphics module, a dynamic capture module and an infrared sensing module in communication connection with the signal processing module, and the voice module, the graphics module, the dynamic capture module and the infrared sensing module in the system are combined to realize real-time prompting on voice and image and realize the motion accuracy feedback of the recovery training guidance.

[0043] Beneficial effects: the user is preliminarily screened for pelvic floor muscles, so that the user can roughly grasp the state of the pelvic floor muscles; the pelvic floor muscle electromyographic signal is analyzed from the time domain and the frequency domain, the pelvic floor muscles are evaluated from multiple angles, the evaluation result can more comprehensively reflect the real functional state of the pelvic floor muscles, if the pelvic floor muscle state is abnormal, more professional evaluation guidance is given to the user according to the evaluation result, the user data is uploaded to the cloud, and the training guidance strategy can be more intelligently optimized. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 It is a flowchart of the present application. DETAILED DESCRIPTION

[0045] The present application is further described below in conjunction with the accompanying drawings of the specification, but the present application is not limited to the following embodiments.

[0046] Prior art: In traditional pelvic floor muscle palpation examination, doctors put their fingers into the vagina or rectum to feel the contraction of the pelvic floor muscles. The results of this examination depend largely on the experience and subjective judgment of the doctor. Different doctors may have different standards for judging muscle contraction strength, duration and symmetry. For example, some doctors may consider a certain degree of contraction to be normal, while another doctor may think that this contraction is not enough, which leads to a lack of objective and accurate standard for the results of the examination. Secondly, the traditional method requires doctors to perform palpation examination, which not only causes discomfort to the patient, but also causes infection. The Glazer scheme mainly evaluates the function of the pelvic floor muscles based on muscle electrical signals. It only provides information about the muscle strength, endurance, etc. of the pelvic floor muscles from the time domain, and does not analyze the state of the pelvic floor muscles in combination with the frequency domain, and the reference value is too one-sided. Secondly, the Glazer scheme cannot accurately detect the coordination and fatigue of the pelvic floor muscles, and the Glazer scheme does not have big data support, and cannot combine the user's own state and a large amount of user data to reflect a more accurate state of the pelvic floor muscles.

[0047] The principles / technical solutions of the present application: A multi-dimensional pelvic floor muscle function evaluation system is formed by a variety of muscle electrical signal indicators in the time domain (MAV, RMS, maximum peak duration t1) and the frequency domain (MF, MPF), which can comprehensively evaluate the state of the muscle strength, muscle endurance, reaction speed, coordination and fatigue of the pelvic floor muscles. According to the multi-dimensional screening results, the user's age, BMI, psychological health status and other information are combined to generate a pelvic floor muscle state report. The report content is rich, including basic information, measured values, comparison results and health ratings, so that the user can clearly understand the health status of their own pelvic floor muscles.

[0048] As Figure 1 shown is a specific embodiment of a pelvic floor muscle early screening training method based on data analysis, which is a pelvic floor muscle early screening training method based on data analysis, and the method comprises the following steps:

[0049] Step a: the user uses the connected pelvic floor muscle non-invasive detection device to complete the specified rating action, and obtains the real-time value of the surface pelvic floor muscle surface electromyography (SEMG) during the action; the pelvic floor muscle non-invasive detection device includes a signal acquisition module, a signal processing module, a signal detection and judgment module, a report generation module, and a data storage module, and the pelvic floor muscle non-invasive detection device further includes a voice module, a graphic module, a dynamic capture module, and an infrared induction module in communication with the signal processing module. Through the joint of the voice module, the graphic module, the dynamic capture module, and the infrared induction module in the system, the real-time prompt on the voice and image is realized to realize the action accuracy feedback of the recovery training guidance. The signal processing module includes a signal amplifier, and the signal acquisition module includes a disposable gel electrode, the signal amplifier is connected with nine disposable gel electrodes, and the nine electrodes are divided into three groups, each group includes one positive electrode, one negative electrode and one reference electrode; such layout can more comprehensively capture the multi-dimensional activity information of the pelvic floor muscle group, providing a rich data basis for subsequent signal processing. The disposable gel electrode is in close contact with the user's skin, ensuring high-quality signal acquisition. These electrodes not only ensure the clarity of the signal, but also effectively avoid the risk of cross infection through their disposable design, improving the hygiene of use;

[0050] The specified rating action includes rapid contraction action, slow sustained contraction action, and intermittent contraction action; the user uses the original device to complete the specified action under the guidance of professional medical personnel to collect signals; wherein, the rapid contraction action requires the user to tighten the pelvic floor muscle to the maximum tightening in an instant, with a duration of about 3-5 seconds, just like simulating the emergency response of the pelvic floor muscle in the sudden cough and sneeze scene in daily life, thereby capturing the high-intensity electromyography signal corresponding to the instantaneous explosive force of the muscle, and accurately evaluating the nerve conduction velocity and rapid activation ability of the pelvic floor muscle; the slow sustained contraction action requires the user to gradually exert force, and gradually reach the maximum contraction degree for 5-10 seconds, and then maintain for 10-15 seconds, which is similar to the working state of the pelvic floor muscle under sustained pressure when standing for a long time or walking under load, and is used to measure muscle endurance and maintain stable tension; the intermittent contraction action is set as a cycle rhythm of "contraction for 3 seconds and relaxation for 2 seconds", repeated for 8-10 times, which accurately maps the dynamic cooperation situation of the pelvic floor muscle in the process of daily walking and climbing stairs, and tests its coordination and flexibility;

[0051] Step b: first, the raw data of the surface electromyography signal is processed, and the evaluation index of the electromyography signal is calculated to obtain index information in the time domain, including the mean absolute value MAV (abbreviated as MAV), the root mean square RMS (abbreviated as RMS), the maximum peak time t1 (abbreviated as t1), and the integral electromyography value iEMG (abbreviated as iEMG); secondly, the signal is subjected to fast Fourier transform to obtain frequency domain related information, including the median frequency MF (abbreviated as MF) and the average power frequency MPF (abbreviated as MPF);

[0052] Step c: the obtained signal index is compared with the expected index, and multi-aspect screening is performed, including muscle strength, muscle endurance, reaction speed, coordination, and fatigue;

[0053] 1) Muscle strength screening: the data of the contraction strength of the pelvic floor muscle is obtained, and the average absolute value MAV, the root mean square RMS, and the integral electromyography value iEMG are obtained to reflect the muscle strength.

[0054] The average absolute value MAV reflects the average contraction force, the root mean square RMS highlights the energy release intensity, and the integral electromyography value iEMG presents the total amount of electrical activity; and the normal muscle strength interval generated by comparing a large sample of people of the same age and the same gender is compared, if the measured average absolute value MAV and the root mean square RMS of the patient are lower than the lower limit, and the integral electromyography value iEMG is small, it is indicated that the contraction strength of the pelvic floor muscle is seriously insufficient.

[0055] 2) Muscle endurance screening: muscle endurance considers the sustained working capacity of the pelvic floor muscle, and the median frequency MF and the average power frequency MPF generated by the user during exercise are used as indexes to evaluate the muscle endurance; if the median frequency MF decreases slowly and the average power frequency MPF is stable, it is determined that the pelvic floor muscle is healthy and can contract for a long time; if the MF decreases sharply and the MPF deviates greatly, it is determined that the endurance is poor; for example, long-distance drivers sit for a long time, the pelvic floor muscle is chronically fatigued, the MF continuously decreases, and the MPF drifts to low frequency.

[0056] 3) Reaction speed screening: the reaction speed is related to the emergency response ability of the pelvic floor muscle, and the maximum peak time t1 is used as the basis; according to a large number of healthy people samples, different motion modes are set to adapt to the reaction time threshold; the abdominal pressure rises instantly when coughing and sneezing, and the pelvic floor muscle should contract quickly, which is normal in tens of milliseconds; the normal threshold is set, if it is far beyond the threshold, such as hundreds of milliseconds, it is indicated that the nerve conduction and muscle activation are abnormal.

[0057] 4) Coordination screening: the coordination of the pelvic floor muscle is judged by observing parameters, including the waveform, frequency, and amplitude of the electromyography signal.

[0058] Under normal circumstances, when the pelvic floor muscles contract in coordination, the starting time, peak time and ending time of the electromyographic signals recorded by each channel corresponding to different electrode positions should be relatively synchronized. If a channel signal is significantly delayed or advanced, it indicates that the pelvic floor muscles at that site are not well coordinated with other sites.

[0059] 5) Fatigue screening: comprehensive time domain and frequency domain indicators are used to achieve fatigue screening; in the time domain, the mean absolute value MAV, root mean square RMS, and integral electromyographic value iEMG decay slope are observed; in the frequency domain, the median frequency MF and average power frequency MPF drift direction and speed are observed; if the index line attenuates linearly, it is a normal pelvic floor muscle fatigue progression, and if the index line decreases exponentially, it indicates abnormal fatigue.

[0060] Step d: According to the comparison with the preset value, the pelvic floor muscle status report is produced through the evaluation result; if an abnormality occurs, targeted recovery training guidance is provided according to the comparison of the signal indicators with the expected indicators;

[0061] Specifically: Based on the detailed results of multi-dimensional screening, the user's key information, including age, BMI, and psychological health status, is closely integrated to generate a pelvic floor muscle status report. The report includes user basic information, actual measured values of each indicator, comparison details with expected indicators, health rating, and intuitive charts and professional interpretations, allowing users to understand at a glance. The health rating is subdivided into multiple levels, and from "excellent" to "severe abnormality" to accurately anchor the pelvic floor muscle function level.

[0062] If the screening determines that there is an abnormality in the pelvic floor muscle status, the system can use built-in intelligent algorithms and rehabilitation expert knowledge bases to customize recovery training guidance programs. The specific algorithms and expert data are stored as needed. The specific training program can take into account the physiological and psychological rehabilitation needs, such as incorporating improved Kegel exercises, pelvic floor yoga, and other multi-element projects. A specific recommendation: reasonable planning of training frequency (recommended 3-5 times per week) and duration (20-30 minutes per time); recommendation of appropriate training aids (such as biofeedback instruments, yoga bricks, etc.); real-time feedback mechanism, real-time monitoring of electromyographic signals through portable devices, real-time voice and image prompts for action accuracy, and full-process training protection. At the same time, great attention is paid to the psychological health of users. For patients with high stress and anxiety, relaxation training and psychological counseling are incorporated, and the concept of physical and mental rehabilitation is adhered to to promote recovery.

[0063] Step e: Upload the data to the cloud to generate a data set, making it easier for users to achieve early screening and training of the pelvic floor muscles based on data analysis. By uploading data to the cloud, training guidance strategies can be more intelligently optimized, training programs can be customized individually and accurately, and users can further understand the status of their pelvic floor muscles to meet the unique rehabilitation needs of each user.

[0064] Preferably, the original surface electromyography SEMG data obtained in step a includes:

[0065] Firstly, 50HZ trap wave processing is performed to eliminate power frequency interference; then, the original signal is processed through an infinite long unit impulse response system for band-pass filtering; and finally, the surface electromyography SEMG signal of the user's surface pelvic floor muscle is extracted for feature value.

[0066] Preferably, the original SEMG signal processing in the time domain obtains {x(i) | (i = 1, 2, 3…N)}, wherein N represents the number of sample points, and the feature extraction calculation formula of the one-dimensional signal is as follows:

[0067] 1) The average absolute value MAV in the index information is:

[0068] In the formula, N is the number of surface electromyography signal data points collected, and x(i) is the i-th data in the signal data sequence, that is, the absolute value of the electromyography signal amplitude is calculated point by point, the absolute values are accumulated and summed, and then divided by the total number of sample points, so that the average level of the electromyography signal amplitude in the period can be obtained;

[0069] 2) The root mean square RMS in the index information is:

[0070] During operation, the amplitude of each sample point in the electromyography signal sequence is squared, all square values are accumulated and averaged, and then the square root is taken to obtain the RMS value;

[0071] 3) The integral electromyography value iEMG in the index information is: That is, the absolute values of the electromyography signal amplitudes are directly accumulated and summed;

[0072] 4) The maximum peak time t1: in the time domain waveform, the time when the electromyography signal amplitude first reaches the maximum value is accurately locked, that is, the maximum peak time t1; it measures the time from the moment when the pelvic floor muscle receives the contraction instruction to the time when it bursts into full power and reaches the maximum contraction force.

[0073] The original SEMG signal is subjected to fast Fourier transform in the frequency domain to obtain the frequency component and amplitude information of the signal, and the power spectral density of the user's surface electromyography signal is set as PSD(f), and the two indexes of median frequency MF and average power frequency MPF are used to characterize the characteristics of the user's SEMG spectrum or power spectrum:

[0074] 1) Median frequency MF: The median frequency refers to the frequency at which the power spectral density function PSD of the electromyography signal is divided into two equal area parts;

[0075] 2) Mean Power Frequency MPF, Represented the average distribution position of the power of the myoelectric signal on the frequency axis.

[0076] A specific division in the present application for comparing the obtained signal indicators with the expected indicators:

[0077] (1) Muscle strength score criteria (muscle strength screening)

[0078] Muscle strength score mainly depends on three core indicators: MAV (average active potential), RMS (root mean square value) and iEMG (total electrical activity). According to these indicators, different score intervals are drawn, and user data is compared with large sample statistics of normal population.

[0079] Score range:

[0080] A. Normal: MAV, RMS, iEMG values are within the normal range (determined according to reference data of the same age and sex).

[0081] B. Mild deficiency: MAV and RMS are at the lower limit of the normal range, and iEMG is slightly low, indicating that the muscle is slightly weak.

[0082] C. Moderate deficiency: MAV and RMS are significantly lower than the lower limit of the normal range, and iEMG is small, indicating that the muscle strength is insufficient.

[0083] D. Severe deficiency: MAV and RMS are significantly lower than the lower limit of the normal range, and iEMG is far below the normal range, indicating that the pelvic floor muscle contraction strength is severely insufficient.

[0084] Score criteria: Normal: 80-100 points Mild deficiency: 60-79 points Moderate deficiency: 40-59 points Severe deficiency: 0-39 points

[0085] (2) Muscle endurance score criteria (muscle endurance screening)

[0086] Muscle endurance screening evaluates the sustained working capacity of the pelvic floor muscle by observing MF (frequency center) and MPF (main frequency point).

[0087] Score range:

[0088] A. Normal: MF stable and slow decline, MPF stable or slight fluctuation.

[0089] B. Mild fatigue: MF gradually decreases, MPF slightly shifts, and endurance slightly decreases.

[0090] C. Moderate fatigue: MF significantly decreases, MPF significantly shifts, indicating pelvic floor muscle fatigue.

[0091] D. Severe fatigue: MF rapidly decreases, MPF drifts to low frequency, indicating long-term fatigue of the pelvic floor muscles, and poor recovery ability.

[0092] Scoring criteria: Normal: 80-100 points Mild fatigue: 60-79 points Moderate fatigue: 40-59 points Severe fatigue: 0-39 points

[0093] (3) Reaction speed scoring criteria (reaction speed screening)

[0094] Reaction speed assesses the emergency response ability of the pelvic floor muscles, based on the maximum peak time t1. According to the sample of healthy people, the reaction time threshold can be set.

[0095] Scoring range:

[0096] A. Normal: Reaction time t1 within tens of milliseconds.

[0097] B. Mild delay: Reaction time t1 exceeds the normal range, but is still within 100 milliseconds.

[0098] C. Moderate delay: Reaction time t1 is between 100-200 milliseconds, indicating abnormalities in nerve or muscle activation.

[0099] D. Severe delay: Reaction time t1 exceeds 200 milliseconds, indicating severe impairment of nerve conduction and activation of the pelvic floor muscles.

[0100] Scoring criteria: Normal: 80-100 points Mild delay: 60-79 points Moderate delay: 40-59 points Severe delay: 0-39 points

[0101] (4) Coordination scoring criteria (coordination screening)

[0102] Coordination screening assesses the coordination ability of the pelvic floor muscles by observing the waveform, frequency, amplitude, and other parameters of the signals in each channel.

[0103] Scoring range:

[0104] A. Normal: Good synchronization of signals in each channel, with relatively consistent start time, peak time, and end time.

[0105] B. Mildly uncoordinated: Some channels have slightly delayed or advanced signals, with small-scale coordination problems.

[0106] C. Moderately uncoordinated: Multiple channels have significant coordination problems, possibly indicating partial coordination problems in the pelvic floor muscle groups.

[0107] D. Severely uncoordinated: Multiple channels have coordination problems, with severe coordination problems in the pelvic floor muscle groups.

[0108] Score criteria: normal: 80-100 points mild incoordination: 60-79 points moderate incoordination: 40-59 points severe incoordination: 0-39 points

[0109] (5) Fatigue score criteria (fatigue screening)

[0110] Fatigue screening mainly evaluates the fatigue condition of the pelvic floor muscles through changes in time domain and frequency domain indicators, focusing on observing the attenuation slope of MAV, RMS, iEMG and the drift direction and speed of MF, MPF.

[0111] Score range:

[0112] A. Normal: MAV, RMS, iEMG gradually attenuate, MF, MPF slowly move to low frequency, showing linear and gentle attenuation trend.

[0113] B. Mild fatigue: MAV, RMS, iEMG slightly accelerate attenuation, MF, MPF slightly shift, and endurance decreases.

[0114] C. Moderate fatigue: MAV, RMS, iEMG significantly attenuate, MF, MPF accelerate shift, and pelvic floor muscle fatigue is more obvious.

[0115] D. Severe fatigue: MAV, RMS, iEMG sharply attenuate, MF, MPF quickly drift to low frequency, and fatigue sharply increases.

[0116] Score criteria: normal: 80-100 points mild fatigue: 60-79 points moderate fatigue: 40-59 points severe fatigue: 0-39 points

[0117] (6) Comprehensive score

[0118] Total score = muscle strength score × 0.2 + muscle endurance score × 0.2 + coordination score × 0.2 + fatigue score × 0.2 + reaction speed score × 0.2.

[0119] Comprehensive score range: normal: 80-100 points mild abnormality: 60-79 points moderate abnormality: 40-59 points severe abnormality: 0-39 points

[0120] Among them, the comprehensive score can adjust the score weight of each part according to the age, MBI, reproductive status, and disease history of the patient, and customize a more suitable scoring system for the patient.

[0121] (7) Generate training guidance

[0122] a. Fast contraction training (improve muscle strength and reaction speed)

[0123] Training goal: improve the rapid activation ability and emergency response ability of pelvic floor muscles, and improve nerve conduction and instantaneous explosive power of muscles.

[0124] Action Demonstration: Under the guidance of medical personnel, the user rapidly contracts the pelvic floor muscles to the maximum within 3-5 seconds, simulating sudden coughing, sneezing, and other situations.

[0125] Training Frequency: 8-10 times per training, with 1-2 minute breaks.

[0126] Training Intensity: According to the scoring criteria, the MAV and RMS should reach medium to high intensity during rapid contraction. If the reaction time t1 exceeds 150 milliseconds, increase the training frequency or shorten the relaxation time to improve reaction speed.

[0127] Advanced Method: Gradually increase the intensity of contraction and extend the duration of high-intensity contraction (5 seconds) to gradually increase the challenge of training.

[0128] Training Effect Evaluation: If the reaction time t1 consistently remains below 100 milliseconds, and the MAV, RMS, and iEMG all increase, it indicates that the rapid activation ability of the pelvic floor muscles has been improved.

[0129] If MAV or RMS is significantly lower than the normal range, continue with low-intensity, short-duration rapid contraction training.

[0130] b. Slow and sustained contraction training (improve muscle endurance and stability)

[0131] Training Goal: Enhance the sustained contraction ability and endurance of the pelvic floor muscles, enabling them to maintain stable tension for a longer period.

[0132] Action Demonstration: Slowly tighten the pelvic floor muscles, gradually reaching maximum contraction over 5-10 seconds, and maintain for 10-15 seconds, then relax.

[0133] Training Frequency: 5-8 times per training, with each contraction lasting 15-20 seconds and relaxation time of 30-60 seconds.

[0134] Training Intensity: According to the scoring criteria, MF and MPF should remain stable or change slowly during contraction. If MF significantly decreases or MPF deviates, increase the duration and intensity of slow contraction.

[0135] Advanced Method: Increase the duration of contraction, gradually extend the maintenance time (20 seconds), and enhance the intensity of each contraction to challenge the endurance of the pelvic floor muscles.

[0136] Training Effect Evaluation: If MF steadily decreases and MPF changes smoothly, it indicates that the endurance of the pelvic floor muscles is improving. If MF and MPF exhibit abnormal fluctuations, training intensity may need to be increased or the maintenance time of each contraction may need to be extended.

[0137] c. Intermittent contraction training (improve coordination and flexibility)

[0138] Training goal: Enhance the coordination and flexibility of the pelvic floor muscles during dynamic movements, simulating alternating contractions and relaxations in daily activities.

[0139] Action demonstration: Perform 8-10 alternating contractions and relaxations following the rhythm of "contraction for 3 seconds - relaxation for 2 seconds".

[0140] Training frequency: 8-10 times per training, maintaining signal synchronization and coordination during training.

[0141] Training intensity: According to the scoring criteria, pay attention to the synchronization and fluctuation of the electromyographic signal. If coordination is poor, you can appropriately reduce the contraction frequency and focus on training the accuracy of each contraction.

[0142] Advanced mode: Gradually increase the frequency of contraction and relaxation rhythm (for example, increase to "contraction for 4 seconds - relaxation for 3 seconds"), and gradually increase the number of training to improve the coordination of dynamic cooperation.

[0143] Training effect evaluation: If the signal synchronization of each channel is good, and the RMS and iEMG fluctuation is small, it indicates that the coordination and flexibility are good. If there is a significant signal lag or advance, it indicates that the coordination of the pelvic floor muscles needs to be improved, and the training frequency should be increased and the signal synchronization should be paid attention to.

[0144] The technical scheme of the present application can perform early screening through multi-dimensional electromyographic signal analysis before pelvic floor muscle dysfunction causes obvious symptoms. This helps to identify potential problems in advance, such as identifying postpartum women with insufficient pelvic floor muscle strength, and identifying elderly people with decreased pelvic floor muscle endurance, etc., so that timely intervention measures can be taken to effectively prevent the occurrence of serious pelvic floor muscle dysfunction diseases such as urinary incontinence and pelvic organ prolapse. The evaluation and guidance are based entirely on data analysis of pelvic floor muscle electromyographic signals, avoiding the subjectivity and uncertainty that may exist in traditional evaluation methods. Through rigorous mathematical calculations and comparisons with expected indicators, scientific and objective data support is provided for the judgment of pelvic floor muscle status and the development of training programs, making the entire health management process more reliable. From data acquisition, signal processing, screening evaluation to training guidance, it provides a foundation for one-stop service. Users only need to complete the specified actions as required to obtain a comprehensive pelvic floor muscle status report and personalized training program, without having to transfer between different institutions or equipment, greatly improving the efficiency and convenience of health management.

[0145] The modules in the present application are described as follows:

[0146] Signal Acquisition Module: The core component of this module is disposable gel electrodes. These electrodes use high-quality gel material that can closely adhere to the user's skin, effectively reducing interference and ensuring that the collected surface electromyography (SEMG) signals are clear and accurate. For example, when the user performs a pelvic floor muscle contraction action, the signal acquisition module will immediately capture these tiny muscle activity signals, providing raw data for subsequent signal processing. In addition, since the electrodes are disposable, they are replaced after each use, effectively avoiding the risk of cross-infection and ensuring the user's health and safety.

[0147] Signal Processing Module: This module contains a signal amplifier that amplifies and preprocesses the collected SEMG signals. The design of the amplifier allows even weak muscle activity signals to be clearly captured and converted into digital signals for further analysis. For example, when the signal acquisition module captures weak contraction signals of the pelvic floor muscles, the signal amplifier quickly amplifies these signals to ensure that the signal quality meets the requirements of subsequent processing.

[0148] Signal Detection and Judgment Module: This module uses advanced algorithms to analyze the processed SEMG signals to detect key parameters such as muscle contraction strength and duration. For example, it can accurately determine whether the user's pelvic floor muscle contraction force meets the standard when performing a certain rating action, thereby providing precise feedback to the user. At the same time, the module can also predict possible pelvic floor muscle dysfunction based on the user's muscle activity pattern, providing scientific diagnostic evidence for doctors.

[0149] Report Generation Module: This module is responsible for converting the analysis results of the signal detection and judgment module into easy-to-understand reports. The report content may include the user's pelvic floor muscle function score, muscle activity chart, and training recommendations, etc. For example, the report may show the user's pelvic floor muscle contraction strength and duration when completing a certain specific action, as well as the deviation from the normal range, helping the user understand their pelvic floor muscle function status and develop a personalized training plan.

[0150] Data Storage Module: This module is used to store user detection data, training records, and generated reports, etc. For example, each user's detection data is automatically saved for future comparison and analysis. This not only helps users track their training progress, but also provides doctors with long-term health monitoring data.

[0151] In addition, there are also voice modules, graphics modules, dynamic capture modules, and infrared sensing modules, etc. auxiliary modules.

[0152] Voice module: For example, when the user is training, the voice module will broadcast training instructions in real time, reminding the user to maintain the correct posture and rhythm. At the same time, it can also give timely encouragement and feedback according to the user's training progress and performance.

[0153] Graphical module: This module will display intuitive graphics and animations on the device's display screen, helping users better understand the training requirements and action details. For example, it will show the contraction and relaxation process of the pelvic floor muscles, as well as the impact of different actions on the pelvic floor muscles.

[0154] Dynamic capture module: This module uses camera or sensor technology to capture the user's action trajectory in real time. For example, it can monitor the user's body tilt angle, arm swing amplitude and other key parameters when performing a certain action, so as to ensure that the user's action conforms to the specification.

[0155] Infrared sensing module: This module automatically adjusts the training parameters and feedback mode by sensing the user's body position and movement state. For example, when the user approaches the device, the infrared sensing module will automatically start the training mode; when the user leaves, it will pause the training and save the data.

[0156] Finally, it should be noted that the present invention is not limited to the above embodiments, but can have many variations. All variations that can be directly derived or inferred from the content disclosed in the present invention by those of ordinary skill in the art should be considered within the scope of protection of the present invention.

Claims

1. A pelvic floor muscle early screening training method based on data analysis, characterized by The method comprises the following steps: Step a: the user uses the connected pelvic floor muscle non-invasive detection device to complete the specified rating action, and obtains the real-time value of the surface pelvic floor muscle surface electromyography SEMG during the action process; Step b: first, the raw data of the surface electromyography signal is processed, the evaluation index of the electromyography signal is calculated, the index information is obtained in the time domain, and the index information includes the mean absolute value MAV, the root mean square RMS, the maximum peak time t1, and the integral electromyography value iEMG; second, the signal is subjected to fast Fourier transform to obtain frequency domain related information, and the related information includes the median frequency MF and the average power frequency MPF; Step c: the obtained signal index is compared with the expected index, and multi-aspect screening is performed, including muscle strength, muscle endurance, reaction speed, coordination, and fatigue; Step d: according to the comparison with the preset value, a pelvic floor muscle state report is produced through the rating result; If an abnormality occurs, targeted recovery training guidance is provided according to the comparison between the signal index and the expected index; Step e: upload the data to the cloud to generate a data set, so that the user can more accurately realize the pelvic floor muscle early screening training based on data analysis.

2. The pelvic floor muscle early screening training method based on data analysis according to claim 1, characterized in that: The pelvic floor muscle non-invasive detection device comprises a signal acquisition module, a signal processing module, a signal detection and judgment module, a report generation module, and a data storage module which are communicatively connected, the signal processing module comprises a signal amplifier, the signal acquisition module comprises disposable gel electrodes, the signal amplifier is connected with nine disposable gel electrodes, and the nine electrodes are divided into three groups, each group comprising one positive electrode, one negative electrode and one reference electrode.

3. The pelvic floor muscle early screening training method based on data analysis according to claim 1 or 2, characterized in that: The specified rating action in step a includes a rapid contraction action, a slow sustained contraction action and an intermittent contraction action; and the signal acquisition is performed when the specified action is completed. The rapid contraction action requires the user to tighten the pelvic floor muscle to the maximum tightening in an instant, the duration is about 3-5 seconds, the high-intensity electromyography signal corresponding to the instantaneous explosive force of the muscle is captured, and the nerve conduction speed and rapid activation ability of the pelvic floor muscle are accurately evaluated. The slow sustained contraction action requires the user to gradually exert force, gradually reach the maximum contraction degree for 5-10 seconds, and then maintain for 10-15 seconds, so as to measure the muscle endurance and the ability to maintain stable tension. The intermittent contraction action is set as a cycle rhythm of "contraction for 3 seconds and relaxation for 2 seconds", which is repeated for 8-10 times.

4. The pelvic floor muscle early screening training method based on data analysis according to claim 1, characterized in that: The original surface electromyography SEMG data obtained in step a includes: First, 50HZ notch processing is performed to eliminate power frequency interference; then, band-pass filtering is performed to complete the processing of the original signal; and finally, the characteristic value of the user's surface pelvic floor muscle surface electromyography SEMG signal is extracted.

5. The pelvic floor muscle early screening training method based on data analysis according to claim 1 or 2 or 4, characterized in that: The original SEMG signal processing obtains {x(i)|(i=1,2,3…N)} in the time domain, wherein N represents the number of sample points, and the characteristic extraction calculation formula of the original SEMG signal is as follows: 1) The mean absolute value MAV in the indicator information is: In the formula, N is the number of data points of the collected surface electromyography signal, x(i) is the i th data in the signal data sequence, the absolute value of the electromyography signal amplitude is first calculated point by point, the absolute values are accumulated and summed, and then divided by the total number of sample points, so that the average level of the amplitude of the collected electromyography signal can be obtained. 2) The root mean square (RMS) in the index information is: During the operation, the amplitude of each sampling point in the myoelectricity signal sequence is squared, and the RMS value is obtained by taking the square root of the average of all squared values; 3) The integrated myoelectric value iEMG in the indicator information is: i.e. the absolute value of the myoelectric signal amplitude is directly accumulated and summed. 4) Maximum peak time t1: the time when the amplitude of the myoelectricity signal reaches the maximum value for the first time in the time domain waveform is the maximum peak time t1; It measures the time from the moment of receiving the contraction instruction to the moment of full burst and maximum contraction force.

6. The pelvic floor muscle early screening training method based on data analysis according to claim 5, characterized in that: In the frequency domain, the original SEMG signal is subjected to fast Fourier transform to obtain the frequency component and amplitude information of the signal, and the power spectral density of the user's surface myoelectricity signal is set as PSD(f), and the two indicators of median frequency MF and average power frequency MPF are used to characterize the characteristics of the user's SEMG spectrum or power spectrum: 1) Median frequency MF: The median frequency is the frequency that divides the power spectral density function PSD of the myoelectric signal into two equal area portions; 2) Mean power frequency MPF, represents the average position of the power of the myoelectric signal on the frequency axis.

7. The method of claim 1, wherein the method is based on data analysis of pelvic floor muscle early screening and training. The multi-aspect screening in step c is specifically: 1) Muscle strength screening: the data of the contraction strength of the pelvic floor muscle is obtained, and the average absolute value MAV, the root mean square RMS, and the integrated myoelectricity value iEMG are obtained to reflect the three indicators during the completion of the specified process; The average absolute value MAV reflects the average contraction force, the root mean square RMS highlights the energy release intensity, and the integrated myoelectricity value iEMG presents the total amount of electrical activity; And compared with the normal muscle strength interval generated by the large sample statistics of the same age and gender population, if the measured average absolute value MAV and root mean square RMS of the patient are lower than the lower limit, and the integrated myoelectricity value iEMG is small, it indicates that the contraction strength of the pelvic floor muscle is seriously insufficient; 2) Muscle endurance screening: the median frequency MF and average power frequency MPF generated by the user during the movement are used to evaluate; if the median frequency MF decreases slowly and the average power frequency MPF is stable, it is determined that the healthy pelvic floor muscle is long-time contraction; if the MF decreases sharply and the MPF deviates greatly, it is determined that the endurance is poor; 3) Reaction speed screening: the maximum peak time t1 is used as the basis; the normal threshold is set, and if it is far beyond the threshold, it indicates that the nerve conduction and muscle activation are abnormal; 4) Coordination screening: the coordination of the pelvic floor muscle is judged by observing the parameters, including the waveform, frequency, and amplitude of the myoelectricity signal; Under normal circumstances, when the pelvic floor muscles contract synchronously, the starting time, peak time, and ending time of the myoelectricity signal recorded by each channel corresponding to different electrode positions should be relatively synchronous, and if a certain channel signal is significantly delayed or advanced, it indicates that the pelvic floor muscle corresponding to the channel does not coordinate well with other pelvic floor muscles; 5) Fatigue screening: the fatigue screening is realized by comprehensively observing the changes of the time domain and frequency domain indicators; the attenuation slope of the average absolute value MAV, the root mean square RMS, and the integrated myoelectricity value iEMG in the time domain, and the drift direction and speed of the median frequency MF and the average power frequency MPF in the frequency domain; if the index line attenuates linearly, it is a normal pelvic floor muscle fatigue progression, and if the index line decreases exponentially, it indicates abnormal fatigue.

8. The pelvic floor muscle early screening training method based on data analysis according to claim 1, characterized in that: The step d specifically comprises: synthesizing the multi-dimension screening detailed results to realize the close integration of the user key information, the key information including age, BMI, mental health state, the system generates the pelvic floor muscle state report, the report including user basic information, each index measured value, comparison details with expected index, health rating, and is matched with intuitive chart; the health rating is subdivided into multiple levels, and from "excellent" to "severe abnormality" corresponds to the pelvic floor muscle function level.

9. The pelvic floor muscle early screening training method based on data analysis according to claim 2, characterized in that: The recovery training guidance in the step d includes Kegel exercise and pelvic floor muscle yoga. The pelvic floor muscle non-invasive detection device further comprises a voice module, a graphics module, a dynamic capture module and an infrared sensing module in communication connection with the signal processing module, and through the joint of the voice module, the graphics module, the dynamic capture module and the infrared sensing module in the system, the real-time prompt on the voice and the image is realized to realize the action accuracy feedback of the recovery training guidance.

Images