Pelvic floor disorder EEG data acquisition system

Abstract

This invention discloses a pelvic floor disorder EEG data acquisition system, comprising: an experimental paradigm module for designing experimental paradigms; an audio-visual technology module for presenting each stage of the experimental paradigm through audio-visual technology, guiding users to perform tasks as required; an EEG acquisition module for collecting EEG data from users at each stage of the experimental paradigm using EEG acquisition equipment; a data preprocessing module for preprocessing the collected EEG data; and a data analysis module for performing feature extraction, classification, and correlation analysis on the preprocessed EEG data to achieve a comprehensive assessment of the functional status of pelvic floor muscles. This pelvic floor disorder EEG data acquisition system comprehensively covers resting state, memory, anal contraction, and defecation tasks in its experimental paradigms. Combined with audio-visual guidance, it ensures accurate user execution and collects high-quality EEG data, providing a scientific basis for accurate assessment and personalized rehabilitation of pelvic floor function.

Description

Technical Field

[0001] This invention specifically relates to an electroencephalogram (EEG) data acquisition system for pelvic floor disorders. Background Technology

[0002] In contemporary medicine, pelvic floor dysfunction is an increasingly concerning issue, especially for individuals who have experienced pregnancy and childbirth. The pelvic floor muscles are a group of muscles that support the organs within the pelvis, including the urethra, bladder, rectum, and uterus. The health of these muscles directly affects an individual's urinary control, sexual function, and the maintenance of organ position. Pelvic floor dysfunction, including symptoms such as urinary incontinence, fecal incontinence, and pelvic organ prolapse, affects millions of people worldwide, particularly women. This problem is exacerbated by population aging and changing birth rates.

[0003] Traditional diagnostic methods for pelvic floor dysfunction often focus on a single indicator, such as pressure measurement or electromyography, which is insufficient to comprehensively assess the functional status of the pelvic floor muscles and has certain limitations. Therefore, developing a data collection method that can comprehensively assess the functional status of the pelvic floor muscles is particularly important. Summary of the Invention

[0004] This invention provides a system for acquiring electroencephalogram (EEG) data related to pelvic floor disorders to solve the aforementioned technical problems. Specifically, the technical solution is as follows:

[0005] A system for acquiring electroencephalogram (EEG) data on pelvic floor disorders, comprising:

[0006] The experimental paradigm module is used to design experimental paradigms, which include resting state, short-term memory, imagined anal contraction, simulated anal contraction, imagined defecation, and simulated defecation tasks.

[0007] The audio and video technology module is used to present the various stages of the experimental paradigm through audio and video technology, guiding users to perform tasks as required.

[0008] The EEG acquisition module is used to collect EEG data from users at various stages of the experimental paradigm using EEG acquisition equipment.

[0009] The data preprocessing module is used to preprocess the acquired EEG data, including steps such as artifact removal, filtering, and noise reduction.

[0010] The data analysis module is used to extract features, classify and identify data, and perform correlation analysis on preprocessed EEG data in order to achieve a comprehensive assessment of the functional status of the pelvic floor muscles.

[0011] Furthermore, the experimental paradigms designed in the experimental paradigm module specifically include:

[0012] Resting-state task: The user remains relaxed and does not perform any pelvic floor muscle activity, which is used to collect the user's baseline EEG data;

[0013] Short-term memory task: Users memorize numbers or images presented through audio and video technology, which is used to collect EEG data of users during the memorization process;

[0014] Visualizing anal contraction task: Users imagine themselves performing anal contraction, that is, the contraction of pelvic floor muscles. Related instructions or images are presented through audio and video technology to help users better understand and perform the visualization task.

[0015] Simulated anal contraction task: The user actually performs the anal contraction action, that is, the contraction of the pelvic floor muscles. The instructions or images presented by audio and video technology ensure that the user performs the action correctly.

[0016] Visualizing a defecation task: Users imagine themselves performing the act of defecation, which involves relaxing the pelvic floor muscles. Relevant instructions or images are presented through audio and video technology to help users better understand and perform the visual task.

[0017] Simulated defecation task: The user actually performs the defecation action, that is, relaxes the pelvic floor muscles. The instructions or images presented by audio and video technology ensure that the user performs the action correctly.

[0018] Furthermore, the audio and video technology module includes a video player, an audio player, and a display screen, used to present the various stages of the experimental paradigm through visual and auditory means, ensuring that users can accurately understand and perform tasks.

[0019] Furthermore, the EEG acquisition module uses an electroencephalograph, and the electrode placement follows the international standard 10-20 electrode system to comprehensively acquire EEG data from different brain regions.

[0020] Furthermore, the data preprocessing module employs a combination of time-domain and frequency-domain analysis to extract statistical features such as mean, variance, kurtosis, and skewness of the EEG signal, as well as the power spectral density features of each frequency band.

[0021] Furthermore, the data analysis module uses a support vector machine algorithm to classify and identify the feature vectors, thereby obtaining the classification results of the pelvic floor muscle functional status.

[0022] Furthermore, the data analysis module calculates indicators such as the correlation coefficient and regression coefficient between EEG signals and pelvic floor muscle activity to assess the correlation between EEG signals and pelvic floor muscle activity.

[0023] Furthermore, the system also includes a user feedback module, which comprises an emotion recognition submodule and a task adjustment submodule, wherein:

[0024] The emotion recognition submodule is used to monitor the user's emotional state in real time through voice emotion analysis or facial expression recognition technology.

[0025] The task adjustment submodule is used to automatically adjust the task difficulty in the experimental paradigm or provide psychological support based on the monitoring results of the emotion recognition submodule, so as to improve user participation and rehabilitation effect.

[0026] Furthermore, the system also includes a physiological monitoring module, which comprises a multi-physiological parameter fusion analysis submodule and a real-time health early warning submodule, wherein:

[0027] The multi-physiological parameter fusion analysis submodule is used to comprehensively analyze physiological data such as heart rate, blood pressure, and blood oxygen saturation with EEG data, and to mine the potential correlations between these physiological parameters through machine learning algorithms in order to more comprehensively assess the user's health status.

[0028] The real-time health warning submodule is used to immediately issue an alarm and suspend the current rehabilitation task when an abnormal physiological state of the user is detected, so as to ensure the user's safety.

[0029] Furthermore, the system also includes an intelligent diagnosis module, which comprises a personalized rehabilitation plan generation submodule, a telemedicine integration submodule, and a rehabilitation effect prediction submodule, wherein:

[0030] The personalized rehabilitation plan generation submodule is used to generate personalized rehabilitation plans based on the user's EEG data, physiological data, and user feedback data. The plans include rehabilitation training suggestions, lifestyle adjustments, and dietary suggestions.

[0031] The telemedicine integration submodule is used to integrate the system with the cloud platform, enabling doctors to remotely monitor the user's rehabilitation progress and adjust the rehabilitation plan in real time. At the same time, it uses the big data analysis function of the cloud platform to collect and analyze a large amount of user rehabilitation data, providing support for clinical research and personalized treatment.

[0032] The rehabilitation effect prediction submodule is used to predict the rehabilitation effect of users under different rehabilitation programs using historical data and machine learning algorithms, helping doctors and patients choose the most suitable rehabilitation path and improve rehabilitation efficiency.

[0033] The advantage of this invention lies in the pelvic floor disorder EEG data acquisition system provided, which comprehensively covers experimental paradigms such as resting state, memory, anal contraction, and defecation. Combined with audio and video guidance, it ensures accurate execution by the user and collects high-quality EEG data, providing a scientific basis for accurate assessment and personalized rehabilitation of pelvic floor function. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of the pelvic floor disorder EEG data acquisition system of this application. Detailed Implementation

[0036] Embodiments of the present invention are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0037] like Figure 1 The image shows a pelvic floor disorder EEG data acquisition system according to this application, including: an experimental paradigm module, an audio-visual technology module, an EEG acquisition module, a data preprocessing module, and a data analysis module.

[0038] The experimental paradigm module is used to design experimental paradigms, including resting state, short-term memory, imagined anal contraction, simulated anal contraction, imagined defecation, and simulated defecation tasks. The audio-visual technology module presents each stage of the experimental paradigm using audio and video technology, guiding users to perform the tasks as required. The EEG acquisition module uses EEG acquisition equipment to collect EEG data from users at each stage of the experimental paradigm. The data preprocessing module preprocesses the collected EEG data, including artifact removal, filtering, and noise reduction. The data analysis module performs feature extraction, classification, and correlation analysis on the preprocessed EEG data to achieve a comprehensive assessment of the pelvic floor muscle function.

[0039] The experimental paradigm comprises six stages: resting state, short-term memory, imagined anal contraction, simulated anal contraction, imagined defecation, and simulated defecation task. Each stage has clear instructions and audio-visual presentation to ensure accurate understanding and execution by the user. In the embodiments of this application, the experimental paradigm designed in the experimental paradigm module specifically includes:

[0040] Resting-state task: Users remain relaxed and do not engage in any pelvic floor muscle activity. This is used to collect baseline EEG data. The resting-state phase is the initial stage of the experiment; users need to remain relaxed and not engage in any pelvic floor muscle activity. This stage is used to collect baseline EEG data for subsequent analysis.

[0041] Short-term memory task: Users memorize numbers or images presented through audio-visual technology, and EEG data is collected during the memorization process. In the short-term memory stage, users need to memorize numbers or images presented through audio-visual technology. This stage is used to collect EEG data during the memorization process to analyze the impact of memory activity on pelvic floor muscle function.

[0042] Visualizing Kegel Exercises: Users imagine themselves performing a pelvic floor muscle contraction exercise. Instructions or images are presented using audio-visual technology to help users better understand and perform the task. Collecting EEG data during this phase allows for analysis of the impact of the imagined movement on pelvic floor muscle function.

[0043] Simulated anal contraction task: Users actually perform anal contractions, i.e., contractions of the pelvic floor muscles. Instructions or images presented through audio and video technology ensure that users perform the movements correctly. EEG data collected during this stage can be analyzed to understand the impact of the actual movements on pelvic floor muscle function.

[0044] Visualizing Defecation: Users imagine themselves performing the act of defecation, i.e., relaxing their pelvic floor muscles. Audio-visual technology is used to present relevant instructions or images to help users better understand and perform the visualization task. During the visualization stage, users need to imagine themselves performing the act of defecation, i.e., relaxing their pelvic floor muscles. Audio-visual technology is used to present relevant instructions or images to help users better understand and perform the visualization task. Collecting EEG data during this stage allows for analysis of the impact of the visualization on pelvic floor muscle function.

[0045] Simulated defecation task: The user actually performs the defecation action, i.e., relaxes the pelvic floor muscles. Instructions or images presented through audio and video technology ensure that the user performs the action correctly. EEG data collected during this stage can be analyzed to analyze the impact of the actual action on pelvic floor muscle function.

[0046] The audio-visual technology module is used to present the various stages of the experimental paradigm through audio-visual technology, guiding users to perform tasks as required. In the embodiments of this application, the audio-visual technology module includes a video player, an audio player, and a display screen, used to present the various stages of the experimental paradigm through visual and auditory means, ensuring that users can accurately understand and perform the tasks. Video presentation is used to display action demonstrations and instructions. For example, in the imagined and simulated anal contraction stages, the video player plays relevant demonstrations of pelvic floor muscle contraction actions to help users better understand and perform the actions. In the short-term memory stage, the video player quickly flashes a series of numbers or images for users to memorize. Audio presentation is used to play instructions and prompts. For example, at the beginning and end of each stage, the audio player plays corresponding instructions to prompt users to proceed to the next stage or end the current stage. In the imagined, simulated, imagined defecation, and simulated defecation stages, the audio player plays relevant pelvic floor muscle activity instructions to help users better understand and perform the actions.

[0047] In the embodiments of this application, the EEG acquisition module employs an electroencephalograph (EEG), and electrode placement follows the internationally standardized 10-20 electrode system to comprehensively acquire EEG data from different brain regions. Specifically, electrode placement is one of the key steps in EEG data acquisition. According to the internationally standardized 10-20 electrode system, the electrodes on the electrode cap are placed at specific locations on the user's scalp. These locations include areas such as the frontal lobe, central region, parietal lobe, occipital lobe, and temporal lobe to comprehensively acquire EEG data from different brain regions. Data recording is the process of recording and storing the acquired EEG signals. The amplified EEG signals are converted into digital signals using a data acquisition card and stored in a computer. The recorded data includes information such as the amplitude, frequency, and phase of the EEG signals, which are used for subsequent data analysis and processing.

[0048] In the embodiments of this application, the data preprocessing module uses a combination of time-domain analysis and frequency-domain analysis to extract statistical features such as mean, variance, kurtosis, and skewness of the EEG signal, as well as the power spectral density features of each frequency band.

[0049] Artifact removal: Artifacts are abnormal signals caused by factors such as user head movement or poor electrode contact, and need to be removed using artifact removal algorithms.

[0050] Filtering and denoising: Filtering and denoising are used to remove high-frequency noise and low-frequency interference from EEG signals and improve the signal-to-noise ratio.

[0051] In the embodiments of this application, the data analysis module uses the support vector machine algorithm to classify and identify the feature vectors, and obtain the classification result of the pelvic floor muscle function status.

[0052] In the embodiments of this application, the data analysis module calculates indicators such as the correlation coefficient and regression coefficient between electroencephalogram (EEG) signals and pelvic floor muscle activity to assess the correlation between EEG signals and pelvic floor muscle activity.

[0053] This module includes steps such as feature extraction, classification and recognition, and correlation analysis to achieve a comprehensive assessment of the functional status of the pelvic floor muscles.

[0054] Feature extraction: Feature extraction involves extracting features related to pelvic floor muscle function from electroencephalogram (EEG) data. These features include parameters such as amplitude, frequency, and phase of the EEG signal, as well as indicators such as connectivity and synchronicity between different brain regions. Through feature extraction, complex EEG data can be transformed into concise feature vectors, providing a foundation for subsequent classification, recognition, and correlation analysis.

[0055] Classification and Recognition: Classification and recognition is the process of classifying and recognizing the extracted feature vectors. Machine learning algorithms, such as Support Vector Machines (SVM) and Neural Networks (NN), are used to categorize feature vectors into different classes to classify and recognize the functional status of the pelvic floor muscles. The results of classification and recognition can be used to assess the user's pelvic floor muscle function, such as normal, mild impairment, or severe impairment.

[0056] Correlation analysis: Correlation analysis examines the connectivity and synchronicity between different brain regions, as well as the correlation between electroencephalogram (EEG) signals and pelvic floor muscle activity. By calculating indices such as coherence and mutual information between different brain regions, connectivity and synchronicity can be assessed. Simultaneously, by calculating indices such as correlation coefficients or regression coefficients between EEG signals and pelvic floor muscle activity, the correlation between these two activities can be evaluated. These analytical results can provide important evidence for further understanding the neural mechanisms underlying pelvic floor muscle function.

[0057] In embodiments of this application, the system further includes a user feedback module, used to collect users' subjective feelings during task execution in real time, and to optimize experimental paradigms and evaluation results based on user feedback. The user feedback module includes an emotion recognition submodule and a task adjustment submodule, wherein:

[0058] The emotion recognition submodule is used to monitor the user's emotional state in real time through voice emotion analysis or facial expression recognition technology. For example, the system can use deep learning algorithms to analyze the user's voice tone or facial expressions to identify changes in the user's emotions, such as anxiety, fatigue, or pleasure.

[0059] The task adjustment submodule is used to automatically adjust the task difficulty or provide psychological support in the experimental paradigm based on the monitoring results of the emotion recognition submodule, in order to improve user engagement and recovery outcomes. For example, if the system detects user anxiety, it can automatically reduce the task difficulty or provide encouraging voice feedback to improve user engagement and recovery outcomes.

[0060] In embodiments of this application, the system further includes a physiological monitoring module for real-time monitoring of the user's physiological data such as heart rate, blood pressure, and blood oxygen saturation, and for synchronous analysis of these data with electroencephalogram (EEG) data to more comprehensively assess the user's health status. The physiological monitoring module includes a multi-physiological parameter fusion analysis submodule and a real-time health early warning submodule, wherein:

[0061] The multi-physiological parameter fusion analysis submodule is used to comprehensively analyze physiological data such as heart rate, blood pressure, and blood oxygen saturation with EEG data. Machine learning algorithms are used to uncover potential correlations between these physiological parameters to more comprehensively assess the user's health status. For example, the system can analyze the relationship between heart rate variability and EEG activity to reveal underlying physiological and psychological states.

[0062] The real-time health alert submodule is used to immediately issue an alarm and suspend the current rehabilitation task when an abnormality in the user's physiological state is detected, to ensure the user's safety. For example, if the system detects that the user's heart rate is too high or blood pressure is abnormal, it will immediately issue an alarm and suspend the rehabilitation task until the user's condition returns to normal.

[0063] In embodiments of this application, the system further includes an intelligent diagnostic module, used to generate personalized diagnostic reports based on EEG data, physiological data, and user feedback data, and to recommend corresponding rehabilitation plans. The intelligent diagnostic module includes a personalized rehabilitation plan generation submodule, a telemedicine integration submodule, and a rehabilitation effect prediction submodule, wherein:

[0064] The personalized rehabilitation plan generation submodule is used to generate personalized rehabilitation plans based on the user's EEG data, physiological data, and user feedback data. These plans include rehabilitation training suggestions, lifestyle adjustments, and dietary recommendations. For example, the system can recommend a suitable pelvic floor muscle training plan based on the user's EEG and physiological data, and provide suggestions for dietary and lifestyle adjustments.

[0065] The telemedicine integration submodule integrates the system with the cloud platform, enabling doctors to remotely monitor users' rehabilitation progress and adjust rehabilitation plans in real time. Simultaneously, it leverages the cloud platform's big data analytics capabilities to collect and analyze vast amounts of user rehabilitation data, supporting clinical research and personalized treatment. For example, doctors can view users' rehabilitation data in real time through the cloud platform and adjust rehabilitation plans as needed.

[0066] The rehabilitation outcome prediction submodule utilizes historical data and machine learning algorithms to predict a user's rehabilitation outcomes under different rehabilitation programs, helping doctors and patients choose the most suitable rehabilitation path and improve rehabilitation efficiency. For example, the system can predict a user's rehabilitation outcomes under different programs based on their EEG and physiological data, providing a reference for doctors and patients.

[0067] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by equivalent substitution or equivalent transformation fall within the protection scope of the present invention.

Claims

1. A pelvic floor disorder electroencephalic data acquisition system, characterized in that, Comprise: An experimental paradigm module for designing an experimental paradigm, including resting state, short-term memory, imagined anal contraction, simulated anal contraction, imagined defecation, and simulated defecation tasks; An audio-video technology module for presenting each stage of the experimental paradigm through audio-video technology, guiding users to perform tasks as required; An electroencephalogram acquisition module for acquiring electroencephalogram data of users performing each stage of the experimental paradigm using an electroencephalogram acquisition device; A data preprocessing module for preprocessing the acquired electroencephalogram data, including removing artifacts, filtering, and denoising steps; A data analysis module for feature extraction, classification identification, and correlation analysis of the preprocessed electroencephalogram data to achieve comprehensive assessment of the functional status of the pelvic floor muscles.

2. The electroencephalogram data acquisition system for pelvic floor disorders according to claim 1, wherein the experimental paradigm designed by the experimental paradigm module specifically comprises: Resting state task: the user remains in a relaxed state without any pelvic floor muscle activity, which is used to acquire baseline electroencephalogram data of the user; Short-term memory task: the user memorizes numbers or images presented through audio-video technology, which is used to acquire electroencephalogram data of the user during the memory process; Imagined anal contraction task: the user imagines himself performing anal contraction, i.e., contraction of the pelvic floor muscles, with relevant instructions or images presented through audio-video technology to help the user better understand and perform the imagined task; Simulated anal contraction task: the user actually performs anal contraction, i.e., contraction of the pelvic floor muscles, with instructions or images presented through audio-video technology to ensure that the user performs the action correctly; Imagined defecation task: the user imagines himself performing defecation, i.e., relaxation of the pelvic floor muscles, with relevant instructions or images presented through audio-video technology to help the user better understand and perform the imagined task; Simulated defecation task: the user actually performs defecation, i.e., relaxation of the pelvic floor muscles, with instructions or images presented through audio-video technology to ensure that the user performs the action correctly.

3. The electroencephalogram data acquisition system for pelvic floor disorders according to claim 1, wherein the audio-video technology module comprises a video player, an audio player, and a display screen for presenting each stage of the experimental paradigm through visual and auditory means to ensure that the user can accurately understand and perform the tasks.

4. The electroencephalogram data acquisition system for pelvic floor disorders according to claim 1, wherein the electroencephalogram acquisition module uses an electroencephalograph, and the electrodes are placed following the international standard 10-20 electrode system to comprehensively acquire electroencephalogram data of different brain regions.

5. The electroencephalogram data acquisition system for pelvic floor disorders according to claim 1, wherein the data preprocessing module uses a combination of time domain analysis and frequency domain analysis to extract the mean, variance, kurtosis, skewness, and power spectral density features of each frequency band of the electroencephalogram signal.

6. The electroencephalogram data acquisition system for pelvic floor disorders according to claim 1, wherein the data analysis module uses a support vector machine algorithm to classify and identify the feature vectors to obtain the classification results of the functional status of the pelvic floor muscles.

7. The electroencephalogram data acquisition system for pelvic floor disorders according to claim 1, wherein ​ ​ ​ ​ ​ The data analysis module calculates the correlation coefficient and regression coefficient between the electroencephalogram signal and the pelvic floor muscle activity, and evaluates the correlation between the electroencephalogram signal and the pelvic floor muscle activity.

8. The pelvic floor disorder electroencephalogram data acquisition system of claim 1, wherein, The system further comprises a user feedback module, which comprises an emotion recognition submodule and a task adjustment submodule, wherein: The emotion recognition submodule is used to monitor the emotional state of the user in real time through voice emotion analysis or facial expression recognition technology; The task adjustment submodule is used to automatically adjust the task difficulty in the experimental paradigm or provide psychological support according to the monitoring results of the emotion recognition submodule, so as to improve the user's participation and rehabilitation effect.

9. The pelvic floor disorder electroencephalogram data acquisition system of claim 1, wherein, The system further comprises a physiological monitoring module, which comprises a multi-physiological parameter fusion analysis submodule and a real-time health warning submodule, wherein: The multi-physiological parameter fusion analysis submodule is used to comprehensively analyze heart rate, blood pressure, blood oxygen saturation and electroencephalogram data, and mine the potential association between these physiological parameters through machine learning algorithm, so as to more comprehensively evaluate the health status of the user; The real-time health warning submodule is used to issue an alarm immediately when the physiological state of the user is detected to be abnormal, and to suspend the current rehabilitation task to ensure the safety of the user.

10. The pelvic floor disorder electroencephalogram data acquisition system of claim 1, wherein, The system further comprises an intelligent diagnosis module, which comprises a personalized rehabilitation scheme generation submodule, a remote medical integration submodule and a rehabilitation effect prediction submodule, wherein: The personalized rehabilitation scheme generation submodule is used to generate a personalized rehabilitation scheme according to the electroencephalogram data, physiological data and user feedback data of the user, which includes rehabilitation training suggestions, lifestyle adjustments and dietary suggestions; The remote medical integration submodule is used to integrate the system with the cloud platform, so that doctors can remotely monitor the rehabilitation progress of the user and adjust the rehabilitation scheme in real time, while utilizing the big data analysis function of the cloud platform to collect and analyze a large amount of rehabilitation data of users, providing support for clinical research and personalized treatment; The rehabilitation effect prediction submodule is used to predict the rehabilitation effect of the user under different rehabilitation schemes by using historical data and machine learning algorithms, helping doctors and patients to choose the most suitable rehabilitation path and improve rehabilitation efficiency.

Images