A system for remote assessment of gluteus medius

Abstract

The application discloses a system for remote evaluation of gluteus medius, comprising a sensor patch, a computer and a remote terminal, wherein the sensor patch comprises a skin contact layer, an electrophysiological sensor, a microprocessor, a transceiver and a power supply for the sensor patch. The skin contact layer adheres the operable sensor element to the skin and connects to the muscle, so that the muscle signal data can be measured. The electrophysiological sensor can activate the muscle and collect the surface electromyography signal data when the muscle is at rest or contraction. The data is processed by the microprocessor and transmitted to the computer through the transceiver. The computer receives the surface electromyography signal data and transmits it to the gluteus medius remote evaluation application program in the computer. The application program analyzes and feeds back the gluteus medius data and displays the training action to be performed according to the state of the gluteus medius. The application has the characteristics of simple operation and convenient carrying, and can realize the function of monitoring and evaluating the gluteus medius data at any time.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of human electromyography recognition and analysis, and in particular to a gluteus medius remote evaluation system. BACKGROUND

[0002] According to the data of the State Council in 2021, the proportion of people who regularly participate in physical exercise accounts for more than one-third of the total population. According to the relevant data of the State General Administration of Sports, the incidence of sports injuries in China is between 10% and 20%, and it is estimated that more than 100 million people will have the need for prevention and treatment of sports injuries every year in the future. After sports injuries occur, in addition to the burden of medical expenses, if training protection is not carried out in time, the risk of secondary injury will be increased. Previous reports have shown that increasing gluteus medius training can improve the prevention and treatment effect of sports injuries.

[0003] In the gluteus medius rehabilitation environment, analyzing muscle activity or movement is the key to evaluating any progress of the patient. The common way to measure muscle activity or movement is usually in a laboratory environment, using multiple sEMG (surface electromyography) for motion capture. However, due to the fact that most professional medical laboratories in China are far away from the patient's living environment, patients with evaluation and rehabilitation needs cannot seek medical treatment in time, and the disease cannot be diagnosed and treated in time. SUMMARY

[0004] The technical problem to be solved by the present application is that, considering the current situation of gluteus medius remote evaluation, the present application proposes a sensor system combining sEMG and portable terminal recording evaluation technology, which can allow patients to leave the laboratory and realize real-time monitoring and evaluation of gluteus medius data, and gluteus medius evaluation can be performed in any scenario.

[0005] The present application adopts the following technical solutions to solve the above technical problems:

[0006] The gluteus medius remote evaluation system proposed by the present application comprises a sensor patch, a computer and a remote terminal, wherein:

[0007] The sensor patch comprises a skin contact layer, an electrophysiological sensor, a microprocessor, a transceiver and a power supply for powering the sensor patch; the skin contact layer is used to adhere the operable sensor element to the skin, so that the muscle signal data can be measured; the electrophysiological sensor can activate the muscle and collect the raw signal data of the surface electromyography signal when the muscle is at rest or contracted; the microprocessor amplifies and pre-processes the raw signal data, and finally transmits the processed signal data to the computer through the transceiver using wireless transmission.

[0008] A gluteus medius remote assessment application is installed on the computer, and the surface electromyographic signal data received from the transceiver is transmitted to the application for receiving, storing and processing the data. The processed muscle signal data is then provided to the patient on a visual and auditory patient interface. The patient can use this information to adjust muscle activity or perform exercises according to recommended training movements.

[0009] The remote terminal serves as a cloud and includes one or more running reference databases, which can store patient data so that the patient can view the data information of the surface electromyographic signal of the gluteus medius muscle at any time.

[0010] The skin contact layer is made of multiple layers of flexible material bonded together in the form of a thin bandage. It contains conductive and non-adhesive areas, both made of the same material height and with no visible boundary between them. The conductive area is located in the middle of the skin contact layer and is responsible for collecting raw electromyographic data. The non-adhesive area is located at the edge of the skin contact layer and allows the sensor patch to move relative to the skin during muscle activity. The adhesion of the skin contact layer will decrease over time, and the conductivity of the sensor will decrease when the patient sweats or the skin secretes oil. In these cases, the patient should promptly replace the patch with a new one.

[0011] Furthermore, the microprocessor includes a high-pass filter, a low-pass filter, and one or more notch filters, wherein:

[0012] High-pass filter, used to filter out polarization voltage and low-frequency noise, with a low-frequency cutoff frequency of 10Hz.

[0013] Low-pass filter, used to filter out high-frequency noise, with a high-frequency cutoff frequency of 200Hz.

[0014] The notch filter is used to filter out the 60Hz power frequency electrical signal through the power frequency notch.

[0015] Furthermore, the power source for the sensor patch is a disposable button battery installed on the sensor patch.

[0016] Furthermore, the computer is a desktop computer, laptop computer, tablet computer or smart phone with Bluetooth function, and the transceiver sends the processed signal data to the computer via Bluetooth transmission.

[0017] When the patient is within the visual range of the computer during measurement, real-time data feedback can be obtained; otherwise, the measured data will be automatically saved to the sensor patch worn by the patient.

[0018] Furthermore, the application stores and displays the data in the following steps:

[0019] S1. Use the analog-to-digital conversion unit to digitize the data through the ADC and output it into digital data.

[0020] S2. Use the sliding window technology to calculate the absolute average time series characteristics of the signal data. The window size is 120ms, and it slides back 40ms each time, that is, there is 67% repeated data in adjacent windows. All gluteus medius surface electromyography signal data are normalized to [0, 1] according to their maximum and minimum values, and then the RMS calculation is performed. The maximum and minimum values ​​are also used to normalize the characteristic values ​​of subsequent test data to facilitate the subsequent simplified calculation and reduce the value.

[0021] S3. Use the data smoothing unit to smooth the surface electromyographic signal data of the gluteus medius muscle so that its signal characteristics correspond to the time of gluteus medius stretching, contraction, etc. The sliding time window corresponding to the surface electromyographic signal data of the i-th gluteus medius muscle is winA is the analysis window size, winB is the sliding distance of the analysis window, and the surface electromyographic signal data of the gluteus medius at time Ti is calculated by interpolation to correspond to it.

[0022] S4, the surface electromyographic signal data of the gluteus medius after feature extraction and the angle signal after interpolation processing are expressed as follows:

[0023]

[0024] Among them, αi represents the surface electromyographic signal feature vector of the gluteus medius muscle of the i-th sample, βi represents the angle vector of the motion joint of the gluteus medius muscle of the i-th sample, and R represents a real number.

[0025] In order to overcome the problem of directly using the Gaussian process regression model for image super-resolution reconstruction, a sparse pseudo-input Gaussian process regression algorithm is used, and the surface electromyography signal-gluteus medius movement feature mapping model is established and saved based on the above-mentioned feature sequence α and angle sequence β.

[0026] S5. After feature extraction, the surface electromyographic signal data of the gluteus medius in the prediction set is input into the mapping model in step S3 for continuous estimation of gluteus medius motion features, thereby obtaining the following:

[0027]

[0028] Among them, α * is the input of the model during continuous estimation; β * It is the gluteus medius motion characteristic continuously estimated by the model.

[0029] Furthermore, the user can log in to his or her account through a computer to view the surface electromyographic signal data, evaluation results and training information of the gluteus medius muscle under the account.

[0030] Furthermore, the patient's personal information under this account includes but is not limited to: height, weight, gluteus medius muscle function level, clinical motor score and affected muscle status.

[0031] Furthermore, training information includes but is not limited to: training objectives, training plans, and training process data records.

[0032] The present invention adopts the above technical solution, and compared with the prior art, its significant technical effects are as follows:

[0033] (1) High adhesion of the sensor patch is crucial for long-term, high-intensity physical activity during dynamic movement. Decreased adhesion of the conductive area of ​​conventional sensors leads to contact loss, increased impedance, and decreased signal quality after long-term testing (t > 20 minutes). The sensor system of the present invention solves these problems of conventional sensors by arranging layers with different hydrophobic properties on the skin surface, which helps remove sweat and oil from the skin surface.

[0034] (2) Remote quantitative assessment of the degree of gluteus medius injury, taking into account portability and scientificity, ultimately allows for convenient data acquisition and ensures data accuracy. Combining the patient's intuitive feelings with objective data facilitates medical staff and patients to adjust their current rehabilitation status and strategies, thereby improving the rehabilitation efficiency of the patient's gluteus medius, preventing overtraining, and ensuring patient safety. At the same time, it provides convenience for patients in real-time acquisition of data signals and dynamic interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a block diagram of the overall structure of the system of the present invention.

[0036] Figure 2 The present invention provides a specific process for monitoring gluteus medius muscle signal data using the system of the present invention and displaying the data using a smart phone.

[0037] Figure 3 The gluteus medius muscle signal data monitored by the system of the present invention.

[0038] Figure 4 The following is a method for monitoring gluteus medius muscle signal data using two systems of the present invention.

[0039] Figure 5 This is the process of processing data signals by the microprocessor in the system of the present invention.

[0040] Figure 6 The present invention provides a specific process for monitoring gluteus medius muscle data using the system of the present invention and displaying the data using a laptop computer.

[0041] Figure 7 The diagram shows the structure of the skin contact layer in the system of the present invention, a side view of the sensor patch, and a comparison diagram before and after impedance improvement. DETAILED DESCRIPTION

[0042] The present invention will be described in further detail below with reference to the accompanying drawings and specific implementations.

[0043] To achieve the above object, the present invention proposes a system for remote assessment of gluteus medius muscle, including a sensor patch, a computer and a remote terminal, such as Figure 1 The overall system structure is shown in the block diagram. The sensor patch includes a skin contact layer, electrophysiological sensors, a microprocessor, a transceiver, and a power supply. The sensor patch is attached to the skin via the skin contact layer. The duration of attachment can be adjusted based on the patient's needs, and the skin contact layer must be removed if it becomes excessively worn or begins to separate from the skin. When the patient is within the computer's visual range, real-time data feedback is provided; otherwise, the measured data is automatically saved to the sensor patch worn by the patient.

[0044] The skin contact layer adheres the operable sensor elements to the skin and connects them to the muscles, so that muscle signal data can be measured. The skin contact layer is made of multiple layers of flexible materials bonded together in the form of a thin bandage to improve wear resistance. It contains conductive and non-adhesive areas, the materials used for the two are of the same height and have no visible boundaries between each other. The conductive area is less sticky than ordinary pressure-sensitive adhesive patches and is located in the middle of the skin contact layer, responsible for collecting raw electromyographic data; the non-adhesive area is located at the boundary of the skin contact layer, which allows the sensor patch to move relative to the skin during muscle activity. The adhesion of the skin contact layer will decrease over time, and the conductivity of the sensor will decrease when the patient sweats or the skin secretes oil. In these cases, the patient should replace the patch with a new one.

[0045] The electrophysiological sensor can activate the muscle and collect data of surface electromyographic signals when the muscle is at rest or contracting.

[0046] The transceiver sends the processed signal data to the computer via Bluetooth.

[0047] A remote gluteus medius muscle assessment application is installed on the computer, which transmits surface electromyographic signal data received from the transceiver to the application for data reception, storage, and processing. The processed surface electromyographic signal data is then presented to the patient via a visual and auditory patient interface. The patient can use this information to adjust muscle activity or perform recommended exercises. The application also transmits all generated data and results to a remote terminal. Users can log in to their account via the computer to view surface electromyographic signal data, assessment results, and training information for the gluteus medius muscle associated with that account. Training information includes, but is not limited to, training goals, training plans, and training process data records. Personal information associated with the patient's account includes, but is not limited to, height, weight, gluteus medius muscle function level, clinical motor score, and affected muscle status.

[0048] The remote terminal acts as a cloud and contains one or more running reference databases that can store patient data so that patients can view the surface electromyographic signal data information of their gluteus medius muscle at any time. At the same time, doctors can track the patient's recovery progress based on the patient information in the database.

[0049] The power source for the sensor patch is a disposable button battery installed on the sensor patch.

[0050] The sensor patch is installed on the skin through the skin contact layer. The length of time it is adhered can be adjusted according to the patient's needs, and it can be removed when the skin contact layer is excessively worn or begins to separate from the skin.

[0051] like Figure 2 As shown, the patient adheres the sensor patch to the skin of the buttocks area and holds a smartphone in hand. The sensor patch can upload relevant data of the gluteus medius muscle to the smartphone. The data can be displayed in the form of images, videos, or audio so that the patient and doctor can monitor muscle performance. The doctor adjusts the workload or implements muscle activity based on the patient's surface electromyographic signal data to change the muscle data to an ideal level. In addition, the smartphone communicates through mobile signals or connects to the Internet via Wi-Fi to upload the patient's data information to a database located in a server as a remote terminal so that the patient's information can be obtained at any time.

[0052] Figure 3The data obtained by the sensor patch is presented in Figure 3A, which is displayed on a computer feedback interface. Figure 3A shows the relationship between the sEMG amplitude of the gluteus medius muscle and time when the patient takes a step. It can be seen that when the patient takes a step, the sEMG amplitude curve of the gluteus medius muscle rises significantly, and when the step is completed, the curve returns to its initial height. Figure 3B shows a graph of the impedance between data points processed by the microprocessor versus time. During exercise, the sEMG noise is higher and the impedance is more active, indicating that the impedance synchronizes the sEMG data. Figure 3C shows a comparative analysis of different graphical data, including the relationship between non-impedance-adjusted sEMG data and time, impedance and time, and impedance-adjusted sEMG data and time, demonstrating that patients can obtain sEMG data information using this system. It can be seen that when there is no impedance, the sEMG amplitude curve of the gluteus medius muscle is not smooth enough, and meaningless fluctuations occur. The data information at this time has no reference value. With the addition of impedance, the noise of other signals can be eliminated and the interference signal can be removed to compensate for the impedance changes at the sensor / skin interface caused by physiological changes during physiological activities, thereby obtaining more accurate sEMG data of the gluteus medius muscle.

[0053] like Figure 4 As shown, in order to ensure that the data obtained is more accurate and complete, two or more sensor patches can be used simultaneously and attached to the gluteus medius muscles on the left and right sides or to different parts of the gluteus medius muscle on the same side, thereby obtaining muscle signal data of the gluteus medius muscle.

[0054] The microprocessor contains a high-pass filter, a low-pass filter, and one or more notch filters, which can amplify the raw signal data obtained from the electrophysiological sensor and process it using hardware filters. The specific processing method of the signal data is as follows Figure 5 As shown: first, it passes through high-pass filtering to filter out polarization voltage and low-frequency noise, and the low-frequency cutoff frequency is 10Hz; then it passes through low-pass filtering to filter out high-frequency noise, and the high-frequency cutoff frequency is 200Hz; then it passes through power frequency notching to filter out the 60Hz power frequency electrical signal.

[0055] After the filtering process is completed, the signal data is processed using software. The specific steps are as follows:

[0056] S1. Use the analog-to-digital conversion unit to digitize the data through the ADC and output it into digital data.

[0057] S2. Use the sliding window technology to calculate the absolute average time series characteristics of the signal. The window size is 120ms, and it slides back 40ms each time, that is, there is 67% repeated data in adjacent windows. All gluteus medius surface electromyography signal data are normalized to [0, 1] according to their maximum and minimum values, and then the RMS calculation is performed. The maximum and minimum values ​​are also used to normalize the characteristic values ​​of subsequent test data to facilitate subsequent simplified calculations and reduce the value.

[0058] S3. Use the data smoothing unit to smooth the surface electromyographic signal data of the gluteus medius muscle so that its signal characteristics correspond to the time of gluteus medius stretching, contraction, etc. The sliding time window corresponding to the surface electromyographic signal data of the i-th gluteus medius muscle is winA is the analysis window size, winB is the sliding distance of the analysis window, and the surface electromyographic signal data of the gluteus medius at time Ti is calculated by interpolation to correspond to it.

[0059] S4, the surface electromyographic signal data of the gluteus medius after feature extraction and the angle signal after interpolation processing are expressed as follows:

[0060]

[0061] Among them, αi represents the surface electromyographic signal feature vector of the gluteus medius muscle of the i-th sample, βi represents the angle vector of the motion joint of the gluteus medius muscle of the i-th sample, and R represents a real number.

[0062] In order to overcome the problem of directly using the Gaussian process regression model for image super-resolution reconstruction, a sparse pseudo-input Gaussian process regression algorithm is used, and the surface electromyography signal-gluteus medius movement feature mapping model is established and saved based on the above-mentioned feature sequence α and angle sequence β.

[0063] S5. After feature extraction, the surface electromyographic signal data of the gluteus medius in the prediction set is input into the mapping model in step S3 for continuous estimation of gluteus medius motion features, thereby obtaining the following:

[0064]

[0065] Among them, α * is the input of the model during continuous estimation; β * It is the gluteus medius motion characteristic continuously estimated by the model.

[0066] like Figure 6As shown, sensor patches are attached to the left and right buttocks, respectively. The computer used in this case is a laptop, so the patient cannot obtain good visual feedback. Therefore, auditory feedback is used to provide gluteus medius muscle signal data and status to the patient through audio and text prompts using computer speakers or headphones. Training exercises to improve gluteus medius performance are also provided, including single-leg deadlifts, lateral shifts, clamshell exercises, kneeling straight leg extensions, and kneeling flexed knee extensions.

[0067] like Figure 7 As shown in FIG7A , the skin contact layer of the sensor patch has three sensor area portions, the first being an active sensor area, the second being an active sensor area, and the third being a reference sensor area. Figure 7 Figure 7B is a side view of the sensor patch showing the circuit substrate and the sensor area and adhesive area opposite the flexible pouch, which can contain and protect the components from body secretions or other contaminants and improve impedance. Figure 7 Figure 7C shows the previous impedance (sloping curve) and the improved impedance. The impedance is basically constant and the slope is significantly reduced, indicating that the improved impedance can more effectively filter noise and interference signals and obtain more accurate sEMG data.

[0068] The computer also includes a bus / interface controller that can be used to facilitate communication between the basic configuration and one or more data storage devices via a storage interface bus. The data storage devices include, but are not limited to, removable storage devices, non-removable storage devices, or a combination thereof. Removable and non-removable storage devices include, but are not limited to, magnetic disk devices such as floppy disk drives and hard disk drives (HDDs), optical disk drives such as digital versatile disks (DVDs), solid-state drives (SSDs), and the like. Example computer storage media include, but are not limited to, volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data.

[0069] The above embodiments are only for illustrating the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the present invention.

Claims

1. A system for remote assessment of gluteus medius, characterized in that: It includes sensor patches, computers and remote terminals, including: The sensor patch includes a skin contact layer, an electrophysiological sensor, a microprocessor, a transceiver, and a power supply for powering the sensor patch. The skin contact layer is used to adhere an operable sensor element to the skin, thereby enabling the measurement of muscle signal data. The electrophysiological sensor can activate the muscle and collect raw signal data of the surface electromyographic signal when the muscle is at rest or contracting. The microprocessor amplifies the raw signal data, performs pre-processing, and finally transmits the processed signal data to a computer via wireless transmission through the transceiver. A gluteus medius remote assessment application is installed on the computer, and the surface electromyographic signal data received from the transceiver is transmitted to the application for data reception, storage, and processing. The processed muscle signals are then provided to the patient on a visual and auditory patient interface. The patient can use this information to adjust muscle activity or perform exercises according to recommended training movements; specifically: S1, using the analog-to-digital conversion unit to digitize the data through the ADC and output it into digital data; S2. Calculate the absolute average temporal characteristics of the signal data using a sliding window technique. The window size is 120 ms, and each window slides backward 40 ms. This means that 67% of adjacent windows contain repeated signal data. All gluteus medius surface electromyography signal data are normalized to the range [0, 1] based on their maximum and minimum values, and then the RMS is calculated. S3. Smoothing the surface electromyographic signal data of the gluteus medius muscle using a data smoothing unit. The sliding time window corresponding to the surface electromyographic signal data of the i-th gluteus medius muscle is Ti = winA + (i-1) winB, where i = 1, 2, ..., n; winA is the analysis window size, winB is the analysis window sliding distance, and the surface electromyographic signal data of the gluteus medius muscle at time Ti is calculated by interpolation. S4, the surface electromyographic signal data of the gluteus medius after feature extraction and the angle signal data after interpolation processing are respectively expressed as: α={=i}αi∈R β={=i}αi∈R Among them, αi represents the surface electromyographic signal feature vector of the i-th sample gluteus medius muscle, βi represents the angle vector of the i-th sample gluteus medius muscle motion joint, and R represents a real number; In order to overcome the problem of directly using the Gaussian process regression model for image super-resolution reconstruction, a sparse pseudo-input Gaussian process regression algorithm is used, and the surface electromyography signal-gluteus medius movement feature mapping model is established and saved based on the above feature sequence α and angle sequence β. S5. After feature extraction, the surface electromyographic signal data of the gluteus medius in the data set is input into the mapping model in step S3 for continuous estimation of gluteus medius motion features, thereby obtaining the following: α * ＝{α *i}α *i ∈R β*＝{β* i}β* i ∈R Among them, α* is the input of the model during continuous estimation, and β* is the gluteus medius movement characteristic value continuously estimated by the model; The remote terminal serves as a cloud and contains one or more running reference databases that can store patient data so that the patient can view the data information of the surface electromyographic signal of the gluteus medius muscle at any time; The skin contact layer is made of multiple layers of flexible material bonded together in the form of a thin bandage, and includes conductive and non-adhesive areas. The materials used for the two areas are of the same height and have no visible boundary between them. The conductive area is located in the middle of the skin contact layer and is responsible for collecting raw electromyographic data. The non-adhesive area is located at the edge of the skin contact layer and enables the sensor patch to move relative to the skin during muscle activity. The power source for the sensor patch is a disposable button battery installed on the sensor patch.

2. The system for remote assessment of gluteus medius according to claim 1, characterized in that: The microprocessor includes a high-pass filter, a low-pass filter, and one or more notch filters; wherein: High-pass filter, used to filter out polarization voltage and low-frequency noise, with a low-frequency cutoff frequency of 10Hz; Low-pass filter, used to filter out high-frequency noise, with a high-frequency cutoff frequency of 200Hz; The notch filter is used to filter out the 60Hz power frequency electrical signal through the power frequency notch.

3. The system for remote assessment of gluteus medius according to claim 1, characterized in that: The computer is a desktop computer, laptop computer, tablet computer or smart phone with Bluetooth function, and the transceiver sends the processed signal data to the computer via Bluetooth transmission.

4. The system for remote assessment of gluteus medius according to claim 1, characterized in that: Users can log in to their account through a computer to view the surface electromyographic signal data, evaluation results and training information of the gluteus medius muscle under the account.

5. The system for remote assessment of gluteus medius according to claim 4, characterized in that: The patient's personal information under this account includes but is not limited to: height, weight, gluteus medius muscle function level, clinical motor score and affected muscle status.

6. The system for remote assessment of gluteus medius according to claim 4, characterized in that: Training information includes but is not limited to: training objectives, training plans, and training process data records.

Images