KR20230159043A - Method and apparatus for evaluating muscle function - Google Patents

Abstract

A method for evaluating the muscle function of a user who wears a rehabilitation device and performs rehabilitation training in a muscle function evaluation device is provided. The muscle function evaluation method includes collecting inertial information sensor signals and EMG signals from an inertial information sensor and an EMG sensor included in the rehabilitation device during rehabilitation training, analyzing inertial information characteristics from the inertial information sensor signals, and EMG signals. It includes analyzing electromyographic features from and performing muscle function evaluation using the inertial information features and the electromyographic features analyzed during the rehabilitation training.

Description

Method and device for evaluating muscle function {METHOD AND APPARATUS FOR EVALUATING MUSCLE FUNCTION}

The present disclosure relates to a muscle function evaluation method and device, and more specifically, to a muscle function evaluation method and device for evaluating the level of muscle function recovery of a rehabilitation patient using electromyography and inertial information analysis.

Because stroke patients are unable to move their bodies, they must do rehabilitation exercises for a long period of time or with the help of specialists and physical therapists. As non-contact medical services become possible after the global pandemic of COVID-19, there is a demand for remote rehabilitation treatment at home. This is increasing. Telerehabilitation is attracting more attention as a way to solve problems in medical services, such as lack of physical therapy time, difficulty in examination, and lack of efficiency of self-rehabilitation.

Additionally, technologies and solutions related to rehabilitation devices using exoskeleton robots or electrical stimulation are being developed to help patients who have lost muscle function due to stroke, trauma, etc. recover.

In order for remote rehabilitation treatment to be activated, it is necessary to measure and analyze the patient's vital signs using ICT and biosensors. In particular, rehabilitation patients whose upper and lower limb muscles are paralyzed due to stroke, etc. need a method to evaluate muscle function in rehabilitation devices and systems so that the rehabilitation effect can be objectively evaluated. These technologies can help not only medical staff but also patients objectively understand the current state of the environment and attempt more appropriate exercise therapy and rehabilitation treatment.

Previously, when doctors or therapists evaluated the muscle function of stroke patients, manual muscle testing (MMT) and FMA (Fugl-Meyer Assessment) methods were mainly used. Level scales make it difficult to quantify sections between scales, and existing muscle function assessment methods lack systematic and continuous standards, making it difficult to quantify assessment results. Therefore, evaluation should be quantitative rather than qualitative so that even subtle changes can be detected, and technology that can evaluate the evaluation in real time is needed.

The problem that the present disclosure aims to solve is to provide a muscle function evaluation method and device that can objectively evaluate the patient's muscle function status when performing rehabilitation training using a patient-centered rehabilitation device without the help of medical staff.

According to one embodiment, a method of evaluating the muscle function of a user who wears a rehabilitation device and performs rehabilitation training using a muscle function evaluation device is provided. The muscle function evaluation method includes collecting inertial information sensor signals and EMG signals from an inertial information sensor and an EMG sensor included in the rehabilitation device during rehabilitation training, analyzing inertial information characteristics from the inertial information sensor signals, and EMG signals. It includes analyzing electromyographic features from and performing muscle function evaluation using the inertial information features and the electromyographic features analyzed during the rehabilitation training.

According to an embodiment, the patient's muscle function status and the treatment results of rehabilitation exercises can be confirmed through an objective evaluation of muscle function by the patient or user without the help of medical staff or physical therapists, and these results can lead to remote medical services.

Additionally, once a system is established that evaluates muscle function in real time and provides analysis results, medical staff can manage rehabilitation exercises remotely using this real-time and accumulated data. This possibility could implement a smart rehabilitation device that allows medical staff to understand in real time what commands were sent from the patient's brain to the muscles and provide customized rehabilitation services tailored to each patient, and contribute to the spread of the personal rehabilitation device market.

Figure 1 is a flowchart showing a method for evaluating muscle function according to an embodiment.
Figure 2 is a flowchart showing a method of analyzing an inertial information sensor signal according to an embodiment.
Figure 3 is a flowchart showing a method of analyzing an electromyogram signal according to an embodiment.
Figure 4 is a flowchart showing a method of evaluating muscle function using inertial information features and electromyography features according to an embodiment.
Figure 5 is a flowchart showing an example of a method for evaluating muscle function and analyzing recovery status before and after rehabilitation training of a user according to an embodiment.
Figure 6 is a diagram showing a muscle function evaluation device according to an embodiment.
Figure 7 is a diagram showing a muscle function evaluation device according to another embodiment.

Below, with reference to the attached drawings, embodiments of the present disclosure will be described in detail so that those skilled in the art can easily practice them. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present disclosure in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification and claims, when a part is said to “include” a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

Now, the muscle function evaluation method and device according to an embodiment of the present disclosure will be described in detail with reference to the drawings.

Figure 1 is a flowchart showing a method for evaluating muscle function according to an embodiment.

Referring to Figure 1, the user wears a rehabilitation device that includes an inertial measurement unit (IMU) and an electromyogram (EMG) sensor and performs rehabilitation training (S110).

Surface electromyography devices, which are used by medical staff in hospitals for biofeedback treatment for rehabilitation, are difficult to use unless you are an expert, and the products are expensive, making it difficult for patients to purchase and use them directly. The patient's muscle function can be monitored not only through electromyography but also through inertial information sensors. Therefore, the muscle function evaluation device according to the embodiment analyzes the signals sensed by the inertial information sensor and the electromyography sensor included in the rehabilitation device to evaluate the muscle function of the user's upper and/or lower limb muscles.

The muscle function evaluation device collects inertial information sensor signals in real time from the inertial information sensor according to rehabilitation training movements (S120) and analyzes the received inertial information sensor signals (S130).

The muscle function evaluation device collects electromyographic data from the electromyographic sensor of the user's rehabilitation training area according to the rehabilitation training movements (S140) and analyzes the collected electromyographic data (S150).

The muscle function evaluation device performs muscle function evaluation and stores the muscle function evaluation information based on the analysis information of the inertial information sensor signal collected from the inertial information sensor and the analysis information of the electromyogram signal collected from the electromyogram sensor during rehabilitation training (S160) . Muscle function evaluation information may be stored in a rehabilitation device or a separate server.

The muscle function evaluation device can visualize the muscle function evaluation information so that the user or medical staff can query the muscle function evaluation information (S170).

By periodically performing muscle function evaluation in the manner described above and tracking and observing the user's muscle function evaluation information, the user's rehabilitation status and degree of recovery can be objectively determined. Additionally, by storing the user's muscle function evaluation information in a rehabilitation device or server, , During the next hospital visit, the medical staff can check the data, accurately determine the level of recovery, and proceed with rehabilitation and exercise appropriate for that stage.

Figure 2 is a flowchart showing a method of analyzing an inertial information sensor signal according to an embodiment.

Referring to FIG. 2, the muscle function evaluation device collects inertial information sensor signals according to the user's rehabilitation training movements from the inertial information sensor and begins analysis of the collected inertial information sensor signals (S210).

The muscle function evaluation device sets a predetermined time window for the inertial information sensor signal (S220).

The muscle function evaluation device performs inertial information sensor signal processing, such as noise processing for the inertial information sensor signal within the time window and extraction of Euler angles (motion information) through sensor fusion (S230).

The muscle function evaluation device performs autoregressive analysis on the extracted Euler angles (S240).

Based on the autoregressive analysis results, the muscle function evaluation device analyzes inertial information features such as Euler angle change corresponding to movement speed, Euler angle residual analysis corresponding to movement deviation, and Euler angle average value corresponding to movement degree (S250). The muscle function evaluation device moves the time window (S260) and analyzes the inertial information characteristics of the inertial information sensor signal within the time window through the process described above (S230 to S250) (S250).

The muscle function evaluation device analyzes inertial information characteristics by repeating the process (S230 to S250) described above while shifting the time window from the inertial information sensor signal collected while the user performs rehabilitation training.

When the user completes rehabilitation training, feature analysis based on inertial information sensor signals also ends.

Figure 3 is a flowchart showing a method of analyzing an electromyogram signal according to an embodiment.

Referring to FIG. 3, when the muscle function evaluation device receives an EMG signal from the EMG sensor, it starts EMG analysis (S300).

The muscle function evaluation device sets a designated time window for the EMG signal (S310) and performs feature analysis of the EMG signal within the time window.

The muscle function evaluation device performs preprocessing on the EMG signal within the time window to remove noise and signals other than those to be analyzed (S320).

The muscle function evaluation device performs time domain analysis on the EMG signal within the time window (S330). The muscle function evaluation device performs absolute value processing on the amplitude of the EMG signal for time domain analysis of the EMG signal (S340).

The muscle function evaluation device divides the electromyography signal within the time window into detailed sections and provides information in the time domain such as the average value of the amplitude for each detailed section, the sum of the amplitude for each detailed section, the peak value for each detailed section, and the root mean square for each detailed section. Analyze electromyography characteristics (S350).

The muscle function evaluation device performs frequency domain analysis on the EMG signal within the time window (S360). The muscle function evaluation device performs frequency conversion processing on the EMG signal in order to analyze the EMG signal in the frequency domain (S370), and performs frequency conversion processing on the EMG signal in the frequency domain, such as MNF (mean frequency), MDF (median frequency), average power, and total power. Analyze electromyography characteristics (S380).

The muscle function evaluation device moves the time window (S390) and performs EMG feature analysis in the time domain and frequency domain through the same process (S320 to S380) on the EMG signal within the time window.

The muscle function evaluation device analyzes inertial information characteristics by repeating the process (S320 to S380) described above while moving the time window from the electromyography signal collected while the user is performing rehabilitation training.

When the user completes rehabilitation training, analysis of EMG characteristics based on EMG signals also ends.

Figure 4 is a flowchart showing a method of evaluating muscle function using inertial information features and electromyography features according to an embodiment.

Referring to Figure 4, when the user's rehabilitation training is completed, muscle function evaluation begins (S410).

The muscle function evaluation device acquires inertial information characteristics and electromyographic characteristics analyzed during the user's rehabilitation training (S420, S430).

The muscle function evaluation device integrates inertial information features and electromyography features to generate input information for the evaluation algorithm (S440). The evaluation algorithm may be an interpretable SVM (Interpretable Support Vector Machine).

The muscle function evaluation device extracts results from the input information using interpretable SVM (S450). Interpretable SVM classifies the positive class as normal and the negative class as patient (abnormal), and when classified as a negative class, solves an optimization problem to find the closest point to go to the positive class. It is a machine learning technique that analyzes the solution and determines what is lacking compared to the positive class. The interpretable SVM determines whether muscle activity is sufficient and joint movement is appropriate based on the input information, and outputs a positive or negative class depending on the judgment result.

The muscle function evaluation device outputs a muscle function evaluation result indicating the degree of muscle function through interpretable SVM results (S460).

The muscle function evaluation device can extract the cause of the lack of muscle function when muscle function is insufficient through the interpretable results of SVM (S470).

Figure 5 is a flowchart showing an example of a method for evaluating muscle function and analyzing recovery status before and after rehabilitation training of a user according to an embodiment.

Referring to Figure 5, when the user's rehabilitation training is completed, muscle function evaluation results are obtained through the process described in Figure 4.

The muscle function evaluation device starts evaluating muscle function and analyzing recovery status (S510).

The muscle function evaluation device analyzes the muscle function recovery state by using the results of inertial information sensor signal analysis before and after rehabilitation training, that is, the inertial information characteristics (S520).

The muscle function evaluation device analyzes the state of muscle function recovery using time domain-based EMG characteristics and domain-based EMG characteristics of EMG signals before and after rehabilitation training (S530).

The muscle function evaluation device analyzes the state of muscle function recovery by fusing the time domain-based EMG features and domain-based EMG features of the inertial information features before and after rehabilitation training and the EMG signals before and after rehabilitation training (S540).

The muscle function evaluation device stores the muscle function evaluation and muscle function recovery status analysis results (S550).

When a user or medical staff searches for the muscle function evaluation results and muscle function recovery state analysis results, the muscle function evaluation device visualizes and provides the muscle function evaluation results and muscle function recovery state analysis results (S560).

In this way, if the medical staff can check the muscle function evaluation results and muscle function recovery state analysis results, they can accurately determine the user's level of recovery, perform rehabilitation appropriate for that stage, and perform more appropriate exercises.

Figure 6 is a diagram showing a muscle function evaluation device according to an embodiment.

Referring to FIG. 6, the muscle function evaluation device 100 includes an inertial information collection unit 110, an EMG signal collection unit 120, an inertial information analysis unit 130, an EMG analysis unit 140, an evaluation unit 150, and Includes a storage unit 160. The muscle function evaluation device 100 may further include a communication unit 170.

The inertial information collection unit 110 collects inertial information sensor signals from the inertial information sensor during the user's rehabilitation training.

The EMG signal collection unit 120 collects EMG signals from the EMG sensor during the user's rehabilitation training.

The inertial information analysis unit 130 analyzes the inertial information sensor signal based on the method described in FIG. 2.

The EMG analysis unit 140 analyzes the EMG signal based on the method described in FIG. 3.

The evaluation unit 150 evaluates muscle function using inertial information characteristics and electromyography characteristics based on the method described in FIG. 4, and extracts the cause of the lack of muscle function when muscle function is insufficient.

Additionally, the evaluation unit 150 may analyze the user's muscle function recovery state based on the method described in FIG. 5.

The storage unit 160 stores the muscle function evaluation results and the muscle function recovery state analysis results by the evaluation unit 150.

Additionally, the muscle function evaluation results and muscle function recovery state analysis results stored in the storage unit 160 may be transmitted to a separate server through the communication unit 170. Additionally, the communication unit 170 can communicate with an inertial information sensor and an electromyography sensor within the rehabilitation device.

Figure 7 is a diagram showing a muscle function evaluation device according to another embodiment.

Referring to FIG. 7 , the muscle function evaluation device 200 may represent a computing device in which the muscle function evaluation method described above is implemented.

The muscle function evaluation device 200 may include at least one of a processor 210, a memory 220, an input interface device 230, an output interface device 240, a storage device 250, and a network interface device 260. there is. Each component is connected by a common bus 270 and can communicate with each other. Additionally, each component may be connected through an individual interface or individual bus centered on the processor 210, rather than through the common bus 270.

The processor 210 may be implemented in various types such as an application processor (AP), central processing unit (CPU), graphics processing unit (GPU), etc., and executes instructions stored in the memory 220 or the storage device 250. It may be any semiconductor device. The processor 210 may execute a program command stored in at least one of the memory 220 and the storage device 250. This processor 210 performs at least some functions of the inertial information collection unit 110, EMG signal collection unit 120, inertial information analysis unit 130, EMG analysis unit 140, and evaluation unit 150 described in FIG. 6. Program instructions for implementing can be stored in the memory 220 and controlled so that the operations described based on FIGS. 1 to 6 are performed.

Memory 220 and storage device 250 may include various types of volatile or non-volatile storage media. For example, the memory 220 may include read-only memory (ROM) 221 and random access memory (RAM) 222. The memory 220 may be located inside or outside the processor 210, and the memory 220 may be connected to the processor 210 through various known means. The memory 220 may implement the functions of the storage unit 160 described in FIG. 6.

The input interface device 230 is configured to provide data to the processor 210. For example, the input interface device 230 may provide an inertial information sensor signal and an electromyography signal to the processor 210.

The output interface device 240 is configured to output data from the processor 210. The output interface device 240 may output the muscle function evaluation result from the processor 210.

The network interface device 260 may communicate with another device, such as a separate server, through a wired network or a wireless network. The network interface device 260 may implement the functions of the communication unit 170 described in FIG. 6.

At least some of the muscle function evaluation methods according to embodiments of the present disclosure may be implemented as programs or software running on a computing device, and the programs or software may be stored in a computer-readable medium.

Additionally, at least some of the muscle function evaluation methods according to embodiments of the present disclosure may be implemented as hardware that can be electrically connected to a computing device.

Although the embodiments of the present disclosure have been described in detail above, the scope of the rights of the present disclosure is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present disclosure defined in the following claims are also possible. It falls within the scope of rights.

Claims (1)

In a method of evaluating the muscle function of a user who wears a rehabilitation device and performs rehabilitation training in a muscle function evaluation device,
During rehabilitation training, collecting inertial information sensor signals and electromyographic signals from the inertial information sensor and electromyographic sensor included in the rehabilitation device, respectively;
Analyzing inertial information features from the inertial information sensor signal,
Analyzing EMG characteristics from the EMG signal, and
Performing muscle function evaluation using the inertial information characteristics and electromyography characteristics analyzed during the rehabilitation training
Muscle function evaluation method including.

Images