KR20210058628A - Paralysis patient motion analysis monitoring system and method - Google Patents

Abstract

The present invention relates to a method for analyzing and monitoring the motion of a paralyzed patient. The method for analyzing and monitoring the motion of the paralyzed patient may include the steps of: receiving state information from a measurement terminal that includes a plurality of sensors and is attached to a part of the body of a patient to collect the state information of the patient; pre-processing motion information and an EMG signal included in the state information; applying the preprocessed motion information and the EMG signal to a pattern analysis tracking algorithm to derive whether paralysis is in progress; and determining whether the paralysis of the patient is in progress in consideration of the analysis result of the pattern analysis and tracking algorithm and the time interval of the movement of the patient. It is possible to evaluate a motor grade based on the EMG and movement patterns of the arms and legs of the patient.

Description

Paralysis patient motion analysis monitoring system and method {PARALYSIS PATIENT MOTION ANALYSIS MONITORING SYSTEM AND METHOD}

The present application relates to a paralyzed patient motion analysis monitoring system and method.

In modern society, the number of patients with neurological diseases and the number of neurological diseases-related surgeries are increasing due to aging and increased adult diseases. As the number of patients with neurological diseases increases, the importance of motor grade evaluation is increasing. The nervous system plays a role in regulating and controlling the activities of the body according to the situation.If a problem occurs in the peripheral nervous system, especially the peripheral nervous system, a degenerative change occurs in the motor neuron, which gradually causes weakness and atrophy of the limb, eventually resulting in death from muscle paralysis.

Currently, a motor grade measurement method using Manual Muscle Testing (MMT) Grading Scale is used to determine the state of neurological disease patients. Motor Grade (motor function assessment) is a scale representing the evaluation grade of Motor Response, the largest proportion of the Glasgow Coma Scale (GCS), for neurological disorder patients.

The motor grade measurement method is a method in which a clinician or a nurse randomly applies stimulation to a patient and subjectively judges the patient's response and movement to rate it. Since this is conducted in an analog method that is determined by the supervision of a medical staff, the measurement grade may appear different for each clinician or nurse, and this causes a problem in that treatment for patients is not unified.

The technology behind the present application is disclosed in Korean Patent Publication No. 10-1814293.

The present application aims to provide a motor function evaluation system and method capable of quantifying stimulation intensity and evaluating motor grade based on a patient's limb movement pattern and EMG according to the present invention to solve the problems of the prior art described above. do.

The present application is to solve the problems of the prior art described above, and aims to provide a motor function evaluation system and method including a clinical decision support device that provides a clinical analysis result through measurement of biosignal and biophysical information do.

The present application is to solve the problems of the prior art described above, and an object of the present invention is to provide a motor function evaluation system and method capable of objectifying and quantifying a patient's movement.

However, the technical problem to be achieved by the embodiments of the present application is not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, the paralysis patient motion analysis monitoring method according to an embodiment of the present application includes a plurality of sensors, and a measurement terminal that is attached to a part of the patient's body to collect patient status information Receiving the state information from the state information, pre-processing the motion information and the EMG signal included in the state information, applying the pre-processed motion information and the EMG signal to a pattern analysis tracking algorithm to derive whether the paralysis progresses And determining whether the patient is paralyzed in consideration of an analysis result of the pattern analysis tracking algorithm and a time interval of the patient's movement.

In addition, the paralysis patient's motion analysis and monitoring method includes receiving information about the intensity of stimulation applied to a part of the patient's body using a stimulation terminal from the stimulation terminal, and receiving after applying a certain stimulation to the patient using the stimulation terminal. It may further include the step of evaluating the motor response (Motor Response) of the patient in consideration of the state information.

In addition, in the step of evaluating the patient's motor response, the patient's motor response may be evaluated by comparing the analysis result of the pattern analysis tracking algorithm with the patient's motor response scale divided into a plurality of stages.

In addition, the pre-processing may include performing pre-processing of removing the gravitational component by applying motion information included in the state information to the first filter, and applying the motion information from which the gravitational component has been removed to a signal vector size algorithm. Extracting intensity data, applying motion information from which the gravity component has been removed to a second filter, and extracting distance data by performing a trapezoidal operation, and a third filter for an EMG signal included in the state information And performing pre-processing of removing noise by applying to, and performing pre-processing of applying the motion intensity data, the distance data, and the EMG signal to a fourth filter.

In addition, the step of deriving whether or not the paralysis progresses may include determining whether the motion intensity data exceeds a preset reference intensity value, and determining whether the motion intensity data exceeds the preset reference intensity value, When the motion intensity data exceeds the preset reference intensity value, it is determined that motion has occurred on the sensor, and when the motion intensity data does not exceed a preset reference intensity value, it is determined that no motion has occurred on the sensor. And, it may be to wait for reception of the preprocessed state information.

In addition, the step of deriving whether the paralysis progresses, further comprising determining whether the EMG signal exceeds a preset reference EMG signal value when it is determined that the motion on the sensor has occurred, wherein the EMG signal is The step of determining whether or not a preset reference EMG signal value is exceeded may include, when the EMG signal exceeds the preset reference EMG signal value, it is determined that the motion on the sensor is a spontaneous movement of the patient, and the EMG signal is If it does not exceed the preset reference EMG signal value, it may be determined that the patient is not spontaneous movement and wait for reception of the pre-processed state information.

In addition, the step of deriving whether the paralysis progresses may include comparing the nth motion information and the n-1th motion information to derive a time interval of the patient's motion when it is determined that the motion on the sensor is a voluntary motion of the patient Step, Comparing the nth EMG signal and the n-1th EMG signal to derive a patient's EMG signal intensity trend, and based on the derived time interval of the patient's movement and the patient's EMG signal intensity trend, It may further include analyzing the movement trend.

In addition, the step of determining whether the patient's paralysis progresses may be determined as paralysis progression when the time interval of the movement time continues to increase by comparing the time point at which the current movement occurred based on the time at which the past movement was measured. I can.

In addition, the paralysis patient motion analysis monitoring method may further include providing a notification to the central control management terminal when it is determined that the paralysis is progressing as a result of analyzing the trend of the patient's motion.

In addition, the paralysis patient motion analysis monitoring method further comprises the step of tracking the motion trajectory of the patient's arm based on the motion information collected from the measurement terminal attached to the patient's arm, the motion trajectory of the patient's arm The step of tracking may include receiving acceleration, angular velocity, and quaternion values from a six-axis motion sensor among the plurality of sensors, and deriving a moving distance of the patient's arm through the acceleration value and the angular velocity value. , Deriving a rotated axis and a rotated angle by the measurement terminal using the quaternion value, and taking into account the derived movement distance of the patient's arm, the rotated axis and the rotated angle, It may include the step of tracking the motion trajectory.

In addition, the first filter for removing the gravitational component is an IIR Highpass filter, and the step of performing the pretreatment of removing the gravitational component may include applying the first filter to remove the gravitational component and the intensity of movement of the patient. Preprocessing can be performed so that the value is expressed as a preset value.

According to an embodiment of the present application, as a motion analysis monitoring system for a paralyzed patient, a measurement terminal including a plurality of sensors and attached to a part of the patient's body to collect state information of the patient, and the state information collected from the measurement terminal are patterned. A motion analysis device for deriving whether or not the patient is paralyzed by applying the analysis tracking algorithm, wherein the analysis device includes a receiving unit receiving the status information obtained from the measurement terminal, and a plurality of filters and preprocessing the status information It may include a pre-processing unit that performs pre-processing by applying to an algorithm, and an analysis unit that analyzes whether paralysis has progressed by applying the state information pre-processed by the pre-processing unit to a pattern analysis tracking algorithm.

In addition, the paralysis patient motion analysis monitoring system further includes a stimulation terminal that applies stimulation to a part of the patient's body, and the analysis device includes the state information received when a certain stimulation is applied to the patient using the stimulation terminal. It may further include an evaluation unit for evaluating the motor response of the patient in consideration of.

In addition, the paralysis patient motion analysis monitoring system may further include a providing unit for providing a notification to the central control management terminal when the analysis result of the trend analysis of the patient's motion is determined to be paralysis progression.

The above-described problem solving means are merely exemplary and should not be construed as limiting the present application. In addition to the above-described exemplary embodiments, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-described problem solving means of the present application, objective evaluation can be performed by establishing a motor grade evaluation system through objectification of stimulation intensity, biometric signal, and biophysical quantity.

According to the above-described problem solving means of the present application, it is possible to provide a clinical analysis result through measurement of bio-signal and bio-physical quantity information.

According to the above-described problem solving means of the present application, system verification and reliability can be secured through clinical trials in medical institutions.

According to the above-described problem solving means of the present application, stimulation intensity may be measured based on a load cell, a biophysical quantity may be measured based on a 6-axis motion sensor, and a biological signal may be measured based on an EMG sensor.

According to the above-described problem solving means of the present application, it is possible to provide an exercise function evaluation system that has low space constraints, enables communication through Bluetooth, and can be used for medical use by using a device worn on a part of the body of a patient (user). .

According to the above-described problem solving means of the present application, accurate motor grade evaluation can be performed by quantifying the movement of the limb by an angle.

However, the effect obtainable in the present application is not limited to the above-described effects, and other effects may exist.

1 is a schematic configuration diagram of a paralysis patient motion analysis monitoring system according to an embodiment of the present application.
2 is a schematic block diagram of a motion analysis apparatus according to an embodiment of the present application.
3 is a schematic operation flowchart of a pre-processing method of a method for analyzing and monitoring a motion of a paralyzed patient according to an embodiment of the present application.
4 is a schematic operation flowchart of a pattern analysis tracking algorithm of a paralysis patient motion analysis monitoring method according to an embodiment of the present application.
5 is a schematic flowchart of an operation analysis and monitoring method of a paralyzed patient according to an embodiment of the present application

Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present application. However, the present application may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts not related to the description are omitted in order to clearly describe the present application, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the present specification, when a part is said to be "connected" with another part, it is not only the case that it is "directly connected", but also "electrically connected" or "indirectly connected" with another element interposed therebetween. "Including the case.

Throughout the present specification, when a member is positioned "on", "upper", "upper", "under", "lower", and "lower" of another member, this means that a member is located on another member. This includes not only the case where they are in contact but also the case where another member exists between the two members.

In the entire specification of the present application, when a certain part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

1 is a schematic configuration diagram of a paralysis patient motion analysis monitoring system according to an embodiment of the present application.

According to an embodiment of the present application, the paralysis patient motion analysis monitoring system 1 quantitatively measures the paralysis that may progress during a neurological surgery (e.g., brain, spine) patient entering the intensive care unit after surgery, and promptly informs the medical staff. It can provide a reminder. In addition, the paralysis patient motion analysis monitoring system (1) measures the patient's motion using an acceleration sensor, measures the patient's EMG using an EMG (electromyogram) sensor, and calculates the interval of the patient's actual motion based on the two data. It can be provided quantitatively.

On the other hand, in the case of neurosurgery patients, a nurse should measure the patient's response speed and posture by applying a certain stimulus to the patient in order to measure the consciousness assessment once an hour. (GCS measurement) However, due to the lack of medical staff, the actual measurement is being performed every 5 to 6 hours, and it is a golden time that an average of 2 hours can recover after the patient's paralysis progresses. The paralysis patient motion analysis monitoring system 1 can prevent medical accidents by immediately notifying the hospital system of the patient's paralysis progression even in the absence of a medical staff.

Referring to FIG. 1, the paralysis patient motion analysis monitoring system 1 may include a motion analysis device 10, a measurement terminal 20, and a stimulation terminal 30. However, the configuration of the paralysis patient motion analysis monitoring system 1 is not limited thereto. For example, the paralysis patient motion analysis monitoring system 1 may include an external server (not shown). The external server (not shown) may include a hospital server, a hospital terminal, a clinical trial acquisition server, and the like. The paralysis patient motion analysis monitoring system 1 may obtain patient medical record information and clinical trial information from an external server (not shown) through a network.

In addition, the paralyzed patient motion analysis monitoring system 1 may perform clinical trial evaluation by correcting the patient's safety after obtaining an IRB (Institutional Review Board) from an external server (not shown) for verification of the motion analysis device 10. .

According to the exemplary embodiment of the present application, the motion analysis apparatus 10 may derive whether the patient is paralyzed by applying the state information collected from the measurement terminal 20 to an analysis tracking algorithm. The pattern analysis tracking algorithm may be an algorithm for analyzing a patient's limb pattern. The pattern analysis tracking algorithm may be an algorithm for estimating a patient's spontaneous motion. In addition, the motion analysis device 10 is attached to the patient's limbs (eg, arms, legs) with a module (measurement terminal 20) with an accelerometer built in to collect motion information measuring the motion of the patient. have. In addition, the motion analysis device 10 collects an EMG signal obtained by measuring the EMG signal of the patient by attaching a module (measurement terminal 20) with an EMG sensor built-in to the patient's limb (eg, arm, leg). I can.

In addition, the motion analysis apparatus 10 may determine that the patient's movement (acceleration) exceeds a certain value, but the EMG signal does not exceed a certain value, as not the patient's own voluntary movement. In addition, the motion analysis apparatus 10 may determine that the patient's movement (acceleration) exceeds a predetermined value, but when the EMG signal exceeds a predetermined value, the patient's own voluntary movement. In addition, in the case of the patient's own voluntary movement, the motion analysis apparatus 10 measures the motion interval (time interval) to measure whether the time of the interval becomes longer or shorter, and the interval (time interval) is longer than a predetermined time. In the case of losing, it can be determined that the paralysis is currently in progress.

In addition, the motion analysis device 10 may provide a notification to a central control management system (eg, a medical staff standby server or terminal) when it is determined that the paralysis is in progress (for example, when the interval is longer than a certain period of time). have. In addition, the motion analysis apparatus 10 may track a trajectory (motion trajectory) of the patient's arm based on data collected from a module (measurement terminal 20) attached to the patient's arm. In addition, the motion analysis apparatus 10 may collect information on the intensity of the stimulation (eg, physical pressure) of the stimulation terminal 30 that applies stimulation to the patient. In addition, the motion analysis apparatus 10 may measure and determine a patient's response in response to the pressure intensity (stimulation intensity).

According to an embodiment of the present application, the measurement terminal 20 may include a plurality of sensors. In addition, the measurement terminal 20 may be attached or worn on a part of the patient's body to collect state information of the patient. The plurality of sensors may include an acceleration sensor, a G-sensor, a 3-axis acceleration sensor, a 6-axis motion sensor, an EMG sensor, a temperature sensor, an optical sensor, and the like. For example, the measurement terminal 20 may be formed in an arm band type (bracelet) and worn on a part of the patient's body to collect state information of the patient. In addition, the measurement terminal 20 may be formed in a patch shape and attached to a part of the patient's body to collect state information of the patient.

The patient's state information may include motion information, EMG signals, bio signals, and the like. The motion information may include movement distance, angle, intensity, direction, acceleration, angular velocity, quaternion information, and the like. As an example, the biosignal may include at least one of heart rate information, respiration volume information, pupil size information, blood oxygen concentration information, blood pressure information, pulse information, body temperature information, electrocardiogram information, blood flow image information, and body composition analysis information. .

According to an embodiment of the present application, the measurement terminal 20 may measure motion information using an acceleration sensor (6-axis motion sensor). Motion information acquired using an acceleration sensor (6-axis motion sensor) may include acceleration, angular velocity, and quaternion values. For example, the measurement terminal 20 may use a six-axis motion sensor to improve an error for motion noise that occurs when only a three-axis accelerometer is used, but is not limited thereto. By using a 6-axis motion sensor, it is possible to minimize the error that occurs when a direction change occurs in a dynamic state. The 6-axis acceleration sensor may be a sensor with a built-in 3-axis accelerometer and a 3-axis gyroscope. The measurement terminal 20 may obtain an acceleration signal from a 6-axis motion sensor. The measurement terminal 20 may acquire gravitational acceleration from a 6-axis motion sensor. In addition, the measurement terminal 20 may detect a change in the location of the center point of the measurement terminal 20. In addition, the acceleration sensor is a sensor that measures dynamic forces such as acceleration, vibration, and impact of an object, and refers to a sensor that enables detection of a motion state of an object.

In addition, the measurement terminal 20 may be designed as a six-axis accelerometer driving circuit to measure the movement of the user's hand and arm operating to measure the motor function, and a plurality of parameters calculated in the process of performing the motor function measurement Can be measured. As an example, a plurality of measured parameters are obtained from a 6-axis motion sensor, from a third axis (Z axis) and a G sensor that are perpendicular to the horizontal axis (X axis), vertical axis (Y axis), and vertical axis (Y axis). It may include parameters corresponding to each of the acquired G1, G2, and G3, but is not limited thereto.

As another example, the measurement terminal 20 may measure a patient's biological signal using an optical heart rate sensor based on a technology called Pulse Oximetry. In this case, the measured patient's vital signal may be heart rate information. The heart rate sensor uses the principle that the optical response differs when hemoglobin contains oxygen in the blood and when oxygen is depleted, and uses the difference in the degree of reflection by periodically shooting an infrared or red LED from the wrist to the skin. It may be a sensor that calculates the heart rate.

As another example, the measurement terminal 20 may communicate with the motion analysis device 10 based on Bluetooth. When network communication with the motion analysis device 10 is impossible, the measurement terminal 20 may store state information collected through a sensor in a storage unit (not shown) included in the measurement terminal 20. When network communication with the motion analysis device 10 is possible, the measurement terminal 20 may provide state information collected through a sensor to a storage unit (not shown) included in the measurement terminal 20. That is, the measurement terminal 20 may collect status information even when network communication is disconnected.

Meanwhile, the measurement terminal 20 may be designed as a 6-axis motion sensor-based band-type terminal circuit, and may include a band-type terminal wireless communication circuit. In addition, the measurement terminal 20 may be an EMG electrode-based arm band type terminal. The measurement terminal 20 is an arm band type terminal and may include a wireless communication circuit.

According to another embodiment of the present application, the measurement terminal 20 includes a camera module (not shown) and may acquire state information of a user by photographing movements of a patient's body. For example, the camera module (not shown) may collect motion information for estimating a change in the position and angle of the measurement terminal 20 based on the measurement terminal 20 attached or worn on a part of the patient's body.

According to the exemplary embodiment of the present application, the stimulation terminal 30 may apply stimulation to a part of the patient's body. For example, the stimulation terminal 30 may apply stimulation to the patient's head or chest. The stimulation terminal 30 may be a tool for determining the degree of voluntary movement of the patient. The stimulation terminal 30 may measure a value of the intensity of pressure applied to a part of the patient's body by a doctor or a nurse using the stimulation terminal 30. The stimulation terminal 30 may be formed based on a load cell. Since the stimulation terminal 30 is formed based on a load cell, the strength of the stimulation can be quantified. A load cell is a sensor that measures load, that is, load, load, and force, and can convert and output a measured pressure value into an electrical signal. The stimulus terminal 30 may include a wireless communication circuit, and may provide information on the intensity of the stimulus applied by the stimulus terminal 30 to the motion analysis device 10 through a network.

According to another embodiment of the present application, although the figure shows that the motion analysis apparatus 10 is separately divided, the motion analysis apparatus 10 may be provided inside the measurement terminal 20. A module attached to the limb (acceleration sensor, EMG sensor built-in) can determine whether the patient's own voluntary movement is true or not.

Meanwhile, the paralysis patient motion analysis monitoring system 1 may further include a motion analysis server (not shown) for storing the determined patient's progression of paralysis and the evaluated motion response information of the patient. The motion analysis server (not shown) may store state information obtained from the measurement terminal 20 and whether the patient's paralysis progression determined by the motion analysis device 10 and the evaluated motion response information of the patient are stored. In addition, the motion analysis server (not shown) may convert and store the state information obtained from the measurement terminal 20 into a data set.

In addition, the motion analysis server (not shown) may build a web server for data collection of the distributed paralysis patient motion analysis monitoring system 1. The motion analysis server (not shown) may collect data received from the motion analysis device 10. In addition, the motion analysis server (not shown) may build a database for systematic management of collected data. In addition, the motion analysis server (not shown) may build a database for management and storage of data collected from the measurement terminal 20.

2 is a schematic block diagram of a motion analysis apparatus according to an embodiment of the present application.

Referring to FIG. 2, the motion analysis apparatus 10 may include a receiving unit 11, a preprocessing unit 12, an analysis unit 13, an evaluation unit 14, and a providing unit 15.

According to an embodiment of the present application, the receiving unit 11 may receive status information obtained from the measurement terminal 20. The receiving unit 11 may receive state information including motion information and an EMG signal from the measurement terminal 20. For example, the motion information is information including a movement distance, angle, intensity, direction, etc. of the patient's arm or leg, and may include acceleration, angular velocity, and quaternion values of the measurement terminal 20. In addition, the EMG signal may be information collected using an EMG sensor. Electromyography is a test to see if there are abnormalities in the peripheral nerves, nerves, and muscles by analyzing electrical signals generated from nerves and muscles through a machine.

In addition, the receiving unit 11 may receive information on the intensity of stimulation applied to a part of the patient's body by using the stimulation terminal 30 from the stimulation terminal 30. The stimulation intensity information may be information related to an intensity applied by a doctor or a nurse to a part of the patient's body (eg, head or chest) using the stimulation terminal 30. The receiving unit 11 may receive information on the intensity of the stimulus so that the intensity of the stimulus (compression) by a doctor or a nurse in order to evaluate the patient's motor response is kept constant.

Meanwhile, the receiving unit 11 may receive personal information of a patient (user), medical treatment information, and the like from an external server (not shown). For example, the personal information information may include the age, name, address, resident registration number, insurance card number, and the like of the patient (user). The treatment information may include a result of a patient (user) visiting a hospital and a doctor's treatment, a result of performing an MRI, CT, X-ray, ultrasound examination, and the like.

In the description of the embodiment of the present application, the external server (not shown) may be a hospital server. The hospital server (not shown) is a terminal owned by the hospital to integrate and manage the personal information and treatment information of a plurality of patients who visit the hospital, and to handle treatment reception and treatment reservation procedures for a given user. Or it could be a server.

Although not shown in the drawing, the motion analysis apparatus 10 may include a communication unit (not shown). For example, the communication unit (not shown) may directly communicate using a mobile communication network, Wi-Fi, etc., and may be provided with Bluetooth, and may communicate with the measurement terminal 20 in a short distance to receive status information. In addition, the communication unit (not shown) may be designed as a Bluetooth-based wireless communication circuit for data synchronization between the measurement terminal 20 and the motion analysis device 10 such as a smart device application. In order to form a wireless network based on Bluetooth communication, a virtual network using a dummy file can be constructed, and power consumption is minimized by using a Bluetooth low power profile, and a network connected to the measurement terminal 20 and the motion analysis device 10 is established. You can also build it.

According to the exemplary embodiment of the present disclosure, the preprocessor 12 may perform preprocessing by applying the state information to a plurality of filters and preprocessing algorithms. The preprocessor 12 may perform preprocessing to quantify a plurality of parameters included in the state information. For example, the preprocessor 12 may preprocess motion information, which is measurement data in the form of a time series obtained from the measurement terminal 20. The preprocessor 12 may preprocess motion information, which is measurement data in a time series format, in the form of N repetition cycles. Since it is difficult to track a data pattern in the measurement data in a time series format that changes with time, the preprocessor 12 may preprocess the measurement data in a time series format in a cycle form in order to avoid time dependence.

3 is a schematic operation flowchart of a pre-processing method of a method for analyzing and monitoring a motion of a paralyzed patient according to an embodiment of the present application.

For example, referring to FIG. 3, in step S210, the preprocessor 12 may receive motion information included in the state information acquired using the measurement terminal 20. In other words, the preprocessor 12 may receive raw data (raw data) related to motion information acquired from the 6-axis motion sensor of the measurement terminal 20.

In step S211, the preprocessor 12 may perform preprocessing of removing the gravity component by applying motion information included in the state information to the first filter. The first filter for removing the gravity component may be an IIR Highpass filter. The preprocessor 12 may apply the first filter to remove the gravitational component, and perform preprocessing so that the intensity of the patient's movement is expressed as a preset value (eg, a value between 0 and 2). In other words, the preprocessor 12 may remove the gravity component by applying motion information included in the state information to the IIR Highpass. IIR Filter (Infinite Impulse Response Filter) is a type of digital filter. Filtering is performed by recursively applying the value of the input signal and the value of the output signal. It is an iterative expression in the form of an implementation expression, and the impulse response, a characteristic function, has an infinite length. For example, the preprocessor 12 applies the state information to an IIR Highpass filter having a cutoff frequency of 0.25 Hz to remove the gravitational component so that the intensity of the patient's motion is expressed as a value between 0 and 2. Pre-treatment can be performed.

In step S212, the preprocessor 12 may extract motion intensity data by applying motion information from which the gravity component has been removed to a signal vector size algorithm. In other words, the preprocessor 12 may extract motion intensity data by applying motion information (motion intensity value) from which gravity components are removed by applying to the first filter to a Signal Vector Machine algorithm. For example, the preprocessor 12 may represent the patient's movement as an intensity of an acceleration value and convert it into a numerical value. The acceleration value comes from the sensor as three values of the x, y, and z axes, and the preprocessor 12 can express the intensity of the patient's motion through a signal vector machine algorithm that processes it as one representative value. .

In step S213, the preprocessor 12 may perform pre-processing of applying the motion intensity data extracted in step S212 to the fourth filter. In other words, the preprocessor 12 may perform preprocessing by using a moving average filter (MAF) to smooth the raw data of the motion intensity data in which the change motion of the data is severe.

In step S221, the preprocessor 12 may perform preprocessing by applying motion information from which the gravity component has been removed to the second filter. In other words, the preprocessor 12 may perform preprocessing of applying motion information from which the gravity component has been removed by applying to the first filter to the second filter (eg, Kalman filter). The motion information includes values such as acceleration and angular velocity, and the acceleration value may include motion acceleration and gravitational acceleration. When moving in the direction in which the gravity acceleration acts, the motion acceleration is transformed by the middle age acceleration. To solve this problem, the preprocessor 12 may obtain an acceleration value and an angular velocity value by applying a Kalman filter, and then obtain an acceleration value to which a slope value is not added through the Kalman filter.

Also, the preprocessor 12 may calculate an acceleration value from which the slope value is removed by applying the acceleration value and the slope value included in the motion information to the Kalman filter. In this case, the Kalman filter may consist of a prediction and an update process. For reference, the preprocessor 12 may remove noise using a Kalman filter. In general, the acceleration value may include motion acceleration and gravitational acceleration. When moving in the direction in which the gravitational acceleration acts, the motion acceleration may be deformed by the gravitational acceleration. To solve this problem, in the present application, the Kalman filter may be applied to estimate the acceleration value. If the distance predicted through integration is diverged due to noise (eg, gravitational acceleration value, etc.), it may cause a serious problem, so filter processing is absolutely necessary. In this application, the Kalman filter is applied to solve the noise. For example, the Kalman filter is a filter that recursively processes an existing measured value containing noise. The preprocessor 12 may perform optimal statistical prediction on the current state by using the Kalman filter. In addition, the preprocessor 12 may calculate an estimated value through a prediction process and an update process included in the Kalman filter.

In step S222, the preprocessor 12 may extract distance data by performing a trapezoidal operation on the motion information preprocessed by applying the Kalman filter. In other words, the preprocessor 12 may extract distance data by applying the motion information preprocessed to the Kalman filter twice to the trapezoidal operation method. The preprocessor 12 obtains the distance moved through the process of integrating the acceleration value included in the preprocessed motion information twice by applying it to the Kalman filter, but the general integration is a limitation of sampling and an error occurs during the quantization process. In order to compensate for the error that occurs, it is possible to solve the error that occurs during double integration by applying a trapezoidal calculation method.

Trapezoidal Method is a method to derive a value for the current distance by calculating the difference between the long side and the small side of the trapezoid with respect to the previous value and the current value, and then multiplying the time corresponding to the height to derive the area of the trapezoid. In other words, the preprocessor 12 applies the preprocessed motion information to the Kalman filter in the trapezoidal calculation method to derive the difference between the long side and the small side of the trapezoid, multiply the height (time), and calculate the area of the parallelogram. After deriving, the value of the current speed (distance) can be derived.

In step S223, the preprocessor 12 may perform pre-processing by applying the motion intensity data extracted in step S222 to the fourth filter. In other words, the preprocessor 12 may perform preprocessing by using a moving average filter (MAF) to smooth the raw data of distance data in which data movement is severe.

In step S231, the preprocessor 12 may receive an EMG signal included in the acquired state information using the measurement terminal 20. In other words, the preprocessor 12 may receive raw data (raw data) related to an EMG signal obtained from an EMG sensor included in the measurement terminal 20.

In step S332, the preprocessor 12 may perform preprocessing of removing noise by applying the EMG signal included in the state information to the third filter. In other words, the preprocessor 12 may perform preprocessing of removing noise by applying a high pass filter to the EMG signal. In addition, the preprocessor 12 may perform preprocessing by applying an EMG signal to a low pass filter (LPF) in order to remove high frequency noise of raw data from the EMG sensor.

In step S333, the preprocessor 12 may perform preprocessing by applying the EMG signal extracted in step S232 to the fourth filter. In other words, the preprocessor 12 may perform preprocessing by using a moving average filter (MAF) to smooth the raw data of the EMG sensor in which data changes and movements are severe.

In step S240, the analysis unit 13 may apply the motion intensity, distance data, quaternion, and EMG signals preprocessed by the preprocessor 12 to the pattern analysis tracking algorithm.

In step S250, the analysis unit 13 may derive whether the patient is paralyzed based on the pattern analysis tracking algorithm.

According to an exemplary embodiment of the present disclosure, the analysis unit 13 may analyze whether the paralysis progresses by applying the state information preprocessed by the preprocessor 12 to a pattern analysis tracking algorithm. The analysis unit 13 may analyze whether the paralysis progresses by applying the motion intensity, distance data, quaternion, and EMG signals that have been preprocessed by the preprocessor 12 to a pattern analysis tracking algorithm.

4 is a schematic operation flowchart of a pattern analysis tracking algorithm of a paralysis patient motion analysis monitoring method according to an embodiment of the present application.

For example, referring to FIG. 4, in step S241, the analysis unit 13 may receive motion intensity, distance data, quaternion, and EMG signals that have been preprocessed by the preprocessor 12. The analysis unit 13 may receive motion intensity data, distance data, quaternion, and root-degree signals that have been subjected to steps S210 to S233 described above. The quaternion may be a value derived to express an attitude angle in a dimensional space. Quaternions are often used to define the 6 Degree of Freedom (6DOF) motion of a rigid body. Quaternion (quaternion) exhibits excellent performance in setting the rotation or orientation of an object, and in particular, quaternion is used to overcome various problems such as gimbal lock that occurs in the calculation of Euler angles. use. Compared to the rotation matrix using 9 elements, it can be expressed concisely with 4 elements.

In step S242, the analysis unit 13 may determine whether the motion intensity data exceeds a preset threshold. For example, the analysis unit 13 may select a preset reference intensity value by determining a magnitude of intensity generated by a medical action (eg, injection, padding, etc.) applied to a patient. The motion intensity value may be expressed as a value between 0 and 2 through filtering of the signal vector size algorithm (SVM algorithm) and the first filter (IIR filter). As another example, the analysis unit 13 may set a preset reference intensity value to a predetermined threshold between 0 and 2. The analysis unit 13 may set the shaking due to a medical action applied to the patient to a predetermined value between 0 and 2 (threshold).

Illustratively, examples of medical actions applied to a patient may include injections, patting, and the like. Movement generated from a patient wearing or attaching the measurement terminal may include a voluntary movement of the patient himself or a movement caused by a medical action applied to the patient, that is, movement by another person. The analysis unit 13 may derive a more accurate paralysis progression by determining the voluntary movement of the patient based on the movement intensity data of the patient.

In step S243, when the motion intensity data exceeds a preset reference intensity value as a result of the determination in step S242, the analysis unit 13 may determine that a motion on the sensor has occurred. In other words, the analysis unit 13 may determine that the patient's movement (acceleration) exceeds a certain value, but the EMG signal exceeds a certain value as the patient's voluntary movement. For example, the analysis unit 13 determines whether the preprocessed motion intensity value exceeds 2, and when the motion intensity value exceeds a preset reference intensity value (eg, 2), It can be determined that motion has occurred on the sensor. The motion on the sensor may include a change in at least one of a distance, an angle, and an intensity direction of the measurement terminal.

In step S244, if the motion intensity data does not exceed a preset reference intensity value as a result of the determination in step S242, the analysis unit 13 may determine that no motion has occurred on the sensor and wait for reception of the preprocessed state information. . In other words, the analysis unit 13 may determine that the patient's movement (acceleration) exceeds a predetermined value, but the EMG signal does not exceed a predetermined value, as not the patient's spontaneous movement. When the preprocessed motion intensity value is less than a predetermined value (eg, 2), the analysis unit 13 may determine that no motion has occurred on the sensor and wait for reception of the preprocessed motion intensity value.

In step S245, when it is determined that motion on the sensor has occurred in step S243, the analysis unit 13 may determine whether the EMG signal exceeds a preset reference EMG signal value. For example, the analysis unit 13 may select a preset EMG signal value by discriminating an EMG signal generated by a medical action applied to a patient (eg, injection, padding, etc.). In other words, the analysis unit 13 may determine whether the motion on the sensor is a voluntary motion of the patient or a medical action applied to the patient. In addition, when the EMG signal does not exceed a preset reference EMG signal value in step S243, the analysis unit 13 may determine that the patient's voluntary motion is not and wait for reception of preprocessed state information.

In step S246, when the EMG signal exceeds a preset reference EMG signal value in step S245, the analysis unit 13 may determine that the motion on the sensor is a spontaneous motion of the patient. The patient's voluntary movement may mean that the patient himself or herself raises arms or legs without the help of others.

In step S247, when it is determined that the motion on the sensor is a voluntary motion of the patient in step S246, the analysis unit 13 may compare the nth motion information and the n-1th motion information to derive the time interval of the patient's motion. have. The analysis unit 13 may derive an EMG intensity trend by comparing the current motion information received by the receiving unit 11 with the motion information received at a previous time at the current point in time. The motion information may include a distance, an angle, an intensity, and a direction that have been moved.

In step S248, the analysis unit 13 may derive a trend of the patient's EMG signal strength by comparing the n-th EMG signal and the n-1 th EMG signal. The analysis unit 13 may compare the current EMG signal received by the receiving unit 11 with the EMG signal received at a previous time at the current point in time to derive a trend of the patient's EMG signal strength.

In step S249, the analysis unit 13 may analyze the motion trend of the patient based on the derived time interval of the patient's motion and the trend of the patient's EMG signal strength. In the case of the patient's own movement, the analysis unit 13 may measure whether the interval time is lengthened or shortened by measuring the movement interval (time interval).

In step S250, the analysis unit 13 may derive whether the patient is paralyzed based on the analysis result in step S249. The analysis unit 13 may compare the time point at which the current motion has occurred based on the time at which the past motion has been measured, and determine that the paralysis progresses when the time interval of the motion time continues to increase.

In addition, the analysis unit 13 may determine that the paralysis of the patient is accelerated when the interval of the movement time continuously increases by comparing the time point at which the current movement has occurred based on the time at which the movement was measured in the past. On the other hand, the analysis unit 13 may determine that if the movement interval is shortened, the symptoms of paralysis are alleviated favorably.

According to an exemplary embodiment of the present application, the evaluation unit 14 may evaluate a motor response of the patient in consideration of state information received after applying a certain stimulus to the patient using the stimulation terminal 30. For example, the state information received after applying a certain stimulation to the patient using the stimulation terminal 30 may be information related to a range of motion (ROM).

Range of Motion (ROM) is a basic technique used to evaluate motion and to initiate motion in therapeutic intervention programs. Movement is essential for performing functional activities by moving bones by muscles or external forces in various patterns or ranges of joint motion. When a person moves, it is a complex regulation of muscle activity that carries and regulates information from the central nervous system. Bones move in relation to each other in adjacent joints. The integrity and flexibility of the soft tissue passing over the joint, as well as the structure of the joint, affect the range of motion that occurs between two adjacent bones. In general, the maximum range of motion possible is called the range of motion of the joint (ROM).

When a body segment moves through the range of motion of the joint, it is affected by the muscles in that part, the surface of the joint, the joint capsule, ligaments, fascia, blood vessels, and nerves. The activity of the joint motion range is easily explained by the joint range and the muscle range. Terms such as flexion, practice, abduction, pronation, and rotation are used to describe joint range. The range of motion of the joint is generally measured with a goniometer and recorded in degrees. In the present application, the joint motion range of the patient (user) may be measured using the measurement terminal 20. The measurement terminal 20 may provide a numerical value for the range of motion of the patient (user) based on a plurality of sensors.

According to an embodiment of the present application, the receiving unit 11 may receive acceleration, angular velocity, and quaternion values obtained using the 6-axis motion sensor of the measurement terminal 20. The receiver 11 may receive acceleration, angular velocity, and quaternion values from a 6-axis motion sensor among a plurality of sensors. The preprocessor 12 may perform preprocessing of acceleration, angular velocity, and quaternion values obtained using a 6-axis motion sensor. The analysis unit 13 may obtain the movement intensity and the movement distance by using the preprocessed acceleration, angular velocity, and quaternion values. The analysis unit 13 may derive the moving distance of the patient's arm through the acceleration value and the angular velocity value based on the acceleration, angular velocity, and quaternion values received by the receiving unit 11. In addition, the evaluation unit 14 may track the motion trajectory of the patient's arm based on the motion information collected from the patient's attached measurement terminal 20. The analysis unit 13 may track the trajectory of the patient's arm by applying the preprocessed acceleration, angular velocity, and quaternion values to an arm pattern analysis tracking algorithm. The analysis unit 13 may derive the rotation axis and the rotation angle of the measurement terminal 20 by using the quaternion value. The analysis unit 13 may use the quaternion value to obtain the axis at which the sensor rotates and the angle at which the sensor rotates. The analysis unit 13 may track the motion trajectory of the patient's arm in consideration of the derived movement distance of the patient's arm, the rotated axis, and the rotated angle. The movement distance is calculated through the acceleration value and the angular velocity value, and the rotation axis and angle are calculated through the quaternion value, and the trajectory of the arm can be tracked.

The evaluation unit 14 is based on the pattern analysis tracking algorithm in the analysis unit 13, i) is it pinched and goes out, ii) is it curled in or cannot come back, iii) the reaction rate is the hand of the nurse (doctor). It is possible to evaluate the trajectory of the patient's arm (movement trajectory) by situations such as whether he cannot hit it and floats to one side.

In addition, the evaluation unit 14 may evaluate the patient's motor response by comparing the analysis result of the pattern analysis tracking algorithm with the patient's motor response scale divided into a plurality of stages. The motor response can be divided into 1 to 6 steps. Each stage of the motor response corresponds to each of 1 to 6 points, and the Motor Grade (motor function assessment) is to assess the amount of exercise of the muscles, which is most often used after spinal surgery to assess with the BEST motor and also assesses muscle strength. In addition to Motor Grade, SLR (straight leg raising, assessing how many degrees of leg can be lifted to a person with back pain after surgery), and dorsi flexion are also assessed. As the grade decreases, paralysis appears.

Evaluation unit (14) Motor Grade 1 = Non-Contraction patient cannot move, Motor Grade 2 = Flicker or trace of Contraction Patient cannot move, but muscle contraction is visible (the degree of muscle flicker), Motor Grade 3 = Active movement, with gravity eliminated, the degree of horizontal movement of the patient while lying down (can't beat gravity), Motor Grade 4 = Active movement against gravity, the limb can be lifted up because it can beat gravity (can't beat resistance) , Motor grade 5 = Active movement against gravity and resistance, can beat gravity and a little resistance, Motor grade 6 = At least one of normal muscle strength can evaluate the motor function of the patient (user).

Motor Grade 1 is No Motor Response, which means that there is no complete reaction without self-breathing. For example, if a certain intensity of stimulation (pressure) is applied to the patient using the stimulation terminal 30, but there is no change in the patient's state information, the evaluation unit 14 evaluates the patient's motor response with Motor Grade 1. Can be evaluated.

In addition, Motor Grade 2 means Extension To Pain and Decerebrate Response. For example, a stimulation (pressure) of a certain intensity is applied to the patient using the stimulation terminal 30, but there is no change in the patient's motion information, but when breathing, the evaluation unit 14 uses Motor Grade 2 for the patient. Can evaluate the motor response of In other words, the evaluation unit 14 may evaluate the patient's motor response with Motor Grade 2 when self-breathing is performed when the response is zero, or when there is self-breathing and the response is insufficient.

In addition, Motor Grade 3 refers to Abnomal Flexion To Pain and Decorticate Response. For example, when a certain stimulation (pressure) is applied to the patient using the stimulation terminal 30, the evaluation unit 14 is Motor Grade when a bendable place such as an elbow or knee is slightly bent on the patient's motion trajectory. With 3, the patient's motor response can be evaluated. In other words, when the motion trajectory of the patient is included in a preset range corresponding to Motor Grade 3, the evaluation unit 14 may evaluate the motion response of the patient with Motor Grade 3.

In addition, Motor Grade 4 means Flexion / Withdrawal From Pain. For example, by using the stimulation terminal 30 to apply a certain stimulation (pressure) to the patient, or to avoid giving pain when a doctor or nurse raises the patient's arm or leg, If you do not try to remove your hand, you can evaluate the patient's motor response with Motor Grade 3. In other words, when the motion trajectory of the patient is included in a preset range corresponding to Motor Grade 4, the evaluation unit 14 may evaluate the motion response of the patient with Motor Grade 4.

In addition, Motor Grade 5 may mean Localizing Pain to pain. For example, when trying to remove the stimulation terminal 30 when applying a certain stimulation (pressure) to the patient using the stimulation terminal 30, bring the hand of the person (patient) to remove the hand of the doctor or nurse In the case of removal, Motor Grade 5 can be used to evaluate the patient's motor response. In other words, when the motion trajectory of the patient is included in a preset range corresponding to Motor Grade 5, the evaluation unit 14 may evaluate the motion response of the patient with Motor Grade 5.

Also, Motor Grade 6 could mean Obey Commands. For example, when a doctor or nurse requests a movement command such as counting numbers, blinking an eye, clenching a fist, or trying scissors with a finger and performing the movement, the motor grade 6 can evaluate the patient's motor response. In other words, when the motion trajectory of the patient is included in a preset range corresponding to Motor Grade 6, the evaluation unit 14 may evaluate the motion response of the patient with Motor Grade 6.

According to an embodiment of the present application, the providing unit 15 may provide a notification to the central control management terminal (not shown) when it is determined that the result of analyzing the trend of the patient's movement is paralysis progression. For example, the central control management terminal (not shown) may be a medical staff terminal or a server. As an example, when the result of analyzing the trend of the patient's movement is determined to be paralysis in response to a preset value assigned to each patient, the provider 15 identifies the patient's location to the central control management terminal (not shown). Number, patient information, etc. can be provided.

According to an embodiment of the present application, the motion analysis device 10 may provide a patient management menu to a central control management terminal (not shown). For example, a central control management terminal (not shown) downloads and installs an application program provided by the motion analysis apparatus 10, and a horse selection menu and a horse management menu may be provided through the installed application.

The motion analysis apparatus 10 includes all kinds of servers, terminals, or devices having functions of transmitting and receiving data, contents, and various communication signals through a network with a central control management terminal (not shown), and storing and processing data. I can.

The central control management terminal (not shown) is a device that interlocks with the motion analysis device 10 through a network. For example, a smartphone, a smart pad, a tablet PC, a wearable device, etc. Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access) -2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) all kinds of wireless communication devices such as terminals, desktop computers, may be fixed terminals such as smart TV.

An example of a network for sharing information between the motion analysis device 10 and the central control management terminal (not shown) is a 3rd Generation Partnership Project (3GPP) network, a Long Term Evolution (LTE) network, a 5G network, and a World Interoperability for WIMAX. Microwave Access) network, wired and wireless Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth (Bluetooth) network, Wifi network, An NFC (Near Field Communication) network, a satellite broadcasting network, an analog broadcasting network, and a Digital Multimedia Broadcasting (DMB) network may be included, but are not limited thereto.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly described.

5 is a schematic flowchart of an operation analysis and monitoring method of a paralyzed patient according to an embodiment of the present application

The paralyzed patient motion analysis monitoring method illustrated in FIG. 5 may be performed by the paralyzed patient motion analysis monitoring system 1 described above. Accordingly, even if omitted below, the description of the paralyzed patient motion analysis monitoring system 1 may be equally applied to the description of the paralyzed patient motion analysis and monitoring method.

In step S101, the paralyzed patient motion analysis monitoring system 1 may receive state information from a measurement terminal 20 that includes a plurality of sensors and is attached to a part of the patient's body to collect state information of the patient.

In step S102, the paralysis patient motion analysis monitoring system 1 may pre-process the motion information and the EMG signal included in the state information.

In step S103, the paralysis patient motion analysis monitoring system 1 may derive whether the paralysis progresses by applying the preprocessed motion information and the EMG signal to the pattern analysis tracking algorithm.

In step S014, the paralysis patient motion analysis monitoring system 1 may determine whether the patient is paralyzed in consideration of the analysis result of the pattern analysis tracking algorithm and the time interval of the patient's movement.

Although not shown in the drawing, before step S101, the paralyzed patient motion analysis monitoring system 1 may receive information on the intensity of stimulation applied to a part of the patient's body from the stimulation terminal 30 by using the stimulation terminal 30. The paralysis patient motion analysis monitoring system 1 may evaluate the motor response of the patient in consideration of state information received after applying a certain stimulus to the patient using the stimulation terminal 30.

In the above description, steps S101 to S104 may be further divided into additional steps or may be combined into fewer steps, depending on the embodiment of the present application. In addition, some steps may be omitted as necessary, or the order between steps may be changed.

The paralyzed patient motion analysis and monitoring method according to an exemplary embodiment of the present disclosure may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

In addition, the above-described method for analyzing and monitoring the motion of a paralyzed patient may be implemented in the form of a computer program or application executed by a computer stored in a recording medium.

The foregoing description of the present application is for illustrative purposes only, and those of ordinary skill in the art to which the present application pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present application is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present application.

1: Paralysis patient motion analysis monitoring system
10: motion analysis device
11: receiving unit 12: preprocessing unit
13: analysis unit 14: evaluation unit
15: Provision
20: measurement terminal
30: stimulation terminal

Claims (15)

In the paralysis patient behavior analysis monitoring method,
Receiving the state information from a measurement terminal including a plurality of sensors and attached to a part of the patient's body to collect state information of the patient;
Pre-processing motion information and an EMG signal included in the state information;
Applying the pre-processed motion information and the EMG signal to a pattern analysis tracking algorithm to derive whether or not paralysis has progressed; And
Determining whether the patient is paralyzed in consideration of the analysis result of the pattern analysis tracking algorithm and the time interval of the patient's movement,
Paralysis patient behavior analysis monitoring method comprising a. The method of claim 1,
Receiving, from the stimulation terminal, information on the intensity of stimulation applied to a part of the patient's body by using a stimulation terminal; And
The method further comprising the step of evaluating a motor response of the patient in consideration of the state information received after applying a certain stimulus to the patient using the stimulation terminal. The method of claim 2,
Evaluating the patient's motor response,
To evaluate the motor response of the patient by comparing the analysis result of the pattern analysis tracking algorithm and the exercise response scale of the patient divided into a plurality of steps, paralysis patient motion analysis monitoring method. The method of claim 1,
The pretreatment step,
Performing pre-processing of removing gravity components by applying motion information included in the state information to a first filter;
Extracting motion intensity data by applying motion information from which gravity components have been removed to a signal vector size algorithm;
Extracting distance data by applying the motion information from which the gravity component has been removed to a second filter and performing a trapezoidal operation;
Performing preprocessing of removing noise by applying the EMG signal included in the state information to a third filter; And
Performing preprocessing of applying the motion intensity data, the distance data, and the EMG signal to a fourth filter,
Comprising, paralyzed patient behavior analysis monitoring method. The method of claim 4,
The step of deriving whether the paralysis progresses,
Including the step of determining whether the motion intensity data exceeds a preset reference intensity value,
The step of determining whether the preset reference intensity value is exceeded,
When the motion intensity data exceeds the preset reference intensity value, it is determined that motion has occurred on the sensor,
When the motion intensity data does not exceed a preset reference intensity value, it is determined that no motion has occurred on the sensor, and the reception of the pre-processed state information is waited for the paralysis patient motion analysis monitoring method. The method of claim 5,
The step of deriving whether the paralysis progresses,
When it is determined that movement on the sensor has occurred, determining whether the EMG signal exceeds a preset reference EMG signal value,
The step of determining whether the EMG signal exceeds a preset reference EMG signal value,
When the EMG signal exceeds the preset reference EMG signal value, it is determined that the motion on the sensor is a voluntary motion of the patient,
If the EMG signal does not exceed the preset reference EMG signal value, it is determined that the patient is not spontaneous movement and waits for reception of preprocessed state information. The method of claim 6,
The step of deriving whether the paralysis progresses,
When it is determined that the motion on the sensor is a voluntary motion of the patient,
comparing the nth motion information and the n-1th motion information to derive a time interval of the patient's motion;
comparing the nth EMG signal and the n-1th EMG signal to derive a trend of the patient's EMG signal strength; And
Analyzing the movement trend of the patient based on the derived time interval of the movement of the patient and the trend of the EMG signal intensity of the patient,
That further comprises, paralyzed patient behavior analysis monitoring method. The method of claim 7,
The step of determining whether the patient's paralysis progresses,
A method for analyzing and monitoring a motion of a paralyzed patient, in which, based on the time at which the past motion was measured, the time interval at which the current motion has occurred is compared to determine the progression of the paralysis if the time interval of the motion time continues to increase. The method of claim 1,
If it is determined that the paralysis is progressing as a result of analyzing the trend of the patient's movement, the method further comprising providing a notification to the central control management terminal. The method of claim 1,
Further comprising the step of tracking the motion trajectory of the patient's arm based on the motion information collected from the measurement terminal attached to the patient's arm,
The step of tracking the motion trajectory of the patient's arm,
Receiving acceleration, angular velocity, and quaternion values from a six-axis motion sensor among the plurality of sensors;
Deriving a moving distance of the patient's arm through the acceleration value and the angular velocity value;
Deriving a rotated axis and a rotated angle by the measurement terminal using the quaternion value; And
Tracking the motion trajectory of the patient's arm in consideration of the derived movement distance of the patient's arm, the rotated axis, and the rotated angle,
That includes, paralyzed patient behavior analysis monitoring method. The method of claim 4,
The first filter for removing the gravitational component is an IIR Highpass filter,
The step of performing a pretreatment to remove the gravitational component,
Applying the first filter to remove the gravitational component, and performing pre-processing so that the intensity value of the patient's motion is expressed as a preset value. As a paralysis patient motion analysis monitoring system,
A measurement terminal including a plurality of sensors and attached to a part of the patient's body to collect state information of the patient; And
Motion analysis device for deriving whether the patient is paralyzed by applying the state information collected from the measurement terminal to a pattern analysis tracking algorithm,
Including,
The analysis device,
A receiving unit for receiving the status information obtained from the measurement terminal;
A preprocessor for performing preprocessing by applying the state information to a plurality of filters and preprocessing algorithms;
An analysis unit that analyzes whether paralysis progresses by applying the state information preprocessed by the preprocessor to a pattern analysis tracking algorithm
That includes, paralyzed patient motion analysis monitoring system. The method of claim 12,
Further comprising a stimulation terminal for applying stimulation to a part of the patient's body,
The analysis device,
The system further comprises an evaluation unit for evaluating a motor response of the patient in consideration of the state information received when a certain stimulus is applied to the patient using the stimulation terminal. The method of claim 13,
The patient motion analysis monitoring system further comprises a providing unit for providing a notification to the central control management terminal when the result of analyzing the trend of the patient's movement is determined to be paralysis progression. A computer-readable recording medium storing a program for executing the method of claim 1 on a computer.

Images