Limb weakness judgment method and system based on mobile phone sensor

Abstract

The invention provides a limb weakness judgment method and system based on a mobile phone sensor, and the method comprises the steps: displaying a guidance video at a mobile phone application front end; capturing completed original action data in real time by using a built-in sensor; preprocessing the original action data, and extracting time sequence feature data; processing the time sequence feature data to obtain action amplitude, direction change, action duration and speed; setting a threshold value and judging limb weakness to obtain a diagnosis conclusion; and returning the diagnosis conclusion to the applet page. By adopting a data acquisition and analysis technology of a built-in sensor of a smart phone, the action amplitude and speed of a patient are calculated to identify a specific action mode related to limb weakness, and the limb weakness symptom of the patient is judged, so that the effect of monitoring and evaluating the limb state of the user in real time is achieved; the problem that a traditional method for evaluating limb weakness of the stroke patient is insufficient in accuracy and convenience is solved, and the method has high real-time performance and interactivity and is easy to popularize.

Description

Technical Field

[0001] The present invention belongs to the field of smart medical technology, and specifically, relates to a method and system for judging limb fatigue based on a mobile phone sensor. Background Art

[0002] Limb weakness is a common symptom in stroke patients. Currently, the diagnosis of limb weakness mainly relies on the experience of clinicians and self-reporting of patients. Doctors usually judge the degree and impact of limb weakness by observing the patient's mobility and performing simple movement tests, such as raising hands, walking, or completing specific tasks. In the early stages, the manifestation of limb weakness may not be obvious. This method is easily affected by the doctor's personal judgment and experience and has a certain degree of subjectivity.

[0003] Sensors in smartphones and wearable devices can provide new solutions for the assessment of limb weakness and overcome the limitations of current methods. In the prior art, the limb weakness detection device disclosed in the patent document "A method and device for stroke assessment based on artificial intelligence" (CN118629657A) can evaluate the movement of upper and lower limbs, but it needs to meet hardware requirements such as cameras, test boards, grippers and pressure sensors, which is difficult to popularize and lacks interactivity and real-time performance.

[0004] The device disclosed in the patent document "A device for assessing limb function of stroke patients" (CN220675991U) also needs to meet multiple external hardware requirements such as force sensors, posture sensors, electromyography sensors and pressure sensors, and lacks interactivity and real-time performance.

[0005] Although the patent document "A method for assessing the gait of stroke patients based on smartphones" (CN118216906A) has simple equipment and real-time performance, it assesses the gait of stroke patients by obtaining the acceleration and angular velocity data of the user while walking. Considering that most stroke patients are elderly, this dynamic measurement and assessment method has low calculation accuracy and high time cost. Summary of the invention

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a method and system for judging limb fatigue based on a mobile phone sensor.

[0007] The method for judging limb weakness based on a mobile phone sensor provided by the present invention comprises:

[0008] Step S1: Displaying a guidance video on the front end of the mobile application;

[0009] Step S2: enabling the built-in sensor to capture the original action data completed according to the instruction video in real time;

[0010] Step S3: preprocessing the original motion data to extract time series feature data;

[0011] Step S4: Processing the time series feature data to obtain the movement amplitude, direction change, duration and speed of the movement;

[0012] Step S5: setting a threshold and judging limb weakness to obtain a diagnosis conclusion;

[0013] Step S6: Return the diagnosis conclusion to the mini program page.

[0014] Preferably, the instruction video in step S1 includes a video of requirements and precautions for the hand-raising action, to guide the user to perform the hand-raising action in a standardized manner.

[0015] In step S6, the diagnosis conclusion obtained by the cloud platform analysis is returned to the mini program page, and subsequent rehabilitation exercises or medical advice are recommended.

[0016] Preferably, in step S2, the hand-raising action is performed through a smart phone according to the video guidance, and the built-in accelerometer and gyroscope are used to capture the original action data in real time.

[0017] In step S3, the captured raw motion data is filtered of noise and smoothed to extract key time series features, including the start and end time of the motion, the maximum acceleration and the average acceleration.

[0018] Preferably, in step S4, the acceleration in the original motion data collected by the sensor is filtered, and the filtered acceleration Integrate to get the speed

[0019] In this discrete data Perform a second integration to obtain displacement data Calculate the standard deviation of acceleration σ:

[0020] Where N represents the total number of data points considered when calculating the average;

[0021] a represents the original acceleration;

[0022] t represents the sampling time;

[0023] i represents the index variable of the i-th data point to be summed;

[0024] v0 represents the initial velocity;

[0025] t′ represents the middle moment of the integration;

[0026] t k represents the kth sampling moment;

[0027] v(t k ) represents the speed at the kth sampling moment;

[0028] s(t k ) represents the displacement at the kth sampling moment;

[0029] It represents the average acceleration of the whole process.

[0030] Preferably, the acceleration standard deviation threshold in step S5 is set to 0.2. If the acceleration standard deviation is higher than the threshold, it is determined that the arm shakes violently during arm raising and there is insufficient muscle strength. If the acceleration standard deviation is less than or equal to the threshold, it is determined that the arm remains stable during arm raising and there is no insufficient muscle strength.

[0031] The displacement threshold is set to 3. If the displacement is less than the threshold, it is determined that the arm has not fallen and there is no limb weakness. If the displacement is greater than or equal to the threshold, it is determined that the arm has fallen more seriously and there is limb weakness.

[0032] According to the present invention, a limb fatigue judgment system based on a mobile phone sensor is provided, comprising:

[0033] Module M1: Display instruction video on the front end;

[0034] Module M2: real-time capture of raw action data completed according to the instruction video;

[0035] Module M3: preprocess the original action data and extract time series feature data;

[0036] Module M4: Processing time series feature data to obtain movement amplitude, direction change, movement duration and speed;

[0037] Module M5: Setting thresholds and judging limb weakness to obtain a diagnosis conclusion;

[0038] Module M6: Return the diagnosis conclusion to the mini program page.

[0039] Preferably, the instruction video in the module M1 includes a video of requirements and precautions for the hand-raising action, to guide the user to perform the hand-raising action in a standardized manner.

[0040] In the module M6, the diagnosis conclusion obtained by the cloud platform analysis is returned to the mini program page, and subsequent rehabilitation exercises or medical advice are recommended.

[0041] Preferably, in the module M2, the hand-raising action is performed through a smart phone according to the video guidance, and the built-in accelerometer and gyroscope are used to capture the original action data in real time.

[0042] The module M3 filters noise from the captured raw motion data and performs smoothing processing to extract key time series features, including the start and end time of the motion, the maximum acceleration and the average acceleration.

[0043] Preferably, the acceleration in the original motion data collected by the sensor is filtered in the module M4, and the filtered acceleration Integrate to get the speed

[0044] In this discrete data Perform a second integration to obtain displacement data Calculate the standard deviation of acceleration σ:

[0045] Where N represents the total number of data points considered when calculating the average;

[0046] a represents the original acceleration;

[0047] t represents the sampling time;

[0048] i represents the index variable of the i-th data point to be summed;

[0049] v0 represents the initial velocity;

[0050] t′ represents the middle moment of the integration;

[0051] t k represents the kth sampling moment;

[0052] v(t k ) represents the speed at the kth sampling moment;

[0053] s(t k ) represents the displacement at the kth sampling moment;

[0054] It represents the average acceleration of the whole process.

[0055] Preferably, the acceleration standard deviation threshold in the module M5 is set to 0.2. If the acceleration standard deviation is higher than the threshold, it is determined that the arm shakes violently during arm raising and there is a lack of muscle strength. If the acceleration standard deviation is less than or equal to the threshold, it is determined that the arm remains stable during arm raising and there is no lack of muscle strength.

[0056] The displacement threshold is set to 3. If the displacement is less than the threshold, it is determined that the arm has not fallen and there is no limb weakness. If the displacement is greater than or equal to the threshold, it is determined that the arm has fallen more seriously and there is limb weakness.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. The present invention identifies specific movement patterns related to limb weakness by calculating the patient's movement amplitude and speed, determines the patient's limb weakness symptoms, and achieves the effect of real-time monitoring and evaluation of the user's limb condition.

[0059] 2. The present invention solves the problem of insufficient accuracy and convenience of traditional methods in assessing limb weakness in stroke patients by adopting data collection and analysis technology of built-in sensors in smartphones.

[0060] 3. The present invention analyzes the motion data captured by the mobile phone sensor during the hand-raising action, which is a static assessment method for upper limbs. It does not require external hardware equipment, has high real-time and interactivity, and is easy to popularize. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0062] Figure 1 The figure is a flow chart of a method for judging limb fatigue using a mobile phone sensor. DETAILED DESCRIPTION

[0063] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0064] The present invention utilizes the built-in sensors of a smartphone, namely, an accelerometer and a gyroscope, to determine limb weakness. Figure 1 For example, including:

[0065] Step S1: On the front end of the smartphone application, a video of the requirements and precautions for the hand-raising action is displayed to guide the user to perform the hand-raising action in a standardized manner.

[0066] Compared with the lower limb dynamic assessment method that evaluates the gait of stroke patients by obtaining the acceleration and angular velocity data of the user when walking, the diagnosis of limb weakness in stroke patients is achieved by analyzing the user's arm-raising action, avoiding the problem that the acceleration data of walking due to the patient's leg and foot inconvenience is difficult to obtain. At the same time, most stroke patients are elderly people with unstable gait, and the upper limb static assessment method improves the calculation accuracy and reduces the time cost.

[0067] Step S2: The user follows the video instructions and performs the hand-raising action through the smartphone, and the built-in sensors (accelerometer and gyroscope) are used to capture the raw action data in real time.

[0068] Step S3: The captured raw sensor data is preprocessed, noise is filtered and smoothed. Next, key time series features are extracted, including the start and end time of the action, the maximum acceleration and the average acceleration.

[0069] The maximum acceleration parameter can reflect the user's strength and arm shaking. Calculating the average acceleration during the entire movement can help evaluate the stability and smoothness of the movement. Recording the start and end time of the movement can complete the integration of the acceleration data, thereby having a clearer understanding of the entire movement process.

[0070] Step S4: Integrate the acceleration data to obtain the mobile phone speed data, and then integrate the speed to obtain the mobile phone displacement, and obtain the movement amplitude and direction change, movement duration and speed.

[0071] The original acceleration data collected by the sensor is filtered, and the filtered acceleration a filtered :

[0072]

[0073] Where N represents the sampling window size used for smoothing, that is, the total number of data points considered when calculating the average;

[0074] a represents the original acceleration;

[0075] t represents the sampling time;

[0076] i represents the index variable for summation, i.e. the i-th data point;

[0077] By integrating the acceleration once, we can get the velocity data v(t):

[0078] And in this discrete data:

[0079] Where v0 represents the initial velocity (which can be assumed to be zero in this case);

[0080] t′ represents the middle moment of the integration;

[0081] t k represents the kth sampling moment;

[0082] v(t k ) represents the speed at the kth sampling moment;

[0083] By integrating the velocity twice, the displacement data s(t) can be obtained:

[0084]

[0085] Finally, calculate the acceleration standard deviation σ:

[0086] Among them, s(t k ) represents the displacement at the kth sampling moment;

[0087] It represents the average value of acceleration during the whole process.

[0088] Step S5: setting the acceleration threshold and displacement threshold to compare with the calculation result, and combining the action duration, direction change and other data to make a judgment, and obtain the diagnosis conclusion of the user's limb fatigue.

[0089] The acceleration standard deviation threshold is set to 0.2, which represents the dividing point of whether the user's arm is stable. If the calculated result is higher than the threshold, it means that the user's arm is shaking violently during the arm raising period. If the calculated result is less than or equal to the threshold, it means that the user's arm remains stable during the arm raising period and there is no lack of muscle strength.

[0090] The displacement threshold is set to 3. Clinically verified, when the patient's muscle strength is insufficient, the arm may slowly fall and it is difficult to maintain the horizontal position. However, at this time, only the acceleration collected by the sensor is relatively stable, and its standard deviation is small, which cannot complete the recognition task. Therefore, the displacement threshold is added to identify the patient's arm slowly falling. If the displacement is less than 3, it means that the arm has not fallen. If the displacement is greater than 3, it means that the arm has fallen more seriously and there is limb weakness.

[0091] During the test, patients only need to raise their arms and remain still. This static movement requires a lower acquisition frequency for hardware devices such as accelerometers, and the results are more accurate. It can also be easier to complete the assessment for most elderly stroke patients and has a wider range of applications.

[0092] Step S6: Return the conclusions obtained from the cloud platform analysis to the mini program page, and recommend subsequent rehabilitation exercises or medical advice to achieve real-time interaction with the user.

[0093] By using the data collection and analysis technology of the built-in sensors of smartphones, namely accelerometers and gyroscopes, the motion data captured by the sensors during the user's hand-raising action is analyzed to identify specific motion patterns related to limb weakness, and the patient's movement amplitude and speed are calculated to determine the patient's limb weakness symptoms. This solves the problem of insufficient accuracy and convenience of traditional methods in assessing limb weakness in stroke patients, and achieves the effect of real-time monitoring and evaluation of the user's limb condition.

[0094] The present invention also provides a limb fatigue judgment system based on a mobile phone sensor. The limb fatigue judgment system based on a mobile phone sensor can be realized by executing the process steps of the limb fatigue judgment method based on a mobile phone sensor, that is, those skilled in the art can understand the limb fatigue judgment method based on a mobile phone sensor as a preferred implementation of the limb fatigue judgment system based on a mobile phone sensor.

[0095] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0096] According to the present invention, a limb fatigue judgment system based on a mobile phone sensor is provided, comprising:

[0097] Module M1: Display instruction video on the front end;

[0098] Module M2: real-time capture of raw action data completed according to the instruction video;

[0099] Module M3: preprocess the original action data and extract time series feature data;

[0100] Module M4: Processing time series feature data to obtain movement amplitude, direction change, movement duration and speed;

[0101] Module M5: Setting thresholds and judging limb weakness to obtain a diagnosis conclusion;

[0102] Module M6: Return the diagnosis conclusion to the mini program page.

[0103] In more preferred examples, the instruction video in the module M1 includes a video of requirements and precautions for the hand-raising action, to guide the user to perform the hand-raising action in a standardized manner.

[0104] In the module M6, the diagnosis conclusion obtained by the cloud platform analysis is returned to the mini program page, and subsequent rehabilitation exercises or medical advice are recommended.

[0105] In more preferred examples, the module M2 performs the hand-raising action through a smart phone according to the video guidance, and uses the built-in accelerometer and gyroscope to capture the original action data in real time.

[0106] The module M3 filters noise from the captured raw motion data and performs smoothing processing to extract key time series features, including the start and end time of the motion, the maximum acceleration and the average acceleration.

[0107] In more preferred embodiments, the module M4 filters the acceleration in the original motion data collected by the sensor, and the filtered acceleration Integrate to get the speed

[0108] In this discrete data Perform a second integration to obtain displacement data Calculate the standard deviation of acceleration σ:

[0109] Where N represents the sampling window size used for smoothing, that is, the total number of data points considered when calculating the average;

[0110] a represents the original acceleration;

[0111] t represents the sampling time;

[0112] i represents the index variable for summation, i.e. the i-th data point;

[0113] v0 represents the initial velocity (which can be assumed to be zero in this case);

[0114] t′ represents the middle moment of the integration;

[0115] t k represents the kth sampling moment;

[0116] v(t k ) represents the speed at the kth sampling moment;

[0117] s(t k ) represents the displacement at the kth sampling moment;

[0118] It represents the average acceleration of the whole process.

[0119] In more preferred examples, the acceleration standard deviation threshold in the module M5 is set to 0.2. If the acceleration standard deviation is higher than the threshold, it is determined that the arm shakes violently during arm raising and there is a lack of muscle strength. If the acceleration standard deviation is less than or equal to the threshold, it is determined that the arm remains stable during arm raising and there is no lack of muscle strength.

[0120] The displacement threshold is set to 3. If the displacement is less than the threshold, it is determined that the arm has not fallen and there is no limb weakness. If the displacement is greater than or equal to the threshold, it is determined that the arm has fallen more seriously and there is limb weakness.

[0121] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for judging limb fatigue based on a mobile phone sensor, characterized in that: include: Step S1: Displaying a guidance video on the front end of the mobile application; Step S2: enabling the built-in sensor to capture the original action data completed according to the instruction video in real time; Step S3: preprocessing the original motion data to extract time series feature data; Step S4: Processing the time series feature data to obtain the movement amplitude, direction change, duration and speed of the movement; Step S5: setting a threshold and judging limb weakness to obtain a diagnosis conclusion; Step S6: Return the diagnosis conclusion to the mini program page.

2. The method for judging limb weakness based on a mobile phone sensor according to claim 1, characterized in that: The instruction video in step S1 includes a video of requirements and precautions for the hand-raising action, which guides the standard hand-raising action; In step S6, the diagnosis conclusion obtained by the cloud platform analysis is returned to the mini program page, and subsequent rehabilitation exercises or medical advice are recommended.

3. The method for judging limb weakness based on a mobile phone sensor according to claim 1, characterized in that: In step S2, according to the video instruction, the hand-raising action is performed through the smart phone, and the built-in accelerometer and gyroscope are used to capture the raw action data in real time; In step S3, the captured raw motion data is filtered of noise and smoothed to extract key time series features, including the start and end time of the motion, the maximum acceleration and the average acceleration.

4. The method for judging limb weakness based on a mobile phone sensor according to claim 1, characterized in that: In step S4, the acceleration in the original motion data collected by the sensor is filtered, and the filtered acceleration Integrate to get the speed In this discrete data Perform a second integration to obtain displacement data Calculate the standard deviation of acceleration σ: Where N represents the total number of data points considered when calculating the average; a represents the original acceleration; t represents the sampling time; i represents the index variable of the i-th data point to be summed; v0 represents the initial velocity; t ′ represents the intermediate moment of the integral; t k represents the kth sampling moment; v(t k ) represents the speed at the kth sampling moment; s(t k ) represents the displacement at the kth sampling moment; It represents the average acceleration of the whole process.

5. The method for judging limb weakness based on a mobile phone sensor according to claim 1, characterized in that: In step S5, the acceleration standard deviation threshold is set to 0.

2. If the acceleration standard deviation is higher than the threshold, it is determined that the arm shakes violently during the arm raising period, and there is a lack of muscle strength. If the acceleration standard deviation is less than or equal to the threshold, it is determined that the arm remains stable during the arm raising period, and there is no lack of muscle strength. The displacement threshold is set to 3. If the displacement is less than the threshold, it is determined that the arm has not fallen and there is no limb weakness. If the displacement is greater than or equal to the threshold, it is determined that the arm has fallen more seriously and there is limb weakness.

6. A limb fatigue judgment system based on mobile phone sensors, characterized in that: include: Module M1: Display instruction video on the front end; Module M2: real-time capture of raw action data completed according to the instruction video; Module M3: preprocess the original action data and extract time series feature data; Module M4: Processing time series feature data to obtain movement amplitude, direction change, movement duration and speed; Module M5: Setting thresholds and judging limb weakness to obtain a diagnosis conclusion; Module M6: Return the diagnosis conclusion to the mini program page.

7. The limb fatigue judgment system based on mobile phone sensor according to claim 6 is characterized in that: The instruction video in the module M1 includes a video of requirements and precautions for the hand-raising action, which guides the standard hand-raising action; In the module M6, the diagnosis conclusion obtained by the cloud platform analysis is returned to the mini program page, and subsequent rehabilitation exercises or medical advice are recommended.

8. The limb fatigue judgment system based on mobile phone sensor according to claim 6 is characterized in that: In the module M2, the hand-raising action is performed through a smartphone according to the video instruction, and the built-in accelerometer and gyroscope are used to capture the raw action data in real time; The module M3 filters noise from the captured raw motion data and performs smoothing processing to extract key time series features, including the start and end time of the motion, the maximum acceleration and the average acceleration.

9. The limb fatigue judgment system based on mobile phone sensor according to claim 6, characterized in that: In the module M4, the acceleration in the original motion data collected by the sensor is filtered, and the filtered acceleration Integrate to get the speed In this discrete data Perform a second integration to obtain displacement data Calculate the standard deviation of acceleration σ: Where N represents the total number of data points considered when calculating the average; a represents the original acceleration; t represents the sampling time; i represents the index variable of the i-th data point to be summed; v0 represents the initial velocity; t ′ represents the intermediate moment of the integral; t k represents the kth sampling moment; v(t k ) represents the speed at the kth sampling moment; s(t k ) represents the displacement at the kth sampling moment; It represents the average acceleration of the whole process.

10. The limb fatigue judgment system based on mobile phone sensor according to claim 6, characterized in that: The acceleration standard deviation threshold in the module M5 is set to 0.

2. If the acceleration standard deviation is higher than the threshold, it is determined that the arm shakes violently during the arm raising period, and there is a lack of muscle strength. If the acceleration standard deviation is less than or equal to the threshold, it is determined that the arm remains stable during the arm raising period, and there is no lack of muscle strength. The displacement threshold is set to 3. If the displacement is less than the threshold, it is determined that the arm has not fallen and there is no limb weakness. If the displacement is greater than or equal to the threshold, it is determined that the arm has fallen more seriously and there is limb weakness.

Images