Quantitative detection method, device and equipment for limb resting tremor and storage medium

Abstract

The present application relates to the technical field of medical monitoring, and particularly relates to a limb resting tremor quantification detection method, device and equipment and a storage medium, which are used to solve the technical problem that the prior art cannot detect and quantitatively score the limb resting tremor continuously without affecting the daily life activities of the subject. The method comprises the following steps: in response to a resting tremor quantification detection request, acquiring motion data of a to-be-detected limb; determining whether the to-be-detected limb is in an active state according to the motion data; if the to-be-detected limb is not in the active state, determining whether the to-be-detected limb is in a resting tremor state according to the motion data; if the to-be-detected limb is in the resting tremor state, inputting the motion data into a quantitative scoring model to obtain a limb resting tremor score. The method can quantitatively score the resting tremor by detecting the motion data of the subject's limb in daily life, so that the quantitative detection steps are more simple and the scoring result is more accurate.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring technology, and in particular to a method, device, equipment and storage medium for quantitative detection of resting tremor of limbs. Background Technology

[0002] Parkinson's disease (PD) is the second most common neurodegenerative disease, occurring globally. A 2021 study published in The Lancet indicated a disproportionately rapid increase in new PD cases in China. It is estimated that by 2030, the number of patients in China will increase to 4.94 million, accounting for half of the global total, placing a significant burden on China's economy and healthcare system. Tremor in Parkinson's disease is an intermittent, oscillating movement primarily in the limbs. Resting tremor is not only an important marker of Parkinson's disease but also a valuable indicator of improvement after treatment. Therefore, the assessment of resting tremor is helpful for treatment adjustment and differential diagnosis. Previously, the clinical assessment standard for resting tremor was the Movement Disorders Association Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Clinical assessment using the MDS-UPDRS requires the involvement of trained clinicians, is inherently subjective, and lacks the necessary resolution to track fine-grained changes.

[0003] In existing technologies, the quantitative detection of resting tremor often requires patients to wear multiple sensors simultaneously and collect raw data during the performance of a predetermined movement task. However, wearing multiple sensors at the same time can affect wearing comfort, and the assessment obtained by collecting raw data during the performance of a predetermined movement task is essentially still an intermittent signal. Therefore, the quality and quantity of data will largely depend on the subject's compliance and motivation. Thus, there is an urgent need for a method that can continuously monitor and quantitatively assess the symptoms of resting tremor in daily life. Summary of the Invention

[0004] The main objective of this invention is to solve the technical problem that existing technologies cannot continuously detect and quantify resting tremors of the limbs without affecting the daily activities of the subjects.

[0005] The first aspect of the present invention provides a method for quantitative detection of resting tremor of a limb, comprising: in response to a resting tremor quantitative detection request, acquiring motion data of the limb to be tested; Based on the motion data, determine whether the limb under test is in an active state; If the limb to be tested is not in an active state, then the motion data is used to determine whether the limb to be tested is in a resting tremor state. If the limb to be tested is in a resting tremor state, the motion data is input into the quantitative scoring model to obtain the limb resting tremor score.

[0006] Optionally, in a first implementation of the first aspect of the present invention, determining whether the limb to be tested is in an active state based on the motion data includes: The motion data is segmented to obtain segmented motion data; The segmented motion data is preprocessed to remove the influence of noise and tremor data, resulting in preprocessed data. Obtain a first judgment condition, calculate a first feature value corresponding to the preprocessed data, and determine whether the first feature value satisfies the first judgment condition. If so, the limb to be tested corresponding to the segmented motion data is in an active state; If not, then the limb to be tested corresponding to the segmented motion data is not in an active state.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the segmented motion data includes acceleration data, and determining whether the limb under test is in a resting tremor state based on the motion data includes: Empirical mode decomposition is performed on the acceleration data to obtain the first mode function corresponding to the acceleration data; The first mode functions are superimposed to obtain the first reconstructed signal; Based on the first reconstructed signal, the eigenvalue is calculated to obtain the second eigenvalue; Obtain the second judgment condition, and determine whether the second feature value satisfies the second judgment condition; If so, the limb to be tested corresponding to the segmented motion data is in a resting tremor state; If not, then the limb to be tested corresponding to the segmented motion data is not in a resting tremor state.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the segmented motion data further includes angular velocity data, and the step of inputting the motion data into a quantitative scoring model to obtain a resting tremor score includes: Extract the temporal features of the segmented motion data based on the acceleration data and the angular velocity data; Frequency domain features of the segmented motion data are extracted based on the acceleration data; The time-domain and frequency-domain features are preprocessed and input into a quantitative scoring model to obtain a score for the degree of resting tremor.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the time-domain features include a first time-domain feature corresponding to the acceleration data and a second time-domain feature corresponding to the angular velocity, and the extraction of the time-domain features of the segmented motion data based on the acceleration data and the angular velocity data includes: The acceleration data is decomposed based on the empirical mode decomposition method to obtain the second mode function; The angular velocity data is decomposed based on the empirical mode decomposition method to obtain the third mode function; The second mode functions are superimposed to obtain the second reconstructed signal; The first time-domain feature is obtained by calculating the eigenvalues ​​of the second reconstructed signal; The third mode functions are superimposed to obtain the third reconstructed signal; The second time-domain feature is obtained by calculating the feature value of the third reconstructed signal.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the step of extracting the frequency domain features of the segmented motion data based on the acceleration data includes: Obtain the power spectrum of the acceleration data; Extract the extreme frequencies corresponding to the maximum values ​​of each power spectrum; The peak amplitude of the power spectrum is calculated based on the maximum and minimum frequencies to obtain the frequency domain characteristics.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the expression of the quantitative scoring model is: ; in, The degree of resting tremor was scored. For the frequency domain features, For the first time-domain feature, This is the second time-domain feature. , , and The correlation coefficient.

[0012] A second aspect of the present invention provides a device for quantitative detection of resting tremor of limbs, comprising: The acquisition module is used to acquire motion data of the limb to be tested in response to a resting tremor quantification detection request. The first judgment module is used to determine whether the limb to be tested is in an active state based on the motion data. The second judgment module is used to determine whether the limb under test is in a resting tremor state based on the motion data if the limb under test is not in an active state. The scoring module is used to input the motion data into a quantitative scoring model to obtain a resting tremor score for the limb if the limb under test is in a resting tremor state.

[0013] Optionally, in a first implementation of the second aspect of the present invention, the first determining module includes: The segmentation unit is used to segment the motion data to obtain segmented motion data; The preprocessing unit is used to preprocess the segmented motion data to remove the influence of noise and tremor data, and obtain preprocessed data. The first judgment execution unit is used to obtain a first judgment condition, calculate a first feature value corresponding to the preprocessed data, and determine whether the first feature value satisfies the first judgment condition; if yes, the limb to be tested corresponding to the segmented motion data is in an active state; if no, the limb to be tested corresponding to the segmented motion data is not in an active state.

[0014] Optionally, in a second implementation of the second aspect of the present invention, the segmented motion data includes acceleration data, and the second determination module includes: The first decomposition unit is used to perform empirical mode decomposition on the acceleration data to obtain the first mode function corresponding to the acceleration data; The superposition unit is used to superimpose the first mode functions to obtain the first reconstructed signal; A feature calculation unit is used to calculate feature values ​​based on the first reconstructed signal to obtain a second feature value; The second judgment execution unit is used to obtain the second judgment condition and determine whether the second feature value satisfies the second judgment condition; if yes, the limb to be tested corresponding to the segmented motion data is in a resting tremor state; if no, the limb to be tested corresponding to the segmented motion data is not in a resting tremor state.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the segmented motion data further includes angular velocity data, and the scoring module includes: The first extraction unit is used to extract the temporal features of the segmented motion data based on the acceleration data and the angular velocity data; The second extraction unit is used to extract the frequency domain features of the segmented motion data based on the acceleration data; The quantization scoring unit is used to preprocess the time-domain and frequency-domain features and input them into the quantization scoring model to obtain a score for the degree of resting tremor of the limbs.

[0016] Optionally, in a fourth implementation of the first aspect of the present invention, the time-domain features include a first time-domain feature corresponding to the acceleration data and a second time-domain feature corresponding to the angular velocity, wherein the first feature extraction unit is specifically used for: The acceleration data is decomposed based on the empirical mode decomposition method to obtain the second mode function; The angular velocity data is decomposed based on the empirical mode decomposition method to obtain the third mode function; The second mode functions are superimposed to obtain the second reconstructed signal; The first time-domain feature is obtained by calculating the eigenvalues ​​of the second reconstructed signal; The third mode functions are superimposed to obtain the third reconstructed signal; The second time-domain feature is obtained by calculating the feature value of the third reconstructed signal.

[0017] Optionally, in a fifth implementation of the second aspect of the present invention, the second feature extraction unit is specifically used for: Obtain the power spectrum of the acceleration data; Extract the extreme frequencies corresponding to the maximum values ​​of each power spectrum; The peak amplitude of the power spectrum is calculated based on the maximum and minimum frequencies to obtain the frequency domain characteristics.

[0018] Optionally, in a sixth implementation of the first aspect of the present invention, the expression of the quantitative scoring model is: ; in, The degree of resting tremor was scored. For the frequency domain features, For the first time-domain feature, This is the second time-domain feature. , , and The correlation coefficient.

[0019] A third aspect of the present invention provides a device for quantitative detection of resting tremor, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the device for quantitative detection of resting tremor to perform the steps of the above-described method for quantitative detection of resting tremor.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the steps of the above-described method for quantifying limb resting tremor.

[0021] The technical solution provided by this invention involves acquiring motion data of the limb to be tested in response to a request for quantitative detection of resting tremor; determining whether the limb is active based on the motion data; if the limb is not active, determining whether it exhibits resting tremor based on the motion data; and if the limb exhibits resting tremor, inputting the motion data into a quantitative scoring model to obtain a resting tremor score. This method can quantify and score resting tremor by detecting limb motion data in the subject's daily life, making the quantitative detection process simpler and the scoring results more accurate. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating one embodiment of the method for quantitative detection of resting tremor of limbs according to the present invention. Figure 2 This is a schematic diagram of a data acquisition method architecture for the quantitative detection method of limb resting tremor in an embodiment of the present invention; Figure 3 This is a flowchart illustrating another embodiment of the method for quantitative detection of resting tremor of limbs in this invention. Figure 4 This is a schematic diagram of raw triaxial acceleration data for a method for quantitative detection of resting tremor of limbs in an embodiment of the present invention; Figure 5 This is a schematic diagram of raw triaxial angular velocity data for a method for quantitative detection of resting tremor in limbs according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the motion state of each segment of motion data in the quantitative detection method for resting tremor of limbs in an embodiment of the present invention; Figure 7 This is a schematic diagram of the process of inputting motion data into a quantitative scoring model to obtain a resting tremor score in the quantitative detection method for resting tremor of limbs in an embodiment of the present invention. Figure 8 This is a schematic diagram of a resting tremor scoring method in the quantitative detection method for resting tremor of limbs in an embodiment of the present invention; Figure 9 This is a schematic diagram of one embodiment of the limb resting tremor quantification detection device of the present invention; Figure 10 This is a schematic diagram of another embodiment of the limb resting tremor quantification detection device of the present invention; Figure 11 This is a schematic diagram of one embodiment of the limb resting tremor quantitative detection device according to the present invention; Figure 12 This is a schematic diagram illustrating the principle of a computer-readable medium according to an embodiment of the present invention. Detailed Implementation

[0023] Exemplary embodiments of the invention will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limiting the invention to the embodiments set forth herein. Rather, these exemplary embodiments are provided to make the invention more comprehensive and complete, and to facilitate a full communication of the inventive concept to those skilled in the art. The same reference numerals in the drawings denote the same or similar elements, components, or parts, and therefore repeated descriptions of them will be omitted.

[0024] Subject to the technical concept of this invention, the features, structures, characteristics or other details described in a particular embodiment may be combined in one or more other embodiments in a suitable manner.

[0025] In the description of specific embodiments, the features, structures, characteristics, or other details described in this invention are intended to enable those skilled in the art to fully understand the embodiments. However, it is not excluded that those skilled in the art can practice the technical solutions of this invention without one or more of the specific features, structures, characteristics, or other details.

[0026] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0027] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] The terms “and / or” or “and / or” include all combinations of any one or more of the listed items.

[0029] Please see Figures 1-2 One embodiment of the method for quantitative detection of resting tremor of limbs in this invention includes: S101. In response to a request for resting tremor quantification detection, acquire motion data of the limb to be tested; It is understood that the executing entity of this invention can be a limb resting tremor quantification detection device, a terminal, or a server; no specific limitation is made here. This embodiment of the invention will be described using a server as an example.

[0030] In this embodiment, before the server responds to the request for quantification of resting tremor, the subject needs to wear a motion data recording device on the limb to be tested. The motion data recording device includes motion sensors that can collect three-axis acceleration and three-axis angular velocity during movement.

[0031] Please see Figure 2 In one specific implementation, the limb to be tested is a single upper limb, and the motion data recording device can be a fitness tracker 201. This fitness tracker can connect to information receiving devices such as mobile phones, tablets, or computers via Bluetooth or other data transmission methods. The fitness tracker 201 is worn on the single upper limb, approximately one finger's distance from the wrist bone, maintaining an appropriate tightness to ensure no relative displacement between the subject and the tracker 201 during movement. Motion signals are collected over a prolonged period; in a specific example, the collection duration is set to 24 hours, and the collection frequency is set to 5 minutes of continuous collection every 6 minutes. In this step, the fitness tracker 201 connects to a mobile phone 202 via Bluetooth, transmitting the collected motion signals to the mobile phone 202. The mobile phone 202 uploads the received motion signals to cloud storage 203 for storage. Server 204 receives and responds to the limb resting tremor quantification detection request, parses the subject information contained in the limb resting tremor quantification detection request, and retrieves the raw motion data from the motion data recording device, i.e., the fitness tracker 201, from cloud storage 203.

[0032] S102. Determine whether the limb to be tested is in an active state based on the motion data; After acquiring the raw motion data, it is preprocessed to transform it from quantified stored values ​​into meaningful motion data. Since resting tremors in limbs caused by Parkinson's disease (PD) or other conditions typically last only a few seconds, the motion data needs to be segmented using a fixed-length time window, ranging from 1 to 10 seconds. If the time window is too long, the resolution of tremor detection will decrease; if the time window is too short, false positives are more likely to occur. In a preferred approach, the time window length is 3 seconds.

[0033] In actual testing, the frequency band of resting tremor is generally between 3.5 Hz and 7.5 Hz, while the frequency band of ordinary limb movement is generally lower than this band. Therefore, the segmented motion data is input into a low-pass filter to filter out the influence of the resting tremor signal, and the filtered segmented motion data is obtained.

[0034] To determine whether each filtered segmented motion data satisfies the first judgment condition, in this embodiment, the first judgment condition is the activity state judgment condition, which specifically determines whether the dispersion of the segmented motion data is greater than the dispersion threshold. In this embodiment, the dispersion is specifically characterized by calculating the sliding coefficient of variation.

[0035] If the value is greater than the value, the upper limb movement state corresponding to the segmented movement data is considered to be an upper limb activity state; if the value is less than the value, the upper limb movement state corresponding to the segmented movement data is considered not to be an upper limb activity state. In this embodiment, the activity state refers to the normal non-pathological movement of the upper limb in the subject's daily life activities.

[0036] S103. If the limb to be tested is not in an active state, determine whether the limb to be tested is in a resting tremor state based on the motion data. If the upper limb movement state corresponding to the segmented motion data is not an upper limb activity state, then it is determined whether the segmented motion data is a resting tremor state or a resting state. In a specific implementation, triaxial acceleration data in the current segmented motion data is acquired, empirical mode decomposition is performed on the triaxial acceleration data to obtain a first mode function corresponding to the acceleration data; the first mode functions are superimposed to obtain a first reconstructed signal; based on the first reconstructed signal, eigenvalues ​​are calculated to obtain a second eigenvalue; a second judgment condition is acquired, and it is determined whether the second eigenvalue satisfies the second judgment condition; if the second eigenvalue satisfies the second judgment condition, then the limb to be tested corresponding to the segmented motion data is in a resting tremor state; if the second eigenvalue does not satisfy the second judgment condition, then the limb to be tested corresponding to the segmented motion data is not in a resting tremor state, but is in a resting state; wherein, the second judgment condition may be to determine whether the second eigenvalue is greater than a resting tremor determination threshold.

[0037] S104. If the limb to be tested is in a resting tremor state, then input the motion data into the quantitative scoring model to obtain the resting tremor score of the limb.

[0038] The time-domain and frequency-domain features of the segmented motion data are extracted using the triaxial acceleration and angular velocity data from the fitness tracker 201. These features are then preprocessed and input into a quantitative scoring model to obtain a resting tremor severity score. In one specific implementation, the quantitative scoring model can be a pre-trained linear regression model.

[0039] This invention enables the collection of limb movement data in the daily life of subjects by wearing a single fitness tracker that does not affect their daily life. Based on the collected limb movement data, it can determine whether resting tremor occurs. If resting tremor occurs, a quantitative score is performed. This scheme makes the quantitative detection process simpler and the scoring results more accurate.

[0040] Please refer to Figure 2-8 Another embodiment of the method for quantitative detection of resting tremor in this invention includes: S301. In response to a request for resting tremor quantification detection, acquire motion data of the limb to be tested; Please see Figure 2 In one specific implementation, the limb to be tested is a unilateral upper limb, and the motion data recording device can be a fitness tracker 201. This fitness tracker can connect to information receiving devices such as mobile phones, tablets, or computers via Bluetooth or other data transmission methods. The fitness tracker 201 is worn on the unilateral upper limb, approximately one finger's distance from the wrist bone, maintaining an appropriate tightness to ensure no relative displacement between the subject and the tracker 201 during movement. Motion signals are collected over a prolonged period; in a specific example, the collection duration is set to 24 hours, and the collection frequency is set to 5 minutes of continuous collection every 6 minutes. In this step, the fitness tracker 201 connects to the mobile phone 202 via Bluetooth, transmitting the collected motion signals to the mobile phone 202. The mobile phone 202 uploads the received motion signals to cloud storage 203 for storage. The server 204 receives and responds to the limb resting tremor quantification detection request, parses the subject information contained in the limb resting tremor quantification detection request, and retrieves the raw motion data from the motion data recording device, i.e., the fitness tracker 201, from cloud storage 203. Please refer to [link to relevant documentation]. Figure 4 as well as Figure 5 The raw data includes triaxial acceleration raw data and triaxial angular velocity raw data.

[0041] S302. Perform segmented processing on the motion data to obtain segmented motion data; In this embodiment, after the server obtains the raw motion data containing triaxial acceleration and triaxial angular velocity from the cloud storage, it first converts the motion data from quantized stored values ​​into meaningful motion data. In one specific implementation, the calculation formula is as follows: ; ; Wherein, ACC represents the acceleration data after linear transformation, GYRO represents the angular velocity data after linear transformation, acc is the raw acceleration data downloaded from cloud storage, and gyro is the raw angular velocity data downloaded from cloud storage. For the linear transformation parameters of acceleration, Here are the linear transformation parameters for angular velocity, where the units of acceleration data are... The unit of angular velocity data is The linear transformation parameters of acceleration and angular velocity are related to the equipment used to acquire motion data. In a specific example, =0.000244, =0.007.

[0042] Since resting tremors caused by Parkinson's disease or other conditions generally last only a few seconds, it is necessary to use a fixed-length time window to segment the motion data for processing. The time window length ranges from 1 second to 10 seconds. If the time window is too long, the resolution of tremor detection will decrease. If the time window is too short, false positives will easily occur in the classification. In a preferred scheme, a time window of 3 seconds is selected.

[0043] S303. Preprocess the segmented motion data to remove the influence of noise and flutter data to obtain preprocessed data; The resultant acceleration data is obtained from the triaxial acceleration data after the aforementioned linear transformation. In actual testing, the frequency band of the resultant acceleration data of resting limb tremor is generally 3.5 Hz to 7.5 Hz, while the frequency band of the resultant acceleration data of ordinary limb movement is generally lower than this band. Therefore, the resultant acceleration data is input into a low-pass filter with a cutoff frequency of 3 Hz and an order of 6 to filter out noise and the influence of resting tremor data.

[0044] S304. Obtain the first judgment condition, calculate the first feature value corresponding to the preprocessed data and determine whether the first feature value satisfies the first judgment condition. In this embodiment, a first judgment threshold is first obtained, and the sliding coefficient of variation of the preprocessed data is extracted. For each segment of preprocessed data, if the sliding coefficient of variation is greater than the first judgment threshold for more than half the time, it is considered that the first judgment condition is met.

[0045] In one specific implementation, the sliding coefficient of variation with a length of 1 second is calculated from the preprocessed segmented motion data after filtering out noise and resting tremor data in the aforementioned steps. The specific formula is as follows: ; ; ; The moving coefficient of variation is the ratio of the standard deviation to the mean. Indicates the number of windows. To represent the average value of the sliding window signal, To represent the standard deviation of the sliding window signal, Indicates the number of elements within the window after sliding calculation. The sliding coefficient of variation data, This indicates the number within the pre-sampling calculation window. The data; since the input signal length is 3 seconds and the data sampling frequency is 100 Hz, the value of i ranges from 1 to 300. Since the sliding window length is 1 second, to avoid the window start and end lengths being too short, half the window data length is selected for transition. Add or subtract 50.

[0046] Based on the clinical test results, a first judgment threshold is determined. In one specific implementation, the first judgment threshold is set to 0.016. The obtained sliding coefficient of variation signal sequence is binarized with 0.016. Signals greater than the first judgment threshold are judged as active states and their signal values ​​are recorded as 1. Conversely, signals less than the first judgment threshold are judged as inactive states and their signal values ​​are recorded as 0, thus obtaining a signal value sequence. Subsequently, each segment of motion data with a duration of 3 seconds is traversed to determine whether the proportion of signal values ​​of 1 in the signal value sequence of that segment of motion data is greater than or equal to 50%.

[0047] S305. If the first judgment condition is not met, the limb to be tested is not in an active state. Perform empirical mode decomposition on the acceleration data to obtain the first mode function corresponding to the acceleration data. If the proportion of signal values ​​of 1 in the signal value sequence of the motion data segment is greater than or equal to 50%, then the current segment of motion data is determined to correspond to a limb activity state. If the proportion of signal values ​​of 1 in the signal value sequence of the motion data segment is less than 50%, then the current segment of motion data is determined not to correspond to a limb activity state.

[0048] If the limb being tested is not in an active state, the current segmented motion data is acquired and Empirical Mode Decomposition (EMD) is performed. The characteristic of this method is that it can adaptively generate an Intrinsic Mode Function (IMF) based on the input signal, thus having good time-frequency resolution and a higher signal-to-noise ratio. In studies on resting tremor, the reconstructed signal has a higher signal-to-noise ratio than the traditional filtered signal, and the root mean square error of the noise is lower.

[0049] S306. The first mode functions are superimposed to obtain the first reconstructed signal; S307. Calculate the eigenvalues ​​based on the first reconstructed signal to obtain the second eigenvalue; S308. Obtain the second judgment condition and determine whether the second feature value satisfies the second judgment condition; Empirical mode decomposition (EMD) based on cubic spline interpolation is used to perform EMD on the triaxial summative acceleration of data segments classified as not being limb activity states. The superposition of the first three mode functions after decomposition is used as the first reconstructed signal. The second eigenvalue of the first reconstructed signal is calculated, where the second eigenvalue can be the root mean square value.

[0050] Obtain the second judgment threshold obtained from clinical testing, compare the second feature value with the second judgment threshold, classify the window with the second feature value (root mean square value) less than the second judgment threshold as resting state, and classify the window with the second feature value (root mean square value) greater than or equal to the second judgment threshold as resting tremor. In a specific example, the second judgment threshold is set to 0.0015.

[0051] In this embodiment, it is first determined whether the limb to be tested corresponding to the current segmented motion data is in an active state, and then it is determined whether the segmented motion data that is not in an active state is in a resting tremor state. Figure 6 This is a schematic diagram of the state of each segment of motion data generated after judging each segment of motion data in a specific example. In this diagram, the vertical axis 0 represents the resting state, the vertical axis 1 represents the hand movement state, and the vertical axis 2 represents the limb being in a resting tremor state.

[0052] S309. If satisfied, the limb to be tested corresponding to the segmented motion data is in a resting tremor state. Input the motion data into the quantitative scoring model to obtain the resting tremor score of the limb.

[0053] Based on the triaxial acceleration and angular velocity data of each segment of motion data, time-domain and frequency-domain features of the segmented motion data are extracted respectively. These time-domain and frequency-domain features are preprocessed and input into a quantitative scoring model to obtain a resting tremor severity score. In one specific implementation, the quantitative scoring model can be a pre-trained linear regression model.

[0054] Please see Figure 7 In this embodiment, the process of inputting motion data into a quantitative scoring model to obtain a resting tremor score involves the following steps: S3091: Extract temporal features from segmented motion data; For segmented motion data identified as stationary tremor, resultant acceleration data is calculated based on triaxial acceleration data, resultant angular velocity data is calculated based on triaxial angular velocity data, and the root mean square value of the second mode function of the resultant acceleration data is calculated using the empirical mode decomposition method based on cubic spline interpolation to obtain the first time-domain feature. The second time-domain feature is obtained by calculating the root mean square value of the second mode function of the resultant angular velocity data. .

[0055] S3092: Extract frequency domain features from segmented motion data; The power spectrum of the resultant acceleration of the data segment identified as stationary flutter is estimated using Welch analysis to obtain the power spectral density of the reconstructed signal of the resultant acceleration of the stationary flutter data segment. The peak amplitude of the power spectrum is then taken. The specific formula is as follows: ; ; in, , , These represent the power spectral densities of the reconstructed signals along the x, y, and z axes, respectively. Indicates the peak amplitude of the power spectrum. The value is the frequency, ranging from 3.5 to 7.5 Hz; This represents the frequency corresponding to the maximum value of the three-axis power spectrum.

[0056] S3093: Logarithmize the time-domain and frequency-domain features and input them into a pre-trained linear regression model to obtain a resting tremor score.

[0057] The specific formula is as follows: ; in, The degree of resting tremor was scored. For the frequency domain features, For the first time-domain feature, This is the second time-domain feature. , , and The correlation coefficient is obtained through the pre-training process. In a specific example, 0.19, 0.30, =0.13, =4.08. The method described in this embodiment can achieve the following: Figure 8 The resting tremor score is shown.

[0058] This invention enables the collection of limb movement data from daily life by a single fitness tracker worn by the subject without affecting their daily routine. Based on the collected limb movement data, it determines whether resting tremor is present. If resting tremor is present, a quantitative score is calculated. This approach places minimal burden on the subject, requiring no special tasks; normal daily life is sufficient. This simplifies the quantitative testing process and does not disrupt the subject's daily life. Furthermore, the quantitative scoring of resting tremor severity through long-term recording of limb data helps improve compliance with testing. Continuous, objective, and accurate assessment of resting tremor enhances the accuracy of quantitative testing results.

[0059] The above describes the method for quantitative detection of resting tremor in limbs according to embodiments of the present invention. The following describes the device for quantitative detection of resting tremor in limbs according to embodiments of the present invention. Please refer to [link to relevant documentation]. Figure 9 One embodiment of the limb resting tremor quantification detection device of the present invention includes: The acquisition module 901 is used to acquire motion data of the limb to be tested in response to a resting tremor quantification detection request. The first judgment module 902 is used to determine whether the limb to be tested is in an active state based on the motion data; The second judgment module 903 is used to determine whether the limb under test is in a resting tremor state based on the motion data if the limb under test is not in an active state. The scoring module 904 is used to input the motion data into the quantitative scoring model to obtain a resting tremor score for the limb if the limb under test is in a resting tremor state.

[0060] This invention enables the collection of limb movement data in the daily life of subjects by wearing a single fitness tracker that does not affect their daily life. Based on the collected limb movement data, it can determine whether resting tremor occurs. If resting tremor occurs, a quantitative score is performed. This scheme makes the quantitative detection process simpler and the scoring results more accurate.

[0061] Please see Figure 9 Another embodiment of the limb resting tremor quantification detection device of the present invention includes: The acquisition module 901 is used to acquire motion data of the limb to be tested in response to a resting tremor quantification detection request. The first judgment module 902 is used to determine whether the limb to be tested is in an active state based on the motion data; The second judgment module 903 is used to determine whether the limb under test is in a resting tremor state based on the motion data if the limb under test is not in an active state. The scoring module 904 is used to input the motion data into the quantitative scoring model to obtain a resting tremor score for the limb if the limb under test is in a resting tremor state.

[0062] In another embodiment of this application, the first determination module 902 includes: Segmentation unit 9021 is used to segment the motion data to obtain segmented motion data; The preprocessing unit 9022 is used to preprocess the segmented motion data to remove the influence of noise and tremor data, and obtain preprocessed data. The first judgment execution unit 9023 is used to obtain a first judgment condition, calculate a first feature value corresponding to the preprocessed data, and determine whether the first feature value satisfies the first judgment condition; if yes, the limb to be tested corresponding to the segmented motion data is in an active state; if no, the limb to be tested corresponding to the segmented motion data is not in an active state.

[0063] In another embodiment of this application, the segmented motion data includes acceleration data, and the second determination module 903 includes: The first decomposition unit 9031 is used to perform empirical mode decomposition on the acceleration data to obtain the first mode function corresponding to the acceleration data; The superposition unit 9032 is used to superimpose the first mode functions to obtain the first reconstructed signal; The feature calculation unit 9033 is used to calculate the feature value based on the first reconstructed signal to obtain the second feature value; The second judgment execution unit 9034 is used to obtain the second judgment condition and determine whether the second feature value satisfies the second judgment condition; if yes, the limb to be tested corresponding to the segmented motion data is in a resting tremor state; if no, the limb to be tested corresponding to the segmented motion data is not in a resting tremor state.

[0064] In another embodiment of this application, the segmented motion data further includes angular velocity data, and the scoring module 904 includes: The first extraction unit 9041 is used to extract the temporal features of the segmented motion data based on the acceleration data and the angular velocity data. The second extraction unit 9042 is used to extract the frequency domain features of the segmented motion data based on the acceleration data; The quantization scoring unit 9043 is used to preprocess the time-domain and frequency-domain features and input them into the quantization scoring model to obtain a score for the degree of resting tremor of the limbs.

[0065] In another embodiment of this application, the time-domain features include a first time-domain feature corresponding to the acceleration data and a second time-domain feature corresponding to the angular velocity, wherein the first feature extraction unit 9041 is specifically used for: The acceleration data is decomposed based on the empirical mode decomposition method to obtain the second mode function; The angular velocity data is decomposed based on the empirical mode decomposition method to obtain the third mode function; The second mode functions are superimposed to obtain the second reconstructed signal; The first time-domain feature is obtained by calculating the eigenvalues ​​of the second reconstructed signal; The third mode functions are superimposed to obtain the third reconstructed signal; The second time-domain feature is obtained by calculating the feature value of the third reconstructed signal.

[0066] In another embodiment of this application, the second feature extraction unit 9042 is specifically used for: Obtain the power spectrum of the acceleration data; Extract the extreme frequencies corresponding to the maximum values ​​of each power spectrum; The peak amplitude of the power spectrum is calculated based on the maximum and minimum frequencies to obtain the frequency domain characteristics.

[0067] In another embodiment of this application, the expression of the quantitative scoring model is: ; in, The degree of resting tremor was scored. For the frequency domain features, For the first time-domain feature, This is the second time-domain feature. , , and The correlation coefficient.

[0068] This invention enables the collection of limb movement data from daily life by a single fitness tracker worn by the subject without affecting their daily routine. Based on the collected limb movement data, it determines whether resting tremor is present. If resting tremor is present, a quantitative score is calculated. This approach places minimal burden on the subject, requiring no special tasks; normal daily life is sufficient. This simplifies the quantitative testing process and does not disrupt the subject's daily life. Furthermore, the quantitative scoring of resting tremor severity through long-term recording of limb data helps improve compliance with testing. Continuous, objective, and accurate assessment of resting tremor enhances the accuracy of quantitative testing results.

[0069] above Figure 9 and Figure 10 The limb resting tremor quantification detection device in the embodiments of the present invention will be described in detail from the perspective of modular functional entities. Based on the same inventive concept, the embodiments of the present specification also provide a limb resting tremor quantification detection device. The limb resting tremor quantification detection device in the embodiments of the present invention will be described in detail below from the perspective of hardware processing.

[0070] Figure 11 This is a schematic diagram of an electronic device provided as an embodiment of this specification. Refer to the following... Figure 11 To describe the electronic device 1100 according to this embodiment of the invention. Figure 11 The electronic device 1100 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0071] like Figure 11 As shown, the electronic device 1100 is presented in the form of a general-purpose computing device. The components of the electronic device 1100 may include, but are not limited to: at least one processing unit 1110, at least one storage unit 1120, a bus 1130 connecting different system components (including storage unit 1120 and processing unit 1110), a display unit 1140, etc.

[0072] The storage unit stores program code that can be executed by the processing unit 1110, causing the processing unit 1110 to perform the steps described in the processing method section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 1110 can perform, for example... Figure 1 , Figure 3 or Figure 7 The steps are shown.

[0073] The storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 11201 and / or a cache storage unit 11202, and may further include a read-only memory unit (ROM) 11203.

[0074] The storage unit 1120 may also include a program / utility 11204 having a set (at least one) program module 11205, such program module 11205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0075] Bus 1130 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0076] Electronic device 1100 can also communicate with one or more external devices 100 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 1100, and / or with any device that enables electronic device 1100 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1150. Furthermore, electronic device 1100 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1160. Network adapter 1160 can communicate with other modules of electronic device 1100 via bus 1130. It should be understood that, although... Figure 11 As not shown, other hardware and / or software modules can be used in conjunction with electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0077] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described in this invention can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the method described above according to this invention. When the computer program is executed by a data processing device, it enables the computer-readable medium to implement the method described above, i.e.: as... Figure 1 , Figure 3 or Figure 7 The method shown.

[0078] Figure 12 This is a schematic diagram of a computer-readable medium provided for embodiments of this specification.

[0079] accomplish Figure 1 , Figure 3 or Figure 7The computer program of the method shown can be stored on one or more computer-readable media. A computer-readable medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0080] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0081] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0082] In summary, the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that in practice, general-purpose data processing devices such as microprocessors or digital signal processors (DSPs) can be used to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0083] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0084] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0085] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for quantitatively detecting resting tremor of limbs, characterized in that, include: In response to a request for quantitative detection of resting tremor, the motion data of the limb to be tested is acquired; The motion data is segmented to obtain segmented motion data; The system determines whether the segmented motion data is in an active state by judging whether the first feature value satisfies a first judgment condition; wherein, the first feature value is the discrete sliding variation coefficient of the segmented motion data, which is used to characterize the dispersion of the segmented motion data; the first judgment condition is that the dispersion of the segmented motion data is greater than a discrete threshold; if the first feature value is greater than the discrete threshold, the segmented motion data corresponds to an active state of the limb being tested; if the first feature value is less than the discrete threshold, the segmented motion data corresponds to an inactive state of the limb being tested. If the limb to be tested is not in an active state, then empirical mode decomposition is performed on the acceleration data contained in the segmented motion data to obtain a first mode function. The obtained first mode functions are superimposed and a second feature value is calculated. It is then determined whether the second feature value satisfies a second judgment condition to determine whether the limb to be tested is in a resting tremor state. The second judgment condition is that the second feature value is greater than the resting tremor judgment threshold. If the second feature value is greater than the second judgment condition, then the limb to be tested corresponding to the segmented motion data is in a resting tremor state. If the second feature value is less than the second judgment condition, then the limb to be tested corresponding to the segmented motion data is in a resting state. If the limb to be tested is in a resting tremor state, the motion data is input into the quantitative scoring model to obtain the limb resting tremor score.

2. The method for quantitative detection of resting tremor of limbs according to claim 1, characterized in that, After segmenting the motion data to obtain segmented motion data, the process further includes: The segmented motion data is preprocessed to remove the influence of noise and tremor data, resulting in preprocessed data. The step of determining whether the first feature value of the segmented motion data satisfies the first judgment condition, thereby determining whether the limb to be tested is in an active state, includes: Calculate the sliding coefficient of variation of the preprocessed data, and determine whether the sliding coefficient of variation is greater than the discrete threshold for more than half the time. If so, the limb to be tested corresponding to the segmented motion data is in an active state; If not, then the limb to be tested corresponding to the segmented motion data is not in an active state.

3. The method for quantitative detection of resting tremor of limbs according to claim 2, characterized in that, The segmented motion data also includes angular velocity data. The process of inputting the motion data into a quantitative scoring model to obtain a resting tremor score includes: Extract the temporal features of the segmented motion data based on the acceleration data and the angular velocity data; Frequency domain features of the segmented motion data are extracted based on the acceleration data; The time-domain and frequency-domain features are preprocessed and input into a quantitative scoring model to obtain a score for the degree of resting tremor.

4. The method for quantitative detection of resting tremor of limbs according to claim 3, characterized in that, The time-domain features include a first time-domain feature corresponding to the acceleration data and a second time-domain feature corresponding to the angular velocity. The extraction of time-domain features from the segmented motion data based on the acceleration data and the angular velocity data includes: The acceleration data is decomposed based on the empirical mode decomposition method to obtain the second mode function; The angular velocity data is decomposed based on the empirical mode decomposition method to obtain the third mode function; The second mode functions are superimposed to obtain the second reconstructed signal; The first time-domain feature is obtained by calculating the eigenvalues ​​of the second reconstructed signal; The third mode functions are superimposed to obtain the third reconstructed signal; The second time-domain feature is obtained by calculating the feature value of the third reconstructed signal.

5. The method for quantitative detection of resting tremor of limbs according to claim 4, characterized in that, The extraction of frequency domain features from the segmented motion data based on the acceleration data includes: Obtain the power spectrum of the acceleration data; Extract the extreme frequencies corresponding to the maximum values ​​of each power spectrum; The peak amplitude of the power spectrum is calculated based on the maximum and minimum frequencies to obtain the frequency domain characteristics.

6. The method for quantitative detection of resting tremor of limbs according to claim 5, characterized in that, The expression for the quantitative scoring model is: ； in, The degree of resting tremor was scored. For the frequency domain features, For the first time-domain feature, This is the second time-domain feature. , , and The correlation coefficient.

7. A device for quantitatively detecting resting tremor of limbs, characterized in that, The limb resting tremor quantification detection device includes: The acquisition module is used to acquire motion data of the limb to be tested in response to a resting tremor quantification detection request. A first judgment module is used to segment the motion data to obtain segmented motion data; to determine whether a first feature value of the segmented motion data satisfies a first judgment condition, thereby determining whether the limb to be tested is in an active state based on the motion data; wherein, the first feature value is the discrete sliding variation coefficient of the segmented motion data, used to characterize the degree of dispersion of the segmented motion data; the first judgment condition is that the degree of dispersion of the segmented motion data is greater than a discrete threshold; if the first feature value is greater than the discrete threshold, then the limb to be tested corresponding to the segmented motion data is in an active state; if the first feature value is less than the discrete threshold, then the limb to be tested corresponding to the segmented motion data is not in an active state. The second judgment module is used to, if the limb to be tested is not in an active state, perform empirical mode decomposition on the acceleration data contained in the segmented motion data to obtain a first mode function, superimpose the obtained first mode functions to calculate a second feature value, and determine whether the second feature value satisfies a second judgment condition to determine whether the limb to be tested is in a resting tremor state; wherein, the second judgment condition is that the second feature value is greater than the resting tremor determination threshold; if the second feature value is greater than the second judgment condition, the limb to be tested corresponding to the segmented motion data is in a resting tremor state; if the second feature value is less than the second judgment condition, the limb to be tested corresponding to the segmented motion data is in a resting state. The scoring module is used to input the motion data into a quantitative scoring model to obtain a resting tremor score for the limb if the limb under test is in a resting tremor state.

8. A device for quantitatively detecting resting tremor of limbs, characterized in that, The limb resting tremor quantitative detection device includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the limb resting tremor quantification detection device to perform the steps of the limb resting tremor quantification detection method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instruction is executed by the processor, it implements the steps of the method for quantitative detection of resting tremor of limbs as described in any one of claims 1-6.

Images