A phonocardiogram analysis system and method based on accelerometer data

Abstract

The application relates to the technical field of healthcare informatics, in particular to a seismocardiogram analysis system and method based on accelerometer data, wherein the system comprises a heart vibration detection unit, a motion artifact detection unit and a data processing unit. The heart vibration detection unit is arranged to collect a sternum vibration signal generated by heart activity. The motion artifact detection unit is arranged to detect a sternum posture signal generated by thoracic activity during breathing. In the application, the data processing unit acquires signals of the heart vibration detection unit and the motion artifact detection unit, encodes the signals into vector group data, performs digital filtering on the vector group data, preliminarily performs band-pass filtering to retain only low-frequency signals, and performs modal decomposition on the sternum vibration signal based on a VMD algorithm to decompose the SCG signal in the sternum posture signal based on parameter characteristics of the sternum posture signal as a constraint condition.

Description

Technical Field

[0001] This application relates to the field of healthcare informatics technology, and in particular to a system and method for analyzing electrocardiograms based on accelerometer data. Background Technology

[0002] Currently, cardiovascular health testing is mainly conducted clinically using methods such as electrocardiography (ECG), echocardiography, and coronary angiography. Among these, echocardiography and coronary angiography require specialized physicians to operate on a testing table, demanding advanced equipment and making long-term monitoring impossible. Furthermore, ECG is not sensitive enough to detect heart lesions, and some arrhythmias caused by certain diseases are not readily apparent on ECG signals.

[0003] The amplitude changes of the SCG signal are strongly correlated with the contraction and relaxation of the heart, and can reflect key information about cardiac activity. Compared with electrocardiogram (ECG) signals, the SCG signal is more sensitive to abnormal vibrations caused by cardiac lesions and shows more obvious features on the SCG signal.

[0004] Currently, the close relationship between various feature points in SCG signals and cardiac activity is not fully understood. To explain the relationship between SCG signals and cardiac activity, feature extraction of SCG signals is needed to narrow down the identification scope and thus determine the correlation between lesion type and signal features.

[0005] Existing cardiac seismogram acquisition systems primarily use accelerometers fixed in the sternal region of the human body. These accelerometers measure the vibration information generated by the contraction and relaxation of the heart, and then process the vibration information to obtain a cardiac seismogram.

[0006] However, the human body also experiences vibrations in the sternum during breathing and movement, resulting in baseline drift and motion artifacts in the vibration information obtained by the accelerometer. Therefore, the vibration information collected by the accelerometer needs to be filtered to obtain an accurate seismogram.

[0007] Accelerometer data is a non-stationary signal with frequent amplitude and phase changes, which means that existing bandpass filters are not effective offline.

[0008] To remove motion artifacts from SCG signals, this application provides a system and method for eccentricogram analysis based on accelerometer data. Summary of the Invention

[0009] To overcome the problems existing in the related technologies, the first aspect of this application provides a cardiac motion analysis system based on accelerometer data, including: a cardiac motion detection unit, a motion artifact detection unit, and a data processing unit;

[0010] The cardiac vibration detection unit and the motion artifact detection unit are communicatively connected to the data processing unit;

[0011] The cardiac vibration detection unit is equipped with a sternal accelerometer, which is used to collect the sternal vibration signal generated by cardiac activity.

[0012] The motion artifact detection unit is equipped with a patch piezoelectric sensor, which is attached to the sternal region to detect the sternal posture signal generated by the movement of the thoracic cage during breathing.

[0013] The data processing unit is used to extract the SCG signal from the sternal vibration signal based on the sternal posture signal.

[0014] In one embodiment, the patch piezoelectric sensor is provided with a dielectric elastomer piezoelectric film, a first electrode, and a second electrode;

[0015] The first electrode and the second electrode are respectively disposed on the top and bottom surfaces of the dielectric elastomer piezoelectric film;

[0016] The first electrode and the second electrode are electrically connected to the data processing unit.

[0017] In one embodiment, the data processing unit includes a signal acquisition module, a pre-filtering module, and a mode decomposition module;

[0018] The signal acquisition module is used to acquire the sternal posture signal and the sternal vibration signal;

[0019] The pre-filtering module is used to perform bandpass filtering on the sternal posture signal and the sternal vibration signal;

[0020] The modal decomposition module is used to decompose the sternal vibration signal into K modal components and extract the SCG signal from the K modal components.

[0021] In one implementation, the signal decomposition module performs mode decomposition based on the VMD algorithm, wherein the VMD algorithm incorporates the parametric features of the sternal posture signal into the constraints of the objective function when performing variational mode decomposition.

[0022] A second aspect of this application provides a method for seismogram analysis based on accelerometer data, applicable to the seismogram analysis system described in the second aspect of this application, comprising the following steps:

[0023] S1. Acquire the sternal vibration signal and the sternal posture signal;

[0024] S2. Perform preliminary filtering on the sternal vibration signal and the sternal posture signal;

[0025] S3. Input the sternal vibration signal into the improved VMD algorithm model to obtain K modal components; K is an integer greater than or equal to 2;

[0026] S4. Identify the SCG signal in the k modal components;

[0027] S5. Perform an angiograph analysis based on the SCG signal.

[0028] In one implementation, S2 specifically includes:

[0029] S200, Construct an improved VMD algorithm model;

[0030] S201. Input the filtered sternal vibration signal and the sternal posture signal;

[0031] S203, Iterative Update u k w k And λ;

[0032] S204. Determine whether the iteration termination condition is met. If yes, stop the iteration and output K modal components; otherwise, execute step S203.

[0033] In one implementation, the mode decomposition function of the VMD algorithm is:

[0034]

[0035] Among them, u k Let f(t) be the k-th modal component, and w be the sternal vibration signal. g w1(t) is the center frequency of the sternal posture signal, and w1(t) is the first modal component of the sternal vibration signal.

[0036] In one implementation, the constraints of the VMD algorithm model are:

[0037] Σu k =f(t)

[0038]

[0039] Among them, u k Let f(t) be the k-th modal component, and w be the sternal vibration signal. g w1(t) is the center frequency of the sternal posture signal, and w1(t) is the first modal component of the sternal vibration signal.

[0040] Introducing penalty factors and Lagrange multipliers to solve variational constraint problems, the resulting augmented Lagrange expression is:

[0041]

[0042] Wherein, L({u k},{w k Let},λ) be the augmented Lagrangian function, α be the penalty factor, λ be the Lagrange multiplier, T be the time length, and w g (t) represents the center frequency of the sternal posture signal.

[0043] In one implementation, the termination condition of the VMD algorithm model is:

[0044]

[0045] in, u in the (n+1)th iteration k Fourier transform of the function (t), u in the nth iteration k The Fourier transform of the function (t), where ∈ represents the discrimination precision, and ∈ is greater than 0.

[0046] The technical solution provided in this application may include the following beneficial effects:

[0047] In this application, the data processing unit acquires the signals from the cardiac vibration detection unit and the motion artifact detection unit, encodes them into vector group data, performs digital filtering on the vector group data, performs preliminary bandpass filtering to retain only low-frequency signals, and then performs mode decomposition on the sternal vibration signal based on the VMD algorithm, using the parameter characteristics of the sternal attitude signal as constraints to decompose the SCG signal.

[0048] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0049] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0050] Figure 1 This is a schematic diagram of the layout structure of the electrocardiogram analysis system shown in the embodiment of this application;

[0051] Figure 2 for Figure 1 The diagram shows the logical structure of the data analysis unit of the angioplasty analysis system.

[0052] Figure 3 This is a schematic flowchart illustrating the angiography analysis method in an embodiment of this application;

[0053] Figure 4 for Figure 3 The flowchart of step S2 in the electrocardiogram analysis method shown is as follows;

[0054] Figure captions: 1. Cardiac vibration detection unit; 2. Motion artifact detection unit; 3. Data processing unit. Detailed Implementation

[0055] Preferred embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0056] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0057] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0058] Example 1

[0059] In the process of angioplasty detection, in order to accurately remove motion artifact signals from accelerometer data, embodiments of this application provide an angioplasty analysis system based on accelerometer data, such as... Figure 1 As shown, it includes: cardiac motion detection unit 1, motion artifact detection unit 2, and data processing unit 3.

[0060] like Figure 1 As shown, the cardiac vibration detection unit 1 is equipped with a sternal accelerometer, and the motion artifact detection unit 2 is equipped with a patch-type piezoelectric sensor.

[0061] Specifically, the sternal accelerometer is integrated into a MEMS chip, which is connected to a data acquisition unit via a communication line. The patch piezoelectric sensor is integrated into a deformable sheet, and is connected to the data processing unit 3 via a communication line.

[0062] Furthermore, the patch-type piezoelectric sensor includes a dielectric elastomer piezoelectric film, a first electrode, and a second electrode. The first electrode and the second electrode are respectively disposed on the top and bottom surfaces of the dielectric elastomer piezoelectric film. The first electrode and the second electrode are electrically connected to the data processing unit 3.

[0063] In this embodiment, the sternal accelerometer is fixed to the top surface of the patch-type piezoelectric sensor, and the bottom surface of the patch-type piezoelectric sensor is adhered to the sternal region of the human body. During cardiac activity, the sternal accelerometer collects time-varying sternal vibration signals and sends them to the data processing unit 3. During human respiration, the patch-type piezoelectric sensor collects sternal posture signals as the sternum moves and sends them to the data processing unit 3.

[0064] The main source of motion artifacts is the expansion and contraction of the sternum. When the sternum moves, the accelerometer on the body surface collects the acceleration changes generated by the sternum movement, which leads to motion artifacts in the sternum vibration signal.

[0065] Furthermore, the data processing unit 3 is used to extract the SCG signal from the sternal vibration signal based on the sternal posture signal.

[0066] In the system shown in this application embodiment, the period, phase, and amplitude parameters of motion artifacts are strongly correlated with the sternal posture. Therefore, this application embodiment acquires the sternal posture signal using a patch-type piezoelectric sensor, and then separates the SCG signal from the motion artifacts in the sternal vibration signal based on the parameter characteristics of the sternal posture signal.

[0067] Furthermore, such as Figure 2 As shown, the data processing unit 3 includes a signal acquisition module, a pre-filtering module, and a mode decomposition module.

[0068] The signal acquisition module is used to acquire the sternal posture signal and the sternal vibration signal;

[0069] The pre-filtering module is used to perform preliminary filtering on the sternal posture signal and the mixed signal;

[0070] The mode decomposition module is used to decompose the mixing signal into K modal components and extract the SCG signal from the K modal components.

[0071] Furthermore, the signal decomposition module performs mode decomposition processing based on an improved VMD algorithm.

[0072] In this embodiment, the signal acquisition module acquires the signals from the cardiac vibration detection unit 1 and the motion artifact detection unit 2, and encodes them into vector group data. The pre-filtering module performs digital filtering on the vector group data, initially performing bandpass filtering to retain only low-frequency signals. The mode decomposition module performs mode decomposition on the sternal vibration signal based on the VMD algorithm, using the parametric features of the sternal attitude signal as constraints to decompose the SCG signal.

[0073] Example 2

[0074] Based on Embodiment 1, this application provides a method for seismogram analysis based on accelerometer data, applied to the seismogram analysis system described in Embodiment 1, such as... Figure 3 As shown, it includes the following steps:

[0075] S1. Acquire the sternal vibration signal and the sternal posture signal;

[0076] S2. Perform preliminary filtering on the sternal vibration signal and the sternal posture signal;

[0077] S3. Input the sternal vibration signal into the improved VMD algorithm model to obtain K modal components;

[0078] S4. Identify the SCG signal in the K modal components;

[0079] S5. Perform an electrocardiogram analysis and detection based on the SCG signal.

[0080] Specifically, such as Figure 4 As shown, S2 specifically includes:

[0081] S200, Constructing the VMD algorithm model;

[0082] Specifically, the mode decomposition function of the VMD algorithm model is:

[0083]

[0084] Among them, {u k} represents a combination of k modal components, {w k} represents the center frequencies corresponding to the k modal components, δ(t) is the unit impulse function, j is the imaginary unit, and * is the convolution operator. Let be a partial derivative function, and t be time.

[0085] The constraints of the VMD algorithm model are:

[0086]

[0087] w g (t)=w1(t)

[0088] Among them, u k Let f(t) be the k-th modal component, and w be the sternal vibration signal. g w1(t) is the center frequency of the sternal posture signal, and w1(t) is the first modal component of the sternal vibration signal.

[0089] For example, in this embodiment, the frequency of the sternal posture signal is used as one of the constraints. In other embodiments, the period or amplitude parameter of the sternal posture signal can also be used as a constraint.

[0090] In this embodiment, the posture changes during human respiration are collected by an accelerometer, thereby generating motion artifacts. Taking advantage of the strong correlation between posture change signals and motion artifacts, when processing the signal using the VMD algorithm, constraints are set based on the parameter characteristics of the posture change signals. This allows the motion artifacts generated by respiration to be decomposed from the sternal vibration signal, resulting in a more accurate SCG signal.

[0091] Introducing penalty factors and Lagrange multipliers to solve variational constraint problems, the resulting augmented Lagrange expression is:

[0092]

[0093] Wherein, L({u k},{w k Let},λ) be the augmented Lagrangian function, α be the penalty factor, λ be the Lagrange multiplier, T be the time length, and w g (t) represents the center frequency of the sternal posture signal.

[0094] S201. Input the filtered sternal vibration signal and the sternal posture signal;

[0095] S202, Initialize {u k}、{w k}, λ, and n;

[0096] Among them, {u k} represents k modal components, {w k Let} be the center frequencies of the k modal components, λ be the Lagrange operator, and n be the number of iterations.

[0097] S203, Iterative Update {u k}、{w k} and λ;

[0098] S204. Determine whether the iteration termination condition is met. If yes, stop the iteration and output k modal components; otherwise, execute step S203.

[0099] Specifically, the iteration termination condition is:

[0100]

[0101] in, u in the (n+1)th iteration k Fourier transform of the function (t), u in the nth iteration k The Fourier transform of the function (t), where ∈ represents the discrimination precision, and ∈ is greater than 0.

[0102] In this embodiment, the phase and frequency characteristics of the sternal posture signal are used as constraints during mode decomposition, so that the phase and frequency characteristics of a mode component obtained by decomposition approximate the sternal posture signal.

[0103] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments concerning the apparatus in the above embodiments, and will not be elaborated further here.

[0104] The solution of this application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have different emphases; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to this application.

[0105] Furthermore, it is understood that the steps in the method of this application embodiment can be adjusted, merged, or deleted in order according to actual needs, and the modules in the device of this application embodiment can be merged, divided, or deleted according to actual needs.

[0106] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0107] Alternatively, this application may be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) that, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the steps of the methods described above according to this application.

[0108] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the present application can be implemented as electronic hardware, computer software, or a combination of both.

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0110] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A system for analysis of an accelerometer-based seismocardiogram, the system comprising: The heart shock detection unit (1), the motion artifact detection unit (2), and the data processing unit (3) are included. The heart shock detection unit 1 and the motion artifact detection unit (2) are in communication connection with the data processing unit (3). The heart shock detection unit (1) is provided with a sternum accelerometer, which is used to collect the sternum vibration signal generated by the heart activity. The motion artifact detection unit (2) is provided with a patch piezoelectric sensor, which is pasted in the sternum area and is used to detect the sternum posture signal generated by the chest activity during breathing. The data processing unit (3) is used to extract the SCG signal in the sternum vibration signal according to the sternum posture signal. The data processing unit (3) includes a signal acquisition module, a pre-filtering module, and a modal decomposition module. The signal acquisition module is used to acquire the sternum posture signal and the sternum vibration signal. The pre-filtering module is used to perform band-pass filtering on the sternum posture signal and the sternum vibration signal. The modal decomposition module is used to decompose the sternum vibration signal into K modal components and extract the SCG signal in the K modal components. The signal decomposition module performs modal decomposition based on the VMD algorithm, which includes the parameter characteristics of the sternum posture signal in the constraint condition of the target function when performing variational modal decomposition. The constraint condition of the VMD algorithm model is: The penalty factor and the Lagrange multiplier are introduced to solve the variational constraint problem, and the obtained augmented Lagrange expression is: ； The patch piezoelectric sensor is provided with a dielectric elastomer piezoelectric film, a first electrode, and a second electrode. wherein, is a Lagrangian multiplier, is a penalty factor, is a Lagrangian multiplier, is a time length, is a center frequency of the sternal posture signal.

2. The accelerometer data based sphygmogram analysis system according to claim 1, wherein, The first electrode and the second electrode are respectively arranged on the top surface and the bottom surface of the dielectric elastomer piezoelectric film. The first electrode and the second electrode are electrically connected to the data processing unit (3). The heart shock map analysis system according to any one of claims 1-2, comprising the following steps:

3. A method of sphygmochart analysis based on accelerometer data, characterized by, S1, acquiring the sternum vibration signal and the sternum posture signal; S2, performing preliminary filtering processing on the sternum vibration signal and the sternum posture signal; S5, performing heart shock map analysis according to the SCG signal. S3, input the sternal vibration signal into the improved VMD algorithm model to obtain modal components; is an integer greater than or equal to 2. S4, identifying SCG signals in the modal components. S2 specifically includes:

4. The method of claim 3, wherein the method further comprises: S200, constructing an improved VMD algorithm model; S201, inputting the filtered sternum vibration signal and the sternum posture signal; The mode decomposition function of the VMD algorithm is: S203, iteratively updating ; S204, judging whether an iteration termination condition is met, if yes, stopping iteration and outputting modal components; if not, performing step S203.

5. The method of claim 4, wherein, The constraint condition of the VMD algorithm model is:

6. The method of claim 5, wherein the method further comprises: The penalty factor and the Lagrange multiplier are introduced to solve the variational constraint problem, and the obtained augmented Lagrange expression is: ； The termination condition of the VMD algorithm model is wherein, is a Lagrangian multiplier, is a penalty factor, is a Lagrangian multiplier, is a time length, is a center frequency of the sternal posture signal.

7. The method of claim 6, wherein the method further comprises: ​ wherein is the is the Fourier transform of the function, is the is the Fourier transform of the function, is the discrimination accuracy, is greater than 0.

Images