Data processing method, device, equipment and product for identifying cardiac status

Abstract

The present invention discloses a data processing method, device, equipment and product for identifying cardiac state, including: obtaining original first electrocardiogram data and preprocessing to obtain second electrocardiogram data; further generating a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix, and respectively generating corresponding two-dimensional images; generating a three-channel image based on three two-dimensional images; inputting the three-channel image into a pre-trained neural network model to obtain the recognition result of the cardiac state. The present invention generates a multimodal fused three-channel image based on two-dimensional images generated by the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix, and realizes automatic recognition of cardiac state with the help of a neural network model, and has the characteristics of sufficient input image expression information, accurate recognition, high degree of automation and wide application range.

Description

Technical Field

[0001] The present invention belongs to the field of medical image recognition, and in particular, relates to a data processing method, device, equipment and product for identifying cardiac status. Background Art

[0002] Accurate identification of heart status usually relies on electrocardiogram as a basis. Under existing technical conditions, accurate identification of electrocardiogram requires professional cardiologists, which takes a lot of time and effort. How to use computer equipment to efficiently process electrocardiogram information, realize automatic identification of heart status, reduce the workload of medical staff, improve the accuracy and efficiency of heart status identification, and achieve the purpose of medical care has become an urgent problem that needs to be solved. Summary of the invention

[0003] In view of this, the present invention aims to overcome the defects in the prior art and proposes a data processing method, device, equipment and product for identifying heart status.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0005] In a first aspect, a data processing method for identifying a cardiac state comprises:

[0006] Acquire original first electrocardiogram data and perform preprocessing to obtain second electrocardiogram data;

[0007] Based on the second electrocardiogram data, a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix are generated respectively;

[0008] Generate corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix;

[0009] Based on three two-dimensional images, a three-channel image is generated;

[0010] The three-channel image is input into a pre-trained neural network model to obtain a recognition result of the heart state, wherein the neural network model can recognize the heart state based on the three-channel image.

[0011] In another embodiment of the present invention, original first electrocardiogram data is obtained and preprocessed to obtain second electrocardiogram data, including: the first electrocardiogram is subjected to signal denoising, R peak detection, heart beat segmentation and standardization in sequence to obtain the second electrocardiogram data.

[0012] In another embodiment of the present invention, signal denoising includes: using a detail filter and a six-scale decomposition based on a wavelet basis function to obtain detail filter coefficients and approximate coefficients of the first electrocardiogram data; obtaining low-frequency coefficients and high-frequency coefficients based on the detail filter coefficients and the approximate coefficients; reconstructing the first electrocardiogram data based on the wavelet basis function, the low-frequency coefficients and the high-frequency coefficients, and completing signal denoising after filter processing.

[0013] In another embodiment of the present invention, R-peak detection is to locate the R-peak of the first electrocardiogram data using an adaptive threshold function.

[0014] In another embodiment of the present invention, signal denoising is completed after filter processing, including: processing using a notch filter and processing using a Twoworth low-pass filter; the notch filter is used to filter power frequency interference, and the Twoworth low-pass filter is used to filter electromyographic interference.

[0015] In another embodiment of the present invention, the neural network model includes a deep residual convolutional network layer, an attention layer, and a fully connected layer connected in sequence.

[0016] In another embodiment of the present invention, the cardiac state includes a normal state, a supraventricular ectopic beat state, a ventricular ectopic beat state, a ventricular and normal fusion heart beat state, and an unknown heart beat state.

[0017] In a second aspect, the present invention discloses a data processing device for identifying a heart state, the device comprising:

[0018] An acquisition module, used for acquiring the original first electrocardiogram data and performing preprocessing to obtain second electrocardiogram data;

[0019] A matrix generation module, for generating a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix respectively based on the second electrocardiogram data;

[0020] A first image generation module is used to generate corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix;

[0021] A second image generation module, used for generating a three-channel image based on the three two-dimensional images;

[0022] The recognition module is used to input the three-channel image into a pre-trained neural network model to obtain a recognition result of the heart state, wherein the neural network model can recognize the heart state based on the three-channel image.

[0023] In a third aspect, the present invention discloses an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0024] In a fourth aspect, the present invention discloses a computer program product, including a computer program, which implements the above method when executed by a processor.

[0025] Compared with the prior art, the present invention has the following advantages:

[0026] The present invention discloses a data processing method, device, equipment and product for identifying cardiac state, including: obtaining original first electrocardiogram data and preprocessing to obtain second electrocardiogram data; generating a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix; generating corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix; generating a three-channel image based on three two-dimensional images; inputting the three-channel image into a pre-trained neural network model to obtain the recognition result of the cardiac state. The present invention discloses a data processing method, device, equipment and product for identifying cardiac state, generating a multimodal fused three-channel image based on two-dimensional images generated by the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix, and further, realizing automatic recognition of cardiac state with the help of a neural network model, which has the characteristics of sufficient input image expression information, accurate recognition, high degree of automation and wide application range. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0028] In the attached picture:

[0029] Figure 1 A schematic diagram of an application scenario of a data processing method for identifying a heart state according to an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of a data processing method for identifying a heart state according to an embodiment of the present invention;

[0031] Figure 3 A two-dimensional image schematic diagram of a data processing method for identifying a heart state according to an embodiment of the present invention;

[0032] Figure 4 A schematic diagram of a neural network model of a data processing method for identifying cardiac status according to an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of a data processing device for identifying a heart state according to an embodiment of the present invention;

[0034] Figure 6 The figure is a schematic diagram of a data processing electronic device for identifying a heart state according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0036] In the description of the present invention, it should be further explained that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0037] Figure 1 This is a schematic diagram of the application scenario of a data processing method, device, equipment and product for identifying heart status disclosed in the present invention. Under existing technical conditions, accurate identification of electrocardiograms requires professional cardiologists, which takes a lot of time and effort. How to use computer equipment to efficiently process electrocardiogram information, realize automatic identification of heart status, reduce the workload of medical staff, and improve the accuracy and efficiency of heart status identification has become an urgent problem to be solved. A data processing method, device, equipment and product for identifying heart status disclosed in the present invention generates a multi-modal fused three-channel image based on two-dimensional images generated by the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix. Further, with the help of a neural network model, automatic identification of heart status is realized, and it has the characteristics of sufficient input image expression information, accurate identification, high degree of automation and wide application range.

[0038] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0039] like Figure 2 As shown, a data processing method for identifying a heart state comprises:

[0040] Step S201, obtaining original first electrocardiogram data and preprocessing it to obtain second electrocardiogram data;

[0041] Step S202, based on the second electrocardiogram data, respectively generate a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix;

[0042] Step S203, generating corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix;

[0043] Step S204, generating a three-channel image based on the three two-dimensional images;

[0044] Exemplarily, the size of a two-dimensional image is (224, 224), and the two-dimensional image is converted into three-dimensional data (224, 224, 1) by channel expansion. Since the size of the third dimension is 1, the three two-dimensional images after channel expansion can be used to generate a new three-channel image with a size of (224, 224, 3). In this way, each channel represents a feature perspective, which improves the richness of information contained in the image and helps the accuracy of subsequent recognition.

[0045] Step S205, inputting the three-channel image into the pre-trained neural network model to obtain the recognition result of the heart state, wherein the neural network model can recognize the heart state based on the three-channel image.

[0046] In step S205, the heart state includes a normal state, a supraventricular ectopic beat state, a ventricular ectopic beat state, a ventricular and normal fusion heart beat state, and an unknown heart beat state.

[0047] This embodiment generates a multimodal fused three-channel image based on the two-dimensional images generated by the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix, and uses a neural network model to realize automatic recognition of the heart state. It has the characteristics of sufficient input image expression information, accurate recognition, high degree of automation and wide application range.

[0048] Based on the previous embodiment, in another embodiment of the present invention, Figure 2 As shown, step S201, obtaining the original first electrocardiogram data and preprocessing it to obtain the second electrocardiogram data, including: the first electrocardiogram is subjected to signal denoising, R peak detection, heart beat segmentation and standardization in sequence to obtain the second electrocardiogram data.

[0049] Based on the previous embodiment, in another embodiment of the present invention, signal denoising includes: using a detail filter and a six-scale decomposition based on a wavelet basis function to obtain detail filter coefficients and approximate coefficients of the first electrocardiogram data; based on the detail filter coefficients and the approximate coefficients, obtaining low-frequency coefficients and high-frequency coefficients; based on the wavelet basis function, the low-frequency coefficients and the high-frequency coefficients, reconstructing the first electrocardiogram data and completing signal denoising after filter processing.

[0050] In this embodiment, db6 is selected as the wavelet basis function, and the approximate coefficient is expressed as ， The detail filter coefficients are expressed as ( n ), the relationship is as follows:

[0051]

[0052] It represents the signal of the first electrocardiogram data. is the low frequency coefficient, is the high frequency coefficient, Indicates the sampling point index of the signal, is the index of the output coefficient;

[0053] For example, The range is 0 to 2.8125 Hz, which is treated as baseline drift to remove and reconstruct the signal;

[0054] Based on the previous embodiment, in another embodiment of the present invention, after filter processing, signal denoising is completed, including: using a notch filter for processing and using a Two-pass filter for processing; the notch filter is used to filter the power frequency interference, and the Two-pass filter is used to filter the electromyographic interference.

[0055] Exemplarily, the notch filter is an IIR notch filter, whose signal length is the same as the input signal, and removes power frequency interference in the ECG signal, and the center frequency should be set to 50 Hz;

[0056] Exemplarily, the Tevos low-pass filter has a passband cutoff frequency of 80 Hz, a stopband cutoff frequency of 100 Hz, a passband gain set to 1.4, and a stopband attenuation of 1.6;

[0057] Based on the previous embodiment, in another embodiment of the present invention, R peak detection is to locate the R peak of the first electrocardiogram data using an adaptive threshold function.

[0058] In this embodiment, after the first electrocardiogram is subjected to signal denoising, an adaptive threshold function is used to perform R peak detection and positioning on the signal of the first electrocardiogram. When a peak exceeds a set low threshold, it is considered that an R peak is detected.

[0059] In this embodiment, illustratively, after the first electrocardiogram is subjected to signal denoising in sequence, it is first filtered in the frequency range of 15-25Hz; in order to reduce the interference of P wave and T wave on the QRS wave extraction process, a 4th-order bandpass FIR filter is used for filtering, and then a double slope process is performed; a 4th-order Butterworth low-pass filter is used for filtering again, and the cutoff frequency is set to 5Hz, in order to eliminate the double peak phenomenon and clutter that may be generated in the previous step, so as to make the electrocardiogram waveform smoother; finally, by performing window sliding integration, the waveform S_integration of the first electrocardiogram that has been processed is obtained;

[0060] The adaptive threshold function is as follows:

[0061] THR

[0062] THR

[0063] in, THR 1 represents the high threshold, THR 0 represents the low threshold. peak Represents the peak value of the detected R peak, mean() represents the average function, peaklist Indicates the current peak value; and They are set to 0.2 and 0.27, representing the lower limits of the two threshold changes.

[0064] initial THR 0 and THR The value of 1 is set to 0.3×max(S_integration) and 0.5×max(S_integration), where max(S_integration) is the maximum magnitude of S_integration.

[0065] In another embodiment of the present invention, the original first electrocardiogram data is obtained and preprocessed, and the heart beat segmentation method is as follows:

[0066] The indirect segmentation method is used to segment the heartbeat into 300 points with the position of the R peak as the reference point, and 150 points are segmented forward and backward respectively.

[0067] In this embodiment, when the heartbeat centered on the R peak is divided into 300 points,

[0068]

[0069] in, is the floor symbol, represents the total number of R peaks, Indicates R peaks, Indicates the total number of split points of S_integration; Indicates The point index of the position of the R peak, when <0, the forward division point along the time axis, When >150 points, split the points backward along the time axis.

[0070] In another embodiment of the present invention, the original first electrocardiogram data is obtained and preprocessed, and the standardization method is as follows:

[0071]

[0072] is the amplitude of S_integration after standardization;

[0073] is the amplitude corresponding to the original S_integration;

[0074] Yes, the average value. is the standard deviation;

[0075] Standardized processing can eliminate unit differences.

[0076] Based on the previous embodiment, in another embodiment of the present invention, Figure 4 As shown, the neural network model includes a deep residual convolutional network layer, an attention layer, and a fully connected layer connected in sequence.

[0077] In this implementation, CrossEntropyLoss is used as the loss function of the neural network model;

[0078] In another embodiment of the present invention, Figure 2 As shown, step S202, based on the second electrocardiogram data, respectively generates a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix, including:

[0079] First, the second electrocardiogram data is normalized as follows. The second electrocardiogram data is represented as an electrocardiogram time series: X={x 1 ,x 2 , ... ,x n }，i Represented as the index of ECG time series;

[0080] When selecting normalization compression to the [-1,1] interval:

[0081]

[0082] In another case, when the normalization is compressed to the interval [0,1]:

[0083]

[0084] Furthermore, polar coordinate encoding is used to represent the normalized ECG time series X ;

[0085]

[0086] represents the angle encoded in polar coordinates, represents the radius of the polar coordinate encoding, Indicates the timestamp, N Represents the constant factor for adjusting the span of polar coordinates;

[0087] Furthermore, the Gram angle sum field matrix is ​​expressed as GASF, and the Gram angle difference field matrix is ​​expressed as GADF, which are expressed as follows:

[0088] ,

[0089] ,

[0090] Furthermore, the Markov transfer field matrix is ​​expressed as MTF, for the ECG time series X={x 1 ,x 2 , ... , x n }，i Represented as the index of the ECG time series, X Divide into Q fractional bins, and divide each value x i Mapped to Q fractional bits, q i and q j Represents the quantile bins with timestamps i and j, and calculates the transfer relationship between the quantile bins on the time axis through a first-order Markov chain. W ij Indicates from q i Transfer to q j The probability of, the Markov transition field matrix MTF is expressed as follows:

[0091] ,

[0092] For example, the two-dimensional image of the Gram angle sum field matrix GASF, the two-dimensional image of the Gram angle difference field matrix GADF, and the two-dimensional image of the Markov transfer field matrix MTF are as follows: Figure 3 As shown, it includes the normal state N, the supraventricular ectopic beat state SVEB, the ventricular ectopic beat state VEB, the ventricular and normal fusion heart beat state F and the unknown heart beat state Q.

[0093] like Figure 5 As shown, the present invention also discloses a data processing device for identifying a heart state, comprising:

[0094] An acquisition module 401 is used to acquire original first electrocardiogram data and perform preprocessing to obtain second electrocardiogram data;

[0095] A matrix generation module 402, for generating a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix respectively based on the second electrocardiogram data;

[0096] A first image generation module 403, used to generate corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix;

[0097] A second image generation module 404 is used to generate a three-channel image based on the three two-dimensional images;

[0098] The recognition module 405 is used to input the three-channel image into the pre-trained neural network model to obtain the recognition result of the heart state, wherein the neural network model can recognize the heart state based on the three-channel image.

[0099] The present invention also discloses an electronic device, such as Figure 6 As shown, an embodiment is disclosed, which is a block diagram of an electronic device suitable for the above-mentioned data processing for identifying cardiac status.

[0100] The electronic device 50 of this embodiment includes a processor 501, which can perform various appropriate actions and processes according to the program stored in the ROM 502 or the program loaded from the storage part 508 to the RAM 503. The processor 501 may include, for example, a general-purpose microprocessor, an instruction set processor and / or a related chipset and / or a dedicated microprocessor, etc. The processor 501 may also include an onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present invention.

[0101] In RAM503, various programs and data required for the operation of electronic device 50 are stored. Processor 501, ROM502 and RAM503 are connected to each other via bus 504, and processor 501 performs various operations of the method flow according to the embodiment of the present invention by executing the program in ROM502 and / or RAM503. It should be noted that the program can also be stored in one or more memories other than ROM502 and RAM503, and processor 501 can also perform various operations of the method flow according to the embodiment of the present invention by executing the program stored in one or more memories.

[0102] According to an embodiment of the present invention, the electronic device 50 may further include an I / O interface 505, which is also connected to the bus 504. The electronic device 50 may further include one or more of the following components connected to the I / O interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube, a liquid crystal display, and a speaker; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 5010 is also connected to the I / O interface 505 as needed. A removable medium 5011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 5010 as needed, so that a computer program read therefrom is installed into the storage portion 508 as needed.

[0103] The present invention also provides a computer-readable storage medium.

[0104] The computer-readable storage medium may be included in the electronic device / device system described in the above embodiment; or it may exist independently without being assembled into the electronic device / device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0105] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory RAM, a read-only memory ROM, an erasable programmable read-only memory EPROM or a flash memory, a portable compact disk read-only memory CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0106] Embodiments of the present invention also include a computer program product.

[0107] The computer program product includes a computer program, which contains program codes for executing the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program codes are used to enable the electronic device to implement the method provided by the embodiment of the present invention.

[0108] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium. The program code included in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0109] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written by any combination of one or more programming languages, and specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages. Programming languages ​​include but are not limited to programming languages ​​such as Java, C++, python, C language or similar. The program code can be executed completely on the user computing device, partially on the user device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network or a wide area network, or can be connected to an external computing device.

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains 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 box may also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present invention can be combined and / or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teaching of the present invention, the features described in the various embodiments and / or claims of the present invention may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0111] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination. The scope of the present invention is limited by the attached claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A data processing method for identifying a cardiac state, characterized in that: include: Acquire original first electrocardiogram data and perform preprocessing to obtain second electrocardiogram data; Based on the second electrocardiogram data, respectively generate a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix; Generate corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix respectively; Based on the three two-dimensional images, a three-channel image is generated; Inputting the three-channel image into a pre-trained neural network model to obtain a recognition result of the heart state, wherein the neural network model can recognize the heart state based on the three-channel image; The method of obtaining the original first electrocardiogram data and preprocessing the data to obtain the second electrocardiogram data includes: obtaining the second electrocardiogram data by performing signal denoising, R peak detection, heart beat segmentation and standardization on the first electrocardiogram in sequence; The R peak detection is to locate the R peak of the first electrocardiogram data using an adaptive threshold function, and when a peak exceeds a set low threshold, it is considered that an R peak is detected; The adaptive threshold function is as follows: ， in, THR 1 represents the high threshold, THR 0 represents the low threshold. peak Represents the peak value of the detected R peak, mean() represents the average function, peaklist Indicates the current peak value; and They represent the lower limits of the two threshold changes respectively.

2. A data processing method for identifying a cardiac state according to claim 1, characterized in that: The signal denoising includes: using a detail filter and a six-scale decomposition based on a wavelet basis function to obtain detail filter coefficients and approximate coefficients of the first electrocardiogram data; obtaining low-frequency coefficients and high-frequency coefficients based on the detail filter coefficients and the approximate coefficients; based on the wavelet basis function, the low-frequency coefficients and the high-frequency coefficients, reconstructing the first electrocardiogram data and completing the signal denoising after filter processing.

3. A data processing method for identifying cardiac status according to claim 2, characterized in that: After the filter processing, the signal denoising is completed, including: using a notch filter for processing and using a Twoworth low-pass filter for processing; the notch filter is used to filter the power frequency interference, and the Twoworth low-pass filter is used to filter the electromyographic interference.

4. A data processing method for identifying a cardiac state according to claim 1, characterized in that: The neural network model includes a deep residual convolutional network layer, an attention layer and a fully connected layer connected in sequence.

5. A data processing method for identifying cardiac status according to claim 1, characterized in that: The heart states include a normal state, a supraventricular ectopic beat state, a ventricular ectopic beat state, a ventricular and normal fusion heart beat state, and an unknown heart beat state.

6. A data processing device for identifying a cardiac state, characterized in that: The device comprises: An acquisition module, used for acquiring the original first electrocardiogram data and performing preprocessing to obtain the second electrocardiogram data, including: the first electrocardiogram is subjected to signal denoising, R peak detection, heart beat segmentation and standardization in sequence to obtain the second electrocardiogram data; The R peak detection is to locate the R peak of the first electrocardiogram data using an adaptive threshold function, and when a peak exceeds a set low threshold, it is considered that an R peak is detected; The adaptive threshold function is as follows: ， in, THR 1 represents the high threshold, THR 0 represents the low threshold. peak Represents the peak value of the detected R peak, mean() represents the average function, peaklist Indicates the current peak value; and They represent the lower limits of the two threshold changes respectively; A matrix generation module, used for generating a Gram angle sum field matrix, a Gram angle difference field matrix and a Markov transfer field matrix respectively based on the second electrocardiogram data; A first image generation module, configured to generate corresponding two-dimensional images based on the Gram angle sum field matrix, the Gram angle difference field matrix and the Markov transfer field matrix; A second image generation module, used for generating a three-channel image based on the three two-dimensional images; The recognition module is used to input the three-channel image into a pre-trained neural network model to obtain a recognition result of the heart state, wherein the neural network model can recognize the heart state based on the three-channel image.

7. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the method according to any one of claims 1 to 5.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images