CN111358460A - Arrhythmia identification method and device and electronic equipment - Google Patents
Arrhythmia identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN111358460A CN111358460A CN202010139361.XA CN202010139361A CN111358460A CN 111358460 A CN111358460 A CN 111358460A CN 202010139361 A CN202010139361 A CN 202010139361A CN 111358460 A CN111358460 A CN 111358460A
- Authority
- CN
- China
- Prior art keywords
- information
- arrhythmia
- time
- extracting
- global
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The application provides a method and a device for identifying arrhythmia and electronic equipment, and belongs to the technical field of computer application. Wherein, the method comprises the following steps: acquiring electrocardiogram data; extracting spatial information and local time information from electrocardiogram data; extracting time-related information and global-related information from electrocardiogram data; and generating arrhythmia information according to the spatial information, the local time information, the time correlation information and the global correlation information. Therefore, by the arrhythmia identification method, the electrocardiogram data are automatically identified, the arrhythmia identification efficiency is improved, and the labor cost is reduced.
Description
Technical Field
The present application relates to the field of computer application technologies, and in particular, to a method and an apparatus for identifying arrhythmia, and an electronic device.
Background
An Electrocardiogram (ECG) is a visible graph record which records the potential change of the human heart by using an electrocardiograph acquisition instrument (such as an electrocardiograph monitor) and is applied to the monitoring and diagnosis of clinical heart diseases according to the potential change, and is an important means for diagnosing common heart diseases. In clinical ECG examination, 12-lead ECG data of 10-20 s are acquired for analysis by doctors. Arrhythmia (tachycardia, bradycardia, atrial fibrillation, atrial flutter and the like) and premature beat (atrial premature beat, ventricular premature beat, junctional premature beat and the like) types occupy most of abnormal electrocardiogram types, and the research on the automatic identification of the electrocardiogram can effectively assist doctors to improve the diagnosis efficiency.
Disclosure of Invention
The arrhythmia identification method, device, electronic equipment, storage medium and computer program provided by the application are used for solving the problem of low efficiency in the related art due to the mode of identifying the electrocardiogram and determining arrhythmia information in an artificial mode.
An embodiment of an aspect of the present application provides a method for identifying arrhythmia, including: acquiring electrocardiogram data; extracting spatial information and local temporal information from the electrocardiogram data; extracting time-related information and global-related information from the electrocardiogram data; and generating arrhythmia information according to the spatial information, the local time information, the time correlation information and the global correlation information.
Another embodiment of the present application provides an apparatus for identifying arrhythmia, including: an acquisition module for acquiring electrocardiogram data; a first extraction module for extracting spatial information and local temporal information from the electrocardiographic data; the second extraction module is used for extracting time-related information and global-related information from the electrocardiogram data; and the generating module is used for generating arrhythmia information according to the spatial information, the local time information, the time correlation information and the global correlation information.
An embodiment of another aspect of the present application provides an electronic device, which includes: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the method for identifying an arrhythmia as described above when executing the program.
A computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, implements a method for identifying cardiac arrhythmias as described above.
In an embodiment of a further aspect of the present application, a computer program is provided, which when executed by a processor, implements the method for identifying cardiac arrhythmia according to an embodiment of the present application.
According to the arrhythmia identification method, the arrhythmia identification device, the electronic device, the computer-readable storage medium and the computer program, the electrocardiogram data are acquired, the spatial information and the local time information are extracted from the electrocardiogram data, the time-related information and the global-related information are extracted from the electrocardiogram data, and the arrhythmia information is generated according to the spatial information, the local time information, the time-related information and the global-related information. Therefore, the model extracts and analyzes the time-space information of the electrocardiogram data, and the arrhythmia information corresponding to the electrocardiogram is determined according to the extracted characteristic information, so that the electrocardiogram data is automatically identified, the arrhythmia identification efficiency is improved, and the labor cost is reduced.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for identifying arrhythmia according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of another arrhythmia identification method according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a multi-label neural network model architecture according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a CNN model provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of each module in a CNN model according to an embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of a bidirectional RNN according to an embodiment of the present disclosure;
FIG. 7 is a schematic view of an attention model provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of an arrhythmia identification apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the like or similar elements throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The embodiment of the application provides an arrhythmia identification method aiming at the problems that in the related art, the arrhythmia information is determined by manually identifying a cardiogram and the efficiency is low.
According to the arrhythmia identification method provided by the embodiment of the application, the electrocardiogram data is obtained, the spatial information and the local time information are extracted from the electrocardiogram data, the time related information and the global related information are extracted from the electrocardiogram data, and the arrhythmia information is generated according to the spatial information, the local time information, the time related information and the global related information. Therefore, the model extracts and analyzes the time-space information of the electrocardiogram data, and the arrhythmia information corresponding to the electrocardiogram is determined according to the extracted characteristic information, so that the electrocardiogram data is automatically identified, the arrhythmia identification efficiency is improved, and the labor cost is reduced.
The arrhythmia identification method, apparatus, electronic device, storage medium, and computer program provided in the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for identifying arrhythmia according to an embodiment of the present disclosure.
As shown in fig. 1, the method for identifying arrhythmia includes the following steps:
The electrocardiogram data may be multi-channel time-series signal data. The number of signal channels of the electrocardiographic data is generally 12 channels, and the number of channels may be 1, 3, 5, 7, 15, 18, and the like, which is not limited in the embodiment of the present application.
It should be noted that the arrhythmia identification method according to the embodiment of the present application may be executed by an arrhythmia identification apparatus according to the embodiment of the present application. The arrhythmia recognition device according to the embodiment of the present application may be configured in any electronic device.
In the embodiment of the present application, the electronic device equipped with the arrhythmia recognition device may be directly connected to the electrocardiograph acquisition instrument, so as to directly acquire electrocardiograph data acquired by the electrocardiograph acquisition instrument.
As a possible implementation, the acquired electrocardiogram data may be preprocessed to facilitate the identification and processing of the electrocardiogram data in subsequent steps. For example, the electrocardiographic data may be subjected to zero-centering processing, normalization processing, or the like.
The spatial information refers to information corresponding to a plurality of channels in electrocardiogram data. It should be noted that different spatial information may describe the electrical signals of the heart at the same time from different directions.
The local time information is information that can describe waveform characteristics in each short period of time included in the electrocardiogram data. For example, the duration of the electrocardiogram data may be 1 minute, and the extracted local time information of the electrocardiogram may describe the waveform characteristics of the electrocardiogram data within each second (or within a shorter time period).
In the embodiment of the present application, the spatial information and the local time information in the electrocardiogram data may be extracted through the first deep learning network model to describe the heart rhythm information of the heart acquired from different channels through the spatial information, and the local detail information of the electrical signal in each channel (such as various types of waveforms included in the electrocardiogram) is characterized through the local time information.
It should be noted that, in actual use, the first deep learning network model in the embodiment of the present application may be any model sensitive to time-series signals, and the embodiment of the present application is not limited to this. For example, the first deep learning network model may be a Convolutional Neural Network (CNN).
The time-related information is a feature that can describe information such as waveform change in electrocardiographic data over a long period of time, and a correlation between electrical signals corresponding to each period of time.
For example, if the duration of the electrocardiogram data is 1 minute, the time-related information of the electrocardiogram may include information, such as a waveform type, a waveform number, a period corresponding to each waveform, a time interval between periods, and a waveform difference corresponding to each period, included in every 10 seconds. In actual use, which types of time-related information to extract can be determined according to actual needs, which is not limited in the embodiment of the present application.
The global correlation information refers to a feature that can describe the correlation between waveforms of each part in the whole time period corresponding to the electrocardiogram data.
For example, if the duration of the electrocardiographic data is 1 minute, the global correlation information of the electrocardiographic data may describe the difference or correlation between the waveform corresponding to the 1 st second and the waveform corresponding to the last 1 second of the electrocardiographic data, that is, the features included in the global correlation information may describe the overall characteristics of the electrocardiographic data.
In the embodiment of the application, after the features such as the spatial information and the local time information which can describe the local details of the electrocardiogram data are extracted from the electrocardiogram, the time-related information of the electrocardiogram data can be extracted by using the second deep learning network model, and the global-related information of the electrocardiogram data can be extracted by using the third deep learning network model.
And 104, generating arrhythmia information according to the spatial information, the local time information, the time correlation information and the global correlation information.
In the embodiment of the application, because the spatial information, the local time information, the time correlation information and the global correlation information of the electrocardiogram data can be respectively described from different dimensions and granularities on the characteristics of the electrocardiogram data, the arrhythmia information corresponding to the electrocardiogram is determined according to the spatial information, the local time information, the time correlation information and the global correlation information of the electrocardiogram data, and the arrhythmia identification efficiency and accuracy can be improved.
As a possible implementation manner, the arrhythmia information may include types of arrhythmia, such as tachycardia, bradycardia, atrial fibrillation, atrial flutter, atrial premature beat, ventricular premature beat, junctional premature beat, and the like, so that the arrhythmia information corresponding to the electrocardiogram data may be determined through a pre-trained multi-label classification model. That is, in a possible implementation form of the embodiment of the present application, the step 104 may include:
and inputting the spatial information, the local time information, the time correlation information and the global correlation information into a multi-label classification model to generate arrhythmia information.
In the embodiment of the application, a large amount of electrocardiogram data can be acquired, and the arrhythmia type corresponding to each electrocardiogram data is labeled to generate the training sample. And then carrying out supervised learning on the labeled training samples through the initial multi-label classification model so as to generate a pre-trained multi-label classification model.
In the embodiment of the application, the pre-trained multi-label classification model may perform recognition processing on the spatial information, the local time information, the time correlation information and the global correlation information of the input electrocardiogram data to determine whether the electrocardiogram data contains abnormal heart rhythm information and the abnormal heart rhythm type corresponding to the electrocardiogram data. Moreover, the multi-label classification model of the embodiment of the application can classify the condition that the electrocardiogram data comprises a plurality of different types of arrhythmia.
It should be noted that the multi-label classification model in the embodiment of the present application may be implemented by using a basic multi-label classifier, and may also be implemented in a multi-task manner. In practical use, a suitable multi-label classification model can be selected according to actual needs and specific application scenarios, which are not limited in the embodiments of the present application,
according to the arrhythmia identification method provided by the embodiment of the application, the electrocardiogram data is obtained, the spatial information and the local time information are extracted from the electrocardiogram data, the time related information and the global related information are extracted from the electrocardiogram data, and the arrhythmia information is generated according to the spatial information, the local time information, the time related information and the global related information. Therefore, the model extracts and analyzes the time-space information of the electrocardiogram data, and the arrhythmia information corresponding to the electrocardiogram is determined according to the extracted characteristic information, so that the electrocardiogram data is automatically identified, the arrhythmia identification efficiency is improved, and the labor cost is reduced.
In a possible implementation form of the present application, feature information included in electrocardiogram data may be efficiently mined through a framework in which a CNN model, a Recurrent Neural Network (RNN) model, and an Attention mechanism (Attention) are combined, so as to greatly improve accuracy of arrhythmia identification.
The arrhythmia identification method provided by the embodiment of the present application is further described below with reference to fig. 2.
Fig. 2 is a flowchart illustrating another arrhythmia identification method according to an embodiment of the present disclosure.
As shown in fig. 2, the method for identifying arrhythmia includes the following steps:
The detailed implementation and principle of the step 201 may refer to the detailed description of the above embodiments, and are not described herein again.
As a possible implementation manner, a multi-label neural network model architecture fused with a CNN + RNN + Attention mechanism may be adopted to implement the method for identifying arrhythmia according to the embodiment of the present application. Fig. 3 is a schematic structural diagram of a multi-label neural network model architecture according to an embodiment of the present disclosure.
The embodiment of the application can adopt the CNN model to extract the spatial information and the local time information in the electrocardiogram data. Because the electrocardiogram data is a multi-channel one-dimensional time sequence signal, and the basic unit of the CNN model is a convolution layer, the CNN model can be formed by adopting the one-dimensional convolution layer to extract the spatial information and the local time information of the electrocardiogram data. Fig. 3 is a schematic structural diagram of a CNN model according to an embodiment of the present disclosure, where the CNN model includes 5 modules (blocks), and each module is composed of 3 one-dimensional convolutional layers and one Dropout layer, as shown in fig. 4.
The CNN model according to the embodiment of the present application may be formed using a two-dimensional convolution layer. In actual use, one-dimensional convolution layers or two-dimensional convolution layers can be selected according to actual needs. The basic structure of each Block forming the CNN model is close, but the corresponding super-parameter of each Block can be adjusted according to the actual situation, and the number of blocks can also be adjusted according to the actual situation.
As a possible implementation manner, the embodiment of the present application may employ an RNN model to extract time-related information in electrocardiogram data. The RNN model has strong capability of extracting the time sequence information, and particularly, the bidirectional RNN model can simultaneously extract the time sequence information in two directions, so that the RNN model is particularly suitable for arrhythmia with characteristics in two directions, such as ventricular premature beat, atrial premature beat and the like. Fig. 6 is a schematic structural diagram of a bidirectional RNN according to an embodiment of the present application.
It should be noted that, in actual use, if it is not necessary to identify the arrhythmia type with bidirectional characteristics, the extraction of the time-related information may also be implemented by using a unidirectional RNN model.
In step 204, global correlation information is extracted from the electrocardiographic data through the attention model.
As a possible implementation, an attention model may be employed to extract globally relevant information in the electrocardiographic data. The attention mechanism is a new technology developed in recent years, which simulates the attention mode of human beings and can extract information particularly relevant to a target in a global or local range so as to greatly improve the accuracy of recognition. There are various ways to implement the attention model, such as a self-attention mechanism, a global attention mechanism, a Transformer, etc. Fig. 7 is a schematic view of an attention model provided in an embodiment of the present application.
The detailed implementation process and principle of step 205 may refer to the detailed description of the above embodiments, and are not described herein again.
According to the arrhythmia identification method provided by the embodiment of the application, the electrocardiogram data is obtained, the CNN model extracts the spatial information and the local time information from the electrocardiogram data, then the RNN model extracts the time correlation information from the electrocardiogram data, the attention model extracts the global correlation information from the electrocardiogram data, and then the spatial information, the local time information, the time correlation information and the global correlation information are input into the multi-label classification model to generate the arrhythmia information. Therefore, through a multi-label neural network architecture fused with the CNN model, the RNN model and the attention mechanism, the characteristic information contained in the electrocardiogram data is efficiently mined, so that the arrhythmia identification efficiency is improved, the labor cost is reduced, and the arrhythmia identification accuracy is greatly improved.
In order to implement the above embodiments, the present application also proposes an arrhythmia identification apparatus.
Fig. 8 is a schematic structural diagram of an arrhythmia identification apparatus according to an embodiment of the present application.
As shown in fig. 8, the arrhythmia recognition apparatus 30 includes:
an acquisition module 31 for acquiring electrocardiogram data;
a first extraction module 32 for extracting spatial information and local temporal information from the electrocardiographic data;
a second extraction module 33, configured to extract time-related information and global-related information from the electrocardiographic data;
and a generating module 34, configured to generate arrhythmia information according to the spatial information, the local temporal information, the temporal correlation information, and the global correlation information.
In practical use, the arrhythmia identification apparatus provided by the embodiment of the application may be configured in an electronic device to execute the arrhythmia identification method.
According to the arrhythmia recognition device provided by the embodiment of the application, the electrocardiogram data is obtained, the spatial information and the local time information are extracted from the electrocardiogram data, the time related information and the global related information are extracted from the electrocardiogram data, and the arrhythmia information is generated according to the spatial information, the local time information, the time related information and the global related information. Therefore, the model extracts and analyzes the time-space information of the electrocardiogram data, and the arrhythmia information corresponding to the electrocardiogram is determined according to the extracted characteristic information, so that the electrocardiogram data is automatically identified, the arrhythmia identification efficiency is improved, and the labor cost is reduced.
In a possible implementation form of the present application, the first extracting module 32 is specifically configured to:
spatial information and local temporal information are extracted from the electrocardiographic data by a convolutional neural network model, wherein the convolutional neural network model comprises a plurality of modules, each module comprising a plurality of one-dimensional convolutional layers and a Dropout layer.
In a possible implementation form of the present application, the second extraction module 33 is specifically configured to:
time-related information is extracted from the electrocardiographic data by a recurrent neural network model.
Further, in a possible implementation form of the present application, the second extraction module 33 is further configured to:
the global correlation information is extracted from the electrocardiographic data by an attention model.
In a possible implementation form of the present application, the generating module 34 is specifically configured to:
and inputting the spatial information, the local time information, the time correlation information and the global correlation information into a multi-label classification model to generate arrhythmia information.
It should be noted that the above explanation of the embodiment of the arrhythmia identification method shown in fig. 1 and fig. 2 is also applicable to the arrhythmia identification apparatus 30 of this embodiment, and is not repeated here.
The arrhythmia recognition device provided by the embodiment of the application generates arrhythmia information by acquiring electrocardiogram data, extracting spatial information and local time information from the electrocardiogram data through a CNN (convolutional neural network) model, then extracting time-related information from the electrocardiogram data through an RNN model, and extracting global related information from the electrocardiogram data through an attention model, and then inputting the spatial information, the local time information, the time-related information and the global related information into a multi-label classification model. Therefore, through a multi-label neural network architecture fused with the CNN model, the RNN model and the attention mechanism, the characteristic information contained in the electrocardiogram data is efficiently mined, so that the arrhythmia identification efficiency is improved, the labor cost is reduced, and the arrhythmia identification accuracy is greatly improved.
In order to implement the above embodiments, the present application further provides an electronic device.
Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
As shown in fig. 9, the electronic device 200 includes:
a memory 210 and a processor 220, a bus 230 connecting the different components (including the memory 210 and the processor 220), wherein the memory 210 stores a computer program, and when the processor 220 executes the program, the method for identifying arrhythmia according to the embodiment of the present application is implemented.
A program/utility 280 having a set (at least one) of program modules 270, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment, may be stored in, for example, the memory 210. The program modules 270 generally perform the functions and/or methodologies of the embodiments described herein.
The processor 220 executes various functional applications and data processing by executing programs stored in the memory 210.
It should be noted that, the implementation process and the technical principle of the electronic device of the present embodiment refer to the foregoing explanation of the arrhythmia identification method according to the embodiment of the present application, and are not described herein again.
The electronic device provided by the embodiment of the application can execute the arrhythmia identification method as described above, and generate arrhythmia information according to the spatial information, the local time information, the time-related information and the global-related information by acquiring electrocardiogram data, extracting the spatial information and the local time information from the electrocardiogram data, and then extracting the time-related information and the global-related information from the electrocardiogram data. Therefore, the model extracts and analyzes the time-space information of the electrocardiogram data, and the arrhythmia information corresponding to the electrocardiogram is determined according to the extracted characteristic information, so that the electrocardiogram data is automatically identified, the arrhythmia identification efficiency is improved, and the labor cost is reduced.
In order to implement the above embodiments, the present application also proposes a computer-readable storage medium.
The computer readable storage medium stores thereon a computer program, which when executed by a processor, implements the method for identifying arrhythmia according to the embodiments of the present application.
In order to implement the foregoing embodiments, a further embodiment of the present application provides a computer program, which when executed by a processor, implements the arrhythmia identification method according to the embodiments of the present application.
In an alternative implementation, the embodiments may be implemented in any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the consumer electronic device, partly on the consumer electronic device, as a stand-alone software package, partly on the consumer electronic device and partly on a remote electronic device, or entirely on the remote electronic device or server. In the case of remote electronic devices, the remote electronic devices may be connected to the consumer electronic device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external electronic device (e.g., through the internet using an internet service provider).
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method for identifying cardiac arrhythmia, comprising:
acquiring electrocardiogram data;
extracting spatial information and local temporal information from the electrocardiogram data;
extracting time-related information and global-related information from the electrocardiogram data;
and generating arrhythmia information according to the spatial information, the local time information, the time correlation information and the global correlation information.
2. The method for identifying arrhythmia according to claim 1, wherein the extracting spatial information and local temporal information from the electrocardiographic data includes:
extracting the spatial information and the local temporal information from the electrocardiographic data by a convolutional neural network model, wherein the convolutional neural network model comprises a plurality of modules, each module comprising a plurality of one-dimensional convolutional layers and a Dropout layer.
3. The method for identifying arrhythmia according to claim 1, wherein the extracting of the temporal correlation information and the global correlation information from the electrocardiographic data includes:
extracting the time-dependent information from the electrocardiographic data by a recurrent neural network model.
4. The method for identifying arrhythmia according to claim 1, wherein the extracting of the temporal correlation information and the global correlation information from the electrocardiographic data includes:
the global correlation information is extracted from the electrocardiographic data by an attention model.
5. The method for identifying arrhythmia according to claim 1, wherein the generating arrhythmia information based on the spatial information, the local temporal information, the temporal correlation information, and the global correlation information includes:
and inputting the spatial information, the local time information, the time correlation information and the global correlation information into a multi-label classification model to generate the arrhythmia information.
6. An arrhythmia recognition device, comprising:
an acquisition module for acquiring electrocardiogram data;
a first extraction module for extracting spatial information and local temporal information from the electrocardiographic data;
the second extraction module is used for extracting time-related information and global-related information from the electrocardiogram data;
and the generating module is used for generating arrhythmia information according to the spatial information, the local time information, the time correlation information and the global correlation information.
7. The arrhythmia identification device of claim 6, wherein the first extraction module is specifically configured to:
extracting the spatial information and the local temporal information from the electrocardiographic data by a convolutional neural network model, wherein the convolutional neural network model comprises a plurality of modules, each module comprising a plurality of one-dimensional convolutional layers and a Dropout layer.
8. The arrhythmia recognition device of claim 1, wherein the second extraction module is specifically configured to:
extracting the time-dependent information from the electrocardiographic data by a recurrent neural network model.
9. An electronic device, comprising: memory, processor and program stored on the memory and executable on the processor, characterized in that the processor implements the method for identifying an arrhythmia according to any of claims 1 to 5 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for arrhythmia identification as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139361.XA CN111358460A (en) | 2020-03-03 | 2020-03-03 | Arrhythmia identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139361.XA CN111358460A (en) | 2020-03-03 | 2020-03-03 | Arrhythmia identification method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111358460A true CN111358460A (en) | 2020-07-03 |
Family
ID=71198327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010139361.XA Pending CN111358460A (en) | 2020-03-03 | 2020-03-03 | Arrhythmia identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111358460A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113693610A (en) * | 2021-08-31 | 2021-11-26 | 平安科技（深圳）有限公司 | Few-lead electrocardiogram data processing method and device, storage medium and computer equipment |
| CN113855037A (en) * | 2021-10-15 | 2021-12-31 | 南方医科大学 | Atrial fibrillation identification method and device based on Transformer |
| CN115211866A (en) * | 2022-09-07 | 2022-10-21 | 西南民族大学 | Arrhythmia classification method and system and electronic equipment |
| WO2023165005A1 (en) * | 2022-03-04 | 2023-09-07 | 平安科技（深圳）有限公司 | Multi-lead elctrocardiogram signal processing method, device, apparatus, and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106901723A (en) * | 2017-04-20 | 2017-06-30 | 济南浪潮高新科技投资发展有限公司 | A kind of electrocardiographic abnormality automatic diagnosis method |
| CN107203692A (en) * | 2017-05-09 | 2017-09-26 | 哈尔滨工业大学（威海） | The implementation method of atrial fibrillation detection based on depth convolutional neural networks |
| CN109091138A (en) * | 2018-07-12 | 2018-12-28 | 上海微创电生理医疗科技股份有限公司 | The judgment means and Mapping System of arrhythmia cordis originating point |
| CN109480816A (en) * | 2018-12-18 | 2019-03-19 | 安徽华米信息科技有限公司 | Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium |
| CN110393519A (en) * | 2019-08-19 | 2019-11-01 | 广州视源电子科技股份有限公司 | Analysis method, device, storage medium and the processor of electrocardiosignal |
| CN110638430A (en) * | 2019-10-23 | 2020-01-03 | 苏州大学 | Multi-task cascade neural network ECG signal arrhythmia disease classification model and method |
| CN110720894A (en) * | 2019-11-08 | 2020-01-24 | 广州视源电子科技股份有限公司 | Atrial flutter detection method, device, equipment and storage medium |
-
2020
- 2020-03-03 CN CN202010139361.XA patent/CN111358460A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106901723A (en) * | 2017-04-20 | 2017-06-30 | 济南浪潮高新科技投资发展有限公司 | A kind of electrocardiographic abnormality automatic diagnosis method |
| CN107203692A (en) * | 2017-05-09 | 2017-09-26 | 哈尔滨工业大学（威海） | The implementation method of atrial fibrillation detection based on depth convolutional neural networks |
| CN109091138A (en) * | 2018-07-12 | 2018-12-28 | 上海微创电生理医疗科技股份有限公司 | The judgment means and Mapping System of arrhythmia cordis originating point |
| CN109480816A (en) * | 2018-12-18 | 2019-03-19 | 安徽华米信息科技有限公司 | Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium |
| CN110393519A (en) * | 2019-08-19 | 2019-11-01 | 广州视源电子科技股份有限公司 | Analysis method, device, storage medium and the processor of electrocardiosignal |
| CN110638430A (en) * | 2019-10-23 | 2020-01-03 | 苏州大学 | Multi-task cascade neural network ECG signal arrhythmia disease classification model and method |
| CN110720894A (en) * | 2019-11-08 | 2020-01-24 | 广州视源电子科技股份有限公司 | Atrial flutter detection method, device, equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113693610A (en) * | 2021-08-31 | 2021-11-26 | 平安科技（深圳）有限公司 | Few-lead electrocardiogram data processing method and device, storage medium and computer equipment |
| CN113693610B (en) * | 2021-08-31 | 2022-10-14 | 平安科技（深圳）有限公司 | Method and device for processing few-lead electrocardiogram data, storage medium and computer equipment |
| CN113855037A (en) * | 2021-10-15 | 2021-12-31 | 南方医科大学 | Atrial fibrillation identification method and device based on Transformer |
| WO2023165005A1 (en) * | 2022-03-04 | 2023-09-07 | 平安科技（深圳）有限公司 | Multi-lead elctrocardiogram signal processing method, device, apparatus, and storage medium |
| CN115211866A (en) * | 2022-09-07 | 2022-10-21 | 西南民族大学 | Arrhythmia classification method and system and electronic equipment |
| CN115211866B (en) * | 2022-09-07 | 2022-12-27 | 西南民族大学 | Arrhythmia classification method and system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11134880B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| US10758139B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| Gao et al. | An effective LSTM recurrent network to detect arrhythmia on imbalanced ECG dataset | |
| US10869610B2 (en) | System and method for identifying cardiac arrhythmias with deep neural networks | |
| Shi et al. | A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification | |
| CN111358460A (en) | Arrhythmia identification method and device and electronic equipment | |
| US20200337580A1 (en) | Time series data learning and analysis method using artificial intelligence | |
| Hammad et al. | Deep learning models for arrhythmia detection in IoT healthcare applications | |
| US9949714B2 (en) | Method, electronic apparatus, and computer readable medium of constructing classifier for disease detection | |
| US20220022799A1 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| Sharma et al. | Automated pre-screening of arrhythmia using hybrid combination of Fourier–Bessel expansion and LSTM | |
| WO2021037102A1 (en) | Electrocardiogram analysis method and apparatus based on picture and heartbeat information, and device and medium | |
| US20220044778A1 (en) | Method and electronic apparatus for providing classification data of electrocardiogram signals | |
| CN112270240B (en) | Signal processing method, device, electronic equipment and storage medium | |
| Xia et al. | Generative adversarial network with transformer generator for boosting ECG classification | |
| KR20220077583A (en) | Method and apparatus of explainable multi electrocardiogram arrhythmia diagnosis | |
| CN113693611B (en) | Machine learning-based electrocardiogram data classification method and device | |
| Deng et al. | ST-Net: Synthetic ECG tracings for diagnosing various cardiovascular diseases | |
| Liu et al. | An efficient neural network-based method for patient-specific information involved arrhythmia detection | |
| Hong et al. | Gated temporal convolutional neural network and expert features for diagnosing and explaining physiological time series: a case study on heart rates | |
| Jang et al. | Cnn-based two step r peak detection method: Combining segmentation and regression | |
| Yao et al. | Arrhythmia classification from single lead ecg by multi-scale convolutional neural networks | |
| CN113854985A (en) | Method and device for obtaining machine learning model samples for blood pressure prediction | |
| Huo et al. | ECG segmentation algorithm based on bidirectional hidden semi-Markov model | |
| KR102437348B1 (en) | Method for wearable ECG signal analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |