A processing method, device and equipment for a twelve-lead electrocardiograph

Abstract

The present application provides a processing method, apparatus, and device for a 12-lead electrocardiograph, which is used to reduce its data storage requirements based on the data processing of the 12-lead electrocardiograph, thereby effectively reducing its maintenance costs. The processing method for a 12-lead electrocardiograph provided by the present application includes: obtaining 12-lead electrocardiogram data of a user, wherein the 12-lead electrocardiogram data is data collected by the user in the past time period; inputting the 12-lead electrocardiogram data into a pre-configured convolutional neural network model, so that the convolutional neural network model determines the lead channels to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained with 12-lead electrocardiogram sample data marked with corresponding ignored lead channels; and reconstructing the lead channels of the user based on the lead channels to be ignored.

Description

Technical Field

[0001] The present application relates to the field of medical devices, and specifically to a processing method, device and equipment for a twelve-lead electrocardiograph. Background Art

[0002] In clinical electrocardiography, it is performed under a conventional twelve-lead system. The twelve-lead electrocardiogram collected by a twelve-lead electrocardiograph (also called a 12-lead electrocardiograph) provides data to facilitate clinical diagnosis.

[0003] However, the inventors of this application discovered during the operation of the existing 12-lead electrocardiograph that it has a large data storage requirement. In actual application scenarios, it is necessary to deploy high-level hardware and software conditions for data storage, and the maintenance cost is high. Summary of the Invention

[0004] The present application provides a processing method, apparatus, and device for a twelve-lead electrocardiograph, which are used to reduce the data storage requirements of the twelve-lead electrocardiograph based on the data processing of the twelve-lead electrocardiograph, thereby effectively reducing the maintenance costs involved.

[0005] In a first aspect, the present application provides a twelve-lead electrocardiograph processing method, the method comprising:

[0006] Obtaining the user's twelve-lead electrocardiogram data, wherein the twelve-lead electrocardiogram data is data collected by the user in the past time period;

[0007] Inputting the 12-lead electrocardiogram data into a preconfigured convolutional neural network model, so that the convolutional neural network model determines the lead channels to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained using the 12-lead electrocardiogram sample data labeled with the corresponding lead channels to be ignored;

[0008] Based on the lead channels to be ignored, the user's own lead channels are reconstructed.

[0009] In conjunction with the first aspect of the present application, in a first possible implementation of the first aspect of the present application, the training process of the convolutional neural network model includes the following:

[0010] Construct a training set and a test set from the 12-lead ECG sample data, and annotate the corresponding ignored lead channels in the form of a lead channel anomaly table. 20% of the samples are constructed into the training set, and the remaining 80% of the samples are constructed into the test set.

[0011] In the training set and the test set, the ECG signals of each lead channel are cut into data segments of the same length. Each ECG data segment in each lead channel has m sampling values, resulting in 12 1×m vectors.

[0012] The data segments are arranged according to the sequence of lead channels, where each ECG sample consists of a 12m×1 vector.

[0013] In combination with the first aspect of the present application, in a second possible implementation of the first aspect of the present application, the training process of the convolutional neural network model includes the following contents:

[0014] The model input data is a 12m×1 vector, and the model output data is a 1×n vector. n samples are selected from the training set as training samples. The small batch stochastic gradient descent method is used to input the training samples in batches into the 1D-CNN network classification model until the accuracy of the test set results meets the expected requirements, and the network architecture and weight parameters of the model at this time are saved.

[0015] In combination with the first aspect of the present application, in a third possible implementation of the first aspect of the present application, obtaining the user's twelve-lead electrocardiogram data includes:

[0016] The user's 12-lead electrocardiogram data is imported by the user's user equipment (UE) or the user's storage medium.

[0017] In combination with the first aspect of the present application, in a fourth possible implementation of the first aspect of the present application, obtaining the user's twelve-lead electrocardiogram data includes:

[0018] Retrieve pre-stored 12-lead ECG data on the system.

[0019] In combination with the first aspect of the present application, in a fifth possible implementation of the first aspect of the present application, based on the lead channel to be ignored, reconstructing the user's own lead channel includes:

[0020] Output prompt information of the lead channel to be ignored.

[0021] In combination with the first aspect of the present application, in a sixth possible implementation of the first aspect of the present application, based on the lead channel to be ignored, reconstructing the user's own lead channel includes:

[0022] Suspend the use of the lead channel to be ignored;

[0023] Alternatively, ignore the data collected by the lead channel to be ignored.

[0024] In a second aspect, the present application provides a processing device for a twelve-lead electrocardiograph, the device comprising:

[0025] an acquiring unit, configured to acquire twelve-lead electrocardiogram data of the user, wherein the twelve-lead electrocardiogram data is data collected by the user in the past time period;

[0026] a processing unit, configured to input the 12-lead electrocardiogram data into a preconfigured convolutional neural network model, so that the convolutional neural network model determines a lead channel to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained using 12-lead electrocardiogram sample data labeled with corresponding lead channels to be ignored;

[0027] The reconstruction unit is used to reconstruct the lead channel of the user based on the lead channel to be ignored.

[0028] In conjunction with the second aspect of the present application, in a first possible implementation of the second aspect of the present application, the training process of the convolutional neural network model includes the following:

[0029] Construct a training set and a test set from the 12-lead ECG sample data, and annotate the corresponding ignored lead channels in the form of a lead channel anomaly table. 20% of the samples are constructed into the training set, and the remaining 80% of the samples are constructed into the test set.

[0030] In the training set and the test set, the ECG signals of each lead channel are cut into data segments of the same length. Each ECG data segment in each lead channel has m sampling values, resulting in 12 1×m vectors.

[0031] The data segments are arranged according to the sequence of lead channels, where each ECG sample consists of a 12m×1 vector.

[0032] In conjunction with the second aspect of the present application, in a second possible implementation of the second aspect of the present application, the training process of the convolutional neural network model includes the following:

[0033] The model input data is a 12m×1 vector, and the model output data is a 1×n vector. n samples are selected from the training set as training samples. The small batch stochastic gradient descent method is used to input the training samples in batches into the 1D-CNN network classification model until the accuracy of the test set results meets the expected requirements, and the network architecture and weight parameters of the model at this time are saved.

[0034] In conjunction with the second aspect of the present application, in a third possible implementation of the second aspect of the present application, the acquiring unit is specifically configured to:

[0035] The user's 12-lead electrocardiogram data is imported from the user's UE or the user's storage medium.

[0036] In conjunction with the second aspect of the present application, in a fourth possible implementation of the second aspect of the present application, the acquiring unit is specifically configured to:

[0037] Retrieve pre-stored 12-lead ECG data on the system.

[0038] In conjunction with the second aspect of the present application, in a fifth possible implementation of the second aspect of the present application, the reconstruction unit is specifically configured to:

[0039] Output prompt information of the lead channel to be ignored.

[0040] In conjunction with the second aspect of the present application, in a sixth possible implementation of the second aspect of the present application, the reconstruction unit is specifically configured to:

[0041] Suspend the use of the lead channel to be ignored;

[0042] Alternatively, ignore the data collected by the lead channel to be ignored.

[0043] In a third aspect, the present application provides a processing device for a twelve-lead electrocardiograph, comprising a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the method provided in the first aspect of the present application or any possible implementation of the first aspect of the present application is executed.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the method provided in the first aspect of the present application or any possible implementation of the first aspect of the present application.

[0045] From the above content, it can be concluded that this application has the following beneficial effects:

[0046] With respect to the application of the twelve-lead ECG machine, this application first obtains the twelve-lead ECG data collected by the user in the past time period, and then inputs the twelve-lead ECG data into a pre-configured convolutional neural network model, so that the convolutional neural network model determines the lead channel to be ignored based on the twelve-lead ECG data. In this way, the lead channel of the user can be reconstructed based on the lead channel to be ignored. Since the lead channels required for this twelve-lead ECG machine are simplified for the lead channel to be ignored, the data storage requirements of the twelve-lead ECG machine can be reduced from the perspective of data processing, thereby effectively reducing the maintenance costs of manpower and material resources involved. In addition, the working costs of manpower and material resources involved in the operation of this twelve-lead ECG machine can be reduced. Obviously, the application value of the twelve-lead ECG machine is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flowchart of a processing method for a twelve-lead electrocardiograph of the present application;

[0049] Figure 2 A schematic diagram of a scenario of the processing method of the twelve-lead electrocardiograph of this application;

[0050] Figure 3 A structural diagram of a processing device of a twelve-lead electrocardiograph of the present application;

[0051] Figure 4 This is a structural diagram of the processing equipment of the twelve-lead electrocardiograph of this application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0053] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can be changed in the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0054] The division of modules in this application is a logical division. In actual application, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. Moreover, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed into multiple circuit modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application.

[0055] Before introducing the processing method of the twelve-lead electrocardiograph provided by this application, the background content involved in this application is first introduced.

[0056] The processing method, device and computer-readable storage medium of the twelve-lead electrocardiograph provided in this application can be applied to the processing equipment of the twelve-lead electrocardiograph, and can be used to reduce its data storage requirements based on the data processing of the twelve-lead electrocardiograph, thereby effectively reducing the maintenance costs involved.

[0057] The processing method of the twelve-lead electrocardiograph mentioned in this application can be executed by the processing device of the twelve-lead electrocardiograph, or the processing equipment of the twelve-lead electrocardiograph that integrates the processing device of the twelve-lead electrocardiograph.

[0058] Among them, it should be understood that the processing device of the twelve-lead electrocardiograph can be implemented in the form of hardware or software, and the processing equipment of the twelve-lead electrocardiograph can be either an integrated twelve-lead electrocardiograph or a twelve-lead electrocardiograph body and other electronic devices for performing data processing or work control. For example, a matching control system is also provided outside the twelve-lead electrocardiograph to control the operation of the twelve-lead electrocardiograph from the outside, or to work in coordination with the twelve-lead electrocardiograph.

[0059] For electronic devices other than the 12-lead ECG machine, the device form can obviously be more flexible, such as different types of electronic devices such as servers, physical hosts or UEs, and the UEs can be terminal devices such as smartphones, tablets, laptops, desktop computers or personal digital assistants (PDAs), and the specific form can be adjusted according to actual needs.

[0060] Next, we will introduce the processing method of the twelve-lead electrocardiograph provided by this application.

[0061] First, see Figure 1 , Figure 1 A flowchart of the processing method of the twelve-lead electrocardiograph provided in the present application is shown. The processing method of the twelve-lead electrocardiograph provided in the present application may specifically include the following steps S101 to S103:

[0062] Step S101, obtaining the user's 12-lead electrocardiogram data, wherein the 12-lead electrocardiogram data is data collected by the user in the past time period;

[0063] It can be understood that this application introduces a reference signal for the operation of the twelve-lead electrocardiograph, so that the effect of simplifying the lead channel can be achieved subsequently, thereby effectively reducing the data size of the twelve-lead electrocardiograph data required to be stored, and even reducing the manpower and material costs involved in the data collection process.

[0064] The reference signal is specifically the user's twelve-lead electrocardiogram data. It is worth noting that the twelve-lead electrocardiogram data obtained here is not collected for the current user, but is data collected from the user in the past time period, which can be understood as data retrieval processing.

[0065] The present application believes that the twelve-lead electrocardiogram data collected in the past time period (historical time period) is related to the specific lead channel to which it is adapted, so that it can provide a data reference for the purpose of simplifying the lead channel to be achieved subsequently.

[0066] Among them, it should be noted that for a twelve-lead electrocardiograph, data is collected through twelve lead channels under a twelve-lead system, which can be reflected on a visual device through twelve intuitive electrodes. The so-called simplified lead channel processing in this application is to retain the adapted lead channels and reduce the number of lead channels required in the current data collection work.

[0067] Furthermore, in a specific application, as a practical implementation method, the process of obtaining the user's twelve-lead electrocardiogram data may specifically include:

[0068] The user's 12-lead electrocardiogram data is imported from the user's UE or the user's storage medium.

[0069] It can be understood that the setting here takes into account the situation that the user may carry with him / her the twelve-lead ECG data that he / she has collected in the past time period. The twelve-lead ECG data collected by the user in the past time period can be stored on his / her UE or storage medium and other types of portable devices. In this way, the twelve-lead ECG data can be imported through a wired / wireless connection, thereby prompting the processing device of the twelve-lead ECG machine of this application to obtain the twelve-lead ECG data of the user in the past time period.

[0070] Under this setting, it is obvious that the user can easily obtain the twelve-lead ECG data of the past time period, which greatly enriches the acquisition path. Moreover, under this type of acquisition path, it is also highly convenient for the user.

[0071] Among them, it is worth mentioning that when the user's UE imports the user's twelve-lead ECG data of the past time period, cloud transmission may also be involved, that is, the UE can push the data to the processing device of the twelve-lead ECG machine of this application through air transmission through relevant cloud services (cloud platform), which can further improve the user's convenience.

[0072] In addition, in another practical implementation, the process of obtaining the user's twelve-lead electrocardiogram data may also specifically include:

[0073] Retrieve pre-stored 12-lead ECG data on the system.

[0074] It can be understood that this setting means that the system of the processing device of the twelve-lead electrocardiograph of the present application, or the system where the processing device of the twelve-lead electrocardiograph of the present application is located, may pre-store the twelve-lead electrocardiograph data collected by the current user in the past time period. The data may have been imported previously (such as the import method mentioned above) or may have been collected previously (and stored after collection).

[0075] In this way, the twelve-lead electrocardiograph of the present application further enriches the way in which the user obtains the twelve-lead electrocardiogram data of the past time period, serves the purpose of automated data acquisition, and can also bring a high degree of convenience to the user.

[0076] Step S102: inputting the 12-lead electrocardiogram data into a pre-configured convolutional neural network model, so that the convolutional neural network model determines the lead channels to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained using the 12-lead electrocardiogram sample data labeled with the corresponding lead channels to be ignored;

[0077] For the twelve-lead electrocardiogram data of the past time period, this application mainly implements it through a convolutional neural network model in its related data processing process. The convolutional neural network model can be trained using different CNN network classification models.

[0078] As for the data processing of the convolutional neural network model, it can be seen that the main idea can be understood as the inventor of this application believes that different twelve-lead ECG data have corresponding specific lead channels in actual applications. Therefore, during the training process, the convolutional neural network model can be trained with twelve-lead ECG sample data marked with corresponding ignored lead channels to train the pertinence and sensitivity of the data features of the twelve-lead ECG data that can be ignored. Therefore, during the use of the model, the corresponding lead channels to be ignored that can be ignored can be identified based on the input twelve-lead ECG data, which can be reflected in the form of the identification results of the lead channels to be ignored.

[0079] It can be understood that convolutional neural networks are an artificial intelligence (AI) technology. Through their deep learning and autonomous learning characteristics, they can quickly and accurately identify the ignored lead channels corresponding to the current twelve-lead electrocardiogram data and that can be ignored in real time in the application scenarios involved in this application.

[0080] It is worth mentioning that this application also has more specific supporting measures for the training process of the convolutional neural network model involved here.

[0081] Specifically, as another practical implementation method, the training process of the convolutional neural network model may include the following:

[0082] Construct a training set and a test set from the 12-lead ECG sample data, and annotate the corresponding ignored lead channels in the form of a lead channel anomaly table. 20% of the samples are constructed into the training set, and the remaining 80% of the samples are constructed into the test set.

[0083] In the training set and the test set, the ECG signals of each lead channel are cut into data segments of the same length. The ECG data segments in each lead channel are set to m (preset value) sampling values, resulting in 12 1×m vectors.

[0084] The data segments are arranged according to the sequence of lead channels, where each ECG sample consists of a 12m×1 vector.

[0085] The sample ratio setting, cropping and arrangement processing involved are all for the purpose of standardizing and granulating the samples, which makes it easier to train the model.

[0086] In addition, during the training process of the convolutional neural network model, as another specific implementation method, the following contents may also be included:

[0087] The model input data is a 12m×1 vector, and the model output data is a 1×n vector. n samples are selected from the training set as training samples. The small batch stochastic gradient descent method is used to input the training samples in batches into the 1D-CNN network classification model until the accuracy of the test set results meets the expected requirements, and the network architecture and weight parameters of the model at this time are saved.

[0088] It can be seen that the convolutional neural network model involved in this application can specifically adopt a 1D-CNN network classification model. Of course, other model types can also be used.

[0089] During the training process, the small-batch stochastic gradient descent method (method) is used. It can be understood that its convergence speed is faster than the ordinary gradient descent method, and it can also balance the convergence speed and computational efficiency. In this way, convenient and accurate recognition applications can be achieved for the lead channels to be ignored.

[0090] It is easy to understand that the lead channels to be ignored are the identified lead channels that do not need to be retained. As an example, for a user's twelve-lead ECG data in the past time period, after being processed by the convolutional neural network model, it can be fed back that only I and aVL lead monitoring are required, corresponding to V2-V6 lead monitoring, and up to four channels of lead monitoring.

[0091] In addition, for the application of the convolutional neural network model here, its sample data can also be configured as data that has been collected after simplifying the corresponding lead channel in the past time period, rather than data collected through the complete lead channel in the past time period. In this way, for the training of the model, it is more targeted for the goal of simplifying the lead channel, and thus a more accurate recognition effect can be achieved.

[0092] Among them, if the sample data includes two types of sample data collected through a complete lead channel and a simplified lead channel, the data ratio of the two can be adjusted.

[0093] Step S103: reconstructing the user's own lead channel based on the lead channel to be ignored.

[0094] As mentioned above, the purpose of this application is to simplify the lead channels through adaptive processing, thereby effectively reducing the data size of the twelve-lead electrocardiogram data that needs to be stored. Correspondingly, after determining the lead channels to be ignored in this adaptation, the reconstruction of the lead channels related to the current user can be carried out based on the lead channels to be ignored.

[0095] The reconstruction process involved here can be started from either the hardware level or the software level.

[0096] Specifically, as another practical implementation, the process of reconstructing the user's own lead channel based on the lead channel to be ignored may specifically include:

[0097] Output prompt information of the lead channel to be ignored.

[0098] It can be understood that the purpose of outputting the prompt information is to remind relevant personnel around the device that there is no need to consider laying out the lead channels to be ignored. In layman's terms, it is recommended not to attach corresponding electrodes to the user, thereby directly achieving the purpose of simplifying the lead channels and directly avoiding excessive data collection and data storage of twelve-lead electrocardiogram data.

[0099] The output method involved can be an image output method based on a display screen, a voice output method based on a speaker, or a light output method based on a prompt light of a lead channel. Of course, it can also be other types of output methods, which are not specifically limited here.

[0100] Specifically, as another practical implementation, the process of reconstructing the user's own lead channel based on the lead channel to be ignored may specifically include:

[0101] Suspend the use of the lead channel to be ignored;

[0102] Alternatively, ignore the data collected by the lead channel to be ignored.

[0103] Obviously, the setting here is to achieve the purpose of ignoring the previously determined to be ignored lead channels from the software level and technical level.

[0104] The so-called pause is that the processing device of the 12-lead electrocardiograph pauses the operation of the lead channel to be ignored, such as pausing the operation of its corresponding electrode.

[0105] The so-called ignoring can achieve the purpose of ignoring the collected data by deleting or not storing it.

[0106] For easier understanding, you can also refer to Figure 2 Taking the scenario diagram of the processing method of the twelve-lead electrocardiograph of the present application as an example, it is obvious that the number of lead channels involved in the figure has been effectively reduced. Compared with the existing technology, the work of collecting and storing twelve-lead electrocardiogram data can be directly reduced.

[0107] From the above content, it can be seen that for the application of the twelve-lead ECG machine, this application first obtains the twelve-lead ECG data collected by the user in the past time period, and then inputs the twelve-lead ECG data into the pre-configured convolutional neural network model, so that the convolutional neural network model determines the lead channel to be ignored based on the twelve-lead ECG data. In this way, based on the lead channel to be ignored, the lead channel of the user can be reconstructed. Since the lead channel required for the twelve-lead ECG machine is simplified for the lead channel to be ignored, the data storage requirements of the twelve-lead ECG machine can be reduced from the data processing of the twelve-lead ECG machine, thereby effectively reducing the maintenance cost of manpower and material resources involved. In addition, the working cost of manpower and material resources involved in the operation of the twelve-lead ECG machine can be reduced. Obviously, the application value of the twelve-lead ECG machine is further improved.

[0108] The above is an introduction to the processing method of the twelve-lead electrocardiograph provided in this application. In order to facilitate better implementation of the processing method of the twelve-lead electrocardiograph provided in this application, this application also provides a processing device of the twelve-lead electrocardiograph from the perspective of functional modules.

[0109] See Figure 3 , Figure 3 This is a schematic diagram of the structure of the processing device of the 12-lead electrocardiograph of the present application. In the present application, the processing device 300 of the 12-lead electrocardiograph may specifically include the following structure:

[0110] An acquisition unit 301 is configured to acquire 12-lead electrocardiogram data of a user, wherein the 12-lead electrocardiogram data is data collected by the user in the past time period;

[0111] a processing unit 302 configured to input the 12-lead ECG data into a preconfigured convolutional neural network model, so that the convolutional neural network model determines lead channels to be ignored based on the 12-lead ECG data, wherein the convolutional neural network model is trained using 12-lead ECG sample data labeled with corresponding lead channels to be ignored;

[0112] The reconstruction unit 303 is configured to reconstruct the user's own lead channel based on the lead channel to be ignored.

[0113] In an exemplary implementation, the training process of the convolutional neural network model includes the following:

[0114] Construct a training set and a test set from the 12-lead ECG sample data, and annotate the corresponding ignored lead channels in the form of a lead channel anomaly table. 20% of the samples are constructed into the training set, and the remaining 80% of the samples are constructed into the test set.

[0115] In the training set and the test set, the ECG signals of each lead channel are cut into data segments of the same length. Each ECG data segment in each lead channel has m sampling values, resulting in 12 1×m vectors.

[0116] The data segments are arranged according to the sequence of lead channels, where each ECG sample consists of a 12m×1 vector.

[0117] In another exemplary implementation, the training process of the convolutional neural network model includes the following:

[0118] The model input data is a 12m×1 vector, and the model output data is a 1×n vector. n samples are selected from the training set as training samples. The small batch stochastic gradient descent method is used to input the training samples in batches into the 1D-CNN network classification model until the accuracy of the test set results meets the expected requirements, and the network architecture and weight parameters of the model at this time are saved.

[0119] In another exemplary implementation, the acquiring unit 301 is specifically configured to:

[0120] The user's 12-lead electrocardiogram data is imported from the user's UE or the user's storage medium.

[0121] In another exemplary implementation, the acquiring unit 301 is specifically configured to:

[0122] Retrieve pre-stored 12-lead ECG data on the system.

[0123] In another exemplary implementation, the reconstruction unit 303 is specifically configured to:

[0124] Output prompt information of the lead channel to be ignored.

[0125] In another exemplary implementation, the reconstruction unit 303 is specifically configured to:

[0126] Suspend the use of the lead channel to be ignored;

[0127] Alternatively, ignore the data collected by the lead channel to be ignored.

[0128] This application also provides a processing device for a twelve-lead electrocardiograph from the perspective of hardware structure, see Figure 4 , Figure 4 A schematic diagram of the structure of the processing device of the 12-lead electrocardiograph of the present application is shown. Specifically, the processing device of the 12-lead electrocardiograph of the present application may include a processor 401, a memory 402, and an input / output device 403. The processor 401 is used to execute the computer program stored in the memory 402 to implement the following Figure 1The steps of the method in the corresponding embodiment; or, when the processor 401 is used to execute the computer program stored in the memory 402, the following is implemented Figure 3 The memory 402 is used to store the functions of each unit in the embodiment corresponding to the processor 401. Figure 1 The computer program required for the method in the corresponding embodiment.

[0129] For example, the computer program may be divided into one or more modules / units, one or more of which are stored in memory 402 and executed by processor 401 to implement the present application. One or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in a computer device.

[0130] The processing device of the 12-lead electrocardiograph may include, but is not limited to, a processor 401, a memory 402, and an input / output device 403. Those skilled in the art will appreciate that the diagram is merely an example of the processing device of the 12-lead electrocardiograph and does not constitute a limitation on the processing device of the 12-lead electrocardiograph. The processing device of the 12-lead electrocardiograph may include more or fewer components than shown, or a combination of certain components, or different components. For example, the processing device of the 12-lead electrocardiograph may further include a network access device, a bus, etc., and the processor 401, the memory 402, the input / output device 403, etc. are connected via the bus.

[0131] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the processing device of the 12-lead electrocardiograph, and connects various parts of the entire device using various interfaces and lines.

[0132] The memory 402 can be used to store computer programs and / or modules. The processor 401 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 402 and accessing the data stored in the memory 402. The memory 402 may primarily include a program storage area and a data storage area. The program storage area may store an operating system, at least one application required for a function, and the like; the data storage area may store data generated based on the use of the processing equipment of the 12-lead electrocardiograph. In addition, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0133] When the processor 401 is used to execute the computer program stored in the memory 402, it can specifically implement the following functions:

[0134] Obtaining the user's twelve-lead electrocardiogram data, wherein the twelve-lead electrocardiogram data is data collected by the user in the past time period;

[0135] Inputting the 12-lead electrocardiogram data into a preconfigured convolutional neural network model, so that the convolutional neural network model determines the lead channels to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained using the 12-lead electrocardiogram sample data labeled with the corresponding lead channels to be ignored;

[0136] Based on the lead channels to be ignored, the user's own lead channels are reconstructed.

[0137] Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working process of the processing device, equipment and corresponding units of the twelve-lead electrocardiograph described above can refer to the following. Figure 1 The description of the processing method of the twelve-lead electrocardiograph in the corresponding embodiment will not be repeated here.

[0138] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0139] To this end, the present application provides a computer-readable storage medium, which stores a plurality of instructions, which can be loaded by a processor to execute the present application as follows: Figure 1The steps of the processing method of the 12-lead electrocardiograph in the corresponding embodiment, the specific operation can be referred to as follows Figure 1 The description of the processing method of the twelve-lead electrocardiograph in the corresponding embodiment will not be repeated here.

[0140] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0141] Due to the instructions stored in the computer readable storage medium, the present application can be executed as follows: Figure 1 The steps of the processing method of the twelve-lead electrocardiograph in the corresponding embodiment, therefore, the present application can be realized as follows Figure 1 The beneficial effects that can be achieved by the processing method of the twelve-lead electrocardiograph in the corresponding embodiment are detailed in the previous description and will not be repeated here.

[0142] The above is a detailed introduction to the processing method, device, equipment and computer-readable storage medium of the twelve-lead electrocardiograph provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A processing method for a twelve-lead electrocardiograph, characterized in that: The method comprises: Acquire twelve-lead electrocardiogram data of the user, wherein the twelve-lead electrocardiogram data is data collected by the user in the past time period; Inputting the 12-lead electrocardiogram data into a preconfigured convolutional neural network model, so that the convolutional neural network model determines the lead channels to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained using 12-lead electrocardiogram sample data labeled with corresponding lead channels to be ignored; reconstructing the lead channel of the user based on the lead channel to be ignored; The training process of the convolutional neural network model includes the following: Constructing a training set and a test set from the twelve-lead electrocardiogram sample data, and marking the corresponding ignored lead channels in the form of a lead channel anomaly table, wherein 20% of the samples are constructed into the training set and the remaining 80% of the samples are constructed into the test set; In the training set and the test set, the ECG signal of each lead channel is cut into data segments of the same length, wherein each ECG data segment in the lead channel is provided with m sampling values, thereby obtaining 12 1×m vectors; The data segments are arranged according to the sequence of lead channels, wherein each electrocardiogram sample consists of a 12m×1 vector.

2. The method according to claim 1, characterized in that The training process of the convolutional neural network model includes the following: The model input data is a 12m×1 vector, and the model output data is a 1×n vector. n samples are selected from the training set as training samples. The small batch stochastic gradient descent method is used to input the training samples in batches into the 1D-CNN network classification model until the accuracy of the test set results meets the expected requirements, and the network architecture and weight parameters of the model at this time are saved.

3. The method according to claim 1, characterized in that The obtaining of the user's twelve-lead electrocardiogram data includes: The twelve-lead electrocardiogram data of the user is imported by the user equipment UE of the user or the storage medium of the user.

4. The method according to claim 1, wherein The obtaining of the user's twelve-lead electrocardiogram data includes: The pre-stored twelve-lead electrocardiogram data is retrieved on the system.

5. The method according to claim 1, wherein The reconstructing the user's own lead channel based on the to-be-ignored lead channel includes: Output the prompt information of the lead channel to be ignored.

6. The method according to claim 1, characterized in that The reconstructing the user's own lead channel based on the to-be-ignored lead channel includes: suspending the use of the lead channel to be ignored; Alternatively, the data collected by the to-be-ignored lead channel is ignored.

7. A processing device for a twelve-lead electrocardiograph, characterized in that: The device comprises: an acquiring unit, configured to acquire twelve-lead electrocardiogram data of a user, wherein the twelve-lead electrocardiogram data is data collected by the user in a past time period; a processing unit, configured to input the 12-lead electrocardiogram data into a preconfigured convolutional neural network model, so that the convolutional neural network model determines lead channels to be ignored based on the 12-lead electrocardiogram data, wherein the convolutional neural network model is trained using 12-lead electrocardiogram sample data labeled with corresponding lead channels to be ignored; a reconstruction unit, configured to reconstruct the lead channel of the user based on the lead channel to be ignored; The training process of the convolutional neural network model includes the following: Constructing a training set and a test set from the twelve-lead electrocardiogram sample data, and marking the corresponding ignored lead channels in the form of a lead channel anomaly table, wherein 20% of the samples are constructed into the training set and the remaining 80% of the samples are constructed into the test set; In the training set and the test set, the ECG signal of each lead channel is cut into data segments of the same length, wherein each ECG data segment in the lead channel is provided with m sampling values, thereby obtaining 12 1×m vectors; The data segments are arranged according to the sequence of lead channels, wherein each electrocardiogram sample consists of a 12m×1 vector.

8. A processing device, characterized in that The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the method according to any one of claims 1 to 6 is executed.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method according to any one of claims 1 to 6.

Images