Electrocardiogram data analysis system and method, electronic device and storage medium

Abstract

The invention relates to an electrocardio data analysis system and method, an electronic device and a storage medium, and the electrocardio data analysis method comprises the steps: obtaining original electrocardio data, and generating a first electrocardio data analysis result according to the original electrocardio data and electrocardio analysis parameters; generating a second electrocardio data analysis result according to the first electrocardio data analysis result and the first target data; wherein the first target data comprises a target typicality heart beat model in the electrocardiogram data. By means of the method and device, the technical problem that in the prior art, when dynamic electrocardio data are reanalyzed, all modifications of a user in the early stage are ignored, and consequently the work of the user is repeated is solved, and in the electrocardio data reanalysis process, the diagnosis speed is greatly increased, the labor intensity of the user is reduced, and the user experience is improved. And the accuracy of the diagnosis conclusion is improved.

Description

Technical Field

[0001] The present application relates to the field of electrocardiogram technology, and in particular to an electrocardiogram data analysis system and method, an electronic device and a storage medium. Background Art

[0002] Electrocardiogram examination has become one of the four routine examinations in clinical practice and health examinations. Since the electrocardiogram examination is non-destructive, simple and fast, it has been widely used in clinical practice and has become one of the most important means of diagnosing cardiovascular diseases. It plays an important role in diagnosing heart rate variability, myocardial ischemia, myocardial infarction, etc. However, due to the wide variety and great variation of pathological electrocardiograms, there are great differences in the electrocardiograms of different subjects with the same pathology and even the electrocardiograms of the same subject. To make an accurate judgment, users are usually required to have rich knowledge and accumulated a lot of clinical experience. In addition, electrocardiograms, especially dynamic electrocardiograms, monitor for a long time and have a large amount of data. Electrocardiogram examination reports are generally edited manually by users.

[0003] In traditional ECG examination methods, the ECG data of the patient is collected through the ECG acquisition system, and then the user observes the ECG printed out or displayed on the computer screen, and analyzes and diagnoses the ECG beats one by one in combination with the user's own professional knowledge. However, ECG data usually contains a large amount of data, and it is generally difficult for users to make a quick and accurate diagnosis in a short period of time; and if the ECG is viewed for a long time, it is inevitable that a lot of time and energy will be consumed, which is not conducive to improving the user's work efficiency; at the same time, the user's long-term observation of ECG data is prone to missed detection due to visual fatigue or lack of concentration, affecting the final ECG diagnosis results.

[0004] In the dynamic ECG analysis software, there will be a scenario where the recognition accuracy of the data under the main analysis lead automatically identified by the software is not enough, or the parameter settings do not match the case, and the report cannot be effectively output. At this time, the user needs to modify the parameters and re-edit them to re-analyze the data. The re-analysis of the existing software is a completely independent process, which will ignore all the modifications made by the previous users. That is, the existing re-analysis does not refer to the user's historical data, and the user's work will be repetitive, resulting in low analysis efficiency.

[0005] There is currently no effective solution to the technical problem of low analysis efficiency when re-analyzing dynamic electrocardiogram data in the existing technology. Summary of the invention

[0006] In this embodiment, an ECG data analysis system and method, an electronic device and a storage medium are provided to solve the problem in the prior art that when reanalyzing dynamic ECG data, all previous user modifications are ignored, resulting in duplication of user work.

[0007] In a first aspect, an ECG data analysis system is provided in this embodiment, and the ECG data analysis system includes: an original ECG analysis module and an ECG re-analysis module;

[0008] The original ECG analysis module is used to obtain original ECG data and generate a first ECG data analysis result according to the original ECG data and ECG analysis parameters;

[0009] The ECG re-analysis module is used to generate a second ECG data analysis result based on the first ECG data analysis result and the first target data; wherein the first target data includes a target typical heart beat model in the ECG data.

[0010] In some embodiments, the ECG data analysis system further includes: a parameter acquisition module; the parameter acquisition module is used to acquire the ECG analysis parameters 。

[0011] In some of the embodiments, the ECG reanalysis module further includes: a heart beat selection submodule;

[0012] The heartbeat selection submodule is used to obtain the first target data after screening or modifying the second target data; wherein the second target data includes a typical heartbeat model.

[0013] In some of the embodiments, the ECG re-analysis module is further used to generate the second ECG data analysis result based on the first ECG data analysis result, the first target data and third target data; the third target data includes a target interference segment model in the ECG data.

[0014] In some of the embodiments, the ECG reanalysis module further includes: a target interference segment selection submodule;

[0015] The target interference segment selection submodule is used to obtain the third target data after screening or modifying the fourth target data; the fourth target data includes a typical interference segment model.

[0016] In some embodiments, the ECG data analysis system further includes: a first ECG data annotation module, wherein the first ECG data annotation module is used to annotate the first ECG data analysis result to obtain a first ECG data annotation result.

[0017] In some embodiments, the ECG re-analysis module further includes a labeling selection submodule; the labeling selection submodule is used to screen or modify the first ECG data labeling result to generate a second ECG data labeling result.

[0018] In some embodiments, the ECG re-analysis module is used to generate the second ECG data analysis result based on the first target data and the second ECG data labeling result; or, the ECG re-analysis module is used to generate the second ECG data analysis result based on the third target data and the second ECG data labeling result; or, the ECG re-analysis module is used to generate the second ECG data analysis result based on the first target data, the third target data and the second ECG data labeling result.

[0019] In the second aspect, an ECG data analysis method is provided in this embodiment, and the ECG data analysis method includes: acquiring original ECG data, and generating a first ECG data analysis result based on the original ECG data and ECG analysis parameters; generating a second ECG data analysis result based on the first ECG data analysis result and first target data; wherein the first target data includes a target typical heart beat model in the ECG data.

[0020] In some embodiments, the ECG data analysis method further includes: obtaining the ECG analysis parameters 。

[0021] In some embodiments, the first target data is obtained after screening or modification based on the second target data; the second target data includes a typical heartbeat model.

[0022] In some of the embodiments, the ECG data analysis method further includes: generating the ECG data analysis result based on the original ECG data, the ECG analysis parameters, the first target data and the third target data; the third target data includes a target interference segment model in the ECG data.

[0023] In some of the embodiments, the third target data is obtained after screening or modification based on the fourth target data; the fourth target data includes a typical interference segment model.

[0024] In some embodiments, the ECG data analysis method further includes: labeling the first ECG data analysis result to obtain a first ECG data labeling result.

[0025] In some embodiments, the ECG data analysis method further includes: screening or modifying the first ECG data annotation result to generate a second ECG data annotation result.

[0026] In some of the embodiments, the ECG data analysis method further includes: generating the second ECG data analysis result according to the first target data and the second ECG data annotation result;

[0027] Alternatively, generating the second electrocardiogram data analysis result according to the third target data and the second electrocardiogram data annotation result;

[0028] Alternatively, the second electrocardiogram data analysis result is generated according to the first target data, the third target data and the second electrocardiogram data annotation result.

[0029] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electrocardiogram data analysis method described in the second aspect is implemented.

[0030] In a fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the electrocardiogram data analysis method described in the second aspect is implemented.

[0031] Compared with the prior art, an ECG data analysis system and method, an electronic device and a storage medium are provided in this embodiment, which obtain original ECG data, generate a first ECG data analysis result according to the original ECG data and ECG analysis parameters; generate a second ECG data analysis result according to the first ECG data analysis result and first target data; wherein the first target data includes a target typical heart beat model in the ECG data, thereby solving the technical problem in the prior art that when re-analyzing dynamic ECG data, all previous user modifications are ignored, resulting in repetitive work of the user, thereby improving the diagnosis speed and accuracy of the diagnosis conclusion of the user during the ECG data re-analysis process.

[0032] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0034] Figure 1 is a hardware structure block diagram of a terminal for executing an electrocardiogram data analysis method of this embodiment;

[0035] Figure 2 is a structural schematic diagram of an electrocardiogram data analysis system of this embodiment;

[0036] Figure 2a is a schematic diagram of an interface of an electrocardiogram data analysis system of the preferred embodiment;

[0037] Figure 2a-1 is a schematic diagram of an interface of another electrocardiogram data analysis system of the preferred embodiment;

[0038] Figure 2b is a schematic diagram of an interface of another electrocardiogram data analysis system of the preferred embodiment;

[0039] Figure 2b-1 is a schematic diagram of an interface of another electrocardiogram data analysis system of the preferred embodiment;

[0040] Figure 3 is a flow chart of an electrocardiogram data analysis method of this embodiment;

[0041] Figure 4 is a flow chart of an intelligent re-analysis method in an electrocardiogram data analysis system of the preferred embodiment;

[0042] Figure 4a is a schematic diagram of an interface of an electrocardiogram data analysis system of the preferred embodiment;

[0043] Figure 5 is a flow chart of an ECG re-analysis method in an ECG data analysis system of the preferred embodiment;

[0044] Figure 5a is a flow chart of an electrocardiogram data analysis method of the preferred embodiment;

[0045] Figure 6 is a flow chart of a typical heartbeat model generation method in an electrocardiogram data analysis system of the preferred embodiment;

[0046] Figure 7 is a flow chart of a typical interference segment model generation method in an electrocardiogram data analysis system of the preferred embodiment;

[0047] Figure 8 It is a flowchart of another method for generating a typical interference segment model in an electrocardiogram data analysis system according to the preferred embodiment. DETAILED DESCRIPTION

[0048] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0049] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0050] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal for executing an electrocardiogram data analysis method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0051] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the ECG data analysis method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0052] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0053] Electrocardiogram (ECG) diagnosis is one of the important tools used in modern medicine to diagnose heart diseases and is widely used in clinical medicine.

[0054] In this embodiment, a system for analyzing electrocardiogram data is provided. Figure 2 is a structural diagram of an electrocardiogram data analysis system of this embodiment. Figure 2 As shown, the ECG data analysis system 100 includes: an original ECG analysis module 10 and an ECG re-analysis module 20 .

[0055] Specifically, the ECG data analysis system is connected to a dynamic ECG analyzer; the dynamic ECG analyzer includes leads and an ECG acquisition circuit module, the leads are connected to the ECG acquisition circuit module, the leads are connected to the subject, and the ECG acquisition circuit module continuously acquires all ECG data of the subject during the detection time through the leads. In an embodiment of the present invention, the detection time of the subject can be one hour or multiple hours, which is not limited by the embodiment of the present invention. An exemplary implementation, such as a dynamic ECG analyzer obtains the original ECG data of all heart beats of the subject for 24 hours. In this embodiment, the dynamic ECG analyzer has a twelve-lead structure. Of course, it is not limited to this embodiment, and can also be a two-lead structure, a three-lead structure, or a five-lead structure.

[0056] The original ECG analysis module 10 is used to obtain the original ECG data and generate a first ECG data analysis result according to the original ECG data and the ECG analysis parameters. The ECG re-analysis module 20 is used to generate a second ECG data analysis result according to the first ECG data analysis result and the first target data; wherein the first target data includes a target typical heart beat model in the ECG data.

[0057] Specifically, the original ECG analysis module 10 is connected to the ECG re-analysis module 20. The original ECG analysis module 10 and the ECG re-analysis module 20 can be software modules or hardware devices on the server side. The ECG data analysis system is connected to the dynamic ECG analyzer, and the dynamic ECG analyzer sends the original ECG data to the original ECG analysis module 10. The ECG analysis parameters can be parameters input by the user (such as a medical worker or operator) according to actual conditions, including but not limited to analysis leads, pacemaker type settings, arrhythmia judgment thresholds, etc. The original ECG analysis module 10 generates a first ECG data analysis result based on the original ECG data and the ECG analysis parameters. In this embodiment, the first ECG data analysis result is an ECG report. In this embodiment, the first target data includes a target typical heartbeat model in the ECG data, which may be a typical heartbeat model generated by the system through self-learning based on the analysis results of the first ECG data or a sample ECG report, or a typical heartbeat model added by the user; further, the target typical heartbeat model includes but is not limited to a normal heartbeat (N-type heartbeat), a left bundle branch block heartbeat (L-type heartbeat), a right bundle branch block heartbeat (R-type heartbeat), and a ventricular premature beat (V-type heartbeat), etc.

[0058] By setting an original ECG analysis module 10 and an ECG re-analysis module 20 in an ECG data analysis system, the original ECG analysis module 10 obtains original ECG data, generates a first ECG data analysis result according to the original ECG data and ECG analysis parameters, and the ECG re-analysis module 20 generates a second ECG data analysis result according to the first ECG data analysis result and first target data; wherein the first target data includes a target typical heart beat model in the ECG data. The technical problem that all previous user modifications are ignored when re-analyzing dynamic ECG data in the prior art is solved, resulting in repetitive work of the user, thereby improving the diagnosis speed and accuracy of the diagnosis conclusion of the user during the ECG data re-analysis process.

[0059] In some embodiments, the ECG data analysis system further includes a parameter acquisition module, which is used to acquire ECG analysis parameters. 。

[0060] Specifically, the parameter acquisition module in this embodiment can be a smart terminal or a software module on the smart terminal. The smart terminal includes but is not limited to desktop computers, tablet computers, smart phones, etc. The parameter acquisition module acquires the parameters entered by the user on the smart terminal according to actual conditions.

[0061] In some of the embodiments, the ECG reanalysis module 20 further includes: a heartbeat selection submodule; a heartbeat selection submodule, used to obtain the first target data after screening or modifying the second target data; wherein the second target data includes a typical heartbeat model.

[0062] Specifically, the first target data is obtained by the user after screening or modifying the second target data according to the re-analysis needs. An exemplary implementation is as follows: Figure 2a As shown, after clicking to enter the re-analysis operation on the system initial interface, the system pops up a typical heartbeat selection interface. On the typical heartbeat selection interface, ventricular premature beats (V-shaped heartbeats) and normal heartbeats (N-shaped heartbeats) are provided, and manual modification buttons and "+" signs are correspondingly set. Users can choose whether to add the current ventricular premature beats and normal heartbeats as typical heartbeats, or modify the ventricular premature beats / normal heartbeats to other typical heartbeats according to actual needs; even when the user thinks that a certain heartbeat is missing in the typical heartbeats recommended by the system, he can manually click the "+" sign to add other typical heartbeats. When the user clicks the manual modification button, the typical heartbeat confirmation interface is entered, as shown in FIG. Figure 2a-1 , the user can manually modify the typical heartbeat determination interface. In the embodiment of the present invention, typical N and V heartbeat patterns are given according to the historical editing results, and the information is used to enter the analysis after confirmation by the user, which can avoid the possibility of machine self-learning errors and ensure the correctness of the analysis. It supports users not to use the typical N-type heartbeat and V-type heartbeat recommended by the system, and jump to the template interface to manually select a typical heartbeat.

[0063] In some of the embodiments, the ECG re-analysis module 20 is further used to generate a second ECG data analysis result based on the first ECG data analysis result, the first target data and the third target data; the third target data includes a target interference segment model in the ECG data.

[0064] Specifically, the typical interference segment model is obtained by dividing the original ECG data into several segments according to the set time and performing interference detection on several segments of the original ECG data. During the re-analysis, the typical interference segment will be given according to the historical editing results. After the user confirms, the target interference segment model is obtained, and then the original ECG data is analyzed, so as to ensure that the final analysis results have fewer misidentifications and artifacts, the scatter plot and histogram are cleaner, and the editing efficiency is higher.

[0065] In some of the embodiments, the ECG re-analysis module 20 further includes: a target interference segment selection submodule; a target interference segment selection submodule, used to obtain third target data after screening or modifying the fourth target data; and the fourth target data includes a typical interference segment model.

[0066] Specifically, the third target data is obtained by screening or modifying the fourth target data according to the re-analysis requirements. In an exemplary implementation, after clicking to enter the re-analysis operation on the system initial interface, as shown in FIG. Figure 2b , the system pops up a typical interference segment model selection interface, on which recommended typical interference segment models appear, such as Figure 2b-1 After selecting the target interference segment model from the typical interference segment models, the typical interference segment model selection interface will pop up "Set as interference event" and "Delete event mark". Click "Set as interference event" and the typical interference segment model will be identified as the target interference segment model, and no heartbeat detection will be performed on it. Click "Delete event mark" and the heartbeat segment will be identified as a normal segment, and normal heartbeat detection will be performed.

[0067] In some of the embodiments, the ECG data analysis system further includes: a first ECG data annotation module, the first ECG data annotation module is used to annotate the first ECG data analysis result to obtain a first ECG data annotation result.

[0068] Specifically, the first ECG data analysis result is generated by the system through input parameters, namely the original ECG data. The heartbeats and corresponding heartbeat type labels in the first ECG data analysis result may be erroneous. A first ECG data labeling module is set in the ECG data analysis system, and the labeling data is obtained through the first ECG data labeling module. The first ECG data labeling module labels the first ECG data analysis result according to the labeling data to obtain the first ECG data labeling result.

[0069] In some of the embodiments, the ECG re-analysis module further includes a labeling selection submodule; the labeling selection submodule is used to screen or modify the first ECG data labeling result to generate a second ECG data labeling result.

[0070] Specifically, in an embodiment of the present invention, the original ECG analysis module 10 is used to back up the original ECG data and the first ECG data analysis result generated based on the historical input parameters; the ECG re-analysis module 20 is used to obtain the first ECG data analysis result and / or the first ECG data annotation result generated based on the historical input annotation data.

[0071] Furthermore, when the original ECG data needs to be reanalyzed, the ECG reanalysis module 20 is started, and the first ECG data annotation result is retrieved for the user to refer to and modify, and the user filters or modifies the first ECG data annotation result to generate a second ECG data annotation result.

[0072] In some of the embodiments, the ECG re-analysis module 20 is used to generate a second ECG data analysis result based on the first target data and the second ECG data annotation results; or, the ECG re-analysis module 20 is used to generate a second ECG data analysis result based on the third target data and the second ECG data annotation results; or, the ECG re-analysis module 20 is used to generate a second ECG data analysis result based on the first target data, the third target data and the second ECG data annotation results.

[0073] Specifically, the first target data includes a target typical heartbeat model in the ECG data, and the third target data includes a target interference segment model in the ECG data; the ECG re-analysis module 20 is used to generate a second ECG data analysis result based on the target typical heartbeat model and the second ECG data labeling result; or, the ECG re-analysis module 20 is used to generate a second ECG data analysis result based on the target interference segment model and the second ECG data labeling result; or, the ECG re-analysis module 20 is used to generate a second ECG data analysis result based on the target typical heartbeat model, the target interference segment model and the second ECG data labeling result.

[0074] In this embodiment, a method for analyzing electrocardiogram data is provided. The method for analyzing electrocardiogram data in this embodiment is applied to the above-mentioned electrocardiogram data analyzing system 100. Figure 3 is a flow chart of an electrocardiogram data analysis method of this embodiment. Figure 3 As shown, the process includes the following steps:

[0075] Step S302, acquiring original ECG data, and generating a first ECG data analysis result according to the original ECG data and ECG analysis parameters.

[0076] Specifically, the ECG data analysis system is connected to the Holter analyzer, which sends the original ECG data to the original ECG analysis module 10; the ECG analysis parameters may be parameters input by the user according to actual conditions, including but not limited to analysis leads, pacemaker type, arrhythmia judgment threshold, annotated data, etc. The original ECG analysis module 10 sets and annotates the original ECG data according to the system ECG analysis parameters, and generates a first ECG data analysis result.

[0077] Step S304, generating a second ECG data analysis result according to the first ECG data analysis result and the first target data; wherein the first target data includes a target typical heart beat model in the ECG data.

[0078] Specifically, in an embodiment of the present invention, first operation data is generated according to the first ECG data analysis result, second operation data is generated according to the first target data, and second ECG data analysis result is generated according to the first operation data and the second operation data. The first operation data here may be data generated by screening, modifying or retaining the historical ECG analysis parameters in the first ECG data analysis result; the second operation data here may be data generated by screening, modifying or adding the target typical heart beat model in the first target data.

[0079] Further, in an embodiment of the present invention, the first target data includes a target typical heartbeat model in the ECG data, and the target typical heartbeat model can be generated by the system through self-learning based on the analysis results of the first ECG data or a sample ECG report, or a typical heartbeat model added by the user; further, the target typical heartbeat model includes but is not limited to a normal heartbeat (N-type heartbeat), a left bundle branch block heartbeat (L-type heartbeat), a right bundle branch block heartbeat (R-type heartbeat), and a ventricular premature beat (V-type heartbeat), etc.

[0080] Through the above steps S302 to S304, the original ECG data is obtained, and a first ECG data analysis result is generated according to the original ECG data and the ECG analysis parameters; a second ECG data analysis result is generated according to the first ECG data analysis result and the first target data, and the first ECG data analysis result includes the parameters input historically; wherein the first target data includes a target typical heart beat model in the ECG data. Compared with the prior art, when re-analyzing dynamic ECG data, all historical modifications of the user are ignored, resulting in repetitive work of the user. In an embodiment of the present invention, the parameters input historically are retained. When re-analyzing, the first ECG data analysis result and the first target data are called for user reference. In the process of re-analysis, the workload of the user is greatly reduced and the diagnosis speed is improved; the historical operation data is referenced, thereby improving the accuracy of the diagnosis conclusion.

[0081] In some of the embodiments, the ECG data analysis method further includes: obtaining ECG analysis parameters.

[0082] Specifically, in this embodiment, the ECG analysis parameters are generated by the ECG re-analysis module 20 by acquiring parameters input by the user.

[0083] In some of the embodiments, the first target data is obtained after screening or modifying the second target data; the second target data includes a typical heartbeat model.

[0084] Specifically, the typical heartbeat model can be a typical heartbeat generated by deep learning of the first ECG data analysis result by the ECG re-analysis module 20, or an existing typical heartbeat can be called from a dynamic database. During the re-analysis process, the user can correct the loopholes in the historical analysis by screening or modifying the second target data, and save the time of re-analysis with the help of the historical analysis process, thereby improving the processing efficiency of dynamic ECG data, the diagnostic efficiency of dynamic ECG, and the reliability of diagnostic results.

[0085] In some of the embodiments, the ECG data analysis method further includes: generating ECG data analysis results based on original ECG data, ECG analysis parameters, first target data and third target data; the third target data includes a target interference segment model in the ECG data.

[0086] In some of the embodiments, the third target data is obtained after screening or modification based on the fourth target data; the fourth target data includes a typical interference segment model.

[0087] Specifically, the typical interference segment model is generated by the ECG re-analysis module 20 through interference detection on the first ECG data analysis result, dividing the original ECG data into several segments according to the set time, performing interference detection on the several segments of original ECG data, marking the segments that do not meet the preset standards as interference segments, and generating a typical interference segment model based on the interference segments.

[0088] In some of the embodiments, the ECG data analysis method further includes: annotating the first ECG data analysis result to obtain a first ECG data annotation result.

[0089] Specifically, the ECG annotation may be performed in the form of text annotation to annotate the heartbeat type, position or attribute in the first ECG data analysis result; and the first ECG data annotation result is obtained by annotating the first ECG data analysis result.

[0090] In some of the embodiments, the ECG data analysis method further includes: screening or modifying the first ECG data annotation result to generate a second ECG data annotation result.

[0091] In some of the embodiments, the ECG data analysis method also includes: generating a second ECG data analysis result based on the first target data and the second ECG data labeling results; or, generating a second ECG data analysis result based on the third target data and the second ECG data labeling results; or, generating a second ECG data analysis result based on the first target data, the third target data and the second ECG data labeling results.

[0092] Specifically, in the present embodiment, the third target data includes a target interference segment model, which is obtained by screening, modifying or adding a typical interference segment model. During the re-analysis process, the second ECG data analysis result can be obtained through three embodiments. In the first embodiment, the system generates the second ECG data analysis result by obtaining the first target data obtained by the user screening, modifying or adding a typical heartbeat model and reanalyzing, confirming or modifying the second ECG data annotation result obtained by annotating the first ECG data analysis result obtained by the user in the historical analysis process; in the second embodiment, the system generates the second ECG data analysis result by obtaining the third target data obtained by the user screening, modifying or adding a typical interference segment model and reanalyzing, confirming or modifying the second ECG data annotation result obtained by the user in the historical analysis process. The ECG data analysis results are annotated to obtain the second ECG data annotating result obtained by re-analyzing, confirming or modifying the first ECG data annotating result, thereby generating the second ECG data analysis result; in the third embodiment, the system generates the second ECG data analysis result by acquiring the first target data obtained by the user screening, modifying or adding a typical heartbeat model, the third target data obtained by the user screening, modifying or adding a typical interference segment model, and the second ECG data annotating result obtained by the user re-analyzing, confirming or modifying the first ECG data annotating result obtained by annotating the first ECG data analysis result in the historical analysis process.

[0093] In an embodiment of the present invention, during the re-analysis process, not only the parameters input by the user during the historical analysis process and the first ECG data analysis results are retained, but also the first ECG data analysis results are analyzed to generate first target data and third target data, the first target data includes a typical heartbeat model, and the third target data includes a typical interference segment model; wherein the typical heartbeat model and the typical interference segment model are provided for the user to re-analyze, confirm or modify, which greatly reduces the user's workload, improves the diagnosis speed, and reduces the user's labor intensity. During the re-analysis process, the historical user analysis and diagnosis records are retained, and the system generates target data for the historical analysis and diagnosis records for reference during the next user re-analysis, thereby ensuring the continuity of the ECG analysis.

[0094] The present embodiment is described and illustrated below through preferred embodiments.

[0095] Figure 4 is a flow chart of an intelligent re-analysis method in an ECG data analysis system of the preferred embodiment. Figure 4 As shown, the intelligent re-analysis method in the ECG data analysis system includes the following steps:

[0096] Step S402: backing up the first electrocardiogram analysis result.

[0097] Specifically, the first ECG analysis result includes first operation data and original ECG data, and the first operation data includes operation data input during the re-analysis process and operation data input during the confirmed and retained historical analysis process. The operation data may be user-selected data, input parameters, and annotation data. Furthermore, the user-selected data includes user-selected lead data and pacemaker type data, etc., and the input parameters include arrhythmia thresholds; before each ECG re-analysis, the ECG re-analysis module backs up the historical first operation data.

[0098] Step S404: generating re-analysis option data according to the first electrocardiogram analysis result.

[0099] Specifically, each time re-analysis is required, the system retrieves the first ECG analysis result from the database, and generates re-analysis option data based on the first ECG analysis result, wherein the re-analysis option data is data that requires the user to perform re-analysis confirmation according to pre-set settings. The system generates the re-analysis option data based on the first operation data and the original ECG data for the user to perform re-analysis confirmation.

[0100] Step S406: Generate second operation data according to the re-analysis option data.

[0101] Specifically, the reanalysis option data includes typical heartbeat option data, typical interference segment option data and annotation option data. Among them, the typical heartbeat option data can be displayed as a variety of typical heartbeat option boxes on the system, each typical heartbeat option box includes a corresponding typical heartbeat graph and a selection, modification or deletion button; the typical interference segment option data can be displayed as a variety of typical interference segment option boxes on the system, each typical interference segment option box includes a corresponding typical interference segment graph and a selection, modification or deletion button; the original ECG data includes multiple heartbeats, and the system will annotate the type of each heartbeat to generate original ECG annotation data. If the user modifies the original ECG annotation data, the annotation option data is generated. During the reanalysis process, the user refers to the reanalysis option data and enters the second operation data.

[0102] Furthermore, in an exemplary embodiment, when the user selects a completely independent analysis, the system retrieves the original ECG data, and generates analysis results based on the parameters and annotations input by the user; when the user selects a re-analysis based on the previous analysis results, the system retrieves the historical ECG analysis results for backup, obtains the data that the user has modified and selected with reference to the historical ECG analysis results, and generates analysis results. Each time a re-analysis is performed, the user clicks the "Re-analysis" button, and the interface pops up "Completely Independent Analysis" or "Re-analysis Based on Previous Analysis Results" for the user to select. Furthermore, when the user selects "Re-analysis Based on Previous Analysis Results", the system pops up a recommended typical heart beat model and a typical interference segment model for the user to select or modify.

[0103] Step S408: Generate a second electrocardiogram analysis result according to the second operation data and the first electrocardiogram analysis result.

[0104] Specifically, the original ECG data in the first ECG analysis result is obtained, and the second operation data is input by the user with reference to the re-analysis option data. The second operation data includes data generated by selecting, modifying, adding or deleting typical heart beat model data, typical interference segment model data and annotation option data. The second operation data also includes typical heart beat model data, typical interference segment model data and annotation data added by the user based on his or her own experience.

[0105] Further, in an exemplary embodiment, there is a "manual modification" button on the right side of the heartbeat of the module. When clicked, it enters the manual selection heartbeat interactive interface, enters the "template" interface of the software, and modifies the selected object. Or when the heartbeat morphology of different types of patients is quite different, the user can also click the "add" button, drag the scroll bar below to view other typical heartbeat models, and manually add a typical heartbeat model. Figure 2b The specific waveform information of the typical interference segment model is displayed. The waveform information includes the heart rate trend graph and the interference segment annotation information. The information of the heart rate trend graph can reflect the result of heart beat detection and the degree of interference to a certain extent. Users can modify and confirm the annotation data of the target interference segment according to the waveform information, such as Figure 2b-1 As shown, the typical interference segment model can be operated, and the annotated data of the target interference segment can be selected for annotation or deletion.

[0106] Through the above steps S402 to S408, when the Holter software reanalyzes, the embodiment of the present invention uses the historical analysis results, compares and analyzes the editing results, and performs analysis based on the editing results. The user's historical editing results are retained, and there is no need to restart editing, thereby improving work efficiency. When the embodiment of the present invention reanalyzes again, a typical heartbeat morphology is given based on the historical editing results. After confirmation by the user, the information is used to enter the analysis, which can avoid the possibility of self-learning errors and ensure the correctness of the analysis.

[0107] Figure 5 is a flow chart of an ECG reanalysis method in an ECG data analysis system of the preferred embodiment. Figure 5 As shown, the ECG reanalysis method in the dynamic ECG analysis system includes the following steps:

[0108] Step S502: Acquire second operation data.

[0109] Specifically, the second operation data is input by the user with reference to the re-analysis option data, and the system obtains the second operation data input by the user.

[0110] Step S504, determine whether there is a typical heartbeat, if so, execute step S506, if not, execute step S508.

[0111] Specifically, the system determines whether there is a typical heartbeat in the second operation data, wherein the typical heartbeat includes those recommended by the system, selected by the user after clicking, and added by the user.

[0112] Step S506, construct a first heart beat template, and execute step S510.

[0113] Specifically, when the system determines that there is a typical heartbeat in the second operation data, a first heartbeat template is constructed according to the typical heartbeat in the second operation data.

[0114] Further, the first heart beat template is one or a combination of N-type heart beat, S-type heart beat, V-type heart beat, F-type heart beat or Q-type heart beat. Exemplarily, the first heart beat template is an N-type heart beat template and a V-type heart beat template.

[0115] Step S508, executing the heartbeat self-learning process, obtaining a second heartbeat template, and executing step S510.

[0116] Specifically, when the system determines that there is no typical heartbeat in the second operation data, the system performs a heartbeat self-learning process on the original electrocardiogram data to obtain a second heartbeat template.

[0117] Further, the second heartbeat template is one or a combination of N-type heartbeat, S-type heartbeat, V-type heartbeat, F-type heartbeat or Q-type heartbeat. Exemplarily, the second heartbeat template is an N-type heartbeat template.

[0118] Step S510, performing ECG analysis on the original ECG data beat by beat.

[0119] Specifically, the original electrocardiogram data is subjected to beat-by-beat electrocardiogram analysis according to the first heart beat template or the second heart beat template.

[0120] Through the above steps, by obtaining the second operation data, determining whether there is a typical heartbeat in the second operation data, classifying and establishing a heartbeat model, and performing heartbeat detection beat by beat, the workload of the system on heartbeat data analysis during the re-analysis process is greatly reduced, and the efficiency of ECG data analysis is improved.

[0121] Figure 5a is a specific implementation of step S510, Figure 5a is a flow chart of an electrocardiogram analysis method of the preferred embodiment, such as Figure 5a As shown, performing ECG analysis on the original ECG data beat by beat includes the following steps:

[0122] Step S512, determine whether the current heartbeat is a marked heartbeat. If yes, execute step S514; if no, execute step S516.

[0123] Specifically, annotating a heartbeat means that the type or position of the current heartbeat in the original ECG data is annotated, and corresponding annotated data is generated, and the annotated data of the annotated heartbeat includes the heartbeat type and the heartbeat position. When the system determines that the current heartbeat has been annotated, the annotated current heartbeat is classified into the unmodified heartbeat collection, that is, the current heartbeat is not detected or classified.

[0124] Step S514, assigning a value to the current heartbeat according to the labeled data of the current heartbeat.

[0125] Specifically, the heartbeat position of the current heartbeat and the heartbeat type of the current heartbeat are used to complete the assignment corresponding to the current heartbeat, and step S520 is executed.

[0126] Step S516, determine whether the current heartbeat belongs to the typical interference segment model. If yes, execute step S520, if not, execute step S518.

[0127] Specifically, the typical interference segment model is determined by the typical interference segment model generation method, and it is judged whether the current heartbeat is within the typical interference segment model. If so, it means that there is interference in the current heartbeat, and the electrocardiogram analysis of the current heartbeat is skipped, and step S520 is executed; if not, step S518 is executed to perform electrocardiogram analysis on the current heartbeat.

[0128] Step S518, performing electrocardiographic analysis on the current heartbeat.

[0129] Specifically, the ECG analysis here includes heartbeat position detection and heartbeat type classification, that is, when the current heartbeat does not belong to the typical interference segment, normal heartbeat detection and heartbeat classification are performed on the current heartbeat to obtain the heartbeat position and heartbeat type of the current heartbeat, and step S520 is executed.

[0130] Step S520, determine whether the current heartbeat is a cut-off heartbeat. If yes, execute step S524, if no, execute step S522.

[0131] Specifically, the cutoff heartbeat here can be understood as the last heartbeat in the original ECG data, that is, the end of the ECG data, at which time the ECG analysis of all the heartbeats of the original ECG data has been completed.

[0132] Step S522, obtain the next heartbeat, and set the next heartbeat as the current heartbeat. The above steps are executed repeatedly.

[0133] Specifically, when the beat-by-beat ECG analysis is not finished, the next beat is set as the current beat, and step S512 is executed to continue the ECG analysis of the next beat until the ECG analysis of all beats of the original ECG data is completed.

[0134] Step S524, end.

[0135] Through the above steps S510 to S524, the ECG analysis is performed on the original ECG data beat by beat. During the beat detection process, the corresponding values ​​are directly assigned to the ECG data in the unmodified beat set, which greatly reduces the workload of the system on the beat data analysis during the re-analysis process and improves the efficiency of ECG data analysis.

[0136] Figure 6 FIG. 1 is a flow chart of a typical heart beat model generation method in an electrocardiogram data analysis system of the preferred embodiment. Figure 6 As shown, the typical heartbeat model generation method in the electrocardiogram data analysis system includes the following steps:

[0137] Step S602: acquiring a first heart beat result set according to a first electrocardiogram analysis result.

[0138] Specifically, in an embodiment of the present invention, the first ECG analysis result may be an analysis result generated in a historical analysis process according to the first operation data and the original ECG data, or the first ECG analysis result may be an analysis result generated in a historical analysis process according to the first operation data, the second operation data and the original ECG data; wherein the first operation data and the second operation data have been described in the above embodiment. According to the historical ECG analysis results, the heartbeats in the historical ECG analysis results are obtained to obtain a first heartbeat result set.

[0139] Step S604: compare the first heartbeat result set with the second heartbeat result set in the current environment to obtain a difference set.

[0140] Specifically, the second heartbeat result set in the current environment is a heartbeat set generated in the current analysis process according to the second operation data, the confirmed and retained first operation data, and the original electrocardiogram data. The system determines the heartbeat set whose type has changed in the re-analysis process according to the second heartbeat result set and the first heartbeat result set in the current environment, and defines the heartbeat set whose type has changed as a difference set.

[0141] Step S606: Divide the difference set into different subsets according to different heart beat types.

[0142] Specifically, the existing heartbeat types include normal heartbeat (N-type heartbeat), left bundle branch block heartbeat (L-type heartbeat), right bundle branch block heartbeat (R-type heartbeat) and ventricular premature beat (V-type heartbeat), etc. Through the classification neural network model, the difference set is classified according to different heartbeat types and divided into subsets corresponding to different types.

[0143] It should be understood that the model structure of the classification neural network model includes but is not limited to deep neural network models (Deep Neural Networks, DNN), recurrent neural network models (Recurrent Neural Networks, RNN), convolutional network models (Convolutional Neural Networks, CNN), deep generative models (Deep Generative Models, DGM), generative adversarial networks (Generative Adversarial Networks, GAN), long / short term memory network models (Long / short term memory, LSTM), support vector machines (Support vector machines, SVM), deep cross model (Deep Crossing), etc.

[0144] Step S608: cluster each subset to obtain a typical heartbeat model.

[0145] Specifically, all the heartbeats in each subset are clustered according to the preset clustering rules, and the corresponding typical heartbeat model is obtained according to the clustering results of each subset. The clustering rules mentioned here include mean clustering, hierarchical clustering, etc., and the multiple heartbeats in each subset are quantitatively classified according to the preset clustering rules to obtain clustering results. Furthermore, the process of obtaining the clustering results includes extracting the characteristic parameters of the multiple heartbeats in each subset, and merging similar heartbeats according to the similarity of the characteristic parameters between the heartbeats, taking the first heartbeat from the merged heartbeat as the central heartbeat, and further merging the heartbeats according to the difference in the central heartbeat morphology, and the final merged heartbeat is the typical heartbeat model.

[0146] Step S610: output a typical heartbeat model.

[0147] Specifically, the typical heartbeat model obtained in step S608 is output.

[0148] Through the above steps S602 to S610, a typical heartbeat model is obtained by adopting the process of difference screening and clustering, which greatly improves the efficiency and speeds up the analysis running time.

[0149] Figure 7 FIG. 1 is a flow chart of a typical interference segment model generation method in an electrocardiogram data analysis system of the preferred embodiment of the present invention. Figure 7 As shown, the typical interference segment model generation method in the electrocardiogram data analysis system includes the following steps:

[0150] Step S702, dividing the original ECG data into a plurality of ECG data segments according to the set detection time, and performing ECG interference detection on the plurality of ECG data in sequence.

[0151] Specifically, interference detection is performed based on the original ECG data, and different levels are divided. The detection time can be in units of minutes, hours, etc. Preferably, in the embodiment of the present invention, the detection time is set to 1 minute.

[0152] Step S704, counting the proportion of noise signals in the current ECG data segment.

[0153] Step S706: setting the ECG data segment in which the noise signal proportion is greater than the first threshold as the first interference segment.

[0154] Specifically, it is determined whether the proportion of noise signals in the current ECG data segment is greater than a first threshold value. If so, the ECG data is set as a first interference segment. If not, the ECG data segment is set as a normal segment.

[0155] Step S708: Determine a second interference segment according to the preset first time threshold and the first interference segment.

[0156] Specifically, when the time interval between two adjacent first interference segments is less than or equal to the first time threshold, the two adjacent first interference segments and the ECG data segment between the two adjacent first interference segments are determined as the second interference segment. The first time threshold can be set to 2 minutes, 3 minutes, 5 minutes, etc. In an exemplary embodiment, if the time interval between two adjacent first interference segments is 2 minutes, and this time interval includes a 2-minute normal segment, the two adjacent first interference segments and the normal segment in the middle are determined as the second interference segment.

[0157] Step S710: filter the second interference segment to obtain a typical interference segment model.

[0158] Specifically, the filtering process includes wavelet transform, mean filtering, spline curve, smoothing filtering based on piecewise polynomial fitting, etc. Further, the second interference segment is smoothed and filtered to obtain filtered data, and a typical interference segment model is generated based on the filtered data.

[0159] Through the above steps S702 to S710, the signal noise is detected to identify the first interference segment, interference detection is performed based on the original ECG data, a first time threshold is set, and the first interference segment whose time interval between two adjacent first interference segments is within the first time threshold and the ECG data segment between the two adjacent first interference segments are taken as the second interference segment. The second interference segment is filtered to obtain a typical interference segment model, which can effectively improve the accuracy of the automatic analysis results, assist users to quickly complete the dynamic ECG analysis report, and improve the analysis efficiency.

[0160] Figure 8 FIG. 1 is a flow chart of another typical interference segment model generation method in an electrocardiogram data analysis system of the preferred embodiment. Figure 8 As shown, the typical interference segment model generation method in the electrocardiogram data analysis system includes the following steps:

[0161] Step S802, dividing the original ECG data into a plurality of ECG data segments according to the set detection time, and performing ECG interference detection on the plurality of ECG data in sequence.

[0162] Step S804, counting the percentage of electrocardiogram artifacts in multiple electrocardiogram data segments.

[0163] Specifically, the interference level in the ECG data of the set detection time period is analyzed, and the proportion of ECG artifacts in the period is counted. ECG artifacts refer to the appearance of some graphics similar to normal ECG in the ECG test results, such as ST segment elevation and T wave inversion on the ECG.

[0164] Step S806: The ECG data segment in which the proportion of the number of ECG artifacts is greater than the second threshold is set as a third interference segment.

[0165] Specifically, it is determined whether the proportion of electrocardiogram artifacts in the current electrocardiogram data segment is greater than a second threshold value. If so, the electrocardiogram data is set as a third interference segment. If not, the electrocardiogram data segment is set as a normal segment.

[0166] Step S808: Determine a fourth interference segment according to the preset second time threshold and the third interference segment.

[0167] Specifically, when the time interval between two adjacent third interference segments is less than or equal to the second time threshold, the two adjacent third interference segments and the ECG data segment between the two adjacent third interference segments are determined as the fourth interference segment. The second time threshold can be set to 2 minutes, 3 minutes, 5 minutes, etc. In an exemplary embodiment, if the time interval between two adjacent third interference segments is 2 minutes, and this time interval includes a 2-minute normal segment, the two adjacent third interference segments and the middle normal segment are determined as the fourth interference segment.

[0168] Step S810: filter the fourth interference segment to obtain a typical interference segment model.

[0169] Specifically, the filtering process includes wavelet transform, mean filtering, spline curve, smoothing filtering based on piecewise polynomial fitting, etc. Further, the fourth interference segment is smoothed and filtered to obtain filtered data, and a typical interference segment model is generated based on the filtered data.

[0170] Through steps S802 to S810, the number of ECG artifacts is detected to identify the third interference segment, interference detection is performed based on the original ECG data, a second time threshold is set, and the third interference segment whose time interval between two adjacent third interference segments is within the second threshold range and the ECG data segment between the two adjacent third interference segments are taken as the fourth interference segment. The fourth interference segment is filtered to obtain a typical interference segment model, which can effectively improve the accuracy of automatic analysis results, assist users to quickly complete dynamic ECG analysis reports, and improve analysis efficiency.

[0171] When reanalyzing again, the embodiment of the present invention will provide a typical interference segment model based on the historical editing results, and perform the analysis after confirmation by the user, thereby ensuring that the final analysis results have fewer misidentifications and artifacts, cleaner scatter plots and histograms, and higher editing efficiency.

[0172] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0173] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0174] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0175] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0176] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0177] S1, obtaining original ECG data, and generating a first ECG data analysis result according to the original ECG data and ECG analysis parameters.

[0178] S2, generating a second ECG data analysis result according to the first ECG data analysis result and the first target data; wherein the first target data includes a target typical heart beat model in the ECG data.

[0179] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0180] In addition, in combination with the ECG data analysis method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any ECG data analysis method in the above embodiments is implemented.

[0181] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0182] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0183] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0184] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. An electrocardiogram data analysis system, characterized in that: The ECG data analysis system comprises: an original ECG analysis module and an ECG re-analysis module; The original ECG analysis module is used to obtain original ECG data and generate a first ECG data analysis result according to the original ECG data and ECG analysis parameters; The ECG re-analysis module is used to generate a second ECG data analysis result based on the first ECG data analysis result and the first target data; wherein the first target data includes a target typical heart beat model in the ECG data.

2. The electrocardiogram data analysis system according to claim 1, characterized in that: The ECG data analysis system further includes: a parameter acquisition module; the parameter acquisition module is used to acquire the ECG analysis parameters 。 3. The electrocardiogram data analysis system according to claim 1, characterized in that: The ECG reanalysis module also includes: a heartbeat selection submodule; The heartbeat selection submodule is used to obtain the first target data after screening or modifying the second target data; wherein the second target data includes a typical heartbeat model.

4. The electrocardiogram data analysis system according to claim 1, characterized in that: The ECG re-analysis module is further used to generate the second ECG data analysis result based on the first ECG data analysis result, the first target data and third target data; the third target data includes a target interference segment model in the ECG data.

5. The electrocardiogram data analysis system according to claim 4, characterized in that: The ECG re-analysis module also includes: a target interference segment selection submodule; The target interference segment selection submodule is used to obtain the third target data after screening or modifying the fourth target data; The fourth target data includes a typical interference segment model.

6. The electrocardiogram data analysis system according to claim 4, characterized in that: The ECG data analysis system further includes: a first ECG data annotation module, which is used to annotate the first ECG data analysis result to obtain a first ECG data annotation result.

7. The electrocardiogram data analysis system according to claim 4, characterized in that: The ECG reanalysis module further includes a label selection submodule; The annotation selection submodule is used to screen or modify the first ECG data annotation result to generate a second ECG data annotation result.

8. The electrocardiogram data analysis system according to claim 7, characterized in that: The ECG re-analysis module is used to generate the second ECG data analysis result according to the first target data and the second ECG data annotation result; Alternatively, the ECG re-analysis module is used to generate the second ECG data analysis result according to the third target data and the second ECG data annotation result; Alternatively, the ECG re-analysis module is used to generate the second ECG data analysis result according to the first target data, the third target data and the second ECG data annotation result.

9. A method for analyzing electrocardiogram data, characterized in that: The electrocardiogram data analysis method comprises: Acquire original ECG data, and generate a first ECG data analysis result according to the original ECG data and ECG analysis parameters; A second electrocardiogram data analysis result is generated according to the first electrocardiogram data analysis result and the first target data; wherein the first target data includes a target typical heart beat model in the electrocardiogram data.

10. The electrocardiogram data analysis method according to claim 9, characterized in that: The electrocardiogram data analysis method further includes: obtaining the electrocardiogram analysis parameters 。 11. The electrocardiogram data analysis method according to claim 9, characterized in that: The first target data is obtained after screening or modification based on the second target data; the second target data includes a typical heartbeat model.

12. The electrocardiogram data analysis method according to claim 9, characterized in that: The electrocardiogram data analysis method further comprises: The ECG data analysis result is generated according to the original ECG data, the ECG analysis parameters, the first target data and the third target data; the third target data includes a target interference segment model in the ECG data.

13. The electrocardiogram data analysis method according to claim 12, characterized in that: The third target data is obtained after screening or modifying the fourth target data; The fourth target data includes a typical interference segment model.

14. The electrocardiogram data analysis method according to claim 12, characterized in that: The electrocardiogram data analysis method further comprises: The first electrocardiogram data analysis result is annotated to obtain a first electrocardiogram data annotating result.

15. The electrocardiogram data analysis method according to claim 14, characterized in that: The electrocardiogram data analysis method further comprises: The first ECG data labeling result is screened or modified to generate a second ECG data labeling result.

16. The electrocardiogram data analysis method according to claim 15, characterized in that: The electrocardiogram data analysis method further comprises: generating the second ECG data analysis result according to the first target data and the second ECG data annotation result; Alternatively, generating the second electrocardiogram data analysis result according to the third target data and the second electrocardiogram data annotation result; Alternatively, the second electrocardiogram data analysis result is generated according to the first target data, the third target data and the second electrocardiogram data annotation result.

17. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the electrocardiogram data analysis method according to any one of claims 9 to 16.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the electrocardiogram data analysis method according to any one of claims 9 to 16 are implemented.

Images