Method, program, and device for diagnosing heart disease on basis of electrocardiogram signal

The method and device improve heart disease diagnosis by using a user-customized neural network to re-evaluate electrocardiogram signals based on user-specific conditions, addressing accuracy issues in existing deep learning methods and providing real-time, reliable diagnostic results.

WO2024242484A1PCT designated stage expired Publication Date: 2024-11-28MEDICAL AI CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2024/006998
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-05-23
Filing Date
2024-05-23
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Current deep learning-based diagnostic methods for heart disease using electrocardiogram signals often face accuracy issues, particularly in determining the need for re-acquisition of signals based on user-specific conditions such as medication, activity, and health status, which can affect the reliability of the diagnosis.

Method used

A method and device that utilize a user-customized neural network model to analyze electrocardiogram signals, allowing for real-time diagnosis of heart disease by re-acquiring signals based on predefined conditions, such as medication status, activity, and health indicators, and providing iterative diagnostic results to improve accuracy.

Benefits of technology

Enables real-time, user-specific heart disease diagnosis without professional medical intervention, enhancing diagnostic accuracy by re-evaluating electrocardiogram signals in response to changing user conditions, thereby improving the reliability of the diagnostic process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2024006998_28112024_PF_FP_ABST
    Figure KR2024006998_28112024_PF_FP_ABST
Patent Text Reader

Abstract

Provided are a method, a program, and a device for diagnosing heart disease on the basis of an electrocardiogram signal. The method for diagnosing heart disease on the basis of an electrocardiogram signal according to an embodiment of the present disclosure comprises the steps of: acquiring an electrocardiogram signal for a user; and diagnosing heart disease in the user on the basis of the acquired electrocardiogram signal. The diagnosing step includes the steps of: inputting the acquired electrocardiogram signal to a trained neural network model and calculating a first score corresponding to heart disease in the user; re-acquiring an electrocardiogram signal for the user by determining, on the basis of the calculated first score, whether to additionally diagnose heart disease in the user; and additionally diagnosing heart disease in the user on the basis of the re-acquired electrocardiogram signal.
Need to check novelty before this filing date? Find Prior Art

Description

Method, program and device for diagnosing heart disease based on electrocardiogram signals

[0001] The present disclosure relates to deep learning technology in the medical field, and more specifically, to a method, program, and device for obtaining a user-customized neural network model that identifies biometric information.

[0002] With recent advancements in information and communication technology, deep learning is being utilized in various fields. In particular, deep learning is being utilized in various fields, particularly in the medical field, where diagnosis of a patient's condition relied on specialized and limited resources such as doctors and researchers. For example, biometric data acquired in real time from a patient is input into a pre-trained deep learning model to analyze the patient's condition or disease.

[0003] Meanwhile, myocardial infarction is the most common cause of sudden death, and the number of patients with myocardial infarction is increasing every year. Because early detection and treatment can prevent death and disability, extensive research is being conducted on the early diagnosis and prediction of myocardial infarction. In this regard, methods widely used for early diagnosis include measuring electrocardiograms, displaying the measured ECG signals in a graph format, and assessing the presence or absence of myocardial infarction in the patient's heart based on the graph.

[0004] Recently, it has become possible to measure a user's electrocardiogram (ECG) using portable electronic devices like smartwatches, without the need for specialized medical equipment. Various methods have been proposed to analyze a user's ECG without the need for a specialist, utilizing deep learning technology to diagnose and predict conditions like myocardial infarction. However, diagnostic methods utilizing deep learning often suffer from reduced accuracy depending on the user's condition.

[0005] The present disclosure has been made in response to the aforementioned background technology, and aims to provide a method, program, and device for diagnosing heart disease based on electrocardiogram signals.

[0006] However, the problems to be solved in this disclosure are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood based on the description below.

[0007] In order to achieve the above-described task, a method for diagnosing a heart disease based on an electrocardiogram signal, which is performed by a computing device including at least one processor according to an embodiment of the present disclosure, includes the steps of: acquiring an electrocardiogram signal for a user; and diagnosing a heart disease of the user based on the acquired electrocardiogram signal, wherein the diagnosing step includes the steps of: inputting the acquired electrocardiogram signal into a pre-trained neural network model to calculate a first score corresponding to the heart disease of the user; determining whether to additionally diagnose the heart disease of the user based on the calculated first score, thereby re-acquiring the electrocardiogram signal for the user; and further diagnosing the heart disease of the user based on the re-acquired electrocardiogram signal.

[0008] Alternatively, the step of re-acquiring the electrocardiogram signal for the user determines an additional diagnosis of the user's heart disease if the calculated first score is identified as being within a preset range.

[0009] Alternatively, the method comprises a step of obtaining status information of the user, and the step of re-acquiring an electrocardiogram signal for the user comprises a step of determining whether to re-acquire an electrocardiogram signal for the user based on the obtained status information when an additional diagnosis of a heart disease of the user is determined.

[0010] Alternatively, the status information includes medication information of the user, and the step of determining whether to re-acquire includes the step of acquiring the electrocardiogram signal in a state where the user has not taken the medication, based on the medication information of the user, and then determining to re-acquire the electrocardiogram signal if it is determined that the user has taken the medication.

[0011] Alternatively, the status information includes the user's medication information, and the step of determining whether to re-acquire includes a step of determining to re-acquire the electrocardiogram signal after a preset time has elapsed from the time the user took the medication, if the electrocardiogram signal is identified as having been acquired immediately after the user took the medication based on the user's medication information.

[0012] Alternatively, the status information includes disease information including at least one of palpitations, dyspnea, fatigue, and chest pain of the user, and the step of determining whether to re-acquire includes a step of determining to re-acquire the electrocardiogram signal if it is determined that the user has a disease based on the disease information of the user.

[0013] Alternatively, the status information includes activity information of the user, and the step of determining whether to re-acquire includes a step of determining to re-acquire the electrocardiogram signal if, based on the activity information, a preset time has elapsed since the user started the activity after waking up.

[0014] Alternatively, the status information includes the user's exercise information, and the step of determining whether to re-acquire includes the step of determining to re-acquire the electrocardiogram signal if, based on the exercise information, the user is identified as being in a preset exercise, has finished the preset exercise, or has been in a resting state for a preset time from the time of finishing the preset exercise.

[0015] Alternatively, the status information includes meal information of the user, and the step of determining whether to re-acquire includes a step of determining to re-acquire the electrocardiogram signal if, based on the meal information, it is determined that the user has just eaten or a preset amount of time has passed since the user finished eating.

[0016] Alternatively, the status information includes pulse rate information of the user, and the step of determining whether to re-acquire the electrocardiogram signal includes a step of determining whether to re-acquire the electrocardiogram signal based on the pulse rate.

[0017] Alternatively, the step of re-acquiring the electrocardiogram signal for the user comprises the step of repeatedly re-acquiring the electrocardiogram signal for the user when an additional diagnosis of a heart condition of the user is determined.

[0018] Alternatively, the step of further diagnosing the heart disease of the user comprises the step of repeatedly further diagnosing the heart disease of the user based on the re-acquired electrocardiogram signal each time the electrocardiogram signal for the user is re-acquired, thereby providing an additional diagnosis result.

[0019] Alternatively, the step of further diagnosing the user's heart disease includes the step of inputting the repeatedly re-acquired plurality of electrocardiogram signals into the pre-trained neural network model, respectively, to produce a plurality of second scores corresponding to the user's heart disease, and the step of further diagnosing the user's heart disease based on the plurality of second scores.

[0020] Alternatively, the step of further diagnosing the user's heart disease includes the steps of generating a first electrocardiogram signal as an average beat of the repeatedly re-acquired plurality of electrocardiogram signals, inputting the generated first electrocardiogram signal into the pre-trained neural network model to generate a second score corresponding to the user's heart disease, and further diagnosing the user's heart disease based on the second score.

[0021] Alternatively, the step of repeatedly re-acquiring includes a step of monitoring status information of the user, determining a re-acquisition time point of the electrocardiogram signal for the user based on the status information, and repeatedly re-acquiring the electrocardiogram signal for the user according to the determined re-acquisition time point.

[0022] Alternatively, the step of re-acquiring the electrocardiogram signal for the user includes, if the calculated first score is identified as being within a preset range, the step of analyzing the status information of the user to determine whether there is a factor affecting the calculated first score, and if the factor is identified as being present, the step of determining an additional diagnosis of the user's heart disease.

[0023] Alternatively, the step of re-acquiring the electrocardiogram signal for the user determines that the user's heart disease is diagnosed with the calculated first score if the calculated first score is identified as being outside a preset range.

[0024] Alternatively, the re-acquiring step comprises re-acquiring the electrocardiogram signal for the user at preset time intervals when an additional diagnosis of the user's heart condition is determined.

[0025] Alternatively, the step of re-acquiring the electrocardiogram signal for the user at the preset time cycle includes, if the user is identified as having undergone surgery within the preset time, changing the preset cycle from a first cycle to a second cycle shorter than the first cycle, and re-acquiring the electrocardiogram signal for the user at the second cycle.

[0026] According to an embodiment of the present disclosure for realizing the task as described above, a computer program stored in a computer-readable storage medium, wherein the computer program, when executed on at least one processor, performs an operation of obtaining a user-customized neural network model for identifying bio-information, the operation including an operation of obtaining an electrocardiogram signal for a user and an operation of diagnosing a heart disease of the user based on the obtained electrocardiogram signal, wherein the diagnosing operation includes an operation of inputting the obtained electrocardiogram signal into a pre-trained neural network model to calculate a first score corresponding to the heart disease of the user, an operation of re-acquiring an electrocardiogram signal for the user by determining whether to additionally diagnose the heart disease of the user based on the calculated first score, and an operation of additionally diagnosing the heart disease of the user based on the re-acquired electrocardiogram signal.

[0027] A computing device for obtaining a user-customized neural network model for identifying bio-information according to an embodiment of the present disclosure for realizing the task as described above, comprising: a memory including program codes; a sensing unit for obtaining an electrocardiogram signal of a user; and at least one processor for obtaining an electrocardiogram signal for the user through the sensing unit and diagnosing a heart disease of the user based on the obtained electrocardiogram signal, wherein the processor inputs the obtained electrocardiogram signal into a pre-trained neural network model to calculate a first score corresponding to the heart disease of the user, and determines whether to additionally diagnose the heart disease of the user based on the calculated first score, thereby re-acquiring the electrocardiogram signal for the user, and further diagnosing the heart disease of the user based on the re-acquired electrocardiogram signal.

[0028] A method for diagnosing a heart disease based on an electrocardiogram signal according to one embodiment of the present disclosure allows a user to determine the status of a heart disease in real time without the assistance of a specialized medical institution or expert.

[0029] FIG. 1 is an exemplary diagram illustrating a method for predicting heart disease based on a user's electrocardiogram signal according to one embodiment of the present disclosure.

[0030] FIG. 2 is a schematic block diagram of a computing device according to one embodiment of the present disclosure.

[0031] FIG. 3 is a flowchart schematically illustrating a method for diagnosing a user's heart disease based on an electrocardiogram signal according to one embodiment of the present disclosure.

[0032] FIG. 4 is a flowchart schematically illustrating a method for repeatedly diagnosing a user's heart disease based on an electrocardiogram signal according to one embodiment of the present disclosure.

[0033] FIG. 5 is a flowchart schematically illustrating a method for repeatedly diagnosing a user's heart disease based on the user's status information according to one embodiment of the present disclosure.

[0034] FIG. 6 is a block diagram of a computing device according to another embodiment of the present disclosure.

[0035] Below, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. The embodiments presented in this disclosure are provided to enable those skilled in the art to utilize or implement the contents of the present disclosure. Accordingly, various modifications to the embodiments of the present disclosure will be apparent to those skilled in the art. That is, the present disclosure may be implemented in various different forms and is not limited to the embodiments described below.

[0036] Throughout the specification of this disclosure, identical or similar drawing numbers refer to identical or similar components. Furthermore, for the purpose of clearly describing the disclosure, drawing numbers for parts in the drawings that are not relevant to the description of the disclosure may be omitted.

[0037] The term "or" as used herein is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified herein or clear from context, "X employs A or B" should be understood to mean either of the natural inclusive permutations. For example, unless otherwise specified herein or clear from context, "X employs A or B" can be interpreted to mean either X employs A, X employs B, or X employs both A and B.

[0038] The term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the related concepts listed.

[0039] The terms "comprises" and / or "comprising" as used herein should be understood to mean the presence of certain features and / or components. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, other components, and / or combinations thereof.

[0040] Unless otherwise specified in this disclosure or unless the context makes it clear that the singular form is intended to be referred to, the singular should generally be construed to include “one or more.”

[0041] The term "Nth (N is a natural number)" used in this disclosure can be understood as an expression used to mutually distinguish components of this disclosure based on a predetermined standard such as a functional perspective, a structural perspective, or convenience of explanation. For example, components performing different functional roles in this disclosure can be distinguished as a first component or a second component. However, components that are substantially the same within the technical spirit of this disclosure but must be distinguished for convenience of explanation may also be distinguished as a first component or a second component.

[0042] The term "acquisition" as used in this disclosure may be understood to mean not only receiving data through a wired or wireless communication interface with an external device or system, but also generating data in an on-device form.

[0043] Meanwhile, the term "module" or "unit" used in the present disclosure can be understood as a term referring to an independent functional unit that processes computing resources, such as a computer-related entity, firmware, software or a part thereof, hardware or a part thereof, or a combination of software and hardware. At this time, the "module" or "unit" may be a unit composed of a single element, or a unit expressed as a combination or set of multiple elements. For example, as a narrow concept, a "module" or "unit" may refer to a hardware element of a computing device or a set thereof, an application program that performs a specific function of software, a processing process implemented through software execution, or a set of instructions for program execution, etc. In addition, as a broad concept, a "module" or "unit" may refer to the computing device itself that constitutes the system, or an application running on the computing device, etc. However, since the above-described concept is only an example, the concept of “module” or “part” may be defined in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0044] The term "model" as used herein may be understood as a system implemented using mathematical concepts and language to solve a specific problem, a set of software units to solve a specific problem, or an abstract model of a processing process to solve a specific problem. For example, a neural network "model" may refer to the entire system implemented as a neural network that has problem-solving capabilities through learning. In this case, the neural network can have problem-solving capabilities by optimizing the parameters connecting nodes or neurons through learning. A neural network "model" may include a single neural network or a set of neural networks that are a combination of multiple neural networks.

[0045] The term "data" used in this disclosure may include "images," signals, and the like. The term "image" used in this disclosure may refer to multidimensional data composed of discrete image elements. In other words, "image" may be understood as a term referring to a digital representation of an object visible to the human eye. For example, "image" may refer to multidimensional data composed of elements corresponding to pixels in a two-dimensional image. "Image" may refer to multidimensional data composed of elements corresponding to voxels in a three-dimensional image.

[0046] The explanation of the above terms is intended to aid understanding of the present disclosure. Therefore, unless explicitly stated as limiting the contents of the present disclosure, it should be noted that the above terms are not intended to limit the technical ideas of the contents of the present disclosure.

[0047] FIG. 1 is an exemplary diagram illustrating a method for predicting heart disease based on a user's electrocardiogram signal according to one embodiment of the present disclosure.

[0048] A computing device (100) according to an embodiment of the present disclosure may be a hardware device or a part of a hardware device that performs comprehensive processing and calculation of data, or may be a software-based computing environment connected to a communication interface. For example, the computing device (100) may be a server that performs intensive data processing functions and shares resources, or may be a client that shares resources through interaction with a server. In addition, the computing device (100) may be a cloud system in which multiple servers and clients interact to comprehensively process data. Since the above description is only one example related to the type of computing device (100), the type of computing device (100) may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0049] Referring to FIG. 1, a computing device (100) according to an embodiment of the present disclosure may be implemented as a smartwatch. However, the present disclosure is not limited thereto, and the computing device (100) may be implemented as various electronic devices, such as a desktop, laptop, smartphone, server device, smart band, or smart ring. In the following description, for the sake of understanding of the present disclosure, the computing device (100) will be described as a smartwatch.

[0050] According to one embodiment of the present disclosure, a computing device (100) can obtain an electrocardiogram signal of a user (1). Specifically, the computing device (100) can detect an electrical signal generated from the heart of the user (1) to obtain an electrocardiogram signal. Meanwhile, in addition to the electrocardiogram signal, the computing device (100) can obtain various bio-signals from the user (1). For example, the computing device (100) can obtain various bio-information such as pulse, body temperature, blood pressure, and blood flow of the user (1) by using various sensors.

[0051] According to one embodiment of the present disclosure, a pre-trained neural network model (10) may be stored in a computing device (100). The neural network model (10) may be a model (10) trained to predict a potential heart disease of a user (1) based on an electrocardiogram signal of the user (1). The neural network model (10) may be trained in advance to predict heart disease based on an electrocardiogram signal input as learning data, which includes a plurality of electrocardiogram signals and heart disease information (e.g., presence or absence of heart disease, degree of heart disease, etc.) matching each of the electrocardiogram signals. At this time, the plurality of electrocardiogram signals included in the learning data may each include feature information associated with heart disease (e.g., feature points indicated on the electrocardiogram signal, etc.). Through this, when an electrocardiogram signal is input, the neural network model (10) may be trained to extract feature information corresponding to a heart disease from the electrocardiogram signal and to predict the possibility of the presence of a heart disease based on the extracted feature information. The neural network model (10) can be pre-trained to score the likelihood of heart disease. Heart disease can include various diseases and symptoms manifested in the heart, such as heart failure.

[0052] In addition, the pre-learned neural network model (10) may include a plurality of neural network models (10) learned to predict a potential disease of a user (1) based on various bio-information obtainable from a computing device (100) as well as an electrocardiogram signal. In this case, each neural network model (10) may be learned in advance as learning data disease information (e.g., disease presence / absence information, etc.) to be predicted or identified based on bio-information and bio-information matching the bio-information.

[0053] The neural network model (10) can be implemented as a multi-layer perceptron (MLP), a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network, etc. In particular, the neural network model (10) can include a plurality of residual blocks that extract latent features of an input electrocardiogram signal and a classifier that classifies heart disease based on the extracted latent features.

[0054] Meanwhile, referring to FIG. 1, the computing device (100) can repeatedly acquire the electrocardiogram signal of the user (1) to predict the heart disease in order to increase the accuracy of predicting the heart disease of the user (1) based on the electrocardiogram signal. More specifically, when the computing device (100) predicts the heart disease of the user (1) after acquiring the electrocardiogram signal at time t1 at the request of the user (1) (or according to preset conditions), the computing device (100) can re-acquire the electrocardiogram signal at time t2 and then predict the heart disease of the user (1) again. At this time, the computing device (100) can perform the re-acquisition of the electrocardiogram signal at time t2 and the prediction of the heart disease without a request from the user (1). In addition, the computing device (100) can additionally diagnose the heart disease of the user (1) based on the prediction result for the heart disease of the user (1) at time t2.

[0055] In particular, if the computing device (100) determines that there is a risk of inaccuracy in the prediction result of a heart disease based on an electrocardiogram signal, the computing device (100) can re-acquire the electrocardiogram signal and re-predict the heart disease of the user (1) based on the re-acquired electrocardiogram signal. Here, the risk of inaccuracy in the prediction result of a heart disease based on a conduction signal may mean that the prediction result is ambiguous or not highly accurate.

[0056] At this time, the computing device (100) can repeatedly perform additional diagnosis. Specifically, the computing device (100) can repeatedly re-acquire the electrocardiogram signal, and each time the electrocardiogram signal is re-acquired, the computing device (100) can repeatedly additionally diagnose a heart disease of the user (1) based on the re-acquired electrocardiogram signal. In addition, the computing device (100) can provide the diagnosis result to the user (1) each time the additional diagnosis is repeatedly performed.

[0057] Hereinafter, an embodiment of the present disclosure will be described in detail with reference to FIGS. 2 to 6.

[0058] FIG. 2 is a schematic block diagram of a computing device (100) according to one embodiment of the present disclosure.

[0059] Referring to FIG. 2, a computing device (100) according to an embodiment of the present disclosure may include one or more processors (hereinafter, “processors”) (110), a memory (120), and a sensing unit (130). However, FIG. 1 is only an example, and thus the computing device (100) may further include other components for implementing a computing environment. In addition, only some of the disclosed components may be included in the computing device (100).

[0060] A processor (110) according to an embodiment of the present disclosure may be understood as a configuration unit including hardware and / or software for performing computing operations. For example, the processor (110) may read a computer program to perform data processing for machine learning. The processor (110) may process computational processes such as processing input data for machine learning, feature extraction for machine learning, and error calculation based on backpropagation. The processor (110) for performing such data processing may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA). The above-described type of processor (110) is only one example, and thus, the type of processor (110) may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0061] The processor (110) is electrically connected to other components of the computing device (100) (i.e., memory (120), communication interface (240), and sensing unit (130)) and controls the overall operation of the computing device (100).

[0062] The memory (120) according to one embodiment of the present disclosure may be understood as a configuration unit including hardware and / or software for storing and managing data processed in the computing device (100). That is, the memory (120) may store any type of data generated or determined by the processor (110) and any type of data received by the communication interface. For example, the memory (120) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory, a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory (120) may also include a database system that controls and manages data in a predetermined system. The type of memory (120) described above is only one example, and thus the type of memory (120) can be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0063] The memory (120) can structure and organize and manage data, combinations of data, and program codes executable by the processor (110) required for the processor (110) to perform operations. For example, the memory (120) can store a neural network model (10) trained to predict heart disease based on an electrocardiogram signal. In addition, the memory (120) can include program codes and learning data (e.g., a plurality of electrocardiogram signals and a plurality of heart disease information matching each of the electrocardiogram signals) that operate to perform learning on the acquired neural network model (10). In addition, the memory (120) can store program codes that operate the neural network model (10) to receive an electrocardiogram signal and perform inference according to the purpose of use of the computing device (100), and processed data generated as the program codes are executed.

[0064] The sensing unit (130) can obtain an electrocardiogram signal for the user (1). For example, the sensing unit (130) can include at least one electrode. At this time, the processor (110) can obtain an electrocardiogram signal of the user (1) through the at least one electrode. In addition, the sensing unit (130) can include an image sensor or an optical sensor. At this time, the processor (110) can obtain bio-information such as an optical blood flow signal through the image sensor (or optical sensor).

[0065] FIG. 3 is a flowchart schematically illustrating a method for diagnosing a heart disease of a user (1) based on an electrocardiogram signal according to one embodiment of the present disclosure.

[0066] Referring to FIG. 3, according to one embodiment of the present disclosure, the processor (110) acquires an electrocardiogram signal for a user (1) (S310). In this case, step S310 may be referred to as an initial acquisition step of the electrocardiogram signal, as it is distinct from the re-acquisition step of the electrocardiogram signal.

[0067] Specifically, the processor (110) may be requested to diagnose a heart disease from the user (1) through the interface or communication interface of the computing device (100). At this time, when the processor (110) is requested to diagnose a heart disease from the user (1), the processor (110) may obtain an electrocardiogram signal for the user (1). Alternatively, the processor (110) may obtain an electrocardiogram signal according to preset conditions (e.g., time, cycle, etc.). However, the present invention is not limited thereto, and the processor (110) may continuously obtain an electrocardiogram signal while the user (1) wears the computing device (100).

[0068] The processor (110) can detect an electrical signal generated from the heart of the user (1) through the sensing unit (130) and obtain an electrocardiogram signal.

[0069] And, the processor (110) diagnoses a heart disease of the user (1) based on the acquired electrocardiogram signal (S320).

[0070] Specifically, when an electrocardiogram signal is acquired, the processor (110) can identify whether the user (1) has a heart disease based on the acquired electrocardiogram signal. Alternatively, the processor (110) can predict a heart disease of the user (1) based on the acquired electrocardiogram signal. That is, the processor (110) can determine whether the user (1) has a potential heart disease that is not currently present but may be present in the future based on the electrocardiogram signal. In particular, the processor (110) can extract potential characteristic information of a heart disease from the electrocardiogram signal and predict a heart disease.

[0071] To this end, the processor (110) may utilize a pre-learned neural network model (10). Here, the pre-learned neural network model (10) may be a model (10) learned to identify the presence or absence of a heart disease in a user (1) or to predict a heart disease in the user (1) based on an electrocardiogram signal. Since the description of the invention described in FIG. 1 applies equally to the pre-learned neural network model (10), a detailed description thereof will be omitted.

[0072] Meanwhile, the processor (110) can input an electrocardiogram signal into a pre-trained neural network model (10) to obtain a score corresponding to a heart disease. That is, the pre-trained neural network model (10) can be trained to produce a score corresponding to a predicted heart disease based on the input electrocardiogram signal. For example, the pre-trained neural network model (10) can be trained to produce a higher score as the likelihood of heart disease increases.

[0073] The processor (110) can obtain a score from the pre-trained model (10) and diagnose a heart disease of the user (1) based on the obtained score. Specifically, if the obtained score is higher than a preset value, the processor (110) can diagnose that the user (1) has a high possibility of heart disease. For example, if the preset value is 10 and the heart disease is heart failure, the processor (110) can diagnose that the user has a high possibility of heart failure if the score obtained from the pre-trained neural network model (10) is 10 or higher.

[0074] Meanwhile, the processor (110) may output the diagnosis result. For example, the processor (110) may output the diagnosis result through the display or output interface of the computing device (100). In addition, the processor (110) may also output user (1) guidance information according to the diagnosis result. To explain again with the above-described example, if the processor (110) identifies that the user (1) has a high possibility of heart failure based on the electrocardiogram signal of the user (1), the processor (110) may output information notifying the user (1) of the risk of heart failure and information on nearby hospitals based on the user's (1's) location information through the display.

[0075] FIG. 4 is a flowchart schematically illustrating a method for repeatedly diagnosing a heart disease of a user (1) based on an electrocardiogram signal according to an embodiment of the present disclosure. S410 illustrated in FIG. 4 may correspond to S310 illustrated in FIG. 3.

[0076] Meanwhile, according to one embodiment of the present disclosure, the processor (110) can re-acquire an electrocardiogram signal to increase the accuracy of the results of a heart disease diagnosis, and re-diagnose the heart disease based on the re-acquired electrocardiogram signal. To this end, the processor (110) can first determine whether the results of the heart disease diagnosis are likely to be inaccurate. That is, the processor (110) can determine whether the heart disease diagnosis is likely to be inaccurate and determine whether to diagnose the heart disease based on the acquired electrocardiogram. In addition, if the processor (110) determines that the results of the heart disease diagnosis are likely to be inaccurate, the processor (110) can re-acquire the electrocardiogram signal and re-diagnose the heart disease.

[0077] Referring to FIG. 4, the processor (110) inputs the acquired electrocardiogram signal into a pre-trained neural network model (10) to calculate a score corresponding to the heart disease of the user (1) (S420). Hereinafter, for the convenience of explaining the invention, the score initially calculated based on the electrocardiogram signal is referred to as the first score.

[0078] In addition, the processor (110) can re-acquire the electrocardiogram signal for the user (1) by determining whether to additionally diagnose the user's (1) heart disease based on the calculated first score (S430). If an additional diagnosis of the user's (1) heart disease is determined, the processor (110) can repeatedly re-acquire the electrocardiogram signal for the user (1).

[0079] According to one embodiment of the present disclosure, if the processor (110) determines that the calculated first score is within a preset range, the processor (110) may determine an additional diagnosis of the user's (1) heart disease. On the other hand, if the processor (110) determines that the calculated first score is outside the preset range, the processor (110) may determine to diagnose the user's (1) heart disease with the calculated first score.

[0080] For example, when the preset range is 9.5 to 10.5, the processor (110) can determine an additional diagnosis for heart disease of the user (1) if the first score is identified as 10. That is, the processor (110) can determine an additional diagnosis for heart disease based on the first score (10) by determining that there is a possibility that the diagnosis result based on the first score (10) is inaccurate.

[0081] In addition, for example, when the preset range is 9.5 to 10.5, the processor (110) may determine not to perform additional diagnosis on the user (1) if the first score is identified as 12. That is, the processor (110) may determine that the diagnosis result based on the first score (12) is accurate and may determine to diagnose heart disease based on the first score (12). At this time, the processor (110) may provide the user (1) with guide information corresponding to the diagnosis result along with the diagnosis result of the heart disease.

[0082] Meanwhile, the preset range can be set based on the biological characteristics (age, weight, gender, etc.) of the user (1).

[0083] According to one embodiment of the present disclosure, if the processor (110) identifies that the calculated first score is within a preset range, it analyzes the status information of the user (1) to determine whether there is a factor affecting the calculated first score, and if it is determined that there is a factor, it may determine an additional diagnosis for the heart disease of the user (1).

[0084] Specifically, if the processor (110) determines that the first score produced is within a preset range, the processor (110) may determine that the diagnosis result for heart disease based on the first score is likely to be inaccurate, and analyze factors contributing to the inaccuracy of the diagnosis result. To this end, the processor (110) may utilize the user's (1) status information.

[0085] The processor (110) can obtain status information of the user (1). The status information of the user (1) is information indicating the status of the user (1), and may be information indicating the exercise status of the user (1) or the eating status of the user (1). In addition, the status information of the user (1) may further include biometric information (blood pressure, pulse, body temperature, blood flow, etc.) other than the electrocardiogram signal of the user (1).

[0086] If the calculated first score is identified as being within a preset range, the processor (110) can analyze the acquired status information of the user (1) to determine the status of the user (1). In addition, it can be determined whether there is a factor affecting the calculated first score based on the status of the user (1). For example, when an electrocardiogram signal is acquired, if it is determined that the user (1) is in an exercise state, the processor (110) can determine that the electrocardiogram of the user (1) is affected by an increase in blood flow and body temperature due to the exercise of the user (1). That is, the processor (110) can determine that the increase in blood flow and body temperature due to the exercise state of the user (1) affects the first score calculated based on the electrocardiogram signal.

[0087] If it is determined that a factor affecting the first score exists, the processor (110) may determine to perform an additional diagnosis in addition to the diagnosis of heart disease using the first score. In particular, if it is determined that a factor affecting the first score continues to exist based on the status information of the user (1) (or if it is determined that the user (1) status in which the factor affecting the first score occurs continues), the processor (110) may determine to perform an additional diagnosis.

[0088] In addition, if the processor (110) identifies that the electrocardiogram signal has a lot of noise, the processor (110) may determine an additional diagnosis of a heart disease for the user (1) based on the electrocardiogram signal. Specifically, if the first score is outside a preset range and the noise included in the electrocardiogram signal is identified as being greater than a preset value, the processor (110) may determine to diagnose a heart disease for the user (1) based on the first score, and then proceed with an additional diagnosis based on the re-acquired electrocardiogram signal.

[0089] In addition, the processor (110) may compare the diagnosis result of heart disease based on other biometric information about the user (1) with the diagnosis result of heart disease based on the electrocardiogram signal, and may determine to additionally perform a diagnosis of heart disease based on the electrocardiogram signal. That is, the processor (110) may compare the diagnosis result of heart disease based on the first score with the diagnosis result of heart disease obtained based on other biometric information of the user (1) (e.g., brain conduction signal, etc.) if the first score is identified as being outside a preset range. At this time, if the diagnosis results (i.e., the diagnosis result based on the electrocardiogram signal and the diagnosis result based on the other biometric information) are identified as different, the processor (110) may determine to re-acquire the electrocardiogram signal to additionally perform a diagnosis of heart disease.

[0090] When an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) can re-acquire an electrocardiogram signal for the user (1). Specifically, when an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) can re-acquire an electrocardiogram signal for the user (1) using the sensing unit (130). In particular, when an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) can re-acquire an electrocardiogram signal for the user (1) regardless of a request from the user (1) or preset conditions.

[0091] Additionally, when an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) may output a message through a display or output interface indicating that the diagnosis result of the heart disease may be inaccurate and requesting that the diagnosis request for the heart disease be requested again after a preset period of time.

[0092] FIG. 5 is a flowchart schematically illustrating a method for repeatedly diagnosing a heart disease of a user (1) based on the user's (1) status information according to one embodiment of the present disclosure. S510, S520, and S570 illustrated in FIG. 5 may correspond to S410, S420, and S440 illustrated in FIG. 4.

[0093] Referring to FIG. 5, according to one embodiment of the present disclosure, the processor (110) can acquire status information of a user (1) (S530). The status information of the user (1) can be acquired in real time through the sensing unit (130). However, the present invention is not limited thereto, and the status information of the user (1) can also be acquired by inputting it through a communication interface or input interface of the computing device (100).

[0094] The processor (110) compares the first score with a preset range, and if an additional diagnosis of the user's (1) heart disease is determined, the processor (110) can determine whether to re-acquire the electrocardiogram signal for the user (1) based on the status information acquired at the time the electrocardiogram signal was acquired (S550). The status information of the user (1) is information indicating the status of the user (1), and may be information indicating the user's (1) exercise status or the user's (1) eating status, etc. In addition, the status information of the user (1) may further include biometric information (blood pressure, pulse, body temperature, blood flow, etc.) other than the user's (1) electrocardiogram signal.

[0095] In particular, the processor (110) monitors the status information of the user (1), and if it is determined that there is no factor identified as having influenced the first score, it can determine to re-acquire the electrocardiogram signal for the user (1). That is, based on the status information, the processor (110) can determine the timing of re-acquisition of the electrocardiogram signal to produce a more accurate score.

[0096] According to one embodiment of the present disclosure, the status information may include medication information of the user (1). Here, the medication information may be received from a smart medicine bottle or may be identified based on a medication time set in the computing device (100). In this case, if the processor (110) identifies that the user (1) has taken medication based on the medication information of the user (1), it may determine to re-acquire the electrocardiogram signal.

[0097] Specifically, the processor (110) may determine, based on the medication information, that whether or not the user (1) is taking the medication affects the electrocardiogram signal and that the first score is calculated inaccurately. Accordingly, if the processor (110) identifies that the user (1) has taken the medication based on the medication information, the processor (110) may determine to re-acquire the electrocardiogram signal for the user (1). For example, if the processor (110) identifies that the electrocardiogram signal for the user (1) was acquired before the user took the medication and that the user has taken the medication thereafter, the processor (110) may determine to re-acquire the electrocardiogram signal based on the medication information. At this time, the processor (110) may compare the time at which the user (1) took the medication and the time at which the electrocardiogram signal for the user (1) was acquired based on the medication information.

[0098] In addition, if the processor (110) identifies, based on the medication information of the user (1), that the ECG signal was acquired immediately after the user took the medication, it may determine to re-acquire the ECG signal after a preset time has elapsed from the time the user took the medication. Specifically, the processor (110) may identify, based on the medication information of the user (1), the time at which the user (1) took the medication. At this time, if the processor (110) identifies, based on the medication information, that the time at which the ECG signal for the user (1) was acquired is within a preset first time (e.g., 2 seconds) from the time at which the user (1) took the medication (i.e., if the ECG signal was acquired immediately after the user (1) took the medication), it may determine to re-acquire the ECG signal for the user (1) after a preset second time (e.g., 10 minutes) has elapsed.

[0099] According to one embodiment of the present disclosure, the status information may include pulse rate information of the user (1). Here, the pulse rate information may be acquired based on a PPG (Photoplethysmogram) sensor included in the sensing unit (130) of the computing device (100). In addition, the processor (110) may determine to re-acquire the electrocardiogram signal based on the pulse rate. Specifically, the processor (110) may determine that the electrocardiogram signal may be acquired differently depending on the pulse rate of the user (1) based on the medication information, and that the first score is inaccurately calculated based on the pulse rate. Accordingly, the processor (110) may determine whether to re-acquire the electrocardiogram signal based on the pulse rate information. For example, if the processor (110) determines that the electrocardiogram signal was acquired in a state where the pulse rate of the user (1) was unstable and that the pulse rate of the user (1) has stabilized thereafter, the processor (110) may determine to re-acquire the electrocardiogram signal for the user (1). Alternatively, the processor (110) may determine to re-acquire the electrocardiogram signal for the user (1) based on the pulse rate information of the user (1) if the pulse rate of the user (1) changes rapidly or becomes irregular.

[0100] According to one embodiment of the present disclosure, the status information may include disease information of the user (1). Here, the disease information may include at least one of palpitations, shortness of breath, fatigue, and chest pain of the user (1). However, the present invention is not limited thereto, and various diseases may be included in the status information. In this case, if the processor (110) identifies that the user (1) has developed a disease, based on the disease information of the user (1), it may determine to re-acquire the electrocardiogram signal. Here, the disease information may be input by the user (1) through the user interface of the computing device (100), or may be acquired by identifying the occurrence of the disease using pulse rate, etc.

[0101] According to one embodiment of the present disclosure, the status information may include activity information of the user (1). The activity information may include movement information of the user (1), and thus, information on whether the user (1) is sleeping, waking up, and active after waking up. At this time, if the processor (110) determines that a preset third period of time (e.g., 30 minutes) has passed from the time the user started activity after waking up based on the activity information, the processor (110) may determine to re-acquire the electrocardiogram signal. Specifically, if the processor (110) determines that a preset third period of time has passed since the user (1) woke up and started activity based on the activity information, the processor (110) may determine to re-acquire the electrocardiogram signal for the user (1). In particular, if the electrocardiogram signal of the user (1) is determined to have been acquired while the user (1) was sleeping based on the activity information, the processor (110) may determine to re-acquire the electrocardiogram signal after the user (1) woke up. Meanwhile, activity information may be acquired by detecting the movement of the user (1) by the sensing unit (130), or may be input by the user (1) through the user interface of the computing device (100).

[0102] According to one embodiment of the present disclosure, the status information may include exercise information of the user (1). Here, the exercise information includes information on the type of exercise performed by the user (1) and whether the exercise is in progress. If the processor (110) determines that the user is in the middle of a preset exercise, has finished the preset exercise, or has been in a resting state for a preset fourth period of time (e.g., 30 minutes) from the time of finishing the preset exercise based on the exercise information, the processor (110) may determine to re-acquire the electrocardiogram signal. Here, the preset exercise is classified as vigorous exercise. For example, the preset exercise includes running, mountain climbing, stair climbing, etc. Meanwhile, the exercise information may be acquired by analyzing the movement of the user (1) detected by the sensing unit (130), or information on the type of exercise and the progress of the exercise may be input by the user (1) through the user interface of the computing device (100).

[0103] According to one embodiment of the present disclosure, the status information may include meal information of the user (1). Here, the meal information may include information on whether the user (1) has eaten and the type of food. At this time, if the processor (110) determines that the user has just finished eating or a preset amount of time has elapsed since the user finished eating based on the meal information, the processor (110) may determine to re-acquire the electrocardiogram signal. If it is within a preset fifth amount of time (e.g., 5 minutes) from the time the user finished eating, the processor (110) may determine that the user has just finished eating. Meanwhile, the meal information may be acquired based on an image acquired through a camera of the computing device (100), or may be input by the user (1) through a user interface.

[0104] Meanwhile, according to one embodiment of the present disclosure, if an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) may re-acquire an electrocardiogram signal for the user at a preset time cycle. For example, if an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) may re-acquire an electrocardiogram signal every day. That is, if an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) may re-acquire an electrocardiogram signal once a day. However, the present invention is not limited thereto, and the preset time cycle may be variously set to 5 minutes, 1 week, or 1 month.

[0105] At this time, the processor (110) can change the cycle according to the status of the user (1). In particular, if the processor (110) identifies that the user has undergone surgery within a preset 6th hour, the processor (110) can change the preset cycle to a shorter time. Here, whether the user (1) has undergone surgery can be obtained as status information of the user (1), which can be obtained through a communication interface of the computing device (100) or input by the user (1) through a user interface. For example, the processor (110) can acquire status information of the user (1) while re-acquiring the electrocardiogram signal once a day as an additional diagnosis of the user's (1) heart disease is determined. At this time, if the processor (110) identifies that the user has undergone surgery within a week (the preset 6th hour) based on the acquired status information, the processor (110) can change the re-acquisition cycle from 1 day to a shorter 6 hours, and re-acquire the electrocardiogram signal for the user every 6 hours. Referring to FIG. 5, if it is determined to re-acquire the electrocardiogram signal for the user based on the status information, the processor (110) can re-acquire the electrocardiogram signal for the user through the sensing unit (130) (S560).

[0106] Referring again to FIG. 4, the processor (110) can further diagnose a heart disease of the user (1) based on the re-acquired electrocardiogram signal (S440).

[0107] Specifically, the processor (110) can input the re-acquired electrocardiogram signal into the pre-trained neural network model (10) to re-acquire a score corresponding to a heart disease. Hereinafter, for the convenience of describing the invention, the score re-calculated based on the re-acquired electrocardiogram signal is referred to as a second score. The processor (110) can re-diagnose the heart disease of the user (1) based on the second score.

[0108] At this time, if the second score is within a preset range, the processor (110) diagnoses the user's (1) heart disease based on the second score, then obtains the electrocardiogram signal again to calculate a score (i.e., a third score), and can further diagnose the user's (1) heart disease based on the third score.

[0109] Meanwhile, according to one embodiment of the present disclosure, if an additional diagnosis of a heart disease of the user (1) is determined, the processor (110) may repeatedly re-acquire the electrocardiogram signal for the user (1). That is, the processor (110) may re-acquire the electrocardiogram signal of the user (1) multiple times, and perform an additional diagnosis of the heart disease of the user (1) each time the electrocardiogram signal is re-acquired, thereby providing an additional diagnosis result. That is, the additional diagnosis result may be repeatedly provided.

[0110] In particular, the processor (110) can acquire user status information, monitor the user status information, and determine a re-acquisition time point of the electrocardiogram signal for the user based on the status information. In addition, the processor (110) can repeatedly re-acquire the electrocardiogram signal for the user according to the determined re-acquisition time point. The processor (110) can input a plurality of repeatedly re-acquired electrocardiogram signals into a pre-trained neural network model (10), calculate a plurality of second scores corresponding to the heart disease of the user (1), and further diagnose the heart disease of the user (1) based on the plurality of second scores. As an example, the processor (110) can calculate a third score based on an average value, a median value, or a most frequent value of the plurality of second scores, and further diagnose the heart disease of the user (1) with the calculated third score.

[0111] Meanwhile, according to one embodiment of the present disclosure, when an additional diagnosis of a heart disease of a user (1) is determined, the processor (110) may repeatedly re-acquire an electrocardiogram signal for the user (1) and then generate a new electrocardiogram signal (first electrocardiogram signal) with an average beat of the repeatedly re-acquired multiple electrocardiogram signals. That is, the processor (110) may identify the beats of the multiple electrocardiogram signals and generate a first electrocardiogram signal having an average beat of the multiple electrocardiogram signals. Here, the first electrocardiogram signal is different from an electrocardiogram signal directly measured from the user (1) in that it is generated by the processor (110). In addition, the processor (110) may input the generated first electrocardiogram signal into a pre-trained neural network model (10), calculate a second score corresponding to the heart disease of the user (1), and further diagnose the heart disease of the user (1) based on the second score.

[0112] FIG. 6 is a block diagram of a computing device (200) according to another embodiment of the present disclosure.

[0113] Referring to FIG. 6, a computing device (200) according to an embodiment of the present disclosure includes a processor (210), a memory (220), a sensing unit (230), a communication interface (240), a display (250), a user interface (260), a camera (270), and a speaker (280). Among the configurations illustrated in FIG. 6, the processor (210), the memory (220), and the sensing unit (230) correspond to the configurations of the processor (110), the memory (120), and the sensing unit (130) of the computing device (100) illustrated in FIG. 2, and thus a detailed description thereof will be omitted.

[0114] The sensing unit (230) according to one embodiment of the present disclosure may further include a PPG sensor, a blood pressure sensor, a body temperature sensor, etc., through which various biometric information and status information about the user can be obtained.

[0115] A communication interface (240) according to an embodiment of the present disclosure may be understood as a component that transmits and receives data through any known wired or wireless communication system. For example, the communication interface (240) may perform data transmission and reception using a wired or wireless communication system such as a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), wireless broadband internet (WiBro), fifth generation mobile communication (5G), ultrawide-band, ZigBee, radio frequency (RF) communication, wireless LAN, wireless fidelity, near field communication (NFC), or Bluetooth. Since the above-described communication systems are only examples, the wired and wireless communication system for data transmission and reception of the communication interface (240) may be applied in various ways other than the above-described examples.

[0116] The communication interface (240) can receive data required for the processor (110) to perform calculations through wired or wireless communication with any system or any client, etc. In addition, the communication interface (240) can transmit data generated through calculations of the processor (110) through wired or wireless communication with any system or any client, etc. For example, the communication interface (240) can receive medical data through communication with a cloud server that performs tasks such as databases in a hospital environment, standardization of medical data, or a computing device, etc. The communication interface (240) can transmit output data of the neural network model (10), and intermediate data, processed data, etc. derived from the calculation process of the processor (110) through communication with the aforementioned database, server, or computing device, etc. As an example, the processor (110) can obtain a pre-learned neural network model (10) from an external computing device (e.g., an external server device) through the communication interface (240). Additionally, the processor (110) may obtain learning data of the neural network model (10) from an external computing device (e.g., a biosignal measuring device) through a communication interface (240).

[0117] The display (250) can display various images. Here, the images include both still images and moving images. The display (250) can output guide information based on the diagnosis results of the user (1). The display (250) can be implemented as various types of displays, such as an LCD (Liquid Crystal Display Panel), an OLED (Organic Light Emitting Diodes), an LCoS (Liquid Crystal on Silicon), a DLP (Digital Light Processing), etc. In addition, the display (250) can also include a driving circuit, a backlight unit, etc., which can be implemented in a form such as an a-si TFT, an LTPS (low temperature poly silicon) TFT, an OTFT (organic TFT), etc.

[0118] Meanwhile, the display (250) may be implemented as a touch screen by being combined with a touch panel, and in this case, the display (250) may perform the function of not only an output interface that outputs an image through the touch screen, but also an input interface that receives a touch input from a user (1).

[0119] The user interface (260) is a configuration used by the computing device (100) to perform interaction with the user (1), and may include at least one of a touch sensor, a motion sensor, a button, a jog dial, and a switch, but is not limited thereto. The processor (210) may receive a diagnostic request and biological information (occupation, age, gender, etc.) through the user interface (260).

[0120] The camera (270) photographs objects around the user (1) to obtain images of the objects. Specifically, the camera (270) can obtain images of food consumed by the user (1). At this time, the processor (210) can determine whether the user (1) has eaten based on the state of the user (1) and the image of the food consumed by the user (1). To this end, the camera (270) may be implemented with an imaging device such as an imaging device having a CMOS structure (CIS, CMOS Image Sensor) or an imaging device (Charge Coupled Device) having a CCD structure. However, the present invention is not limited thereto, and the camera (270) may be implemented with camera modules of various resolutions capable of photographing a subject. Meanwhile, the camera (270) may be implemented with a depth camera (e.g., an IR depth camera), a stereo camera, an RGB camera, or the like.

[0121] The speaker (280) is a component that outputs various audio data on which various processing operations such as decoding, amplification, and noise filtering have been performed by an audio processing unit (not shown). The speaker (280) can output various notification sounds or voice messages. According to one embodiment of the present disclosure, the processor (210) can convert an electrical signal received from an external device into a user's (1) voice and output it through the speaker (280). For example, the speaker (280) can output guide information of the user (1) according to the diagnosis result as a voice message.

[0122] The various embodiments of the present disclosure described above can be combined with additional embodiments and modified within the scope understood by those skilled in the art in light of the detailed description above. It should be understood that the embodiments of the present disclosure are illustrative in all respects and not restrictive. For example, each component described as a single component may be implemented in a distributed manner, and likewise, components described as distributed may be implemented in a combined manner. Accordingly, all changes or modifications derived from the meaning, scope, and equivalent concepts of the claims of the present disclosure should be construed as being included within the scope of the present disclosure.

Claims

1. A method for diagnosing a heart disease based on an electrocardiogram signal, performed by a computing device including at least one processor, A step of obtaining an electrocardiogram signal for a user; and A step of diagnosing a heart disease of the user based on the acquired electrocardiogram signal; The above diagnosing steps are: A step of inputting the acquired electrocardiogram signal into a pre-trained neural network model to produce a first score corresponding to the user's heart disease; A step of re-acquiring an electrocardiogram signal for the user by determining whether to additionally diagnose the user's heart disease based on the first score calculated above; and A step of further diagnosing a heart disease of the user based on the re-acquired electrocardiogram signal; including, method.

2. In paragraph 1, The step of re-acquiring the electrocardiogram signal for the above user is: If the first score calculated above is identified as being within a preset range, a step of determining an additional diagnosis of the user's heart disease; including, method.

3. In paragraph 1, A step of obtaining status information of the user; The above re-acquisition step is: When an additional diagnosis of the user's heart disease is determined, a step of re-acquiring an electrocardiogram signal for the user based on the acquired status information; including, method.

4. In paragraph 3, The above status information is, Contains the user's medication information, The step of re-acquiring the electrocardiogram signal for the user based on the acquired status information is: A step of re-acquiring the electrocardiogram signal based on the user's medication information when the user is not taking the medication, and then re-acquiring the electrocardiogram signal when the user is identified as having taken the medication; including, method.

5. In paragraph 3, The above status information is, Contains the user's medication information, The step of re-acquiring the electrocardiogram signal for the user based on the acquired status information is: Based on the user's medication information, if it is determined that the electrocardiogram signal was acquired immediately after the user took the medication, a step of re-acquiring the electrocardiogram signal after a preset time has elapsed from the time the user took the medication; including, method.

6. In paragraph 1, The step of re-acquiring the electrocardiogram signal for the above user is: When an additional diagnosis of a heart disease of the user is determined, a step of repeatedly re-acquiring an electrocardiogram signal for the user; including, method.

7. In paragraph 6, The step of further diagnosing the above user's heart disease is: A step of repeatedly additionally diagnosing a heart disease of the user based on the re-acquired electrocardiogram signal each time the electrocardiogram signal for the user is re-acquired, thereby providing additional diagnosis results; including, method.

8. In paragraph 6, The step of further diagnosing the above user's heart disease is: A step of inputting the plurality of electrocardiogram signals repeatedly re-acquired into the pre-trained neural network model to produce a plurality of second scores corresponding to the user's heart disease; and A step of further diagnosing a heart disease of the user based on the plurality of second scores; including, method.

9. In paragraph 6, The step of further diagnosing the above user's heart disease is: A step of generating a first electrocardiogram signal as an average beat of a plurality of electrocardiogram signals repeatedly re-acquired as described above; and A step of inputting the generated first electrocardiogram signal into the learned neural network model to produce a second score corresponding to the user's heart disease; and A step of further diagnosing the user's heart disease based on the second score; including, method.

10. In paragraph 6, The above steps of re-acquiring repeatedly are: A step of monitoring the status information of the user, determining a re-acquisition time of an electrocardiogram signal for the user based on the status information, and repeatedly re-acquiring the electrocardiogram signal for the user according to the determined re-acquisition time; including, method.

11. In paragraph 3, The step of re-acquiring the electrocardiogram signal for the user based on the acquired status information is: If the calculated first score is identified as being within a preset range, a step of analyzing the user's status information to determine whether there is a factor affecting the calculated first score; and If the above elements are found to be present, a step of determining an additional diagnosis of the user's heart disease; including, method.

12. In paragraph 6, The step of re-acquiring the electrocardiogram signal for the above user is: When an additional diagnosis of a heart disease of the user is determined, a step of repeatedly re-acquiring an electrocardiogram signal for the user at a preset time cycle; including, method.

13. In paragraph 12, The step of re-acquiring the electrocardiogram signal for the user at the above-described preset time cycle is: If the user is identified as having undergone surgery within a preset time, a step of changing the preset cycle from a first cycle to a second cycle shorter than the first cycle, and re-acquiring an electrocardiogram signal for the user with the second cycle; including, method.

14. A computer program stored in a computer-readable storage medium, wherein the computer program, when executed on at least one processor, performs an operation of obtaining a user-customized neural network model for identifying biometric information. The above action is, An action to obtain an electrocardiogram signal for a user; and An operation of diagnosing a heart disease of the user based on the acquired electrocardiogram signal; The above diagnostic action is, An operation of inputting the acquired electrocardiogram signal into a pre-trained neural network model to produce a first score corresponding to the user's heart disease; An operation of re-acquiring an electrocardiogram signal for the user by determining whether to further diagnose the user's heart disease based on the first score calculated above; and An operation of further diagnosing a heart disease of the user based on the re-acquired electrocardiogram signal; including, Computer program.

15. A computing device that obtains a user-customized neural network model that identifies biometric information, Memory containing program codes; A sensing unit that acquires the user's electrocardiogram signal; and At least one processor is included that obtains an electrocardiogram signal for the user through the sensing unit and diagnoses a heart disease of the user based on the obtained electrocardiogram signal. The above processor, By inputting the acquired electrocardiogram signal into a pre-trained neural network model, a first score corresponding to the user's heart disease is calculated, and based on the calculated first score, whether or not to additionally diagnose the user's heart disease is determined, thereby re-acquiring the electrocardiogram signal for the user, and further diagnosing the user's heart disease based on the re-acquired electrocardiogram signal. Computing device.

Citation Information

Patent Citations

  • ECG-based future atrial fibrillation prediction system and method

    JP2022550705A

  • Compound and organic light emitting device

    KR1020240082800A

  • Electronic pedal apparatus

    KR1020240133827A

  • Manual Therapy System Using Elevating Bed

    KR102333735B1

  • Health Monitoring

    US20140058280A1