Method, device and program for diagnosing brugada syndrome on basis of electrocardiogram data

Abstract

The present disclosure provides a method, device and program for diagnosing Brugada syndrome on the basis of electrocardiogram data. The method according to one embodiment of the present disclosure comprises the steps of: acquiring electrocardiogram data of a subject; and identifying Brugada syndrome in the subject on the basis of the acquired electrocardiogram data by using a pre-trained first neural network model.

Description

Method, device and program for diagnosing Burgada syndrome based on electrocardiogram data

[0001] The present disclosure relates to the field of artificial intelligence in medicine, and more particularly, to a method, device, and program for diagnosing Burgada syndrome in a user by analyzing electrocardiogram data.

[0002] Recent advancements in information and communication technology have led to the widespread adoption of artificial intelligence (AI) across various fields. In particular, AI is increasingly being adopted in the medical field, where diagnosis and analysis of a user's condition previously relied on the experience and judgment of specialized personnel such as doctors and researchers. This has enabled efficient and rapid diagnosis. For example, various technologies have been proposed that analyze a user's health status or predict the presence of specific diseases by inputting biometric data acquired in real time from the user into a pre-trained AI model.

[0003] Electrocardiogram (ECG) data is a recording of signals generated based on the heart's electrical activity, containing diverse information such as heart rhythm, heart rate, conduction abnormalities, and ischemic conditions. Simply analyzing this ECG data can lead to early detection of cardiovascular disease and structural heart abnormalities. Therefore, ECG analysis is considered a crucial technological tool among the various biometric data available to users in the medical field.

[0004] Meanwhile, Brugada syndrome is a hereditary cardiac electrical disorder that can cause sudden cardiac death even in people without underlying heart disease, leading to life-threatening arrhythmias such as ventricular fibrillation. This condition is primarily caused by mutations in genes related to sodium channels in the heart, such as the SCN5A gene. It can manifest suddenly and lead to death in seemingly healthy young adult males.

[0005] In recent electrocardiogram research, the potential of electrocardiogram data to provide valuable information for the diagnosis of Burghada syndrome has been highlighted. However, automated diagnostic technologies or analysis methods capable of accurately and early identifying or predicting Burghada syndrome based on electrocardiogram data are still not sufficiently developed.

[0006] The present disclosure has been made in response to the aforementioned background technology, and aims to provide a method, device and computer program for diagnosing Burgada syndrome based on electrocardiogram data.

[0007] 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.

[0008] A method for diagnosing Burgada syndrome based on electrocardiogram data, performed by a computing device including at least one processor according to one embodiment of the present disclosure for realizing the task described above, includes a step of acquiring electrocardiogram data of a subject and a step of identifying Burgada syndrome of the subject based on the acquired electrocardiogram data using a first neural network model that has been previously learned.

[0009] Alternatively, the step of identifying Burgada syndrome of the subject includes the step of inputting the acquired electrocardiogram data of the subject into the first neural network model to obtain a first score corresponding to the likelihood of the Burgada syndrome, and the step of identifying whether the subject has Burgada syndrome based on the acquired first score.

[0010] Alternatively, the step of identifying Burgada syndrome of the subject includes the step of identifying a preset state of the subject based on the acquired electrocardiogram data using a pre-trained second neural network model, and the step of identifying Burgada syndrome of the subject based on the acquired electrocardiogram data using the pre-trained first neural network model when the subject is identified as being in the preset state.

[0011] Alternatively, the step of identifying the preset state of the subject includes the step of inputting the acquired electrocardiogram data into a second neural network model trained to predict acute myocardial infarction of the subject to obtain a second score corresponding to the possibility of the acute myocardial infarction, and the step of comparing the acquired second score with a first value to identify the preset state of the subject.

[0012] Alternatively, the first neural network model may be trained based on training data consisting of a plurality of electrocardiogram data acquired from a subject in which ST segment abnormalities and negative T waves are observed in the electrocardiogram signal.

[0013] Alternatively, the second neural network model can be trained based on training data consisting of a plurality of electrocardiogram data labeled with whether or not an acute myocardial infarction of a subject in which ST segment abnormalities are observed in the electrocardiogram signal is present.

[0014] Alternatively, the step of identifying the Burgada syndrome of the subject may include the step of comparing the first score and the second score to identify the condition of the subject as either the Burgada syndrome or the acute myocardial infarction, if the first score is greater than or equal to the second value and the second score is greater than or equal to the first value.

[0015] Alternatively, the electrocardiogram data may be acquired based on a first measurement method of a single-inductor measuring device, and the step of identifying Burgada syndrome of the subject may include the step of inputting the acquired electrocardiogram data into a second neural network model trained to predict acute myocardial infarction of the subject to acquire a second score corresponding to the possibility of the acute myocardial infarction, and the step of requesting re-acquisition of the electrocardiogram data using a second measurement method different from the first measurement method, if the first score is less than a preset third value and the second score is less than a fourth value.

[0016] A computer program stored in a computer-readable storage medium according to one embodiment of the present disclosure for realizing the task as described above, wherein the computer program, when executed on one or more processors, causes an operation of diagnosing Burgada syndrome based on electrocardiogram data, the operation including a step of acquiring electrocardiogram data of a subject and a step of identifying Burgada syndrome of the subject based on the acquired electrocardiogram data using a first neural network model that has been previously learned.

[0017] A computing device for diagnosing Burgada syndrome based on electrocardiogram data according to one embodiment of the present disclosure for realizing the task described above includes a memory including program codes, a communication interface, and one or more processors for obtaining electrocardiogram data of a subject through the communication interface, and identifying Burgada syndrome of the subject based on the obtained electrocardiogram data using a first neural network model that has been previously learned.

[0018] The method for diagnosing Burghada syndrome based on electrocardiogram data disclosed herein automatically predicts the presence of Burghada syndrome based on electrocardiogram data, enabling early and accurate diagnosis of the condition without relying on the expertise or experience of medical professionals. Furthermore, by utilizing an artificial intelligence model to quantitatively and consistently analyze electrocardiogram data, the reliability and reproducibility of the diagnosis can be improved.

[0019] FIG. 1 is a schematic block diagram of a computing device for diagnosing Burgada syndrome based on electrocardiogram data according to one embodiment of the present disclosure.

[0020] FIG. 2 is a flowchart of a method for diagnosing Burgada syndrome based on electrocardiogram data according to one embodiment of the present disclosure.

[0021] FIG. 3 is an exemplary diagram of a method for diagnosing Burgada syndrome based on electrocardiogram data according to one embodiment of the present disclosure.

[0022] FIG. 4 is a flowchart of a method for diagnosing Burgada syndrome by determining a user's condition based on electrocardiogram data according to an embodiment of the present disclosure.

[0023] FIG. 5 is an exemplary diagram of a method for diagnosing Burgada syndrome by determining a user's condition based on electrocardiogram data according to an embodiment of the present disclosure.

[0024] FIG. 6 is an example diagram of requesting re-acquisition of single electrocardiogram data using another inductive measurement method according to one embodiment of the present disclosure.

[0025] FIG. 7 is a detailed configuration diagram of a computing device according to another embodiment of the present disclosure.

[0026] 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.

[0027] Throughout the specification of this disclosure, identical or similar drawing numbers refer to identical or similar components. Furthermore, for clarity in the description of this disclosure, drawing numbers for parts unrelated to the description of this disclosure may be omitted in the drawings.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.”

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 1 is a schematic block diagram of a computing device (100) for diagnosing BRUGADA SYNDROME based on electrocardiogram data according to one embodiment of the present disclosure.

[0039] 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.

[0040] For example, the computing device (100) may be implemented as a server device that links with an external electronic device worn by a user (e.g., a smart watch, an electrocardiogram measuring device, etc.). However, the present invention is not limited thereto, and the computing device (100) may be implemented as various electronic devices such as a desktop, a laptop, a smartphone, a smart watch, a smart band, a smart ring, etc. In the following, for the purpose of understanding the present disclosure, the computing device (100) will be described as a server device.

[0041] Referring to FIG. 1, a computing device (100) according to an embodiment of the present disclosure may include one or more processors (hereinafter, “processors”) (110), memory (120), and a communication interface (130). However, FIG. 1 is merely 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).

[0042] 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.

[0043] The processor (110) is electrically connected to other components of the computing device (100) (i.e., memory (120) and communication interface (130)) and controls the overall operation of the computing device (100).

[0044] 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.

[0045] 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) may store a neural network model trained to identify the possibility of Burghada syndrome based on electrocardiogram data and a neural network model trained to identify the user's condition (e.g., acute myocardial infarction) based on electrocardiogram data. In addition, the memory (120) may include program codes and learning data (e.g., label data in which label information of Burghada syndrome is assigned to a plurality of electrocardiogram data and each electrocardiogram data) that operate to perform learning for the above-described neural network model. In addition, the memory (120) may store program codes that operate the neural network model to receive electrocardiogram data and perform inference according to the intended use of the computing device (100), and processed data generated as the program codes are executed.

[0046] The communication interface (130) can be understood as a component that transmits and receives data through any type of known wired or wireless communication system. For example, the communication interface (130) can 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), 5th 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 (130) can be applied in various ways other than the above-described examples. The communication interface (130) can receive data necessary for the processor (110) to perform calculations through wired or wireless communication with any system or any client, etc. In addition, the communication interface (130) 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 (130) 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 an external computing device (e.g., a smart watch worn by a user, an electrocardiogram signal measuring device).

[0047] The communication interface (130) can transmit output data of the neural network model (10), intermediate data, processed data, etc. derived from the computational process of the processor (110), etc. through communication with the aforementioned database, server, or computing device. For example, the processor (110) can obtain electrocardiogram data from an external computing device (e.g., a smart watch) through the communication interface.

[0048] FIG. 2 is a flowchart of a method for diagnosing Burgada syndrome based on electrocardiogram data according to an embodiment of the present disclosure. FIG. 3 is an exemplary diagram of a method for diagnosing Burgada syndrome based on electrocardiogram data according to an embodiment of the present disclosure.

[0049] According to one embodiment of the present disclosure, the processor (110) may acquire electrocardiogram data of a subject (S210). Here, the subject may be a user using the computing device (100) or registered with the computing device (100), or may be a subject identified when the computing device (100) receives a request for judgment regarding Burghada syndrome. The computing device (100) may acquire biometric information, such as the subject's age, gender, and presence or absence of disease, along with the electrocardiogram data.

[0050] The processor (110) can obtain the user's biometric data from a biometric signal measuring device (e.g., a smart watch worn by the user) that is connected to the computing device through a communication interface (130).

[0051] In addition, the processor (110) may acquire the user's electrocardiogram data by directly detecting an electrical signal generated from the user's heart through a sensing unit of the computing device. To this end, the sensing unit may include a plurality of electrodes. The processor (110) may measure the user's electrocardiogram as the plurality of electrodes are attached to the user's body, thereby acquiring the user's electrocardiogram data. The processor (110) may acquire 1-lead electrocardiogram data for the user using the plurality of electrodes, or may acquire various forms of electrocardiogram data, such as 3-lead, 6-lead, and 12-lead, using the plurality of electrodes.

[0052] Meanwhile, the present invention is not limited thereto, and the processor (110) may obtain various bio-data that can be obtained from the user in addition to electrocardiogram data. For example, the processor (110) may obtain various bio-data such as the user's body temperature, photoreceptor blood flow, heart rate, electroencephalogram data, etc. This may be determined based on the type of bio-data that constitutes the learning data used to train the neural network model that identifies the user's Burghada syndrome. The sensing unit may include a temperature sensor, an image sensor, or a light sensor, etc., to obtain various bio-data of the user.

[0053] And, the processor (110) can determine the Burgada syndrome of the subject based on the electrocardiogram data acquired using the first neural network model that has been previously learned (S220).

[0054] According to one embodiment of the present disclosure, the first neural network model (20) may be a model trained to extract feature information from electrocardiogram data when electrocardiogram data is input to determine whether the subject has Burgada syndrome. However, as described above, the first neural network model (20) may also be trained to determine whether the subject has Burgada syndrome based on biometric data other than electrocardiogram data. This may be set differently depending on the type of biometric data included in the training data.

[0055] In particular, the first neural network model (20) can be trained in advance to produce a score corresponding to the possibility of Burgada syndrome. Specifically, the first neural network model (20) can be trained based on input data including a plurality of electrocardiogram data and training data including label data in which the presence or absence of Burgada syndrome (or a numerical value indicating the severity of Burgada syndrome) is labeled for each input data. At this time, the processor (110) can be trained to minimize the error between the output corresponding to the input data and the label data by a backpropagation algorithm. When electrocardiogram data is input, the trained neural network model can extract feature information (for example, feature points such as ST segments and T waves observed in the electrocardiogram signal) from the electrocardiogram data and output a score (or probability value) regarding the possibility of Burgada syndrome in the subject. For example, the first neural network model (20) may 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 first neural network model (20) may include a plurality of residual blocks that extract latent feature information of input electrocardiogram data and a classifier that classifies Burgada syndrome based on the extracted latent feature information.

[0056] For example, referring to FIG. 3, in the case of electrocardiogram data of a subject with Burgada syndrome, ST segment abnormalities and negative T waves can be observed in the electrocardiogram signal in any one of leads V1 to V3. Specifically, the electrocardiogram of a subject with Burgada syndrome shows that the ST segment is elevated by 2 mm or more compared to the baseline, and the elevated ST segment continues in a concave-type curve, followed by an inverted T wave. Accordingly, the first neural network model (20) can be trained to extract feature information of the electrocardiogram data regarding the shape of the ST segment and negative T wave, determine the relationship with Burgada syndrome, and identify Burgada syndrome in the subject. However, the present invention is not limited thereto, and during the learning process, the first neural network model (20) can identify feature information related to Burgada syndrome in addition to the ST segment and negative T wave.

[0057] Meanwhile, the processor (110) can input the acquired electrocardiogram data and the subject's biometric information (age, gender, etc.) together into the first neural network model (20) that has been previously trained. At this time, the first neural network model (20) can further include a convolutional layer that extracts features related to the biometric information into a one-dimensional feature vector. The first neural network model (20) can identify the subject's Burgada syndrome by combining the feature vector related to the biometric information and the feature information extracted through a plurality of residual blocks.

[0058] And, the processor (110) can input the acquired biometric data into the pre-trained first neural network model (20) to obtain a score (hereinafter, the first score) corresponding to the possibility of Burgada syndrome. Here, the score can correspond to a probability value output from the first neural network model (20). In particular, the processor (110) can obtain a probability value corresponding to Burgada syndrome from a softmax layer arranged at the rear end of the first neural network model (20). The processor (110) can identify the acquired probability value as the first score. Alternatively, the processor (110) can obtain the first score by adjusting the probability value or applying a weight to the probability value. And, the processor (110) can determine whether the subject has Burgada syndrome based on the acquired first score. Referring to FIG. 3, if the acquired first score is greater than or equal to a preset first value, the processor (110) can determine that the subject has Brugada syndrome. The first value can be set differently depending on the subject's gender, age, etc.

[0059] FIG. 4 is a flowchart illustrating a method for diagnosing Burgada syndrome by identifying a user's condition based on electrocardiogram data according to an embodiment of the present disclosure. FIG. 5 is an exemplary diagram illustrating a method for diagnosing Burgada syndrome by identifying a user's condition based on electrocardiogram data according to an embodiment of the present disclosure. S410 illustrated in FIG. 4 may correspond to S210 illustrated in FIG. 2 .

[0060] According to one embodiment of the present disclosure, before determining whether or not a subject has Burgada syndrome, the processor (110) determines a preset state of the subject based on electrocardiogram data acquired using a pre-learned second neural network model (30) (S420), and if it is determined that the subject is in the preset state, Burgada syndrome of the subject can be determined based on electrocardiogram data acquired using a pre-learned first neural network model (20) (S430).

[0061] According to one embodiment of the present disclosure, the second neural network model (30) may be a model trained to extract feature information from electrocardiogram data when electrocardiogram data is input and determine a predetermined state of the subject. However, as described above, the first neural network model (20) may also be trained to determine a predetermined state of the subject based on biometric data other than electrocardiogram data. This may be set differently depending on the type of biometric data included in the training data.

[0062] According to one embodiment of the present disclosure, the preset state of the metabolite may be related to acute myocardial infarction. That is, in step S420, the processor (110) inputs the acquired electrocardiogram data into a second neural network model (30) trained to predict acute myocardial infarction of the subject, thereby obtaining a second score corresponding to the possibility of acute myocardial infarction, and if the obtained second score is equal to or greater than the second value, the subject may be determined to be in the preset state.

[0063] To this end, the second neural network model (30) may be trained in advance to produce a score corresponding to the possibility of acute myocardial infarction. Specifically, the second neural network model (30) may be trained based on input data including a plurality of electrocardiogram data and training data including label data in which the presence or absence of acute myocardial infarction (or a value quantifying the severity of acute myocardial infarction) is labeled for each input data. At this time, the processor (110) may be trained to minimize the error between the output corresponding to the input data and the label data by a backpropagation algorithm. When electrocardiogram data is input, the trained neural network model may extract feature information (for example, feature points such as ST segments observed in the electrocardiogram signal) from the electrocardiogram data and output a score (or probability value) regarding the possibility of acute myocardial infarction of the subject. For example, the second neural network model (30) may 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 second neural network model (30) may include a plurality of residual blocks that extract latent feature information of input electrocardiogram data and a classifier that classifies acute myocardial infarction based on the extracted latent feature information.

[0064] For example, referring to FIG. 5, in the case of electrocardiogram data of a subject with acute myocardial infarction, the ST segment may be observed as elevated compared to the baseline in the electrocardiogram signal in any one of leads V1 to V4. This ST segment elevation is a representative electrocardiogram abnormality caused by damage or ischemia of the heart muscle, and may be utilized as a major diagnostic indicator of acute myocardial infarction. Accordingly, the second neural network model (30) may be trained to extract feature information of the electrocardiogram data regarding the ST segment, determine the correlation with acute myocardial infarction, and identify acute myocardial infarction in the subject. To this end, the training data used to train the second neural network model (30) may be composed of a plurality of electrocardiogram data labeled with whether or not the subject with an ST segment abnormality observed in the electrocardiogram signal has acute myocardial infarction.

[0065] However, it is not limited to this, and during the learning process, the second neural network model (30) can identify feature information related to acute myocardial infarction in addition to the ST segment.

[0066] Meanwhile, the processor (110) can input the acquired electrocardiogram data and the subject's biometric information (age, gender, etc.) together into the pre-trained second neural network model (30). At this time, the second neural network model (30) can further include a convolutional layer that extracts features related to the biometric information into a one-dimensional feature vector. The second neural network model (30) can identify acute myocardial infarction of the subject by combining the feature vector related to the biometric information and the feature information extracted through a plurality of residual blocks.

[0067] And, the processor (110) can input the acquired biometric data into the pre-trained second neural network model (30) to obtain a score (hereinafter, the second score) corresponding to the possibility of acute myocardial infarction. Here, the score can correspond to a probability value output from the second neural network model (30). In particular, the processor (110) can obtain a probability value corresponding to acute myocardial infarction from a softmax layer arranged at the rear end of the second neural network model (30). The processor (110) can identify the obtained probability value as the second score. Alternatively, the processor (110) can obtain the second score by adjusting the probability value or applying a weight to the probability value. And, the processor (110) can determine whether the subject has acute myocardial infarction based on the obtained second score.

[0068] Referring to FIG. 5, the processor (110) may determine that the subject is in a predetermined risk group for acute myocardial infarction by comparing the acquired second score with a preset second value. If the processor (110) determines that the subject is in a predetermined risk group for acute myocardial infarction, the processor (110) may determine Burgada syndrome of the subject based on electrocardiogram data acquired using a pre-learned first neural network model (20). In particular, the acute myocardial infarction of the subject may be classified into multiple risk groups according to multiple reference values ​​for the second score. In addition, the preset risk group may be the highest high-risk group among the multiple risk groups. In this case, if the processor (110) determines that the second score is equal to or greater than a second value set corresponding to a high-risk group in relation to acute myocardial infarction, the processor (110) may determine that the subject is in a Burgada syndrome. The second value may be set differently depending on the age, gender, etc. of the subject.

[0069] However, this is not limited thereto, and the preset risk group can be set in various ways, and the second value can be set corresponding to the preset risk group. For example, the preset risk group may be a medium risk group, and the second value may be set corresponding to the medium risk group. In this case, the second value includes multiple values ​​(the second-1 value and the second-2 value), and when the second score is equal to or greater than the lower limit value and less than the upper limit value among the multiple values, the processor (110) can determine the condition of the subject as a medium risk group.

[0070] Meanwhile, if the processor (110) determines that the subject is in the high-risk group based on the second score and that the subject has Brugada syndrome based on the first score, the condition of the subject can be diagnosed as Brugada syndrome.

[0071] In addition, if the second score is equal to or greater than a third value that is greater than a second value set corresponding to a high-risk group, the processor (110) can preemptively diagnose acute myocardial infarction in the subject and then determine whether the subject has Brugada syndrome based on the first score. In particular, the processor (110) can transmit information warning of the risk of acute myocardial infarction in the subject through the communication interface (130). Thereafter, the processor (110) can determine whether the subject has Brugada syndrome using electrocardiogram data and the first neural network model (20).

[0072] Meanwhile, the electrocardiogram data input to the first neural network model (20) and the second neural network model (30) may be electrocardiogram data obtained based on the same induction method. For example, the electrocardiogram data may be electrocardiogram data corresponding to the same induction among leads V1 to V3. However, the present invention is not limited thereto, and the first neural network model (20) may be input with multiple single electrocardiogram data measured according to the V1 to V3 induction methods, and may determine whether or not Burghada syndrome exists based on the highest first score. At this time, the second neural network model (30) may be input with multiple single electrocardiogram data measured according to the V1 to V4 induction methods, and may determine whether or not acute myocardial infarction exists based on the highest second score.

[0073] Meanwhile, the processor (110) may determine the condition of the subject as either Burgada syndrome or acute myocardial infarction by comparing the first score and the second score, if the first score is equal to or greater than a preset first value and the second score is equal to or greater than a preset second value. That is, if the processor (110) determines that the subject is at high risk for acute myocardial infarction based on the second score and has Burgada syndrome based on the first score, the processor (110) may compare the first score and the second score to diagnose the disease or condition of the final subject. To this end, the processor (110) may perform a normalization (calibration) process so that the two scores can be compared on the same basis, considering that the first score and the second score are values ​​derived from different neural network models. For example, each score may be normalized to a value reflecting the actual disease occurrence probability through at least one of Platt Scaling, Isotonic Regression, or other statistical calibration techniques based on the output characteristics of the model used during learning and verification data. Based on the normalized score, the processor (110) can accurately determine whether the subject has Burghada syndrome or acute myocardial infarction. The processor (110) can identify the subject's condition and disease based on a score with a higher value.

[0074] According to one embodiment of the present disclosure, it may be obtained based on the first measurement method of a single-induction measuring device. At this time, the processor (110) inputs the obtained electrocardiogram data into a second neural network model (30) trained to predict acute myocardial infarction of the subject to obtain a second score corresponding to the possibility of acute myocardial infarction, and if the second score is identified as being equal to or greater than a fourth value, the processor (110) inputs the obtained electrocardiogram data into a first neural network model (20) trained to predict Burgada syndrome of the subject to obtain a first score corresponding to Burgada syndrome, and if the first score is less than a preset fifth value, the processor (110) may request that the electrocardiogram data be re-acquired using a second measurement method different from the first measurement method. That is, if acute myocardial infarction is identified as belonging to a high-risk group, but Burgada syndrome is identified as normal, the processor (110) may request that single electrocardiogram data of a different induction method be acquired for further diagnosis of the subject. Here, the fourth value may be higher than the second value, which corresponds to the high-risk group, and the fifth value may be lower than the first value, which corresponds to the Burghada syndrome. In particular, the fourth value may be a value corresponding to the normal group in relation to Burghada syndrome.

[0075] FIG. 6 is an example diagram of requesting re-acquisition of single electrocardiogram data using another inductive measurement method according to one embodiment of the present disclosure.

[0076] Referring to FIG. 6, the processor (110) may provide single-induction electrocardiogram measurement method information through the display of the computing device (100) or the display of the smart watch (200) (or electrocardiogram data measurement device) of the object that is linked to the computing device (100). When the electrocardiogram data measurement device is the smart watch (200), the processor (110) may display information on body parts that are in contact with the first and second electrodes included in the smart watch (200). Referring to FIG. 6, the processor (110) may notify the user through the display (140) of the smart watch (200) that Burghada syndrome cannot be determined based on the electrocardiogram data acquired according to the V1 induction method and may recommend re-measuring the electrocardiogram data through another measurement method (i.e., the V2 induction method). At this time, the display may display text and graphics indicating the body parts of the user that are in contact with the first and second electrodes included in the smart watch (200). Specifically, the processor (110) may display graphic objects corresponding to the user's body and the smart watch on the display (200) when the other measurement method is a V2-induced measurement method, and may display text indicating the location where the smart watch is placed on the user's body and the body parts of the user that come into contact with the first and second electrodes.

[0077] In this regard, the method of measuring an electrocardiogram signal using a single-lead electrocardiogram measuring device can be set in various ways depending on the lead type. When the single-lead electrocardiogram measuring device is a smartwatch, the measurement method of Lead 1 may be such that the first electrode positioned on the back of the smartwatch contacts the user's left wrist and the second electrode positioned on the side of the smartwatch contacts the user's right finger. In addition, the measurement method of Lead ± may be such that the first electrode positioned on the back of the smartwatch contacts the user's left lower abdomen and the second electrode positioned on the side of the smartwatch contacts the user's right finger. In addition, the measurement method of Lead 2 may be such that the first electrode positioned on the back of the smartwatch contacts the user's left lower abdomen and the user's left finger contacts the second electrode positioned on the side of the smartwatch. In addition, the measurement method of Lead V1 may be such that the first electrode positioned on the back of the smartwatch contacts the sternal side of the user's right fourth intercostal space and the user's right finger (or left finger) contacts the second electrode positioned on the side of the smartwatch. And, the measurement method of lead V2 may be a method in which the first electrode arranged on the back of the smartwatch is brought into contact with the sternal side of the user's left fourth intercostal space, and the user's right finger (or left finger) is brought into contact with the second electrode arranged on the side of the smartwatch. And, the measurement method of lead V3 may be a method in which the first electrode is brought into contact with a body part located between the contact position of the first electrode in the measurement method of V2 and the contact position of the first electrode in the measurement method of V4 described below, and the user's right finger (or left finger) is brought into contact with the second electrode. And, the measurement method of lead V4 may be a method in which the first electrode arranged on the back of the smartwatch is brought into contact with the fifth intercostal space along the center line of the user's left clavicle, and the user's right finger (or left finger) is brought into contact with the second electrode.And, the measurement method of Lead V5 may be a method in which the first electrode placed on the back of the smartwatch is contacted to the fifth intercostal space along the user's left anterior axillary line (or midaxillary line), and the user's right finger (or left finger) is contacted to the second electrode. And, the measurement method of Lead V6 may be a method in which the first electrode placed on the back of the smartwatch is contacted to the fifth intercostal space along the user's left middle axillary line (or midaxillary line), and the user's right finger (or left finger) is contacted to the second electrode.

[0078] FIG. 7 is a detailed configuration diagram of a computing device (700) according to another embodiment of the present disclosure. Referring to FIG. 6, the computing device (700) according to one embodiment of the present disclosure includes a processor (710), a memory (720), a communication interface (730), a display (740), a user interface (750), a sensing unit (760), and a speaker (770). Among the configurations illustrated in FIG. 6, a detailed description of configurations that overlap with those illustrated in FIG. 1 will be omitted.

[0079] The display (740) can display various images. The images include both still images and moving images. The display (740) can also output an electrocardiogram corresponding to the acquired electrocardiogram data, and can output information regarding the severity of Burghada syndrome or acute myocardial infarction.

[0080] The display (740) may be implemented as a display of various forms, 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 (740) may also include a driving circuit, a backlight unit, etc., which may be implemented as a form, such as an a-si TFT, an LTPS (low temperature poly silicon) TFT, an OTFT (organic TFT), etc.

[0081] Meanwhile, the display (740) may be implemented as a touch screen by being combined with a touch panel, and in this case, the display (740) 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 user's touch input.

[0082] The user interface (750) is a component used by the computing device (700) to perform interaction with a user, and may include, but is not limited to, at least one of a touch sensor, a motion sensor, a button, a jog dial, and a switch. The user interface (750) may receive biometric information of a subject.

[0083] The sensing unit (760) senses the patient's bio-signals to obtain bio-data. For example, the patient's electrocardiogram data can be obtained by detecting the electrical signal of the patient's heartbeat through at least one electrode included in the sensing unit (760).

[0084] The speaker (770) is a component that outputs various audio data that have undergone various processing operations, such as decoding, amplification, and noise filtering, by an audio processing unit (not shown). The speaker (770) can output various notification sounds or voice messages. The processor (710) can convert an electrical signal into the user's (1) voice and output it through the speaker (770). As an example, the speaker (770) can output information on the judgment result regarding the subject's Burghada syndrome or acute myocardial infarction as voice data.

[0085] Meanwhile, according to one embodiment of the present disclosure, a non-transitory computer-readable medium storing a program for performing a method of identifying a user's Burgada syndrome based on the electrocardiogram data described above may be provided. Here, the non-transitory computer-readable medium refers to a medium that permanently stores data and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, the various applications or programs described above may be stored and provided on a non-transitory computer-readable medium, such as a CD, DVD, hard disk, Blu-ray disc, USB, memory card, or ROM. The various embodiments of the present disclosure described above may be combined with additional embodiments and may be modified within a range understandable to those skilled in the art in light of the detailed description described above.

[0086] It should be understood that the embodiments of this disclosure are illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and likewise, components described as distributed may be implemented in a combined manner. Accordingly, all modifications or variations derived from the meaning, scope, and equivalent concepts of the claims of this disclosure should be construed as being included within the scope of this disclosure.

Claims

1. A method for diagnosing Burgada syndrome based on electrocardiogram data, performed by a computing device including at least one processor, A step of acquiring electrocardiogram data of a subject; and A step of identifying Burgada syndrome of the subject based on the acquired electrocardiogram data using the first neural network model that has been previously learned; method.

2. In paragraph 1, The step of identifying the Burgada syndrome of the above subject is: A step of inputting the acquired electrocardiogram data into the first neural network model of the subject to obtain a first score corresponding to the possibility of the Burgada syndrome; and A step of identifying whether the subject has Burgada syndrome based on the first score obtained above; including; method.

3. In paragraph 2, The step of identifying the Burgada syndrome of the above subject is: A step of identifying a preset state of the subject based on the acquired electrocardiogram data using a second neural network model that has been previously learned; and If the subject is identified as being in a preset state, a step of identifying Burgada syndrome of the subject based on the acquired electrocardiogram data using the first neural network model learned in advance; method.

4. In paragraph 3, The step of identifying the preset state of the above object is: A step of inputting the acquired electrocardiogram data into a second neural network model trained to predict acute myocardial infarction of the subject to obtain a second score corresponding to the possibility of the acute myocardial infarction; and A step of identifying a preset state of the object by comparing the acquired second score with the first value; method.

5. In paragraph 4, The above first neural network model is, Learned based on training data consisting of multiple electrocardiogram data acquired from subjects in which ST segment abnormalities and negative T waves are observed in the electrocardiogram signal. method.

6. In paragraph 5, The above second neural network model is, Whether or not acute myocardial infarction is observed in a subject with ST segment abnormality in the electrocardiogram signal is learned based on training data consisting of multiple labeled electrocardiogram data. method.

7. In paragraph 4, The step of identifying the Burgada syndrome of the above subject is: A step of comparing the first score and the second score to identify the condition of the subject as either the Burgada syndrome or the acute myocardial infarction, if the first score is greater than or equal to the second value and the second score is greater than or equal to the first value; method.

8. In paragraph 2, The above electrocardiogram data is, It is obtained based on the first measurement method of a single induction measuring device, The step of identifying the Burgada syndrome of the above subject is: A step of inputting the acquired electrocardiogram data into a second neural network model trained to predict acute myocardial infarction of the subject to obtain a second score corresponding to the possibility of the acute myocardial infarction; and A step of requesting re-acquisition of the electrocardiogram data using a second measurement method different from the first measurement method, if the first score is less than a preset third value and the second score is greater than or equal to a fourth value; method.

9. A computer program stored in a computer-readable storage medium, wherein the computer program, when executed on one or more processors, causes the computer program to perform an operation of diagnosing Burgada syndrome based on electrocardiogram data, the operation comprising: A step of acquiring electrocardiogram data of a subject; and A step of identifying Burgada syndrome of the subject based on the acquired electrocardiogram data using the first neural network model that has been previously learned; Computer program.

10. In a computing device for diagnosing Burgada syndrome based on electrocardiogram data, Memory containing program codes; Communication interface and One or more processors that acquire electrocardiogram data of a subject through the communication interface and identify Burgada syndrome of the subject based on the acquired electrocardiogram data using a first neural network model that has been previously learned. Computing device.

Images