WO2024014838A1 - Procédé, programme et dispositif de fourniture de contenu de visualisation basé sur une lecture d'ecg - Google Patents

Procédé, programme et dispositif de fourniture de contenu de visualisation basé sur une lecture d'ecg Download PDF

Info

Publication number
WO2024014838A1
WO2024014838A1 PCT/KR2023/009857 KR2023009857W WO2024014838A1 WO 2024014838 A1 WO2024014838 A1 WO 2024014838A1 KR 2023009857 W KR2023009857 W KR 2023009857W WO 2024014838 A1 WO2024014838 A1 WO 2024014838A1
Authority
WO
WIPO (PCT)
Prior art keywords
electrocardiogram
heart
data
ecg
visualization content
Prior art date
Application number
PCT/KR2023/009857
Other languages
English (en)
Korean (ko)
Inventor
권준명
강선미
임선유
이병탁
Original Assignee
주식회사 메디컬에이아이
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from KR1020230081780A external-priority patent/KR20240009348A9/ko
Application filed by 주식회사 메디컬에이아이 filed Critical 주식회사 메디컬에이아이
Publication of WO2024014838A1 publication Critical patent/WO2024014838A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/339—Displays specially adapted therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/353—Detecting P-waves
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/355—Detecting T-waves
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/366—Detecting abnormal QRS complex, e.g. widening
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • the present disclosure relates to a method of providing visualization content based on electrocardiogram readings. Specifically, visualization of electrocardiogram waveforms and anatomical heart shapes based on electrocardiogram features obtained by analyzing electrocardiogram data using a pre-trained neural network model. It's about how you can provide content.
  • ECG electrocardiogram
  • the heartbeat which is the cause of the electrocardiogram, is an impulse that originates from the sinus node located in the right atrium, first depolarizes the right and left atrium, and after a brief delay in the atrioventricular node, Activates the ventricles.
  • the right ventricle which has the fastest septum and thin walls, activates before the left ventricle, which has thick walls.
  • the depolarization wave transmitted to the Purkinje fibers spreads from the endocardium to the epicardium like a wavefront in the myocardium, causing ventricular contraction. Because electrical impulses are normally conducted through the heart, the heart contracts approximately 60 to 100 times per minute. Each contraction is represented by one heart beat.
  • Such an electrocardiogram can be detected through a bipolar lead, which records the potential difference between two parts, and a unipolar lead, which records the potential of the area where the electrode is attached.
  • Methods for measuring an electrocardiogram include the bipolar lead. There is a standard limb lead, a unipolar limb lead, and a unipolar thoracic lead (precordial lead).
  • the electrical activity stage of the heart is largely divided into atrial depolarization, ventricular depolarization, and ventricular repolarization, and each of these stages is reflected in the form of several waves called P, Q, R, S, and T waves, as shown in Figure 1.
  • These waves must have a standard shape for the heart's electrical activity to be considered normal. In order to determine whether it is a standard shape or not, it is necessary to check whether characteristics such as the time each wave is maintained, the interval between each wave, the amplitude of each wave, and kurtosis are within the normal range (or standard).
  • electrocardiograms are measured with expensive measuring equipment and used as an auxiliary tool to measure the patient's health status. In general, electrocardiogram measuring equipment only displays measurement results and diagnosis is entirely up to the doctor.
  • the 24-hour electrocardiogram test is a test that measures electrocardiogram changes after a small cassette-sized measuring device is mounted on the user's body and the electrocardiogram test is completed after a certain period of time (for example, about 20 hours).
  • This 24-hour electrocardiogram test is a test to diagnose heart disease by checking on the electrocardiogram whether symptoms such as dizziness, fainting, palpitations, and chest pain that appear during daily life are related to arrhythmia.
  • the device must be attached and There is an inconvenience in that the user has to visit the examination room (e.g., hospital, etc.) twice to remove the device.
  • future ECG testing systems are not limited to users continuously measuring ECG in their daily lives, but can quickly and accurately identify the user's ECG data through a pre-trained neural network model by linking it with the medical information system installed in the hospital.
  • the present disclosure was made in response to the above-described background technology, and presents heart condition information, including heart movement, blood flow, and electrical flow, along with the electrocardiogram waveform in the form of an anatomical heart so that users without medical knowledge can understand the electrocardiogram data.
  • the purpose is to provide a method of providing visualization content based on electrocardiogram readings that can be displayed in a visualized animation form.
  • the present disclosure seeks to provide a method of providing visualization content based on electrocardiogram reading.
  • the method includes providing visualization content based on electrocardiogram readings, performed by a computing device including at least one processor, the method comprising: acquiring electrocardiogram data; extracting electrocardiogram features from the electrocardiogram data; and generating visualization content including an electrocardiogram graph representing an electrocardiogram waveform of the electrocardiogram data and cardiac animation data visualizing an anatomical shape of the heart based on the extracted electrocardiogram features, wherein the cardiac animation data includes the It is played in synchronization with an electrocardiogram graph and displays heart condition information including at least one of heart movement, blood flow, or electrical flow.
  • the electrocardiogram features may include P waves, QRS complex, and T waves.
  • the step of generating visualization content including an ECG graph representing an ECG waveform of the ECG data and heart animation data visualizing an anatomical heart based on the extracted ECG features includes extracting the ECG data and the Calculating the heart axis based on the electrocardiogram characteristics; and generating the heart animation data by arranging the anatomical shape of the heart based on the calculated heart axis.
  • calculating a heart axis based on the ECG data and the extracted ECG features may include calculating a standard lead and a limb lead in the ECG data based on the ECG features, respectively. calculating the net amplitude of; and calculating the angle of the heart axis based on a mathematical operation using the summed amplitude of the standard leads and the summed amplitude of the limb leads as input variables. may include.
  • generating the cardiac animation data by placing the anatomical view of the heart relative to the calculated cardiac axis comprises: wherein the calculated cardiac axis does not fall within the range of 45 degrees to 90 degrees relative to induction I; If not, generating the heart animation data by placing the anatomical shape of the heart at 60 degrees; may include.
  • the step of generating visualization content including an ECG graph representing an ECG waveform of the ECG data and heart animation data visualizing an anatomical heart based on the extracted ECG features may include generating visualization content based on the ECG features. Identifying at least one of the start point, end point, or duration of the electrocardiogram waveform; and synchronizing heart movement, blood flow, or electrical flow in the electrocardiogram waveform and the anatomical view of the heart based on at least one of the start point, end point, or duration.
  • the method may further include providing a user interface for playing the visualization content to a user terminal.
  • the step of providing a user interface for reproducing the visualization content to a user terminal may include, when a first event occurs based on a user input for a reference point or baseline preset in the electrocardiogram graph, the anatomy corresponding to the reference point or baseline. Playing the visualization content so that an image of an enemy heart is displayed; It can be included.
  • the step of providing a user interface for playing the visualization content to a user terminal may include changing at least one of color, brightness, saturation, or highlight effect of the anatomical heart shape according to a change in the electrocardiogram graph. It may include the step of playing the visualization content so that the visual content is reproduced.
  • the step of providing a user interface for playing the visualization content to a user terminal may include a second event based on a user input that specifies a predetermined position in the anatomical view of the heart while the visualization content is stopped.
  • it may include reproducing the visualization content so that an ECG waveform that has a correlation with the specified location is displayed.
  • providing a user interface for playing the visualization content to a user terminal may include, when a third event occurs based on a user input for selecting and zooming out an atrial region in the anatomical view of the heart, Playing the visualization content so that blood fills the selected atrial region and an electrocardiogram waveform corresponding to the activity of the selected atrial region is displayed; It can be included.
  • the step of generating visualization content including an ECG graph representing the ECG waveform of the ECG data and heart animation data visualizing an anatomical heart based on the extracted ECG features may include: Identifying waveforms not included in; And it may include generating the electrocardiogram graph by modifying at least one of the color, shape, or shape of the waveform that is not included in the identified normal category.
  • a computer program stored in a computer-readable storage medium wherein the computer program, when executed on one or more processors, performs operations for providing visualization content based on electrocardiogram reading. And the operations include: acquiring electrocardiogram data; Extracting electrocardiogram features from the electrocardiogram data using a pre-trained neural network model; And an operation of generating visualization content including an electrocardiogram graph representing an electrocardiogram waveform of the electrocardiogram data and cardiac animation data visualizing an anatomical heart based on the extracted electrocardiogram features, wherein the cardiac animation data includes: It is played in synchronization with an electrocardiogram graph and displays heart condition information including at least one of heart movement, blood flow, or electrical flow.
  • a computing device for providing visualization content based on electrocardiogram readings includes: a processor including at least one core; and a memory including program codes executable by the processor, wherein the processor obtains electrocardiogram data according to execution of the program code and uses a pre-trained neural network model to obtain the electrocardiogram data.
  • ECG features are extracted from ECG data, and based on the extracted ECG features, visualization content is generated including an ECG graph representing the ECG waveform of the ECG data and heart animation data visualizing the anatomical shape of the heart, wherein the heart animation
  • the data is played in synchronization with the electrocardiogram graph and displays heart condition information including at least one of heart movement, blood flow, or electrical flow.
  • a method of providing visualization content based on electrocardiogram reading includes visualization of the anatomical appearance of the heart along with electrocardiogram waveforms based on electrocardiogram features obtained by analyzing electrocardiogram data using a pre-trained neural network model.
  • the present disclosure is synchronized with the electrocardiogram waveform to express heart movement, blood flow, or electric flow in the anatomical shape of the heart and display it in an animated manner, so that anyone can easily and interestingly understand the electrocardiogram, and have interest in cardiac activity and heart health. This has the effect of increasing it.
  • FIG. 1 is a diagram showing electrocardiogram data according to the present disclosure.
  • FIG. 2 is a block diagram of a computing device according to an embodiment of the present disclosure.
  • Figure 3 is a block diagram illustrating the configuration of a system that provides visualization content based on electrocardiogram readings according to an embodiment of the present disclosure.
  • Figure 4 is an example diagram explaining visualization content according to an embodiment of the present disclosure.
  • FIG. 5 is a diagram illustrating electrocardiogram graphs measured in standard leads and limb leads according to an embodiment of the present disclosure.
  • FIG. 6 is a diagram illustrating electrode positions and the heart axis in standard ECG guidance according to an embodiment of the present disclosure.
  • Figure 7 is an example diagram illustrating the summed amplitude of QRS waveforms according to an embodiment of the present disclosure.
  • Figure 8 is a flowchart explaining a method of providing visualization content based on electrocardiogram reading according to an embodiment of the present disclosure.
  • Figure 9 is an example diagram illustrating a synchronization process between an electrocardiogram graph and heart animation data according to an embodiment of the present disclosure.
  • FIG. 10 is an example diagram illustrating heart animation data in which the electrocardiogram and the electrical flow of the heart are synchronized according to an embodiment of the present disclosure.
  • Figure 11 is a flowchart explaining a method of playing visualization content according to an embodiment of the present disclosure.
  • Figure 12 is an exemplary diagram showing an electrocardiogram graph according to an embodiment of the present disclosure.
  • FIG. 13 is a diagram illustrating a process of synchronizing and playing back an electrocardiogram graph and heart animation data according to an embodiment of the present disclosure.
  • FIG. 14 is a diagram illustrating a normal standard for an ECG waveform based on ECG characteristics according to an embodiment of the present disclosure.
  • x uses a or b should be understood to mean one of natural implicit substitutions.
  • x uses a or b means that x uses a, x uses b, or x uses a and It can be interpreted as one of the cases where both b are used.
  • th nth (n is a natural number)
  • n is a natural number
  • a predetermined standard such as a functional perspective, a structural perspective, or explanatory convenience.
  • components performing different functional roles may be distinguished as first components or second components.
  • components that are substantially the same within the technical spirit of the present disclosure but must be distinguished for convenience of explanation may also be distinguished as first components or second components.
  • acquisition used in this disclosure is understood to mean not only receiving data through a wired or wireless communication network with an external device or system, but also generating data in an on-device form. It can be.
  • module refers to a computer-related entity, firmware, software or part thereof, hardware or part thereof.
  • the “module” or “unit” can be understood as a term referring to an independent functional unit that processes computing resources, such as a combination of software and hardware.
  • the “module” or “unit” may be a unit composed of a single element, or may be a unit expressed as a combination or set of multiple elements.
  • a “module” or “part” in the narrow sense is a hardware element or set of components of a computing device, an application program that performs a specific function of software, a process implemented through the execution of software, or a program. It can refer to a set of instructions for execution, etc.
  • module or “unit” may refer to the computing device itself constituting the system, or an application running on the computing device.
  • module or “unit” may be defined in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.
  • model refers to a system implemented using mathematical concepts and language to solve a specific problem, a set of software units to solve a specific problem, or a process to solve a specific problem. It can be understood as an abstract model of a process.
  • a neural network “model” may refer to an overall system implemented as a neural network that has problem-solving capabilities through learning. At this time, the neural network can have problem-solving capabilities by optimizing parameters connecting nodes or neurons through learning.
  • a neural network “model” may include a single neural network or a neural network set in which multiple neural networks are combined.
  • a neural network “block” can be understood as a set of neural networks containing at least one neural network. At this time, it can be assumed that the neural networks included in the neural network “block” perform the same specific operation.
  • the explanation of the foregoing terms is intended to aid understanding of the present disclosure. Therefore, if the above-mentioned terms are not explicitly described as limiting the content of the present disclosure, it should be noted that the content of the present disclosure is not used in the sense of limiting the technical idea.
  • Figure 2 is a block diagram of a computing device according to an embodiment of the present disclosure.
  • the computing device 100 may be a hardware device or 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 network.
  • the computing device 100 may be a server that performs intensive data processing functions and shares resources, or it may be a client that shares resources through interaction with the server.
  • the computing device 100 may be a cloud system in which a plurality of servers and clients interact to comprehensively process data. Since the above description is only an 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.
  • the computing device 100 may include a processor 110, a memory 120, and a network unit 130. there is. However, since FIG. 2 is only an example, the computing device 100 may include other components for implementing a computing environment. Additionally, only some of the configurations disclosed above may be included in computing device 100.
  • the processor 110 may be understood as a structural unit including hardware and/or software for performing computing operations.
  • the processor 110 may read a computer program and perform data processing for machine learning.
  • the processor 110 may process computational processes such as processing input data for machine learning, extracting features for machine learning, and calculating errors based on backpropagation.
  • the processor 110 for performing such data processing includes a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), and a custom processing unit (TPU). It may include a semiconductor (ASICc: application specific integrated circuit), or a field programmable gate array (FPGA: field programmable gate array). Since the type of processor 110 described above is only an example, 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.
  • the processor 110 may extract ECG features including P waves, QRS complexes, and T waves based on ECG data, and learn a neural network model for diagnosing heart disease based on the extracted ECG features. For example, the processor 110 may learn a neural network model to estimate heart disease by analyzing the ECG based on biological information including information such as gender, age, weight, height, etc., along with the ECG data. Specifically, the processor 110 may input electrocardiogram data and various biological information into the neural network model and train the neural network model to detect changes in the electrocardiogram due to arrhythmia or other heart diseases. At this time, the neural network model can perform learning based on an ECG dataset that includes features extracted from ECG data and diagnostic data for arrhythmia and other heart diseases. The processor 110 may perform an operation representing at least one neural network block included in the neural network model during the learning process of the neural network model.
  • the processor 110 may extract ECG features from ECG data obtained from an ECG meter using a neural network model generated through the above-described learning process, and estimate ECG reading data based on the extracted ECG features.
  • the processor 110 inputs biological information including electrocardiogram data and information such as gender, age, weight, height, etc. into a neural network model learned through the above-described process to generate inference data representing the result of estimating the probability of heart disease. can be created.
  • the processor 110 can input electrocardiogram data into a trained neural network model to predict the presence or progression of arrhythmia or other heart disease.
  • the types of medical data and the output of the neural network model may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.
  • the processor 110 may generate visualization content that can show ECG waveforms, heart movement, blood flow, or electricity flow based on ECG characteristics analyzed through a neural network model.
  • the visualization content may include an ECG graph representing the ECG waveform of the ECG data, and heart animation data that is played in synchronization with the ECG graph.
  • the memory 120 may be understood as a structural unit including hardware and/or software for storing and managing data processed in the computing device 100. That is, the memory 120 can store any type of data generated or determined by the processor 110 and any type of data received by the network unit 130.
  • the memory 120 may be a flash memory type, hard disk type, multimedia card micro type, card type memory, or random access memory (RAM). ), SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), PROM (prom: programmable read-only memory), magnetic memory , may include at least one type of storage medium among a magnetic disk and an optical disk.
  • the memory 120 may include a database system that controls and manages data in a predetermined system. Since the type of memory 120 described above is only an example, the type of memory 120 may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.
  • the memory 120 can structure, organize, and manage data necessary for the processor 110 to perform operations, combinations of data, and program codes executable on the processor 110.
  • the memory 120 may store ECG data received through the network unit 130, which will be described later.
  • the memory 120 includes program code that operates the neural network model to receive medical data and perform learning, program code that operates the neural network model to receive medical data and perform inference according to the purpose of use of the computing device 100, and Processed data generated as the program code is executed can be saved.
  • the network unit 130 may be understood as a structural unit that transmits and receives data through any type of known wired or wireless communication system.
  • the network unit 130 may be connected to a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), or wireless (WIBRO).
  • LAN local area network
  • WCDMA wideband code division multiple access
  • LTE long term evolution
  • WIBRO wireless
  • broadband internet 5th generation mobile communication
  • 5g ultra wide-band wireless communication
  • zigbee radio frequency (RF) communication
  • RF radio frequency
  • wireless LAN wireless fidelity
  • NFC near field communication
  • Bluetooth Bluetooth
  • the network unit 130 may receive data necessary for the processor 110 to perform calculations through wired or wireless communication with any system or client. Additionally, the network unit 130 may transmit data generated through the calculation of the processor 110 through wired or wireless communication with any system or any client. For example, the network unit 130 may receive medical data through communication with an electrocardiogram monitor 10, including a wearable device. The network unit 130 may transmit output data of the neural network model, intermediate data derived from the calculation process of the processor 110, processed data, etc. through communication with the above-mentioned devices.
  • FIG. 3 is a block diagram illustrating the configuration of a system that provides visualization content based on electrocardiogram reading according to an embodiment of the present disclosure
  • FIG. 4 is an example diagram explaining visualization content according to an embodiment of the present disclosure.
  • a system that provides visualization content based on electrocardiogram readings includes, but is not limited to, at least one electrocardiogram measuring device 10 and a computing device 100.
  • the electrocardiogram measuring device 10 can use various devices capable of measuring electrocardiograms, such as wearable devices that are worn on the user's body and can measure and collect various health indicators such as heart rate, body fat percentage, and blood pressure, and electrocardiogram kiosks. At this time, the electrocardiogram measuring device 10 can measure the electrocardiogram using various electrode combinations, such as a 12-guide method and a 6-guide method, as well as a single-guide method using a wearable device such as a wrist watch or a patch. It is desirable that the electrocardiogram measurement time is also set by adding or subtracting depending on the signal to be obtained.
  • This electrocardiogram measuring device 10 may include a user terminal connected to a wearable device, including an electronic appcessory and a smartwatch, which have received medical device approval from the Ministry of Food and Drug Safety to measure the electrocardiogram. there is.
  • the computing device 100 can extract ECG features including P waves, QRS complexes, and T waves based on machine learning or various statistical techniques based on ECG data acquired from the ECG meter 10. .
  • the neural network model includes the frequency of tachycardia, the length of the QT interval, the direction of deviation of the P wave, R wave, and T wave, Alternatively, it may be learned based on ECG characteristics including at least one of QRS duration.
  • the computing device 100 displays visualization content including an electrocardiogram graph 310 representing an electrocardiogram waveform based on electrocardiogram characteristics and heart animation data 320 that visualizes the anatomical appearance of the heart.
  • the heart animation data 320 may represent heart condition information including at least one of heart movement, blood flow, or electric flow through various color expressions and image expressions such as two-dimensional images, three-dimensional images, or real-life images.
  • the computing device 100 synchronizes the electrocardiogram graph 310 and the heart animation data 320 so that the heart animation data 320 is played.
  • the computing device 100 extracts an ECG graph representing the ECG waveform from the ECG data using a pre-trained neural network model, and determines at least one of the start point, end point, or duration of the ECG waveform based on the ECG characteristics.
  • This computing device 100 may provide a user interface capable of transmitting ECG data and playing visualization content to a user terminal. Accordingly, the user can transmit the electrocardiogram data measured by the wearable device to the computing device 100 through the user terminal, and play visualization content based on the electrocardiogram characteristics to provide the user's heart condition information (cardiac activity, heart health, etc.) to the medical staff. Can be understood without help.
  • the user can transmit the electrocardiogram data measured by the wearable device to the computing device 100 through the user terminal, and play visualization content based on the electrocardiogram characteristics to provide the user's heart condition information (cardiac activity, heart health, etc.) to the medical staff. Can be understood without help.
  • the computing device 100 can calculate the cardiac axis (Ha) for each individual based on electrocardiogram data and electrocardiogram characteristics, and arranges the anatomical shape of the heart in the cardiac animation data 320 based on the calculated cardiac axis (Ha). can do.
  • FIG. 5 is a diagram illustrating electrocardiogram graphs measured in standard ECG and limb induction according to an embodiment of the present disclosure
  • FIG. 6 is a diagram illustrating electrode positions and heart axis in standard ECG induction according to an embodiment of the present disclosure
  • 7 is an example diagram illustrating the summed amplitude of the QRS waveform according to an embodiment of the present disclosure.
  • the computing device 100 calculates the heart axis (Ha) using characteristic information of the P wave, QRS complex, and T wave of the electrocardiogram graph extracted using a pre-trained neural network model.
  • the standard 12-lead electrocardiogram records the standard leads, limb leads, and precordial leads.
  • the standard leads and limb leads record the electrocardiogram in the front part of the heart
  • the thoracic leads record the electrocardiogram in the horizontal part of the heart. do.
  • FIG. 5 and 6 there are three standard limb leads (I, II, and III) that record the potential difference between the subject's left and right hands, the potential difference between the right hand and left foot, and the potential difference between the left foot and right hand.
  • the normal standards for the heart axis (Ha) using the QRS waveform vary, but in general, 0° to +90° is a normal heart axis, 0° to -90° is left axis deviation, +90° to +180° is right axis deviation, and -90° to -180° is called severe axis deviation.
  • the cardiac axis (Ha) using the waveform of the QRS complex is usually divided into four zones by lead I and lead aVF. If the sum of the QRS complex in both leads is upward, it is a normal electric axis, and if it is upward in lead I and lead aVF, it is a normal electric axis. If it is downward, it is left axis deviation. Also, if it is downward in lead I and upward in lead aVF, it can be said to be right axis deviation, and if it is downward in both leads, it can be said to be severe axis deviation.
  • the computing device 100 calculates the net amplitude of each of the standard leads and limb leads from the ECG data based on the ECG characteristics, and uses the summed amplitude of the standard leads and the summed amplitude of the limb leads as input variables. Based on Equation 1, the angle of the heart axis (Ha) can be calculated. For example, the computing device 100 may calculate the angle of the heart axis using the summed amplitude of induced I and induced aVF based on Equation 1 below. At this time, the summed amplitude may include a summed QRS amplitude (net QRS amplitude), a summed P amplitude (net P amplitude), and a summed T amplitude (net T amplitude).
  • the QRS complex is formed by ventricular depolarization and consists of three waves. 12
  • the QRS complex can be used to evaluate heart rate, cardiac electrical axis, and degree of rotation, as well as the presence of intraventricular conduction abnormalities.
  • the summed P amplitude and summed T amplitude may mean the highest point in the positive direction of the P wave and T wave, respectively. If there is a lowest point in the negative direction, such as P'/T', the summed P amplitude and the summed T amplitude have a positive value at the highest point in the positive direction and a negative value at the lowest point in the negative direction, respectively. It can be calculated by adding up.
  • the computing device 100 calculates the summed amplitude using the derived aVL and derived II pair, and adds 30 to the value. By adding up the degrees, you can calculate the angle of the heart axis. If the above-described value cannot be obtained, the computing device 100 calculates the summed amplitude using a pair of derived aVR and derived III, and the derived aVR may be a value multiplied by -1. Additionally, the computing device 100 may obtain the angle of the heart axis by adding 30 degrees to the value of the summed amplitude obtained using the pair of induction aVR and induction III .
  • the computing device 100 may generate heart animation data by arranging the anatomical shape of the heart based on the angle of the heart axis calculated in this way. Since people generally do not know that the axis of the heart is different for each person, showing the heart based on the axis of the heart has the advantage of adding interest and making it easier to identify a personalized heart shape. In addition, in the case of normal hearts, the angle of the heart axis is mostly within the range of 0 degrees to 90 degrees, so there is also the advantage that the user can easily predict the possibility of disease based on the appearance of the heart arranged with respect to the heart axis. .
  • heart animation data can be generated by placing the anatomical shape of the heart at 60 degrees.
  • FIG. 8 is a flowchart illustrating a method of providing visualization content based on ECG reading according to an embodiment of the present disclosure
  • FIG. 9 is a flowchart illustrating a synchronization process of an ECG graph and heart animation data according to an embodiment of the present disclosure.
  • FIG. 10 is an exemplary diagram illustrating heart animation data in which the electrocardiogram and the electrical flow of the heart are synchronized according to an embodiment of the present disclosure.
  • the computing device 100 may acquire ECG data from at least one ECG meter 10 (S10).
  • the ECG data may include biological information along with the ECG for each user.
  • the computing device 100 analyzes the ECG data using a pre-trained neural network model or various statistical techniques (S20) and extracts ECG features based on the ECG data for each user (S30).
  • the electrocardiogram is a unique signal for each individual because it varies depending on gender, age, heart location, and size. Accordingly, the computing device 100 may extract electrocardiogram features for the electrocardiogram data using a neural network model, and use biological information including at least one of age, gender, weight, and height along with the electrocardiogram data to provide information about the user. ECG reading information is estimated.
  • the neural network model learns ECG data for each ECG feature using a deep learning algorithm, and uses the learned model to derive ECG reading information, including the diagnosis of heart disease. Additionally, the neural network model may be learned based on the correlation between left ventricular systolic dysfunction and changes in characteristics such as electrocardiogram, gender, age, weight, and height. Specifically, the neural network model may be learned based on a learning dataset including electrocardiogram and heart disease diagnosis results and the correlation between various factors in the learning dataset.
  • the neural network model may be learned based on the electrocardiogram measured with 12 leads obtained from electrodes of an electrocardiogram measuring device connected to the human body. For example, an electrocardiogram can be measured with 12 leads of 10 seconds in length and stored at 500 points per second. Additionally, the neural network model can be learned based on partial information extracted from only 6 limb lead ECGs and a single lead (lead I) ECG among the 12 lead ECGs.
  • the neural network model can receive ECG data as input, extract ECG features, and output ECG reading information based on the extracted ECG features, using at least one convolutional neural network (CNN), batch normalization, It includes a ReLU activation function layer and may include a Dropout layer.
  • CNN convolutional neural network
  • the neural network model may include a fully connected layer in which biological information such as age, gender, height, and weight is input as auxiliary information.
  • the neural network model may include a neural network corresponding to each of a plurality of leads of ECG data. That is, the neural network model may include an individual neural network into which electrocardiograms measured with individual leads are input.
  • the neural network model according to an embodiment of the present invention may be configured in various ways based on the above-described examples.
  • the computing device 100 extracts an electrocardiogram graph representing the electrocardiogram waveform of the electrocardiogram data based on the extracted electrocardiogram features (S40), and visualizes it including heart animation data that is synchronized with the extracted electrocardiogram graph and visualizes the anatomical appearance of the heart. Content can be created (S50).
  • the computing device 100 selects one representative electrocardiogram among the standard 12 lead electrocardiograms, and displays the selected representative electrocardiogram and an anatomical view of the heart.
  • the heart animation data representing is synchronized and played.
  • the computing device 100 includes the peak (start and end point) positions, duration, interval between waveforms, length, amplitude, and wave shape for the P wave, QRS complex, and T wave of the ECG waveform during one heart beat.
  • Information is extracted, and the synchronization of heart movement, blood flow, or electrical flow is synchronized in the anatomical shape of the heart based on at least one of the extracted information.
  • the computing device 100 uses location information about the start and end points of the P wave to express the anatomical shape of the heart so that the blood filling the left ventricle and the right atrium moves to the ventricle. Specifically, the computing device 100 calculates the time interval between the starting point of the P wave and the ending point of the P wave and sets it as the time when the blood filling the atrium passes to the ventricle, so that the anatomical shape of the heart moves.
  • the computing device 100 sets the ventricle to be filled with blood during the anatomical heart in the characteristic section from the point where the P wave ends (end point) to the point where the QRS complex begins, and the point where the QRS complex starts ( In the characteristic section at the point where the QRS complex ends (end point), the anatomical heart is set to fill the atrium with blood while emptying the blood that fills the ventricle, and at the point where the T wave begins (start point), T In the characteristic section at the point where the wave ends (end point), the atrium is set to be filled with blood in the anatomical view of the heart.
  • the computing device 100 reproduces the interval and intensity of the electrical signal that causes the heart to beat in the electrocardiogram waveform of the electrocardiogram graph, and is synchronized with the electrocardiogram waveform to provide an anatomical appearance of the heart. It can show the process of blood circulation through the contraction and relaxation of the heart.
  • the computing device 100 may play heart animation data by synchronizing the electrocardiogram and the electrical flow within the heart.
  • the cardiac animation data is synchronized with the front part of the P wave to generate an electrical signal at the SA node, and is synchronized with the back part of the P wave, so the electrical signal generated at the SA node spreads through the left atrium and right atrium.
  • the electrical signal is briefly delayed in the AV node, in synchronization with the QRS complex, the electrical signal spreads from the AV node along the His bundle, left bundle, and right bundle, and in synchronization with the T wave, the ventricular excitation recovery period occurs.
  • the electrical signal is set to disappear.
  • FIG. 11 is a flowchart explaining a method of playing visualization content according to an embodiment of the present disclosure
  • FIG. 12 is an exemplary diagram showing an electrocardiogram graph according to an embodiment of the present disclosure
  • FIG. 13 is a diagram illustrating a process of synchronizing and playing back ECG graphs and heart animation data according to an embodiment of the present disclosure
  • FIG. 14 is a diagram illustrating a normal standard of an ECG waveform based on ECG characteristics according to an embodiment of the present disclosure. This is a drawing to explain.
  • the computing device 100 provides a user interface that can reproduce visualization content using a user terminal or an electrocardiogram monitor 10 that includes a display function.
  • the computing device 100 detects the start of playback of visualization content based on a user input such as a start button or touch (S110), it provides visualization content including an electrocardiogram graph and heart animation data.
  • the computing device 100 displays and provides a reference point or baseline on the electrocardiogram graph, and the reference point or baseline is used by a user such as touch and drag or click and drag.
  • heart animation data is provided so that the anatomical heart shape corresponding to the reference point or reference line of the electrocardiogram graph is displayed (S130).
  • the computing device 100 synchronizes the electrocardiogram graph and heart animation data to reproduce the interval and intensity of the electrical signal generated during the heartbeat of the electrocardiogram waveform, along with changes in the electrocardiogram graph.
  • the anatomical image of the heart is played in real time as heart condition information, including heart movement, blood flow, and electrical flow, changes from moment to moment (S140).
  • the computing device 100 moves the ECG waveform by clicking and dragging the background screen of the ECG graph if all 10 seconds of ECG waveforms cannot be played on one screen, and moves the ECG waveform. Provides cardiac animation data of the anatomical heart shape according to the movement of the waveform.
  • the computing device 100 may reproduce visualization content such that at least one of the color, brightness, saturation, or highlight effect of the anatomical heart shape changes according to changes in the electrocardiogram graph.
  • the computing device 100 identifies a waveform that is not included in the normal category based on the ECG characteristics and finds a waveform that is not included in the normal category (S150), the color of the waveform that is not included in the normal category;
  • An electrocardiogram graph can be generated and displayed by modifying at least one of the shape or form (S160).
  • the computing device 100 displays and provides visualization content showing the anatomical heart changed by the disease or abnormal heart movement or electrical flow. do.
  • the computing device 100 uses a neural model based on rule-based machine learning to detect ECG waveforms in the ECG graph that are outside the normal standard in the ECG reading information obtained by analyzing the ECG data.
  • the characteristics of the ECG waveform can be displayed in colors or patterns that are different from the normal ECG waveform.
  • the computing device 100 provides animated visualization content of the heart position or heart activity corresponding to abnormal results, so that users can increase their understanding of their own abnormal heart movement or disease and become more active in treatment. It can help you participate.
  • the computing device 100 controls the movement of the electrocardiogram waveform or anatomical heart shape corresponding to the generated user input event. Or, execute a content control operation to change a specific configuration of the electrocardiogram waveform or anatomical heart shape (S180).
  • the computing device 100 can display the path where electricity is generated, that is, the electric flow, in synchronization with the electrocardiogram graph, using a highlight effect, based on the voltage value of the electrocardiogram signal as well as the direction of the electric flow. You can also display the strength of electricity by brightness or size.
  • the computing device 100 is configured to display an electrocardiogram waveform that has a correlation with the specified location when a second event occurs based on a user input that specifies a predetermined location in the anatomical view of the heart while the visualization content is stopped.
  • Visualization content can be played. For example, when a user clicks and drags an electrical icon in the anatomical heart view, the electrical signals in the electrocardiogram graph are synchronized, causing the electrical signals to move along the general electrical flow path in the anatomical heart view. Allow it to move.
  • the computing device 100 displays the corresponding image of the first heartbeat electrocardiogram.
  • the ECG waveform of the part most similar to the part is played, and when two click events occur in succession, the ECG waveform corresponding to the second heartbeat ECG is played. That is, the computing device 100 can reproduce one of the ECG waveforms most closely associated with the heart region at a user's specific location.
  • the left atrium and right atrium are associated with the P wave
  • the left and right ventricles are associated with the QRS complex
  • the wall area that distinguishes the left and right ventricles is associated with the Q wave
  • the SA node is associated with the P wave. relationship appears high.
  • the computing device 100 may play visualization content so that the P wave most associated with left atrial activity is displayed.
  • the computing device 100 causes blood to fill in the selected atrial region, and generates an event corresponding to the activity of the selected atrial region.
  • Visualization content can be played so that the ECG waveform is displayed.
  • the present disclosure provides animated visualization content so that users without medical knowledge can easily understand it, thereby eliminating the need for a diagnosis by a professional medical staff to check the user's current heart health status, thereby reducing the cost of electrocardiogram diagnosis. savings can be achieved.
  • the present disclosure can calculate the heart axis for each user using electrocardiogram data, and provide personalized heart animation data by reflecting the calculated heart axis, allowing the user to intuitively observe the appearance of his or her heart. Users can check changes in cardiac activity over time without the help of medical staff.
  • This disclosure allows hospitals and health check-up centers to use visualization content when explaining heart health to patients, and the anatomical heart changes in real time before, during, and after exercise by linking with exercise equipment with an electrocardiogram measurement function. It can also be visualized and shown.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Cardiology (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Molecular Biology (AREA)
  • Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

La présente divulgation se rapporte à un procédé, un programme et un dispositif de fourniture de contenu de visualisation basé sur une lecture d'ECG, et concerne un procédé de fourniture de contenu de visualisation basé sur une lecture d'ECG, le procédé étant exécuté par un dispositif informatique comprenant au moins un processeur, et présentant les étapes suivantes : l'acquisition de données d'ECG ; l'extraction d'une caractéristique d'ECG à partir des données d'ECG ; et la génération, sur la base de la caractéristique d'ECG extraite, d'un contenu de visualisation comprenant un graphique d'ECG indiquant les formes d'ondes d'ECG des données d'ECG ainsi que des données d'animation cardiaque obtenues par visualisation de la forme anatomique du cœur, les données d'animation cardiaque étant synchronisées avec le graphique d'ECG et reproduites, et les informations sur l'état cardiaque contenant un des mouvements cardiaques, le flux sanguin et/ou le flux électrique pouvant être affichées.
PCT/KR2023/009857 2022-07-13 2023-07-11 Procédé, programme et dispositif de fourniture de contenu de visualisation basé sur une lecture d'ecg WO2024014838A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
KR20220086191 2022-07-13
KR10-2022-0086191 2022-07-13
KR1020230081780A KR20240009348A9 (ko) 2022-07-13 2023-06-26 심전도 판독에 기반한 시각화 콘텐츠를 제공하는 방법, 프로그램 및 장치
KR10-2023-0081780 2023-06-26

Publications (1)

Publication Number Publication Date
WO2024014838A1 true WO2024014838A1 (fr) 2024-01-18

Family

ID=89537028

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2023/009857 WO2024014838A1 (fr) 2022-07-13 2023-07-11 Procédé, programme et dispositif de fourniture de contenu de visualisation basé sur une lecture d'ecg

Country Status (1)

Country Link
WO (1) WO2024014838A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001008914A (ja) * 1999-06-30 2001-01-16 Dainippon Pharmaceut Co Ltd 状態量表示装置および状態量表示方法
JP2012000135A (ja) * 2010-06-14 2012-01-05 Hitachi Medical Corp マルチモダリティ動画像診断装置
JP5305616B2 (ja) * 2007-06-07 2013-10-02 株式会社東芝 検査データ処理装置及び検査システム
JP2019063527A (ja) * 2017-10-02 2019-04-25 バイオセンス・ウエブスター・（イスラエル）・リミテッドＢｉｏｓｅｎｓｅ Ｗｅｂｓｔｅｒ （Ｉｓｒａｅｌ）， Ｌｔｄ． 選択されたｅｃｇチャネルの対話型表示
JP2020124582A (ja) * 2014-03-25 2020-08-20 アクタス メディカル インクＡｃｕｔｕｓ Ｍｅｄｉｃａｌ，Ｉｎｃ． 心臓解析ユーザインタフェースのシステム及び方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001008914A (ja) * 1999-06-30 2001-01-16 Dainippon Pharmaceut Co Ltd 状態量表示装置および状態量表示方法
JP5305616B2 (ja) * 2007-06-07 2013-10-02 株式会社東芝 検査データ処理装置及び検査システム
JP2012000135A (ja) * 2010-06-14 2012-01-05 Hitachi Medical Corp マルチモダリティ動画像診断装置
JP2020124582A (ja) * 2014-03-25 2020-08-20 アクタス メディカル インクＡｃｕｔｕｓ Ｍｅｄｉｃａｌ，Ｉｎｃ． 心臓解析ユーザインタフェースのシステム及び方法
JP2019063527A (ja) * 2017-10-02 2019-04-25 バイオセンス・ウエブスター・（イスラエル）・リミテッドＢｉｏｓｅｎｓｅ Ｗｅｂｓｔｅｒ （Ｉｓｒａｅｌ）， Ｌｔｄ． 選択されたｅｃｇチャネルの対話型表示

Similar Documents

Publication Publication Date Title
Burnes et al. Noninvasive electrocardiogram imaging of substrate and intramural ventricular tachycardia in infarcted hearts
US20210038088A1 (en) System and method for client-side physiological condition estimations based on a video of an individual
CN107092771A (zh) 采用定期数据整合的个性化模型
EP4042445A1 (fr) Systèmes et procédés pour diagnostic électrocardiographique à nombre réduit de dérivations utilisant des réseaux neuronaux profonds et des systèmes à base de règles
CN109414242A (zh) 用于监测人类心脏的特定活动参数的方法和测量装置
WO2023022507A1 (fr) Procédé de génération d'électrocardiogrammes synchrones sur la base d'électrocardiogrammes asynchrones de deux dérivations
KR20200004725A (ko) 실시간 부정맥 종류 판단 방법 및 판단 장치
Qtaish et al. A Portable IoT-cloud ECG Monitoring System for Healthcare
Magjarević et al. Inspection and testing of electrocardiographs (ECG) devices
WO2024014838A1 (fr) Procédé, programme et dispositif de fourniture de contenu de visualisation basé sur une lecture d'ecg
WO2024014854A1 (fr) Procédé, programme et appareil pour fournir un contenu de visualisation sur la base de lectures d'électrocardiogramme
Gillette et al. Medalcare-xl: 16,900 healthy and pathological 12 lead ecgs obtained through electrophysiological simulations
Zia et al. Modeling consistent dynamics of cardiogenic vibrations in low-dimensional subspace
WO2021162488A2 (fr) Méthode de prédiction de maladie et appareil prévu à cet effet
Achi'ldiev et al. Gyrocardiography unit for non-invasive human diseases diagnosis
Gonzalez et al. Signal quality for rr interval prediction on wearable sensors
KR20240009348A (ko) 심전도 판독에 기반한 시각화 콘텐츠를 제공하는 방법,프로그램 및 장치
KR20240009349A (ko) 심전도 판독에 기반한 시각화 콘텐츠를 제공하는 방법,프로그램 및 장치
Cuadros et al. ECG multilead QT interval estimation using support vector machines
Gaigawali et al. Cloud based ECG monitoring and fibrillation detection for healthcare system
KR20220117632A (ko) 원격 상담 서비스 제공 방법 및 시스템
WO2024014864A1 (fr) Clavier fournissant une fonction de mesure d'électrocardiogramme, système le comprenant et procédé associé
EP4398262A1 (fr) Systèmes de diagnostic de cardiopathie structurelle basés sur des données d'électrocardiogramme
WO2024191200A1 (fr) Procédé, programme et dispositif pour identifier une fibrillation auriculaire potentielle sur la base d'un modèle d'intelligence artificielle
Jarvis Electrocardiogram 1: purpose, physiology and practicalities

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23839930

Country of ref document: EP

Kind code of ref document: A1