Method and device for providing electrocardiogram measurement guide

Abstract

Disclosed are a method, a program, and a device for providing an electrocardiogram measurement guide according to an embodiment of the present disclosure. The method may comprise the steps of: storing an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal; analyzing at least one of quality and diagnostic reliability for each stored electrocardiogram signal; and analyzing at least one of the quality and the diagnostic reliability and the stored measurement information to generate an electrocardiogram measurement guide for an electrocardiogram measurement target.

Description

Method and device for providing an electrocardiogram measurement guide

[0001] The content of the present disclosure relates to electrocardiogram measurement technology, and specifically to a method for generating and providing an electrocardiogram measurement guide for obtaining a high-quality electrocardiogram.

[0002]

[0003] Standard 12-lead electrocardiogram measurements performed in medical institutions are carried out by attaching electrodes to designated anatomical positions while the patient is at rest under the control of skilled medical personnel. Since electrocardiogram data acquired in this environment has a high signal-to-noise ratio and maintains consistent signal quality, it has the advantage of ensuring high accuracy and reliability when diagnosing heart disease and analyzing data using artificial intelligence or machine learning algorithms.

[0004] However, since the recently introduced portable device-based electrocardiogram measurement method allows users to perform measurements directly without the intervention of medical professionals, errors caused by user factors, such as poor electrode contact or inaccurate selection of measurement sites, occur frequently. In particular, due to the nature of detecting minute changes in bioelectric potential, electrocardiograms are sensitive to external interference factors such as body hair, skin dryness, and minute muscle movements. These factors cause serious noise within the data, which leads to the unreadability of analysis algorithms or exacerbates errors in analysis results.

[0005] Conventional signal processing technologies focus on removing noise through software filtering in the post-measurement stage; however, when the quality of the raw data itself is low, there are fundamental limitations in restoring high-quality signals due to information loss. Therefore, to enhance the accuracy of electrocardiogram analysis, it is essential to acquire high-quality signals from the measurement stage rather than relying on post-correction. In other words, there is an urgent need for technical means to monitor and actively control the user's measurement posture, electrode contact status, and surrounding measurement environment to acquire high-quality signals.

[0006]

[0007] The present disclosure aims to provide a method for providing a user-customized electrocardiogram measurement guide that minimizes signal distortion and noise ingress factors that may occur during the process of a user of a portable electrocardiogram measuring device measuring an electrocardiogram, thereby enabling the acquisition of a high-quality electrocardiogram that can be immediately utilized for disease diagnosis or analysis of health conditions.

[0008] However, the problems to be solved in this disclosure are not limited to those mentioned above, and other unmentioned problems may be clearly understood based on the description below.

[0009]

[0010] A method for providing an electrocardiogram measurement guide is disclosed according to one embodiment of the present disclosure for realizing the aforementioned objectives. The method may include the steps of: storing an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal; analyzing at least one of quality or diagnostic reliability for each of the stored electrocardiogram signal; and analyzing at least one of the quality or diagnostic reliability and the stored measurement information to generate an electrocardiogram measurement guide for the electrocardiogram measurement target.

[0011] Alternatively, the measurement information may include at least one of the wrist rotation angle of the electrocardiogram measurement target, the wearing site of the electrocardiogram measurement device, the wearing pressure of the electrocardiogram measurement device, the contact state of the electrodes of the electrocardiogram measurement device, the movement of the electrocardiogram measurement target, or the surrounding environment of the electrocardiogram measurement target.

[0012] Alternatively, the diagnostic reliability can be determined based on the distribution of artificial intelligence inference results based on the stored electrocardiogram signals.

[0013] Alternatively, the step of generating an electrocardiogram measurement guide for the electrocardiogram measurement target may include: a step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing area of ​​the electrocardiogram measurement device, signal distortion according to the wrist rotation angle, or sensitivity to movement, based on at least one of the quality or diagnostic reliability and the stored measurement information; and a step of generating an electrocardiogram measurement guide including at least one of the electrocardiogram measurement posture, measurement location, or measurement environment of the electrocardiogram measurement target based on the analysis result.

[0014] Alternatively, the step of deriving an analysis result regarding at least one of poor electrode contact according to the wearing site of the electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement may include: a step of calculating the statistical characteristics of electrode impedance and noise generation rate for each wearing site of the electrocardiogram measuring device to calculate an electrode contact index for each wearing site; and a step of comparing the contact index with a first reference value to determine whether there is suitability for contact with a specific wearing site or to determine an adjustment value for the adhesion strength of the electrode.

[0015] Alternatively, the step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing site of the electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement may include: a step of calculating a quality distribution by segment of the wrist rotation angle; and a step of identifying the rate of change of the quality distribution by segment of the wrist rotation angle to determine a specific angle segment as a distortion occurrence segment.

[0016] Alternatively, the step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing site of the electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement may include: a step of calculating a correlation coefficient between a movement indicator recorded through the electrocardiogram measuring device and a quality indicator of the electrocardiogram signal to calculate a quality attenuation slope according to the amount of change in movement; and a step of determining signal sensitivity according to the movement of the electrocardiogram measurement target by comparing the slope with a third reference value.

[0017] Alternatively, the method may further include the step of providing the generated electrocardiogram measurement guide to an electrocardiogram measurement device when a new electrocardiogram measurement is performed.

[0018] Alternatively, the method may further include the steps of: acquiring a new electrocardiogram signal; analyzing noise in the new electrocardiogram signal to determine whether the new electrocardiogram signal is readable; and, if the acquired new electrocardiogram signal is determined to be unreadable, analyzing measurement information corresponding to the new electrocardiogram signal based on the electrocardiogram measurement guide to generate measurement conditions for re-measurement.

[0019] According to another embodiment of the present disclosure for realizing the aforementioned objectives, a method for providing an electrocardiogram measurement guide is disclosed. The method may include the step of initiating a measurement trigger for acquiring an electrocardiogram signal; and the step of providing an electrocardiogram measurement guide for measuring the electrocardiogram signal as a user interface. In this case, the electrocardiogram measurement guide may be generated by analyzing at least one of the already accumulated quality or diagnostic reliability of the electrocardiogram signal and measurement information corresponding to the electrocardiogram signal.

[0020] According to one embodiment of the present disclosure for realizing the aforementioned objectives, a computing device for providing an electrocardiogram measurement guide is disclosed. The device may include a processor comprising at least one core; a memory comprising program codes executable on the processor; and a network unit. In this case, the processor may store an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal in the memory, analyze at least one of quality or diagnostic reliability for each of the stored electrocardiogram signal, and analyze at least one of the quality or diagnostic reliability with the stored measurement information to generate an electrocardiogram measurement guide for the electrocardiogram measurement target.

[0021]

[0022] The present disclosure can improve the purity and consistency of data in the long term by optimizing the guide based on the user's accumulated electrocardiogram profile, thereby blocking the user's unique signal distortion patterns, which are difficult to remove with general filtering, in advance during the measurement process.

[0023] The present disclosure can raise the quality of electrocardiogram (ECG) data for interpretation by establishing a standardized measurement environment through a user-customized guide. In other words, this prevents computational waste for processing invalid data under limited system resources and increases the efficiency of collecting valid data, thereby enhancing the technical efficiency and data reliability of the entire data processing system. Furthermore, as a result, it provides technical advantages that minimize the misinterpretation rate in diagnosis using ECG signals and deepen diagnostic precision for specific individuals.

[0024]

[0025] FIG. 1 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0026] FIG. 2 is a sequence diagram illustrating the process of providing an electrocardiogram measurement guide according to one embodiment of the present disclosure.

[0027] FIG. 3 is a sequence diagram illustrating the process of utilizing an electrocardiogram measurement guide according to one embodiment of the present disclosure.

[0028] FIG. 4 is a sequence diagram illustrating the process of utilizing an electrocardiogram measurement guide according to another embodiment of the present disclosure.

[0029] FIG. 5 is a flowchart illustrating a method for generating an electrocardiogram measurement guide according to one embodiment of the present disclosure.

[0030] FIG. 6 is a flowchart illustrating a method of providing an electrocardiogram measurement guide through a user interface according to one embodiment of the present disclosure.

[0031]

[0032] Embodiments of the present disclosure are described below with reference to the attached drawings so that those skilled in the art (hereinafter, those skilled in the art) can easily implement them. The embodiments presented in the present disclosure are provided to enable those skilled in the art to use 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 embodied in various different forms and is not limited to the embodiments below.

[0033] Throughout the specification of the present disclosure, identical or similar reference numerals refer to identical or similar components. Additionally, to clearly explain the present disclosure, reference numerals in the drawings that are unrelated to the description of the present disclosure may be omitted.

[0034] The term “or” as used in this disclosure is intended to mean an implicit “or” rather than an exclusive “or.” That is, unless otherwise specified in this disclosure or its meaning is not clear from the context, “X uses A or B” should be understood to mean one of the natural implicit substitutions. For example, unless otherwise specified in this disclosure or its meaning is not clear from the context, “X uses A or B” may be interpreted as X using A, X using B, or X using both A and B.

[0035] The term “and / or” as used in this disclosure should be understood to refer to and include all possible combinations of one or more of the enumerated related concepts.

[0036] The terms “comprising” and / or “comprising” as used in this disclosure should be understood to mean the presence of certain features and / or components. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, other components and / or combinations thereof.

[0037] Where not otherwise specified in the present disclosure or where it is not clear from the context that the singular form indicates, the singular should generally be interpreted as including “one or more.”

[0038] The term “the N (N is a natural number)” used in this disclosure may be understood as an expression used to distinguish the components of this disclosure from one another according to certain criteria, such as functional perspectives, structural perspectives, or convenience of explanation. For example, components performing different functional roles in this disclosure may be distinguished as a first component or a second component. However, components that are substantially identical within the technical scope of this disclosure but must be distinguished for the convenience of explanation may also be distinguished as a first component or a second component.

[0039] The term “acquisition” as used in this disclosure may be understood to mean not only receiving data through a wired or wireless communication network with an external device or system, but also generating data internally within the device in an on-device form.

[0040] Meanwhile, the terms "module" or "unit" used in this disclosure may be understood as 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. In this case, "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, in a narrow sense, "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 procedure implemented through software execution, or a set of instructions for program execution. Furthermore, in a broad sense, "module" or "unit" may refer to the computing device itself that constitutes the system, or an application executed on the computing device. However, since the above-described concept is merely an example, the concepts of "module" or "part" may be defined in various ways within the scope understandable to those skilled in the art based on the contents of this disclosure.

[0041] As used in this disclosure, the term "model" 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 regarding a processing process to solve a specific problem. For example, a neural network "model" may refer to an overall system implemented as a neural network that possesses problem-solving capabilities through learning. In this case, the neural network may possess problem-solving capabilities by optimizing parameters connecting nodes or neurons through learning. A neural network "model" may include a single neural network or a set of neural networks composed of multiple neural networks.

[0042] The term “control graphic” as used in this disclosure can be understood as a graphic object that executes a command to produce a visible result when manipulating a user interface. In other words, “control graphic” can be understood as a basic unit constituting a user interface, which displays content to be provided to the user or enables the user to operate it.

[0043] The explanation of the foregoing terms is intended to aid in understanding the present disclosure. Accordingly, it should be noted that unless a foregoing term is explicitly stated as a matter limiting the content of the present disclosure, it is not to be used in the sense of limiting the technical concept of the content of the present disclosure.

[0044] FIG. 1 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0045] A computing device (100) according to one embodiment of the present disclosure may be a hardware device or part of a hardware device that performs comprehensive processing and computation of data, or it may be a software-based computing environment connected to a communication network. For example, the computing device (100) may be a server that performs intensive data processing functions and is an entity that shares resources, or it may be a client that shares resources through interaction with the server. Additionally, 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 merely one example regarding 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.

[0046] Referring to FIG. 1, a computing device (100) according to one embodiment of the present disclosure may include a processor (110), memory (120), a network unit (130), and an input / output unit (140). However, since FIG. 1 is merely an example, the computing device (100) may include other configurations for implementing a computing environment. Additionally, only some of the disclosed configurations may be included in the computing device (100). For example, if the computing device (100) is a client, the computing device (100) may include all of the disclosed configurations. If the computing device (100) is a server, the computing device (100) may include the remaining configurations among the disclosed configurations, excluding the input / output unit (140).

[0047] A processor (110) according to one embodiment of the present disclosure may be understood as a constituent unit comprising hardware and / or software for performing computing operations. For example, the processor (110) may process commands generated as a result of user interaction through a user interface. Additionally, the processor (110) may read a computer program to perform operations for data acquisition and analysis, and 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. A processor (110) for performing such data processing and operations 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). Since the above-described type of processor (110) is merely an example, the type of processor (110) can be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0048] The processor (110) can generate an electrocardiogram measurement guide by analyzing electrocardiogram signals and measurement information obtained in synchronization with the electrocardiogram signals. Here, the measurement information can be understood as information related to the subject's posture, electrode attachment location, and surrounding environmental conditions at the time of electrocardiogram measurement. When the electrocardiogram signal for the subject and the corresponding measurement information are stored, the processor (110) can generate an electrocardiogram measurement guide tailored to the subject's anatomical characteristics, measurement habits, etc. by analyzing the stored signals and information in conjunction. When the electrocardiogram signal for the subject and the corresponding measurement information are accumulated in a time series, the processor (110) can generate a customized measurement guide more optimized for each individual subject based on the electrocardiogram profile accumulated for each electrocardiogram measurement subject. For example, the processor (110) can analyze at least one of the quality or diagnostic reliability for each electrocardiogram signal for each measurement cycle. The quality of the electrocardiogram signal can be expressed as a signal quality index (SQI) or a noise index. The diagnostic reliability of an electrocardiogram signal can be understood as the statistical confidence of the artificial intelligence's inference result regarding the electrocardiogram signal. The processor (110) can generate suggestion information for optimal signal acquisition by analyzing the correlation between at least one of the quality or diagnostic reliability of the electrocardiogram signal for each measurement round and the measurement information for each measurement round. The suggestion information may include adjusting electrode positions to specific anatomical locations, suggesting an environment with minimized interference, etc. The processor (110) can structure the suggestion information to generate an electrocardiogram measurement guide optimized for a specific subject.

[0049] The processor (110) can generate a user interface for electrocardiogram measurement and reading. The user interface may include control graphics for outputting information necessary to perform electrocardiogram measurement and reading, receiving input based on user operation, or implementing functions necessary for electrocardiogram measurement and reading. For example, the user interface may include control graphics representing an electrocardiogram measurement guide to induce electrocardiogram measurement. The user interface may include control graphics that visualize location information where electrodes should be attached for electrocardiogram measurement, the progress of the electrocardiogram measurement, and the waveform of the electrocardiogram signal being measured. Such control graphics may have their visual representation or state changed by user operation or during the implementation of specific functions.

[0050] A memory (120) according to one embodiment of the present disclosure may be understood as a configuration unit comprising hardware and / or software for storing and managing data processed by a computing device (100). That is, the memory (120) may store data of any form generated or determined by a processor (110) and data of any form received by a network unit (130). 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, RAM (random access memory), SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, a magnetic disk, and an optical disk. Additionally, the memory (120) may include a database system that controls and manages data in a predetermined system. Since the above-described type of memory (120) is merely an example, 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.

[0051] The memory (120) can structure and organize data, combinations of data, and program code executable by the processor (110) that are necessary for the processor (110) to perform calculations. For example, the memory (120) can store medical data received through the network unit (130) described later. The memory (120) can store program code that stores rules for processing medical data, program code that causes a neural network model to receive medical data and perform learning, program code that causes a 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.

[0052] A network unit (130) according to one embodiment of the present disclosure may be understood as a configuration unit that transmits and receives data through any known form of wired or wireless communication system. For example, the network unit (130) may perform data transmission and reception using wired or wireless communication systems 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), ultra-wide-band wireless communication, ZigBee, radio frequency (RF) communication, wireless LAN, wireless fidelity (Wi-Fi), near field communication (NFC), or Bluetooth. Since the communication systems described above are merely examples, wired or wireless communication systems for data transmission and reception of the network unit (130) may be applied in various ways other than those described above.

[0053] The network unit (130) can receive data necessary for the processor (110) to perform calculations through wired or wireless communication with any system or any client. Additionally, the network unit (130) can transmit data generated through the calculations of the processor (110) through wired or wireless communication with any system or any client. For example, the network unit (130) can receive biometric data through communication with a database within a hospital environment, a cloud server performing tasks such as standardization of medical data, a client such as a smart watch, or a medical computing device. The network unit (130) can transmit output data of a neural network model, intermediate data derived during the calculation process of the processor (110), processed data, etc., through communication with the aforementioned database, server, client, or computing device.

[0054] An input / output unit (140) according to one embodiment of the present disclosure may be understood as a configuration unit including hardware and / or software for implementing a user interface. That is, the input / output unit (140) can visualize and output data of any form generated or determined by the processor (110) and data of any form received by the network unit (130). In addition, the input / output unit (140) can receive user input that generates commands to be transmitted to any system or any client, etc., connected via wired or wireless communication with the processor (110) and the computing device (100). For example, the input / output unit (140) may include a display module capable of outputting visualized information or implementing a touch screen, such as a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, a 3D display, etc. Additionally, the input / output unit (140) may include an input module capable of recognizing actions such as user motion, voice, etc., such as a camera, microphone, keyboard, and mouse. Since the above-described modules are merely examples, the modules included in the input / output unit (140) may be configured in various ways within a range understandable to those skilled in the art based on the contents of this disclosure, in addition to the above-described examples.

[0055] The input / output unit (140) implements a user interface and can output graphics generated through the processor (110) or receive user input generated by user operation and transmit it to the processor (110). For example, the input / output unit (140) can output graphics regarding an electrocardiogram measurement guide generated through the processor (110), graphics for receiving user input regarding a specific function, graphics for providing information, etc., in a specific area of ​​the user interface. Additionally, the input / output unit (140) can receive user input regarding graphics output in a specific area of ​​the user interface. In this case, user input regarding a specific graphic can be understood as an input signal generated by an operation in which the user selects a specific graphic through the input / output unit (140). Additionally, the operation of selecting a specific graphic may refer to actions that the user can perform through the input / output unit (140), such as clicking, double-clicking, or hovering over the specific graphic. The input / output unit (140) receives user input and transmits it to the processor (110), thereby enabling the operation of the device to be performed based on the user's control.

[0056] FIG. 2 is a sequence diagram illustrating the process of providing an electrocardiogram measurement guide according to one embodiment of the present disclosure.

[0057] An electrocardiogram measurement system according to one embodiment of the present disclosure may include a client (200) that acquires an electrocardiogram signal from a user and provides an interface, and a server (200) that analyzes data received from the client (200). The client (200) may include a hardware configuration that receives data by communicating with a measurement device that collects the user's electrocardiogram signal, or directly measures the electrocardiogram signal. The server (300) may include a hardware configuration that is connected to the client via a network and can independently process large-scale computations such as database management, generation of measurement guides, and operation of diagnostic algorithms. The client (200) and the server (300) may include some or all of the configurations of the computing device (100) of FIG. 1 described above.

[0058] Referring to FIG. 2, a client (200) according to one embodiment of the present disclosure can obtain an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal (S110). When an electrocardiogram measurement trigger is initiated according to a user command input through an interface provided by the client (200), the client (200) can generate a command for electrocardiogram measurement and receive the electrocardiogram signal and measurement information synchronized with the signal through communication with a separate measurement device. The client (200) may also generate an electrocardiogram signal and synchronized measurement information by directly performing an operation for electrocardiogram measurement through electrodes. Here, the measurement information may include at least one of the information examples such as [Table 1] below.

[0059] Measurement Information Measurement Method Wrist rotation angle of the ECG subject Position and angle estimation technology based on 3-axis accelerometer and gyroscope Wearing site of the ECG device (upper or lower wrist, etc.) Wearing site identification technology based on gravity direction vector analysis, electrode signal distribution analysis, or sensor fusion Wearing pressure of the ECG device Contact state detection technology based on electrode contact impedance measurement, pressure sensor, or capacitance Contact state of the ECG device electrodes Movement of the ECG subject Movement speed and movement pattern analysis technology based on 3-axis accelerometer, gyroscope, and GPS Microphone-based noise level (decibels) measurement or ambient environment analysis technology based on environmental sensors Ambient environment of the ECG subject

[0060] When the measurement of the electrocardiogram signal is completed, the client (200) can convert the measured analog electrocardiogram signal into digital data and configure it into a data packet of a standard that the server (300) can process, and transmit it through the network (S120). For convenience of explanation, the digital data processed by the server (300) will also be referred to as the electrocardiogram signal.

[0061] When the server (300) receives an electrocardiogram signal from the client (200), it can store the electrocardiogram signal and the corresponding measurement information (S130). Since the server (300) can communicate with multiple clients, it can identify the user by checking the unique identifier within the packet transmitted from a specific client. Furthermore, the server (300) can manage signals and information by user by allocating an independent data storage space for each individual user and performing logically separated indexing. The server (300) can accumulate and store the electrocardiogram signal and measurement information received from the client (200) in a time-series manner. Additionally, the server (300) can build and update user profiles based on the accumulated data.

[0062] The server (300) can analyze at least one of quality or diagnostic reliability for each stored electrocardiogram signal (S140). The server (300) can analyze at least one of quality or diagnostic reliability for the corresponding signal whenever an electrocardiogram signal is stored. If electrocardiogram signals are stored cumulatively in a time series, the server (300) may analyze at least one of quality or diagnostic reliability for the entire stored signal on a per-cycle basis when the accumulated storage amount reaches a threshold value. The server (300) can evaluate the quality of the electrocardiogram signal using a quality index such as SQI or a noise index. The server (300) can evaluate the diagnostic reliability of the electrocardiogram signal based on the distribution of artificial intelligence inference results based on the stored electrocardiogram signals. Specifically, the server (300) can input the stored electrocardiogram signal into a pre-trained artificial intelligence model to produce an inference result. At this time, the artificial intelligence model may be a model trained to output the probability of occurrence of a specific disease based on training data in which the electrocardiogram signal and a specific disease are labeled. At this time, the learning may be supervised learning that updates the parameters constituting the model by performing backpropagation using a loss function such as cross-entropy. When the artificial intelligence inference results are derived, the server (300) can calculate the variance or entropy of the output distribution of the artificial intelligence model and calculate the diagnostic reliability of the electrocardiogram signal.

[0063] The server (300) can generate an electrocardiogram measurement guide for an electrocardiogram measurement target by analyzing at least one of the quality or diagnostic reliability of the electrocardiogram signal and measurement information matching the signal (S150). The server (300) can generate an electrocardiogram measurement guide by analyzing what value the measurement information represents and how it changes according to the quality or diagnostic reliability of the electrocardiogram signal. Based on at least one of the quality or diagnostic reliability of the electrocardiogram signal and measurement information matching the electrocardiogram signal, the server (300) can derive an analysis result regarding at least one of electrode contact failure according to the wearing location of the electrocardiogram measurement device, signal distortion according to the wrist rotation angle, or sensitivity to movement. Then, based on the analysis result, the server (300) can generate an electrocardiogram measurement guide including at least one of the electrocardiogram measurement posture, measurement location, or measurement environment of the electrocardiogram measurement target. That is, the server (300) can structure the analysis results regarding at least one of poor contact of the electrode, signal distortion due to wrist rotation angle, or sensitivity of movement to generate a guide including a measurement method specialized for the electrocardiogram measurement target.

[0064] Specifically, the server (300) can calculate the statistical characteristics of the electrodes for each wearing site of the electrocardiogram measuring device and the noise generation rate for each wearing site, and based on this, calculate the contact index of the electrodes for each wearing site. For example, the electrode contact index for each wearing site can be defined as the following quantified numerical value.

[0065] Contact indicator of the first area (e.g., upper wrist): Average impedance value X, noise generation rate 60%

[0066] Contact indicator of the second area (e.g., lower wrist): Average impedance value Y(Y <X), 노이즈 발생률 15%

[0067] The server (300) can compare the calculated contact index with a preset first reference value to determine whether the contact of a specific wearing area is suitable or to determine an adjustment value for the adhesion strength of the electrode. Additionally, the server (300) can generate first guide information that suggests an optimal wearing area and contact strength by combining information on the area determined to have poor contact and information on the adjustment value for adhesion strength. For example, the average impedance value of the first reference value is Z(Y <Z<X)이고, 노이즈 발생률은 20%로 설정된 경우, 서버(300)는 상대적으로 제 1 기준 값을 초과하는 손목 상부를 접촉 불량 부위로 결정하고, 손목 하부로의 위치 변경을 권고하는 제 1 가이드 정보를 생성할 수 있다. 만약 제 1 기준 값의 임피던스 평균값이 Z'(Z'<Y)로 설정되었다면, 서버(300)는 손목 상부의 접촉 불량 판정과 동시에 손목 하부의 임피던스 역시 기준치를 상회하는 것으로 판단할 수 있다. 이 경우, 서버(300)는 측정 부위를 손목 하부로 변경할 것과 더불어 전극의 밀착 압력을 조정 수치에 대응하는 단계만큼 높일 것을 지시하는 복합적인 제1 가이드 정보를 생성할 수 있다.

[0068] The server (300) can calculate the quality distribution of the wrist rotation angle by segment. For example, the quality distribution of the wrist rotation angle by segment can be defined as a quantified value from multiple electrocardiogram signals measured within the rotational range of motion of the wrist as follows.

[0069] Quality distribution within the first angle range (e.g., ±15°): SQI mean 0.85

[0070] Quality distribution within the second angle range (e.g., ±20°): SQI mean 0.80

[0071] Quality distribution within the third angle range (e.g., ±25°): SQI mean 0.52

[0072] The server (300) can identify the rate of change of the quality distribution by segment of the calculated wrist rotation angle and determine a specific angle segment where the validity of the signal rapidly deteriorates as a distortion occurrence segment. Then, the server (300) can generate second guide information that suggests a wrist rotation direction and posture that can maintain optimal signal quality by avoiding the identified segment. For example, the server (300) can identify that the amount of quality change when transitioning from the second angle range to the third angle range is greater than the amount of quality change when transitioning from the first angle range to the second angle range, based on a preset second reference value. Based on this identification result, the server (300) can determine the segment between the second and third angle ranges where an inflection point of signal quality occurs as a distortion occurrence segment. Finally, the server (300) can generate second guide information including correction direction and posture information that induces the user's wrist angle to be maintained within the first angle range that guarantees optimal quality.

[0073] The server (300) can calculate the correlation coefficient between the movement indicator recorded through the electrocardiogram measuring device and the quality indicator of the electrocardiogram signal to calculate the slope of quality decay according to the amount of change in movement. For example, the movement indicator may be a quantified value such as acceleration RMS (root mean square), and the slope of quality decay can be expressed as the range of variation of the quality index according to the amount of change in unit movement as follows.

[0074] Quality Damping Slope: 3.0 (= 30% decrease in SQI for every 0.1g increase in RMS acceleration)

[0075] The server (300) can determine the signal sensitivity according to the movement of the subject by comparing the calculated inclination with a pre-set third reference value. Subsequently, the server (300) can generate third guide information that suggests an optimal measurement posture and surrounding environment based on the determined sensitivity level. For example, if the third reference value is set to decrease SQI by 20% when the acceleration RMS increases by 0.1g, the server (300) can classify the subject whose calculated inclination exceeds the third reference value as a movement-sensitive group. Based on this judgment result, the server (300) can generate third guide information that instructs the subject to maintain a fixed state with their arm resting on a stable plane (e.g., a table) or recommends measurement in a static environment where physical activity is completely excluded.

[0076] The server (300) can generate an electrocardiogram measurement guide to be finally provided to an electrocardiogram measurement subject by cross-referencing the first guide information (contact area and intensity), the second guide information (wrist rotation angle and posture), and the third guide information (movement sensitivity and measurement environment). Specifically, if the analysis result of a specific subject simultaneously indicates electrode contact failure and fine movement sensitivity, the server (300) can generate a customized message for the specific subject by combining the first guide information and the third guide information. At this time, the server (300) can construct the message by reflecting a specific error pattern identified based on the accumulated electrocardiogram profile. For example, it can generate a guide message based on statistical evidence such as, "Since noise caused by wrist rotation occurred in more than 70% of the last N measurements, please keep your wrist horizontal during this measurement."

[0077] When the generation of the electrocardiogram measurement guide (S150) is completed, the server (300) can transmit the electrocardiogram measurement guide to the client via the network (S160). The server (300) can pack the data containing the electrocardiogram measurement guide into an optimized format and transmit it, taking into account the client's communication environment and performance. By providing the structured integrated guide to the client (200) as described above, the server (300) can ensure the repeatability of data collection and maximize the reliability of remote diagnosis.

[0078] FIG. 3 illustrates an embodiment of the present disclosure utilizing an electrocardiogram measurement guide generated through FIG. 2. Among the steps of FIG. 3, specific descriptions of steps that can be replaced by the description of FIG. 2 will be omitted below.

[0079] Referring to FIG. 3, the client (200) can initiate an electrocardiogram measurement trigger based on a user command entered through a user interface for electrocardiogram measurement and diagnosis (S210). For example, if the client (200) is a smart watch capable of electrocardiogram measurement, the client (200) can provide a control graphic to the user to start the electrocardiogram measurement through the input / output section of the smart watch. When user input is detected through the graphic, the client (200) can generate an electrocardiogram measurement trigger signal and simultaneously perform tasks to proceed with the electrocardiogram measurement. Then, the client (200) can transmit the electrocardiogram measurement trigger signal to the server (300) via a network (S220).

[0080] The server (300) receives an electrocardiogram measurement trigger signal transmitted from the client (200), verifies the unique identifier or user account information of the client (200), and identifies the user. Then, the server (300) can identify an electrocardiogram measurement guide that matches the identified user in the database (S230). If there is no electrocardiogram measurement guide that matches the recognized user, the server (300) can proceed with the task of creating an electrocardiogram measurement guide for the user as in the process of FIG. 2 above. Once an electrocardiogram measurement guide is identified, the server (300) can transmit the guide to the client (200) via the network.

[0081] The client (200) can output an electrocardiogram measurement guide transmitted from the server (300) through an interface (S250). The client (200) can configure control graphics output through the interface based on data corresponding to the electrocardiogram measurement guide and provide them to the user. For example, the client (200) can generate a guide message containing a suggestion for at least one of the measurement site, posture, or environment and output it in a visual or auditory form. The client (200) can also configure and output graphics that visualize at least one of the measurement site, posture, or environment. In addition to these methods, the client (200) can output the electrocardiogram measurement guide in the form of an interface that the user can intuitively understand.

[0082] When a user completes an electrocardiogram measurement according to the electrocardiogram measurement guide, the client (200) can obtain an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal (S260). Since a personalized guide is provided in advance, the user can proceed with the measurement in a state optimized for their physical characteristics. Consequently, the client (200) can obtain a high-quality electrocardiogram signal with minimized noise within a single session without re-measurement. In other words, by providing an electrocardiogram measurement guide, the present disclosure can drastically reduce measurement fatigue on the user's side, while simultaneously preventing database waste caused by low-quality data and maximizing data availability on the system resource side.

[0083] FIG. 4 illustrates another embodiment of the present disclosure utilizing the electrocardiogram measurement guide generated through FIG. 2. Among the steps of FIG. 4, specific descriptions of steps that can be replaced by the descriptions of FIG. 2 and FIG. 3 will be omitted below.

[0084] When a client (200) acquires electrocardiogram signal and measurement information (S310) and transmits it to a server (300) (S320), the server (300) can evaluate the quality of the electrocardiogram signal transmitted by the client (200) and quantitatively analyze the readability of the electrocardiogram signal (S330). The server (300) can evaluate the quality of the electrocardiogram signal by calculating quality indices such as SQI and signal-to-noise ratio. Then, the server (300) can determine whether the index derived from the evaluation result exceeds a threshold value for valid reading. If the quality evaluation index exceeds the threshold value, the server (300) can determine that the electrocardiogram signal is readable. Then, the server (300) can perform reading on the signal (S340). At this time, reading can be understood as a task of diagnosing the likelihood of a specific disease developing using an artificial intelligence model. If the quality evaluation index is below a threshold value, the server (300) may determine that the electrocardiogram signal is an unreadable signal. In this case, the server (300) may generate measurement conditions for re-measurement based on the electrocardiogram signal and measurement information transmitted from the client (200) (S350).

[0085] Specifically, the server (300) can generate measurement conditions for re-measurement by comparing a previously generated electrocardiogram measurement guide with a signal determined to be unreadable and the corresponding measurement information. For example, if the optimal wrist rotation angle suggested in the guide was a first angle range (e.g., ±15°), but the angle extracted from the actual measurement information was identified as a third angle range (e.g., ±25°), the server (300) can generate specific numerical-based conditions to correct physical displacement, such as "rotate 10 degrees clockwise from the current angle," rather than simply indicating poor posture. In this way, the server (300) can generate measurement conditions for re-measurement by comparing the optimal state and the current state and suggesting a specific correction direction. Once measurement conditions for re-measurement are generated in this manner, the server (300) can transmit the conditions to the client (200) via a network (S360).

[0086] The client (200) can output measurement conditions for re-measurement transmitted from the server (300) through an interface (S370). At this time, the client (200) can dynamically vary the interface components according to the form of the measurement conditions. For example, if the measurement conditions are text messages, the client (200) can output the text in a visual form or an auditory form such as voice guidance.

[0087] When the user completes the electrocardiogram measurement according to the measurement conditions for re-measurement, the client (200) can re-acquire the electrocardiogram signal and the measurement information corresponding to the electrocardiogram signal (S380). This re-acquisition process can implement a mechanism in which the system monitors the user's incomplete measurement behavior in real time and immediately provides feedback equal to the error. In other words, the present disclosure enables easy self-calibration in the measurement process performed by a general user who is not a measurement expert, thereby easily overcoming the limitations of electrocardiogram measurement devices that are susceptible to exposure to environmental noise. That is to say, the present disclosure can improve the overall efficiency of the electrocardiogram reading system by minimizing trial and error in data acquisition.

[0088] Meanwhile, according to another embodiment of the present disclosure, the system may have a variable computation structure that allows the client (200) to directly perform at least some of the computation functions of the server (300) depending on the hardware resource status of the client (200). That is, depending on the hardware specifications of the client (200), the data processing process for generating an electrocardiogram measurement guide may not be entrusted to the server, and at least some of it may be processed at the client (200). In other words, if the hardware specifications of the client (200) can handle as much computational load as the server (300), the configurations mentioned as the execution steps of the server in FIGS. 2 to 4 can all be performed at the client (200) without passing through the server (300).

[0089] FIG. 5 is a flowchart illustrating a method for generating an electrocardiogram measurement guide according to one embodiment of the present disclosure. Among the steps of FIG. 5, specific descriptions of steps that can be replaced by the descriptions of FIG. 2 to 4 will be omitted below.

[0090] Referring to FIG. 5, a computing device (100) according to one embodiment of the present disclosure may store an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal (S410). At this time, the measurement information may include at least one of the wrist rotation angle of the electrocardiogram measurement target, the wearing part of the electrocardiogram measurement device, the wearing pressure of the electrocardiogram measurement device, the contact state of the electrodes of the electrocardiogram measurement device, the movement of the electrocardiogram measurement target, or the surrounding environment of the electrocardiogram measurement target.

[0091] The computing device (100) can analyze at least one of quality or diagnostic reliability for each stored electrocardiogram signal (S420). At this time, the diagnostic reliability can be determined based on the distribution of artificial intelligence inference results based on the stored electrocardiogram signals.

[0092] The computing device (100) can generate an electrocardiogram measurement guide for an electrocardiogram measurement target by analyzing at least one of quality or diagnostic reliability and stored measurement information (S430). Based on at least one of quality or diagnostic reliability and stored measurement information, the computing device (100) can derive an analysis result regarding at least one of electrode contact failure according to the wearing area of ​​the electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement. Specifically, the computing device (100) can calculate the contact index of the electrode according to the wearing area by calculating the statistical characteristics of the electrode impedance and the noise generation rate for each wearing area of ​​the electrocardiogram measuring device. The computing device (100) can determine whether the contact of a specific wearing area is suitable or determine an adjustment value for the adhesion strength of the electrode by comparing the contact index with a first reference value. In addition, the computing device (100) can calculate the quality distribution for each section of the wrist rotation angle. The computing device (100) can identify the rate of change of the quality distribution by segment of the wrist rotation angle and determine a specific angle segment as a distortion occurrence segment. Additionally, the computing device (100) can calculate a quality attenuation slope according to the amount of change in movement by calculating a correlation coefficient between the movement indicator recorded through the electrocardiogram measuring device and the quality indicator of the electrocardiogram signal. The computing device (100) can determine the signal sensitivity according to the movement of the electrocardiogram measurement subject by comparing the slope with a third reference value. Based on such analysis results, the computing device (100) can generate an electrocardiogram measurement guide that includes at least one of the electrocardiogram measurement posture, measurement location, or measurement environment of the electrocardiogram measurement subject.

[0093] When a new electrocardiogram measurement is performed, the computing device (100) can provide an electrocardiogram measurement guide generated via S430 to the electrocardiogram measuring device. When a new electrocardiogram signal is acquired, the computing device (100) can analyze the noise of the new electrocardiogram signal to determine whether the new electrocardiogram signal is readable. And, if it is determined that the acquired new electrocardiogram signal is unreadable, the computing device (100) can analyze measurement information corresponding to the new electrocardiogram signal based on the electrocardiogram measurement guide generated via S430 to generate measurement conditions for re-measurement. The computing device (100) can provide the measurement conditions for re-measurement to the electrocardiogram measuring device. Meanwhile, depending on the case, the computing device (100) may directly output the electrocardiogram measurement guide or the measurement conditions for re-measurement through the input / output unit (140).

[0094] FIG. 6 is a flowchart illustrating a method of providing an electrocardiogram measurement guide through a user interface according to one embodiment of the present disclosure. Among the steps of FIG. 6, specific descriptions of steps that can be replaced by the descriptions of FIG. 2 to 4 will be omitted below.

[0095] Referring to FIG. 6, a computing device (100) according to one embodiment of the present disclosure may initiate a measurement trigger for acquiring an electrocardiogram signal (S510). This trigger may be generated not only by explicit input from a user through a user interface, but also automatically when a sensor hub embedded in the device detects a change in the bioimpedance of the subject and determines that a valid electrode contact has occurred. When the trigger is initiated, the computing device (100) may perform the task of preparing the most suitable measurement environment by recognizing the user's previous data records before the actual measurement begins.

[0096] The computing device (100) can provide an electrocardiogram measurement guide for measuring electrocardiogram signals as a user interface (S520). The computing device (100) can provide an electrocardiogram measurement guide optimized to match the unique characteristics of the identified object as a user interface, either visualized or audibly. The guide provided at this time can be configured in the form of a dynamic indicator that is linked in real-time with the signal acquired from the computer device (100). For example, the user interface can map and display electrode attachment points according to the guide on a 3D model. Additionally, if the current measurement posture deviates from the recommended range of the guide, the user interface can induce immediate correction through a change in screen color or feedback. Through this user interface configuration, the computing device (100) can create an intelligent measurement environment that allows the user to preemptively avoid errors that are likely to occur in the corresponding measurement.

[0097] The various embodiments of the present disclosure described above may be combined with additional embodiments and modified to the extent understandable to those skilled in the art in light of the detailed description above. The embodiments of the present disclosure are illustrative in all respects and should be understood as not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form. Accordingly, all modifications or variations derived from the meaning, scope, and equivalents of the claims of the present disclosure should be interpreted as being included within the scope of the present disclosure.

Claims

1. A method for providing an electrocardiogram measurement guide, performed by a computing device comprising at least one processor, wherein A step of storing an electrocardiogram signal and measurement information corresponding to the electrocardiogram signal; A step of analyzing at least one of quality or diagnostic reliability for each of the stored electrocardiogram signals; and A step of generating an electrocardiogram measurement guide for the electrocardiogram measurement target by analyzing at least one of the above quality or diagnostic reliability and the above stored measurement information; including, method.

2. In Paragraph 1, The above measurement information is, at least one of the wrist rotation angle of the electrocardiogram measurement target, the wearing site of the electrocardiogram measurement device, the wearing pressure of the electrocardiogram measurement device, the contact state of the electrodes of the electrocardiogram measurement device, the movement of the electrocardiogram measurement target, or the surrounding environment of the electrocardiogram measurement target. method.

3. In Paragraph 1, The above diagnostic reliability is, Determined based on the distribution of artificial intelligence inference results based on the above-mentioned stored electrocardiogram signals, method.

4. In Paragraph 1, The step of generating an electrocardiogram measurement guide for the above-mentioned electrocardiogram measurement target is, A step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing area of ​​the electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement, based on at least one of the above quality or diagnostic reliability and the above stored measurement information; and Based on the above analysis results, a step of generating an electrocardiogram measurement guide including at least one of the electrocardiogram measurement posture, measurement location, or measurement environment of the electrocardiogram measurement target; including, method.

5. In Paragraph 4, The step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing site of the above-mentioned electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement is: A step of calculating the statistical characteristics of the electrode impedance and the noise generation rate for each wearing site of the above electrocardiogram measuring device, and calculating the contact index of the electrode for each wearing site; and A step of comparing the above contact indicator with a first reference value to determine contact suitability of a specific wearing area or to determine an adjustment value for the adhesion strength of the electrode; including, method.

6. In Paragraph 4, The step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing site of the above-mentioned electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement is: A step of calculating the quality distribution by segment of the wrist rotation angle; and A step of identifying the rate of change in the quality distribution by segment of the wrist rotation angle and determining a specific angle segment as a distortion occurrence segment; including, method.

7. In Paragraph 4, The step of deriving an analysis result regarding at least one of electrode contact failure according to the wearing site of the above-mentioned electrocardiogram measuring device, signal distortion according to the wrist rotation angle, or sensitivity to movement is: A step of calculating a correlation coefficient between a movement indicator recorded through the electrocardiogram measuring device and a quality indicator of the electrocardiogram signal to calculate a quality attenuation slope according to the amount of change in movement; and A step of determining signal sensitivity according to the movement of the electrocardiogram measurement target by comparing the above slope and a third reference value; including, method.

8. In Paragraph 1, A step of providing the generated electrocardiogram measurement guide to an electrocardiogram measurement device when a new electrocardiogram measurement is performed; including, method.

9. In Paragraph 1, Step of acquiring a new electrocardiogram signal; A step of analyzing the noise of the new electrocardiogram signal to determine whether the new electrocardiogram signal is readable; and If it is determined that the newly acquired electrocardiogram signal is unreadable, a step of analyzing measurement information corresponding to the new electrocardiogram signal based on the electrocardiogram measurement guide to generate measurement conditions for re-measurement; including, method.

10. A method for providing an electrocardiogram measurement guide, performed by a computing device comprising at least one processor, wherein Step of initiating a measurement trigger for acquiring an electrocardiogram signal; and A step of providing an electrocardiogram measurement guide for measuring the above electrocardiogram signal as a user interface; Includes, The above electrocardiogram measurement guide is, at least one of the already accumulated quality or diagnostic reliability of each electrocardiogram signal and the measurement information corresponding to said electrocardiogram signal, which is generated by analyzing said electrocardiogram signal, method.

11. As a computing device that provides an electrocardiogram measurement guide, A processor comprising at least one core; Memory containing program code executable in the above processor; and It includes a network unit, The above processor is, An electrocardiogram signal and measurement information corresponding to the electrocardiogram signal are stored in the memory, and Analyze at least one of quality or diagnostic reliability for each of the stored electrocardiogram signals, By analyzing at least one of the above quality or diagnostic reliability and the above stored measurement information, generating an electrocardiogram measurement guide for the electrocardiogram measurement target. device.

Images