WO2023048463A1 - 딥러닝 기반으로 연속적인 신체 상태를 계측하는 방법, 컴퓨터 프로그램 및 장치 - Google Patents
딥러닝 기반으로 연속적인 신체 상태를 계측하는 방법, 컴퓨터 프로그램 및 장치 Download PDFInfo
- Publication number
- WO2023048463A1 WO2023048463A1 PCT/KR2022/014109 KR2022014109W WO2023048463A1 WO 2023048463 A1 WO2023048463 A1 WO 2023048463A1 KR 2022014109 W KR2022014109 W KR 2022014109W WO 2023048463 A1 WO2023048463 A1 WO 2023048463A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- disease
- model
- sub
- feature
- neural network
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
-
- 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
- A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4842—Monitoring progression or stage of a disease
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the present disclosure relates to deep learning technology in the medical field, and more specifically, to a method, computer program, and device for measuring continuous body conditions based on deep learning to represent body characteristics for diseases as continuous numerical values. .
- An electrocardiogram signal is a graph representing a state of electrical activity of the heart occurring during a heartbeat cycle. Therefore, we can observe the structural and functional aspects of the heart through ECG signals. Accordingly, electrocardiogram signals are used to diagnose various diseases including heart diseases such as arrhythmia and myocardial infarction.
- Common physical diseases including heart disease, represent a situation in which a continuously changing physical condition worsens by a set reference value to be diagnosed as a disease.
- the physical state continuously changes like an analog rather than a digital 0 or 1, and the disease is determined according to an artificially set reference value.
- the state of coronary arteries supplying blood to the heart continuously changes, and diseases such as arteriosclerosis, angina pectoris, and myocardial infarction are determined according to the degree of stenosis in which coronary arteries are narrowed.
- the purpose of disease prediction is to prevent a disease by estimating the possibility of developing the disease. Therefore, in the field of disease prediction, it is also important to accurately predict a physical state related to a disease as much as predicting the presence or absence of a disease. That is, we need to predict continuously changing body conditions related to disease.
- the present disclosure has been made in response to the above-mentioned background art, and individually predicts biological information about body characteristics and pathological information about diseases based on electrocardiogram data, and integrates them to measure body conditions as continuous values. It aims to provide a method.
- a method for measuring a continuous body state based on deep learning performed by a computing device includes obtaining electrocardiogram data and using a pretrained neural network model to infer, on the basis of the electrocardiogram data, a physical state corresponding to the onset of a disease or the progress of the disease of a target whose electrocardiogram is measured.
- the neural network model includes at least one of a first feature related to biological information representing the body characteristic having a correlation with the disease, and a second feature related to pathological information reflecting the degree of progression of the disease. It is characterized by being learned based on one.
- the neural network model includes a first sub-model learned to output the first feature based on the electrocardiogram data, and the first sub-model includes at least one factor included in the biological information. ), it may be configured according to the number of the factors to individually output the numerical value.
- the neural network model further includes a second sub-model learned to output the second feature based on the electrocardiogram data, wherein the second sub-model includes at least one information included in the pathological information. It may be configured according to the number of factors to individually output values for the factors.
- the neural network model based on the first feature, which is an output of the first sub-model, and the second feature, which is an output of the second sub-model, continuously according to the onset or progress of the disease It may further include a third sub-model learned to express the changing body state as a numerical value.
- the third sub-model may receive a third feature generated by combining the first feature and the second feature based on a weight determined according to the type of the disease and output the numerical value. there is.
- each of the first sub-model and the second sub-model may be learned based on semi-supervised learning performed using training data including unlabeled samples. .
- the disease may include a vascular disease.
- the biological information may include at least one of age, sex, height, or weight as a body characteristic factor related to coronary artery disease included in pre-existing cardiovascular disease.
- the pathological information is a pathological characteristic factor reflecting the degree of progression of coronary artery disease included in the existing cardiovascular disease, whether or not myocardial infarction, degree of vascular calcification, stability of thrombus, intravascular coronary artery It may include at least one of speed, or degree of coronary artery stenosis.
- a computer program stored in a computer readable storage medium is disclosed according to an embodiment of the present disclosure for realizing the above object.
- the computer program When executed on one or more processors, it performs operations for measuring continuous body states based on deep learning.
- the operations include an operation of acquiring electrocardiogram data and a physical state corresponding to the onset of a disease or progress of a disease of a target whose electrocardiogram data is measured based on the electrocardiogram data using a pretrained neural network model. and an operation of inferring, wherein the neural network model comprises a first feature related to biological information representing a physical characteristic of the subject having a correlation with the disease, or a first feature related to pathological information reflecting the degree of progression of the disease. It is characterized in that it is learned based on at least one of the two features.
- a computing device for continuously measuring a body state based on deep learning.
- the apparatus includes a processor including at least one core, a memory including program codes executable in the processor, and a network unit for obtaining electrocardiogram data.
- the processor is based on at least one of a first feature related to biological information representing a physical characteristic of a subject having a correlation with a disease, or a second feature related to pathological information reflecting a degree of progression of the disease
- a learned neural network model based on the electrocardiogram data, it is characterized in that a physical state corresponding to the onset of a disease or progress of the disease of a target whose electrocardiogram is measured is inferred.
- the present disclosure provides a method for preparing for the previous or subsequent stages of a disease by individually inferring physical factors and pathological factors for a disease using electrocardiogram data and describably identifying factors influencing a physical condition. can do.
- the present disclosure may provide a method for preparing for a previous or subsequent stage of a disease by representing a patient's physical condition related to a disease to be predicted as a continuous numerical value.
- FIG. 1 is a block diagram of a computing device according to one embodiment of the present disclosure.
- FIG. 2 is a block diagram illustrating a neural network model according to an embodiment of the present disclosure.
- FIG. 3 is a block diagram showing the internal configuration of a neural network model according to an embodiment of the present disclosure.
- FIG. 4 is a flowchart illustrating an inference method of a neural network model according to an embodiment of the present disclosure.
- FIG. 5 is a flowchart illustrating an inference method of sub-models constituting a neural network model according to an embodiment of the present disclosure.
- N N is a natural number
- N a natural number
- components performing different functional roles in the present disclosure may be classified as first components or second components.
- components that are substantially the same within the technical spirit of the present disclosure but should be distinguished for convenience of description may also be classified as first components or second components.
- acquisition used in the present disclosure is understood to mean not only receiving data through a wired/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 , It can be understood as a term referring to an independent functional unit that processes computing resources, such as a combination of software and hardware.
- a “module” or “unit” may be a unit composed of a single element or a unit expressed as a combination or set of a plurality of elements.
- a “module” or “unit” is a hardware element or set thereof of a computing device, an application program that performs a specific function of software, a process implemented through software execution, or a program. It may refer to a set of instructions for execution.
- a “module” or “unit” may refer to a computing device constituting a system or an application executed in the computing device.
- the concept of “module” or “unit” may be defined in various ways within a range understandable by those skilled in the art based on the contents of the present disclosure.
- model used in this disclosure 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 for a process.
- a neural network “model” may refer to an overall system implemented as a neural network having problem-solving capabilities through learning. At this time, the neural network may have problem solving ability by optimizing parameters connecting nodes or neurons through learning.
- a neural network "model” may include a single neural network or may include a neural network set in which a plurality of neural networks are combined.
- FIG. 1 is a block diagram of a computing device according to one 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 through a communication network.
- the computing device 100 may be a server that performs intensive data processing functions and shares resources, or may be a client that shares resources through interaction with 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 one example related to the type of the computing device 100, the type of the computing device 100 may be configured in various ways within a range understandable by those skilled in the art based on the contents of the present disclosure.
- a computing device 100 may include a processor 110, a memory 120, and a network unit 130. there is.
- the computing device 100 may include other configurations for implementing a computing environment. Also, only some of the components disclosed above may be included in the 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 input data processing for machine learning, feature extraction for machine learning, calculation of an error based on backpropagation, and the like.
- 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 on-demand It may include a semiconductor (application specific integrated circuit (ASIC)) or a field programmable gate array (FPGA). Since the above-described type of processor 110 is just one example, the type of processor 110 may be variously configured within a range understandable by those skilled in the art based on the content of the present disclosure.
- the processor 110 may continuously measure the body state of the subject whose electrocardiogram data is measured using a neural network model based on the electrocardiogram data.
- the processor 110 may receive electrocardiogram data and train a neural network model to estimate a physical condition related to a disease, for example, a physical condition corresponding to whether a disease has occurred or progressed. In this case, whether or not the disease occurs may be a discrete value, and the progress of the disease may be a continuous value that changes over time.
- the processor 110 may use a neural network model to indicate a disease or infer continuous body conditions that affect the disease.
- the processor 110 not only predicts whether or not the onset of a disease appears as a discrete value, but also accurately predicts the possibility of onset of a disease because it predicts a physical state according to continuously progressing diseases. Therefore, through the processor 110 of the present disclosure, we can establish a disease prevention plan and treatment plan in detail.
- the processor 110 may individually train a plurality of sub-models to predict a body state. For example, the processor 110 may use electrocardiogram data to train a first sub-model that outputs a first characteristic of biological information representing a physical characteristic of a target subject to measure electrocardiogram data. In addition, the processor 110 may use the electrocardiogram data to train a second sub-model that outputs a second feature related to pathological information that affects changes in the body caused by the disease, that is, the degree of progression of the disease. there is. Further, the processor 110 may use the first feature output from the first sub-model and the second feature output from the second sub-model to train a third sub-model that infers a physical state related to a disease.
- the first feature may include at least one factor included in the biological information and a numerical value corresponding to the factor.
- Biological factors may vary depending on the disease.
- biological factors may include age, height, weight, and the like.
- the second characteristic may include at least one factor included in the pathological information and a numerical value corresponding to the factor.
- Pathological factors may vary depending on the disease.
- pathological factors may include myocardial infarction, degree of vascular calcification, stability of thrombosis, intravascular velocity of coronary artery, degree of coronary artery stenosis, and the like.
- the processor 110 may perform learning based on supervised learning by inputting training data including samples and labels corresponding to the samples to the first sub-model and the second sub-model.
- the sample input to the first sub-model may be electrocardiogram data
- the label may be the first feature.
- a sample input to the second sub-model is electrocardiogram data, and a label may be a second feature.
- the processor 110 may perform semi-supervised learning by inputting training data including unlabeled samples to the first sub-model and the second sub-model.
- the first sub-model may extract a first feature from the ECG data
- the second sub-model may extract a second feature from the ECG data. Factors extracted by the first sub-model and the second sub-model may vary depending on the type of disease.
- Each of the neural network model, the first sub-model, the second sub-model, and the third sub-model may include at least one neural network.
- the neural network includes at least one of neural networks such as a deep neural network (DNN), a recurrent neural network (RNN), a bidirectional recurrent deep neural network (BRDNN), a multilayer perceptron (MLP), a convolutional neural network (CNN), a transformer, and the like. It may include, but is not limited to.
- the processor 110 may individually learn and infer neural network models corresponding to factors that may act as risk factors for diseases. Therefore, we can accurately determine the extent to which each factor affects the disease through the processor 110 .
- the processor 110 may provide basic data for disease prevention and treatment by accurately targeting factors influencing diseases.
- the memory 120 may be understood as a unit including hardware and/or software for storing and managing data processed by the computing device 100 . That is, the memory 120 may store any type of data generated or determined by the processor 110 and any type of data received by the network unit 130 .
- the memory 120 may include a flash memory type, a hard disk type, a multimedia card micro type, a card type memory, and random access memory (RAM). ), 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 may include at least one type of storage medium.
- 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 just one example, the type of memory 120 may be configured in various ways within a range understandable by those skilled in the art based on the contents of the present disclosure.
- the memory 120 may organize and manage data necessary for the processor 110 to perform calculations, data combinations, program codes executable by the processor 110, and the like.
- the memory 120 may store medical data received through the network unit 130 to be described later.
- the memory 120 includes program codes for operating the neural network model to perform learning by receiving medical data, program codes for operating the neural network model to perform inference according to the purpose of use of the computing device 100 by receiving medical data, and Processing data generated as the program code is executed may be stored.
- the network unit 130 may be understood as a unit that transmits and receives data through any type of known wired/wireless communication system.
- the network unit 130 may include a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), and WiBro (wireless).
- broadband internet 5th generation mobile communication (5G), ultra wide-band wireless communication, ZigBee, radio frequency (RF) communication, wireless LAN, wireless fidelity ), near field communication (NFC), or data transmission/reception may be performed using a wired/wireless communication system such as Bluetooth. Since the above-described communication systems are only examples, a wired/wireless communication system for data transmission and reception of the network unit 130 may be applied in various ways other than the above-described examples.
- the network unit 130 may receive data necessary for the processor 110 to perform an operation through wired/wireless communication with an arbitrary system or an arbitrary client.
- the network unit 130 may transmit data generated through the operation of the processor 110 through wired/wireless communication with an arbitrary system or an arbitrary client.
- the network unit 130 may receive medical data through communication with a database in a hospital environment, a cloud server that performs tasks such as standardization of medical data, or a computing 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, and processed data through communication with the aforementioned database, server, or computing device.
- FIG. 2 is a block diagram illustrating a neural network model according to an embodiment of the present disclosure.
- the neural network model 200 may receive electrocardiogram data 300 and output a physical state 400 related to a disease of a subject whose electrocardiogram data 300 is measured as a continuous numerical value.
- electrocardiogram (ECG) data may include an electrocardiogram signal capable of determining the presence or absence of a disease by measuring electrical signals generated from the heart and checking the presence or absence of abnormalities in the conduction system from the heart to the electrodes.
- the electrocardiogram data 300 may be obtained from an electrocardiogram measuring device or through a network.
- the neural network model 200 includes a first sub-model 210 outputting a first feature related to biological information related to a disease, a second sub-model 220 outputting a second feature related to pathological information related to a disease, and a second sub-model 220 outputting a second feature related to pathological information related to a disease.
- a third sub-model 230 that outputs the continuously changing body condition 400 as a numerical value for diagnosis of a disease by using the output value of the first sub-model 210 and the output value of the second sub-model 220 can do.
- Each of the first sub-model 210 and the second sub-model 220 may be configured in plurality according to output information.
- the first sub-model 210 may output a first feature corresponding to each of body characteristic factors representing biological characteristics related to a disease from the electrocardiogram data 300 .
- the number of first sub-models 210 may correspond to the number of body characteristic factors.
- Each of the plurality of first sub-models 210 may individually output numerical values for body characteristic factors.
- the second sub-model 220 may output second features corresponding to each of the pathological characteristic factors determined according to the progression of the disease from the electrocardiogram data 300 .
- the number of second sub-models 220 may correspond to the number of pathological characteristic factors.
- Each of the plurality of second sub-models 220 may individually output numerical values for pathological characteristic factors.
- the number of risk factors associated with a disease may vary depending on the type of disease. Therefore, since the first sub-model and the second sub-model can be configured according to the number of factors through the neural network model according to the present disclosure, the first sub-model and the second sub-model can be modularized and managed.
- the third sub-model 230 outputs the body state 400 related to the disease as a numerical value by using the first feature, which is an output of the first sub-model 210, and the second feature, which is an output of the second sub-model 220. can do.
- the third sub-model 230 may output the body state 400 by receiving a third feature generated by merging the first feature and the second feature.
- the first feature and the second feature may be combined into a third feature by giving weights according to the type of disease.
- the processor 110 may adjust the weight for the combination of the first feature and the second feature according to the type of disease.
- the third sub-model 230 can predict the body state 400 that continuously changes according to the type of disease based on the first and second characteristics whose proportions are adjusted according to the type of disease.
- a value output from the third sub-model 230 may be a continuous numerical value representing the physical condition 400 for a disease. Therefore, the medical staff can determine whether or not the disease has occurred or can determine the progression of the disease based on the corresponding numerical value.
- the neural network model 200 can predict a physical state by comprehensively identifying factors related to a disease, rather than simply predicting whether or not a disease will occur according to an artificially set criterion. Using this neural network model 200, we can accurately grasp complex changes in the physical condition caused by various factors related to diseases affecting the body.
- do 3 is a block diagram showing the internal configuration of a neural network model according to an embodiment of the present disclosure. .
- the neural network model 200 includes a plurality of first sub-models 210 learned to output a first feature 211 and a plurality of second sub-models learned to output a second feature 221. 220 , the first feature 211 and the second feature 221 may be merged to output the body state 400 .
- the first feature 211 may include a factor included in the biological information and a numerical value corresponding to the factor.
- the second feature 221 may include a factor included in the pathological information and a numerical value corresponding to the factor.
- the types of body characteristic factors individually learned by the first sub-model 210 may be determined by labels included in training data or directly extracted by the first sub-model 210 .
- the types of pathological characteristic factors individually learned by the second sub-model 220 may be determined by labels included in training data or directly extracted by the second sub-model 220 . That is, depending on the learning method, the first sub-model 210 and the second sub-model 220 may output only the values corresponding to the factors or output both the values and the factors corresponding thereto.
- the operation of the neural network model 200 to measure the body state 400 for cardiovascular disease, particularly coronary artery disease will be described as an example, but the type of disease to which the present disclosure is applied is not limited thereto.
- Risk factors associated with the development of coronary artery disease are well known. Even risk factors that do not have a causal relationship with coronary artery disease have a correlation with the disease, so they can be used as an important tool for identifying the cause of the disease or preventing the disease.
- body characteristic factors affecting coronary artery disease may include age, sex, height, weight, and the like, and may further include a family or personal history of coronary artery disease.
- pathological factors affecting coronary artery disease may include myocardial infarction, degree of vascular calcification, stability of thrombosis, intravascular speed of coronary artery, degree of coronary artery stenosis, etc., blood sugar, blood pressure , cholesterol level, triglyceride level, obesity, smoking status, etc. may be further included.
- the neural network model 200 according to the present disclosure can individually learn and infer the extent to which risk factors related to the occurrence of coronary artery disease have an effect on coronary artery disease, using electrocardiogram data 300 that can be obtained relatively easily.
- the neural network model 200 according to the present disclosure is trained through self-supervised learning to extract factors related to the induction of coronary artery disease by itself and infer how much each factor affects coronary artery disease.
- the plurality of first sub-models 210 receive electrocardiogram data 300, and from the electrocardiogram data 300, age, It is trained to infer gender, height, and weight, respectively.
- numerical values for age, gender, height, and weight may be respectively output.
- the value may be a value indicating an effect on coronary artery disease.
- the plurality of second sub-models 220 receive electrocardiogram data 300, and from the electrocardiogram data 300, the presence or absence of myocardial infarction, the degree of vascular calcification, the stability of thrombosis, the intravascular speed of coronary arteries, and the stenosis of coronary arteries are determined. It is learned to infer the degree of each.
- values for myocardial infarction, vascular calcification, thrombosis stability, coronary intravascular velocity, and coronary artery stenosis can be output.
- the value may be a value indicating an effect on coronary artery disease.
- the third sub-model 230 may receive a third feature generated based on numerical values output from the first sub-model 210 and the second sub-model 220 .
- the third feature is a value combined by the processor 110, and the processor 110 assigns weights to numerical values output from the first sub-model 210 and the second sub-model 220 according to the type of disease. can be combined For example, when it is found that the correlation between a specific disease and a body characteristic factor is high, the processor 110 may assign a high weight to numerical values output from the first sub-model 210 . Conversely, if it is found that the influence of the body characteristic factor on a specific disease is low and the incidence rate due to the pathological characteristic factor is high, the processor 110 may assign a high weight to the numerical values output from the second sub-model 220. .
- the third sub-model 230 may output the body condition 400 for coronary artery disease as a numerical value using the third feature.
- the output value may be interpreted as a value indicating the degree of coronary artery health, the probability of coronary artery disease, the degree of angina pectoris, or the possibility of myocardial infarction.
- the medical staff may make a diagnosis of angina pectoris for the target having measured the electrocardiogram data 300, administer a drug, or set up a treatment plan such as performing surgery. Alternatively, medical personnel may establish and guide a plan for disease prevention.
- FIG. 4 is a flowchart illustrating an inference method of a neural network model according to an embodiment of the present disclosure.
- the computing device 100 may acquire electrocardiogram data (S110).
- the computing device 100 may acquire electrocardiogram data from an electrocardiogram measuring device or through a network.
- the computing device 100 may use the pretrained neural network model to infer, based on the electrocardiogram data, a physical state corresponding to the onset or progression of a disease of a subject measured by the electrocardiogram data (S120).
- the computing device 100 may train a neural network model in advance to output a continuous body state related to a specific disease as a numerical value using electrocardiogram data.
- the neural network model may be the neural network model described above with reference to FIGS. 2 and 3 .
- the computing device 100 is configured to train a neural network model based on at least one of a first feature related to biological information representing body characteristics correlated with a disease or a second feature related to pathological information reflecting the progression of a disease.
- the computing device 100 may train the neural network model through supervised learning or self-supervised learning.
- the computing device 100 may learn the neural network model by inputting, as learning data, various factors related to the disease and numerical values representing correlations between each factor and the disease in the electrocardiogram data, to the neural network model.
- the computing device 100 learns the neural network model so that the neural network model extracts disease-related factors by itself using training data including unlabeled electrocardiogram data, and outputs a numerical value indicating a correlation between each factor and the disease. can make it
- the pretrained neural network model may receive electrocardiogram data and output values related to diseases.
- the corresponding numerical value represents the physical condition of the subject whose electrocardiogram data is measured, and is a numerical value related to a disease.
- the corresponding numerical value may indicate whether or not a disease has occurred or indicate a progress state of a disease.
- FIG. 5 is a flowchart illustrating an inference method of sub-models constituting a neural network model according to an embodiment of the present disclosure.
- the computing device 100 may acquire electrocardiogram data (S210). Since this is similar to step S110 of FIG. 4, a detailed description thereof will be omitted.
- the computing device 100 may output a first feature related to biological information through the first sub-model (S220).
- the first sub-model may be learned to output the first feature based on electrocardiogram data.
- the first feature may include at least one factor included in the biological information or a numerical value for the factor.
- There may be a plurality of first sub-models, and each of the first sub-models may individually output at least one factor included in biological information. Accordingly, the number of first sub-models may be configured according to the number of factors.
- the computing device 100 may output a second feature related to pathological information through the second sub-model (S230).
- the second sub-model may be learned to output the second feature based on electrocardiogram data.
- the second characteristic may include at least one factor included in the pathological information or a numerical value for the factor.
- each of the first sub-model and the second sub-model may be learned based on self-supervised learning performed using training data including unlabeled samples.
- the computing device 100 may output a numerical value for a body state through a third sub-model based on the first feature output from the first sub-model and the second feature output from the second sub-model (S240). .
- the third sub-model may be learned to express a body state that continuously changes according to the onset or progress of a disease as numerical values based on the first and second characteristics.
- the computing device 100 may determine a weight for combining the first feature and the second feature according to the type of disease.
- the computing device 100 may generate a third feature by combining the first feature and the second feature according to the determined weight. Accordingly, the third sub-model may receive the third feature and output a numerical value representing a body state.
- steps S220 and S230 are illustrated as sequentially performed in FIG. 5 , steps S220 and S230 may be performed in parallel.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Cardiology (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Physiology (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
Claims (11)
- 적어도 하나의 프로세서(processor)를 포함하는 컴퓨팅 장치에 의해 수행되는, 딥러닝 기반으로 연속적인 신체 상태를 계측하는 방법으로서,심전도 데이터를 획득하는 단계; 및사전 학습된 신경망 모델을 사용하여, 상기 심전도 데이터를 기초로 상기 심전도 데이터를 측정한 대상의 질환의 발병 또는 상기 질환의 진행 상황에 대응되는 신체 상태를 추론하는 단계;를 포함하고,상기 신경망 모델은,상기 질환과 상관관계를 갖는 상기 신체 특성을 나타내는 생물학적 정보에 관한 제1 특징, 또는 상기 질환의 진행 정도를 반영하는 병리학적 정보에 관한 제2 특징 중 적어도 하나를 기초로 학습된,방법.
- 제1항에 있어서,상기 신경망 모델은,상기 심전도 데이터를 기초로 상기 제1 특징을 출력하도록 학습된 제1 서브 모델;을 포함하고,상기 제1 서브 모델은상기 생물학적 정보에 포함된 적어도 하나의 인자(factor)에 대한 수치를 개별적으로 출력하도록, 상기 인자의 개수에 맞추어 구성되는,방법.
- 제2항에 있어서,상기 신경망 모델은,상기 심전도 데이터를 기초로 상기 제2 특징을 출력하도록 학습된 제2 서브 모델;을 더 포함하고,상기 제2 서브 모델은,상기 병리학적 정보에 포함된 적어도 하나의 인자에 대한 수치를 개별적으로 출력하도록, 상기 인자의 개수에 맞추어 구성되는,방법.
- 제3항에 있어서,상기 신경망 모델은,상기 제1 서브 모델의 출력인 제1 특징 및 상기 제2 서브 모델의 출력인 제2 특징을 기초로, 상기 질환의 발병 또는 상기 질환의 진행 상황에 따라 연속적으로 변화하는 신체 상태를 수치 값으로 표현하도록 학습된 제3 서브 모델;을 더 포함하는,방법.
- 제4 항에 있어서,상기 제3 서브 모델은,상기 질환의 종류에 따라 결정된 가중치를 기초로, 상기 제1 특징 및 상기 제2 특징을 조합하여 생성된 제3 특징을 입력 받아 상기 수치 값을 출력하는,방법.
- 제3 항에 있어서,상기 제1 서브 모델 및 상기 제2 서브 모델 각각은,라벨이 지정되지 않은 샘플을 포함하는 학습 데이터를 이용하여 수행되는 자기 지도 학습(semi-supervised learning)을 기반으로 학습된,방법.
- 제1항에 있어서,상기 질환은,심혈관 질환을 포함하는,방법.
- 제7항에 있어서,상기 생물학적 정보는,상기 심혈관 질환에 포함된 관상동맥 질환과 관련된 신체 특성 인자로서, 나이, 성별, 키, 또는 몸무게 중 적어도 하나를 포함하는,방법.
- 제8항에 있어서,상기 병리학적 정보는,상기 심혈관 질환에 포함된 관상동맥 질환의 진행 정도를 반영하는 병리학적 특성 인자로서, 심근경색 여부, 혈관 칼슘화의 정도, 혈전의 안정성, 관상동맥의 혈관 내 속도, 또는 관상동맥의 협착의 정도 중 적어도 하나를 포함하는,방법.
- 컴퓨터 판독가능 저장 매체 저장된 컴퓨터 프로그램(program)으로서, 상기 컴퓨터 프로그램은 하나 이상의 프로세서(processor)에서 실행되는 경우, 딥러닝 기반으로 연속적인 신체 상태를 계측하는 동작들을 수행하도록 하며,상기 동작들은,심전도 데이터를 획득하는 동작; 및사전 학습된 신경망 모델을 사용하여, 상기 심전도 데이터를 기초로 상기 심전도 데이터를 측정한 대상의 질환의 발병 또는 상기 질환의 진행 상황에 대응되는 신체 상태를 추론하는 동작;을 포함하고,상기 신경망 모델은,상기 질환과 상관관계를 갖는 상기 대상의 신체 특성을 나타내는 생물학적 정보에 관한 제1 특징, 또는 상기 질환의 진행 정도를 반영하는 병리학적 정보에 관한 제2 특징 중 적어도 하나를 기초로 학습된,컴퓨터 프로그램.
- 딥러닝 기반으로 연속적인 신체 상태를 계측하기 위한 컴퓨팅 장치로서,적어도 하나의 코어(core)를 포함하는 프로세서(processor);상기 프로세서에서 실행 가능한 프로그램 코드(code)들을 포함하는 메모리(memory); 및심전도 데이터를 획득하기 위한 네트워크부(network unit);를 포함하고,상기 프로세서는,질환과 상관관계를 갖는 대상의 신체 특성을 나타내는 생물학적 정보에 관한 제1 특징, 또는 상기 질환의 진행 정도를 반영하는 병리학적 정보에 관한 제2 특징 중 적어도 하나를 기초로 학습된 신경망 모델을 사용하여, 상기 심전도 데이터를 기초로 상기 심전도 데이터를 측정한 대상의 질환의 발병 또는 상기 질환의 진행 상황에 대응되는 신체 상태를 추론하는,장치.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202280062072.1A CN117979902A (zh) | 2021-09-25 | 2022-09-21 | 以深度学习为基础计测连续的身体状态的方法、计算机程序及装置 |
| JP2024516342A JP7746547B2 (ja) | 2021-09-25 | 2022-09-21 | ディープラーニングに基づいて連続的な身体状態を計測する方法、コンピュータプログラム及び装置 |
| EP22873168.3A EP4385413A4 (en) | 2021-09-25 | 2022-09-21 | METHOD, COMPUTER PROGRAM AND DEVICE FOR CONTINUOUSLY MEASURING A BODY STATE BASED ON DEEP LEARNING |
| US18/692,334 US20240374196A1 (en) | 2021-09-25 | 2022-09-21 | Method, computer program, and device for continuously measuring body condition on basis of deep learning |
| JP2025154550A JP2025179219A (ja) | 2021-09-25 | 2025-09-17 | ディープラーニングに基づいて連続的な身体状態を計測する方法、コンピュータプログラム及び装置 |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR20210126782 | 2021-09-25 | ||
| KR10-2021-0126782 | 2021-09-25 | ||
| KR10-2022-0118514 | 2022-09-20 | ||
| KR1020220118514A KR102740470B1 (ko) | 2021-09-25 | 2022-09-20 | 딥러닝 기반으로 연속적인 신체 상태를 계측하는 방법, 컴퓨터 프로그램 및 장치 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023048463A1 true WO2023048463A1 (ko) | 2023-03-30 |
Family
ID=85720934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2022/014109 Ceased WO2023048463A1 (ko) | 2021-09-25 | 2022-09-21 | 딥러닝 기반으로 연속적인 신체 상태를 계측하는 방법, 컴퓨터 프로그램 및 장치 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20240374196A1 (ko) |
| EP (1) | EP4385413A4 (ko) |
| JP (2) | JP7746547B2 (ko) |
| WO (1) | WO2023048463A1 (ko) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4670621A4 (en) * | 2023-04-03 | 2026-02-25 | Medical Ai Co Ltd | METHOD, PROGRAM AND DEVICE FOR DISEASE PREDICTION BASED ON ARTIFICIAL INTELLIGENCE |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024238786A1 (en) * | 2023-05-17 | 2024-11-21 | Heartflow, Inc. | Systems and methods for processing electronic images to quantify coronary microvascualar disease |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060117546A (ko) * | 2005-05-11 | 2006-11-17 | 인하대학교 산학협력단 | 신경망을 이용한 심전도 기반의 심장질환 진단장치 및방법 |
| KR101538916B1 (ko) * | 2014-09-26 | 2015-07-24 | (주)와이브레인 | Eeg 데이터를 이용하여 사용자 특성의 변화를 예측하는 방법 |
| KR20200084561A (ko) * | 2019-01-03 | 2020-07-13 | 인하대학교 산학협력단 | 딥러닝을 이용한 정상동율동 심전도 상태에서의 발작성 심방세동 예측방법 |
| KR20210109879A (ko) * | 2020-02-28 | 2021-09-07 | 한국외국어대학교 연구산학협력단 | 심전도 전처리 방법 및 st 상승 심근경색 검출 방법 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007116295A2 (en) * | 2006-04-07 | 2007-10-18 | Kantonsspital Bruderholz | Individual assessment and classification of complex diseases by a data-based clinical disease profile |
| JP6484625B2 (ja) * | 2013-11-30 | 2019-03-13 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | Ecgによる患者の年齢の自動化された検出 |
| EP3730040B1 (en) * | 2017-12-20 | 2025-10-29 | Medi Whale Inc. | Method and apparatus for assisting in diagnosis of cardiovascular disease |
| GB2570131A (en) * | 2018-01-11 | 2019-07-17 | Imperial Innovations Ltd | Fluid flow analysis |
| CN111261278A (zh) * | 2018-11-30 | 2020-06-09 | 上海图灵医疗科技有限公司 | 一种基于三维图像的深度学习模型的心脏疾病检测方法 |
-
2022
- 2022-09-21 JP JP2024516342A patent/JP7746547B2/ja active Active
- 2022-09-21 WO PCT/KR2022/014109 patent/WO2023048463A1/ko not_active Ceased
- 2022-09-21 US US18/692,334 patent/US20240374196A1/en active Pending
- 2022-09-21 EP EP22873168.3A patent/EP4385413A4/en active Pending
-
2025
- 2025-09-17 JP JP2025154550A patent/JP2025179219A/ja active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060117546A (ko) * | 2005-05-11 | 2006-11-17 | 인하대학교 산학협력단 | 신경망을 이용한 심전도 기반의 심장질환 진단장치 및방법 |
| KR101538916B1 (ko) * | 2014-09-26 | 2015-07-24 | (주)와이브레인 | Eeg 데이터를 이용하여 사용자 특성의 변화를 예측하는 방법 |
| KR20200084561A (ko) * | 2019-01-03 | 2020-07-13 | 인하대학교 산학협력단 | 딥러닝을 이용한 정상동율동 심전도 상태에서의 발작성 심방세동 예측방법 |
| KR20210109879A (ko) * | 2020-02-28 | 2021-09-07 | 한국외국어대학교 연구산학협력단 | 심전도 전처리 방법 및 st 상승 심근경색 검출 방법 |
Non-Patent Citations (2)
| Title |
|---|
| PARK, SUNG JUN, CHOI SEUNG YEON, KIM YOUNG MO: "Performance Evaluation of Deep Neural Network (DNN) Based on HRV Parameters for Judgment of Risk Factors for Coronary Artery Disease", JOURNAL OF BIOMEDICAL ENGINEERING RESEARCH, vol. 40, no. 2, 1 January 2019 (2019-01-01), pages 62 - 67, XP093053590, DOI: 10.9718/JBER.2019.40.2.62 * |
| See also references of EP4385413A4 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4670621A4 (en) * | 2023-04-03 | 2026-02-25 | Medical Ai Co Ltd | METHOD, PROGRAM AND DEVICE FOR DISEASE PREDICTION BASED ON ARTIFICIAL INTELLIGENCE |
Also Published As
| Publication number | Publication date |
|---|---|
| JP7746547B2 (ja) | 2025-09-30 |
| US20240374196A1 (en) | 2024-11-14 |
| EP4385413A4 (en) | 2025-08-06 |
| EP4385413A1 (en) | 2024-06-19 |
| JP2025179219A (ja) | 2025-12-09 |
| JP2024535229A (ja) | 2024-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019031794A1 (ko) | 피검체의 치명적 증상의 발생을 조기에 예측하기 위한 예측 결과를 생성하는 방법 및 이를 이용한 장치 | |
| WO2022019402A1 (ko) | 시계열 생체 신호 기반의 인공신경망 모델 학습 컴퓨터 프로그램 및 방법 | |
| WO2020116942A1 (ko) | 피검체의 위험도를 평가하여 상기 위험도에 따라 상기 피검체를 분류하는 방법 및 이를 이용한 장치 | |
| JP2025179219A (ja) | ディープラーニングに基づいて連続的な身体状態を計測する方法、コンピュータプログラム及び装置 | |
| KR20240017319A (ko) | 심전도 판독 서비스를 제공하는 방법, 프로그램 및장치 | |
| KR102740470B1 (ko) | 딥러닝 기반으로 연속적인 신체 상태를 계측하는 방법, 컴퓨터 프로그램 및 장치 | |
| EP4550352A1 (en) | Method, program, and device for providing ecg interpretation service | |
| WO2024191246A1 (ko) | 심부전의 예후 예측 방법, 프로그램 및 장치 | |
| KR20240013676A (ko) | 심전도를 이용한 심근경색 진단 방법, 프로그램 및장치 | |
| WO2024019584A1 (ko) | 심전도를 이용한 심근경색 진단 방법, 프로그램 및 장치 | |
| WO2024019575A1 (ko) | 심전도를 이용한 건강 상태의 예측 방법, 프로그램 및 장치 | |
| WO2025159552A1 (ko) | 딥 러닝 모델 기반의 생체 데이터로부터 환자의 중증도를 판단하는 방법, 장치 및 프로그램 | |
| WO2026054587A1 (ko) | 복수의 학습 데이터 셋에 기초하여 사용자의 상태를 파악하도록 학습된 신경망 모델을 획득하는 장치, 방법 및 프로그램 | |
| WO2025105848A1 (ko) | 심전도 판독 정보를 제공하는 방법, 프로그램 및 장치 | |
| WO2024205254A1 (ko) | 인공지능 기반 감염병 모니터링 방법, 프로그램 및 장치 | |
| WO2024019500A1 (ko) | 심전도 세그먼트를 이용한 건강 상태의 예측 방법, 프로그램 및 장치 | |
| WO2024039218A1 (ko) | 생체신호 데이터의 증강 방법, 컴퓨터 프로그램 및 장치 | |
| WO2026014979A1 (ko) | 심전도 데이터에 기초하여 사용자의 좌심실 이완 기능 부전을 예측하는 장치, 방법 및 컴퓨터 프로그램 | |
| WO2026029451A1 (ko) | 셀프 라벨링 방식을 통해 획득된 학습 데이터에 기초하여 신경망 모델을 학습시키는 장치, 방법 및 컴퓨터 프로그램 | |
| WO2024019523A1 (ko) | 심전도를 이용한 건강 상태의 예측 방법, 프로그램 및 장치 | |
| WO2025198398A1 (ko) | 심전도를 기반으로 질환을 진단하는 인공지능을 생성하는 방법, 프로그램 및 장치 | |
| CN117979902A (zh) | 以深度学习为基础计测连续的身体状态的方法、计算机程序及装置 | |
| WO2025211677A1 (ko) | 심전도 데이터에 기초하여 부르가다 증후군을 진단하는 방법, 장치 및 프로그램 | |
| WO2024191200A1 (ko) | 인공 지능 모델에 기반하여 잠재적 심방 세동을 식별하는 방법, 프로그램 및 장치 | |
| WO2024014888A1 (ko) | 단기 측정된 심장 신호를 기반으로 장기 심박 변이도를 생성하는 방법, 프로그램 및 장치 |
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: 22873168 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2024516342 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202280062072.1 Country of ref document: CN |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18692334 Country of ref document: US Ref document number: 2022873168 Country of ref document: EP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202447022082 Country of ref document: IN |
|
| ENP | Entry into the national phase |
Ref document number: 2022873168 Country of ref document: EP Effective date: 20240315 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |