Prediction method for chronic diseases based on electrocardiogram signals

Abstract

According to an embodiment of the present disclosure, a method for predicting a chronic disease based on an electrocardiogram signal, the method being executed in a computing device, may include generating lead-specific integrated data based on the electrocardiogram signal, generating N-dimensional input data based on the lead-specific integrated data, predicting a chronic disease based on the N-dimensional input data, and generating prognostic information related to the chronic disease to be provided to a user.

Description

Technical Field

[0001] The present invention relates to a method for analyzing biological signals, and more specifically, to a method for predicting chronic diseases based on electrocardiogram signals using machine learning.

Background Art

[0002] Development related to technologies using electrocardiogram signals as raw data for the diagnosis and prediction of chronic diseases has been attempted in various fields. One of them is a method that utilizes artificial intelligence. In order to utilize artificial intelligence, it is necessary to perform a preliminary operation of processing the electrocardiogram signal so that the artificial intelligence can analyze it. When using the one-dimensional electrocardiogram signal as input data for the artificial intelligence model as it is, the information of the lead where the electrocardiogram signal is measured is included in the calculation channel, and there is a problem that the degree of freedom for processing the correlation between leads that must be considered for the diagnosis and prediction of chronic diseases decreases. Therefore, it is necessary to adjust the input format of the electrocardiogram signal, and it is necessary to process the electrocardiogram signal so that unique information is not lost in the process of adjusting the input format.

[0003] In order to address the above-mentioned necessity, conventionally, a method of converting the frequency domain has been used to process a one-dimensional electrocardiogram signal into a two-dimensional image format and used as input data for an artificial intelligence model. However, such a conventional method has a problem that it becomes difficult to analyze time-series information. In addition, conventionally, a method of separately inputting lead information has been attempted in order to use the one-dimensional signal as it is. However, such an attempt has a problem that although the artificial intelligence model can utilize the correlation between leads in the calculation process, it becomes difficult for domain experts to analyze the importance of each lead for diagnosing chronic diseases.

[0004] Republic of Korea Patent Registration No. 10-2119169 (May 29, 2020) discloses a method for generating a two-dimensional image of an electrocardiogram signal.

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure is devised in response to the foregoing background art, and aims to provide a method for predicting chronic diseases based on machine learning that can analyze the mutual importance between leads for electrocardiogram measurement without losing the inherent information of electrocardiogram signals.

Means for Solving the Problems

[0006] Based on an embodiment of the present disclosure for realizing the foregoing problems, a method for predicting chronic diseases based on electrocardiogram signals, which is executed by a computing device, is disclosed. The method includes: generating gradient information and interval information for each waveform of the electrocardiogram signal from electrocardiogram data; generating integrated data for each lead based on at least one of the electrocardiogram data, the gradient information, and the interval information for each waveform; and generating N-dimensional input data based on the integrated data for each lead.

[0007] In an alternative embodiment, the step of generating the gradient information and the interval information for each waveform includes: sampling the electrocardiogram signal through interpolation to generate the electrocardiogram data; generating the gradient information based on the differential value for each sample of the electrocardiogram data; and generating the interval information for each waveform based on the numerical values of a plurality of electrocardiogram signal waveforms included in the electrocardiogram data.

[0008] In an alternative embodiment, the step of generating the interval information for each waveform based on the numerical values of a plurality of electrocardiogram signal waveforms included in the electrocardiogram data includes: extracting the characteristic value of each of the plurality of electrocardiogram signal waveforms included in the electrocardiogram data; deriving the numerical value corresponding to the characteristic value of each of the plurality of electrocardiogram signal waveforms, and normalizing each of the plurality of electrocardiogram signal waveforms based on the derived numerical value; and generating the interval information for each waveform by combining the numerical values of each of the plurality of normalized electrocardiogram signal waveforms.

[0009] In an alternative embodiment, the step of generating the lead-by-lead integrated data may include a step of generating the lead-by-lead integrated data by combining two or more of the electrocardiogram data, gradient information, and waveform interval information.

[0010] In an alternative embodiment, the step of generating the N-dimensional input data may include a step of arranging the lead-by-lead integrated data on a plane to generate N-dimensional input data in the form of a matrix that represents the time-series information and spatial information of the electrocardiogram signal.

[0011] In an alternative embodiment, the method may further include a step of predicting a chronic disease of a subject corresponding to the electrocardiogram signal based on the N-dimensional input data using a pre-trained machine learning model.

[0012] In an alternative embodiment, the machine learning model may include an encoder that receives the input of the N-dimensional input data and extracts features; and a decoder that generates information related to a plurality of different types of chronic diseases based on the extracted features.

[0013] In an alternative embodiment, the machine learning model may include an encoder that receives the input of the N-dimensional input data and extracts features; and a decoder that generates information related to one chronic disease based on the extracted features. In this case, if there are two or more decoders, each of the two or more decoders may generate information related to different types of chronic diseases.

[0014] In an alternative embodiment, the machine learning model may be trained based on N-dimensional learning data including the time-series information and spatial information of the electrocardiogram signal.

[0015] In an alternative embodiment, the method may further include generating a user interface based on information related to chronic diseases predicted by the machine learning model.

[0016] Based on one embodiment of the present disclosure for realizing the above problems, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed in one or more processors, it causes the following operations to be performed for predicting chronic diseases based on electrocardiogram signals, and the operations are: generating gradient information and waveform-specific interval information of electrocardiogram signals from electrocardiogram data; generating lead-specific integrated data based on at least one of the electrocardiogram data, gradient information, and waveform-specific interval information; and generating N-dimensional input data based on the lead-specific integrated data.

[0017] Based on one embodiment of the present disclosure for solving the above problems, a computing device for predicting chronic diseases based on electrocardiogram signals is disclosed. The device includes a processor including at least one core; a memory including a plurality of program codes executable in the processor; and a network unit for receiving electrocardiogram signals, and the processor can generate gradient information and waveform-specific interval information of electrocardiogram signals from electrocardiogram data, generate lead-specific integrated data based on at least one of the electrocardiogram data, gradient information, and waveform-specific interval information, and generate N-dimensional input data based on the lead-specific integrated data.

[0018] Based on an embodiment of the present disclosure for realizing the foregoing problems, a user terminal providing a user interface is disclosed. The user terminal may include a processor including at least one core; a memory; a network unit receiving a user interface based on analysis information of an electrocardiogram signal from a computing device; and an output unit providing the user interface. In this case, the analysis information of the electrocardiogram signal may include information related to a chronic disease predicted through a pre-trained machine learning model based on N-dimensional input data generated from the electrocardiogram signal.

Advantages of the Invention

[0019] The present disclosure can provide a machine learning-based prediction method for chronic diseases that can analyze the mutual importance between leads for electrocardiogram measurement without losing the unique information of the electrocardiogram signal.

Brief Description of the Drawings

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

[0021] Various embodiments will be described below with reference to the drawings. In this specification, various explanations are presented to facilitate the understanding of the present disclosure. However, it is obvious that such embodiments can be implemented even without such specific explanations.

[0022] As used herein, terms such as "component", "module", "system", etc. refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component can be a processing procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer, but is not limited thereto. For example, both an application executed on a computing device and the computing device can be components. One or more components can be resident within a processor and / or an execution thread. One component can be localized within one computer. One component can be distributed across two or more computers. Also, such components can be executed in various computer-readable media having various data structures stored therein. A component can communicate through local and / or remote processing, for example, using a signal (e.g., data and / or signals from one component interacting with other components in a local system or a distributed system, and data transmitted through a network such as the Internet) including one or more data packets.

[0023] Note that the term "or" is used with the intention of meaning an inclusive "or" rather than an exclusive "or". That is, when not specifically specified and not clear from the context, "X uses A or B" is intended to mean one of the natural inclusive substitutions. That is, it is possible that "X uses A or B" applies to any of the following cases: X uses A; X uses B; or X uses both A and B. Also, the term "and / or" in this specification should be understood to refer to all possible combinations of one or more of the listed multiple related items and to include them.

[0024] Also, the term "comprising (including)" as a predicate and / or the term "comprising (including)" as a modifier should be understood to mean that the said feature and / or component exists. However, the term "comprising (including)" as a predicate and / or the term "comprising (including)" as a modifier should be understood not to exclude the existence or addition of one or more other further features, components and / or groups thereof. Also, when the number is not specifically specified or when it is not clear from the context that the singular form is indicated, the singular number in this specification and the claims should generally be interpreted to mean "one or more".

[0025] And the term "at least one of A or B" should be interpreted to mean "the case where only A is included", "the case where only B is included", "the case of a combination of A and B".

[0026] Those skilled in the art should further recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described as being related to the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design constraints of the overall system. A skilled technician can implement the described functionality in various ways for individual specific applications. However, such a determination of implementation should not be construed as departing from the scope of the present disclosure.

[0027] The description of the embodiments shown herein is provided so that those of ordinary skill in the art of the present disclosure can utilize or implement the present invention. Various modifications to such embodiments will be clearly understood by those of ordinary skill in the art of the present disclosure. The general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present invention is not limited only to the embodiments shown herein. The present invention should be construed in the broadest scope consistent with the principles and novel features shown herein.

[0028] In the present disclosure, network functions, artificial neural circuits, and neural networks can be used interchangeably.

[0029] FIG. 1 is a block configuration diagram of a computing device for predicting chronic diseases based on an electrocardiogram signal according to an embodiment of the present disclosure.

[0030] The configuration of the computing device (100) illustrated in FIG. 1 is merely an exemplary simplified illustration. In one embodiment of the present disclosure, the computer device (100) may include other configurations for implementing the computing environment of the computer device (100), and it is also possible to configure the computer device (100) with only a part of the disclosed configurations.

[0031] The computer device (100) can include a processor (110), a memory (130), and a network unit (150).

[0032] In one embodiment of the present disclosure, the processor (110) can be composed of one or more cores, and can include a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), or other processors for data analysis and deep learning. The processor (110) can read a computer program stored in the memory (130) and execute data processing for machine learning in one embodiment of the present disclosure. Based on one embodiment of the present disclosure, the processor (110) can perform operations for neural network learning. In deep learning (DL), the processor (110) can execute calculations for neural network learning, such as processing input data for learning, extracting features from the input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) can process network function learning. For example, both the CPU and GPGPU can perform network function learning and data classification using network functions. Note that in one embodiment of the present disclosure, the processors of multiple computing devices can be used together to perform network function learning and data classification using network functions. Also, the computer program executed in the computing device in one embodiment of the present disclosure can be a program executable by a CPU, GPGPU, or TPU.

[0033] In one embodiment of the present disclosure, the processor (110) can perform preprocessing to convert an electrocardiogram signal into an input format of a machine learning model for predicting chronic diseases. The processor (110) can generate N-dimensional (N is a natural number) input data used for predicting chronic diseases based on a one-dimensional electrocardiogram signal measured via at least two or more leads. For example, the processor (110) can perform a sampling operation to digitize an electrocardiogram signal that is an analog signal measured by a 12-lead electrocardiogram. The processor (110) can extract unique information of each electrocardiogram signal from a plurality of electrocardiogram data generated through the sampling operation. The processor (110) can generate two-dimensional input data based on at least one of a plurality of electrocardiogram data and unique information of a plurality of electrocardiogram signals. The processor (110) can combine two or more of a plurality of electrocardiogram data and unique information of a plurality of electrocardiogram signals by lead and generate two-dimensional input data based on the combined result. The two-dimensional input data generated in such a manner can include both information related to the time of the electrocardiogram signal and information related to the leads of the electrocardiogram signal. Therefore, the processor (110) can generate interpretable data in the machine learning model without losing the time series information and spatial information of the electrocardiogram signal.

[0034] The processor (110) can learn a machine learning model for predicting chronic diseases based on the N-dimensional input data generated by preprocessing. For example, the processor (110) can input the two-dimensional input data into the model and learn the model to predict whether the subject corresponding to the electrocardiogram signal has a specific chronic disease. The processor (110) can also input the two-dimensional input data into the model and learn the model to estimate the quantitative value of the specific chronic disease suffered by the subject of the electrocardiogram signal. That is, depending on the purpose of using the prediction result of chronic diseases, the processor (110) can learn the machine learning model in various ways based on the two-dimensional input data generated by preprocessing for the one-dimensional electrocardiogram signal.

[0035] The processor (110) can predict chronic diseases based on the N-dimensional input data generated by preprocessing for the electrocardiogram signal using a pre-trained machine learning model. In this case, since the N-dimensional input data contains both the information related to the time of the electrocardiogram signal and the information related to the leads without loss, the machine learning model can output a prediction result of chronic diseases that can analyze not only the unique information of the electrocardiogram signal but also the mutual importance between leads. Therefore, there is an advantage that the processor (110) does not need to separately analyze the mutual importance for each lead or re-learn the machine learning model to grasp the information for each lead. In addition, there is an advantage that the processor (110) does not need to perform processing through a separate visualization operation such as a heatmap so that the main expert can analyze the correlation for each lead.

[0036] The processor (110) can generate a user interface based on the prediction results of chronic diseases generated through a machine learning model. In this case, the prediction results of chronic diseases output by the machine learning model can include the occurrence probabilities of various chronic diseases including cardiovascular diseases, brain diseases, and lung diseases, the presence or absence based on the occurrence probabilities of each of the various chronic diseases, and the quantitative values of the chronic diseases currently suffered by the subject, etc. Depending on the purpose of utilization of the computing device (100) according to an embodiment of the present disclosure, it is possible that the entire output result in the above example is configured as one area and included in the user interface, but it is also possible that only a part of the output result is included in the user interface.

[0037] In one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (550).

[0038] In one embodiment of the present disclosure, the memory (130) can include at least one type of storage medium such as a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read-Only Memory (ROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Programmable Read-Only Memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. The computing device (100) can also operate in cooperation with a web storage that executes the storage function of the memory (130) on the internet. The description of the foregoing memory is merely illustrative and the present disclosure is not limited thereto.

[0039] In one embodiment of the present disclosure, the network unit (150) can operate in cooperation with a known wired or wireless communication system having any form.

[0040] The network unit (150) can receive an electrocardiogram signal from a signal measurement system. In this case, the signal measurement system can be understood as a system including all devices capable of measuring, storing, processing, etc. of the electrocardiogram signal. For example, the signal measurement system can include a portable electrocardiogram measurement device including leads that can contact the body of a subject, a database server that can be linked with the portable electrocardiogram measurement device, and the like. The network unit (150) can receive the electrocardiogram signal measured via leads with two or more various combinations through communication with the portable electrocardiogram measurement device. The network unit (150) can also receive the electrocardiogram signal that has been previously measured by the portable electrocardiogram measurement device and stored in the database server through communication with the database server.

[0041] In addition, the network unit (150) can transmit and receive information processed by the processor (110), the user interface, etc. through communication with other terminals. For example, the network unit (150) can provide the user interface generated by the processor (110) to a client (for example, a user terminal). Also, the network unit (150) can receive an external input of the user input to the client and transfer it to the processor (110). In this case, the processor (110) can process operations such as output, correction, change, addition, etc. of the information provided through the user interface based on the external input of the user received from the network unit (150).

[0042] On the one hand, the computing device (100) in an embodiment of the present disclosure can include a server as a computing system that transmits and receives information through communication with a client. In this case, the client can be any form of terminal that can access the server. For example, the computing device (100) serving as a server can receive an electrocardiogram signal from a signal measurement system, predict a chronic disease, and provide a user interface including the predicted result to a user terminal. In this case, the user terminal can output the user interface received from the computing device (100) serving as a server, and can receive or process information input through interaction with the user.

[0043] The user terminal can display the user interface provided to provide the analysis information of the chronic disease transmitted from the computing device (100) serving as a server. Although the illustration is omitted, the user terminal can include a network unit that receives the user interface from the computing device (100), a processor including at least one core, a memory, an output unit that provides the user interface, and an input unit that receives an external input input by the user.

[0044] In an additional embodiment, the computing device (100) can also include any form of terminal that receives a data resource generated in any server and performs additional information processing.

[0045] Figure 2 is a schematic diagram showing a network function in an embodiment of the present disclosure.

[0046] A machine learning model for chronic disease prediction or a deep learning model for preprocessing an electrocardiogram signal according to an embodiment of the present disclosure may include a neural circuit network. Throughout this specification, an arithmetic model, a neural circuit network, a network function, and a neural network can be used interchangeably. A neural circuit network generally consists of a set of interconnected computational units commonly called nodes. Such nodes can also be referred to as neurons. A neural circuit network is configured to include at least one or more nodes. The nodes (or neurons) that make up the neural circuit network can be interconnected by one or more links.

[0047] In a neural circuit network, one or more nodes connected via a link can form a relative relationship of input nodes and output nodes. The concepts of input nodes and output nodes are relative. Any node that becomes an output node for a certain node can become an input node in the relationship with other nodes, and vice versa. As described above, the relationship between the input node and the output node can be established centering around the link. One or more output nodes can be connected to one input node via a link, and vice versa.

[0048] In the relationship between the input node and the output node connected via one link, the value of the data of the output node can be determined based on the data input to the input node. Here, the node connecting the input node and the output node can have a weight value. The weight value can be variable, but it can be changed by the user or an algorithm for the neural circuit network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by each link, the output node can determine the value of the output node based on the values input to the input nodes connected to the output node and the weight values set for the links corresponding to each input node.

[0049] As described above, a neural circuit network is formed by interconnecting one or more nodes via one or more links to form the relationship between the input nodes and the output nodes within the neural circuit network. In a neural circuit network, the characteristics of the neural circuit network can be determined by the number of nodes and links, the correlation relationship between the nodes and links, and the values of the weighted values assigned to each link. For example, when there are two neural circuit networks with the same number of nodes and links but different values of the weighted values of the links, the two neural circuit networks can be recognized as different ones.

[0050] A neural circuit network can be composed of a set of one or more nodes. A subset of the nodes that make up the neural circuit network can form a layer. Among the multiple nodes that make up the neural circuit network, some can form one layer based on the distance from the first input node. For example, a set of nodes with a distance of n from the first input node can form the nth layer. The distance from the first input node can be defined based on the minimum number of links that must be passed through to reach the node from the first input node. However, such a definition of a layer is arbitrarily cited for the purpose of explanation, and the configuration of the layer within the neural circuit network can be defined in a way different from the above description. For example, the layer of nodes can also be defined based on the distance from the final output node.

[0051] The first input node can mean one or more nodes among the nodes in the neural circuit network where data is directly input without passing through a link in the relationship with other nodes. Or, within the network of the neural circuit network, it can mean a node that does not have other input nodes connected via a link in the relationship between nodes based on the link. Similarly, the final output node can mean one or more nodes among the nodes in the neural circuit network that do not have an output node in the relationship with other nodes. Also, a hidden node can mean a node that is not the first input node or the final output node and constitutes the nodes of the neural circuit network.

[0052] The neural circuit network according to an embodiment of the present disclosure can be a neural circuit network in which the number of nodes in the input layer is the same as the number of nodes in the output layer, and as it progresses from the input layer to the hidden layer, the number of nodes first decreases and then increases again. The neural circuit network according to an embodiment of the present disclosure can be a neural circuit network in which the number of nodes in the input layer is less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. Further, the neural circuit network according to another embodiment of the present disclosure can be a neural circuit network in which the number of nodes in the input layer is more than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. The neural circuit network in another embodiment of the present disclosure can be a neural circuit network that combines the above-described neural circuit networks.

[0053] A deep neural network (DNN) can be meant to refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. By using a deep neural network, the latent structures of data can be grasped. That is, it is possible to grasp the latent structures of photos, articles, videos, voices, music (for example, whether a certain object is shown in a photo, what the content and sentiment of an article are, what the content and sentiment of a voice are, etc.). Deep neural networks can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, GANs (Generative Adversarial Networks), restricted boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Sham networks, Generative Adversarial Networks (GANs), etc. The above-mentioned deep neural networks are merely examples and the present disclosure is not limited thereto.

[0054] In one embodiment of the present disclosure, the network function may also include an autoencoder. The autoencoder can be a type of artificial neural network circuit for outputting output data similar to the input data. The autoencoder can include at least one hidden layer, and an odd number of hidden layers can be arranged between the input and output layers. The number of nodes in each layer can decrease from the number of nodes in the input layer towards the intermediate layer called the bottleneck layer (encoding), and can also expand in a form contrasting with the reduction from the bottleneck layer towards the output layer (symmetric to the input layer). The autoencoder can perform non-linear dimensionality reduction. The number of input and output layers can correspond to the dimensions after preprocessing the input data. In the autoencoder structure, the number of nodes in the hidden layers included in the encoder can have a structure that decreases as it gets farther from the input data. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and the decoder) is too small, there is a possibility that not enough information will be transmitted, so it may be maintained above a specific number (for example, more than half of the input layer, etc.).

[0055] The neural network can be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. The training of the neural network can be a process of providing the neural network with knowledge for the neural network to perform a specific operation.

[0056] A neural network can be trained in a direction to minimize the error of the output. In the training of a neural network, training data is repeatedly input into the neural network, the error between the output of the neural network regarding the training data and the target is calculated, and the error of the neural network is backpropagated from the output layer of the neural network to the input layer in the direction to reduce the error, and the weight values of each node of the neural network are updated. In the case of supervised learning, training data with the correct answer labeled for each individual training data is used (that is, labeled training data), and in the case of unsupervised learning, there may be cases where the correct answer is not labeled for each individual training data. That is, for example, the training data in supervised learning regarding data classification can be data where each category is labeled for each of the training data. By inputting the labeled training data into the neural network and comparing the output (category) of the neural network with the label of the training data, it is possible to calculate the error. As another example, in the case of unsupervised learning regarding data classification, it is possible to calculate the error by comparing the input training data with the output of the neural network. The calculated error is backpropagated in the reverse direction (that is, from the output layer to the input layer direction) in the neural network, and it is possible to update the connection weight values of each node of each layer of the neural network through backpropagation. The amount of change in the connection weight value of each updated node can be determined by the learning rate. The calculation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The application method of the learning rate can change depending on the number of repetitions of the learning cycle of the neural network. For example, at the initial stage of the training of the neural network, the learning rate can be increased to improve the efficiency by enabling the neural network to quickly ensure a certain level of performance, and at the latter half of the training, the learning rate can be decreased to improve the accuracy.

[0057] In the learning of neural networks, generally, the training data can be a subset of the actual data (that is, the data to be processed using the trained neural network). Therefore, there can be a learning cycle in which the error related to the training data decreases, but the error related to the actual data increases. Overfitting is a phenomenon in which the error increases in the actual data because of excessive learning about the training data. For example, a neural network that has learned cats by seeing yellow cats may not be able to recognize a cat of a color other than yellow as a cat, which can be a type of overfitting. Overfitting can cause an increase in the error of machine learning algorithms. To prevent such overfitting, various optimization methods can be applied. To prevent overfitting, methods such as increasing the training data, regularization, dropout (deactivating some of the nodes in the network during the learning process), and utilization of a batch normalization layer can be applied.

[0058] FIG. 3 is a flowchart showing a preprocessing process for an electrocardiogram signal in an embodiment of the present disclosure. And FIG. 4 is a conceptual diagram showing a process of generating integrated data for each lead based on an embodiment of the present disclosure. Hereinafter, the preprocessing and the process of predicting chronic diseases based on an embodiment of the present disclosure will be described based on two-dimensional input data, which is one of the N-dimensional input data.

[0059] As shown in FIG. 3, in step S110, a computing device (100) according to an embodiment of the present disclosure can digitally sample an electrocardiogram signal to generate electrocardiogram data. The computing device (100) can generate electrocardiogram data, which is a digital signal, from an electrocardiogram signal, which is an analog signal, through interpolation. Interpolation can be understood as an operation of reconstructing missing values between a plurality of samples created by capturing analog amplitudes at specific time intervals. In this case, it is possible to determine at what time interval the signal is captured to generate samples based on a predetermined sample rate. For example, the computing device (100) can perform interpolation based on a predetermined sampling rate for each pre-trained machine learning model and process the electrocardiogram signal. The computing device (100) can process the sampled electrocardiogram signal through interpolation to a length corresponding to the input length of the model. The computing device (100) can generate electrocardiogram data from the electrocardiogram signal through the aforementioned interpolation and length processing.

[0060] In step S110, the computing device (100) can generate gradient information of the electrocardiogram signal from the electrocardiogram data. The computing device (100) can generate gradient information of the electrocardiogram signal based on the differential value for each sample of the electrocardiogram data. In this case, the gradient information can be understood as unique information of the electrocardiogram signal indicating the direction of the peak value of the electrocardiogram signal. For example, if the number of samples of the electrocardiogram data generated through the above process is N (N is a natural number), the computing device (100) can calculate the differential value based on the N samples and calculate N - 1 gradient information. The computing device (100) can calculate the last gradient information insufficient for the number of samples through various padding methods such as constant padding and symmetric padding. That is, the computing device (100) can make the calculated N - 1 gradient information become N through padding and generate the same number of gradient information as the samples of the electrocardiogram data.

[0061] Also, the computing device (100) can generate interval information for each waveform of the electrocardiogram signal from the electrocardiogram data. The computing device (100) can generate interval information for each waveform based on the numerical values of a plurality of electrocardiogram signal waveforms included in the electrocardiogram data. For example, the waveforms of the electrocardiogram signal reflecting the electrical activation stage of the heart can basically be classified into P waves, QRS - complexes, T waves, and other waveforms. The computing device (100) can normalize a plurality of different numerical values related to the waveforms corresponding to P waves, QRS - complexes, T waves, and others. In this case, the numerical values to be normalized can also include the peak values of each of the P wave, Q wave, R wave, S wave, and T wave. The computing device (100) can configure the numerical values for each waveform normalized based on the time - series information of the electrocardiogram data to have a length corresponding to the electrocardiogram data and generate interval information for each waveform of the electrocardiogram signal.

[0062] Specifically, the computing device (100) can extract the characteristic values of each of the plurality of electrocardiogram signal waveforms included in the electrocardiogram data. For example, the computing device (100) can extract the characteristic values of a plurality of waveforms constituting the electrocardiogram signal, such as P waves, QRS complexes, T waves, etc., through a pre-trained deep learning model. In this case, the characteristic values can include the unique information of each of the plurality of electrocardiogram signal waveforms including P waves, QRS complexes, and T waves, such as the onset point time of the P wave, the offset point time of the P wave, the onset point time of the QRS complex, etc. The computing device (100) can also extract the characteristic values of each signal waveform based on a specific rule.

[0063] The computing device (100) can derive the numerical values of each signal waveform corresponding to the characteristic values of each signal waveform. The computing device (100) can process the waveforms constituting the electrocardiogram signal into a form corresponding to the electrocardiogram signal based on the numerical values of each signal waveform. The computing device (100) can combine the plurality of electrocardiogram signal waveforms processed into a form corresponding to the electrocardiogram signal to generate waveform-specific interval information. For example, the computing device (100) can derive that the numerical value corresponding to the characteristic value of the P wave is 1, the numerical value corresponding to the characteristic value of the QRS complex is 2, the numerical value corresponding to the characteristic value of the T wave is 3, and the numerical values corresponding to the characteristic values of the other remaining waveforms are 0. The computing device (100) can normalize the P wave, QRS complex, T wave, and the other remaining waveforms based on the numerical values of each waveform. The computing device (100) can combine the normalized P wave, QRS complex, T wave, and the other remaining waveforms to generate one piece of waveform-specific interval information. Note that the specific numerical values such as 1, 2, 3, and 0 are only examples and can be changed to other values within the range understandable by those skilled in the art.

[0064] In step S120, the computing device (100) can generate lead-by-lead integrated data based on at least one of the electrocardiogram data, gradient information, and waveform interval information generated through step S110. The computing device (100) can also generate lead-by-lead integrated data by combining two or more of the three data without considering the order. In this case, the number and types of data combined for generating the lead-by-lead integrated data can vary depending on the purpose of utilizing the prediction results of chronic diseases. For example, as shown in FIG. 4, the computing device (100) can execute a convolution operation by combining electrocardiogram data (11), gradient information (13), and waveform interval information (15). In other words, the computing device (100) can execute a convolution operation to combine the electrocardiogram data (11), gradient information (13), and waveform interval information (15) to generate integrated data (17) for a specific lead. However, the operations for combining data can include all possible operations provided for combining data, such as multiplication, addition, average operation, etc., in addition to the above-mentioned convolution operation. The lead-by-lead integrated data generated through such a process supports the machine learning model to perform data analysis for predicting chronic diseases based on information and criteria similar to those of human domain experts.

[0065] In step S130, the computing device (100) can generate two-dimensional input data used for input to a machine learning model for predicting chronic diseases based on the lead-by-lead integrated data generated through step S120. In this case, the two-dimensional input data can be in the form of a matrix representing the time-series information and spatial information of the electrocardiogram signal. For example, the computing device (100) can generate input data in the form of a two-dimensional matrix where the lead-by-lead integrated data is arranged on a plane based on the same time point, the X-axis represents the time-series information, and the Y-axis represents the lead information. Assuming that the number of leads used for measuring the electrocardiogram signal is K (K is a natural number), the computing device (100) can arrange the K lead-by-lead integrated data at the same time point based on the time interval T on a plane to generate input data in the form of a KxT two-dimensional matrix. An example of the two-dimensional input data can be confirmed by referring to the image (20) illustrated in FIG. 6 or FIG. 7 described later. The two-dimensional input data generated through such a process enables integrated processing of the spatial information of the electrocardiogram signal and supports the effective reflection of the lead-by-lead correlation relationship necessary for diagnosing a specific chronic disease in the inference process of the machine learning model.

[0066] FIG. 5 is a flowchart relating to a method for predicting chronic diseases based on an electrocardiogram signal according to an embodiment of the present disclosure.

[0067] Referring to FIG. 5, based on an embodiment of the present disclosure, the step S210 of generating two-dimensional input data based on an electrocardiogram signal can be understood to correspond to all the steps shown in FIG. 3 described above. Therefore, additional description regarding step S210 is omitted.

[0068] In step S220, the computing device (100) in one embodiment of the present disclosure can predict the chronic diseases of the subject who has had an electrocardiogram signal measured, based on the two-dimensional input data generated in step S210, through a pre-trained machine learning model. For example, the computing device (100) can input two-dimensional input data in which the time-series information and spatial information of the electrocardiogram signal are arranged in a matrix format into the machine learning model. The machine learning model can infer the presence or absence of various types of chronic diseases, quantitative numerical values, etc., based on the features present in the two-dimensional input data. In this case, the machine learning model can also receive inputs such as biological information and environmental information related to the subject corresponding to the electrocardiogram signal, and can also perform predictions of chronic diseases. Chronic diseases that the machine learning model can predict can all include cardiovascular diseases such as arrhythmia, heart failure, myocardial infarction, etc., brain diseases such as cerebral hemorrhage, cerebral infarction, stroke, etc., lung diseases such as pulmonary thromboembolism, and other chronic diseases such as diabetes and hypertension. Therefore, the computing device (100) can derive, as analysis information of the electrocardiogram signal, all chronic diseases that the machine learning model can predict, or probability information, linear numerical information, etc. related to a part thereof, according to the purpose of utilization.

[0069] In step S230, the computing device (100) can generate a user interface based on the analysis information of the electrocardiogram signal, which is the prediction result of the chronic disease generated in step S220. The computing device (100) can generate a user interface based on all or part of the analysis information of the electrocardiogram signal, including probability information indicating the presence or absence of a specific chronic disease, linear numerical information indicating the severity of a specific chronic disease, etc. For example, the computing device (100) can generate a user interface including a first region indicating probability information related to the presence or absence of cardiovascular disease and a second region indicating linear numerical information related to the severity of cardiovascular disease. The computing device (100) can provide the user interface that outputs the prediction result of the chronic disease to the user terminal, to the user terminal via communication with the user terminal.

[0070] Each of FIGS. 6 and 7 is a block configuration diagram showing the structure of a machine learning model in an embodiment of the present disclosure.

[0071] Referring to FIG. 6, a machine learning model (200) in an embodiment of the present disclosure can include an encoder (210) that receives an input of two-dimensional input data (20) and extracts features, and a decoder (220) that generates information (31, 33, 35, 36) related to a plurality of different types of chronic diseases based on the features extracted by the encoder. Since the machine learning model (200) receives an input of two-dimensional input data (20) including spatial information related to leads of an electrocardiogram signal, it is possible to extract features of the input data through one encoder (210), which is different from the conventional method. Therefore, compared with the existing one-dimensional model or the two-dimensional model based on frequency conversion, the model can be downsized, and the data processing speed of the model can be significantly improved. In addition, since the machine learning model (200) can perform integrated processing on spatial information by using two-dimensional input data (20), the accuracy of predicting and determining a specific chronic disease can be significantly improved compared with the conventional model.

[0072] The machine learning model (200) can generate information (31, 33, 35, 36) related to different types of chronic diseases based on the features of the two-dimensional input data (20) extracted by the encoder (210) through one decoder (220). For example, the decoder (220) can output at least one or more of brain disease information (31), cardiovascular disease information (33), lung disease information (35), and other chronic disease information (36) such as diabetes based on the features of the two-dimensional input data (20). In this case, the information related to a specific chronic disease may include a prediction result related to the presence or absence of a specific chronic disease, a judgment result for a quantitative value related to a specific chronic disease, and the like. The decoder (220) can also selectively output brain disease information (31), cardiovascular disease information (33), lung disease information (35), and other chronic disease information (36) through the control of the computing device (100) for the machine learning model (200).

[0073] Referring to FIG. 7, the machine learning model (200) in an alternative embodiment of the present disclosure can include a plurality of decoders (221, 222, 223, 224) that generate information (31, 33, 35, 36) related to different types of a plurality of chronic diseases based on the features extracted by the encoder. Different from FIG. 6, the machine learning model (200) can include a plurality of decoders (221, 222, 223, 224) that individually correspond to different types of chronic diseases. For example, the machine learning model (200) can include a first decoder (221) that generates brain disease information (31), a second decoder (222) that generates cardiovascular disease information (33), a third decoder (223) that generates lung disease information (35), and an Nth decoder (224) that generates other chronic disease information (36). In this case, when other chronic diseases are further subdivided, the Nth decoder (224) can also be subdivided into a plurality of ones in the same way. The machine learning model (200) can independently operate a plurality of decoders (221, 222, 223, 224) to selectively generate information related to various chronic diseases.

[0074] The types of the above chronic diseases are merely examples of positions, and various types of examples can be applied within the scope understandable by those skilled in the art.

[0075] Based on one embodiment of the present disclosure, a computer-readable storage medium storing a data structure is disclosed.

[0076] A data structure can mean the organization, management, and storage of data that enable efficient access to and modification of the data. A data structure can mean a data organization for solving a specific problem (e.g., data search in the shortest time, data storage, data modification). A data structure can also be defined as the physical or logical relationship between data elements designed to support a specific data processing function. The logical relationship between data elements can include the concatenation relationship between data elements considered by a user. The physical relationship between data elements can include the actual relationship between data elements physically stored in a computer-readable storage medium (e.g., a hard disk). A data structure can specifically include a set of data, the relationship between data, functions or commands applicable to the data. With an effectively designed data structure, a computing device can perform calculations while minimizing the use of the resources of the computing device. Specifically, the computing device can enhance the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through an effectively designed data structure.

[0077] Data structures can be classified into linear data structures and non-linear data structures according to their forms. A linear data structure may be a structure in which only one data is connected after another data. Linear data structures can include lists, stacks, queues, and deques. A list can mean a series of data sets with an internal order. A list can include a linked list. A linked list can be a data structure in which data is linked in a way that each data has a pointer and is linked in a column. In a linked list, the pointer can include connection information with the next or previous data. A linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list according to its form. A stack may be a data list structure with restricted access to data. A stack can be a linear data structure that can process (e.g., insert or delete) data only at one end of the data structure. The data stored in a stack can be a data structure (LIFO - Last in First Out) where the later the data enters, the earlier it comes out. A queue is a data arrangement structure with restricted access to data and, unlike a stack, can be a data structure (FIFO - First in First Out) where the later the data is stored, the later it comes out. A deque can be a data structure that can process data at both ends of the data structure.

[0078] A non-linear data structure may be a structure in which multiple data are connected after one data. Non-linear data structures can include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. A graph data structure can include a tree data structure. A tree data structure can be a data structure formed by a path connecting two different vertices among the multiple vertices included in the tree. That is, it can be a data structure that does not form a loop in the graph data structure.

[0079] Throughout this specification, an arithmetic model, a neural circuit network, a network function, and a neural network can be used interchangeably. (Hereinafter, they will be uniformly described using the term "neural network".) A data structure can include a neural network. And a data structure including a neural network can be stored in a computer-readable storage medium. A data structure including a neural network can also include data input to the neural network, weight values of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and a loss function for training the neural network. A data structure including a neural network can include any of the components of the disclosed configurations. That is, a data structure including a neural network can be configured to include all or any combination of data input to the neural network, weight values of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, a loss function for training the neural network, etc. In addition to the above-described configurations, a data structure including a neural network can include any other information that determines the characteristics of the neural network. Also, the data structure can include all forms of data used or generated in the arithmetic process of the neural network, and is not limited to the foregoing matters. A computer-readable storage medium can include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network can generally be composed of a set of interconnected computing units commonly called nodes. Such nodes can be called neurons. A neural network is composed of at least one or more nodes.

[0080] A data structure can include data input into a neural network. A data structure including data input into a neural network can be stored in a computer-readable storage medium. The data input into a neural network can include learning data input during the learning process of the neural network and / or input data input into the neural network after learning is completed. The data input into a neural network can include pre-processed data and / or data to be pre-processed. Pre-processing can include a data processing process for inputting the data into the neural network. Therefore, the data structure can include data to be pre-processed and data generated by the pre-processing. The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0081] A data structure can include the weights of a neural network. (In this specification, weights and parameters can be used interchangeably.) And a data structure including the weights of a neural circuit network can be stored in a computer-readable storage medium. A neural network can include a plurality of weights. The weights are variable and can be varied by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected by respective links to one output node, the output node can determine an output node value based on the values input to the input nodes connected to the output node and the parameters set for the respective links corresponding to the input nodes. The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0082] By way of example and not limitation, the weighted values can include weighted values that vary during the neural network learning process and / or weighted values after the neural network learning is completed. The weighted values that are varied during the neural network learning process can include the weighted values at the start of the learning cycle and / or the weighted values that are varied during the learning cycle. The weighted values after the neural network learning is completed can include the weighted values after the learning cycle is completed. Accordingly, a data structure including the weighted values of the neural network can include a data structure including the weighted values that vary during the neural network learning process and / or the weighted values after the neural network learning is completed. Accordingly, the above-described weighted values and / or combinations of each weighted value are assumed to be included in a data structure including the weighted values of the neural network. The foregoing data structure is merely exemplary and the present disclosure is not limited thereto.

[0083] A data structure including the weighted values of the neural network can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be a process of converting a data structure into a form that can be stored in the same or another computing device and later reconstructed and used. A computing device can serialize a data structure and transmit and receive data via a network. A data structure including the weighted values of the serialized neural network can be reconstructed on the same computing device or another computing device through deserialization. A data structure including the weighted values of the neural network is not limited to serialization. Further, a data structure including the weighted values of the neural network can include a data structure (e.g., non-linear data structures such as B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) for enhancing the efficiency of operations while minimizing the resources of the computing device. The foregoing matters are merely exemplary and the present disclosure is not limited thereto.

[0084] The data structure can include hyper-parameters of the neural network. And the data structure including the hyper-parameters of the neural network can be stored in a computer-readable storage medium. The hyper-parameters can be variables that can be changed by the user. The hyper-parameters can include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weights to be initialized), the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layer). The above-described data structure is only an example, and the present disclosure is not limited thereto.

[0085] FIG. 8 is a simplified and general schematic diagram related to an exemplary computing environment in which embodiments of the present disclosure can be implemented.

[0086] Although it has been described above that the present disclosure can generally be implemented by a computing device, those skilled in the art will well understand that the present disclosure can be implemented in combination with computer-executable instructions that can be executed on one or more computers and / or other program modules and / or as a combination of hardware and software.

[0087] Generally, a module in this specification includes routines, programs, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Those skilled in the art will also readily understand that the methods of the present disclosure can be implemented by other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based platforms, or programmable household appliances, and the like (each of which can operate in connection with one or more associated devices).

[0088] The embodiments described in the present disclosure can further be implemented in a distributed computing environment where a task is performed by a remote processing device connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote memory storage devices.

[0089] The computer includes a variety of computer-readable media. Any media accessible by the computer can be a computer-readable media, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-removable media. By way of example and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media is volatile and non-volatile media, transitory and non-transitory media, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media includes RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and can be used to store information, but is not limited thereto.

[0090] Computer-readable transmission media typically implements computer-readable instructions, data structures, program modules or other data, etc. in a modulated data signal such as a carrier wave or other transport mechanism, and includes all information transmission media. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or changed so as to encode information in the signal. By way of example and not limitation, computer-readable transmission media includes wired media such as a wired network or a direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Any combination by any of the foregoing media is also considered to be within the scope of computer-readable transmission media.

[0091] An exemplary environment (1100) is shown that implements various aspects of the present disclosure, including a computer (1102), which includes a processing device (1104), a system memory (1106), and a system bus (1108). The system bus (1108) couples system components, including but not limited to the system memory (1106), to the processing device (1104). The processing device (1104) can be any of a variety of commercial processors. Dual processors and other multiprocessor architectures can also be utilized as the processing device (1104).

[0092] The system bus (1108) can be any of a plurality of types of bus structures that can be further interconnected to a local bus that uses any of a memory bus, a peripheral device bus, and various commercial bus architectures. The system memory (1106) includes a read only memory (ROM) (1110) and a random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110) such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that support the exchange of information between multiple components within the computer (1102) during startup and the like. The RAM (1112) can also include high-speed RAM such as static RAM for caching data.

[0093] In the computer (1102), there is also a built-in hard disk drive (HDD) (1114) (e.g., EIDE, SATA) - this built-in hard disk drive (1114) can also be configured for external use within a suitable chassis (not shown) - a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from and writing to a removable diskette (1118)) and an optical disk drive (1120) (e.g., for reading from a CD-ROM disk (1122), reading from and writing to other high-capacity optical media such as DVDs). The hard disk drive (1114), magnetic disk drive (1116), and optical disk drive (1120) can each be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128), respectively. The interface (1124) for the implementation of an external drive includes, for example, at least one or both of USB (Universal Serial Bus) and IEEE1394 interface technologies.

[0094] These drives and the computer-readable media associated therewith provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of the computer (1102), the drives and media correspond to storing any data in a suitable digital format. Although the foregoing description of computer-readable storage media refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will also recognize that other types of storage media readable by a computer, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, can also be used in exemplary operating environments, and it will be well understood that any of such media can contain computer-executable instructions for performing the methods of the present disclosure.

[0095] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), can be stored in a drive and RAM (1112). All or a portion of the operating system, applications, modules, and / or data can also be cached in RAM (1112). It will be readily understood that the present disclosure can be implemented by various commercially available operating systems or combinations of multiple operating systems.

[0096] A user can input commands and information into a computer (1102) through one or more wired and wireless input devices, such as a keyboard (1138) and a pointing device like a mouse (1140). Other input devices (not shown) can include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and so on. These and other input devices may be connected to a processing device (1104) through an input device interface (1142) that is well-connected to a system bus (1108), but can also be connected by other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and others.

[0097] A monitor (1144) or other type of display device is also connected to the system bus (1108) through an interface such as a video adapter (1146). In addition to the monitor (1144), a computer generally includes other peripheral output devices such as speakers, printers, and others (not shown).

[0098] The computer (1102) can operate in a networked environment using logical connections to one or more remote computers, such as (multiple) remote computers (1148) via wired and / or wireless communication. The (multiple) remote computers (1148) can be workstations, server computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and generally include many or all of the components described for the computer (1102), but for simplicity only the memory storage device (1150) is shown. The illustrated logical connections include wired and wireless connections in a local area network (LAN) (1152) and / or a larger network, such as a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies, facilitating enterprise-wide computer networks such as intranets, all of which can be connected to the world-wide computer network, such as the Internet.

[0099] When used in a LAN networking environment, computer (1102) connects to local network (1152) through a wired and / or wireless communication network interface, or adapter (1156). Adapter (1156) can facilitate wired or wireless communication to LAN (1152), and this LAN (1152) also includes a wireless access point installed thereon for communicating with wireless adapter (1156). When used in a WAN networking environment, computer (1102) can include a modem (1158), connect to a communication server on WAN (1154), or have other means of setting up communication through WAN (1154), such as through the Internet. Modem (1158), which can be an internal or external, wired or wireless device, connects to system bus (1108) through serial port interface (1142). In a networked environment, program modules or portions thereof described for computer (1102) can be stored in remote memory / storage device (1150). It is readily understood that the illustrated network connections are exemplary and that other means of establishing communication links between multiple computers can be used.

[0100] Computer (1102) operates to communicate with any wireless device or unit arranged and operating in wireless communication, such as a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or location related to a wirelessly detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth (registered trademark) wireless technologies. Thus, the communication can be in a predefined structure like a conventional network or simply be ad hoc communication between at least two devices.

[0101] Wi-Fi (Wireless Fidelity) enables connection to the Internet and the like without being wired. Wi-Fi is a wireless technology such as a cell phone that allows such devices, for example, computers to send and receive data indoors and outdoors, that is, from anywhere within the coverage area of a base station. Wi-Fi networks use wireless technologies such as IEEE 802.11 (a, b, g, etc.) to provide a secure, reliable, and high-speed wireless connection. Wi-Fi can be used to connect computers to each other and to the Internet and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate at data rates such as 11 Mbps (802.11a) or 54 Mbps (802.11b) in unlicensed 2.4 and 5 GHz wireless bands, or can operate in products that include both bands (dual-band).

[0102] Those of ordinary skill in the art to which this disclosure pertains can appreciate that information and signals can be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced in the foregoing description can be represented by voltages, currents, electromagnetic waves, magnetic fields, etc., or particles, optical fields, etc., or particles, or any combination thereof.

[0103] Those of ordinary skill in the art of the present disclosure will understand that the various exemplary logical blocks, modules, processors, means, circuits, algorithm steps recited in the description of the embodiments disclosed herein can be implemented by electronic hardware, various forms of programs or design codes (referred to herein as "software" for convenience), or any combination of these. To clearly illustrate such interchangeability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in terms of their functions. Whether such functions are implemented in hardware or software depends on the design constraints imposed on a particular application and the overall system. Those of ordinary skill in the art of the present disclosure can implement the functions described in various ways for individual specific applications, but such implementation decisions should not be construed as departing from the scope of the present disclosure.

[0104] The various embodiments shown herein can be implemented by a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes any computer program, carrier, or medium accessible from any computer-readable device. For example, computer-readable storage media includes, but is not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Also, the various storage media shown herein include one or more devices for storing information and / or other machine-readable media.

[0105] It should be understood that the specific order or hierarchical structure of the multiple steps in the presented process is an example of an exemplary approach. Based on design priorities, it should be understood that within the scope of the present disclosure, the specific order or hierarchical structure of the steps in the process can be rearranged. The appended method claims provide elements of various steps in sample order, but are not meant to be limited to the specific order or hierarchical structure shown.

[0106] The description of the presented embodiments is provided so that a person of ordinary skill in any art of the present disclosure can make use of or practice the present disclosure. Various modifications to such embodiments will be readily apparent to those of ordinary skill in the art of the present disclosure, and the general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Accordingly, the present disclosure is not limited by the embodiments shown herein, but should be construed in the broadest scope consistent with the principles and novel features shown herein.

Claims

1. A method for predicting chronic diseases based on an electrocardiogram signal, which is executed by a computing device including at least one processor, comprising: generating lead-by-lead integrated data by combining two or more of the electrocardiogram data generated from the electrocardiogram signal, the gradient information of the electrocardiogram signal, or the waveform-by-section information of the electrocardiogram signal, and generating two-dimensional input data based on the lead-by-lead integrated data; predicting the chronic disease through a pre-trained machine learning model based on the two-dimensional input data; generating prediction information related to the chronic disease provided to a user; and a method.

2. In Claim 1, the step of generating the two-dimensional input data includes: generating at least one of the gradient information of the electrocardiogram signal and the waveform-by-section information of the electrocardiogram signal; generating the lead-by-lead integrated data based on at least one of the gradient information of the electrocardiogram signal and the waveform-by-section information of the electrocardiogram signal; generating the two-dimensional input data based on the lead-by-lead integrated data; and a method.

3. In Claim 2, the step of generating at least one of the gradient information of the electrocardiogram signal and the waveform-by-section information of the electrocardiogram signal includes: sampling the electrocardiogram signal by interpolating missing values between a plurality of samples to generate the electrocardiogram data; generating the gradient information based on the differential values of the samples of the electrocardiogram data; generating the waveform-by-section information based on the numerical values of a plurality of electrocardiogram signal waveforms included in the electrocardiogram data; and a method.

4. In Claim 3, the step of generating the waveform-by-section information based on the numerical values of a plurality of electrocardiogram signal waveforms included in the electrocardiogram data includes: extracting the characteristic values of each of a plurality of electrocardiogram signal waveforms included in the electrocardiogram data; deriving the numerical values corresponding to the characteristic values of each of the plurality of electrocardiogram signal waveforms, and normalizing each of the plurality of electrocardiogram signal waveforms based on the derived numerical values; combining each of the normalized plurality of electrocardiogram signal waveforms to generate the waveform-by-section information; and a method.

5. In Claim 1, the step of generating the two-dimensional input data includes: Arranging the lead-by-lead integrated data on a plane to generate two-dimensional input data in the form of a matrix that represents the time-series information and spatial information of the electrocardiogram signal including a method

6. In claim 1 the step of predicting the chronic disease is the step of predicting the chronic disease of the subject corresponding to the electrocardiogram signal based on the two-dimensional input data using the machine learning model including a method

7. In claim 6 the machine learning model an encoder that receives the input of the two-dimensional input data and extracts features, a decoder that generates information related to a plurality of different types of chronic diseases based on the extracted features including a method

8. In claim 6 the machine learning model an encoder that receives the input of the two-dimensional input data and extracts features, a decoder that generates information related to one chronic disease based on the extracted features including when there are two or more decoders, each of the two or more decoders generates information related to a different type of chronic disease a method

9. In claim 6 the machine learning model is learned based on two-dimensional learning data including the time-series information and spatial information of the electrocardiogram signal a method

10. In claim 6 the step of generating prediction information related to the chronic disease provided to the user is the step of generating a user interface based on the prediction information related to the chronic disease predicted through the machine learning model including a method

11. A computer program stored in a computer-readable storage medium, when the computer program is executed in one or more processors, causes operations for predicting a chronic disease based on an electrocardiogram signal to be performed, the operations are generating lead-by-lead integrated data by combining two or more of the electrocardiogram data generated from the electrocardiogram signal, the gradient information of the electrocardiogram signal, or the waveform-by-waveform interval information of the electrocardiogram signal, and generating two-dimensional input data based on the lead-by-lead integrated data; predicting the chronic disease through a pre-trained machine learning model based on the two-dimensional input data; generating prediction information related to the chronic disease provided to the user; including A computer program stored on a computer-readable storage medium.

12. A computing device for predicting chronic diseases based on electrocardiogram signals, comprising: A processor including at least one core; A memory including a plurality of program codes executable by the processor; A network unit for receiving the electrocardiogram signals; The processor is configured to: Generate lead-specific integrated data by combining two or more of the electrocardiogram data generated from the electrocardiogram signals, the gradient information of the electrocardiogram signals, or the waveform-specific interval information of the electrocardiogram signals, generate two-dimensional input data based on the lead-specific integrated data, Predict the chronic diseases through a pre-trained machine learning model based on the two-dimensional input data, and Generate prediction information related to the chronic diseases provided to the user. Computing device.

13. A user terminal, comprising: A processor including at least one core; A memory; A network unit for receiving analysis information of electrocardiogram signals from a computing device; An output unit for providing the analysis information of the electrocardiogram signals, The analysis information of the electrocardiogram signals includes prediction information related to chronic diseases predicted based on the electrocardiogram signals, The prediction information related to the chronic diseases corresponds to the information predicted through a pre-trained machine learning model based on the lead-specific integrated data and the two-dimensional input data generated from the electrocardiogram signals, The lead-specific integrated data is generated by combining two or more of the electrocardiogram data generated from the electrocardiogram signals, the gradient information of the electrocardiogram signals, or the waveform-specific interval information of the electrocardiogram signals. Terminal. ​ ​

Images