How to predict heart age

Abstract

To provide a method of predicting heart age.SOLUTION: An exemplary embodiment of the present disclosure discloses a method of estimating heart age using a pretrained neural network model. In particular, according to the present disclosure, a computing device acquires vital sign data of a user and estimates the heart age of the user based on the vital sign data of the user using the pretrained neural network model, where the pretrained neural network model corresponds to a neural network model pretrained based on information related to heart disease.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a method for predicting heart age, and more particularly to a method for predicting heart age by inputting a user's biological signal data into a pre-trained neural network model based on information related to heart disease. [Background technology]

[0002] There has been much research into methods for detecting and predicting various cardiovascular diseases using biosignal data such as photoplethysmography (PPG) and electrocardiogram (ECG), but these methods are limited to providing classification results for specific types of cardiovascular diseases and do not provide information about the overall cardiac health of the user.

[0003] Meanwhile, heart age can be used as an index that can provide information related to the overall health condition of the heart. Heart age can provide intuitive information related to the overall health condition of the user's heart by utilizing the difference between the estimated heart age and the user's chronological age. For example, if the estimated heart age is higher than the user's chronological age, this can be used as information that the user's heart health condition is unhealthy for their chronological age and that the user has a relatively high risk of cardiovascular disease.

[0004] Conventional methods for measuring heart age have only been devised to indirectly calculate the user's heart age by examining whether the user has risk factors that may cause cardiovascular disease and then applying a predetermined formula to the calculation, or to perform invasive measurements. However, such methods not only have low accuracy in estimating heart age, but also are unable to provide multifaceted analyses such as predictions of the possibility of heart disease or future changes in heart age in relation to the user's heart age.

[0005] Therefore, there is a need in the art for a more accurate and non-invasive method for predicting cardiac age than conventional techniques, and a method for correlating cardiac age information with related information in a multifaceted manner to provide a user with information regarding their overall cardiac health.

[0006] Korean Patent Registration No. 2309022 (September 29, 2021) discloses a biological signal remote monitoring system based on artificial intelligence. Summary of the Invention [Problem to be solved by the invention]

[0007] The present disclosure has been devised in response to the above-mentioned background art, and aims to receive a user's biological signal data as input through a neural network model pre-trained based on information related to heart disease, more accurately estimate the user's cardiac age, analyze the estimated cardiac age information, and generate predictive information related to the user's future cardiac age. [Means for solving the problem]

[0008] In order to solve the above-mentioned problems, according to an embodiment of the present disclosure, a method for estimating cardiac age, executed by a computing device, is disclosed, which includes: acquiring biosignal data of a user; and estimating the cardiac age of the user based on the biosignal data of the user using a pre-trained neural network model, wherein the pre-trained neural network model can correspond to a neural network model pre-trained based on information related to cardiac disease.

[0009] In an alternative embodiment, the pre-trained neural network model corresponds to a neural network model pre-trained by supervised learning, and the training data for the supervised learning includes input data including measured biosignal data; and a ground truth label including age information of the user associated with the measured biosignal data.

[0010] In an alternative embodiment, the pre-trained artificial neural network model may correspond to an artificial neural network model trained through transfer learning based on a cardiac disease model designed to predict cardiac disease.

[0011] In an alternative embodiment, the pre-trained artificial neural network model may correspond to an artificial neural network model that has been transfer trained through the steps of obtaining the cardiac disease model after training; and tuning the weights of the cardiac disease model using training data related to age estimation.

[0012] In an alternative embodiment, the pre-trained artificial neural network model may include a plurality of artificial neural network models trained through transfer learning based on a plurality of cardiac disease models each configured to predict a plurality of cardiac diseases, and the architecture of the pre-trained artificial neural network model may include an ensemble of the plurality of artificial neural network models.

[0013] In an alternative embodiment, the structure for ensembling the plurality of artificial neural network models may include an artificial neural network structure for specifying the plurality of probabilities associated with the plurality of heart diseases as weights and for weighting the output values ​​of the plurality of artificial neural network models using the weights.

[0014] In an alternative embodiment, the method further includes generating analytical information related to the user's cardiac age estimated by the pre-trained neural network model, wherein the analytical information may include information related to the user's cardiac age estimated by the pre-trained neural network model; information related to the user's position in a cardiac age distribution of multiple users in the same age group; and information related to a comparison with a group of users suffering from major cardiac diseases.

[0015] In an alternative embodiment, the method may further include utilizing the pre-trained neural network model to generate predictive information regarding the user's future cardiac age based on the user's estimated cardiac age.

[0016] In an alternative embodiment, the step of utilizing the pre-trained neural network model to generate predictive information regarding the user's future cardiac age based on the user's estimated cardiac age may include the steps of: determining whether past vital sign data of the user exists; and utilizing the pre-trained neural network model to generate predictive information regarding the user's future cardiac age based on the estimated cardiac age information and the past vital sign data.

[0017] In an alternative embodiment, the past vital sign data can be measured at different time intervals.

[0018] In an alternative embodiment, the pre-trained artificial neural network model corresponds to an artificial neural network model pre-trained by supervised learning, and the training data for the supervised learning may correspond to input data including a plurality of biological signal data measured over a specific period of time; and an artificial neural network model trained to output predictive information regarding future cardiac ages, including a correct label including cardiac age information relating to a point in time any time after the specific period of time has elapsed.

[0019] In an alternative embodiment, the pre-trained neural network model may include at least one of: a Gated Recurrent Unit; or a Long Short-term Memory.

[0020] In an alternative embodiment, the pre-trained artificial neural network model may include at least one of the following steps: using an interpolation network to interpolate the user's past biosignal data and reflecting it in the training; or introducing a decay rate into the input layer and hidden layer of the artificial neural network model.

[0021] To achieve the above object, according to one embodiment of the present disclosure, a computer program for estimating cardiac age is disclosed, the program including: an operation of acquiring biosignal data of a user; and an operation of estimating the cardiac age of the user based on the biosignal data of the user by utilizing a pre-trained neural network model, the pre-trained neural network model being capable of corresponding to a neural network model pre-trained based on information related to cardiac disease.

[0022] To achieve the above object, according to one embodiment of the present disclosure, a computing device for estimating cardiac age is disclosed, which includes a processor including one or more cores, a network unit for receiving one or more biological signal data, and a memory, wherein the processor acquires a user's biological signal data and utilizes a pre-trained neural network model to estimate the user's cardiac age based on the user's biological signal data, and the pre-trained neural network model can correspond to a neural network model pre-trained based on information related to cardiac disease. [Effects of the Invention]

[0023] The present disclosure is capable of inputting a user's biometric signals into an artificial neural network to estimate the user's cardiac age, providing related analysis results, and outputting predictive information regarding the user's future cardiac age. [Brief explanation of the drawings]

[0024] The following drawings attached for use in explaining the embodiments of the present disclosure are merely a part of the embodiments of the present disclosure, and a person having ordinary knowledge in the technical field to which the present disclosure pertains (hereinafter referred to as "ordinary engineers") can derive other drawings based on these drawings without making any effort to come up with a new invention.

[0025] [Figure 1] FIG. 1 is a block diagram of a computing device for estimating cardiac age according to one embodiment of the present disclosure. [Figure 2] FIG. 2 is a schematic diagram illustrating a network function in one embodiment of the present disclosure. [Figure 3] FIG. 3 is a flowchart illustrating a process for transfer learning an artificial neural network model in one embodiment of the present disclosure. [Figure 4] FIG. 4 is a flowchart illustrating a process for ensembling one or more artificial neural network models in one embodiment of the present disclosure. [Figure 5] FIG. 5 is a schematic diagram illustrating an ensemble of one or more artificial neural network models in accordance with one embodiment of the present disclosure. [Figure 6] FIG. 6 is a conceptual diagram illustrating a process of generating analytical information related to a user's cardiac age estimated by an artificial neural network model in one embodiment of the present disclosure. [Figure 7] FIG. 7 is a conceptual diagram illustrating an example of analysis information related to the cardiac age of a user in one embodiment of the present disclosure. [Figure 8] FIG. 8 is a conceptual diagram showing predicted information related to a user's future heart age in one embodiment of the present disclosure. [Figure 9] FIG. 9 is a simplified general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION OF THE INVENTION

[0026] The present disclosure discloses a method for estimating cardiac age based on information related to heart disease, using an artificial neural network to receive input of a biological signal.

[0027] Various embodiments are described below with reference to the drawings, wherein like reference numerals are used to represent like elements throughout the drawings. Various descriptions are provided herein to facilitate understanding of the present disclosure. However, these embodiments can undoubtedly be practiced without these specific descriptions.

[0028] As used herein, terms such as "component," "module," and "system" 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, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a processor and / or thread of execution, and a component can be localized within one computer or distributed across two or more computers. Such components can also execute from various computer-readable media having various data structures stored therein. Components can communicate via local and / or remote processes, for example, by signals carrying one or more data packets (e.g., data from one component interacting with other components in a local system, a distributed system, or data transmitted over a network such as the Internet to other systems).

[0029] The term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X utilizes A or B" shall mean one of the natural inclusive permutations. That is, if X utilizes A; X utilizes B; or X utilizes both A and B, then "X utilizes A or B" can apply to any of these. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated listed items.

[0030] Additionally, the predicate "comprises" and / or the modifier "comprises" should be understood to mean that the feature and / or component in question is present. However, the predicate "comprises" and / or the modifier "comprises" should be understood not to exclude the presence or addition of one or more other further features, components and / or groups thereof. Additionally, unless a specific number is specified or the context is clear that a singular form is indicated, the singular form in this specification and claims should generally be construed to mean "one or more."

[0031] Furthermore, the term "at least one of A or B" should be interpreted as meaning "when only A is included," "when only B is included," or "when a combination of A and B is included."

[0032] Those skilled in the art should further recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in accordance with 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, the various illustrative components, blocks, components, means, logic, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints of the overall system. Skilled artisans can implement the described functionality in various ways for each particular application. However, such implementation decisions should not be interpreted as departing from the scope of the present disclosure.

[0033] The description of the embodiments set forth herein is provided to enable one of ordinary skill in the art to make and practice the invention. Various modifications to these embodiments will be apparent to those of ordinary skill in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited by the embodiments set forth herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0034] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably.

[0035] In this disclosure, chronological age, physical age, and chronological age can be used interchangeably.

[0036] FIG. 1 is a block diagram of a computing device for estimating cardiac age according to one embodiment of the present disclosure.

[0037] The configuration of the computing device (100) illustrated in Figure 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other components for implementing the computing environment of the computing device (100), and the computing device (100) may be configured with only some of the disclosed components.

[0038] The computer device (100) may include a processor (110), a memory (130), and a network unit (150).

[0039] In one embodiment of the present disclosure, the processor 100 may be configured with one or more cores and may include processors for data analysis and deep learning, such as a computing central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). The processor 110 may read a computer program stored in the memory 130 and execute data processing for machine learning in one embodiment of the present disclosure. According to one embodiment of the present disclosure, the processor 110 may perform calculations for neural network training. In deep learning (DL), the processor 110 may execute calculations for neural network training, such as processing input data for training, extracting features from the input data, calculating errors, and updating neural network weights using backpropagation.

[0040] At least one of the CPU, GPGPU, and TPU of the processor 110 can process network function training. For example, the CPU and GPGPU can both train the network function or classify data using the network function. In one embodiment of the present disclosure, processors of multiple computing devices can be used together to train the network function or classify data using the network function. In one embodiment of the present disclosure, the computer program executed in the computing device can be a program executable by the CPU, GPGPU, or TPU.

[0041] According to one embodiment of the present disclosure, the processor 110 may estimate a user's cardiac age based on the user's biosignal data by utilizing a neural network model pre-trained on information related to cardiac disease. To this end, the processor 110 may acquire the user's biosignal data. For example, the processor 110 may use the user's biosignal data stored in the memory 130, receive the user's biosignal data via the network 150, or directly acquire the user's biosignal data from a biosignal measurement device (not shown). However, the present disclosure is not limited to the biosignal acquisition method illustrated as an example.

[0042] The processor 110 can pre-train an artificial neural network model for estimating cardiac age using techniques such as supervised learning, transfer learning, model ensemble, etc., to achieve the desired performance. The specific process of pre-training the artificial neural network model will be described later with reference to Figures 3 to 5.

[0043] In a further embodiment of the present disclosure, the processor 110 may generate analytical information related to the user's cardiac age estimated by the pre-trained neural network model. In this case, the analytical information related to the cardiac age may include, but is not limited to, information related to the user's estimated cardiac age, information related to the user's position in the cardiac age distribution of multiple users in the same age group, or information related to a comparison with a group of users suffering from major cardiac diseases. A specific process for generating analytical information related to the user's cardiac age will be described below with reference to FIG. 6.

[0044] In a further embodiment of the present disclosure, the processor 110 may utilize a pre-trained neural network model to generate predictive information regarding the user's future cardiac age based on the user's estimated cardiac age. A specific method for generating predictive information regarding the user's future cardiac age and a training method for the artificial neural network model for generating the predictive information will be described later with reference to FIG. 7.

[0045] In one embodiment of the present disclosure, the memory 130 may include at least one type of storage medium selected from the group consisting of flash memory, hard disk, micro multimedia card, card-type memory (e.g., SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The computing device 100 may also operate in conjunction with web storage that performs storage functions of the memory 130 over the Internet. The above descriptions of memory are merely examples, and the present disclosure is not limited thereto.

[0046] The network unit 150 in one embodiment of the present disclosure can use various wired communication systems such as a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), Very High Speed ​​DSL (VDSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and a Local Area Network (LAN).

[0047] In addition, the network unit (150) in this specification can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0048] In the present disclosure, the network unit 150 can use any type of wired or wireless communication system.

[0049] The techniques described herein can be used in the above networks as well as other networks.

[0050] FIG. 2 is a schematic diagram illustrating network functions used to provide diagnostically relevant information for medical data in one embodiment of the present disclosure.

[0051] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. A neural network is often composed of a collection of interconnected computational units, commonly called nodes. Such nodes may also be referred to as neurons. A neural network is composed of at least one or more nodes. The nodes (or neurons) that make up a neural network may be interconnected by one or more links.

[0052] In a neural network, one or more nodes connected via links can form a relative relationship between an input node and an output node. The concepts of input node and output node are relative, and any node that is an output node for one node can also be an input node for another node, and vice versa. As mentioned above, the relationship between input node and output node can be established around links. One or more output nodes can be connected to one input node via links, and vice versa.

[0053] In a relationship between an input node and an output node connected via a link, the value of the data in the output node can be determined based on the data input to the input node. Here, the node interconnecting the input node and the output node can have a weight. The weight can be variable and can be changed by a user or an algorithm so that the neural network performs a desired function. For example, if one or more input nodes are interconnected to one output node by each link, the output node can determine its value based on the value input to the input node connected to the output node and the weight set for the link corresponding to each input node.

[0054] As described above, a neural network has one or more nodes interconnected via one or more links, forming a relationship between an input node and an output node within the neural network. The characteristics of a neural network can be determined by the number of nodes and links, the correlation between the nodes and links, and the weights assigned to each link. For example, if two neural networks have the same number of nodes and links but different link weights, the two neural networks can be recognized as different.

[0055] A neural network can be composed of a set of one or more nodes. A subset of the nodes in a neural network can form a layer. Some of the nodes in a neural network can form a layer based on their distance from a first input node. For example, a set of nodes whose distance from a first input node is n can form n layers. The distance from the first input node can be defined based on the minimum number of links that must be traversed to reach that node from the first input node. However, this definition of a layer is arbitrary for the purpose of explanation, and the configuration of layers in a neural network can be defined in a manner different from the above description. For example, a layer of nodes can also be defined based on their distance from the final output node.

[0056] A first input node may refer to one or more nodes in a neural network to which data is directly input without passing through a link in relation to other nodes. Alternatively, a first input node may refer to a node in a neural network that does not have other input nodes connected via a link in relation to other nodes based on links. Similarly, a final output node may refer to one or more nodes in a neural network that do not have output nodes in relation to other nodes. Furthermore, a hidden node may refer to a node that is neither a first input node nor a final output node and that constitutes a neural network.

[0057] A neural network according to an embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer is the same as the number of nodes in the output layer, and the number of nodes decreases once and then increases again as the network progresses from the input layer to the hidden layer. A neural network according to an embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer is fewer than the number of nodes in the output layer, and the number of nodes decreases as the network progresses from the input layer to the hidden layer. A neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer is greater than the number of nodes in the output layer, and the number of nodes increases as the network progresses from the input layer to the hidden layer. A neural network according to another embodiment of the present disclosure may be a neural network that combines the above-mentioned neural networks.

[0058] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to understand the latent structures of data. That is, they can understand the latent structures of photos, text, video, audio, and music (e.g., whether a certain object appears in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, generative adversarial networks (GANs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), Q-networks, U-networks, Siamese networks, and generative adversarial networks (GANs). The above-mentioned deep neural networks are merely examples and the present disclosure is not limited thereto.

[0059] In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network that outputs output data similar to input data. An autoencoder may include at least one hidden layer, and an odd number of hidden layers may be arranged between the input and output layers. The number of nodes in each layer may decrease from the number of nodes in the input layer toward an intermediate layer called a bottleneck layer (encoder), and may expand from the bottleneck layer toward the output layer (symmetrical to the input layer) in a manner similar to contraction. An autoencoder may perform nonlinear dimensionality reduction. The number of input and output layers may correspond to the dimensionality of the input data after preprocessing. In an autoencoder structure, the number of nodes in the hidden layer included in the encoder may decrease as the distance from the input data increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, it may not convey enough information, so it may be maintained at a certain number or more (e.g., more than half of the input layer).

[0060] Neural networks can be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Training a neural network can be a process of providing the neural network with knowledge that enables it to perform a specific operation.

[0061] Neural networks can be trained to minimize output errors. Training involves repeatedly inputting training data into the neural network, calculating the error between the neural network's output and the target for the training data, and backpropagating the neural network's error from the output layer to the input layer to update the weights of each node in the neural network in a way that reduces the error. In supervised learning, training data in which the correct answer is labeled is used (i.e., labeled training data). In unsupervised learning, the correct answer may not be labeled. For example, in supervised learning for data classification, the training data may be data in which each training data is labeled with a category. Labeled training data is input into the neural network, and the error can be calculated by comparing the neural network's output (category) with the label of the training data. As another example, in unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network's output. The calculated error is backpropagated in the reverse direction in the neural network (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated through backpropagation. The amount of change in the connection weights of each node to be updated can be determined by the learning rate. The neural network calculation for input data and backpropagation of the error can constitute a learning cycle (epoch). The application method of the learning rate can change depending on the number of iterations of the neural network learning cycle. For example, in the early stages of neural network learning, the learning rate can be increased to allow the neural network to quickly achieve a certain level of performance, thereby improving efficiency, and in the later stages of learning, the learning rate can be decreased to improve accuracy.

[0062] In neural network training, the training data can generally be a subset of the actual data (i.e., the data to be processed using the trained neural network). Therefore, there can be a learning cycle in which the error associated with the training data decreases while the error associated with the actual data increases. Overfitting is a phenomenon in which the error associated with the actual data increases due to excessive learning of the training data. For example, a neural network that has learned to recognize a yellow cat may be unable to recognize a cat that is a different color from yellow. Overfitting can increase the error of machine learning algorithms. Various optimization methods can be applied to prevent overfitting. Methods that can be used include increasing the amount of training data, regularization, dropout (which deactivates some nodes in the network during the training process), and the use of batch normalization layers.

[0063] FIG. 3 is a flowchart illustrating a process for transfer learning an artificial neural network model in one embodiment of the present disclosure.

[0064] In the present disclosure, supervised learning can be used as a learning method for an artificial neural network model for estimating cardiac age. When training an artificial neural network model using supervised learning, labeled data for training the artificial neural network model can be biosignals, and the biosignals can be labeled with the user's chronological age information. Through this type of supervised learning, the artificial neural network model for estimating cardiac age can learn the user's biosignal patterns and receive biosignals as input in the inference stage of the artificial intelligence model to infer cardiac age.

[0065] As another example, in the present disclosure, transfer learning can be used in conjunction with supervised learning as a training method for an artificial neural network model for estimating cardiac age. Transfer learning refers to utilizing part of the capabilities of a neural network trained in a specific field to solve problems in a similar or completely different field. For example, if a model trained to distinguish dogs is further trained to distinguish cats, this constitutes transfer learning. In general, in situations where data is scarce, an artificial neural network model trained through transfer learning is believed to achieve higher performance than an artificial neural network model trained solely through supervised learning.

[0066] In conjunction with the supervised learning-based embodiment of the present disclosure described above, the structure of the artificial neural network model can be designed such that biosignal data of unhealthy users can also be used to train the artificial neural network model.

[0067] In one embodiment of the present disclosure, a pre-trained artificial neural network model can be subjected to transfer learning to estimate a user's cardiac age. For example, a cardiac disease model designed to predict information related to a specific cardiac disease based on a biological signal can be used as the pre-trained artificial neural network model. However, it will be obvious to those skilled in the art that other models suitable for transfer learning can be used in the present disclosure, in addition to models predicting information related to a specific cardiac disease.

[0068] In step S310, the processor 110 may obtain a pre-trained cardiac disease model for predicting cardiac disease from the user's biosignal information. For example, the pre-trained cardiac disease model may receive the user's biosignal and output a probability that the user has cardiac failure. In this case, the type of cardiac disease may include, but is not limited to, arrhythmia, myocardial infarction, cardiac failure, etc.

[0069] In step S320, the processor 110 may perform transfer learning on the pre-trained cardiac disease model using training data related to age estimation. In this case, the transfer-trained artificial neural network model additionally learns training data related to age estimation, thereby adjusting the weights of the pre-trained model, and as a result, it is possible to grasp the correlation between cardiac age and cardiac disease.

[0070] In step S330, the processor (110) can utilize the transfer learned model to estimate cardiac age.

[0071] The artificial neural network model (300) that has undergone transfer learning using this method can use not only biosignal data from healthy users but also biosignal data from users suffering from specific heart diseases as training data. In conclusion, the artificial neural network model that has undergone transfer learning as disclosed herein can become a robust model that can respond to input of more diverse types of biosignal information in the inference stage and accurately infer cardiac age.

[0072] FIG. 4 is a flowchart illustrating a process for ensembling one or more artificial neural network models in one embodiment of the present disclosure.

[0073] Ensemble learning is a machine learning technique that combines multiple decision trees to achieve better performance than a single decision tree. Bagging, boosting, and voting are well-known examples of ensemble learning.

[0074] An artificial neural network model that utilizes an artificial neural network model previously trained to predict a specific heart disease and is then transfer trained to estimate cardiac age is more robust than a simple supervised artificial neural network model when it receives input biosignals from a user who may have the specific disease, but the accuracy of the cardiac age information estimated by the artificial neural network model may be lower when it receives input biosignals from a user who may have another disease.

[0075] In step S410, the processor 110 may obtain a plurality of transfer-trained artificial neural network models capable of estimating cardiac age. For example, a model pre-trained to output a probability that a user has arrhythmia may be used to obtain a transfer-trained model capable of estimating cardiac age.

[0076] In step S420, the processor 110 can cause each of the plurality of artificial neural network models to output probability information corresponding to a specific disease and cardiac age. For example, a model that has been transferred from a pre-trained model to output probability information corresponding to arrhythmia can be used as one of the plurality of artificial neural network models to output probability information corresponding to arrhythmia and cardiac age of the user based on the user's biosignal.

[0077] In step S430, the processor 110 can determine a weight for each model based on the probability information output by the multiple artificial neural network models in step S420. For example, if the probability that a user has arrhythmia is 40% and the user's cardiac age output by a model that has been transferred and trained using a model that has been pre-trained to output the probability of arrhythmia is 42 years old, a weight of 40% can be assigned to the model's output value of 42 years old.

[0078] In step S440, the processor 110 may ensemble the output values ​​of each artificial neural network model using the determined weights. For example, assume that the user has a 40% probability of arrhythmia, and the user's cardiac age output by a model transferred from a pre-trained model to output the arrhythmia probability is 42 years old. Also assume that the user has a 10% probability of myocardial infarction, and the user's cardiac age output by a model transferred from a pre-trained model to output the myocardial infarction probability is 50 years old. In this case, the output value of the ensemble model may be 43.6 years old, which is a weighted average of the weights for 42 and 50 years old. However, in the present disclosure, the method of ensembling the model output values ​​is not limited to the weighted average method described here.

[0079] FIG. 5 is a schematic diagram illustrating an ensemble of one or more artificial neural network models in accordance with one embodiment of the present disclosure.

[0080] In additional embodiments of the present disclosure, the artificial neural network model for estimating cardiac age may be an ensemble of multiple artificial neural network models that have been transfer trained based on artificial neural network models pre-trained to predict specific cardiac diseases. For example, the artificial neural network model for estimating cardiac age may be an ensemble of a model (510) that has been transfer trained based on a model pre-trained to predict arrhythmia, a model (520) that has been transfer trained based on a model pre-trained to predict myocardial infarction, and a model (530) that has been transfer trained based on a model pre-trained to predict heart failure.

[0081] Specifically, the output of the artificial neural network model for estimating cardiac age (540) may be a value that combines the output values ​​of multiple artificial neural network models (510, 520, and 530) trained through transfer learning based on multiple cardiac disease models designed to predict specific diseases.

[0082] For example, each of the multiple transfer-trained artificial neural network models (510, 520, and 530) can derive probability information corresponding to a specific disease and cardiac age information from the input biological signal. Then, the multiple transfer-trained artificial neural network models (510, 520, and 530) can specify weights (514, 515, and 516) for each model based on the probability information. Then, using the weights specified based on the probability information, the cardiac ages (511, 512, and 513) estimated by each of the multiple transfer-trained artificial neural network models (510, 520, and 530) can be weighted-averaged to obtain an output value (540) of the final model. In the present disclosure, the structure for ensembling the multiple transfer-trained artificial neural network models is not limited to the above-described example, and other methods such as bagging, voting, and boosting can also be used.

[0083] According to the above example, if the user is likely to have a particular disease, for example, arrhythmia, the weight (514) of the model (510) transferred and learned from the arrhythmia prediction model is calculated to be large in the output of the overall model, so that the cardiac age (511) estimated by the model (510) transferred and learned from the arrhythmia prediction model can occupy a high weight in the output of the overall model.

[0084] As described above, the cardiac age estimation model finally completed by ensembling multiple transfer-learned models can be more robust to inputs of biological signals from multiple users suffering from various types of diseases, and as a result, the performance of the model can be improved.

[0085] FIG. 6 is a conceptual diagram illustrating a process of generating analytical information related to a user's cardiac age estimated by an artificial neural network model in one embodiment of the present disclosure.

[0086] The processor 110 may provide analytical information relating to the user's cardiac age and the degree of risk and management needs of the user for cardiac disease.

[0087] Specifically, in the training phase of the artificial neural network model, the processor 110 can train the artificial neural network with data in which the biological signals are labeled with diseases and chronological age. For example, the processor 110 can train the artificial neural network model 640 to estimate cardiac age, calculate the difference between the estimated cardiac age and the user's chronological age, and determine the correlation between the difference and each disease.

[0088] In the inference stage of the artificial neural network model, the processor (110) can utilize the artificial neural network model to receive input biometric data and estimate cardiac age through the output (620) of the artificial neural network model. The processor (110) can compare the estimated cardiac age with the actual age (610), i.e., chronological age, to calculate the delta age (630). Because the artificial neural network is trained (640) to understand the correlation between the delta age and various diseases, the artificial neural network can analyze the likelihood of disease (650) for the input biometric signal data. The analysis results of the artificial neural network model described above can be visualized and displayed to the user in a format such as that shown in FIG. 6.

[0089] FIG. 7 is a conceptual diagram illustrating an example of analysis information related to the cardiac age of a user in one embodiment of the present disclosure.

[0090] As an example of the analytical information, the processor 110 may display the user's cardiac age and the user's chronological age as estimated by the artificial neural network model, and the difference between the user's cardiac age and the user's chronological age.

[0091] In addition, the processor 110 can calculate where the user's heart age falls in a normalized distribution created by collecting the heart age estimation results of users in the same age group, and display the result to the user. For example, the processor 110 can display analytical information to the user in the form of, "The estimated heart age is 9.8 years higher than the chronological age, which is a value that falls in the bottom 17% of users in the same age group."

[0092] The processor 110 can also display the level of the user's cardiac age compared to the cardiac age of a group of users suffering from major cardiac diseases. For example, as shown in FIG. 6, the processor 110 can generate a graph showing that the user's estimated cardiac age is 9.8 years higher than their chronological age, and provide analysis results that plot the values ​​of multiple patients suffering from cardiac diseases, such as patients with atrial fibrillation, for reference. In this way, displaying information using the difference between the user's estimated cardiac age and their chronological age and comparing it with other users can help the user or medical personnel determine whether the user has a cardiac disease and whether they need to take action.

[0093] FIG. 8 is a conceptual diagram showing predicted information related to a user's future heart age in one embodiment of the present disclosure.

[0094] The processor 110 can utilize an artificial neural network model to generate predictive information regarding the user's future cardiac age based on the user's estimated cardiac age. In this case, a specific step of generating the predictive information can first determine whether past measurement data of the user's vital signs are available. If past vital sign data is available, the processor 110 can utilize an artificial neural network model to estimate the cardiac age at each past measurement point from the past vital sign data, thereby estimating the current cardiac age. The artificial neural network can then generate predictive information regarding the future cardiac age from the past cardiac age and the current cardiac age. The predictive information can be expressed as a specific point at a specific time point, or as a region showing possible gradient values, although the present disclosure is not limited thereto.

[0095] The processor 110 can calculate and display to the user a graph of changes in estimated heart age over the past few years based on past estimated heart age values, along with numerical values ​​such as the difference between chronological age and heart age at each point in time. For example, as shown in Figure 7, the processor 110 can provide the user with information that the average age has increased by approximately 8.6 years per year over the past year, and by approximately 3.5 years per year over the past five years.

[0096] Past biosignal data from the same user can be collected periodically or irregularly, i.e., at different time intervals between data points. When the time intervals between points constituting the time series data are different, an artificial neural network model may be needed to predict future information.

[0097] In the present disclosure, the artificial neural network model that generates prediction information regarding future cardiac age using the processor (110) can be trained through supervised learning. Training data for supervised learning can include multiple biological signal data measured over a specific period of time, and the correct labels associated with the training data can include cardiac age information related to a point in time any time after the specific period of time has elapsed. By constructing such pairs of input data and correct labels using training data and then training an artificial neural network model including a long short-term memory (LTSM) or a gated recurrent unit (GRU), the artificial neural network model can calculate future estimates from past data.

[0098] It is well known that in models that handle time series data, if there are missing values ​​in the data or if there are gaps in the data due to irregular measurement intervals, the performance of the model will decrease during training using the data. In this disclosure and other inventions in the field of biosignals, since a user's biosignals are often measured at irregular time intervals, resolving the problem of missing values ​​or gaps in the data can be an important challenge for improving the performance of the model. To solve this problem, a method of preprocessing the data to improve the learning effect, a method of constructing and training an artificial neural network model to prevent performance degradation without additional preprocessing, or a combination of the two methods can be used.

[0099] For example, the artificial neural network model for generating predictive information related to future cardiac age of the present disclosure can be designed to include an interpolation network, in which case the artificial neural network model can interpolate data at vacant points and then learn through the interpolated data and existing data.

[0100] As yet another example, a decay rate mechanism can be introduced into the input and hidden layers of an artificial neural network model trained on time series data measured at irregular intervals. The decay rate can be determined through prior knowledge, modeling, or data-based learning, using the time interval information to determine how other measured data influences missing or missing data. It is believed that those skilled in the art would have no difficulty in constructing an artificial neural network model with such characteristics based on the description of the interpolation network and decay rate mechanism described in this disclosure.

[0101] Through such pre-processing and model construction of the present disclosure, the model can be properly trained even if the user's biological signals use data measured at irregular time intervals.

[0102] In accordance with one embodiment of the present disclosure, a computer-readable storage medium having a data structure stored thereon is disclosed.

[0103] A data structure can refer to the organization, management, and storage of data that allows efficient access and modification. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval, data storage, data modification) in the shortest possible time. A data structure can also be defined as the physical or logical relationships between data elements designed to support a specific data processing function. Logical relationships between data elements can include the interconnections between data elements as perceived by a user. Physical relationships between data elements can include the actual relationships between data elements physically stored on a computer-readable storage medium (e.g., a hard disk). A data structure can specifically include a collection of data, the relationships between the data, and functions or commands that can be applied to the data. An effectively designed data structure allows a computing device to perform calculations while minimizing the use of computing device resources. Specifically, an effectively designed data structure can increase the efficiency of operations, reading, inserting, deleting, comparing, exchanging, and searching.

[0104] Data structures can be divided into linear and non-linear data structures depending on their type. A linear data structure can be a structure in which only one piece of data is linked to another. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a series of data sets that have an internal order. Lists can also include linked lists. A linked list can be a data structure in which data is linked in a row with a pointer to each piece of data. In a linked list, the pointer can contain information about the connection to the next or previous piece of data. Depending on the type, linked lists can be expressed as singly linked lists, doubly linked lists, or circularly linked lists. A stack can be a data list structure that allows limited data access. A stack can be a linear data structure in which data can only be accessed (e.g., inserted or deleted) at one end of the data structure. Data stored in a stack can be a LIFO (Last in First Out) data structure. A queue is a data structure that allows limited access to data, and unlike a stack, it can be a data structure (FIFO - First in First out) where the slowest data stored is the slowest data available. A deck can be a data structure that allows data to be processed at both ends of the data structure.

[0105] A non-linear data structure may be a structure in which multiple pieces of data are concatenated after one piece of data. A non-linear data structure may include a graph data structure. A graph data structure may be defined by vertices and edges, and a backbone may include a line connecting two different vertices. A graph data structure may include a tree data structure. A tree data structure may be a data structure in which a path connecting two different vertices among multiple vertices included in a tree is a single data structure. In other words, a graph data structure may be a data structure that does not form loops.

[0106] Throughout this specification, the terms computational model, neural network, network function, and neural network are used interchangeably (hereinafter, they will be referred to as neural network). A data structure may include a neural network. The data structure including a neural network may be stored on a computer-readable storage medium. The data structure including a neural network may also include data input to the neural network, neural network weights, neural network hyperparameters, data acquired 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. The data structure including a neural network may include any of the components disclosed above. That is, the data structure including a neural network may include all or any combination of data input to the neural network, neural network weights, neural network hyperparameters, data acquired 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. In addition to the above-mentioned components, the data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated in the computational process of a neural network, and is not limited to the foregoing. The computer-readable storage medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a collection of interconnected computational units generally called nodes. Such nodes may be called neurons. A neural network is composed of at least one or more nodes.

[0107] The data structure may include data to be input to the neural network. The data structure including the data to be input to the neural network may be stored in a computer-readable storage medium. The data to be input to the neural network may include training data input during the training process of the neural network and / or input data to be input to the neural network after training has been completed. The data to be input to the neural network may include data that has undergone pre-processing and / or data to be pre-processed. Pre-processing may include a data processing process for inputting data to the neural network. Therefore, the data structure may include data to be pre-processed and data generated by pre-processing. The above-described data structures are merely examples, and the present disclosure is not limited thereto.

[0108] The data structure may include weights of the neural network. (In this specification, the terms "weights" and "parameters" may be used interchangeably.) The data structure including the weights of the neural network may be stored in a computer-readable storage medium. The neural network may include multiple weights. The weights are variable and can be changed by a user or an algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to an output node by respective links, the output node may determine its output node value based on the values ​​input to the input nodes connected to the output node and the parameters set for the links corresponding to each input node. The above data structure is merely exemplary, and the present disclosure is not limited thereto.

[0109] By way of example and not limitation, the weights may include weights that change during neural network training and / or weights at which neural network training has been completed. The weights that change during neural network training may include weights at the start of a training cycle and / or weights that change during a training cycle. The weights at which neural network training has been completed may include weights at which a training cycle has been completed. Therefore, a data structure including neural network weights may include a data structure including weights that change during neural network training and / or weights at which neural network training has been completed. Therefore, the above-mentioned weights and / or combinations of each weight are included in a data structure including neural network weights. The above-mentioned data structures are merely examples, and the present disclosure is not limited thereto.

[0110] The data structure including the neural network weights may be stored in a computer-readable storage medium (e.g., memory, hard disk) after undergoing a serialization process. Serialization may be a process of converting a data structure into a form that can be stored on the same or another computing device and later reconstructed for use. A computing device may serialize the data structure and transmit or receive the data over a network. The serialized data structure including the neural network weights may be reconstructed on the same or another computing device through deserialization. The data structure including the neural network weights is not limited to serialization. Furthermore, the data structure including the neural network weights may include a data structure (e.g., a nonlinear data structure such as a B-tree, a Trie, an m-way search tree, an AVL tree, or a Red-Black tree) that increases computational efficiency while minimizing the use of computing device resources. The foregoing is merely exemplary, and the present disclosure is not limited thereto.

[0111] The data structure may include hyperparameters of the neural network. The data structure including the hyperparameters of the neural network may be stored in a computer-readable storage medium. The hyperparameters may be variables that can be changed by a user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting a range of weights to be initialized), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0112] FIG. 9 is a simplified general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure can be implemented.

[0113] While the present disclosure has been described above as generally being embodied in a computing device, those skilled in the art will appreciate that the present disclosure can also be embodied in combination with computer-executable instructions and / or other program modules that can be executed on one or more computers and / or as a combination of hardware and software.

[0114] Generally, modules herein include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Those skilled in the art will also appreciate that the methods of the present disclosure can be practiced with 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 or programmable consumer electronics, etc., each of which can operate in conjunction with one or more associated devices.

[0115] The embodiments described in this disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0116] A computer includes a variety of computer-readable media. Any medium accessible by a computer can be computer-readable, including volatile and nonvolatile media, transitory and non-transitory media, and portable and non-portable 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 include volatile and non-volatile media, transitory and non-transitory media, portable and non-portable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage devices, magnetic cassettes, magnetic tape, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be accessed by a computer and used to store information.

[0117] Computer-readable transmission media typically embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed in such a manner 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 direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Any combination of any of the foregoing media should also be included within the scope of computer-readable transmission media.

[0118] An exemplary environment (1100) for implementing various aspects of the present disclosure is shown, including a computer (1102) including a processing unit (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 unit (1104). The processing unit (1104) can be any of a variety of commercially available processors. Dual processors and other multi-processor architectures can also be utilized as the processing unit (1104).

[0119] The system bus (1108) can be any of several types of bus structures that can be further interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. The system memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, or EEPROM. The BIOS contains the basic routines that support the exchange of information between the various components within the computer (1102), such as during startup. The RAM (1112) can also include high-speed RAM, such as static RAM, for caching data.

[0120] The computer 1102 also includes an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 can also be configured for external use in 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 or for 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 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 implementing an external drive includes, for example, at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0121] These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of computer 1102, the drives and media accommodate storing any data in a suitable digital format. While the foregoing description of computer-readable storage media refers to hard disk drives, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will appreciate that other types of computer-readable storage media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., can also be used in the exemplary operating environment, and that any such media can contain computer-executable instructions for performing the methods of the present disclosure.

[0122] A number of program modules, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136, may be stored on the drives and in RAM 1112. All or portions of the operating system, applications, modules, and / or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented with various commercially available operating systems or combinations of operating systems.

[0123] A user can enter commands and information into the computer 1102 through one or more wired or wireless input devices, such as a keyboard 1138 and a pointing device such as a mouse 1140. Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices are often connected to the processing unit 1104 through an input device interface 1142 connected to the system bus 1108, but may also be connected through other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.

[0124] 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, computers typically include other peripheral output devices (not shown), such as speakers, printers, etc.

[0125] The computer 1102 can operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and / or wireless communications. The remote computer(s) 1148 can be a workstation, a server computer, a router, a personal computer, a handheld computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and typically includes many or all of the components described for the computer 1102, although for simplicity, only a memory storage device 1150 is shown. The logical connections shown include wired and wireless connections in a local area network (LAN) 1152 and / or larger networks, e.g., a long-range network (WAN) 1154. Such LAN and WAN networking environments are commonplace in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may connect to a global computer network, e.g., the Internet.

[0126] When used in a LAN networking environment, the computer 1102 connects to the local network 1152 through a wired and / or wireless communication network interface or adapter 1156. The adapter 1156 can facilitate wired or wireless communication to the LAN 1152, which may also include a wireless access point attached thereto for communicating with the wireless adapter 1156. When used in a WAN networking environment, the computer 1102 can include a modem 1158 or other means for establishing communications over the WAN 1154, such as connecting to a communications server on the WAN 1154 or through the Internet. The modem 1158, which can be internal or external and can be a wired or wireless device, connects to the system bus 1108 through the serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory / storage device 1150. It will be readily appreciated that the network connections shown are exemplary and other means of establishing a communications link between two or more computers may be used.

[0127] The computer 1102 is operable to communicate with any wireless device or unit configured and operating in a wireless manner, such as printers, scanners, desktop and / or handheld computers, portable data assistants (PDAs), communications satellites, any equipment or location associated with a radio-detectable tag, and telephones. This includes at least Wi-Fi and Bluetooth® wireless technologies. Thus, communication can be in a predefined structure, such as a traditional network, or simply ad hoc communication between at least two devices.

[0128] Wi-Fi (Wireless Fidelity) allows devices to connect to the Internet without being wired. Wi-Fi is a wireless technology similar to cell phones, allowing such devices, such as computers, to send and receive data indoors and outdoors—anywhere within the coverage area of ​​a base station. Wi-Fi networks use IEEE 802.11 (a, b, g, etc.) radio technology to provide secure, reliable, and fast wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 or 5 GHz radio bands, at data rates of, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual bands).

[0129] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referred to in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields, etc. or particles, optical fields, etc. or particles, or any combination thereof.

[0130] Those skilled in the art will appreciate that the various illustrative logic blocks, modules, processors, means, circuits, and algorithm steps described in the description of the embodiments disclosed herein can be implemented with electronic hardware, various forms of program or design code (for convenience, referred to herein as "software"), or a combination of all of these. To clearly illustrate this interoperability of hardware and software, the various illustrative components, blocks, modules, circuits, and steps have been described above generally by focusing on their functionality. Whether such functionality is implemented in hardware or software depends on the particular application and design constraints imposed on the overall system. Those skilled in the art will appreciate that the described functionality can be implemented in various ways for each particular application, and such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0131] The various embodiments described herein may be implemented by a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes a computer program, carrier, or medium accessible by any computer-readable device. For example, computer-readable storage media include, but are 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.). Additionally, the various storage media described herein include one or more devices and / or other machine-readable media for storing information.

[0132] It should be understood that the specific order or hierarchy of steps in the processes depicted is an example of an exemplary approach. Based on design priorities, it should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy depicted.

[0133] The description of the illustrated embodiments is provided to enable any person skilled in the art to which the disclosure pertains to use or practice the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited by the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. 1. A method performed by a computing device for estimating cardiac age, comprising: acquiring biosignal data of the user; estimating probability information indicating that the user has a specific disease and the user's cardiac age based on the user's biosignal data by utilizing each of a plurality of artificial neural network models; and generating a final output value by weighting the cardiac ages estimated by each of the plurality of artificial neural network models using the estimated probability information as weights for the corresponding artificial neural network models; Including, each of the plurality of artificial neural network models estimates the cardiac age of the user based on the biosignal data of the user and corresponds to a model further trained based on a pre-trained artificial neural network model; each of the pre-trained artificial neural network models predicts probability information indicating that the user has a particular disease based on the biosignal data of the user; method.

2. In claim 1, the plurality of artificial neural network models correspond to models further trained by supervised learning based on the pre-trained artificial neural network models; The learning data for the supervised learning is input data including measured biosignal data; and A correct answer label including age information of the user associated with the measured biological signal data is included. method.

3. In claim 1, The plurality of artificial neural network models correspond to models further trained through transfer learning based on the pre-trained artificial neural network model. method.

4. In claim 3, the plurality of artificial neural network models, obtaining the pre-trained artificial neural network model; and tuning weights of the pre-trained artificial neural network model using training data related to age estimation; This corresponds to the transfer-trained model based on The learning data related to the age estimation is input data including measured biosignal data; and a correct answer label including age information of the user linked to the measured biological signal data; Including, method.

5. In claim 3, the architecture of the plurality of artificial neural network models includes an ensemble of the plurality of artificial neural network models; method.

6. In claim 5, The structure for ensembling the plurality of artificial neural network models includes: Specifying multiple probabilities of multiple heart conditions as weights; and an artificial neural network structure for weighted averaging of output values ​​of the plurality of artificial neural network models using the weights; method.

7. In claim 1, The method comprises: generating analytical information related to the cardiac age of the user estimated by the plurality of artificial neural network models; The analytical information is information related to the cardiac age of the user estimated by the plurality of artificial neural network models; information regarding the user's position in a cardiac age distribution of multiple users in the same age group; and Information on comparisons with groups of users with the same heart condition; Including, method.

8. In claim 1, estimating a past cardiac age of the user based on past biosignal data of the user utilizing the plurality of artificial neural network models; and generating predictive information about the user's future cardiac age based on the estimated past cardiac age of the user, utilizing an artificial neural network model for generating predictive information about the user's future cardiac age; further comprising: method.

9. In claim 8, generating prediction information about the user's future cardiac age based on the estimated past cardiac age of the user by utilizing an artificial neural network model for generating prediction information about the user's future cardiac age, generating prediction information about the future cardiac age based on the estimated cardiac age information and past vital sign data by utilizing an artificial neural network model for generating prediction information about the future cardiac age; Including, method.

10. In claim 9, The past biological signal data are collected at different time intervals between data. method.

11. In claim 9, the artificial neural network model for generating the prediction information regarding the future cardiac age corresponds to an artificial neural network model pre-trained by supervised learning; The learning data for the supervised learning is Input data including a plurality of biosignal data measured over a specific period of time; and A correct label including cardiac age information at a point in time after an arbitrary time has elapsed since the specific period; Including, method.

12. In claim 9, The artificial neural network model for generating the prediction information regarding the future cardiac age includes: Interpolating the past biosignal data of the user using an interpolation network and reflecting the interpolated past biosignal data in learning; or introducing a decay rate into an input layer and a hidden layer of the artificial neural network model for generating the prediction information regarding the future heart age; and corresponding pre-trained artificial neural network models including at least one of method.

13. A computer program stored on a computer-readable storage medium that includes instructions that cause a computing device to perform operations, The operation is acquiring biosignal data of a user; and estimating probability information indicating that the user has a specific disease and the user's cardiac age based on the biosignal data of the user by utilizing each of a plurality of artificial neural network models; and generating a final output value by weighting the cardiac ages estimated by each of the plurality of artificial neural network models using the estimated probability information as weights for the corresponding artificial neural network models; Including, each of the plurality of artificial neural network models estimates the cardiac age of the user based on the biosignal data of the user and corresponds to a model further trained based on a pre-trained artificial neural network model; each of the pre-trained artificial neural network models predicts probability information indicating that the user has a particular disease based on the biosignal data of the user; Computer program.

14. 1. A computing device comprising: a processor containing one or more cores; a network portion for receiving one or more biosignal data; and memory; Including, The processor: Acquire the user's biosignal data, Utilizing each of a plurality of artificial neural network models, based on the biosignal data of the user, estimate probability information indicating that the user has a specific disease and a cardiac age of the user; generating a final output value by weighting the cardiac ages estimated by each of the plurality of artificial neural network models using the estimated probability information as weights for the corresponding artificial neural network models; each of the plurality of artificial neural network models estimates the cardiac age of the user based on the biosignal data of the user and corresponds to a model further trained based on a pre-trained artificial neural network model; each of the pre-trained artificial neural network models predicts probability information indicating that the user has a particular disease based on the biosignal data of the user; Computing equipment.

Images