Biological age estimation device and method based on disease risk

Abstract

The present invention relates to a biological age estimation device and method that can estimate disease risks for a plurality of diseases by using healthcare bigdata including information about genes of a user, information about lifestyle habits of the user, and information about medical examination records of the user, and then estimate the biological age of the user by synthesizing the disease risks. The biological age estimation device comprises: a data collection module for receiving at least one of genetic information about genes of a user, lifestyle information about lifestyle habits of the user, and examination information about medical examination records of the user; and an estimation module for generating an estimated age by estimating the biological age of the user on the basis of at least one of the genetic information, the lifestyle information, or the examination information.

Description

Device and method for predicting biological age based on disease risk

[0001] The present invention relates to a device and method for predicting biological age based on disease risk.

[0002] Specifically, the present invention relates to a biological age prediction device and method capable of predicting the biological age of a user by predicting the risk of multiple diseases using healthcare big data including information about the user's genes, information about lifestyle habits, and information about medical examination records, and then synthesizing each disease risk.

[0003]

[0004] The content described in this section merely provides background information for the present embodiment and does not constitute prior art.

[0005] As a method of measuring aging, the current aging status and speed can be checked by measuring the biological age (physical age) compared to the age on the resident registration, that is, the actual age. This biological age or physical age is an indicator that can be used to check the overall health status along with the risk of disease.

[0006] In general, measuring telomere length is a representative method used to predict biological age, but there is a large difference in validity and predictive power depending on the tissue from which the telomeres are collected or the method used to measure the length (e.g., minimum length, average length, etc.).

[0007] Recently, methods for predicting biological age based on factors such as DNA methylation levels, gene expression levels, and protein expression levels, which significantly change with age, have been developed. However, because the biological age prediction methods reported so far directly used or combined biomarkers that have been shown to be correlated with biological age, not only did the prediction accuracy of biological age not increase, but they also had limited ability to explain the causes and effects of the predicted biological age and to explain which aspects (e.g., diseases, etc.) should be managed to improve biological age (or if improvement is possible).

[0008] Meanwhile, the present invention used human resources from the National Central Bank of the National Institute of Health, Korea Centers for Disease Control and Prevention (NBK-2023-061).

[0009]

[0010] The purpose of the present invention is to provide a biological age prediction device and method capable of predicting the biological age of a user by predicting the disease risk for multiple diseases using healthcare big data and then synthesizing each disease risk.

[0011] That is, the purpose of the present invention is to provide a biological age prediction device and method capable of improving the accuracy of biological age prediction by calculating the disease risk for each of a plurality of diseases through information about the user's genes, lifestyle habits, medical examination records, etc., and predicting the biological age of the user through the calculated disease risk, and providing the user with information regarding which disease risk must be improved to improve the biological age.

[0012] The objectives of the present invention are not limited to those mentioned above. Other objectives and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, it will be readily apparent that the objectives and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0013]

[0014] According to some embodiments of the present invention, a biological age prediction device includes a data collection module that receives at least one of genetic information about a user's genes, lifestyle information about lifestyle habits, and checkup information about a medical checkup record, and a prediction module that predicts the biological age of the user based on at least one of the genetic information, the lifestyle information, and the checkup information and generates a predicted age, wherein the prediction module may include a disease risk calculation unit that calculates a disease risk for at least one predefined disease based on at least one of the genetic information, the lifestyle information, and the checkup information, and an age prediction unit that generates the predicted age based on the calculated disease risk.

[0015] In addition, the data collection module can receive at least one of the genetic information, the lifestyle information, and the examination information from an external database including a genetic database linked to the biological age prediction device, a user terminal carried by the user, and a medical record database storing the medical examination record.

[0016] In addition, the data collection module can receive, from the user terminal, the results of a survey related to the user's disease entered into the user terminal as the lifestyle information.

[0017] In addition, the decision unit can determine and output the disease risk for each of a plurality of diseases.

[0018] In addition, the disease risk calculation unit may include at least one of a first calculation unit that calculates a genetic risk related to the disease using a pre-learned genetic risk calculation model and the genetic information, a second calculation unit that calculates a lifestyle risk related to the disease using a pre-learned lifestyle risk calculation model and the lifestyle information, a third calculation unit that calculates a screening risk related to the disease using a pre-learned screening risk calculation model and the screening information, and an integrated calculation unit that calculates a comprehensive risk using a pre-learned comprehensive risk calculation model, the genetic risk, the lifestyle risk, and the screening risk.

[0019] In addition, the disease risk calculation unit may further include a determination unit that determines and outputs at least one of the genetic risk, the lifestyle risk, the examination risk, and the comprehensive risk as the disease risk.

[0020] In addition, the age prediction unit can generate the predicted age using a pre-learned age prediction model and the multiple disease risks.

[0021] In addition, the biological age prediction device may further include a learning module that learns the genetic risk calculation model, the lifestyle risk calculation model, the examination risk calculation model, the comprehensive risk calculation model, and the age prediction model.

[0022] Additionally, the learning module can train the age prediction model to generate and output the predicted age based on a weighted sum of the plurality of disease risks.

[0023] In addition, the biological age prediction device further includes an output module that generates output data based on the biological age of the user and provides the generated output data to an external source, wherein the output data may include at least one of comparison data between the actual age of the user and the predicted age, data on changes in the predicted age over time that are periodically generated, and feedback data related to a disease that is a major cause of determining the predicted age.

[0024]

[0025] The biological age prediction device and method according to some embodiments of the present invention can significantly improve the accuracy of biological age prediction by predicting the disease risk for multiple diseases using healthcare big data, and then predicting the biological age of the user by synthesizing each disease risk.

[0026] In addition, the biological age prediction device and method according to some embodiments of the present invention have a novel effect of being able to provide the user with information regarding which disease risks must be improved to improve the biological age (whether the biological age can be reduced) by calculating the disease risk for each of a plurality of diseases through information about the user's genes, lifestyle habits, medical examination records, etc., and predicting the biological age of the user through the calculated disease risk.

[0027] In addition to the above-described contents, the specific effects of the present invention are described together with the specific matters for carrying out the invention below.

[0028]

[0029] FIG. 1 illustrates a biological age prediction system according to some embodiments of the present invention.

[0030] FIG. 2 is a block diagram of a biological age prediction device according to some embodiments of the present invention.

[0031] FIG. 3 is a diagram illustrating the structure of a neural network model according to some embodiments of the present invention.

[0032] FIG. 4 is a block diagram of a prediction module according to some embodiments of the present invention.

[0033] FIG. 5 is a detailed block diagram of a disease risk calculation unit according to some embodiments of the present invention.

[0034] FIGS. 6A to 6D are diagrams for explaining a learning control process for a disease risk calculation unit of a learning module according to some embodiments of the present invention.

[0035] FIG. 7 is a detailed block diagram of an age prediction unit according to some embodiments of the present invention.

[0036] FIGS. 8A to 8C are diagrams for explaining the operation and learning process of an age prediction unit according to some embodiments of the present invention.

[0037] FIG. 9 is a diagram for explaining output data output by an output module according to some embodiments of the present invention.

[0038] Figure 10 is experimental data to explain the accuracy of biological age prediction results according to some embodiments of the present invention.

[0039] Figure 11 is a flowchart of a biological age prediction method according to some embodiments of the present invention.

[0040] FIG. 12 is a diagram illustrating a hardware implementation of a biological age prediction device that performs a biological age prediction method according to some embodiments of the present invention.

[0041]

[0042] The terms and words used in this specification and claims should not be interpreted based on their general or dictionary meanings. In accordance with the principle that inventors can define the concepts of terms and words to best describe their inventions, they should be interpreted in a way that is consistent with the technical concept of the present invention. Furthermore, the embodiments described in this specification and the configurations depicted in the drawings are merely examples of how the present invention can be realized and do not fully represent the technical concept of the present invention. Therefore, it should be understood that various equivalents, modifications, and applicable examples may exist as of the time of filing.

[0043] The terms first, second, A, B, etc. used in this specification and claims may be used to describe various components, but the components should not be limited by these terms. These terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component. The term "and / or" includes any combination of a plurality of related listed items or any item among a plurality of related listed items.

[0044] The terminology used in this specification and claims is for the purpose of describing specific embodiments only and is not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. It should be understood that terms such as "comprise" or "have" in this application do not preclude the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification.

[0045] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0046] Terms defined in commonly used dictionaries should be interpreted to have a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless expressly defined in this application.

[0047] In addition, each configuration, process, procedure or method included in each embodiment of the present invention may be shared within a scope that is not technically inconsistent with each other.

[0048] Hereinafter, a biological age prediction device and method according to some embodiments of the present invention and a biological age prediction system including the same will be described with reference to FIGS. 1 to 11.

[0049]

[0050] FIG. 1 illustrates a biological age prediction system according to some embodiments of the present invention.

[0051] Referring to FIG. 1, the biological age prediction system (1) may include an external database (100), a biological age prediction device (200), and a communication network (300).

[0052] The external database (100) is a device that transmits input data for predicting the user's biological age to the biological age prediction device (200).

[0053] As some examples, the external database (100) may include a genetic database (101), a user terminal (102), a medical record database (103), etc. However, the embodiments of the present invention are not limited thereto, and it is obvious that the external database (100) may include more types of objects.

[0054] The genetic database (101) can store genetic information about the user and transmit such genetic information to the biological age prediction device (200). At this time, the genetic information may include information related to genes in the user's body. For example, the genetic information may include DNA sequencing (Deoxyribo Nucleic Acid Sequencing), DNA chip (Deoxyribo Nucleic Acid Chip), PCR (Polymerase Chain Reaction) results for the user's skin, blood, etc., telomere length information, transcriptome information, proteome information, metabolome information, epigenome information (e.g., DNA methylation), etc., but the embodiments of the present invention are not limited thereto. At this time, when the genetic database (101) receives a control signal regarding the transmission of genetic information of the biological age prediction device (200), it collects genetic information according to the signal and transmits the genetic information to the biological age prediction device (200), or when it already has genetic information about the user, it can transmit the pre-stored genetic information to the biological age prediction device (200) without going through the process of collecting the genetic information. Meanwhile, this genetic database (101) may be in the form of a workstation, a data center, an internet data center (IDC), a direct attached storage (DAS) system, a storage area network (SAN) system, a network attached storage (NAS) system, and a redundant array of inexpensive disks (RAID) system, but the embodiments of the present invention are not limited thereto.

[0055] The user terminal (102) can store lifestyle information about the user and transmit such lifestyle information to the biological age prediction device (200). At this time, the lifestyle information may include information about the user's daily lifestyle habits. For example, the lifestyle information may include the user's smoking information, drinking information, exercise information, food intake information, body mass index, sleep time, stress index, etc., but the embodiments of the present invention are not limited thereto. For example, the user terminal (102) may output a survey pop-up or the like that can obtain the user's lifestyle information on the screen, receive the user's response thereto as a survey result, and determine the received survey result as the lifestyle information. As another example, the user terminal (102) may include a sensor that can obtain the user's lifestyle information (e.g., a sensor that measures a biosignal mounted on a smartphone or a wearable device, etc.), sense the user's lifestyle habits using such a sensor, and then determine the sensing result as the lifestyle information. Meanwhile, the user terminal (102) may be in the form of various types of electronic devices such as a smartphone, a computer, a laptop PC, a wearable device, an IoT device, etc., but the embodiments of the present invention are not limited thereto.

[0056] The medical record database (103) can store examination information about the user and transmit such examination information to the biological age prediction device (200). At this time, the examination information can include information about the user's medical examination record. For example, the examination information can include the user's personal information, hospital visit records, prescription records, examination records, health examination records, etc., but the embodiment of the present invention is not limited thereto. Meanwhile, the medical record database (103) can be in the form of a workstation, a data center, an internet data center (IDC), a direct attached storage (DAS) system, a storage area network (SAN) system, a network attached storage (NAS) system, and a redundant array of inexpensive disks (RAID) system, but the embodiment of the present invention is not limited thereto.

[0057] The biological age prediction device (200) can predict and output the user's biological age based on input data received from an external database (100). In other words, the biological age prediction device (200) can generate a predicted age of the user based on input data received from the external database (100), and generate and output output data using the generated predicted age. This will be described in detail later.

[0058] The communication network (300) refers to a communication means that performs data exchange between an external database (100) and a biological age prediction device (200).

[0059] At this time, the communication network (300) may include a network based on wired Internet technology, wireless Internet technology, and short-range communication technology. The wired Internet technology may include, for example, at least one of a local area network (LAN) and a wide area network (WAN). The wireless Internet technology may include, for example, at least one of wireless LAN (WLAN), Digital Living Network Alliance (DMNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), and 5G NR (New Radio) technology. However, the present embodiment is not limited thereto. Short-range communication technologies may include, for example, at least one of Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), ZigBee, Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, Wi-Fi Direct, and 5G NR (New Radio).However, this embodiment is not limited thereto.

[0060] Hereinafter, the structure and operation of a biological age prediction device (200) according to some embodiments of the present invention will be described in more detail with reference to FIGS. 2 to 11.

[0061]

[0062] FIG. 2 is a block diagram of a biological age prediction device according to some embodiments of the present invention.

[0063] Referring to FIGS. 1 and 2, the biological age prediction device (200) may include a data collection module (210), a prediction module (220), a learning module (230), and an output module (240).

[0064] The data collection module (210) can receive input data from an external database (100). At this time, the input data can include genetic information (Genetic Data, hereinafter referred to as "GD"), lifestyle information (Lifestyle Data, hereinafter referred to as "LD"), and medical examination information (Medical Data, hereinafter referred to as "MD"). In other words, the data collection module (210) can receive genetic information (GD) from a genetic database (101), lifestyle information (LD) from a user terminal (102), and medical examination information (MD) from a medical record database (103).

[0065] Genetic information (GD) may include information related to genes within the user's body. For example, genetic information (GD) may include DNA sequencing (Deoxyribo Nucleic Acid Sequencing), DNA chip (Deoxyribo Nucleic Acid Chip), PCR (Polymerase Chain Reaction) results from the user's skin, blood, etc., telomere length information, transcriptome information, proteome information, metabolome information, epigenome information (e.g., DNA methylation), etc., but embodiments of the present invention are not limited thereto.

[0066] Lifestyle information (LD) may include information about the user's daily living habits. For example, the lifestyle information (LD) may include the user's smoking information, drinking information, exercise information, food intake information, body mass index, sleep time, stress index, etc., but the embodiments of the present invention are not limited thereto. Food intake information may include information about the category of food consumed (e.g., meat, fish, processed food, fried food, caffeine), intake amount, salinity, etc., but it is to be understood that the embodiments of the present invention are not limited thereto. For example, the lifestyle information (LD) may include data in the form of survey results or text data obtained by post-processing the survey results. As another example, the lifestyle information (LD) may include the results of automatically sensing the user's lifestyle habits, etc. using a sensor included in the user terminal (102) as described above in FIG. 1 (e.g., a sensor measuring a biosignal mounted on a smartphone or a wearable device).

[0067] Medical examination information (MD) may include information regarding the user's medical examination records. For example, MD may include the user's personal information, hospital visit records, prescription records, examination records, health examination records, etc., but embodiments of the present invention are not limited thereto.

[0068] The data collection module (210) can transmit genetic information (GD), lifestyle information (LD), and medical examination information (MD) to other components within the biological age prediction device (200). For example, the data collection module (210) can transmit genetic information (GD), lifestyle information (LD), and medical examination information (MD) to the prediction module (220) and the learning module (230), but the embodiments of the present invention are not limited thereto.

[0069] The prediction module (220) can produce a predicted age (hereinafter referred to as "FA"), which is a biological age prediction result for the user, based on genetic information (GD), lifestyle information (LD), and medical examination information (MD). In this case, the predicted age (FA) may be an age predicted based on the user's physical condition, i.e., biological age.

[0070] As some examples, the prediction module (220) can calculate the predicted age (FA) by inputting genetic information (GD), lifestyle information (LD), and medical examination information (MD) into at least one prediction model used to calculate the predicted age (FA). At this time, the prediction model may include a genetic risk calculation model, a lifestyle risk calculation model, a medical examination risk calculation model, a comprehensive disease risk calculation model, an age prediction model, etc., as described below, but the embodiments of the present invention are not limited thereto.

[0071] These predictive models can be trained through various methods. For example, the predictive model may be a pre-known algorithm, or a model trained through statistical analysis (e.g., association analysis, Cox regression, Mendelian randomization), artificial intelligence, machine learning, or deep learning.

[0072] At this time, if the prediction model is trained using a deep learning method, the prediction model may include a pre-trained neural network structure. To explain in more detail, deep learning, a type of machine learning technology, is a technique that learns at a deep level in multiple stages based on data. In other words, deep learning refers to a set of machine learning algorithms that extract core data from multiple data sets by increasing the level.

[0073] As examples, neural networks can utilize various well-known deep learning architectures. For example, neural networks can utilize structures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep belief networks (DBNs), graph neural networks (GNNs), generative adversarial networks (GANs), transformers, and autoencoders.

[0074] Specifically, a Convolutional Neural Network (CNN) is a model that mimics the function of the human brain, based on the assumption that when recognizing an object, humans extract its basic features, then perform complex computations in the brain to recognize the object based on the results. CNNs can include, but are not limited to, well-known structures such as LeNet, AlexNet, VGGNet, GoogleNet, and ResNet.

[0075] RNN (Recurrent Neural Network) is widely used in natural language processing, etc., and is an effective structure for processing time-series data that changes over time. It can construct an artificial neural network structure by stacking layers at each moment.

[0076] A DBN (Deep Belief Network) is a deep learning structure constructed by stacking multiple layers of Restricted Boltzman Machines (RBMs), a deep learning technique. By repeatedly training RBMs (Restricted Boltzman Machines), a certain number of layers can be created, creating a DBN (Deep Belief Network) with that number of layers.

[0077] GNN (Graphic Neural Network, hereinafter referred to as GNN) represents an artificial neural network structure implemented in a way that derives similarity and feature points between modeling data by using modeling data modeled based on data mapped between specific parameters.

[0078] A Generative Adversarial Network (GAN) is an artificial neural network structure that uses a generative neural network and a discriminative neural network to generate new data in a similar form to the input data. GANs may include the well-known DCGAN (Deep Convolutional GAN), CGAN (Conditional GAN), WGAN (Wasserstein GAN), StyleGAN (Style-Based GAN), CycleGAN, etc., but embodiments of the present invention are not limited thereto.

[0079] Transformer is an artificial neural network with an attention-based encoder-decoder structure that can understand the overall meaning between input and output sequences. Transformer uses the attention mechanism to ensure that all elements of the input sequence influence the output sequence, allowing both the encoder and decoder to consider the entire sequence. Transformer can use natural language, time-series data, and even patched images as input.

[0080] An autoencoder is a deep learning architecture that extracts and reconstructs data features. Typically, an autoencoder comprises an encoder, which compresses input values, and a decoder, which restores the compressed data. The encoder transforms the input values ​​into a low-dimensional latent representation, and the decoder reconstructs the latent representation to the same dimensionality as the input values. Each encoder and decoder can be configured as a multilayer perceptron (MLP). When training an autoencoder, input data is input, and weights and biases are trained to minimize the difference between the output and the input values. This trained autoencoder can effectively extract input data features and reconstruct noisy input data. Autoencoders are primarily used in fields such as data compression, dimensionality reduction, noise removal, and data generation, and can also be utilized in areas such as image recognition, natural language processing, and speech recognition.

[0081] Meanwhile, artificial neural network learning can be achieved by adjusting the weights of connections between nodes (and, if necessary, bias values) to ensure the desired output for a given input. Furthermore, artificial neural networks can continuously update their weight values ​​through learning. Furthermore, methods such as backpropagation can be used for artificial neural network learning.

[0082] At this time, machine learning methods for artificial neural networks can include unsupervised learning, semi-supervised learning, and supervised learning. Furthermore, the neural network can be controlled to automatically update its structure to output post-learning analysis data, depending on the settings.

[0083] Hereinafter, a neural network structure according to some embodiments of the present invention will be described with reference to FIG. 3.

[0084]

[0085] FIG. 3 is a diagram illustrating the structure of a neural network model according to some embodiments of the present invention.

[0086] Referring to FIG. 3, a neural network (hereinafter referred to as “NN”) according to some embodiments of the present invention may include an input layer, an output layer, and M hidden layers positioned between the input layer and the output layer.

[0087] Here, weights can be assigned to the edges connecting the nodes of each layer. These weights or the presence or absence of edges can be added, removed, or updated during the learning process. Therefore, the weights of the nodes and edges between the k input nodes and i output nodes can be updated during the learning process.

[0088] Before a neural network (NN) begins learning, all nodes and edges can be set to initial values. However, as information accumulates, the weights of nodes and edges change, and this process can create a match between the parameters input as learning factors and the values ​​assigned to output nodes.

[0089] Additionally, when using a cloud server, neural networks (NNs) can receive and process a large number of parameters. Therefore, neural networks (NNs) can learn based on massive amounts of data.

[0090] The weights of the nodes and edges between the input and output nodes that make up a neural network (NN) can be updated through the NN's learning process. Furthermore, the parameters input or output from a neural network (NN) can be further expanded with various data.

[0091]

[0092] Referring again to FIGS. 1 and 2, this prediction module (220) can be trained by a learning module (230).

[0093] In some examples, the learning module (230) may control the learning of at least one prediction model utilized by the prediction module (220). In other words, the learning module (230) may use predefined learning data to perform and control the learning process for a genetic risk calculation model, a lifestyle risk calculation model, a screening risk calculation model, a comprehensive disease risk calculation model, an age prediction model, etc. utilized by the prediction module (220).

[0094] At this time, the training data may include patient group data and control group data. Patient group data may refer to data on individuals with a specific disease, while control group data may refer to data on individuals without the disease.

[0095] Hereinafter, the operation of the prediction module (220) and the learning module (230) according to some embodiments of the present invention will be described in more detail with reference to FIGS. 4 to 8d.

[0096]

[0097] FIG. 4 is a block diagram of a prediction module according to some embodiments of the present invention.

[0098] Referring to FIG. 4, a prediction module (220) according to some embodiments of the present invention may include a disease risk calculation unit (221) and an age prediction unit (222).

[0099] The disease risk calculation unit (221) can output a disease risk score (Risk Score of Disease, hereinafter referred to as “RS”) based on genetic information (GD), lifestyle information (LD), and examination information (MD).

[0100] As some examples, the disease risk calculation unit (221) can calculate the disease risk (RS) for each of multiple diseases using genetic information (GD), lifestyle information (LD), and examination information (MD).

[0101] Hereinafter, the operation and learning process of the disease risk calculation unit (221) according to some embodiments of the present invention will be described with reference to FIGS. 5 to 6d.

[0102]

[0103] FIG. 5 is a detailed block diagram of a disease risk calculation unit according to some embodiments of the present invention. FIGS. 6a to 6d are diagrams illustrating a learning control process for a disease risk calculation unit of a learning module according to some embodiments of the present invention.

[0104] Referring to FIGS. 2, 4 and 5, a disease risk calculation unit (221) according to some embodiments of the present invention may include a first calculation unit (221a), a second calculation unit (221b), a third calculation unit (221c), an integrated calculation unit (221d) and a decision unit (221e).

[0105] At this time, as described above, the disease risk calculation unit (221) can calculate the disease risk (RS) for each of a plurality of diseases. To explain with a specific example, the disease risk calculation unit (221) can calculate the disease risk (RS) for each of the first disease, the second disease, the third disease, and the nth disease.

[0106] Hereinafter, for convenience of explanation, the process by which the disease risk calculation unit (221) calculates the disease risk (RS) for one specific disease among multiple diseases will be described.

[0107] The first generating unit (221a) can calculate a genetic risk score (hereinafter referred to as "GS") by inputting genetic information (GD) into a genetic risk score calculating model (Generic Risk Score Calculating Model, hereinafter referred to as "M_GS"). At this time, the genetic risk score (GS) may include the probability that a user will genetically have a specific disease defined in advance. In other words, the genetic risk score (GS) may include a result of predicting the probability that a user will have a specific disease (incidence prediction result) based on the genetic information (GD).

[0108] This genetic risk calculation model (M_GS) can be trained by a learning module (230) to output a genetic risk (GS) when genetic information (GD) is input.

[0109] More specifically, referring to FIGS. 2, 4, 5, and 6a, the learning module (230) can determine a genetic biomarker (hereinafter referred to as “GB”) related to a specific predefined disease, and train the genetic risk calculation model (M_GS) to output a genetic risk (GS) based on the genetic information (GD) and the genetic biomarker (GB). At this time, the genetic biomarker (GB) may include information about a biomarker in the human body that has a correlation with the specific disease. For example, the genetic biomarker (GB) may include information about a genetic variant or polymorphism (single nucleotide polymorphism, SNP) related to the specific disease, but the embodiments of the present invention are not limited thereto. For example, the learning module (230) can determine the degree of influence of the genetic mutation of gene A on the disease by comparing the rate at which the genetic mutation of gene A occurs in patient group data with the rate at which the genetic mutation of gene A occurs in control group data, and can determine which associated genes have a correlation higher than a predefined threshold with the disease through this method, and then determine the determined associated genes as genetic biomarkers (GB).

[0110] Specifically, first, the learning module (230) can determine a genetic biomarker (GB) associated with at least one disease. For example, the learning module (230) can receive information about what biomarkers are known to be associated with each of a plurality of diseases in advance (e.g., the high probability of occurrence of a specific disease depending on the type and presence of gene A) from an external source (e.g., a medical-related academic DB), and determine the received information as a genetic biomarker (GB) for each disease. As another example, the learning module (230) can derive a genetic biomarker (GB) associated with each of a plurality of diseases by performing a genome-wide association study and / or a case control study on learning data including patient group data and control group data prepared in advance.

[0111] Next, the learning module (230) can train the genetic risk calculation model (M_GS) to output the genetic risk (GS) for the specific user when the genetic biomarker (GB) and the genetic information (GD) of the specific user are input. At this time, as described above, the learning module (230) can train the genetic risk calculation model (M_GS) through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. For example, the learning module (230) can train the genetic risk calculation model (M_GS) to compare the genetic information (GD) and the genetic biomarker (GB) of the specific user and then output the genetic risk (GS) as the probability that the user will have the disease based on the comparison result. For example, the genetic risk calculation model (M_GS) can be trained by inputting genetic information (GD) of patient group data and control group data, determining inclusion information (e.g., whether included, type of inclusion, etc.) for genetic biomarkers (GB) of each genetic information (GD), and then comparing the inclusion information in each of the patient group data and the control group data to output a genetic risk (GS) corresponding to the genetic information (GD). At this time, the genetic risk (GS) may include an absolute score in the form of a probability value (e.g., a probability value) or a relative score through comparison with a comparison group (e.g., an incidence ranking in a comparison group). However, the embodiments of the present invention are not limited thereto.

[0112] Referring back to FIGS. 2, 4, and 5, the second calculation unit (221b) can calculate a Lifestyle Risk Score (hereinafter referred to as “LS”) by inputting lifestyle information (LD) into a Lifestyle Risk Score Calculating Model (hereinafter referred to as “M_LS”). At this time, the Lifestyle Risk Score (LS) may include the probability of the user having a specific disease defined in advance based on the user’s lifestyle habits. In other words, the Lifestyle Risk Score (LS) may include a result of predicting the probability of the user having a specific disease (incidence rate prediction result) based on the lifestyle information (LD).

[0113] The life risk calculation model (M_LS) can be trained by a learning module (230) to output a life risk (LS) when life information (LD) is input.

[0114] More specifically, referring to FIGS. 2, 4, 5, and 6b, the learning module (230) can determine a related index of lifestyle (hereinafter referred to as “RL”) related to a predefined specific disease, and train the lifestyle risk calculation model (M_LS) to output a lifestyle risk (LS) based on the lifestyle information (LD) and the lifestyle risk correlation (RL). At this time, the lifestyle risk correlation (RL) may include information related to diet, sleep, activity, etc., which are presumed to have a correlation with the specific disease. For example, the lifestyle risk correlation (RL) may include a correlation analysis result between a group, range, or value in each item included in the lifestyle information (LD) and the lifestyle risk (LS), but the embodiment of the present invention is not limited thereto. That is, as described above, lifestyle information (LD) may include the user's smoking information, drinking information, exercise information, food intake information, body mass index, sleep time, and stress index, and lifestyle correlation (RL) may include the results of analyzing the correlation between each of these multiple items and lifestyle risk (LS).

[0115] Specifically, first, the learning module (230) can determine a lifestyle association (RL) related to at least one disease. For example, the learning module (230) can receive information from an external source (e.g., a medical academic DB) regarding lifestyle habits known in advance to be related to each of a plurality of diseases (e.g., a high possibility of lung disease when smoking), and determine the received information as a lifestyle association (RL) for each disease. As another example, the learning module (230) can derive a lifestyle association (RL) related to each of a plurality of diseases by performing a genome-wide association study and / or a case-control study on learning data including pre-prepared patient group data and control group data.

[0116] Next, the learning module (230) can train the lifestyle risk calculation model (M_LS) to output the lifestyle risk (LS) for a specific user when the lifestyle association (RL) and the lifestyle information (LD) of the specific user are input. At this time, as described above, the learning module (230) can train the lifestyle risk calculation model (M_LS) through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. For example, the learning module (230) can train the lifestyle risk calculation model (M_LS) to compare the lifestyle information (LD) and the lifestyle association (RL) of a specific user, and then output the probability that the user will have the disease based on the lifestyle as the lifestyle risk (LS) based on the comparison result. For example, the lifestyle risk calculation model (M_LS) can be trained by inputting lifestyle information (LD) of patient group data and control group data, determining similarity information between each lifestyle information (LD) and lifestyle habit association (RL), and then comparing the similarity information in each of the patient group data and the control group data to output a lifestyle risk (LS) corresponding to the lifestyle information (LD). At this time, the lifestyle risk (LS) may include an absolute score in the form of a probability value (e.g., a probability value) or a relative score through comparison with a comparison group (e.g., an incidence rate ranking in a comparison group). However, the embodiments of the present invention are not limited thereto.

[0117] Referring back to FIGS. 2, 4, and 5, the third calculation unit (221c) can calculate a medical risk score (hereinafter referred to as “MS”) by inputting the medical examination information (MD) into a medical examination risk calculation model (Medical Risk Score Calculating Model, hereinafter referred to as “M_MS”). At this time, the medical examination risk (MS) may include the probability of the user having a specific disease defined in advance based on the user’s medical examination record. In other words, the medical examination risk (MS) may include a result of predicting the probability of the user having a specific disease (incidence rate prediction result) based on the medical examination information (MD).

[0118] The screening risk calculation model (M_MS) can be trained by the learning module (230) to output a screening risk (MS) when screening information (MD) is input. At this time, as described above, the screening information (MD) may include the user's personal information, hospital visit records, prescription records, examination records, health checkup records, etc., but the embodiments of the present invention are not limited thereto.

[0119] For example, referring to FIGS. 2, 4, 5, and 6c, the learning module (230) can train the screening risk calculation model (M_MS) to output a screening risk (MS) when screening information (MD) is input. At this time, as described above, the learning module (230) can train the screening risk calculation model (M_MS) through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. For example, the learning module (230) can train the screening risk calculation model (M_MS) to output the probability that the user will have the disease based on the screening information (MD) as the screening risk (MS). For example, the screening risk calculation model (M_MS) can be trained by comparing the screening information (MD) of the patient group data and the control group data when the screening information (MD) of the patient group data and the control group data is input, thereby outputting the screening risk (MS) corresponding to the screening information (MD). At this time, the screening risk (MS) can include an absolute score in the form of a probability value (e.g., a probability value) or a relative score through comparison with a comparison group (e.g., an incidence rate ranking in a comparison group). However, the embodiments of the present invention are not limited thereto.

[0120] Referring back to FIGS. 2, 4, and 5, the integrated calculation unit (221d) can calculate an integrated disease risk (IRS) by inputting genetic risk (GS), lifestyle risk (LS), and screening risk (MS) into an integrated disease risk calculation model (Integrated Risk Score Calculating Model, hereinafter referred to as “M_IRS”). Accordingly, the integrated disease risk (IRS) can include a disease risk prediction result for a specific disease in which genetic information (GD), lifestyle information (LD), and screening information (MD) are all taken into account. At this time, the integrated disease risk (IRS) output by the integrated calculation unit (221d) can be in the form of a probability value.

[0121] The comprehensive disease risk calculation model (M_IRS) can be trained by a learning module (230) to output a comprehensive disease risk (IRS) when genetic risk (GS), lifestyle risk (LS), and screening risk (MS) are input.

[0122] For example, referring to FIGS. 2, 4, 5, and 6d, the learning module (230) can train the comprehensive disease risk calculation model (M_IRS) to output the comprehensive disease risk (IRS) when the genetic risk (GS), the lifestyle risk (LS), and the screening risk (MS) are input. At this time, as described above, the learning module (230) can train the comprehensive disease risk calculation model (M_IRS) through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. For example, the learning module (230) can train the comprehensive disease risk calculation model (M_IRS) to output the probability that the user will have the disease as the comprehensive disease risk (IRS) by combining the genetic risk (GS), the lifestyle risk (LS), and the screening risk (MS). For example, the comprehensive disease risk calculation model (M_IRS) can be trained in a way that, when the genetic risk (GS), the lifestyle risk (LS), and the screening risk (MS) of the patient group data and the control group data are input, the comprehensive disease risk calculation model (M_IRS) outputs the comprehensive disease risk (IRS) by comparing the genetic risk (GS), the lifestyle risk (LS), and the screening risk (MS) of the patient group data and the control group data with the actual onset of the disease, respectively. At this time, the comprehensive disease risk (IRS) can include an absolute score in the form of a probability value (e.g., a probability value) or a relative score through comparison with a comparison group (e.g., an incidence rate ranking in the comparison group). However, the embodiments of the present invention are not limited thereto.

[0123] As another example, the learning module (230) may determine additional parameters (hereinafter referred to as “AP”) related to a predefined specific disease, and train the comprehensive disease risk calculation model (M_IRS) to output a comprehensive disease risk (IRS) based on the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS), and the additional parameters (AP). The additional parameters (AP) may include information related to human body conditions, diet, sleep, activity, etc., which are predefined to be highly correlated with a specific disease (e.g., age is a highly correlated parameter in the case of Parkinson's disease).

[0124] More specifically, first, the learning module (230) can receive information from an external source (e.g., a medical-related academic DB) about what additional parameters (AP) are known in advance to have a high correlation with each disease for each of a plurality of diseases, and determine the received information as the additional parameters (AP) for each disease.

[0125] Next, the learning module (230) can train the comprehensive disease risk calculation model (M_IRS) to output the comprehensive disease risk (IRS) when the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS), and the additional parameter (AP) are input. At this time, as described above, the learning module (230) can train the comprehensive disease risk calculation model (M_IRS) through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. For example, the learning module (230) can train the comprehensive disease risk calculation model (M_IRS) to output the probability that the user will have the disease as the comprehensive disease risk (IRS) by combining the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS), and the additional parameter (AP). For example, the comprehensive disease risk calculation model (M_IRS) can be trained in a way that, when the genetic risk (GS), lifestyle risk (LS), screening risk (MS) and additional parameter (AP) of patient group data and control group data are input, the genetic risk (GS), lifestyle risk (LS), screening risk (MS) and additional parameter (AP) of the patient group data and the control group data are compared with the actual onset of the disease, thereby outputting the comprehensive disease risk (IRS). At this time, the comprehensive disease risk (IRS) may include an absolute score in the form of a probability value (e.g., a probability value) or a relative score through comparison with a comparison group (e.g., an incidence rate ranking in a comparison group). However, the embodiments of the present invention are not limited thereto.

[0126] Referring again to FIGS. 2, 4 and 5, the decision unit (221e) can determine the disease risk (RS) based on at least one of the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS) and the integrated disease risk (IRS).

[0127] As some examples, the decision unit (221e) may determine at least one of genetic risk (GS), lifestyle risk (LS), screening risk (MS), and integrated disease risk (IRS) as the disease risk (RS).

[0128] For example, the decision unit (221e) may select any one of the genetic risk (GS), lifestyle risk (LS), screening risk (MS), and integrated disease risk (IRS) and determine the selected risk as the disease risk (RS). As another example, the decision unit (221e) may generate the disease risk (RS) by combining (e.g., averaging, weighting, etc.) any two of the genetic risk (GS), lifestyle risk (LS), screening risk (MS), and integrated disease risk (IRS).

[0129]

[0130] Referring again to FIG. 4, the age prediction unit (222) according to some embodiments of the present invention can generate and output a predicted age (FA) based on a disease risk (RS).

[0131] At this time, as described above, the disease risk (RS) may include a disease risk (RS) for each of a plurality of diseases, and the age prediction unit (222) may generate a predicted age (FA) based on the disease risk (RS) for each of a plurality of diseases.

[0132] Hereinafter, the operation and learning process of the age prediction unit (222) according to some embodiments of the present invention will be described with reference to FIGS. 7 to 8c.

[0133]

[0134] Fig. 7 is a detailed block diagram of an age prediction unit according to some embodiments of the present invention. Figs. 8a to 8c are diagrams for explaining the operation and learning process of an age prediction unit according to some embodiments of the present invention.

[0135] Referring to FIG. 4, FIG. 7 to FIG. 8b, the age prediction unit (222) according to some embodiments of the present invention can generate a predicted age (FA) using an age prediction model (hereinafter referred to as “M_FA”).

[0136] As some examples, the age prediction unit (222) can output a predicted age (FA) by inputting the disease risk (RS) for each of a plurality of diseases into the age prediction model (M_FA).

[0137] For example, the age prediction unit (222) can generate a comprehensive predicted age (FA) based on the disease risk (RS) for a plurality of random diseases, as illustrated in FIG. 8A. For example, when the disease risk calculation unit (221) calculates the disease risk (RS) for each of the plurality of diseases, the age prediction unit (222) can generate the predicted age (FA) by inputting the corresponding disease risk (RS) into the age prediction model (M_FA). At this time, although FIG. 8A illustrates the disease risk (RS) for each of the plurality of diseases, such as diabetes risk (RS_1), hypertension risk (RS_2), macular degeneration risk (RS_3), and lung cancer risk (RS_n), this is merely for the convenience of explanation, and the embodiments of the present invention are not limited thereto. That is, the age prediction model (M_FA) can generate a predicted age (FA) for a user by combining the probability of the user having diabetes, the probability of the user having high blood pressure, the probability of the user having macular degeneration, the probability of the user having lung cancer, etc.

[0138] As another example, the age prediction unit (222) can generate a forecasted age of category (hereinafter referred to as “FA_C”) corresponding to the category based on the disease risk (RS) for the categorized diseases, as illustrated in FIG. 8b. For example, when the disease risk calculation unit (221) calculates the disease risk (RS) for each categorized disease, the age prediction unit (222) can generate a forecasted age (FA) by inputting the disease risk (RS) into the age prediction model (M_FA). At this time, in FIG. 8b, the category is “Cancer”, and the categorized multiple diseases are illustrated as stomach cancer, colon cancer, esophageal cancer, lung cancer, etc., and accordingly, the disease risk (RS) for each of the multiple diseases is illustrated as including stomach cancer risk (RS_a), colon cancer risk (RS_b), esophageal cancer risk (RS_c), and lung cancer risk (RS_n), but this is only for convenience of explanation, and the embodiments of the present invention are not limited thereto. That is, the age prediction model (M_FA) can generate a category predicted age (FA_C) for the category called “Cancer” of the user by combining the probability of the user developing stomach cancer, the probability of the user developing colon cancer, the probability of the user developing esophageal cancer, the probability of the user developing lung cancer, etc.

[0139]

[0140] Meanwhile, this age prediction model (M_FA) can be pre-trained to output a predicted age (FA) when the disease risk (RS) for each of multiple diseases is input.

[0141] For example, referring to FIGS. 2, 4, 7, and 8c, the learning module (230) can train the age prediction model (M_FA) to output a predicted age (RS) when a disease risk (RS) is input. For example, the learning module (230) can train the age prediction model (M_FA) to combine disease risks (RS) for each of a plurality of diseases to predict the user's biological age and output the result as the predicted age (RS). For example, the learning module (230) can train the age prediction model (M_FA) to output the predicted age (RS) based on a weighted sum of disease risks (RS) for each of a plurality of diseases included in the disease risk (RS). In other words, the learning module (230) can be trained to determine a disease-specific coefficient for each of a plurality of diseases during the process of the age prediction model (M_FA) outputting the predicted age (RS), and to generate the sum of the values ​​obtained by multiplying the determined disease-specific coefficients by the disease risk (RS) for each disease as the predicted age (RS). At this time, as described above, the learning module (230) can train the age prediction model (M_FA) through a method such as statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, or deep learning. For example, the age prediction model (M_FA) can be trained in a way that, when the disease risk (RS) for each of a plurality of diseases of users included in the learning data is input, the disease risk (RS) is compared with the actual age on the resident registration, and the predicted age (FA) is output. However, the embodiment of the present invention is not limited thereto.

[0142] As another example, the learning module (230) may determine an age-related parameter (hereinafter referred to as “ARP”) and train the age prediction model (M_FA) to output a predicted age (RS) based on the disease risk (RS) and the age-related parameter (ARP). The age-related parameter (ARP) may be a parameter that is generally predefined to be related to human age. For example, the age-related parameter (ARP) may include the user’s basic information (age, height, weight, family history, etc.), lifestyle information (LD), and medical examination information (MD), but the embodiment of the present invention is not limited thereto. For example, the learning module (230) may receive information regarding the type of age-related parameter (ARP) from an external source (e.g., a medical-related academic DB) and determine the received information as an age-related parameter (ARP) for each disease. At this time, the learning module (230) can train the age prediction model (M_FA) through the above-described method, and can control the age prediction model (M_FA) to additionally consider the age-related parameter (ARP). For example, the learning module (230) can train the age prediction model (M_FA) to use the age-related parameter (ARP) as a single factor together with the disease risk (RS) for each of a plurality of diseases. For example, the learning module (230) can train the age prediction model (M_FA) to generate a predicted age (RS) by post-processing or correcting the sum of the product of the coefficients for each of a plurality of diseases and the disease risk (RS) for each disease through the age-related parameter (ARP). However, the embodiments of the present invention are not limited thereto.

[0143]

[0144] Referring back to FIGS. 1 and 2, the prediction module (220) can transmit the generated predicted age (PR) to the output module (240).

[0145] The output module (240) can generate output data (hereinafter referred to as "OD") based on the predicted age (PR) and provide the generated output data (OD) to an external source. For example, the output module (240) can provide the generated output data (OD) to a user terminal (102), etc., but the embodiments of the present invention are not limited thereto.

[0146] At this time, the output data (OD) may include predicted age (FA), comparison data between the user's actual age on the resident registration and the predicted age (FA), data on changes in the predicted age (FA) over time generated periodically, feedback data related to the causal disease that is the main cause of determining the predicted age (FA), etc.

[0147] Hereinafter, output data (OD) according to some embodiments of the present invention will be described with reference to FIG. 9.

[0148]

[0149] FIG. 9 is a diagram for explaining output data output by an output module according to some embodiments of the present invention.

[0150] Referring to FIGS. 1, 2, and 9, output data (OD) according to some embodiments of the present invention may include predicted age (FA), comparison data (OD1), change data (OD2), feedback data (OD3), etc. In other words, the output module (240) may output predicted age (FA), comparison data (OD1), change data (OD2), feedback data (OD3), etc. as output data (OD).

[0151] Comparison data (OD1) may include the results of a comparison between the user's actual age on their resident registration and their predicted age (FA). Specifically, comparison data (OD1) may include information regarding which age has a larger value between the user's actual age and predicted age (FA), as well as the error between the actual age and predicted age (FA).

[0152] The change data (OD2) may include information about changes in the predicted age (FA) generated periodically over time. In other words, the data collection module (210) may collect genetic information (GD), lifestyle information (LD), and examination information (MD) according to a predetermined cycle (e.g., monthly, quarterly, semi-annually, annually, etc.), and the prediction module (220) may generate the predicted age (FA) according to the cycle. At this time, the output module (240) may generate information about the cumulative information on the predicted age (FA) generated according to the cycle, the direction of change between each predicted age (FA), the change speed, etc., as the change data (OD2).

[0153] The feedback data (OD3) may include information regarding the disease that is the main cause of determining the predicted age (FA). In other words, the feedback data (OD3) may include, after identifying the disease that has contributed significantly to generating the predicted age (FA), type information regarding the type of the identified disease and management information for managing the disease. That is, during the prediction age (FA) generation process, the output module (240) may search for diseases in which the product of the disease-specific coefficient of each disease and the disease risk (RS) for each disease exceeds a predefined value or rank, and then generate the type information and management information of the searched disease as feedback data (OD3).

[0154] Through this feedback data (OD3), the present invention can provide a personalized solution for reducing the biological age, or predicted age (FA), to the user. For example, even if the actual age and predicted age (FA) of user A and user B are the same, the diseases that are the main causes in the generation process of the predicted age (FA) may be different between the two users. For example, for user A, the main diseases (diseases in which the product of the disease-specific coefficient and the disease risk score (RS) for each disease exceeds a predefined value or rank) may be “senile cataract, obesity, and gout,” while for user B, the main diseases may be “stroke, chronic obstructive pulmonary disease, and diabetes.” In this case, the output module (240) can customize and provide feedback data (OD3) for the main diseases of each user, and through this, even if user A and user B have the same predicted age (FA), they can receive personalized type information and management information tailored to each individual, which has a new effect.

[0155] Hereinafter, with reference to FIG. 10, experimental data for testing the accuracy of predicted age (PR), i.e., biological age prediction results, according to some embodiments of the present invention will be described.

[0156]

[0157] Figure 10 illustrates experimental data illustrating the accuracy of biological age prediction results according to some embodiments of the present invention. More specifically, the graph depicted in Figure 10 illustrates the correlation between training data used to train each prediction model in the present invention and test data used to test the performance of the corresponding prediction model.

[0158] Before this, the learning step for generating the experimental data of Fig. 10 will first be described.

[0159] Referring to FIGS. 1, 4, 5, 7, and 10, in the process of generating the experimental data of FIG. 10, information on 39,141 users was used as training data in the learning stage.

[0160] First, the screening risk calculation model (M_MS) used by the third output unit (221c) was trained. At this time, the screening information (MD) used included height, weight, waist circumference, systolic blood pressure, diastolic blood pressure, fasting blood sugar, creatinine, hemoglobin, glomerular filtration rate, total cholesterol, triglycerides, high-density cholesterol, low-density cholesterol, AST, ALT, gamma-GTP, proteinuria, and family history (stroke, heart disease, hypertension, diabetes, cancer). At this time, the screening risk calculation model (M_MS) was trained to calculate screening risks (MS) for a total of 20 diseases. At this time, the diseases were set as "senile cataracts, Alzheimer's disease, asthma, breast cancer, cervical cancer, chronic kidney disease, chronic obstructive pulmonary disease, colon cancer, coronary artery disease, stomach cancer, gout, liver cancer, hyperlipidemia, hypertension, lung cancer, obesity, osteoporosis, stroke, thyroid cancer, and diabetes."

[0161] Next, the age prediction model (M_FA) used by the age prediction unit (222) was trained. That is, the age prediction model (M_FA) was trained to generate a predicted age (FA) based on the disease risk (RS) for each of the 20 diseases. At this time, the age prediction model (M_FA) was trained through non-negative multiple logistic regression. This can prevent the incorrect interpretation that "the predicted age (FA) decreases when the disease risk (RS) is high."

[0162] At this time, the disease-specific coefficients used by the age prediction model (M_FA) are summarized in below.

[0163] Diseases Disease Coefficient Age-related cataracts 23.74764 Alzheimer's disease 2.824405 Asthma 0 Breast cancer 2.526459 Cervical cancer 0.971985 Chronic kidney disease 1.005182 Chronic obstructive pulmonary disease 4.01543 Colon cancer 0 Coronary artery disease 0 Gastric cancer 3.057458 Gout 0 Liver cancer 0 Hyperlipidemia 6.598042 Hypertension 0.776807 Lung cancer 0 Obesity 0 Osteoporosis 11.32953 Stroke 0 Thyroid cancer 2.719042 Type 2 diabetes 0 Intercept (y-intercept) 31.53012

[0164]

[0165] In order to evaluate the performance of a biological age prediction device (200) according to several embodiments of the present invention that has gone through a learning stage through the above process, information on 4,349 users was used as test data. First, the disease risk calculation unit (221) calculated the screening risk (MS) based on the screening information (MD) for each user included in the test data through the third calculation unit (221c). At this time, the screening risk calculation model (M_MS) used by the third output unit (221c) used, similar to the learning stage, height, weight, waist circumference, systolic blood pressure, diastolic blood pressure, fasting blood sugar, creatinine, hemoglobin, glomerular filtration rate, total cholesterol, triglycerides, high-density cholesterol, low-density cholesterol, AST, ALT, gamma-GTP, proteinuria, and family history (stroke, heart disease, hypertension, diabetes, cancer) as screening information (MD), and calculated the screening risk (MS) for a total of 20 diseases. At this time, the diseases included, as described above, "senile cataract, Alzheimer's disease, asthma, breast cancer, cervical cancer, chronic kidney disease, chronic obstructive pulmonary disease, colon cancer, coronary artery disease, stomach cancer, gout, liver cancer, hyperlipidemia, hypertension, lung cancer, obesity, osteoporosis, stroke, thyroid cancer, and diabetes."

[0166] Next, the decision unit (221e) determined the screening information (MD) generated through the third output unit (221c) as a disease risk (RS). At this time, the decision unit (221e), like the third output unit (221c), generated disease risks (RS) for a total of 20 diseases. That is, the decision unit (221e) set the screening risk (MS) for each of the set disease types, “senile cataract, Alzheimer’s disease, asthma, breast cancer, cervical cancer, chronic kidney disease, chronic obstructive pulmonary disease, colon cancer, coronary artery disease, stomach cancer, gout, liver cancer, hyperlipidemia, hypertension, lung cancer, obesity, osteoporosis, stroke, thyroid cancer, and diabetes,” as the disease risk (RS) for each disease.

[0167] Next, the age prediction unit (222) generated a predicted age (FA) based on the disease risk (RS) for each of the 20 diseases using the age prediction model (M_FA).

[0168] As a result, the agreement rate (R) between the training data and the test data used in this experiment 2 ) is shown in Figure 10. At this time, for the training data, the matching rate (R 2 ) was confirmed to be 0.77, and the agreement rate (R) for the test data 2 ) was confirmed to be 0.78, which shows that it has a very high agreement rate compared to existing biological age prediction technologies. That is, in the case of the present invention, rather than predicting biological age based on a single disease or factor, it was confirmed that higher accuracy in biological age prediction can be secured by calculating the disease risk for each of multiple diseases and weighting them to generate a predicted age (FA).

[0169]

[0170] FIG. 11 is a flowchart of a biological age prediction method according to some embodiments of the present invention. Each step (S100 to S300) of FIG. 11 can be performed by the biological age prediction device (200 of FIGS. 1 and 2) of FIGS. 1 and 2. Hereinafter, overlapping content will be briefly described.

[0171] Referring to FIGS. 1, 2, 4, 5, 7, 8a, 8b, and 11, first, the biological age prediction device (200) can receive genetic information (GD), lifestyle information (LD), and medical examination information (MD) (S100).

[0172] As some examples, the biological age prediction device (200) can receive at least one of genetic information (GD), lifestyle information (LD), and medical examination information (MD).

[0173] Genetic information (GD) may include information related to genes within the user's body. For example, genetic information (GD) may include DNA sequencing (Deoxyribo Nucleic Acid Sequencing), DNA chip (Deoxyribo Nucleic Acid Chip), PCR (Polymerase Chain Reaction) results from the user's skin, blood, etc., telomere length information, transcriptome information, proteome information, metabolome information, epigenome information (e.g., DNA methylation), etc., but embodiments of the present invention are not limited thereto.

[0174] Lifestyle information (LD) may include information about the user's daily living habits. For example, the lifestyle information (LD) may include the user's smoking information, drinking information, exercise information, food intake information, body mass index, sleep time, stress index, etc., but the embodiments of the present invention are not limited thereto. Food intake information may include information about the category of food consumed (e.g., meat, fish, processed food, fried food, caffeine), intake amount, salinity, etc., but it is to be understood that the embodiments of the present invention are not limited thereto. For example, the lifestyle information (LD) may include data in the form of survey results or text data obtained by post-processing the survey results. As another example, the lifestyle information (LD) may include the results of automatically sensing the user's lifestyle habits, etc. using a sensor included in the user terminal (102) as described above in FIG. 1 (e.g., a sensor measuring a biosignal mounted on a smartphone or a wearable device).

[0175] Medical examination information (MD) may include information regarding the user's medical examination records. For example, MD may include the user's personal information, hospital visit records, prescription records, examination records, health examination records, etc., but embodiments of the present invention are not limited thereto.

[0176] Next, the biological age prediction device (200) can calculate the disease risk (RD) for multiple diseases based on genetic information (GD), lifestyle information (LD) and medical examination information (MD) (S200).

[0177] As some examples, the biological age prediction device (200) can calculate a disease risk (RS) for each of a plurality of diseases based on at least one of genetic information (GD), lifestyle information (LD), and medical examination information (MD).

[0178] For example, the biological age prediction device (200) can calculate genetic risk (GS), lifestyle risk (LS), screening risk (MS), comprehensive disease risk (IRS), etc. using a genetic risk calculation model (M_GS), a lifestyle risk calculation model (M_LS), a screening risk calculation model (M_MS), a comprehensive disease risk calculation model (M_IRS), etc., and can determine at least one of the genetic risk (GS), lifestyle risk (LS), screening risk (MS), and comprehensive disease risk (IRS) as a disease risk (RS).

[0179] Next, the biological age prediction device (200) can predict the user's biological age based on multiple disease risks (RD) (S300). That is, the biological age prediction device (200) can generate a predicted age (FA) based on multiple disease risks (RD).

[0180] As some examples, the age prediction unit (222) can output a predicted age (FA) by inputting the disease risk (RS) for each of a plurality of diseases into the age prediction model (M_FA).

[0181] For example, the age prediction unit (222) can generate a comprehensive predicted age (FA) based on the disease risk (RS) for a plurality of random diseases, as illustrated in FIG. 8A. For example, when the disease risk calculation unit (221) calculates the disease risk (RS) for each of the plurality of diseases, the age prediction unit (222) can generate the predicted age (FA) by inputting the corresponding disease risk (RS) into the age prediction model (M_FA). At this time, although FIG. 8A illustrates the disease risk (RS) for each of the plurality of diseases, such as diabetes risk (RS_1), hypertension risk (RS_2), macular degeneration risk (RS_3), and lung cancer risk (RS_n), this is merely for the convenience of explanation, and the embodiments of the present invention are not limited thereto. That is, the age prediction model (M_FA) can generate a predicted age (FA) for a user by combining the probability of the user having diabetes, the probability of the user having high blood pressure, the probability of the user having macular degeneration, the probability of the user having lung cancer, etc.

[0182] As another example, the age prediction unit (222) can generate a category predicted age (FA_C) corresponding to the category based on the disease risk (RS) for the categorized diseases, as illustrated in FIG. 8b. For example, when the disease risk calculation unit (221) calculates the disease risk (RS) for each categorized disease, the age prediction unit (222) can generate the predicted age (FA) by inputting the disease risk (RS) into the age prediction model (M_FA). At this time, FIG. 8b illustrates that the category is “Cancer” and the categorized multiple diseases are stomach cancer, colon cancer, esophageal cancer, lung cancer, etc., and accordingly, the disease risk (RS) for each of the multiple diseases is illustrated as including a stomach cancer risk (RS_a), a colon cancer risk (RS_b), an esophageal cancer risk (RS_c), and a lung cancer risk (RS_n), but this is merely for convenience of explanation and the embodiments of the present invention are not limited thereto. That is, the age prediction model (M_FA) can generate a category predicted age (FA_C) for the category of "cancer" for the user by combining the probability of the user developing stomach cancer, the probability of the user developing colon cancer, the probability of the user developing esophageal cancer, the probability of the user developing lung cancer, etc.

[0183] Meanwhile, this age prediction model (M_FA) can be pre-trained to output a predicted age (FA) when the disease risk (RS) for each of multiple diseases is input.

[0184] For example, the learning module (230) can train the age prediction model (M_FA) to output the result of predicting the user's biological age by combining the disease risks (RS) for each of a plurality of diseases, as the predicted age (RS). For example, the learning module (230) can train the age prediction model (M_FA) to output the predicted age (RS) based on the weighted sum of the disease risks (RS) for each of a plurality of diseases included in the disease risks (RS). In other words, the learning module (230) can train the age prediction model (M_FA) to determine a disease-specific coefficient for each of a plurality of diseases during the process of outputting the predicted age (RS), and to generate the sum of the values ​​obtained by multiplying the determined disease-specific coefficient by the disease risks (RS) for each disease as the predicted age (RS). At this time, as described above, the learning module (230) can train the age prediction model (M_FA) through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. For example, the age prediction model (M_FA) can be trained in a way that, when multiple disease risks (RS) for each disease of users included in the learning data are input, the disease risks (RS) are compared with the actual age on the resident registration to output the predicted age (FA). However, the embodiments of the present invention are not limited thereto.

[0185]

[0186] FIG. 12 is a diagram illustrating a hardware implementation of a biological age prediction device that performs a biological age prediction method according to some embodiments of the present invention.

[0187] Referring to FIGS. 1 and 12, a biological age prediction device (200) according to some embodiments of the present invention may be implemented as an electronic device (1000). The electronic device (1000) may include a controller (1010), an input / output device (1020), a memory device (1030), an interface (1040), and a bus (1050). The controller (1010), the input / output device (1020), the memory device (1030), and / or the interface (1040) may be coupled to each other via a bus (1050). In this case, the bus (1050) corresponds to a path through which data is transferred.

[0188] Specifically, the controller (1010) may include at least one of a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphics Processing Unit), a microprocessor, a digital signal processor, a microcontroller, an application processor (AP), and logic elements capable of performing functions similar thereto.

[0189] The input / output device (1020) may include at least one of a keypad, a keyboard, a touchscreen, and a display device.

[0190] The memory device (1030) can store data and / or programs, etc.

[0191] The interface (1040) may perform a function of transmitting data to or receiving data from a communication network. The interface (1040) may be wired or wireless. For example, the interface (1040) may include an antenna or a wired / wireless transceiver. Although not illustrated, the memory device (1030) may further include high-speed DRAM and / or SRAM as an operating memory for improving the operation of the controller (1010). The memory device (1030) may store programs or applications therein.

[0192] The biological age prediction device (200) according to embodiments of the present invention may be a system formed by connecting multiple electronic devices (1000) to each other via a network. In this case, each module or combination of modules may be implemented as an electronic device (1000). However, the present embodiment is not limited thereto.

[0193] Additionally, the biological age prediction device (200) may be implemented as at least one of a workstation, a data center, an internet data center (IDC), a direct attached storage (DAS) system, a storage area network (SAN) system, a network attached storage (NAS) system, a redundant array of inexpensive disks (RAID) system, and an electronic document management (EDMS) system, but the present embodiment is not limited thereto.

[0194] Additionally, the biological age prediction device (200) can transmit data to an external database (100) via a network. The network may include a network based on wired Internet technology, wireless Internet technology, and short-range communication technology. For example, the wired Internet technology may include at least one of a local area network (LAN) and a wide area network (WAN).

[0195] The wireless Internet technology may include, for example, at least one of Wireless LAN (WLAN), Digital Living Network Alliance (DMNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), and 5G NR (New Radio) technologies. However, the present embodiment is not limited thereto.

[0196] Short-range communication technologies may include, for example, at least one of Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), ZigBee, Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, Wi-Fi Direct, and 5G NR (New Radio). However, the present embodiment is not limited thereto.

[0197] A biological age prediction device (200) communicating over a network may comply with technical standards and standard communication methods for mobile communications. For example, the standard communication method may include at least one of GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTEA (Long Term Evolution-Advanced), and 5G NR (New Radio). However, the present embodiment is not limited thereto.

[0198] The above description is merely an example of the technical idea of ​​the present embodiment, and those skilled in the art will appreciate that various modifications and variations can be made without departing from the essential characteristics of the present embodiment. Therefore, the present embodiments are not intended to limit the technical idea of ​​the present embodiment, but rather to explain it, and the scope of the technical idea of ​​the present embodiment is not limited by these embodiments. The scope of protection of the present embodiment should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of rights of the present embodiment.

Claims

1. A data collection module that receives at least one of genetic information about the user's genes, lifestyle information about lifestyle habits, and medical examination information about medical examination records; and A prediction module that predicts the biological age of the user based on at least one of the genetic information, the lifestyle information, and the examination information and generates a predicted age, The above prediction module, A disease risk calculation unit that calculates a disease risk for at least one predefined disease based on at least one of the genetic information, the lifestyle information, and the examination information; An age prediction unit that generates the predicted age based on the calculated disease risk. Biological age prediction device.

2. In paragraph 1, The above data collection module, Receiving at least one of the genetic information, the lifestyle information and the examination information from an external database including a genetic database linked to the biological age prediction device, a user terminal carried by the user and a medical record database storing the medical examination record. Biological age prediction device.

3. In paragraph 2, The above data collection module, From the user terminal, the results of a survey related to the user's disease entered into the user terminal are received as the lifestyle information. Biological age prediction device.

4. In paragraph 1, The above decision-making body, Determine and output the disease risk for each of the multiple diseases. Biological age prediction device.

5. In paragraph 4, The above disease risk calculation section is, A first calculation unit that calculates a genetic risk related to the disease using a pre-learned genetic risk calculation model and the genetic information; A second calculation unit that calculates the lifestyle risk related to the disease using a pre-learned lifestyle risk calculation model and the lifestyle information; A third calculation unit that calculates the screening risk related to the disease using a pre-learned screening risk calculation model and the screening information; It includes at least one of a pre-learned comprehensive risk calculation model and an integrated calculation unit that calculates a comprehensive risk using the genetic risk, the lifestyle risk, and the examination risk. Biological age prediction device.

6. In paragraph 5, The above disease risk calculation section is, It further includes a decision unit that determines and outputs at least one of the genetic risk, the lifestyle risk, the examination risk, and the comprehensive risk as the disease risk. Biological age prediction device.

7. In paragraph 6, The above age prediction part, Generating the predicted age using the pre-learned age prediction model and the above multiple disease risks. Biological age prediction device.

8. In paragraph 7, Further comprising a learning module that learns the genetic risk calculation model, the lifestyle risk calculation model, the screening risk calculation model, the comprehensive risk calculation model, and the age prediction model. Biological age prediction device.

9. In paragraph 8, The above learning module, The above age prediction model is trained to generate and output the predicted age based on the weighted sum of the multiple disease risks. Biological age prediction device.

10. In paragraph 1, Further comprising an output module that generates output data based on the biological age of the user and provides the generated output data to an external party, The above output data is, Comprising at least one of comparison data between the actual age of the user and the predicted age, data on changes in the predicted age over time generated periodically, and feedback data related to a disease that is a major cause of determining the predicted age. Biological age prediction device.

Images