Comprehensive disease risk prediction device and method considering associated disease risk

Abstract

The present invention relates to a comprehensive disease risk prediction device and method that comprehensively use 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 can predict disease risk for a specific disease by additionally considering the risk of associated diseases associated with the specific disease. The comprehensive disease risk prediction device comprises: a data collection module for receiving 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 a prediction module for predicting a comprehensive disease risk, which is the risk of the user with regard to a predefined disease, on the basis of the genetic information, the lifestyle information, and the examination information.

Description

Comprehensive disease risk prediction device and method considering associated disease risk

[0001] The present invention relates to a comprehensive disease risk prediction device and method that considers associated disease risks.

[0002] Specifically, the present invention relates to a comprehensive disease risk prediction device and method capable of predicting the disease risk for a specific disease by comprehensively utilizing healthcare big data including information about a user's genes, information about lifestyle habits, and information about medical examination records, while additionally considering the risk of associated diseases that have a correlation with the onset of a specific disease.

[0003]

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

[0005] The development of disease is comprehensively influenced by genetic and environmental factors (lifestyle factors, medical information, etc.). Except for rare genetic disorders, which are absolutely influenced by specific genetic factors, most diseases are influenced by lifestyle and environmental factors in addition to genetics.

[0006] Recently, methods for predicting disease risk (susceptibility) based on genetic factors have been widely used by genetic testing service companies. These methods predict disease risk by examining genetic mutations associated with disease. However, predicting disease risk based solely on these genetic factors has limitations in terms of prediction accuracy and usability.

[0007] Additionally, some methods for predicting disease risk using medical records and medical information have recently been commercialized. These methods generally demonstrate higher accuracy than disease susceptibility tests based on genetic factors. However, disease risk prediction based on medical records, such as health checkups, has limitations: because they do not account for genetic factors, they fail to account for individual differences in disease incidence due to genetic predisposition.

[0008] Therefore, there is a significant need to increase the accuracy and commercialization potential of disease risk prediction by synthesizing a vast amount of healthcare big data on specific diseases to predict disease risk.

[0009] Meanwhile, certain diseases may be associated with other diseases, and there are also attempts to predict the likelihood of developing a specific disease using these associated diseases as parameters.

[0010] 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).

[0011]

[0012] The purpose of the present invention is to provide a comprehensive disease risk prediction device and method capable of predicting the disease risk for a specific disease by comprehensively utilizing healthcare big data including information on a user's genes, information on lifestyle habits, and information on medical examination records, and additionally considering the risk of associated diseases that have a correlation with the onset of a specific disease.

[0013] That is, the purpose of the present invention is to provide a comprehensive disease risk prediction device and method capable of predicting a disease risk related to genes through information about a user's genes, predicting a disease risk related to lifestyle habits through information about lifestyle habits, predicting a disease risk related to medical examination records through information about medical examination records, and then predicting a related disease risk through each of these disease risks, and more accurately predicting a final disease risk related to the disease by synthesizing and integrating each predicted risk.

[0014] 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.

[0015]

[0016] According to some embodiments of the present invention, a comprehensive disease risk prediction device includes a data collection module that receives 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 a comprehensive disease risk, which is a risk of the user related to a predefined disease, based on the genetic information, the lifestyle information, and the checkup information, wherein the prediction module may include a first calculation unit that calculates a genetic risk related to the disease based on the genetic information, a second calculation unit that calculates a lifestyle risk related to the disease based on the lifestyle information, a third calculation unit that calculates a checkup risk related to the disease based on the checkup information, a fourth calculation unit that calculates an associated risk related to the disease based on an associated disease that is related to the disease, and an integrated calculation unit that calculates the comprehensive disease risk based on the genetic risk, the lifestyle risk, the checkup risk, and the associated risk.

[0017] In addition, the data collection module can receive the genetic information, the lifestyle information, and the examination information from an external database including a genetic database linked to the comprehensive disease risk prediction device, a user terminal carried by the user, and a medical record database storing the medical examination records.

[0018] 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.

[0019] In addition, the first calculation unit calculates the genetic risk using a pre-learned genetic risk calculation model and the genetic information, the second calculation unit calculates the lifestyle risk using a pre-learned lifestyle risk calculation model and the lifestyle information, the third calculation unit calculates the screening risk using a pre-learned examination risk calculation model and the screening information, the fourth calculation unit calculates the associated risk using a pre-learned associated risk calculation model and the associated disease, and the integrated calculation unit can calculate the comprehensive disease risk using a pre-learned comprehensive disease risk calculation model, the genetic risk, the lifestyle risk, the screening risk, and the associated risk.

[0020] In addition, the comprehensive disease risk prediction device may further include a learning module that learns the genetic risk calculation model, the lifestyle risk calculation model, the screening risk calculation model, the associated risk calculation model, and the comprehensive disease risk calculation model.

[0021] In addition, the learning module, when training the associated risk calculation model, can determine an associated disease that is related to the disease, and train the associated risk calculation model to determine the associated risk based on at least one of the genetic risk, the lifestyle risk, and the screening risk for the determined associated disease.

[0022] In addition, the learning module can extract, from among a plurality of target diseases, a disease having a positive correlation with the disease exceeding a predetermined value through statistical analysis, and determine the extracted disease as the associated disease.

[0023] In addition, the associated risk calculation model may determine any one of the genetic risk, the lifestyle risk, and the screening risk for the associated disease as the associated risk for the disease, or may determine a combination of any two or three of the genetic risk, the lifestyle risk, and the screening risk for the associated disease as the associated risk.

[0024] In addition, the comprehensive disease risk prediction device may further include an output module that outputs the comprehensive disease risk in the form of a probability value or converts the probability value into a rank compared to a comparison group and outputs it.

[0025] A comprehensive disease risk prediction method performed by a comprehensive disease risk prediction device according to some embodiments of the present invention includes a receiving step of receiving genetic information about a user's genes, lifestyle information about lifestyle habits, and examination information about a medical examination record, and a prediction step of predicting a comprehensive disease risk, which is a risk of the user related to a predefined disease, based on the genetic information, the lifestyle information, and the examination information, wherein the prediction step may include a step of calculating a genetic risk related to the disease based on the genetic information, a step of calculating a lifestyle risk related to the disease based on the lifestyle information, a step of calculating a examination risk related to the disease based on the examination information, a step of calculating an associated risk related to the disease based on an associated disease having a correlation with the disease, and a step of calculating the comprehensive disease risk based on the genetic risk, the lifestyle risk, the examination risk, and the associated risk.

[0026]

[0027] The comprehensive disease risk prediction device and method according to some embodiments of the present invention can further improve the accuracy and commercialization potential of disease risk prediction by comprehensively using information about a user's genes, information about lifestyle habits, and information about medical examination records to predict the disease risk for a specific disease. In other words, the comprehensive disease risk prediction device and method according to some embodiments of the present invention can predict the disease risk related to genes using information about the user's genes, predict the disease risk related to lifestyle habits using information about lifestyle habits, and predict the disease risk related to medical examination records using information about medical examination records, and then calculate the disease risk by integrating these individual disease risks, thereby having a remarkable effect of more accurately predicting the disease risk.

[0028] In addition, the comprehensive disease risk prediction device and method according to some embodiments of the present invention separately predicts disease risks related to genes, disease risks related to lifestyle habits, and disease risks related to medical examination records, and then integrates them to calculate a comprehensive disease risk, thereby enabling the main cause of the disease to be identified when interpreting and utilizing the comprehensive disease risk, and thereby providing disease risk improvement information more effectively.

[0029] In addition, since disease risks related to lifestyle habits and disease risks related to medical examination records have characteristics that can fluctuate over time, the comprehensive disease risk prediction device and method according to some embodiments of the present invention can separately predict disease risks related to genes, disease risks related to lifestyle habits, and disease risks related to medical examination records, and then calculate a comprehensive disease risk by integrating them, thereby distinguishing and processing the volatility characteristics of each risk.

[0030] In addition, the comprehensive disease risk prediction device and method according to some embodiments of the present invention can further improve the accuracy of disease risk prediction by predicting the disease risk for a specific disease by additionally considering the risk of associated diseases that have an onset association with a specific disease.

[0031] 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.

[0032]

[0033] FIG. 1 illustrates a comprehensive disease risk prediction system according to some embodiments of the present invention.

[0034] FIG. 2 is a block diagram of a comprehensive disease risk prediction device according to some embodiments of the present invention.

[0035] FIG. 3 is a diagram illustrating the structure of a neural network model according to some embodiments of the present invention.

[0036] FIG. 4 is a detailed block diagram of a prediction module according to some embodiments of the present invention.

[0037] FIGS. 5A to 5E are diagrams for explaining a learning control process of a learning module according to some embodiments of the present invention.

[0038] Figure 6 is a flowchart of a comprehensive disease risk prediction method according to some embodiments of the present invention.

[0039] FIG. 7 is a diagram illustrating a hardware implementation of a comprehensive disease risk prediction device that performs a comprehensive disease risk prediction method according to some embodiments of the present invention.

[0040]

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] Hereinafter, a comprehensive disease risk prediction device and method according to some embodiments of the present invention and a comprehensive disease risk prediction system including the same will be described with reference to FIGS. 1 to 7.

[0048]

[0049] FIG. 1 illustrates a comprehensive disease risk prediction system according to some embodiments of the present invention.

[0050] Referring to FIG. 1, a comprehensive disease risk prediction system (1) may include an external database (100), a comprehensive disease risk prediction device (200), and a communication network (300).

[0051] The external database (100) is a device that transmits input data regarding the user's disease risk to the comprehensive disease risk prediction device (200).

[0052] 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.

[0053] The genetic database (101) can store genetic information about the user and transmit such genetic information to the comprehensive disease risk 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 targeting the user's skin, blood, 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 genetic information transmission of the comprehensive disease risk prediction device (200), it collects genetic information according to the signal and transmits it to the comprehensive disease risk prediction device (200), or when it already has genetic information about the user, it can transmit previously stored genetic information to the comprehensive disease risk prediction device (200) without a process of collecting 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.

[0054] The user terminal (102) can store lifestyle information about the user and transmit such lifestyle information to the comprehensive disease risk 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, etc., which can obtain the user's lifestyle information, on the screen, and 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 (e.g., a sensor measuring a biosignal mounted on a smartphone or a wearable device, etc.) that can obtain the user's lifestyle information, and use such a sensor to sense the user's lifestyle habits, etc., 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.

[0055] The medical record database (103) can store examination information about the user and transmit such examination information to the comprehensive disease risk 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.

[0056] The comprehensive disease risk prediction device (200) can calculate a comprehensive disease risk based on input data received from an external database (100) and output the calculated comprehensive disease risk as output data.

[0057] At this time, the comprehensive disease risk may be a disease risk prediction result that takes into account all genetic information, lifestyle information, examination information, and associated diseases that are related to a specific disease received from an external database (100). In other words, the comprehensive disease risk prediction device (200) can calculate a comprehensive disease risk by combining, integrating, and / or synthesizing genetic information received from a genetic database (101), lifestyle information received from a user terminal (102), examination information received from a medical record database (103), and information on associated diseases. 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 comprehensive disease risk 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 the comprehensive disease risk prediction device (200) according to some embodiments of the present invention will be described in more detail with reference to FIGS. 2 to 7.

[0061]

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

[0063] Referring to FIGS. 1 and 2, the comprehensive disease risk 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, etc. targeting the user's skin, blood, 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 comprehensive disease risk 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 calculate an integrated disease risk score (hereinafter referred to as "IRS") based on genetic information (GD), lifestyle information (LD), and medical examination information (MD). At this time, the integrated disease risk score (IRS) may be a predicted result of the user's risk for a predefined disease (e.g., kidney disease, lung disease, etc.). In other words, the integrated disease risk score (IRS) may include a predicted incidence rate for a specific disease of the user, taking into account all of the genetic information (GD), lifestyle information (LD), and medical examination information (MD).

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

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

[0072] In this case, if the risk model is trained using deep learning, the risk model may include a pre-trained neural network structure. To explain in more detail, deep learning, a type of machine learning technology, learns at multiple levels based on data, going down to a deeper level. 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 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 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, the detailed process of calculating the comprehensive disease risk (IRS) by inputting genetic information (GD), lifestyle information (LD) and screening information (MD) into at least one risk model by the prediction module (220) will be described later.

[0093] Meanwhile, the comprehensive disease risk score (IRS) output by the prediction module (220) may be in the form of a probability value. In other words, the prediction module (220) may output the probability value that the user will have the disease as the comprehensive disease risk score (IRS). In this case, the prediction module (220) may provide the comprehensive disease risk score (IRS) to an output module (240), etc.

[0094] The learning module (230) can control the learning of at least one risk model used by the prediction module (220). In other words, the learning module (230) can use predefined learning data to perform and control the learning process for the genetic risk calculation model, lifestyle risk calculation model, screening risk calculation model, and comprehensive disease risk calculation model used by the prediction module (220).

[0095] 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.

[0096] The specific process by which the learning module (230) controls learning for the risk model will be described later.

[0097] The output module (240) can output output data (hereinafter referred to as “OD”) based on the comprehensive disease risk score (IRS).

[0098] At this time, as described above, the comprehensive disease risk (IRS) provided by the output module (240) from the prediction module (220) may be in the form of a probability value.

[0099] For example, the output module (240) can output the comprehensive disease risk score (IRS) in the form of a probability value as output data (OD). In other words, the output module (240) can provide the absolute score, which is the comprehensive disease risk score (IRS) itself in the form of a probability value provided from the prediction module (220), as output data (OD) to the user terminal (102), etc.

[0100] As another example, the output module (240) may post-process the comprehensive disease risk (IRS) in the form of a probability value to convert it into a ranking compared to a comparison group, and output the converted data as output data (OD). In other words, the output module (240) may compare the comprehensive disease risk (IRS) in the form of a probability value provided from the prediction module (220) with similar users in the comparison group, thereby calculating the risk ranking in the comparison group, and may provide the calculated ranking or the relative score based on the comparison with the comparison group as output data (OD) to the user terminal (102), etc.

[0101] 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 5e.

[0102]

[0103] FIG. 4 is a detailed block diagram of a prediction module according to some embodiments of the present invention. FIGS. 5A to 5E are diagrams illustrating a learning control process of a learning module according to some embodiments of the present invention.

[0104] Referring to FIGS. 2 and 4, a prediction module (220) according to some embodiments of the present invention may include a first calculation unit (221), a second calculation unit (222), a third calculation unit (223), a fourth calculation unit (224), and an integrated calculation unit (225).

[0105] The first generating unit (221) 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).

[0106] 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.

[0107] More specifically, referring to FIGS. 2, 4, and 5A, 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).

[0108] 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.

[0109] 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 be data in the form of a probability value. However, the embodiments of the present invention are not limited thereto.

[0110] Referring back to FIGS. 2 and 4, the second calculation unit (222) 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).

[0111] 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.

[0112] More specifically, referring to FIGS. 2, 4, and 5b, 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 embodiments of the present invention are 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).

[0113] 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 risk 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.

[0114] 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 lifestyle risk (LS) as the probability that the user will have the disease 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 the 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 control group data to output a lifestyle risk (LS) corresponding to the lifestyle information (LD). At this time, the lifestyle risk (LS) may be data in the form of a probability value. However, the embodiments of the present invention are not limited thereto.

[0115] Referring back to FIGS. 2 and 4, the third calculation unit (223) 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 (prevalence prediction result) based on the medical examination information (MD).

[0116] 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.

[0117] For example, referring to FIGS. 2, 4, and 5c, 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, respectively, when the screening information (MD) of the patient group data and the control group data are input, and outputting the screening risk (MS) corresponding to the screening information (MD). At this time, the screening risk (MS) may be data in the form of a probability value. However, the embodiments of the present invention are not limited thereto.

[0118] Referring back to FIGS. 2 and 4, the fourth calculation unit (224) can calculate a related disease risk score (hereinafter referred to as “RS”) using a related disease risk score calculation model (hereinafter referred to as “M_RS”). At this time, the related disease risk score (RS) may include a probability that a user will have a specific disease based on related diseases that are related to a predefined specific disease. In other words, the related risk score (RS) may include a result of predicting the probability that a user will have a specific disease (incidence prediction result) based on related disease information related to related diseases that are related to a specific disease.

[0119] This associated risk calculation model (M_RS) can be trained by a learning module (230) to output an associated risk (RS) when genetic risk (GS), lifestyle risk (LS), and screening risk (MS) for associated diseases are input.

[0120] More specifically, referring to FIGS. 2, 4, and 5d, the learning module (230) determines a related disease (hereinafter referred to as "RD") that is related to a predefined specific disease among a plurality of target diseases, and trains the related risk calculation model (M_RS) to output a related risk (RS) based on the related disease (RD), the genetic risk (GS_RD), the lifestyle risk (LS_RD), and the screening risk (MS_RD) for the related disease (RD). At this time, the related disease (RD) may include other diseases that have an onset association with the specific disease. For example, since a user who is obese has a high risk of developing type 2 diabetes, if the specific disease is "type 2 diabetes," the related disease (RD) for this may be "obesity," but it is to be understood that the embodiments of the present invention are not limited thereto.

[0121] Specifically, first, the learning module (230) can determine at least one associated disease (RD) related to a specific disease among a plurality of target diseases. For example, the learning module (230) can receive information about an associated disease (RD) known in advance to be related to each of the plurality of diseases from an external source (e.g., a medical-related academic DB) (e.g., if the specific disease is “type 2 diabetes,” the associated disease (RD) for it can be “obesity”), and determine the received information as an associated disease (RD) for the specific disease. As another example, the learning module (230) can derive an associated disease (RD) related to each of the 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. At this time, the learning module (230) can determine the onset correlation between each of a plurality of target diseases and a specific disease through statistical analysis of patient group data and control group data, and then determine a target disease whose onset correlation is greater than a predetermined threshold as a related disease (RD), but the embodiment of the present invention is not limited thereto.

[0122] Next, the learning module (230) can train the associated risk calculation model (M_RS) to output an associated risk (RS) for a specific user through the genetic risk (GS_RD), lifestyle risk (LS_RD) and screening risk (MS_RD) for the associated disease (RD) of the specific user. More specifically, the associated risk calculation model (M_RS) can be trained by the learning control of the learning module (230) to output an associated risk (RS) based on at least one of the genetic risk (GS_RD), lifestyle risk (LS_RD) and screening risk (MS_RD) for the associated disease (RD). For example, the associated risk calculation model (M_RS) can determine any one of the genetic risk (GS_RD), lifestyle risk (LS_RD) and screening risk (MS_RD) for the associated disease (RD) as the associated risk (RS) for the specific disease. As another example, the associated risk calculation model (M_RS) can determine the associated risk (RS) as a combination (e.g., average, weighted sum, etc.) of any two or three of the genetic risk (GS_RD), lifestyle risk (LS_RD), and screening risk (MS_RD) for the associated disease (RD). In this case, the associated risk (RS) may be data in the form of a probability value. However, embodiments of the present invention are not limited thereto.

[0123] Referring back to FIGS. 2 and 4, the integrated calculation unit (225) can calculate the integrated disease risk (IRS) by inputting genetic risk (GS), lifestyle risk (LS), screening risk (MS), and associated risk (RS) into the 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), screening information (MD), and associated risk (RS) are all taken into account. At this time, the integrated disease risk (IRS) output by the integrated calculation unit (225) can be in the form of a probability value.

[0124] 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), screening risk (MS), and associated risk (RS) are input.

[0125] For example, referring to FIGS. 2, 4, and 5e, the learning module (230) can train a comprehensive disease risk calculation model (M_IRS) to output a comprehensive disease risk (IRS) when genetic risk (GS), lifestyle risk (LS), screening risk (MS), and association risk (RS) 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 be trained to output the comprehensive disease risk calculation model (M_IRS) by combining the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS), and the associated risk (RS) to comprehensively output the probability that the user will have the disease as the comprehensive disease risk (IRS). For example, the comprehensive disease risk calculation model (M_IRS) can be trained in a manner that, when the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS), and the associated risk (RS) 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), the screening risk (MS), and the associated risk (RS) of the patient group data and the control group data, respectively, with the actual onset. At this time, the comprehensive disease risk (IRS) may be data in the form of a probability value. However, the embodiments of the present invention are not limited thereto.

[0126] 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), the associated risk (RS), 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).

[0127] 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.

[0128] 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), lifestyle risk (LS), screening risk (MS), association risk (RS), and additional parameters (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), the associated risk (RS), and the additional parameter (AP). For example, the comprehensive disease risk calculation model (M_IRS) can be trained in a manner that, when the genetic risk (GS), the lifestyle risk (LS), the screening risk (MS), the associated risk (RS), and the additional parameter (AP) 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), the screening risk (MS), the associated risk (RS), and the additional parameter (AP) of the patient group data and the control group data, respectively, with the actual onset. At this time, the comprehensive disease risk (IRS) may be data in the form of a probability value. However, the embodiments of the present invention are not limited thereto.

[0129]

[0130] Referring again to FIGS. 2 and 4, the following describes experimental data predicting the comprehensive disease risk (IRS) through the comprehensive disease risk prediction device (200) of the present invention.

[0131] The experimental data included the results of experiments on type 2 diabetes (hereinafter referred to as "diabetes") and hypertension, with the experimental groups divided into male and female groups. Diabetics were defined as those with a fasting blood sugar level of 126 mg / dL or higher, and hypertensive patients were defined as those with a systolic blood pressure (SBP) of 140 mmHg or higher or a diastolic blood pressure (DBP) of 90 mmHg or higher.

[0132] The composition of the experimental group in the experimental data was as follows: for male diabetes, the experiment consisted of 1,806 patients and 18,060 controls; for female diabetes, the experiment consisted of 1,785 patients and 17,850 controls; for male hypertension, the experiment consisted of 4,497 patients and 18,843 controls; and for female hypertension, the experiment consisted of 5,349 patients and 38,076 controls.

[0133] First, the first output unit (221) calculated the genetic risk (GS) using the genetic risk calculation model (M_GS).

[0134] In the case of below, an example of a genetic biomarker (GB) determined by the learning module (230) to calculate the genetic risk (GS) for this experimental group is shown.

[0135] Disease GeneBiomarker(GB)(SNP(rsID))Gene NameRisk FactorEffect Size(Odds Ratio)Type 2 Diabetes rs243021BCL11AA1.08Type 2 Diabetes rs3923113GRB14A1.15Type 2 Diabetes rs1801282PPARGC1.16Type 2 Diabetes rs4402960IGF2BP2T1.14Type 2 Diabetes rs6813195TMEM154C1.08Type 2 Diabetes rs4712523CDKAL1G1.27Type 2 Diabetes rs13266634SLC30A8C1.22Type 2 Diabetes rs7041847GLIS3A1.10Type 2 Diabetes rs10811661CDKN2A / 2BT1.20Type 2 Diabetes rs2796441LOC101927502G1.06Type 2 diabetes rs11257655CDC123T1.11Type 2 diabetes rs1111875HHEXC1.21Type 2 diabetes rs7903146TCF7L2T1.40Type 2 diabetes rs2237892KCNQ1C1.33Type 2 diabetes rs5219KCNJ11T1.14Type 2 diabetes rs10830963MTNR1BG1.07Type 2 Diabetes rs8050136FTOA1.17 Hypertension rs880315CASZ1C1.10 Hypertension rs2932538MOV10G1.05 Hypertension rs16849225FIGNC1.08 Hypertension rs16998073FGF5T1.29 Hypertension rs1799945HFEG1.10 Hypertension rs1004467CYP17A1A1.09 Hypertension rs17249754ATP2B1G1.22 Hypertension rs35444TBX3A1.09 Hypertension rs1378942CSKC1.10 Hypertension rs16948048ZNF652G1.06

[0136]

[0137] In the above , single nucleotide polymorphism (SNP) was used as the genetic biomarker (GB), and accordingly, explains the "SNP (rsID)" which is the identifier ID of multiple SNPs for each disease, the "gene name" related to the name of the gene to which the SNP belongs, the "risk factor" related to the specific base associated with the disease within the gene, and the "effect size (Odds ratio)" which is a value indicating the effect of the SNP on the disease. At this time, the genetic risk calculation model (M_GS) calculated the genetic risk (GS) using a method such as <Mathematical Formula 1> below.

[0138] <Mathematical Formula 1>

[0139]

[0140] In the above <Mathematical Formula 1>, GS is the genetic risk, represents the effect size (Odds ratio) of the i-th genetic biomarker (GB), represents the number of risk variants of the i-th genetic biomarker (GB) (one of 0, 1, or 2), and n represents the total number of genetic biomarkers (GB).

[0141] Next, the second output unit (222) calculated the life risk (LS) using the life risk calculation model (M_LS).

[0142] In the case of below, an example of the lifestyle association (RL) determined by the learning module (230) to calculate the lifestyle risk (LS) for the experimental group as above is shown.

[0143] Lifestyle effect size (Effect size) Diabetes Hypertension Male Female Male Female Drinking habits Low level 1 Not used 1 1 Medium level 1.19 Not used 1.07 1.16 High 1.42 Not used 1.77 1.19 Smoking habits Smoker 1.5 1.43 1.11 1.19 Non-smoker 11 11 Body mass index Underweight to normal weight 11 11 Overweight 1.45 1.5 1.28 1.65 Obese 2.04 2.42 1.84 2.42 Meat intake Less than once a week 11 1-2 times a week 1.14 1.22 3-5 times a week 1.23 1.28 Daily 1.34 1.39 Processed food intake Less than twice a week Not used 1 3-5 times a week Not used 1.04 Daily Not used 1.25 Fried food intake Less than once a week 11 weeks 1-2 times 1.06 1 3-5 times a week 1.13 1.18 Daily 1.19 1.21 Salty eating habits Do not eat salty not used 1 Eat salty not used 1.33 Exercise habits Less than 3 times a week 11 3-5 times a week 0.72 0.89 Daily 0.56 0.81 Depression Not high 1 1 High 1.38 1.42 Stress Low not used 1 Moderate not used 1.47 High not used 1.84 Caffeine intake Less than 1 cup per day 1 not used 1-2 cups per day 0.96 not used 3-4 cups per day 0.71 not used 5 or more cups per day 0.59 not used Average sleep time Less than 5 hours 1.23 not used 5-6 hours 1.14 not used 7-8 hours 1 not used 9 or more hours 1.14 not used

[0144]

[0145] In the above , the influence of each numerical value or range of multiple lifestyle habits (e.g., drinking habits, etc.) on diseases (e.g., male diabetes, female diabetes, male hypertension, female hypertension), i.e., the "Effect Size" that analyzes the correlation between multiple lifestyle information (LD) and diseases is explained. In other words, the learning module (230) can determine the effect size (Effect Size) for each lifestyle habit as in the above as the lifestyle association (RL) that serves as the basis for calculating the lifestyle risk (LS). At this time, the lifestyle risk calculation model (M_LS) calculated the lifestyle risk (LS) using a method such as <Mathematical Formula 2> below.

[0146] <Mathematical Formula 2>

[0147]

[0148] In the above <Mathematical Formula 2>, represents the effect size of the ith lifestyle information (LD), and n represents the number of lifestyle information (LD) considered to be associated with the disease.

[0149] Next, the third output unit (223) calculated the screening risk (MS) using the screening risk calculation model (M_MS).

[0150] At this time, the screening risk calculation model (M_MS) was machine-learned to calculate the screening risk (MS) based on the input of screening information (MD) such as 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 information (stroke, heart disease, diabetes, hypertension, cancer).

[0151] In other words, the third output unit (223) calculates the screening risk (MS) by using a machine-learned screening risk calculation model (M_MS) to calculate the screening risk (MS) according to the input information of 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 information (stroke, heart disease, diabetes, hypertension, cancer).

[0152] Next, the fourth output unit (224) calculated the associated risk (RS) using the associated risk calculation model (M_RS).

[0153] and below illustrate an example of an associated disease (RD) determined by the learning module (230) to calculate the associated risk (RS) for the experimental group as above. Specifically, illustrates the process of deriving an associated disease (RD) when a specific disease is set to “diabetes,” and illustrates the process of deriving an associated disease (RD) when a specific disease is set to “hypertension.” E in and below represents exponential notation.

[0154] DiseaseDiabetesGenderMaleFemaleAverageMedical InformationRiskPatientsControlP-valuePatientsControlP-valueAging Cataracts 0.4110.3572.24.E-180.4240.3106.82.E-46 Alzheimer's disease 0.2570.1105.56.E-330.2130.1219.77.E-27 Asthma 0.3470.3813.93.E-040.5230.4479.88.E-16 Breast cancer 0.3550.3882.65.E-13 Cervical cancer 0.3650.4705.19.E-66 Chronic kidney disease 0.4880.3476.01.E-370.5360.3382.06.E-155 Chronic obstructive pulmonary disease Lung disease 0.269 0.327 3.93.E-11 0.35 10.39 28.73.E-11 Colon cancer 0.38 30.44 51.04.E-13 0.5 210.41 83.46.E-22 Coronary artery disease 0.42 0.29 51.23.E-36 0.49 20.28 92.85.E-107 Stomach cancer 0.177 0.2434 .22.E-120.2320.3116.77.E-26Gout0.4180.4404.23.E-030.4420.3187.48.E-26Liver cancer0.2880.2699.35.E-020.2690.2044.04.E-10Hyperlipidemia0.4540.4896.86.E-190.5740.4802 .14.E-84 Hypertension 0.576 0.458 8.91 0.82 0.62 9 0.43 4 1.17 1.14 ... .4575.65.E-020.4260.4362.24.E-01Prostate cancer0.2450.3169.25.E-09Stroke0.3310.3081.69.E-030.4730.2611.44.E-73Thyroid cancer0.3840.3722.16.E-010.3710.3594.65.E-02

[0155] Disease Hypertension Gender Male Female Average Medical Information Risk Patient Group Control Group P-value Patient Group Control Group P-value Aging Cataracts 0.373 0.349 1.40 0.3800 289 1.50 0.33 Alzheimer's disease 0.1400 115 1.57 0.1470 1203 78 0.3800 40 13.24 0.20 ... Lung disease 0.2940.3433.84.E-080.3970.3766.11.E-04 Colon cancer 0.3860.4583.84.E-200.4870.4502.35.E-04 Coronary artery disease 0.3070.3245.29.E-020.4130.2811.97.E-52 Stomach cancer 0. 2020.2441.98.E-050.2430.2927.79.E-12 Gout0.5240.4491.29.E-220.4090.3084.38.E-17 Liver cancer0.2650.2921.38.E-020.1800.1856.26.E-01 Hyperlipidemia0.5000.4963 .44.E-010.5600.4873.14.E-63Lung cancer0.3090.3761.04.E-190.3690.3943.36.E-02Obesity0.2590.1551.30.E-150.3110.1451.26.E-37Osteoporosis0.3980.4641.18.E-19 0.5090.4501.97.E-14 Prostate cancer 0.3070.2932.70.E-01 Stroke 0.3330.3231.69.E-010.4440.2784.85.E-50 Thyroid cancer 0.3160.3763.43.E-100.3470.3261.04.E-04 Type 2 diabetes 0.5010.4271.69.E-220.5240.3631.01.E-62

[0156] At this time, the learning module (230) can calculate a P-value through a t-test, and based on the size of this P-value, can determine an associated disease (RD) related to a specific disease (e.g., male diabetes, female diabetes, male hypertension, female hypertension). For example, the learning module (230) can determine the target disease as an associated disease (RD) when the P-value is less than 1E-10, but it is obvious that the embodiment of the present invention is not limited thereto. In the case of the above , if the specific disease is male diabetes, the learning module (230) can determine "aging cataract, Alzheimer's disease, chronic kidney disease, coronary artery disease, hypertension, obesity", etc. as related diseases (RD), and if the specific disease is female diabetes, it can determine "aging cataract, Alzheimer's disease, asthma, chronic kidney disease, colon cancer, coronary artery disease, gout, hyperlipidemia, hypertension, obesity, stroke", etc. as related diseases (RD). In the case of the above , the learning module (230) can determine "gout, obesity, diabetes", etc. as associated diseases (RD) when the specific disease is male hypertension, and can determine "senile cataract, asthma, chronic kidney disease, coronary artery disease, gout, hyperlipidemia, obesity, osteoporosis, stroke, diabetes", etc. as associated diseases (RD) when the specific disease is female hypertension. At this time, the associated risk calculation model (M_RS) outputs an associated risk (RS) based on the determined associated disease (RD), the genetic risk (GS_RD), the lifestyle risk (LS_RD), and the screening risk (MS_RD) for the associated disease (RD).

[0157] Next, the integrated output unit (225) calculated the comprehensive disease risk (IRS) using the comprehensive disease risk calculation model (M_IRS).

[0158] At this time, the comprehensive disease risk calculation model (M_IRS) was trained through multiple logistic regression to calculate the comprehensive disease risk (IRS) based on the input genetic risk (GS), lifestyle risk (LS), screening risk (MS), and associated risk (RS).

[0159] In other words, the integrated output unit (225) calculates the comprehensive disease risk (IRS) by using the comprehensive disease risk calculation model (M_IRS) learned according to multiple logistic regression when the genetic risk (GS), lifestyle risk (LS), screening risk (MS) and associated risk (RS) are input to calculate the comprehensive disease risk (IRS).

[0160] below shows the performance test results of the comprehensive disease risk (IRS) predicted by the comprehensive disease risk prediction device (200) according to some embodiments of the present invention.

[0161] ROC Area Performance of Disease Sex Genetic Risk (GS) ROC Area Performance of Lifestyle Risk (LS) ROC Area Performance of Screening Risk (MS) ROC Area Performance of Comprehensive Risk ROC Area Performance of Comprehensive Disease Risk (IRS) Diabetes M 0.62 2 0.57 4 0.76 0 0.77 3 0.83 3 Diabetes F 0.58 3 0.62 10.82 10.82 4 0.87 9 Hypertension M 0.54 10.58 10.66 0 0.67 0 0.69 8 Hypertension F 0.54 7 0.59 9 0.71 0 0.71 4 0.76 6

[0162] above shows the ROC Area performance of genetic risk (GS) by disease and gender, ROC Area performance of lifestyle risk (LS), ROC Area performance of screening risk (MS), ROC Area performance of the comprehensive risk that combines genetic risk (GS), lifestyle risk (LS), and screening risk (MS), and ROC Area performance of comprehensive disease risk (IRS). Here, ROC Area performance refers to the prediction accuracy (e.g., area under the curve) evaluated based on the ROC curve (Receiver Operating Characteristic curve) in which the X-axis is composed of the False Positive Rate (FPR) and the Y-axis is composed of the True Positive Rate (TPR). As explained in above, the ROC Area performance of the comprehensive disease risk (IRS) is higher than the ROC Area performance of each individual risk (GS, LS, MS) or the comprehensive risk that combines the total risk (GS), lifestyle risk (LS), and screening risk (MS). This suggests that using the IRS (Integrated Risk Score) yields higher predictive performance than using individual risks (GS, LS, MS) or a composite risk score that combines the global risk (GS), lifestyle risk (LS), and screening risk (MS). In other words, by calculating the IRS by additionally considering the associated risk (RS) in addition to each individual risk score (GS, LS, MS), the predictive potential for specific diseases based on each user's gender can be further enhanced.

[0163]

[0164] FIG. 6 is a flowchart of a comprehensive disease risk prediction method according to some embodiments of the present invention. Each step (S100 to S600) of FIG. 6 can be performed by the comprehensive disease risk prediction device (200 of FIGS. 1 and 2) of FIGS. 1 and 2 . Below, overlapping details are briefly described.

[0165] Referring to FIGS. 1, 2, 4 and 6, first, the comprehensive disease risk prediction device (200) can receive genetic information (GD) about the user's genes, lifestyle information (LD) about lifestyle habits and examination information (MD) about medical examination records (S100).

[0166] At this time, the genetic information (GD) may include information related to the genes in the user's body. For example, the genetic information (GD) 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., but the embodiments of the present invention are not limited thereto. The 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. The 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 obvious that the embodiments of the present invention are not limited thereto. At this time, the lifestyle information (LD) may be in the form of a survey result or in the form of text data obtained by post-processing the survey result. 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, and health examination records. However, embodiments of the present invention are not limited to these. A detailed description is omitted.

[0167] Next, the comprehensive disease risk prediction device (200) can calculate genetic risk (GS) based on genetic information (GD) (S200), can calculate lifestyle risk (LS) based on lifestyle information (LD) (S300), and can calculate screening risk (MS) based on screening information (MD) (S400).

[0168] For example, the comprehensive disease risk prediction device (200) can calculate genetic risk (GS) by inputting genetic information (GD) into a genetic risk calculation model (M_GS), can calculate lifestyle risk (LS) by inputting lifestyle information (LD) into a lifestyle risk calculation model (M_LS), and can calculate screening risk (MS) by inputting screening information (MD) into a screening risk calculation model (M_MS). At this time, the genetic risk calculation model (M_GS), lifestyle risk calculation model (M_LS), and screening risk calculation model (M_MS) can be pre-trained through statistical analysis (e.g., association analysis, Cox regression, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc. to output genetic risk (GS), lifestyle risk (LS), and screening risk (MS) respectively when genetic information (GD), lifestyle information (LD), and screening information (MD) are input.

[0169] Next, the comprehensive disease risk prediction device (200) can calculate the associated risk (RS) (S500).

[0170] For example, the comprehensive disease risk prediction device (200) can determine an associated disease (RD) related to a specific disease, and can calculate an associated risk (RS) by inputting the genetic risk (GS_RD), lifestyle risk (LS_RD), and screening risk (MS_RD) for the determined associated disease (RD) into an associated risk calculation model (M_RS). At this time, the associated risk calculation model (M_RS) can be learned in advance to output an associated risk (RS) based on at least one of the genetic risk (GS_RD), lifestyle risk (LS_RD), and screening risk (MS_RD) for the associated disease (RD).

[0171] Next, the comprehensive disease risk prediction device (200) can calculate the comprehensive disease risk (IRS) based on the genetic risk (GS), lifestyle risk (LS), screening risk (MS), and associated risk (RS) (S600).

[0172] For example, the comprehensive disease risk prediction device (200) can calculate the comprehensive disease risk (IRS) by inputting genetic risk (GS), lifestyle risk (LS), screening risk (MS), and associated risk (RS) into the comprehensive disease risk calculation model (M_IRS), and at this time, the comprehensive disease risk calculation model (M_IRS) can be learned in advance through statistical analysis (e.g., association analysis, Cox regression analysis, Mendelian randomization), artificial intelligence, machine learning, deep learning, etc., so that when the genetic risk (GS), lifestyle risk (LS), screening risk (MS), and associated risk (RS) are input, the model outputs the comprehensive disease risk (IRS).

[0173] Next, the comprehensive disease risk prediction device (200) can output a comprehensive disease risk (IRS) (S700).

[0174] For example, the output module (240) can output the comprehensive disease risk score (IRS) in the form of a probability value as output data (OD). In other words, the output module (240) can provide the absolute score, which is the comprehensive disease risk score (IRS) itself in the form of a probability value provided from the prediction module (220), as output data (OD) to the user terminal (102), etc.

[0175] As another example, the output module (240) may post-process the comprehensive disease risk (IRS) in the form of a probability value to convert it into a ranking compared to a comparison group, and output the converted data as output data (OD). In other words, the output module (240) may compare the comprehensive disease risk (IRS) in the form of a probability value provided from the prediction module (220) with similar users in the comparison group, thereby calculating the risk ranking in the comparison group, and may provide the calculated ranking or the relative score based on the comparison with the comparison group as output data (OD) to the user terminal (102), etc.

[0176]

[0177] FIG. 7 is a diagram illustrating a hardware implementation of a comprehensive disease risk prediction device that performs a comprehensive disease risk prediction method according to some embodiments of the present invention.

[0178] Referring to FIGS. 1 and 7, a comprehensive disease risk 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.

[0179] 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.

[0180] The input / output device (1020) may include at least one of a keypad, a keyboard, a touchscreen, and a display device.

[0181] The memory device (1030) can store data and / or programs, etc.

[0182] 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.

[0183] The comprehensive disease risk prediction device (200) according to embodiments of the present invention may be a system formed by connecting multiple electronic devices (1000) 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.

[0184] Additionally, the comprehensive disease risk 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.

[0185] Additionally, the comprehensive disease risk 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).

[0186] 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.

[0187] 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.

[0188] A comprehensive disease risk prediction device (200) communicating through 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.

[0189] 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 genetic information about the user's genes, lifestyle information about lifestyle habits, and medical examination information about medical examination records; and Including a prediction module that predicts the comprehensive disease risk, which is the user's risk related to a predefined disease, based on the genetic information, the lifestyle information, and the examination information, The above prediction module, A first calculation unit that calculates a genetic risk related to the disease based on the genetic information; A second calculation unit that calculates the lifestyle risk related to the disease based on the above lifestyle information, A third calculation unit that calculates the screening risk related to the disease based on the above screening information, A fourth calculation unit that calculates the associated risk related to the disease based on associated diseases that are related to the disease; Including an integrated calculation unit that calculates the comprehensive disease risk based on the genetic risk, the lifestyle risk, the examination risk, and the associated risk. Comprehensive disease risk prediction device.

2. In paragraph 1, The above data collection module, Receiving the genetic information, the lifestyle information and the examination information from an external database including a genetic database linked to the comprehensive disease risk prediction device, a user terminal carried by the user and a medical record database storing the medical examination records. Comprehensive disease risk 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. Comprehensive disease risk prediction device.

4. In paragraph 1, The first output unit calculates the genetic risk using a pre-learned genetic risk calculation model and the genetic information, The second output unit calculates the life risk using a pre-learned life risk calculation model and the life information, The third output unit calculates the screening risk using a pre-learned screening risk calculation model and the screening information, The fourth output unit calculates the associated risk using a pre-learned associated risk calculation model and the associated disease, The above integrated calculation unit calculates the comprehensive disease risk using a pre-learned comprehensive disease risk calculation model, the genetic risk, the lifestyle risk, the screening risk, and the associated risk. Comprehensive disease risk prediction device.

5. In paragraph 4, Further comprising a learning module that learns the genetic risk calculation model, the lifestyle risk calculation model, the screening risk calculation model, the associated risk calculation model, and the comprehensive disease risk calculation model. Comprehensive disease risk prediction device.

6. In paragraph 5, The above learning module, When training the above-mentioned associated risk calculation model, the associated diseases that are related to the above-mentioned disease are determined, The above-mentioned associated risk calculation model is trained to determine the associated risk based on at least one of the genetic risk, the lifestyle risk, and the screening risk for the determined associated disease. Comprehensive disease risk prediction device.

7. In paragraph 6, The above learning module, Among multiple target diseases, diseases that have a positive correlation with the disease exceeding a predetermined value are extracted through statistical analysis, Determining the extracted disease as the related disease Comprehensive disease risk prediction device.

8. In paragraph 6, The above associated risk calculation model is, Any one of the genetic risk, the lifestyle risk and the screening risk for the associated disease is determined as the associated risk for the disease, or any two or three of the genetic risk, the lifestyle risk and the screening risk for the associated disease are determined as the associated risk. Comprehensive disease risk prediction device.

9. In paragraph 1, It further includes an output module that outputs the above comprehensive disease risk in the form of a probability value or converts the probability value into a rank compared to a comparison group and outputs it. Comprehensive disease risk prediction device.

10. In a comprehensive disease risk prediction method performed by a comprehensive disease risk prediction device, A receiving step for receiving genetic information about the user's genes, lifestyle information about lifestyle habits, and medical examination information about medical examination records; and Including a prediction step of predicting the comprehensive disease risk, which is the user's risk related to a predefined disease, based on the genetic information, the lifestyle information, and the examination information, The above prediction step is, A step of calculating the genetic risk related to the disease based on the genetic information; A step of calculating the lifestyle risk related to the disease based on the above lifestyle information, A step of calculating the screening risk related to the disease based on the above screening information, A step of calculating the associated risk related to the disease based on the associated disease that is related to the disease; A step of calculating the comprehensive disease risk based on the genetic risk, the lifestyle risk, the screening risk, and the associated risk. A comprehensive disease risk prediction method.

Images