KR20190099660A - Method for predicting health age - Google Patents

Abstract

Disclosed is a method for predicting figures associated with health. The method comprises the following steps: receiving life expectancy learning data including learning condition information and learning life expectancy information; performing deep learning using the life expectancy learning data and generating a life expectancy prediction model; and receiving the condition information, processing the received condition information with the life expectancy prediction model and outputting a life expectancy prediction value.

Description

How to predict health age {METHOD FOR PREDICTING HEALTH AGE}

The present disclosure relates to artificial intelligence technology, and more particularly, to prediction using artificial intelligence technology.

A lot of research has been conducted in order for the machine to perform different motions according to the situation without human continuous instruction, which led to the development of artificial intelligence. Artificial neural network technology, which mimics neural network among various methods of artificial intelligence, requires a lot of data and computing power to learn in order to realize satisfactory performance. Therefore, artificial neural network technology was considered to be non-industrial due to the high cost of learning compared to the benefits of using artificial neural network technology industrially. However, it is considered that the development of computer performance and optimization of learning methods are made. The cost of use has been lowered, and artificial neural network technology has emerged again. For this reason, attempts have been made to industrially use artificial neural network technology in various industries, and there is a demand for industrial use of artificial neural network technology in healthcare.

Prior art document: Korea Patent Registration KR10-1744775

The present disclosure is conceived based on the background art described above and is intended to provide numerical predictions relating to health.

According to one embodiment of the present disclosure for realizing the above-described problem, a method of predicting a numerical value related to health is disclosed. The method includes receiving life expectancy learning data including learning status information and life expectancy information for learning; Generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And receiving the state information and processing the received state information into the expected life expectancy model to output the expected life expectancy value.

Alternatively, the method may further include calculating at least one of an age prediction value and a health age prediction value by comparing the output life expectancy value with statistical life expectancy information corresponding to the state information.

Alternatively, The learning status information and status information, name, personal ID, year of birth, age, gender, personal information, date of health examination, height, weight, BMI, blood test value, biometric data, family history, drinking status, It may include at least one of exercise, smoking, medical treatment date, medical institution information, medical history, death, death date and disease code.

Alternatively, the method may further include labeling the learning life expectancy information on each of the learning status information of the life expectancy learning data.

Alternatively, labeling the learning life expectancy information on each of the learning status information of the life expectancy learning data may include time related information included in the learning status information when the subject included in the learning status information is a dead person. Labeling the learning state information with the difference between the time-related information of the subject and the life expectancy information; And labeling the learning status information using statistical life expectancy information based on the personal information of the subject as the life expectancy information when the subject included in the learning status information is not the death.

Alternatively, the step of generating a life expectancy prediction model by performing deep learning using the life expectancy learning data may include: inputting the learning state information into an artificial neural network; Deriving an error by comparing the output of the learning state information output from the artificial neural network with the expected life expectancy for learning; And back-propagating the error derived as a result of the comparison to the artificial neural network to update the weight of the artificial neural network.

Alternatively, the step of generating a life expectancy prediction model by performing deep learning using the learning data may include: when the learning epoch for learning the artificial neural network is less than or equal to a predetermined epoch, When the learning rate is set to a predetermined value or more, and the learning epoch for learning the artificial neural network is greater than or equal to the predetermined epoch, the learning rate of the artificial neural network may be set to be less than or equal to the predetermined value.

Alternatively, receiving aging training data including the learning status information, the life expectancy prediction value and the aging training information for learning; Generating a aging training prediction model by performing deep learning using the aging training training data; And receiving the state information and processing the received state information as the aging years prediction model to output the aging years prediction value.

Alternatively, performing deep learning using the aging training data to generate a aging training numerical prediction model related to health may include: inputting the learning state information into an aging training prediction artificial neural network; Deriving an error by comparing the learning state information output from the aging training prediction artificial neural network with the learning aging training information; And back-propagating the error derived as a result of the comparison to the aging-year prediction artificial neural network to update the weight of the artificial neural network.

Alternatively, the method may further include labeling the training aging training information on each of the learning state information of the aging training training data.

Alternatively, the step of labeling the training aging training information on each of the learning status information of the aging training training data, the time-related information included in the learning status information, when the subject included in the learning status information is a dead person Labeling the learning status information with a difference between the death time-related information of the subject as aging years information; Inputting the learning state information into the artificial neural network before updating if the subject included in the learning state information is not a death person; And labeling the learning state information using the output of the life expectancy prediction model related to the learning state information as the aging years information.

Alternatively, the method may include labeling the learning state information using the output of the life expectancy prediction model related to the learning state information as the aging years information.

Alternatively, the learning status information dictionary including at least one of birth year, age, sex, height, weight, BMI, blood test values, biometric data, family history, drinking, exercise, smoking, and disease code The method may further include grouping according to the determined criteria.

Alternatively, the method may further include performing deep learning using grouped life expectancy learning data according to the predetermined criterion to generate the grouped life expectancy prediction model.

Alternatively, the learning status information may be generated by processing the re-learning status information of which the subject is a deceased and the subject is a non-death by the generated life expectancy prediction model to generate the re-learning life expectancy information; Generating re-learning data by labeling the re-learning life expectancy information on each of the re-learning state information; The method may further include updating the generated life expectancy prediction model by performing deep learning using the life expectancy learning data and the re-learning data.

In another embodiment of the present disclosure, an apparatus for predicting a numerical value related to health is disclosed. The apparatus includes a receiving unit for receiving life expectancy learning data including learning state information for learning and life expectancy information for learning; Health-related to receive the learning unit and the state information to generate the life expectancy prediction model by performing deep learning using the life expectancy learning data and to process the received state information as the life expectancy prediction model to output the expected life expectancy value Include predictive models.

In yet another embodiment of the present disclosure, a computer program stored on a computer readable storage medium including encoded instructions is disclosed. The computer program, when executed by one or more processors of a computer system, causes the one or more processors to perform the following steps for predicting a health related figure, the steps: learning status information and learning expectations. Receiving life expectancy learning data including life expectancy information; Generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And receiving the state information and processing the received state information as the expected life expectancy model to output the expected life expectancy value.

The present disclosure can provide numerical predictions related to health.

1 is a block diagram of a numerical prediction apparatus 100 related to health according to an embodiment of the present disclosure.
2 is a block diagram of a neural network according to an embodiment of the present disclosure.
3 is a flowchart of a numerical method related to health according to an embodiment of the present disclosure.
4 is a flowchart of a method of labeling learning life expectancy information on each of the learning state information according to an exemplary embodiment of the present disclosure.
5 is a flowchart of a method for obtaining an aging training prediction value using aging training training data according to an embodiment of the present disclosure.
6 is a flowchart of a method of generating a life expectancy prediction model according to a criterion by grouping the learning state information according to a predetermined criterion.
7 is a flowchart illustrating a method of updating a life expectancy prediction model by receiving deep learning data in the life expectancy model and performing deep learning again.
8 is a block diagram illustrating a means for implementing a method of predicting a number related to health according to an embodiment of the present disclosure.
FIG. 9 is a block diagram illustrating a module for implementing a method of predicting health related numbers according to an embodiment of the present disclosure.
FIG. 10 is a block diagram illustrating logic for implementing a method for predicting a health related figure according to an embodiment of the present disclosure.
FIG. 11 is a block diagram illustrating a circuit for implementing a method of predicting a number related to health according to an embodiment of the present disclosure.
12 is a simplified, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. It is evident, however, that such embodiments may be practiced without these specific details. In other instances, well-known structures and devices are provided in block diagram form in order to facilitate describing the embodiments.

As used herein, the terms “component”, “module”, “system” and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a processor and / or thread of execution, and a component can be localized within one computer or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components may, for example, via a network such as the Internet and other systems via signals with one or more data packets (e.g., data and / or signals from one component interacting with other components in a local system, distributed system). Data transmitted) may be communicated via local and / or remote processes.

In addition, the terms "comprises" and / or "comprising" mean that such features and / or components are present, but exclude the presence or addition of one or more other features, components, and / or groups thereof. It should be understood that it does not. Also, unless otherwise specified or in the context of indicating a singular form, the singular in the specification and claims should generally be interpreted as meaning "one or more."

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure should not be limited to the embodiments presented herein but should be construed in the broadest scope consistent with the principles and novel features presented herein.

1 is a block diagram of a numerical prediction apparatus 100 related to health according to an embodiment of the present disclosure. The numerical prediction apparatus 100 related to health according to an exemplary embodiment of the present disclosure may include a receiver 110, a health related prediction model 120, a labeling unit 130, a learning unit 140, and an operation unit 150. Can be. The block diagram shown in FIG. 1 is a simplified configuration of the numerical prediction apparatus 100 related to health, and the present disclosure is not limited thereto and may include additional components required for driving.

The receiver 110 may receive data for performing a method for predicting health related to health according to an embodiment of the present disclosure from another computing device, a server, or the like. The receiver 110 may receive life expectancy learning data including learning state information and life expectancy information for learning. Learning status information includes name, personal ID, year of birth, age, gender, personal information, date of health checkup, height, weight, BMI, blood count, biometric data, family history, drinking status, exercise status, smoking status , At least one of a medical treatment date, medical institution information, medical history, death status, death date, and disease code. The learning state information may include any information related to the current state of the subject and the current health state for learning the numerical predictive model related to health according to an embodiment of the present disclosure. The life expectancy information for learning may include any information related to the life expectancy of the subject. The life expectancy information for learning is the time interval between the subject's status information (ie, the subject's health examination information) and the subject's death time (that is, when the subject of the learning status information is the deceased). Time interval between creation and subject death). Life expectancy information for learning is information that relates to the life expectancy of the subject statistically determined if the subject is not a deceased (ie, if the subject of the learning status information is a male in his 30s who is not deceased, the survival is statistically predicted until age 80). Life expectancy information is 50 years).

The receiver 110 may receive state information. Status information includes name, personal ID, year of birth, age, gender, personal information, date of health examination, height, weight, BMI, blood count, biometric data, family history, drinking status, exercise status, smoking status, It includes at least one of the date of treatment, the information of the medical institution, the medical history, the death, the date of death and the disease code. The state information may be transmitted to a numerical predictive model related to health according to an embodiment of the present disclosure, and may include any information related to the current state and current state of the subject for outputting the numerical predictive value related to health. Numerical predictive values related to health include life expectancy prediction values and aging prediction values. Life expectancy is an indication of how many years the subject will live. For example, a life expectancy value of 30 indicates that we are expected to live another 30 years. The age of aging indicates how old the body is compared to the actual age of the subject. For example, if the aging prediction value is -1, one-year-old body aging may be less than the actual age, and if the aging prediction value is one, aging may be one year older than the actual age.

The receiver 110 may receive aging training data including life expectancy prediction values and aging training information for learning. The life expectancy prediction value may be a value related to the life expectancy predicted by the life expectancy prediction model generated by an embodiment of the present disclosure. The aging training information for learning may be a difference between the expected life expectancy value for the subject and the statistical life expectancy information. For example, if a 30-year-old male has a life expectancy of 40 years and a statistical life expectancy of 50 years, the subject is judged to be older than his or her actual age because the life expectancy is shorter than expected. Can be. In this case, the age of 30 years male subjects can be 10 years. Conversely, if the expected life expectancy is 60 years and the statistical life expectancy is 50 years, the subject may be judged to be less aging than his or her actual age because the life expectancy is longer than expected. In this case, the age of 30-year male subjects can be -10 years. For example, the receiver 110 may receive an electronic health record (EHR) from a hospital server or a government server, and may also receive an electronic medical record (EMR) from a hospital server. Can be. In addition, the receiver 110 may receive a record of the user's health examination from a user terminal (not shown). In addition, the receiver 110 may receive numerical prediction values related to health from the existing model as new training data. The foregoing descriptions are merely examples and the present disclosure is not limited thereto.

The health-related prediction model 120 may include an artificial neural network that outputs numerical predictive values related to health. Numerical predictive values related to health include life expectancy prediction values and aging prediction values. The health-related prediction model 120 inputs the state information received by the receiver 110 to the artificial neural network and outputs the numerical predictive value related to the health to the user to perform the numerical predictive related to health according to an embodiment of the present disclosure. Can be done. The foregoing descriptions are merely examples and the present disclosure is not limited thereto. The health-related prediction model 120 may include a life expectancy prediction model and an age prediction model according to the artificial neural network learning of the learning unit 140. The health-related prediction model 120 may include an artificial neural network, and output a life expectancy prediction value and an age prediction value.

The health related prediction model 120 may include a life expectancy prediction model and an age prediction model.

The labeling unit 130 may associate the learning data with a label for supervised learning. The labeling unit 130 may label the learning life expectancy information for each learning state information of the life expectancy learning data. The labeling unit 130 may label, for example, the learning life expectancy information of the subject A by relating the learning state information about the subject A.

If the subject included in the learning status information is a deceased person, the labeling unit 130 labels the learning status information using the difference between the time-related information included in the learning status information and the death time-related information of the subject as the life expectancy information. can do. If the subject included in the learning status information is not a deceased person, the labeling unit 130 may label the learning status information using statistical life expectancy information based on personal information of the subject as the life expectancy information. For example, if the subject A is a deceased person, the labeling unit 130 may determine the difference between the time-related information included in the subject A's learning status information (ie, the medical examination date) and the actual death of the subject A (that is, from the dryness examination date). Time to death) can be labeled in subject A's learning status information. The labeling unit 130 may label statistical life expectancy information based on subject B's personal information (for example, life expectancy based on age-specific life expectancy information of the National Statistical Office) in the subject B's learning status information when the subject B is not a deceased person. Can be. For example, if subject B is a male in his 30s and has a statistical life expectancy of 50 years, subject B may be labeled with 50 years of life expectancy. In addition, the labeling unit 130 may label the life expectancy information of each subject in the learning state information of the subject C when the subject C is not a deceased and is a time-limited disease patient with a high probability of death in the future. For example, if subject C is 4 patients with lung cancer in their 50s and the average life expectancy of 4 lung cancers is 5 years, life expectancy of 5 years can be labeled in C learning status information.

The labeling unit 130 may label the learning aging training information on each of the learning state information of the aging training training data. If the subject included in the learning status information is a deceased person, the labeling unit 130 may label the learning status information with the difference between the time-related information included in the learning status information and the death time-related information of the subject as aging training information. can do. The labeling unit 130 inputs the learning status information to the generated life expectancy prediction model when the subject included in the learning status information is not the dead, and outputs the output of the life expectancy prediction model related to the learning status information. The learning status information may be labeled as the aging training information.

The labeling unit 130 includes at least one of the learning state information, such as birth year, age, sex, height, weight, BMI, blood test values, biometric data, family history, drinking, exercise, smoking, and disease codes. Can be grouped according to predetermined criteria. For example, even in the case of learning status information for the same 30-year-old male, statistical life expectancy may be different according to the birth year, income quartile, etc. of the subject. Therefore, the labeling unit 130 may group the training data according to a predetermined criterion to generate a different health related prediction model for each group.

When the subject of the learning status information is a non-death, the labeling unit 130 adds the expected life expectancy value predicted by the generated life expectancy prediction model (ie, the life expectancy information for re-learning) to the learning status information where the subject is a non-death. Can be labeled. That is, in the case of learning status information in which the subject is a non-death, the labeling unit 130 may label the learning status information using statistical life expectancy information, or the expectation predicted using the generated life expectancy prediction model. It is also possible to label life expectancy values. The labeling unit 130 may generate re-learning data by labeling the re-learning life expectancy information on each of the re-learning state information.

The learning unit 140 may generate a life expectancy prediction model by performing deep learning on an artificial neural network of the health related prediction model 120 using life expectancy learning data. The learning unit 140 inputs the learning state information to the artificial neural network of the health-related prediction model 120 and derives an error by comparing the output of the learning state information output from the artificial neural network with the expected life expectancy for learning, and The error derived as a result of the comparison is propagated back to the artificial neural network to update the weight of the artificial neural network so that the health-related prediction model 120 may learn to output the expected life expectancy value. As a result, the learner 140 may generate the life expectancy prediction model. The life expectancy prediction model of the present disclosure may output the life expectancy of the subject by inputting the state information of the subject. In the present disclosure, the artificial neural network may be configured as a recurrent neural network (RNN), or may be configured as a long short term memory (LSTM) in which long-term memory problems of the RNNs are solved.

When the learning epoch for learning the artificial neural network is less than or equal to a predetermined epoch, the learning unit 140 sets a learning rate of the artificial neural network to a predetermined value or more, and learns to learn the artificial neural network. When the epoch is greater than or equal to the predetermined epoch, the learning rate of the artificial neural network may be set to be less than or equal to a predetermined value. For example, the learning unit 140 sets the learning rate of 0.8 in the initial 100,000 epochs to train the artificial neural network to speed up the initial learning speed, thereby validating the artificial neural network model, and 0.2 for epochs of 100,000 or more times. You can fine tune the learning results by setting the learning rate.

The learner 140 may generate an aging training prediction model by performing deep learning on an artificial neural network of the health-related prediction model 120 using the aging training training data. The learning unit 140 may train the health-related prediction model 120 to output the aging years prediction value by using the artificial neural network of the health-related prediction model 120. The learning unit 140 may perform deep learning using the aging training data to train the health-related prediction model 120 to output the aging training prediction data. The learning unit 140 may input the learning state information into the aging-year prediction artificial neural network of the health-related prediction model 120. The learning unit 140 derives an error by comparing the output of the learning state information output from the aging training prediction artificial neural network and the learning aging training information, and reverse propagates the derived error to the aging training prediction artificial neural network to age the training. By updating the weights of the predictive artificial neural network, the health-related prediction model 120 may be trained to output an age prediction value. As a result, the learner 140 may generate an aging training prediction model.

The learner 140 may generate the life expectancy prediction model for each grouped group by performing deep learning using the life expectancy learning data grouped according to a predetermined criterion by the labeling unit 130. That is, even if the subjects have the same current state, the life expectancy may be different due to social influences such as the time of birth and income tier, and thus, the learning unit 140 predicts life expectancy using learning life expectancy grouped according to social factors. By allowing models to be created, we can reflect social factors.

The learning unit 140 may update the life expectancy prediction model generated by performing deep learning using the life expectancy learning data and the re-learning data. The updated life expectancy prediction model may reduce the influence of statistical life expectancy information by using re-learning data labeled using the life expectancy prediction model for the non-death life status information. Accordingly, it is possible to prevent errors that may occur due to statistical life expectancy information that may change due to social factors such as times by updating the life expectancy prediction model.

The calculation unit 150 may receive the life expectancy prediction value, the aging age prediction value, and the state information from the receiver 110 and the life expectancy-related prediction model 120.

The calculation unit 150 may generate a numerical predictive value related to new health from statistical life expectancy information, life expectancy prediction value, and state information of the state information. The numerical predictive value related to the new health may be, for example, the predicted health age. Health age includes a person's physical health age. Numerical predictive values related to new health can be obtained through mathematical calculations according to the mathematical relationship between the existing predictive values and the numerical predictive values related to new health. For example, the health age prediction value may be obtained by adding statistical life expectancy information to the age of the subject included in the status information and subtracting the life expectancy prediction value. In addition, the predicted health age value can be obtained by adding the age of aging to the age of the subject included in the status information.

The calculation unit 150 may calculate at least one of an age prediction value and a health age prediction value by comparing the output life expectancy value and statistical life expectancy information corresponding to the state information. The health age prediction value is the difference between the subject's age and age prediction value included in the status information. For example, if the subject is 30 years old and the aging prediction value is +10, the subject may be 40 years old since the subject is older than his or her age. The aging prediction value can be obtained by subtracting the expected life expectancy value from the statistical life expectancy information.

2 is a block diagram of a neural network according to an embodiment of the present disclosure.

Throughout this specification, neural networks, network functions, neural networks may be used in the same sense. A neural network may consist of a set of interconnected computing units, which may generally be referred to as "nodes." Such "nodes" may be referred to as "neurouns". The neural network comprises at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more "links".

Within a neural network, one or more nodes connected via a link may form a relationship of input node and output node relatively. The concept of an input node and an output node is relative; any node in an output node relationship to one node may be in an input node relationship in relation to another node, and vice versa. As mentioned above, the input node to output node relationship can be created around the link. One or more output nodes can be connected to a single input node via a link, and vice versa.

In an input node and output node relationship connected via one link, the output node may be determined based on data input to the input node. Here, the node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, if one or more input nodes are interconnected by each link to one output node, the output node is set to the values input to the input nodes associated with the output node and to the links corresponding to the respective input nodes. The output node value may be determined based on the weight.

As noted above, a neural network is formed by interconnecting one or more nodes through one or more links to form input and output node relationships within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the relationship between the nodes and the links, and the value of the weight assigned to each of the links. For example, if there are the same number of nodes and links, and there are two neural networks with different weight values between the links, the two neural networks may be recognized as different from each other.

As shown in FIG. 2, a neural network may be configured, including one or more nodes. Some of the nodes that make up the neural network may construct one layer based on distances from the original input node, for example, a set of nodes with a distance n from the original input node, You can configure n layers. The distance from the original input node may be defined by the minimum number of links that must pass to reach the node from the original input node. However, the definition of such a layer is arbitrary for explanation, and the order of the layer in the neural network may be defined in a manner different from that described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes into which data is directly input without going through a link in relation to other nodes of the neural network. Alternatively, in a neural network network, in a relationship between nodes based on a link, it may mean nodes having no other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes of the nodes in the neural network. Also, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. 2, the output node is omitted. The neural network according to an embodiment of the present disclosure may be more than the nodes of the hidden layer closer to the output layer than the node of the input layer, and may be a neural network in which the number of nodes decreases as the node progresses from the input layer to the hidden layer.

In an embodiment of the present disclosure, the neural network may include a multilayer perceptron (MLP), a recurrent neural network (RNN), a convolutional neural network (CNN), and the like, to enable processing of data. In addition, in an embodiment of the present disclosure, the neural network of the present disclosure may include a long short-term memory (LSTM) to prevent performance degradation caused by a long range dependency vanishing gradient that may occur as the length of an event increases. It may include. In addition, in an embodiment of the present disclosure, as an optimization technique of the artificial neural network method, stochastic gradient descent (SGD), momentum (Momentum), Adam, AdaGrad, RMSprop, or the like may be used. In addition, if training data D can be learned only once, parameters that minimize the error function can be obtained through repeated epochs several times, and it can be determined whether to complete the training step after checking whether sufficient optimization has been made. have.

Unlike general feedforward neural network, RNN can output hidden layer's input again. The RNN is a neural network that has memory capability by having a feedback structure and calculating the current input data and the data input in the past at the same time. Thus, the RNN can be trained to interpret the current data according to the meaning of the previous data in the data. One of the RNNs, LSTM, is also called a long short term memory network and can learn long-term dependencies. In one embodiment of the present disclosure, the neural network may include any neural network capable of processing data such as a depth gated RNN, a clockwork RNN, as well as LSTM, one of the RNNs. have.

The neural network 200 of FIG. 2 may include one or more hidden layers. The hidden node of the hidden layer can take as input the output of the previous layer and the output of the surrounding hidden nodes. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes of the input layer may be determined based on the number of data fields of the input data, and may be the same as or different from the number of hidden nodes. The input data input to the input layer may be calculated by a hidden node of the hidden layer and may be output by a fully connected layer (FCL) which is an output layer.

3 is a flowchart of a numerical method related to health according to an embodiment of the present disclosure.

The numerical prediction apparatus related to health may receive life expectancy learning data (310). The life expectancy learning data may include learning status information and life expectancy information for learning. Learning status information includes name, personal ID, year of birth, age, gender, personal information, date of health checkup, height, weight, BMI, blood count, biometric data, family history, drinking status, exercise status, smoking status , At least one of a medical treatment date, medical institution information, medical history, death status, death date, and disease code. The learning state information may include any information related to the current state of the subject and the current health state for learning the numerical predictive model related to health according to an embodiment of the present disclosure. The life expectancy information for learning may include any information related to the life expectancy of the subject. The life expectancy information for learning is the time interval between the subject's status information (ie, the subject's health examination information) and the subject's death time (that is, when the subject of the learning status information is the deceased). Time interval between creation and subject death). Life expectancy information for learning is information that relates to the life expectancy of the subject statistically determined if the subject is not a deceased (ie, if the subject of the learning status information is a male in his 30s who is not deceased, the survival is statistically predicted until age 80). Life expectancy information is 50 years).

The numerical prediction apparatus 100 related to health may generate a life expectancy prediction model by performing deep learning using life expectancy learning data (320). The numerical prediction apparatus 100 related to health may include an artificial neural network that outputs life expectancy prediction values. The numerical prediction apparatus related to health inputs the learning state information included in the life expectancy learning data into an artificial neural network of the numerical prediction apparatus related to health, and outputs the learning state information output from the artificial neural network. The life expectancy prediction model may be trained to output the life expectancy by comparing the learning life expectancy with the learning life expectancy to derive an error, and back propagating the error derived as a result of the comparison to the artificial neural network. As a result, the numerical prediction apparatus 100 related to health may generate a life expectancy prediction model. In the present disclosure, the artificial neural network may be configured as a recurrent neural network (RNN), or may be configured as a long short term memory (LSTM) in which long-term memory problems of the RNNs are solved.

The numerical prediction apparatus related to health may output the life expectancy prediction value after receiving the state information in the life expectancy prediction model (330). The numerical prediction apparatus 100 related to health may receive state information. Status information includes name, personal ID, year of birth, age, gender, personal information, date of health examination, height, weight, BMI, blood count, biometric data, family history, drinking status, exercise status, smoking status, It includes at least one of the date of treatment, the information of the medical institution, the medical history, the death, the date of death and the disease code. The state information may be transmitted to the numerical prediction model related to health according to an embodiment of the present disclosure and may include any information related to the current state and the current state of health of the subject for outputting the expected life expectancy value. The apparatus 100 for predicting health may perform life expectancy prediction according to an embodiment of the present disclosure by inputting the received state information to the life expectancy prediction model and outputting the output life expectancy prediction value to the user.

4 is a flowchart of a method of labeling learning life expectancy information on each of the learning state information according to an exemplary embodiment of the present disclosure.

The apparatus 100 for predicting health may label according to whether the learning state information is a dead person (410).

When the state information for learning is a deceased person, the numerical prediction apparatus related to health may label the learning state information with the difference between the time-related information included in the learning state information and the death time-related information of the subject as the life expectancy information. There is (421). When the subject A is a deceased person, the numerical predictive apparatus related to health may determine a difference between the time-related information (ie, the health examination date) included in the subject A's learning status information and the actual death of the subject A (that is, from the dry examination date). Time to death) can be labeled in subject A's learning status information. For example, if subject A is a 50-year-old man who died at age 54, four years of life expectancy can be labeled in subject A's learning status information.

If the learning state information related to health is non-death, the numerical prediction apparatus 100 may label the learning state information based on statistical life expectancy information based on personal information of the subject as the life expectancy information (422). Statistical life expectancy information may be the above-described year, sex, age-specific life table, life-signal-free life table, and average life expectancy by specific disease. If the subject B is not a deceased, the numerical predictive apparatus related to health receives statistical life expectancy information based on the subject B's personal information (for example, life expectancy based on age-specific life expectancy information of the National Statistical Office). Information can be labeled. For example, if subject B is a male in his 30s and has a statistical life expectancy of 50 years, subject B's life expectancy of 50 years may be labeled in subject B's status information.

5 is a flowchart of a method for obtaining an aging training prediction value using aging training training data according to an embodiment of the present disclosure.

In operation 510, the numerical prediction apparatus related to health may receive aging training data including life expectancy prediction values and state information. The life expectancy prediction value may be a value related to the life expectancy predicted by the life expectancy prediction model generated by an embodiment of the present disclosure. The aging training information for learning may be a difference between the expected life expectancy value for the subject and the statistical life expectancy information. For example, if a 30-year-old male has a life expectancy of 40 years and a statistical life expectancy of 50 years, the subject is judged to be older than his or her actual age because the life expectancy is shorter than expected. Can be. In this case, the age of 30 years male subjects can be 10 years. On the contrary, if the expected life expectancy is 60 years and the statistical life expectancy is 50 years, the subject may have a longer life expectancy than the expected life expectancy, and thus may be judged to be less aging than his or her actual age. In this case, the age of 30-year male subjects can be -10 years.

The numerical prediction apparatus 100 related to health may generate an aging years prediction model after deep learning using the aging years training data (520). The numerical prediction apparatus 100 related to health may input the learning state information into the age-aging prediction artificial neural network of the numerical prediction apparatus 100 related to health. The numerical apparatus 100 related to health derives an error by comparing the output of the learning state information output from the aging prediction artificial neural network and the learning aging training information, and inverses the derived error to the aging prediction artificial neural network. By propagating and updating the weight of the aging prediction prediction artificial neural network, the health-related prediction model 120 may be trained to output aging years. As a result, the numerical prediction apparatus 100 related to health may generate an age prediction model.

The numerical prediction apparatus 100 related to health may output the aging years prediction value after receiving the state information in the aging years prediction model (530). The numerical prediction apparatus 100 related to health may perform numerical prediction related to health according to an embodiment of the present disclosure by inputting the received state information to an aging years prediction model and outputting the output aging years prediction value to a user. have.

6 is a flowchart of a method of generating a life expectancy prediction model according to a criterion by grouping the learning state information according to a predetermined criterion.

The numerical prediction apparatus 100 related to health may group learning state information according to a predetermined criterion (610). The predetermined criteria may include at least one of birth year, age, sex, height, weight, BMI, blood test values, biometric data, family history, drinking alcohol, exercise, smoking, and disease code.

In operation 620, the numerical prediction apparatus 100 related to health may generate deep learning prediction models for each grouped group by performing deep learning using the life expectancy learning data grouped according to a predetermined criterion. For example, the statistical life expectancy at birth in the 1990s at age 30 and the statistical life expectancy at birth in the 1970s at age 30 may be different due to social factors, such as changing times. Therefore, the numerical prediction apparatus 100 related to health groups life expectancy learning data based on a predetermined social factor, and then performs learning using the grouped life expectancy learning data to generate a life expectancy prediction model for each group. Can be. By generating a predictive model using grouped life expectancy learning data, the numerical prediction apparatus 100 related to health of the present disclosure may provide life expectancy prediction values reflecting social factors.

7 is a flowchart illustrating a method of updating a life expectancy prediction model by receiving deep learning data in the life expectancy model and performing deep learning again.

The numerical prediction apparatus 100 related to health may receive life expectancy learning data in which the subject is a dead person (710).

The numerical prediction apparatus 100 related to health may generate a life expectancy prediction model after deep learning using 720 life expectancy learning data in which the subject is a dead person (720). The numerical prediction apparatus 100 related to health inputs learning state information for which the subject is a dead person to an artificial neural network of the health related prediction model 120 and outputs the learning state information for which the subject output from the artificial neural network is a death person. The learning life expectancy may be derived by comparing the learning life expectancy, and the error resulting from the comparison may be propagated back to the artificial neural network to update the weight of the artificial neural network to output the life expectancy. As a result, the numerical prediction apparatus 100 related to health may generate a life expectancy prediction model.

The numerical prediction apparatus 100 related to health may generate information about life expectancy for re-learning by receiving state information for re-learning for which the target is non-deceased in the life expectancy prediction model (730). Re-learning status information includes name, personal ID, year of birth, age, gender, personal information, date of health checkup, height, weight, BMI, blood count, biometric data, family history, drinking status, exercise status, smoking Whether or not, the date of treatment, medical institution information, medical history, death, death date and disease code. The re-learning state information may include any information related to the current state of the subject and the current state of health for learning the numerical predictive model related to health according to an embodiment of the present disclosure. The life expectancy information for re-learning may be a value inputted from the numerical prediction device 100 related to health by inputting the re-learning state information to the numerical predicting device 100 related to health. That is, the numerical predictor 100 related to health according to an exemplary embodiment of the present disclosure may receive state information of the non-death, and generate life expectancy information of the non-death using the learned health-related prediction model 120. .

The apparatus 100 for predicting health may generate re-learning data by labeling the re-learning life expectancy information on each of the re-learning state information. The numerical prediction apparatus 100 related to health may label the predicted life expectancy value generated by receiving the re-learning state information (ie, the re-learning life expectancy information) on each of the re-learning state information. That is, the numerical prediction apparatus related to health may label the predicted life expectancy value using the generated life expectancy prediction model on each of the re-learning state information.

The numerical prediction apparatus 100 related to health may update the life expectancy prediction model by performing deep learning using the life expectancy learning data and the re-learning data (750). The numerical prediction apparatus 100 related to the health inputs the state information for learning and the re-learning state information to the artificial neural network of the health-related prediction model 120, and outputs and regenerates the learning state information output from the artificial neural network. Compute the error by comparing the learning status information with the learning life expectancy for learning and the life expectancy for re-learning, and back propagates the error derived as a result of the comparison to the artificial neural network to update the weight of the artificial neural network to learn to output life expectancy. Can be. As a result, the numerical prediction apparatus 100 related to health may update the life expectancy prediction model. According to an embodiment of the present disclosure, the numerical prediction apparatus related to health generates a life expectancy prediction model using death data, and extracts a life expectancy prediction value from non-death death data to perform relearning. This can lower the dependency on statistical life expectancy information that can change over time, thereby providing consistent results.

8 is a block diagram illustrating a means for implementing a method of predicting a number related to health according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method of predicting a health-related numerical value includes means for receiving life expectancy learning data including learning state information and life expectancy information for learning 1210; Means for performing deep learning using the life expectancy learning data to generate a life expectancy prediction model 1220; And means 1230 for receiving the state information and processing the received state information as the expected life expectancy model to output the expected life expectancy value.

In an alternative embodiment, the method may further include means for comparing at least one of the output life expectancy value and statistical life expectancy information corresponding to the state information to calculate at least one of an age prediction value and a health age prediction value.

In an alternative embodiment the learning status information and status information, name, personal ID, year of birth, age, gender, personal information, date of health examination received, height, weight, BMI, blood test values, biometric data, It may include at least one of family history, drinking, exercise, smoking, medical treatment date, medical institution information, medical history, death, death date and disease code.

In an alternative embodiment, the method may further include means for labeling the learning life expectancy information on each of the learning status information of the life expectancy learning data.

In an alternative embodiment, the means for labeling the learning life expectancy information on each of the learning status information of the life expectancy learning data is related to the time included in the learning status information when the subject included in the learning status information is a deceased person. Means for labeling the learning status information with the difference between the information and the time of death of the subject as the life expectancy information; And when the subject included in the learning status information is not the deceased person, labeling the learning status information using statistical life expectancy information based on personal information of the subject as the life expectancy information.

In an alternative embodiment, the means for performing the deep learning using the life expectancy learning data to generate the life expectancy prediction model comprises: means for inputting the learning state information into an artificial neural network; Means for deriving an error by comparing the output of the learning state information output from the artificial neural network with the learning life expectancy; And means for updating the weight of the artificial neural network by back propagating the error derived from the comparison to the artificial neural network.

In an alternative embodiment, the means for generating a life expectancy prediction model by performing deep learning using the training data may include learning learning of the artificial neural network when the learning epoch for learning the artificial neural network is less than or equal to a predetermined epoch. rate) is set to a predetermined value or more, and when the learning epoch for learning the artificial neural network is greater than or equal to the predetermined epoch, the learning rate of the artificial neural network may be set to be less than or equal to the predetermined value.

Means for receiving aging training training data comprising the learning status information, the expected life expectancy value and training aging training information in an alternative embodiment; Means for performing deep learning using the aging training data to generate an aging training prediction model; And means for receiving the status information and processing the received status information as the aging years prediction model to output an aging years prediction value.

In an alternative embodiment, the means for performing deep learning using the aging training data to generate a aging training numerical predictive model related to health comprises: inputting the learning state information into an aging training prediction artificial neural network; Means for deriving an error by comparing the learning state information output from the aging training prediction artificial neural network with the learning aging training information; And means for updating the weight of the artificial neural network by back propagating the error derived as a result of the comparison to the aging predictive artificial neural network.

In an alternative embodiment, the method may further include means for labeling the learning age training information in each of the learning state information of the aging training training data.

In an alternative embodiment, the means for labeling the learning age training information on each of the learning status information of the aging training learning data is related to the time included in the learning status information when the subject included in the learning status information is a dead person. Means for labeling the learning state information with the difference between the information and the death time related information of the subject as aging years information; Means for inputting the learning status information into the generated life expectancy prediction model when the subject included in the learning status information is not the deceased; And means for labeling the learning state information with the output of the life expectancy prediction model related to the learning state information as the aging years information.

In an alternative embodiment the learning status information includes at least one of birth year, age, sex, height, weight, BMI, blood test values, biometric data, family history, drinking, exercise, smoking, and disease codes The method may further comprise means for grouping according to predetermined criteria.

In an alternative embodiment, the method may further include means for performing deep learning using grouped life expectancy learning data according to the predetermined criterion to generate the grouped life expectancy prediction model.

In an alternative embodiment, the learning status information may comprise means for processing the re-learning status information in which the subject is a deceased and the subject is a non-death, with the generated life expectancy prediction model to generate re-learning life expectancy information; Means for labeling the re-learning life expectancy information in each of the re-learning state information to generate re-learning data; The method may further include means for updating the generated life expectancy prediction model by performing deep learning using the life expectancy learning data and the re-learning data.

FIG. 9 is a block diagram illustrating a module for implementing a method of predicting health related numbers according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method of predicting a numerical value related to health includes a module 1310 for receiving life expectancy learning data including learning state information and life expectancy information for learning; A module 1320 for generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And a module 1330 for receiving the state information and processing the received state information as the expected life expectancy model to output the expected life expectancy value.

FIG. 10 is a block diagram illustrating logic for implementing a method for predicting a health related figure according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method of predicting a numerical value related to health includes logic 1410 for receiving life expectancy learning data including learning state information and life expectancy information for learning; Logic 1420 for generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And logic 1430 for receiving the state information and processing the received state information as the expected life expectancy model to output the expected life expectancy value.

FIG. 11 is a block diagram illustrating a circuit for implementing a method of predicting a number related to health according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method of predicting a numerical value related to health may include a circuit 1510 for receiving life expectancy learning data including learning state information and life expectancy information for learning; A circuit 1520 for generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And a circuit 1530 for receiving the state information and processing the received state information as the expected life expectancy model to output the expected life expectancy value.

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be electronic hardware, computer software, or a combination of both. It should be appreciated that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

12 is a simplified, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above generally with respect to computer executable instructions that may be executed on one or more computers, those skilled in the art will appreciate that the present disclosure may be implemented in combination with other program modules and / or as a combination of hardware and software. will be.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present disclosure may include uniprocessor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like (each of which And other computer system configurations, including one or more associated devices, which may operate in conjunction with one or more associated devices.

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

Computers typically include a variety of computer readable media. Any medium that can be accessed by a computer can be a computer readable medium, which can be volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Removable media. By way of example, and not limitation, computer readable media may comprise computer readable storage media and computer readable transmission media. Computer-readable storage media are volatile and nonvolatile media, temporary and non-transitory media, removable and non-removable implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Media. Computer storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROMs, digital video disks or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, Or any other medium that can be accessed by a computer and used to store desired information.

Computer-readable transmission media typically embody computer readable instructions, data structures, program modules or other data on modulated data signals, such as carrier waves or other transport mechanisms, and the like. Includes all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed to encode information in the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, or other wireless media. Combinations of any of the above should also be included within the scope of computer readable transmission media.

An example environment 1600 is illustrated that implements various aspects of the present disclosure, including a computer 1602, which includes a processing unit 1604, a system memory 1606, and a system bus 1608. do. System bus 1608 connects system components, including but not limited to system memory 1606, to processing unit 1604. Processing unit 1604 may be any of a variety of commercial processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1604.

System bus 1608 may be any of several types of bus structures that may be further interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1606 includes read only memory (ROM) 1610 and random access memory (RAM) 1612. The basic input / output system (BIOS) is stored in nonvolatile memory 1610, such as ROM, EPROM, EEPROM, etc., which is a basic BIOS that assists in transferring information between components in the computer 1602, such as during startup. Contains routines. RAM 1612 may also include fast RAM, such as static RAM, for caching data.

Computer 1602 also includes an internal hard disk drive (HDD) 1614 (eg, EIDE, SATA) —this internal hard disk drive 1614 can also be configured for external use within a suitable chassis (not shown). Yes, magnetic floppy disk drive (FDD) 1616 (eg, for reading from or writing to removable diskette 1618), and optical disc drive 1620 (eg, CD-ROM Disc 1622 for reading from or writing to or from other high capacity optical media, such as a DVD). The hard disk drive 1614, the magnetic disk drive 1616, and the optical disk drive 1620 are respectively connected to the system bus 1608 by the hard disk drive interface 1624, the magnetic disk drive interface 1626, and the optical drive interface 1628. ) Can be connected. The interface 1624 for external drive implementation includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide nonvolatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 1602, drives and media correspond to storing any data in a suitable digital format. Although the above description of computer readable media refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will appreciate zip drives, magnetic cassettes, flash memory cards, cartridges, and the like. Other types of media readable by the computer, etc. may also be used in the exemplary operating environment and it will be appreciated that any such media may include computer executable instructions for performing the methods of the present disclosure.

Multiple program modules may be stored in the drive and RAM 1612, including operating system 1630, one or more application programs 1632, other program modules 1634, and program data 1636. All or a portion of the operating system, applications, modules and / or data may also be cached in RAM 1612. It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1602 through one or more wired / wireless input devices, such as a keyboard 1638 and a mouse 1640. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. While these and other input devices are often connected to the processing unit 1604 through an input device interface 1644 that is connected to the system bus 1608, the parallel port, IEEE 1394 serial port, game port, USB port, IR interface, Etc. can be connected by other interfaces.

A monitor 1644 or other type of display device is also connected to the system bus 1608 via an interface such as a video adapter 1646. In addition to the monitor 1644, the computer generally includes other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 1602 can operate in a networked environment using logical connections to one or more remote computers, such as remote computer (s) 1648, via wired and / or wireless communications. Remote computer (s) 1648 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and generally may be coupled to computer 1602. Although many or all of the components described above are included, for simplicity, only memory storage 1650 is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) 1652 and / or a larger network, such as a telecommunications network (WAN) 1654. Such LAN and WAN networking environments are commonplace in offices and businesses, facilitating enterprise-wide computer networks such as intranets, all of which may be connected to worldwide computer networks, such as the Internet.

When used in a LAN networking environment, the computer 1602 is connected to the local network 1652 through a wired and / or wireless communication network interface or adapter 1656. Adapter 1656 may facilitate wired or wireless communication to LAN 1652, which also includes a wireless access point installed therein for communicating with wireless adapter 1656. When used in a WAN networking environment, the computer 1602 may include a modem 1658, to establish communications over the WAN 1654, such as to connect to a communications computing device on the WAN 1654, or via the Internet. Other means. The modem 1658, which may be an internal or external and wired or wireless device, is connected to the system bus 1608 via the serial port interface 1644. In a networked environment, program modules or portions thereof described with respect to computer 1602 may be stored in remote memory / storage device 1650. It will be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers can be used.

Computer 1602 is associated with any wireless device or entity disposed and operating in wireless communication, such as a printer, scanner, desktop and / or portable computer, portable data assistant, communication satellite, wireless detectable tag. Communicate with any equipment or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technology. Thus, the communication can be a predefined structure as in a conventional network or simply an ad hoc communication between at least two devices.

Wireless Fidelity (Wi-Fi) allows you to connect to the Internet without wires. Wi-Fi is a wireless technology such as a cell phone that allows such a device, for example, a computer, to transmit and receive data indoors and outdoors, ie anywhere within the coverage area of a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, high-speed wireless connections. Wi-Fi may be used to connect computers to each other, to the Internet, and to a wired network (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). .

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

One of ordinary skill in the art of the disclosure will appreciate that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, It will be appreciated that for purposes of the present invention, various forms of program or design code, or combinations thereof, may be implemented. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. One skilled in the art of the present disclosure may implement the described functionality in various ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The various embodiments presented herein may be embodied in a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term “article of manufacture” includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flashes. Memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited to these. In addition, various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. Based upon design priorities, it is understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure should not be limited to the embodiments presented herein but should be construed in the broadest scope consistent with the principles and novel features presented herein.

Claims (16)

In the method of predicting a figure related to health,
Receiving life expectancy learning data including learning state information and life expectancy information for learning;
Generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And
Receiving state information and processing the received state information as the life expectancy prediction model to output a life expectancy prediction value;
Including,
How to predict health related numbers
The method of claim 1,
Calculating at least one of an aging age prediction value and a health age prediction value by comparing the output life expectancy value and statistical life expectancy information corresponding to the state information;
Further comprising,
How to predict health related numbers
The method of claim 1,
The learning state information and state information,
Name, personal ID, year of birth, age, gender, personal information, date of medical examination, height, weight, BMI, blood test value, biometric data, family history, drinking status, exercise status, smoking status, medical date, Including at least one of medical institution information, medical history, death status, death date and disease code,
How to predict health related numbers
The method of claim 1,
Labeling the learning life expectancy information on each of the learning status information of the life expectancy learning data;
Further comprising,
How to predict health related numbers
The method of claim 4, wherein
Labeling the learning life expectancy information on each of the learning status information of the life expectancy learning data,
If the subject included in the learning status information is a dead person, labeling the learning status information with the difference between the time-related information included in the learning status information and the death time-related information of the subject as the life expectancy information; And
If the subject included in the learning status information is not a deceased person, labeling the learning status information with statistical life expectancy information based on personal information of the subject as the life expectancy information;
Including,
How to predict health related numbers
The method of claim 1
Generating the life expectancy prediction model by performing deep learning using the life expectancy learning data,
Inputting the learning state information into an artificial neural network;
Deriving an error by comparing the output of the learning state information output from the artificial neural network with the expected life expectancy for learning; And
Updating the weight of the artificial neural network by back-propagating the error derived as a result of the comparison to the artificial neural network;
Including,
How to predict health related numbers
The method of claim 1,
Generating the life expectancy prediction model by performing deep learning using the learning data,
If the learning epoch for learning the artificial neural network is less than or equal to a predetermined epoch, the learning rate of the artificial neural network is set to a predetermined value or more, and the learning epoch for learning the artificial neural network is greater than or equal to a predetermined epoch. In this case, to set the learning rate of the artificial neural network to a predetermined value or less,
How to predict health related numbers
The method of claim 1,
Receiving aging training training data including the learning status information, the life expectancy prediction value, and training aging training information;
Generating a aging training prediction model by performing deep learning using the aging training training data; And
Receiving the state information and processing the received state information as the aging years prediction model to output an aging years prediction value;
Further comprising,
How to predict health related numbers
The method of claim 8
By performing deep learning using the aging training data to generate a aging training numerical prediction model related to health,
Inputting the learning state information into an aging training prediction artificial neural network;
Deriving an error by comparing the learning state information output from the aging training prediction artificial neural network with the learning aging training information; And
Updating the weight of the artificial neural network by back propagating the error derived as a result of the comparison to the aging prediction artificial neural network;
Including,
How to predict health related numbers
The method of claim 9,
Labeling the learning aging training information on each of the learning state information of the aging training training data;
Further comprising,
How to predict health related numbers
The method of claim 10,
Labeling the learning aging training information on each of the learning state information of the aging training training data,
If the subject included in the learning status information is a deceased person, labeling the learning status information with the difference between the time-related information included in the learning status information and the death time-related information of the subject as aging training information;
Inputting the learning status information into the generated life expectancy prediction model when the subject included in the learning status information is not the deceased; And
Labeling the learning status information with the output of the life expectancy prediction model related to the learning status information as the aging years information;
Including,
How to predict health related numbers
The method of claim 1,
According to a predetermined criterion including at least one of the year of birth, age, sex, height, weight, BMI, blood test values, biometric data, family history, drinking alcohol, exercise, smoking, and disease code. Grouping;
Further comprising,
How to predict health related numbers
The method of claim 12,
Generating deep life expectancy prediction models for each grouped group by performing deep learning using the life expectancy learning data grouped according to the predetermined criterion;
Further comprising,
How to predict health related numbers
The method of claim 1,
The learning status information indicates that the subject is a deceased person, and
Generating life expectancy information for re-learning by processing the re-learning state information for which the subject is non-death with the generated life expectancy prediction model;
Generating re-learning data by labeling the re-learning life expectancy information on each of the re-learning state information;
Updating the generated life expectancy prediction model by performing deep learning using the life expectancy learning data and the re-learning data;
Further comprising,
How to predict health related figures.
As a device for predicting health-related numbers,
A receiver for receiving life expectancy learning data including learning state information and life expectancy information for learning;
A learning unit generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And
A health-related prediction model that receives state information and processes the received state information as the life expectancy prediction model to output a life expectancy prediction value;
Including,
Device for predicting figures related to health.
A computer program stored in a computer readable storage medium containing encoded instructions, wherein the computer program, when executed by one or more processors of a computer system, causes the one or more processors to predict a health related figure. To perform the steps of:
Receiving life expectancy learning data including learning state information and life expectancy information for learning;
Generating a life expectancy prediction model by performing deep learning using the life expectancy learning data; And
Receiving state information and processing the received state information as the life expectancy prediction model to output a life expectancy prediction value;
Including,
Computer program stored on a computer readable storage medium.

Images