Data estimation device, data estimation method, and data estimation program

Abstract

To provide a data estimation device capable of easily estimating data related to health in the future.SOLUTION: The data estimation device includes an acquisition unit 11, an estimation unit 13, and an output unit 15. The acquisition unit 11 acquires health-related data for each of persons in different age groups. The inference unit 13 infers a transition destination of health-related data of a target person in a case where the age of the target person in a first age group becomes a second age group. The output unit 15 outputs health-related data for a case in which the age of the target person has increased, on the basis of the estimation result of the transition destination. With such a configuration, the data estimation device 10 can support decision making related to a future health state.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a data estimation device and the like. [Background technology]

[0002] The future health condition of a target person can be important in estimating assets necessary for receiving medical treatment, etc. in the future, and in determining assets available for investment excluding assets necessary for receiving medical treatment, etc. The future health condition is estimated, for example, based on the target person's current health condition. For example, the future health condition is estimated using a machine learning model that predicts the future health condition from the target person's health condition.

[0003] The predictive model construction device in Patent Document 1 clusters health status data for multiple years for each of multiple subjects into a collection of data by subject and age group. The predictive model construction device in Patent Document 1 generates a predictive model that predicts changes in health status based on transitions between clusters of data for the same subject. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-173728 Summary of the Invention [Problem to be solved by the invention]

[0005] The technology described in Patent Document 1 requires data on the health condition of the same person over multiple years, which may make it difficult to estimate the future health condition.

[0006] In order to solve the above-mentioned problems, the present disclosure aims to provide a data estimation device and the like that can easily estimate future health-related data. [Means for solving the problem]

[0007] In order to solve the above problems, the data estimation device disclosed herein includes an acquisition means for acquiring health data for each person in different age groups, an estimation means for estimating the transition destination of the health data of a target person when the target person's age changes from a first age group to a second age group, and an output means for outputting health data when the target person's age increases based on the estimation result of the transition destination.

[0008] The data estimation method disclosed herein acquires health data for each person in different age groups, estimates the transition destination of the target person's health data when the target person's age changes from a first age group to a second age group, and outputs health data when the target person's age increases based on the estimated transition destination.

[0009] The data estimation program disclosed herein causes a computer to perform the following processes: a process of acquiring health data for each person in different age groups; a process of estimating the transition destination of the health data of a target person when the target person's age changes from a first age group to a second age group; and a process of outputting health data when the target person's age increases based on the estimated transition destination. [Effects of the Invention]

[0010] According to the present disclosure, future health-related data can be easily estimated. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a data estimation system according to the present disclosure. [Figure 2] FIG. 1 is a diagram illustrating an example of data transition in the present disclosure. [Figure 3] FIG. 1 is a diagram illustrating an example of a configuration of a data estimation device according to the present disclosure. [Figure 4]FIG. 10 is a diagram illustrating an example of a display screen for the estimation results of health-related data in the present disclosure. [Figure 5] FIG. 10 is a diagram illustrating an example of a display screen for the estimation results of health-related data in the present disclosure. [Figure 6] FIG. 10 is a diagram illustrating an example of a display screen for the estimation results of health-related data in the present disclosure. [Figure 7] FIG. 10 is a diagram illustrating an example of an operation flow of a data estimation device according to the present disclosure. [Figure 8] FIG. 1 is a diagram illustrating an example of a configuration of a data estimation system according to the present disclosure. [Figure 9] FIG. 1 is a diagram illustrating an example of a configuration of a data estimation device according to the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of a display screen for the estimated results of changes in health-related data in the present disclosure. [Figure 11] FIG. 10 is a diagram illustrating an example of a display screen for the estimation results of health-related data in the present disclosure. [Figure 12] FIG. 10 is a diagram illustrating an example of a display screen for the estimated medical expenses according to the present disclosure. [Figure 13] FIG. 10 is a diagram illustrating an example of an operation flow of a data estimation device according to the present disclosure. [Figure 14] FIG. 10 is a diagram illustrating an example of an operation flow of a data estimation device according to the present disclosure. [Figure 15] FIG. 1 is a diagram illustrating an example of a hardware configuration of a data estimation device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] (First embodiment) A first embodiment of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is a diagram illustrating an example of the configuration of a data estimation system. The data estimation system includes a data estimation device 10, a terminal device 20, and a data management device 30. The data estimation device 10 is connected to the terminal device 20, for example, via a network. The data estimation device 10 is connected to the data management device 30, for example, via a network. There may be a plurality of terminal devices 20 and a plurality of data management devices 30. The number of terminal devices 20 and the number of data management devices 30 may be set as appropriate.

[0013] The data estimation system, for example, estimates health data of a target person as they age. The health data is, for example, the results of a health checkup. The data estimation system, for example, estimates future health data of a target person based on the health data of the target person. For example, if the target person is currently 50 years old, the data estimation system estimates health data of the target person when they are 70 years old based on the health data of the target person when they were 50 years old.

[0014] The target person is a person for whom future health data is to be estimated. The target person is, for example, a person for whom future health data is needed in making plans for the future. Plans for the future are, for example, plans related to asset management, housing, or insurance. Plans for the future may also be plans related to exercise to maintain a healthy state. Plans for the future are not limited to the above. Furthermore, health data is, for example, data indicating a health condition. Specific examples of health data will be described later.

[0015] The data estimation system, for example, uses health data for each of a plurality of age groups to estimate health data for a target person as the target person ages. For example, assume that a first age group and a second age group higher than the first age group are set. In this case, the data estimation system estimates health data for a target person as the target person ages from the first age group to the second age group, based on health data for each person belonging to the first age group and health data for each person belonging to the second age group.

[0016] When the health-related data is the results of a health checkup, the data estimation system, for example, uses the results of health checkups conducted by age group in the current fiscal year to estimate the results of the health checkup if the age of the person who underwent the health checkup increases. For example, the data estimation system uses the results of health checkups for people in a first age group and people in a second age group to estimate health-related data for a target person belonging to the first age group if the target person's age increases to the second age group. The target person is a person whose future health-related data is to be estimated. The data estimation system, for example, uses health-related data for people from different age groups to estimate the target person's future health-related data. Therefore, the data estimation system, for example, estimates the target person's future health-related data without requiring long-term health-related data for the same person.

[0017] Furthermore, the results of the target person's health checkup may be the results of a health checkup conducted in a year different from the year in which the health checkup results for the age group were obtained. Furthermore, the results of the health checkup for each age group may be the results of health checkups conducted in multiple years. In this case, when the results of the health checkup for the same person are included in the results of health checkups for different years, the data estimation system, for example, performs estimation by regarding each of the results of the health checkup for the same person included in the results of health checkups for different years as the results of health checkups for different people.

[0018] The data estimation system may classify health-related data for each age group into data groups and estimate the transition of the health-related data as the target person's age increases as a transition between data groups. For example, when a person whose health checkup results are classified into the first data group in a first age group moves to a second age group, the data estimation system estimates to which data group in the second age group the health checkup results classified into the first data group belong. Then, for example, based on the results of the target person's health checkup, the data estimation system estimates the results of the health checkup when the target person's age increases from the first age group to the second age group.

[0019] FIG. 2 is a diagram illustrating an example of how health-related data, which are the results of a medical checkup, transition as age increases. In the example of FIG. 2, for example, 55 years old corresponds to the first age group, and 75 years old corresponds to the second age group. The example of FIG. 2 shows that the results of a medical checkup for a person who belongs to data group A1 at age 55 transition to data group C1 via the results of a medical checkup at age 65 when the person's age increases to 75. Also, in the example of FIG. 2, the results of a medical checkup for a person who belongs to data group A1 at age 55 transition to data group B1 via the results of a medical checkup at age 65. That is, in the example of FIG. 2, between different age groups, data from data group A1 transitions to data group C1 via data group B1. In this case, when the results of a medical checkup for a target person at age 55 are included in data group A1, the data estimation system estimates that the results of a medical checkup the target person will receive at age 75 will fall within the range of data group C1.

[0020] Here, an example of the configuration of the data estimation device 10 will be described. Fig. 3 is a diagram showing an example of the configuration of the data estimation device 10. The data estimation device 10 basically includes an acquisition unit 11, an estimation unit 13, and an output unit 15. The data estimation device 10 further includes, for example, a classification unit 12, a prediction unit 14, and a storage unit 16.

[0021] The acquisition unit 11 acquires health-related data for each person in a different age group. The health-related data may include indices calculated from the health-related data. For example, the acquisition unit 11 acquires the health-related data in a state in which information indicating the age of the person corresponding to each piece of health-related data is associated with each piece of health-related data. The acquisition unit 11 may also acquire the health-related data in a state in which information indicating the attributes of the person corresponding to each piece of health-related data is associated with each piece of health-related data. The attributes are, for example, information indicating a group in which differences in the attributes may cause differences in the trends of the health-related data. For example, a person living in a cold region may have a different trend in the health-related data from a person living in a warm region. In such a case, information indicating the place of residence is used as the attribute. The attributes are, for example, information on one or more items of gender, place of residence, nationality, occupation, medical history, and medical history of family members. The attributes are not limited to the above. The acquisition unit 11 acquires the health-related data for each person in a different age group from, for example, the data management device 30.

[0022] Health-related data is, for example, data indicating a health condition. Health-related data is, for example, data on one or more items of health checkup results, hospital test results, vital signs, whether or not a disease has occurred, the probability of developing a disease, a doctor's findings, motor function, whether or not care is required, and the level of care required. Health checkup results are, for example, data on one or more items of height, weight, eyesight, blood pressure, abdominal circumference, tension, blood test measurements, image diagnostic results, and doctor's interview results measured during the health checkup. Health-related data may also include expenses necessary for maintaining a healthy state or for daily life. Health-related data is not limited to the above.

[0023] When the health-related data is the results of a health checkup, the acquisition unit 11 acquires, for example, the results of the health checkup within a predetermined period as the health-related data. The predetermined period is set, for example, as a period during which a sufficient amount of data can be collected and during which the trend of the data does not change. The trend of the data does not change, for example, when the standards for conducting health checkups do not change and data can be acquired using the same standards. The predetermined period is, for example, within the same fiscal year. The predetermined period may be multiple years. The predetermined period may be one month or multiple months. The predetermined period is not limited to the above.

[0024] Furthermore, when the health-related data is the result of a health check, the acquisition unit 11 may acquire, for example, the results of a health check for a predetermined group as the health-related data. The predetermined group is, for example, a group in which the health status of individuals belonging to the group tends to differ from that of other groups. The predetermined group is, for example, a region, a company, an industry, or an occupation. The predetermined group is not limited to the above. For example, suppose there is a difference in the tendency for individuals engaged in the fishing industry to develop a disease compared to individuals engaged in other industries. In this case, when estimating health-related data for individuals engaged in the fishing industry, the predetermined group is set, for example, as a group of individuals engaged in the fishing industry. In this case, for example, the results of a health check conducted by a fishing cooperative are used as the health-related data.

[0025] The acquisition unit 11 acquires, for example, data related to the health of the target person. The acquisition unit 11 acquires, for example, the most recent health-related data from the health-related data of the target person. For example, if the health-related data is the result of a health check, the acquisition unit 11 acquires the result of the most recent health check that the target person underwent. The acquisition unit 11 also acquires, for example, the age of the target person. The age of the target person may be, for example, the age at the time the health-related data of the target person was measured. The acquisition unit 11 may also acquire attributes of the target person. The acquisition unit 11 acquires, for example, information identifying the target person from the terminal device 20. The acquisition unit 11 also acquires health-related data from the data management device 30. The acquisition unit 11 may also acquire the health-related data of the target person from the terminal device 20.

[0026] When classifying health-related data for each age group into data groups and estimating transitions as age increases, the classifier 12, for example, classifies the health-related data for each age group into data groups. For example, the classifier 12 generates a probability density distribution of the health-related data for each age group based on the classified data groups. When generating the probability density distribution of the health-related data, the classifier 12, for example, classifies the health-related data for each age group into data groups for each predetermined interval. Then, the classifier 12 generates a probability density distribution of the health-related data for each age group using, for example, the data groups classified for each predetermined interval. For example, when using data on two items of health-related data, the classifier 12 classifies the health-related data on a grid with the two items of data as axes, thereby generating a probability density distribution of the health-related data for each age group. In this case, the data groups are, for example, data classified into each grid.

[0027] When the health-related data is blood pressure, the classification unit 12 classifies the systolic blood pressure and the diastolic blood pressure into data groups of 5 mmHg each for each age group, for example. When the health-related data is blood pressure, the classification unit 12 may classify the health-related data into two-dimensional data groups that associate the systolic blood pressure with the diastolic blood pressure. For example, the classification unit 12 classifies the health-related data into one of grids that divide the systolic blood pressure and the diastolic blood pressure for each age group into 5 mmHg increments. Then, the classification unit 12 generates a probability density distribution of the blood pressure data for each age group.

[0028] Also, for example, if the health-related data is HbA1c and glucose, the classification unit 12 classifies the health-related data into one of grids that divides HbA1c in increments of 0.1 percent and glucose in increments of 5 mg / dL for each age group.

[0029] The classification unit 12 generates a probability density distribution of the health-related data based on, for example, data groups into which the health-related data is classified. For example, the classification unit 12 generates the probability density distribution of the health-related data by dividing the number of data in each data group by the total number of data.

[0030] Figure 4 shows examples of health data for 50-year-olds and 70-year-olds. The example health data in Figure 4 is two-dimensional data with glucose and HbA1c test data as axes. In the health example in Figure 4, many 50-year-olds have low glucose and HbA1c values, whereas at 70 years old, there are groups with rising glucose values, groups with rising values ​​for both glucose and HbA1c, and groups with little change in values.

[0031] The classification unit 12 may classify the health-related data based on the attributes of the person corresponding to each health-related data. For example, if the attribute is gender, the classification unit 12 classifies the health-related data into female data and male data.

[0032] The classification unit 12 may classify the health-related data based on the attributes of the target person. For example, the classification unit 12 classifies health-related data of a person having the same attributes as the target person from among the health-related data acquired by the acquisition unit 11. Furthermore, when classifying the health-related data into data groups to estimate the health-related data when the target person ages, the classification unit 12 may classify the health-related data into data groups based on the attributes of the target person.

[0033] When the disease onset probability is predicted, the classifying unit 12 may generate a probability density distribution of the disease onset probability. For example, the classifying unit 12 generates a probability density distribution of the disease onset probability by age group based on the disease onset probability predicted by the predicting unit 14.

[0034] When the health-related data acquired by the acquisition unit 11 is not classified into data by age group, the classification unit 12 classifies the health-related data into data by age group based on the age category estimated by the estimation unit 13. For example, when the estimation unit 13 estimates health-related data in 10-year age categories, the classification unit 12 classifies the health-related data into data by 10-year age categories. Furthermore, when classifying the health-related data into data groups to estimate health-related data as the target person's age increases, the classification unit 12 may classify the health-related data into data by age group based on the age category estimated by the estimation unit 13 to generate probability density distribution data for each age group. For example, the classification unit 12 uses the health-related data classified by 10-year age categories to generate probability density distribution data for each 10-year age category.

[0035] The estimation unit 13 estimates a transition destination of the health-related data of a target person when the target person's age changes from a first age group to a second age group. The estimation unit 13 estimates a transition destination of the health-related data of the target person using, for example, an algorithm related to an optimal transportation problem. The algorithm related to the optimal transportation problem is, for example, an algorithm for performing optimization processing using optimal transportation. Furthermore, when classifying the health-related data for each age group into data groups and estimating a transition destination when the age increases, the estimation unit 13 estimates a second data group to which the health-related data of the target person will transition when the target person in the first age group, whose health-related data is classified into the first data group, ages into the second age group. For example, the estimation unit 13 estimates, as the second data group, a transition destination when a transition occurs from a first data group on the probability density distribution of health-related data for the first age group to a data group on the probability density distribution of health-related data for the second age group.

[0036] The estimation unit 13 calculates, for example, a state transition probability when a transition occurs from each piece of health-related data in a first age group to each piece of health-related data in a second age group. The estimation unit 13 calculates, for example, a state transition probability from each piece of data in the first age group to each piece of data in the second age group using an algorithm for an optimal transportation problem.

[0037] The estimation unit 13 calculates the state transition probability when transitioning from each piece of data on the probability density distribution in the first age group to each piece of health-related data in the second age group, for example, using an algorithm for the optimal transportation problem. The estimation unit 13 calculates the state transition probability by estimating π(dx, dy) that minimizes the transportation cost c(x, y) in the following equation 1, for example.

[0038]

number

[0039] For example, based on the calculated state transition probability, the estimation unit 13 estimates a transition destination of the data related to the health of the target person when the target person's age changes from a first age group to a second age group. For example, the estimation unit 13 estimates the expected value of the calculated state transition probability as data to be a transition destination when the target person's age changes to the second age group. Then, for example, the estimation unit 13 estimates the estimated transition destination data as data related to the health of the target person when the target person's age changes to the second age group.

[0040] Furthermore, when classifying health-related data for each age group into data groups and estimating a transition destination when age increases, the estimation unit 13 estimates, for example, based on the calculated state transition probability, a data group to which the health-related data of a target person will transition when the target person's age changes from a first age group, whose health-related data is classified into a first data group, to a second age group. For example, the estimation unit 13 estimates the data group with the highest calculated state transition probability as the data group to which the target person will transition when their age changes to the second age group. Then, for example, the estimation unit 13 estimates data indicated by the estimated transition destination data group as the health-related data of the target person when their age changes to the second age group. For example, the estimation unit 13 estimates the mode of the data indicated by the estimated transition destination data group as the health-related data of the target person when their age changes to the second age group. The estimation unit 13 may estimate the minimum or maximum value of the data indicated by the estimated transition destination data group as the health-related data for the target person when his / her age falls into the second age group.

[0041] The estimation unit 13, for example, calculates a state transition probability for each of the data items of predetermined items among the health-related data when a transition occurs from the health-related data for a first age group to the health-related data for a second age group. The estimation unit 13, for example, calculates the state transition probability by changing the setting values ​​of the first age group and the second age group for each of the data items of predetermined items. That is, the estimation unit 13 calculates the state transition probability for each combination of the predetermined item, the first age group, and the second age group. Then, the estimation unit 13 stores the state transition probability for each combination of the predetermined item, the first age group, and the second age group as a database in the storage unit 16, for example. The estimation unit 13 estimates the future health-related data of the target person by, for example, storing the state transition probability optimized for each combination of the predetermined item, the first age group, and the second age group as a database.

[0042] The data of the predetermined item is, for example, data of an item related to a predetermined disease. The predetermined disease is, for example, a disease that has a large impact on the life of the subject person if the subject is affected. The predetermined disease may be a disease that affects more people as the person gets older. The predetermined disease is, for example, cancer, myocardial infarction, diabetes, high blood pressure, and brain disease. The predetermined disease is not limited to the above. Furthermore, the predetermined item is not limited to the above.

[0043] The estimation unit 13 selects state transition probability data from the database based on, for example, the age of the target person and the item to be estimated. Then, based on, for example, the selected state transition probability data, the estimation unit 13 estimates health-related data for when the target person's age falls into a second age group.

[0044] The estimation unit 13 estimates a second data group to be a transition destination from the first data group, for example, by using an item related to a predetermined disease among the health-related data as a variable. For example, when the health-related data is the results of a medical checkup and the predetermined disease is diabetes, the estimation unit 13 may estimate a second data group to be a transition destination from the first data group by using measured values ​​of HbA1c and glucose used as indicators for diagnosing diabetes as variables.

[0045] The estimation unit 13 may estimate a transition destination of a data group between multiple age groups. For example, the estimation unit 13 estimates a second data group to which a first data group will transition via a data group of health-related data in at least one or more age groups between a first age group and a second age group. For example, when the first age group is set to the 50s and the second age group is set to the 70s, the estimation unit 13 estimates a data group to which a first data group will transition via a data group of health-related data in the 60s. There may be two or more age groups between the first age group and the second age group. Furthermore, the interval between the age groups may be narrower than 10 years.

[0046] The estimation unit 13 may estimate a transition destination of the data of the disease probability of the target person when the target person's age changes to a second age group, based on the disease onset probability in a first age group. For example, the estimation unit 13 calculates a state transition probability between the disease onset probability in the first age group and the disease onset probability in the second age group. Then, the estimation unit 13 estimates a transition destination of the data of the disease probability of the target person when the target person's age changes to the second age group, based on the calculated state transition probability.

[0047] The prediction unit 14 predicts the probability of a person in a first age group developing a disease when they move into a second age group, for example, based on data in a second data group estimated as a transition destination from the first data group.

[0048] The prediction unit 14 predicts the probability of a disease occurring when a person in a first age group moves to a second age group using a disease prediction model, for example, based on data estimated as the transition destination of the target person's health data. The disease prediction model is, for example, a machine learning model that uses the target person's health data as input and predicts the probability of the target person's disease occurring. The disease prediction model is generated, for example, by machine learning the relationship between the health data of each of multiple people and the presence or absence of the disease occurring in each person. The disease prediction model is generated, for example, by deep learning using a neural network. The learning algorithm for generating the disease prediction model is not limited to the above. The disease prediction model is generated, for example, in a system external to the data estimation device 10. The disease prediction model may also be generated, for example, by a learning means (not shown) inside the data estimation device 10.

[0049] The prediction unit 14 may predict the probability of disease onset for each age group in each data group into which health-related data is classified. For example, the prediction unit 14 predicts the probability of disease onset for each data group based on the health-related data for each age group.

[0050] The prediction unit 14 may predict the medical expenses of the target person. The medical expenses are, for example, the costs incurred by the target person to receive medical care. Medical care may include nursing care. The prediction unit 14 predicts the medical expenses of the target person based on the probability of disease onset. The relationship between the disease onset probability and the medical expenses is set, for example, as table-format data. The prediction unit 14 may predict the medical expenses of the target person using a function with the predicted value of medical expenses as the objective variable and the disease onset probability as the explanatory variable. The function used to predict the medical expenses is set, for example, for each disease.

[0051] Based on the estimation result of the transition destination, the output unit 15 outputs health-related data for the target person when the target person's age increases. For example, the output unit 15 outputs health-related data for the target person in a first age group and health-related data for the target person when the target person's age increases to a second age group. For example, if the first age group is 50 years old and the second age group is 70 years old, the output unit 15 outputs the health-related data for the target person at age 50 and the estimation result of the health-related data for the target person at age 70.

[0052] The output unit 15 may output the estimated results of health-related data corresponding to each predetermined disease. Furthermore, the output unit 15 may output the disease onset probability when the target person in a first age group changes age to a second age group as health-related data. Furthermore, the output unit 15 may output a sentence explaining the estimated results of the health-related data of the target person. The relationship between the estimated results of the health-related data and the sentence explaining the estimated results is set as data in a table format, for example. The output unit 15 outputs the health-related data when the target person's age increases, for example, to the terminal device 20.

[0053] The output unit 15 may output a prediction result of medical expenses required for the target person to receive medical care in the future as the target person ages, as an estimation result of the health-related data. The output unit 15 may also output at least one of the health-related data and the prediction result of medical expenses as the target person ages as time-series data. The time-series data is, for example, a graph with the horizontal axis representing time and the vertical axis representing the health-related data or the prediction result of medical expenses as the target person ages.

[0054] FIG. 5 is an example of a display screen displaying the estimated results of future health data for a target person. For example, the example of the display screen in FIG. 5 shows the estimated results of health data for a target person when the target person's age increases from 50 to 70, where the first age group is 50 years old and the second age group is 70 years old. The example of the display screen in FIG. 5 shows that the health data for a person whose health data is within the dashed line at age 50 transitions to the dashed line for data at age 70 when the target person increases in age to 70. Furthermore, in the example of the display screen in FIG. 5, because the data is in an area with a low incidence rate even when the target person increases in age to 70, the following sentence is displayed: "Even at age 70, the risk of developing diabetes is considered low."

[0055] FIG. 6 is an example of a display screen that displays the estimated results of data related to a target person's future health along with the error range of the estimated value. In the example of the display screen in FIG. 6, estimated HbA1c and glucose values ​​for a 50-year-old person at ages 60 and 70 are displayed. In the example of the display screen in FIG. 6, the error range of the estimated value at age 60 and the error range of the estimated value at age 70 are displayed using concentric circles. In the example of the display screen in FIG. 6, the error range of the estimated value at age 60 and the error range of the estimated value at age 70 are displayed using two levels of concentric circles, one with a dashed line and the other with a solid line. The output unit 15 outputs the error range of the estimated value based on, for example, a state transition probability. For example, when outputting two levels of concentric circles, the output unit 15 outputs the error range of the estimated value based on the standard of state transition probability set in the two levels.

[0056] The memory unit 16 stores, for example, information related to the process of estimating data related to the future health of a target person. The memory unit 16 stores, for example, state transition probabilities for each combination of a predetermined item, a first age group, and a second age group as a database. The memory unit 16 stores, for example, data related to the health of the target person. The memory unit 16 stores, for example, estimation results of data related to the health of the target person. The memory unit 16 also stores a disease prediction model. The disease prediction model may be stored in a storage means external to the data estimation device 10.

[0057] The terminal device 20 is, for example, a terminal device that accesses the data estimation device 10 and is used for processing to estimate data related to future health. The terminal device 20 acquires the estimation result of the data related to the future health of the target person, for example, from the output unit 15 of the data estimation device 10. Then, the terminal device 20 outputs the estimation result of the data related to the future health of the target person to, for example, a display device (not shown).

[0058] The terminal device 20 is used, for example, by a person who provides advice to the target person regarding health or assets, or by the target person. The person who provides advice to the target person is, for example, a medical professional, an insurance officer, a human resources officer, a financial planner, or a financial institution employee. The medical professional is a doctor, a nurse, a physical therapist, a pharmacist, a laboratory technician, or a counselor. The medical professional is not limited to the above. Furthermore, the person who provides advice to the target person is not limited to the above.

[0059] For example, a personal computer, a tablet computer, a smartphone, or a smartwatch can be used as the terminal device 20. The information processing device used as the terminal device 20 is not limited to the above.

[0060] The data management device 30 stores, for example, health-related data. For example, the data management device 30 stores the health-related data by associating the measurement date of the health-related data and the age of the person corresponding to the health-related data. The data management device 30 may also store the health-related data by associating the attributes of the person corresponding to the health-related data. The data management device 30 also outputs the health-related data to the acquisition unit 11 of the data estimation device 10, for example.

[0061] When the health-related data is the results of a health checkup, the data management device 30 stores, for example, the date of the health checkup, the age of the person who underwent the health checkup, and the results of the health checkup in association with each other. The attributes are, for example, information on one or more of the following: gender, place of residence, nationality, occupation, medical history, and medical history of family members. The attributes are not limited to the above. The date of the health checkup may be information indicated by the month, year, or fiscal year in which the health checkup was conducted. Furthermore, the data management device 30 may store the results of the health checkup as a database categorized based on at least one of the date of the health checkup and the attributes of the person who underwent the health checkup.

[0062] The data management device 30 may store, for example, the results of a health checkup as anonymously processed information or pseudonymized information. Anonymously processed information is, for example, information that has been processed so that an individual cannot be identified even when compared with other information. Pseudonymized information is, for example, information that cannot identify an individual by itself but has been processed so that an individual can be identified when compared with other information.

[0063] The data management device 30 stores, for example, the results of health checkups conducted for a predetermined group. The predetermined group is, for example, a group for which health checkups are conducted. The predetermined group is, for example, a local government, a company, an organization, a cooperative, a school, or a health insurance association. The predetermined group is not limited to the above. The data management device 30 may also store the results of health checkups for multiple groups.

[0064] The following describes the process in which the data estimation device 10 estimates health-related data for a target person as the target person ages. Fig. 7 shows an example of an operational flow of the process in which the data estimation device 10 estimates health-related data for a target person as the target person ages.

[0065] The acquisition unit 11 acquires health-related data for each person in a different age group (step S11). The acquisition unit 11 acquires the health-related data from the data management device 30, for example.

[0066] When the health-related data is acquired, the estimation unit 13 estimates the transition destination of the health-related data of the target person when the target person in the first age group changes age to the second age group (step S12).

[0067] When the transition destination of the data is estimated, the output unit 15 outputs the health-related data of the target person when the age increases based on the estimation result of the transition destination (step S13). The output unit 15 outputs the health-related data of the target person when the age increases to, for example, the terminal device 20.

[0068] The processes in the data estimation device 10 may be distributed and executed among a plurality of information processing devices connected via a network. For example, the processes in the classification unit 12 and the estimation unit 13 and the process in the prediction unit 14 may be executed in different information processing devices. It can be appropriately set which information processing device executes each process in the data estimation device 10.

[0069] The data estimation device 10 estimates the transition destination of the health-related data of a target person when the target person's age changes from a first age group to a second age group. Then, the data estimation device 10 outputs the health-related data of the target person when the target person's age increases based on the transition destination estimation result. By estimating the health-related data of the target person when the target person's age increases in this way, the data estimation device 10 can easily estimate the health-related data of the target person when the target person's age increases.

[0070] As described above, the data estimation device 10 estimates health-related data for a target person as they age, thereby enabling estimation of future health-related data without requiring long-term health-related data for the same person. Therefore, the data estimation device 10 can easily estimate health-related data for a target person as they age. Furthermore, by estimating health-related data for a target person as they age, the data estimation device 10 can, for example, assist the target person in making health-related decisions.

[0071] Furthermore, by predicting the probability of disease onset, the data estimation device 10 can provide information regarding the future risk of the target person developing the disease. Furthermore, by estimating the medical expenses required for receiving medical treatment in the future, the data estimation device 10 can provide information for creating an accurate asset plan for the target person.

[0072] (Second embodiment) A second embodiment of the present disclosure will be described in detail with reference to the drawings. FIG. 8 is a diagram illustrating an example of the configuration of a data estimation system. The data estimation system includes a data estimation device 40, a terminal device 20, a measurement device 50, and a data management device 30. The data estimation device 40 is connected to the terminal device 20, for example, via a network. The data estimation device 40 is connected to the measurement device 50, for example, via a network. The data estimation device 40 is connected to the data management device 30, for example, via a network. Furthermore, there may be a plurality of terminal devices 20, a plurality of measurement devices 50, and a plurality of data management devices 30. The numbers of terminal devices 20, measurement devices 50, and data management devices 30 can be set as appropriate.

[0073] The data estimation system of this embodiment estimates data regarding the future health of a target person based on, for example, data regarding the target person's health and daily data. The daily data is, for example, data acquired during the target person's daily life. The data acquired during the target person's daily life is data regarding at least one of daily life behavior and daily life physical condition. Daily life behavior is, for example, the target person's behavior that may affect their health condition. The health condition may include cognitive function. The target person's daily data is data regarding one or more of vital signs, number of steps taken, walking distance, running distance, sleep time, food intake, food content, type of sports played, type of strength training, strength training duration, sports performance time, yoga duration, and reading volume.

[0074] The daily data is measured using, for example, the measuring device 50. The daily data may also be data input by the subject or another person. The other person may be, for example, a family member, an instructor, a medical professional, a caregiver, or a care supporter. The medical professional may be a doctor, a nurse, a physical therapist, a pharmacist, a laboratory technician, or a counselor. The medical professional is not limited to the above. The other person is not limited to the above.

[0075] Here, we will explain a specific example of the configuration of the data estimation device 40. Fig. 9 is a diagram showing an example of the configuration of the data estimation device 40. The data estimation device 40 includes, for example, an acquisition unit 41, a change estimation unit 42, a classification unit 43, an estimation unit 44, a prediction unit 45, an output unit 46, and a storage unit 47.

[0076] The acquisition unit 41 has the same functions as the acquisition unit 11 of the first embodiment. The acquisition unit 41 further acquires, for example, daily data of the target person. The acquisition unit 41 acquires, for example, daily data of the target person after the time when the data related to the target person's health is measured. For example, if the health data is the results of a health check, the acquisition unit 41 acquires daily data after the day the target person underwent the health check. If the health data is the results of a health check, the acquisition unit 41 may acquire daily data after the time when the target person received an explanation of the results of the health check from a medical professional.

[0077] The acquisition unit 41 may further acquire daily data of the target person before the time when the data related to the target person's health was measured. The daily data of the target person before the time when the data related to the target person's health was measured is used, for example, to calculate the amount of change in the daily data before and after the time when the data related to the target person's health was measured.

[0078] The acquisition unit 41 may further acquire information indicating the content of the behavior performed to improve the health state and a target value. For example, if the behavior to improve the health state is walking, the behavior content related to health improvement is information indicating that the behavior to improve the health state is walking and a target value for the number of steps. The target value for the number of steps is, for example, the number of steps to be achieved per day. The target value for the number of steps is not limited to the number of steps per day. The target value may also be indicated by a distance. The acquisition unit 41 also acquires daily data of the target person from, for example, the measurement device 50. The acquisition unit 41 may acquire the daily data via the terminal device 20.

[0079] The change estimation unit 42 estimates a change in the health-related data caused by the target person's daily life, for example, based on the target person's daily life data. The change estimation unit 42 estimates the health-related data after a change has occurred due to the target person's daily life, for example. The change estimation unit 42 may estimate the amount of change in the health-related data caused by the change due to the target person's daily life.

[0080] For example, if a subject continues running, the subject's blood test data in a health checkup may show improvements in cholesterol, triglycerides, blood glucose, and Hba1c levels. In such a case, the change estimation unit 42 estimates the blood test data that reflects the effects of running, based on, for example, the subject's daily running distance and the actual measured values ​​of the blood test data.

[0081] The change estimation unit 42 may also estimate the health-related data based on the amount of change in the daily data before and after the time point when the target person's health-related data was measured. Alternatively, the change estimation unit 42 may estimate the health-related data based on the amount of change in the daily data when the target person changes their daily life.

[0082] The change estimation unit 42 estimates health-related data after changes have occurred due to daily life, for example, using a change estimation model. The change estimation model is, for example, a machine learning model that uses daily life data of a target person as input and estimates health-related data after changes have occurred due to daily life. The change estimation model is generated, for example, by machine learning the relationship between the health-related data and daily life data of each of multiple people and the health-related data of each person after changes have occurred due to daily life. The change estimation model is generated, for example, by deep learning using a neural network. The learning algorithm for generating the change estimation model is not limited to the above. The change estimation model is generated, for example, in a system external to the data estimation device 10. The change estimation model may also be generated, for example, by learning means (not shown) inside the data estimation device 10.

[0083] FIG. 10 shows an example of an estimation result of health data after changes have occurred due to the daily life of a target person. In the example of the estimation result in FIG. 10, the measurement value is the health data that was actually measured. For example, if the health data is the result of a blood test in a health checkup, the measurement value is the value measured by blood in the blood test performed in the health checkup. Also, in the example of the estimation result in FIG. 10, the estimated value indicates the value of the health data after changes have occurred due to daily life. That is, the estimated value is, for example, an estimated value of the health data estimated based on daily life data. The change estimation unit 42 calculates the value of the health data after changes have occurred due to daily life as the estimated value shown in the example of the estimation result in FIG. 10, based on, for example, the daily data of the target person.

[0084] The change estimation unit 42 may estimate health-related data when the behavior to improve the health state is performed according to the target, based on information indicating the content of the behavior to improve the health state and the target value. The change estimation unit 42 may, for example, use a change estimation model to estimate health-related data when the behavior to improve the health state is performed according to the target. In this case, the change estimation unit 42 may, for example, input the target value into the change estimation model as daily data to estimate health-related data when the behavior to improve the health state is performed according to the target. The change estimation unit 42 may estimate health-related data when the behavior to improve the health state is performed according to the target, by referring to table-format data indicating the relationship between the content of the behavior to improve the health state, the target value, and the amount of change in the health-related data.

[0085] The classification unit 43 has the same function as the classification unit 12 of the first embodiment. The classification unit 43 may also classify into data groups the health-related data after changes due to daily life have occurred, which have been estimated by the change estimation unit 42. For example, the classification unit 43 generates a probability density distribution of the health-related data for each age group based on the data groups into which the health-related data after changes due to daily life have been classified.

[0086] The estimation unit 44 has the same function as the estimation unit 13 of the first embodiment. For example, the estimation unit 44 further calculates a state transition probability when a transition occurs from each of the health-related data in a first age group, which is a measurement value, to each of the health-related data in a second age group. Then, for example, the estimation unit 44 uses the health-related data estimated by the change estimation unit 42 as the data in the first age group of the target person, to estimate a transition destination of the target person's health-related data when the target person's age becomes the second age group. Then, the estimation unit 44 estimates the transition destination data as health-related data when the target person's age increases to the second age group.

[0087] The estimation unit 44 stores, for example, in the storage unit 47, a database of state transition probabilities for each combination of a predetermined item, a first age group, and a second age group. The predetermined items are the same as the predetermined items in the first embodiment. The estimation unit 44 selects state transition probability data from the database based on, for example, the age of the target person and the item to be estimated. Then, based on, for example, the selected state transition probability data, the estimation unit 44 uses the health-related data estimated by the change estimation unit 42 as data for the target person in the first age group, to estimate health-related data for when the target person's age becomes the second age group.

[0088] For example, suppose the first age group of the target person is 50 years old and the second age group is 70 years old. Furthermore, suppose the health-related data is the results of a medical checkup. In this case, the change estimation unit 42 estimates changes in the results of a medical checkup taken at age 50, for example, based on the daily data of the target person who is 50 years old. For example, the change estimation unit 42 estimates the results of a medical checkup that would occur if the target person were to undergo a medical checkup after changes due to the target person's daily life have occurred, based on data on state transition probabilities when the target person's age increases from 50 to 70 years old. Then, the estimation unit 44 uses the estimated results of the medical checkup as the results of the medical checkup at age 50 to estimate the results of a medical checkup that would occur if the target person were to undergo a medical checkup at age 70.

[0089] Furthermore, the estimation unit 44 may calculate state transition probabilities when a transition occurs from each piece of health-related data in the first age group estimated from the daily data to each piece of health-related data in the second age group.

[0090] The prediction unit 45 has the same functions as the prediction unit 14 of the first embodiment. The prediction unit 45 further predicts the probability of disease onset based on, for example, health-related data after changes have occurred due to daily life. The prediction unit 45 predicts the probability of disease onset using, for example, a disease prediction model similar to that of the prediction unit 14 of the first embodiment. For example, the prediction unit 45 predicts the probability of disease onset by using health-related data for an increase in age estimated based on the health-related data after changes have occurred due to daily life as input to the disease prediction model. The prediction unit 45 may predict the probability of disease onset by using the health-related data after changes have occurred due to daily life as input to the disease prediction model. The prediction unit 45 may also predict the medical expenses of the target person based on the health-related data after changes have occurred due to daily life.

[0091] The output unit 46 has the same function as the output unit 15 of the first embodiment. For example, when the target person's age increases to a second age, the output unit 46 further outputs health-related data that has changed due to daily life. The output unit 46 may output, as the health-related data when the target person's age increases to the second age, health-related data that has changed due to daily life and health-related data that has not changed due to daily life. In other words, the output unit 46 may output an estimation result of health-related data in a second age group estimated from an estimated value of health-related data in a first age group that has changed due to daily life, and an estimation result of health-related data in the second age group estimated from a measured value of health-related data in the first age group.

[0092] The output unit 46 may output a prediction result of future medical expenses of the target person, which is estimated based on the estimation result of the health-related data after changes occur due to daily life. The output unit 46 may also output at least one of the target person's future health-related data and the prediction result of medical expenses as time-series data. The time-series data is, for example, a graph in which the horizontal axis represents time and the vertical axis represents the health-related data or the prediction result of medical expenses as the target person ages.

[0093] The output unit 46 outputs the estimated results of the health-related data to, for example, the terminal device 20. The output unit 46 may output the estimated results of the health-related data to the measurement device 50. The output unit 46 may also output the estimated results of the health-related data to the terminal device 20 and the measurement device 50.

[0094] Figure 11 shows an example of a display screen that displays health data estimation results for a target person as they age, including health data after changes have occurred due to daily life and health data that has not changed due to daily life. In the example of the display screen in Figure 11, the dashed line indicates the change over time in estimated future health data based on current measurements. Also, in the example of the display screen in Figure 11, the solid line indicates the change over time in estimated future health data based on estimated health data after changes have occurred due to daily life.

[0095] In the example display screen of FIG. 11 , the estimated value of health data after changes due to daily life, shown by the solid line, is displayed as an "estimated value from improved data." In the example display screen of FIG. 11 , the estimated value of health data after changes due to daily life, shown by the solid line, is displayed as an estimated value of future health data when, for example, current health data improves as a result of daily behavior. For example, if a subject referring to the example display screen of FIG. 11 walks in their daily lives, the subject can recognize the estimated value of the improvement effect of their health data resulting from walking.

[0096] FIG. 12 is an example of a display screen displaying the cost of medical care for a subject as the subject ages. In the example of the display screen of FIG. 12, the dashed line indicates the change over time in estimated future medical costs based on current measurements. Also, in the example of the display screen of FIG. 12, the solid line indicates the change over time in estimated future medical costs based on estimated values ​​of health data after changes due to daily life. In the example of the display screen of FIG. 12, the estimated value of medical care after changes due to daily life, shown by the solid line, is displayed as the estimated value of future medical care if, for example, the current health data improves as a result of daily life actions.

[0097] The storage unit 47 has the same function as the storage unit 16 of the first embodiment. The storage unit 47 further stores, for example, estimation results of health-related data estimated based on daily data. The storage unit 47 also stores a change estimation model. The change estimation model may be stored in a storage means external to the data estimation device 40.

[0098] The measuring device 50 is, for example, a terminal device that acquires daily data of a target person. The measuring device 50 measures the daily data of the target person using, for example, a sensor. The measuring device 50 then outputs the measured daily data to the acquisition unit 41 of the data estimation device 40. Some or all of the target person's daily data may be input to the measuring device 50 by the target person. Furthermore, the daily data acquired by the measuring device 50 may be input to the data estimation device 40 using a removable storage medium. For example, a non-volatile semiconductor storage device may be used as the storage medium.

[0099] The measurement device 50 is not limited to a device dedicated to measurement. For example, the measurement device 50 may include a device with multiple functions, such as a smartphone or a smart watch. Furthermore, the terminal device 20 and the measurement device 50 may be integrated into one device.

[0100] The following describes a process for calculating a state transition probability from each data group of a first age group to each data group of a second age group in the data estimation device 40. Fig. 13 shows an example of an operational flow of the process for calculating a state transition probability from each data group of a first age group to each data group of a second age group in the data estimation device 40.

[0101] The acquiring unit 41 acquires, for example, health-related data for each of people in different age groups (step S21). The acquiring unit 11 acquires the health-related data from the data management device 30, for example.

[0102] When the health-related data is acquired, the estimation unit 44 calculates, for example, the state transition probability from each piece of data in the first age group to each piece of data in the second age group (step S22).

[0103] When the state transition probabilities are calculated, the estimation unit 44 stores, for example, the estimated state transition probabilities (step S23). The estimation unit 44 stores, for example, in the storage unit 47, the state transition probabilities for each combination of a predetermined item, a first age group, and a second age group as a database.

[0104] The following describes the operation of the data estimation device 40 to estimate health-related data for a target person as their age increases, based on health-related data that has changed due to daily life. Fig. 14 shows an example of the operation flow of a process to estimate health-related data for a target person as their age increases, based on health-related data that has changed due to daily life.

[0105] The acquisition unit 41 acquires, for example, data related to the health of the target person and daily data (step S31). The acquisition unit 41 acquires the daily data of the target person from, for example, the measurement device 50. The acquisition unit 41 also acquires the health data of the target person from, for example, the data management device 30.

[0106] Once the target person's health data and daily data are acquired, the change estimation unit 42 estimates, based on the daily data, health data that has changed due to the target person's daily life, for example (step S32).

[0107] After estimating the health-related data that has changed due to daily life, the estimation unit 44 estimates the health-related data of the target person as the target person ages, based on the health-related data that has changed due to daily life (step S33).

[0108] When the data on the health of the target person when the target person ages has been estimated, the output unit 46 outputs the data on the health of the target person when the target person ages (step S34).

[0109] The processes in the data estimation device 40 may be distributed and executed among a plurality of information processing devices connected via a network. For example, the processes in the classification unit 43 and the estimation unit 44 and the process in the change estimation unit 42 may be executed in different information processing devices. It can be appropriately set which information processing device executes each process in the data estimation device 40.

[0110] For example, the data estimation device 40 estimates health-related data that has changed due to the target person's daily life based on daily data. Then, the data estimation device 40 estimates health-related data for the target person as the target person ages based on the health-related data that has changed due to daily life. In this way, the data estimation device 40 estimates future health-related data based on daily data from daily life, thereby enabling estimation of future health conditions that may change due to daily life. Therefore, the data estimation device 40 can improve the accuracy of estimation of the target person's future health conditions.

[0111] For example, if the health data is the results of a health checkup and the next health checkup is one year from now, the data estimation device 40 can estimate health data that reflects, for example, changes in daily life by estimating the future health data of the target person based on the daily data. Therefore, the target person can make appropriate decisions regarding behavioral improvements in their daily life by referring to the health data that reflects, for example, changes in daily life.

[0112] Each process in the data estimation device 10 and the data estimation device 40 can be realized by executing a computer program on a computer. Fig. 15 shows an example of the configuration of a computer 100 that executes a computer program that performs each process in the data estimation device 10. The computer 100 includes a CPU (Central Processing Unit) 101, a memory 102, a storage device 103, an input / output I / F (Interface) 104, and a communication I / F 105.

[0113] The CPU 101 reads and executes computer programs for performing each process from the storage device 103. The CPU 101 may be configured by a combination of multiple CPUs. The CPU 101 may also be configured by a combination of a CPU and another type of processor. For example, the CPU 101 may be configured by a combination of a CPU and a graphics processing unit (GPU). The memory 102 is configured by a dynamic random access memory (DRAM) or the like, and temporarily stores the computer programs executed by the CPU 101 and data being processed. The storage device 103 stores the computer programs executed by the CPU 101. The storage device 103 is configured by, for example, a non-volatile semiconductor storage device. Other storage devices such as a hard disk drive may also be used for the storage device 103. The input / output I / F 104 is an interface that receives input from an operator and outputs display data, etc. The communication I / F 105 is an interface that transmits and receives data between the terminal device 20, the data management device 30, the measurement device 50, and other information processing devices. Furthermore, the terminal device 20 and the data management device 30 may also have the same configuration as the computer 100 .

[0114] The computer program used to execute each process can also be stored and distributed on a computer-readable recording medium that non-temporarily stores data. Examples of recording media that can be used include magnetic tapes for recording data and magnetic disks such as hard disks. Optical disks such as CD-ROMs (Compact Disc Read Only Memory) can also be used as recording media. Non-volatile semiconductor storage devices can also be used as recording media.

[0115] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0116] [Appendix 1] A means for acquiring health-related data for each person in a different age group; an estimation means for estimating a transition destination of health-related data of a target person when the target person in a first age group changes age to a second age group; an output means for outputting the health-related data when the target person's age increases based on the estimation result of the transition destination; A data estimation device comprising:

[0117] [Appendix 2] The estimation means estimates a transition destination of the health-related data of the target person using an algorithm related to an optimal transportation problem. 2. The data estimation apparatus of claim 1.

[0118] [Appendix 3] further comprising a classification means for classifying the health-related data into data groups for each age group; the estimation means estimates, as a second data group, a transition destination when a first data group on the probability distribution of health-related data in the first age group transitions to a data group on the probability distribution of health-related data in the second age group; 3. A data estimation device according to claim 1 or 2.

[0119] [Appendix 4] the estimation means estimates the health-related data of the target person when they move up to the second age group, based on a state transition probability when they transition from the first data group on the probability distribution of health-related data in the first age group to a data group on the probability distribution of health-related data in the second age group; 3. The data estimation apparatus of claim 2.

[0120] [Appendix 5] and a prediction means for predicting the probability of disease onset when a person in the first age group increases in age to the second age group, based on health-related data for the second age group estimated as a transition destination of the health-related data for the first age group. 5. A data estimation device according to any one of appendices 1 to 4.

[0121] [Appendix 6] further comprising a change estimation means for estimating health-related data after a change has occurred due to the daily life of the target person based on the daily life data of the target person; the estimation means uses the estimated health-related data as health-related data for the first age group to estimate health-related data for the target person when their age increases to the second age group; 5. A data estimation device according to any one of appendices 1 to 4.

[0122] [Appendix 7] a prediction means for predicting the probability of disease onset for each of the health-related data for each of the age groups; The estimation means estimates a transition destination of data on the disease development probability of the target person when the target person's age falls into the second age group. 5. A data estimation device according to any one of appendices 1 to 4.

[0123] [Appendix 8] The estimation means estimates a transition destination of the health-related data of the target person when the target person in the first age group changes age to a second age group, using an item related to a predetermined disease among the health-related data as a variable. 8. A data estimation device according to any one of appendices 1 to 7.

[0124] [Appendix 9] the prediction means predicts the probability of disease onset when a person in the first age group increases in age to the second age group using a machine learning model that predicts the probability of disease onset based on health-related data; 6. The data estimation device according to claim 5.

[0125] [Appendix 10] the estimation means estimates a transition destination of the health-related data of the target person when the target person in the first age group changes age to a second age group, via the health-related data in at least one or more age groups between the first age group and the second age group; 10. A data estimation device according to any one of appendixes 1 to 9.

[0126] [Appendix 11] the output means outputs health-related data of the target person in the first age group and health-related data of the target person when the target person's age increases to the second age group. 11. A data estimation device according to any one of appendices 1 to 10.

[0127] [Appendix 12] the output means outputs, as the health-related data when the target person's age increases to the second age group, the health-related data when the target person's age has changed due to daily life and the health-related data that has not changed due to daily life. 7. The data estimation apparatus of claim 6.

[0128] [Appendix 13] the output means outputs, as the health-related data, the probability of the target person in the first age group developing the disease when the target person's age changes to the second age group. 8. The data estimation apparatus of claim 7.

[0129] [Appendix 14] the acquiring means acquires, as the health-related data, results of health checkups for at least one of a predetermined period and a predetermined group; 14. A data estimation device according to any one of appendixes 1 to 13.

[0130] [Appendix 15] the classification means classifies the health-related data of a person having the same attributes as the target person into the data group, from among the acquired health-related data; 15. A data estimation device according to any one of appendices 1 to 14.

[0131] [Appendix 16] Obtain health data for individuals of different age groups, predicting a transition of health-related data of a target person when the target person in a first age group changes age to a second age group; outputting the health-related data when the target person's age increases based on the transition destination estimation result; Data estimation methods.

[0132] [Appendix 17] obtaining health-related data for each person in different age groups; A process of estimating a transition destination of health-related data of a target person when the target person in a first age group changes age to a second age group; a process of outputting the health-related data when the target person's age increases based on the transition destination estimation result; A data estimation program that causes a computer to execute the above.

[0133] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 15, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 16 and 17 in the same dependent relationship as Supplementary Notes 2 to 15. Furthermore, not limited to Supplementary Notes 1, 16, and 17, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0134] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate. [Explanation of symbols]

[0135] 10 Data Estimation Device 11 Acquisition Department 12 Classification section 13 Estimation part 14 Prediction Department 15 Output section 16 Memory section 20 Terminal equipment 30 Data management device 40 Data Estimation Device 41 Acquisition Department 42 Change estimation unit 43 Classification Department 44 Estimation part 45 Prediction Department 46 Output section 47 Memory section 50 Measuring Equipment 100 computers 101 CPU 102 memory 103 Storage device 104 Input / Output Interface 105 Communication I / F

Claims

1. A means for acquiring health-related data for each person in a different age group; an estimation means for estimating a transition destination of health-related data of a target person when the target person's age in a first age group changes to a second age group; an output means for outputting the health-related data when the target person's age increases based on the estimation result of the transition destination; A data estimation device comprising:

2. The estimation means estimates a transition destination of the health-related data of the target person using an algorithm related to an optimal transportation problem. The data estimation device according to claim 1 .

3. further comprising a classification means for classifying the health-related data into data groups for each age group; the estimation means estimates, as a second data group, a transition destination when a first data group on the probability distribution of health-related data in the first age group transitions to a data group on the probability distribution of health-related data in the second age group; The data estimation device according to claim 2 .

4. the estimation means estimates the health-related data of the target person when they move up to the second age group, based on a state transition probability when they transition from the first data group on the probability distribution of health-related data in the first age group to a data group on the probability distribution of health-related data in the second age group; The data estimation device according to claim 3 .

5. and a prediction means for predicting a disease onset probability when a person in the first age group increases in age to the second age group, based on health-related data for the second age group estimated as a transition destination of the health-related data for the first age group.

5. A data estimation device according to claim 1.

6. further comprising a change estimation means for estimating health-related data after a change has occurred due to the daily life of the target person based on the daily life data of the target person; the estimation means uses the estimated health-related data as health-related data for the first age group to estimate health-related data for the target person when their age increases to the second age group; 5. A data estimation device according to claim 1.

7. a prediction means for predicting the probability of disease onset for each of the health-related data for each of the age groups; The estimation means estimates a transition destination of data on the disease development probability of the target person when the target person's age falls into the second age group.

5. A data estimation device according to claim 1.

8. the prediction means predicts the probability of disease onset when a person in the first age group increases in age to the second age group using a machine learning model that predicts the probability of disease onset based on health data; The data estimation device according to claim 5 .

9. Obtain health data for individuals of different age groups, predicting a transition of health-related data of a target person when the target person in a first age group changes age to a second age group; outputting the health-related data when the target person's age increases based on the transition destination estimation result; Data estimation methods.

10. obtaining health-related data for each person in different age groups; A process of estimating a transition destination of health-related data of a target person when the target person in a first age group changes age to a second age group; a process of outputting the health-related data when the target person's age increases based on the transition destination estimation result; A data estimation program that causes a computer to execute the above.

Images