Healthy behavior support device, healthy behavior support method, and computer program

Abstract

To provide a technique that enables health management personalized according to individual characteristics.SOLUTION: One aspect of the present invention is a health behavior support device comprising: a recommended behavior setting unit that sets, for a user, a health behavior that is a recommended behavior to improve the user's health based on the user's genetic information; and an application selection unit that selects an application program for supporting the implementation of the health behavior by the user according to the health behavior set for the user, the application program being executable by an electronic device used by the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technique for supporting human health management. [Background technology]

[0002] Conventionally, regular health checkups such as medical examinations and medical check-ups have been conducted for company employees based on relevant laws and regulations. Although the employees (hereinafter referred to as "patients") undergoing regular health checkups may be allowed to add additional test items of their choice, the test items are generally common test items determined by the company that employs the employees. Therefore, in conventional regular health checkups, appropriate test items may not necessarily be set for diseases that employees of a company are commonly susceptible to or diseases that vary in susceptibility to due to the company's work environment (see, for example, Non-Patent Document 1). In addition, a service (hereinafter referred to as "health service") that promotes the health of users is provided by suggesting actions recommended for improving health (hereinafter referred to as "recommended actions") to users and giving a certain incentive for the users to realize the suggested actions (see, for example, Non-Patent Document 2). [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] https: / / www.neckenpo.or.jp / member / hoken / fushime_ningen_dok.php, "Medical checkup assistance (milestone health check)", NEC Health Insurance Association of Japan [Non-Patent Document 2] https: / / health.dmkt-sp.jp / , d Healthcare, NTT DOCOMO Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional regular medical checkups and health services described above, the examination items and recommended actions were not always set according to the characteristics of the examinee or user. As a result, the conventional regular medical checkups and health services may not have been able to fully contribute to improving the health of the examinee or user.

[0005] In view of the above circumstances, an object of the present invention is to provide a technique that can realize health management that is more suited to the characteristics of an individual. [Means for solving the problem]

[0006] One aspect of the present invention is a health behavior support device that includes a recommended behavior setting unit that sets for a user health behavior, which is behavior that is recommended for improving the health of the user based on the user's genetic information, and an application selection unit that selects an application program executable on an electronic device used by the user, for assisting the user in implementing the health behavior, in accordance with the health behavior set for the user.

[0007] One aspect of the present invention is a health behavior support method comprising: a recommended behavior setting step of setting for a user health behavior, which is behavior recommended for improving the health of the user based on the user's genetic information; and an app determination step of determining, in accordance with the health behavior set for the user, a mission management app, which is an application program executable on an electronic device used by the user and which supports the user in implementing the health behavior.

[0008] One aspect of the present invention is a computer program for causing a computer to function as the above-mentioned health behavior support device. Effect of the Invention

[0009] The present invention makes it possible to provide a technique that can realize health management that is more suited to the characteristics of each individual. [Brief description of the drawings]

[0010] [Figure 1] 2 is a diagram showing a specific example of the functional configuration of the clinical test item determination device in the first embodiment. FIG. [Diagram 2] FIG. 4 is a diagram showing a specific example of a method for generating a genetic model in the first embodiment. [Diagram 3] FIG. 1 shows the relationship between SNP1 of alcohol dehydrogenase (ADH) and SNP2 of acetaldehyde dehydrogenase (ALDH2) and lifestyle habits of drinking or smoking in relation to the development of esophageal cancer. [Figure 4] FIG. 4 is a diagram showing a specific example of a method for generating a non-genetic model in the first embodiment. [Diagram 5] FIG. 2 is a diagram showing a specific example of a method for estimating constitution in the first embodiment. [Figure 6] FIG. 1 is a first diagram illustrating a method for determining an examination item in the first embodiment. [Figure 7] FIG. 2 is a second diagram illustrating the method of determining an examination item in the first embodiment. [Figure 8] FIG. 11 is a third diagram illustrating a method for determining an examination item in the first embodiment. [Figure 9] FIG. 11 is a block diagram showing a specific example of a functional configuration of a health action support device in a second embodiment. [Figure 10] FIG. 11 is a diagram showing a specific example of a method for setting a mission in the second embodiment. [Figure 11] FIG. 11 is a diagram showing a specific example of a method for selecting a health application in the second embodiment. [Figure 12] 13 is a flowchart showing a specific example of a method for determining an application utilization level in the second embodiment. [Figure 13] 13 is a flowchart showing a specific example of a method for determining activity details in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described in detail with reference to the drawings. First Embodiment FIG. 1 is a diagram showing a specific example of the functional configuration of the clinical test item determination device in the first embodiment. The clinical test item determination device 1 is a device that supports the determination of clinical test items (hereinafter referred to as "test items") to be performed on a user based on the user's constitution or the organization to which the user belongs. The clinical test item determination device 1 includes a CPU (Central Processing Unit), a memory, an auxiliary storage device, and the like, which are connected by a bus, and executes a program. The clinical test item determination device 1 functions as a device including a database 11, a genetic model generation unit 12, a non-genetic model generation unit 13, a constitution estimation unit 14, and a test item determination unit 15 by executing the program. All or part of the functions of the clinical test item determination device 1 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The program may be recorded in a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, an optical magnetic disk, a ROM, or a CD-ROM, or a storage device such as a hard disk built into a computer system. The program may be transmitted via a telecommunications line.

[0012] The database 11 is a database that stores various information necessary to determine the test items for each user. The database 11 registers various data, deletes registered data, and provides requested data in response to requests from other functional units.

[0013] The genetic model generating unit 12 has a function of generating a genetic model for each user. The genetic model is a model for estimating the possibility that a user will develop a disease (intended is a lifetime cumulative disease risk, but for simplicity, hereinafter referred to as "incidence rate") based on factors due to the genetic properties of the user (hereinafter referred to as "genetic factors"). Specifically, the genetic model generating unit 12 receives the genetic information of the user as input and generates an estimation model that outputs an estimated value of the incidence rate of each disease as a genetic model. Note that the incidence rate estimated by the genetic model generating unit 12 is basically estimated based on the genetic factors of the user, and the influence of non-genetic factors of the user is not taken into consideration.

[0014] In addition, information indicating the results of clinical tests the user has previously undergone, such as at regular health checkups, and information on lifestyle habits (hereinafter referred to as "health checkup history and other information") may be further used to estimate the incidence rate. In this case, the genetic model generation unit 12 may generate a genetic model that inputs the health checkup history and other information in addition to the genetic information. In some cases, when a user with a certain gene has a certain lifestyle habit (such as smoking), the incidence rate may be extremely high. By considering such a combination of genetic information and health checkup history and other information, the accuracy of the incidence rate can be improved.

[0015] Furthermore, the genetic model generation unit 12 may generate an estimation model (hereinafter referred to as a "health checkup history model") that takes health checkup history information as input and outputs an incidence rate, separate from the genetic model. When the health checkup history model is generated separate from the genetic model, the incidence rate of each disease may be determined based on the incidence rates estimated by both models. For example, the incidence rate of each disease may be determined as a weighted sum of the incidence rate estimated based on the genetic model and the incidence rate estimated based on the health checkup history model. Even when the degree of correlation between the incidence rate due to genes and the incidence rate due to information such as health checkup history is unclear, the estimation accuracy of the incidence rate can be improved.

[0016] The non-genetic model generating unit 13 has a function of generating a non-genetic model of a user. The non-genetic model is a model for estimating the incidence of diseases caused by factors other than the user's genetic factors (hereinafter referred to as "non-genetic factors"). For example, non-genetic factors include the user's physical characteristics, lifestyle, age, health check results, etc. Note that the lifestyle here includes individual lifestyle habits such as drinking and smoking.

[0017] Furthermore, the incidence rate of disease may vary depending on the physical characteristics and lifestyle habits of the individual user as described above, as well as the physical load and behavioral constraints that the user experiences in activities performed at the organization to which the user belongs, such as a company. For example, in an organization where desk work is the main focus, it is highly likely that the amount of exercise performed by users is below the general average, and users are likely to suffer from lifestyle-related diseases caused by lack of exercise. For this reason, lifestyle habits as non-genetic factors may include factors based on the user's activities at the organization to which the user belongs.

[0018] For example, for lifestyle-related diseases caused by lack of exercise, the index value of the amount of exercise measured for each user may be included in the non-genetic factors. In addition, when it is difficult to measure the index value of the amount of exercise for each user, information correlating with the amount of exercise may be included in the non-genetic factors. For example, when it is considered that the amount of exercise of a user differs depending on the type of occupation, the non-genetic factors may include the type of occupation of each user. In addition, when it is considered that the amount of exercise of a user differs depending on the organization to which the user belongs, the non-genetic factors may include the organization to which the user belongs. In this way, the non-genetic factors may include any direct or indirect factors that are considered to be correlated with the incidence rate of a disease.

[0019] The non-genetic model does not necessarily have to be configured as one estimation model, but may be configured to estimate the final incidence rate based on the estimation results of multiple estimation models based on different non-genetic factors or combinations thereof. The non-genetic factors may be set based on single-year data or multiple-year data. By inputting non-genetic factors based on multiple-year data, a non-genetic model that takes into account the secular changes of non-genetic factors can be generated.

[0020] The constitution estimation unit 14 has a function of estimating the constitution of the user based on the genetic model and / or non-genetic model of the user. The constitution of the user here means the incidence rate of a disease estimated from the genetic factors and / or non-genetic factors of the user. The genetic characteristics of the user and the non-genetic factors of the user may mutually affect the disease risk. For example, a user with a certain gene polymorphism may be prone to developing lung cancer if he or she smokes. In such a case, a weighted sum of the disease risks estimated by the two models may be calculated as described later, or one model may be constructed based on both the genetic characteristics of the user and the non-genetic characteristics of the user.

[0021] The test item determination unit 15 has a function of determining test items to be administered to the user. Specifically, the test item determination unit 15 determines test items for diseases with a high incidence in an organization (first organization) such as a company to which the user belongs, or test items for diseases with a high incidence in the organization and an organization (second organization) having similar attributes (hereinafter referred to as "common test items"), and individual test items for each user (hereinafter referred to as "individual test items"). The test item determination unit 15 determines the common test items based on the probability that members of the organization to which the user belongs will develop various diseases, and determines the individual test items based on the constitution of the user estimated by the constitution estimation unit 14.

[0022] With such a configuration, the clinical test item determination device 1 of the first embodiment can include test items that contribute to detection of diseases that the user is likely to develop, in the test items of the user, according to the organization to which the user belongs and the constitution of the user. Below, a method for generating a genetic model and a non-genetic model, a method for estimating a constitution of a user, and a method for determining test items for a user will be described in detail.

[0023] 2 is a diagram showing a specific example of a method for generating a genetic model in the first embodiment. A case-control association analysis or the like can be used to generate a genetic model. In the case-control association analysis, a statistical comparison is made to see whether there is a difference in the frequency of gene polymorphisms between a group with a disease and a group without the disease with respect to the association between the disease and SNPs (single-nucleotide polymorphisms), and the lower the obtained P value (the probability of such an occurrence by chance), the stronger the association is considered to be (see, for example, Reference 1).

[0024] It is also known that the association of a certain SNP with a certain disease can be found through research using GWAS (Genome-Wide Association Study). Specifically, the odds ratio r1 of risk heterozygotes (RN) to non-risk homozygotes (NN) and the odds ratio r2 of risk homozygotes (RR) to non-risk homozygotes (NN) can be obtained as information on the risk allele (R) and non-risk allele (N) of the SNP (see, for example, Reference 3).

[0025] Figure 2 is a table summarizing the number of samples of each genotype in cases and controls in GWAS. "Control" indicates the number of samples in the non-ill group, and "Case" indicates the number of samples in the ill group. In this case, the above odds ratios r1 and r2 are obtained by the following formula (1).

[0026]

number

[0027] Here, for each genotype (NN, RN, RR) of the SNP, the frequency at which the risk allele R appears is p (i.e., the frequency at which the non-risk allele N appears is 1-p), the overall incidence rate is q, and the incidence rates for each genotype are d1, d2, and d3, and the incidence rates d1 to d3 for each genotype are obtained by solving these relational expressions. In this case, the overall incidence rate q for a single SNP is expressed by the following formula (2), and the incidence rate can be specified depending on which genotype the single SNP is.

[0028]

number

[0029] Furthermore, when multiple SNPs are associated, the overall incidence rate P can be expressed by, for example, formula (3) by using a multiplication model of the incidence rates of the genotypes of each SNP.

[0030]

number

[0031] It is assumed that the genetic information of each user used in the above generation method is registered in advance in the database 11 as one piece of user information. The creation of the genetic model is not limited to the above method. For example, the genetic model may be created using a polygenic risk score (see, for example, Reference 2) or the like.

[0032] As described above, the disease risk estimated by the genetic model generating unit 12 does not basically take into account the influence of the user's non-genetic factors. This is because the influence of the user's non-genetic factors on the incidence rate of the disease is taken into account by the non-genetic model described later. However, it is known that the estimation result of the disease risk based on SNPs varies greatly depending on the combination with the user's non-genetic factors (see, for example, Reference 4). For example, FIG. 3 is a diagram showing the relationship between SNP1 of alcohol dehydrogenase (ADH), SNP2 of acetaldehyde dehydrogenase ALDH2, and the lifestyle of drinking or smoking, which are related to the onset of esophageal cancer. As can be seen from FIG. 3, the disease risk of a user who has a lifestyle of drinking or smoking is much larger than the disease risk estimated based on SNPs. Therefore, the genetic model generating unit 12 may be configured to estimate the disease risk by combining SNPs with the user's non-genetic factors in order to estimate a more accurate disease risk.

[0033] The genetic model generating unit 12 registers information indicating the correlation between the disease and the genetic information created based on such a method as a genetic model in a database. It can be said that the relationship between the genetic information and the disease risk has been modeled up to this point. By inputting the genetic information of a user whose disease risk is to be estimated into the genetic model thus obtained, the disease risk of the user can be estimated. The construction of the genetic model and the estimation using the genetic model may be performed separately.

[0034] FIG. 4 is a diagram showing a specific example of a method for generating a non-genetic model in the first embodiment. For example, the non-genetic model generating unit 13 in the first embodiment generates a non-genetic model for estimating a user's constitution using a machine learning technique. For example, FIG. 4(A) shows a learning method in the case of using a neural network as an example of a learning model by machine learning. The presence or absence of a disease and symptoms are often reflected in the results of a medical checkup, and the tendency to develop a disease is greatly influenced by the non-genetic factors of the person. Therefore, the non-genetic model generating unit 13 learns the relationship between a person's non-genetic factors (parameters 1 to N) and the incidence rate of each disease (Y1 to YM).

[0035] Specifically, a set of sample data is prepared by associating information indicating a non-genetic factor (explanatory variable) with information indicating the incidence rate of each disease in a group having the non-genetic factor (objective variable), and a set of sample data obtained by classifying the sample data into non-genetic factors is prepared as learning data. The non-genetic model generating unit 13 applies the learning data thus prepared to a neural network learning model to generate a neural network describing the relationship between the explanatory variable and the objective variable as a learned model. The non-genetic model generating unit 13 outputs the learned model thus generated to the constitution estimating unit 14. By inputting the non-genetic information of the user to the non-genetic model thus generated (learned model), the incidence rate of each disease for the user can be estimated. The machine learning method is not limited to the above-mentioned neural network. For example, the machine learning method may use other learning models such as GP (Genetic Programming), or a statistical analysis method such as multivariate analysis.

[0036] Here, the medical examination results that may be included in the non-genetic information may include any test results that can be measured in a physical examination, such as blood test results, urine test results, X-ray test results, and electrocardiogram measurement results. In addition, the physical characteristics that may be included in the non-genetic information may include height, weight, BMI (Body Mass Index) value, waist circumference, blood pressure, sex, etc. In addition, the lifestyle habits that may be included in the non-genetic information may include smoking history, smoking amount, drinking history, alcohol amount, average wake-up time, average bedtime, meal times, daily exercise time, and various information indicating work status. In addition, the information indicating work status may include any information indicating the nature and amount of work, such as average work start time, average work end time, average overtime hours, number of days worked on holidays, percentage of desk work in work, type of work, organization to which one belongs and characteristics of the organization.

[0037] FIG. 5 is a diagram showing a specific example of a method for estimating a constitution in the first embodiment. Specifically, the constitution estimation unit 14 estimates the incidence rate of each disease of the user by taking a weighted sum of the incidence rates of the disease obtained from the genetic model generated by the genetic model generation unit 12 and the non-genetic model generated by the non-genetic model generation unit 13. Here, the incidence rate of the disease based on the genetic model is obtained by comparing the genetic information of the user with the genetic model (which shows the correlation between the genetic information and the incidence rate). When the genetic information of the user includes a gene polymorphism that is highly correlated with the disease, a high incidence rate is estimated for the disease. On the other hand, the incidence rate of the disease based on the non-genetic model is obtained by inputting a parameter indicating the non-genetic factor of the user into the trained model. For example, the incidence rate of the disease is calculated by the following formula (4).

[0038]

number

[0039] Here, α is a coefficient for weighting the influence of the genetic model and the non-genetic model (0≦α≦1). The value of α may be determined based on any judgment criterion. For example, the value of α may be determined as a fixed value, or may be determined as a variable value based on the following idea. For example, since genetic factors are considered to be unlikely to change, they are considered to be the basis for constitution estimation regardless of the age of the user. On the other hand, since non-genetic factors are considered to be likely to change depending on timing and the passage of time, factors according to timing are considered to be added to the base of constitution estimation based on genetic factors. For example, habitual drinking and smoking are examples of non-genetic factors, and these lifestyle habits tend to increase the incidence of diseases as the age increases. In this case, it is considered that the value of α is reduced as the age increases so that the influence of non-genetic factors on the incidence rate increases as the age increases.

[0040] On the other hand, it can be assumed that while children are easily influenced by their parents' lifestyle habits, as they become adults, each person chooses an environment that suits their own nature, which tends to amplify the effect of genetic characteristics on the incidence rate. In this case, it is possible to increase the value of α as the age increases. Also, depending on the disease, the degree to which the incidence rate is affected by non-genetic factors may differ. In this case, the value of α may be determined for each disease. In this way, the value of α may be expressed by a function that changes depending on age and type of disease (see, for example, Reference 5). The constitution estimation unit 14 can determine, as individual test items, the test items for diseases whose incidence rates exceed a threshold value among the diseases whose incidence rates have been calculated in this way.

[0041] The incidence rate may be expressed by a relational expression other than formula (4). For example, the incidence rate may be expressed by a nonlinear expression instead of a linear expression like formula (4). Also, for example, the incidence rate may be calculated by a relational expression that directly estimates the final incidence rate by simultaneously considering the influences of genetic factors and non-genetic factors, instead of determining the final incidence rate based on the incidence rate estimated based on genetic factors and the incidence rate estimated based on non-genetic factors, as in formula (4).

[0042] Also, for example, the incidence rate may be obtained by correcting the incidence rate estimated based on genetic factors based on the results of a case-control study on non-genetic factors. For example, for a disease whose incidence rate is expected to be about six times higher than normal due to a specific genetic factor, experimental data has been obtained showing that the incidence rate increases 190 times when the specific genetic factor is combined with a specific lifestyle habit of drinking alcohol and smoking at a predetermined amount or more as a non-genetic factor. In such a case, the constitution estimation unit 14 may be configured to correct the incidence rate of a user having the specific genetic factor according to whether or not the non-genetic factor of the user corresponds to the experimental data.

[0043] Figs. 6 to 8 are diagrams for explaining a method for determining test items in the first embodiment. Among Figs. 6 to 8, Figs. 6 and 7 are diagrams showing a specific example of a method for determining common test items. First, the test item determination unit 15 acquires organizational information and population information from the database 11. As described above, the organizational information is information indicating the incidence rate of each disease in the organization to which the user belongs. Moreover, the population information is information indicating the incidence rate of each disease in the population to which the user belongs. The organizational information and population information are assumed to be registered in advance in the database 11 as information indicating the results of epidemiological surveys on such organizations and populations.

[0044] The population here refers to a group that is larger than the organization to which the user belongs. For example, the population information is information that indicates the incidence rate of each disease in the area (country, prefecture, city, town, village, etc.) in which the user lives. The test item determination unit 15 extracts diseases whose incidence rate in the organization is higher than the general incidence rate in the population based on the organization information and the population information, and determines test items that are effective in detecting the extracted diseases as common test items for the user.

[0045] For example, the examination item determination unit 15 calculates an index value of the susceptibility of each disease in the tissue by the following formula (5), and extracts diseases whose index value exceeds a predetermined threshold. Alternatively, the examination item determination unit 15 may select a predetermined number of diseases in descending order of the index value.

[0046]

number

[0047] The index value may be the standard deviation of the incidence rate in the organization relative to the incidence rate in the population. Information indicating effective test items for each disease is registered in the database 11 in advance.

[0048] The test item determination unit 15 may be configured to take medical expenses into consideration when determining the common test items. For example, assume that the incidence rate of each disease is set as shown in FIG. 7(A), and the cost (medical expenses) required for treating each disease is set as shown in FIG. 7(B). In this case, the test item determination unit 15 may calculate the weighted sum of the incidence rate and medical expenses as the index value, as shown in the following formula (6). Formula (6) is an example of a formula for calculating the index value when the target disease is "gingivitis / periodontal disease."

[0049]

number

[0050] Here, the "medical expenses" shown in FIG. 7(B) is a normalized value to obtain a weighted sum with the incidence rate. For example, the value of "medical expenses" is the medical expenses for each disease divided by the maximum medical expense among all diseases. Also, β and γ in equation (6) are coefficients for adjusting the weights of the incidence rate and medical expenses. β and γ may be arbitrarily determined depending on how much weight is placed on either the incidence rate or the medical expenses.

[0051] Furthermore, the test item determination unit 15 may include the test items for the following diseases in the common test items without comparing the test items with the population. -Diseases included in receipts issued in the past to the user's organization, or among those diseases, diseases with a large number of patients. By including such diseases as common test items, it is possible to prioritize test items for diseases that are likely to occur in the user's organization.

[0052] Diseases that are estimated to have a high incidence rate based on the results of an epidemiological survey conducted by the Ministry of Health, Labor and Welfare and the average age of the organization. This is because the incidence rate of each disease throughout the organization tends to increase as the organization ages. For example, the test item determination unit 15 may use the average age of the organization as an index, and when the index exceeds a threshold based on the results of an epidemiological survey, include the test items of the disease that is the subject of the epidemiological survey in the common test items.

[0053] -Diseases that are determined to be likely to occur based on the statistical value of the incidence rate estimated from the genetic or non-genetic model of members of the organization. In this way, data that is mainly used to determine individual test items may be used to determine common test items. In particular, non-genetic factors are considered to be likely to be similar among members of the organization.

[0054] 8 is a diagram showing a specific example of a method for determining individual test items in the first embodiment. In general, some diseases have different possibilities of onset depending on age (see, for example, Reference 6). Therefore, it is desirable to suppress an increase in the test cost by performing tests for diseases that are likely to occur at a user's age and not performing tests for diseases that are unlikely to occur. Therefore, first, for each disease that is estimated to have a relatively high incidence rate by the constitution estimation unit 14, the test item determination unit 15 acquires the age at which the disease becomes likely to occur (hereinafter referred to as "onset age") based on the results of an epidemiological survey.

[0055] FIG. 8 is a diagram showing the results of an epidemiological survey used in identifying this age (see, for example, Reference 7). Specifically, FIG. 8 is a diagram showing the results of a survey on the transition of the incidence rate of oral cancer and pharyngeal cancer with age. As can be seen from FIG. 8, the incidence rate of oral cancer and pharyngeal cancer increases sharply from around age 45 in men, and gradually increases from around age 30 in women. The results of such epidemiological surveys on each disease are preregistered in the database 11. In this case, the examination item determination unit 15 specifies the target disease and obtains the survey results of the disease from the database 11, and can identify the age at which the gradient of the incidence rate curve indicated by the survey results exceeds a predetermined threshold as the age of onset.

[0056] Information indicating the age at onset of each disease identified based on the results of an epidemiological survey may be preregistered in the database 11. In this case, the test item determination unit 15 can acquire the age at onset of the disease from the database 11 by specifying the target disease.

[0057] Based on the onset age of each disease thus obtained, for diseases whose onset age exceeds the user's age, the examination item determination unit 15 extracts examination items effective for detecting the disease as individual examination items. For example, in the example of Fig. 8, if the male user's age is 50 years old, the examination item determination unit 15 includes examination items for oral and pharyngeal cancer as individual examination items, and if the user's age is 40 years old, excludes the examination items from the individual examination items.

[0058] In addition, the test item determination unit 15 may include the test items of a disease with a relatively high incidence rate among the diseases whose incidence rates are estimated by the constitution estimation unit 14 in the individual test items regardless of the user's age. In this case, a threshold value of the incidence rate may be determined in advance as a criterion when selecting diseases according to age. The test item determination unit 15 outputs the common test items and individual test items determined in this way as the test items for the user.

[0059] The clinical test item determination device 1 of the first embodiment configured in this way can determine the items of clinical tests to be performed on the user from both the possibility of disease onset based on the organization to which the user belongs and the possibility of disease onset based on the user's genetic factors and / or non-genetic factors. By proposing the test items determined in this way to the user or the organization to which the user belongs, it becomes possible to promote health management more in line with individual characteristics. The clinical test items may be determined using the disease onset rates based on the organization to which the user belongs, the user's genetic factors, and the user's non-genetic factors, respectively, individually, or two or all of them may be combined to determine the clinical test items.

[0060] The locations of the reference documents introduced in the first embodiment are listed below. Reference 1: http: / / www.riken.jp / pr / press / 2010 / 20100212 / , "Discovery of gene 'ACACB' related to diabetic nephropathy." Reference 2: https: / / www.rgare.com / docs / default-source / subsite-materials / japan-reflections / reflections-vol-45.pdf, "Polygenic Risk Score (PRS): Integrating thousands of genetic variants to predict disease." Reference 3: https: / / mycode.jp / benefits / basis.html, "Quality of scientific evidence." Reference 4: https: / / biobankjp.org / cohort_1st / public / tsushin07 / biobank_tsushin07 _02.html, "Looking into the relationship between alcohol, tobacco and esophageal cancer." Reference 5: https: / / dot.asahi.com / aera / 2019072400072.html?page=1, "87% of math, 66% of IQ, and 59% of income are influenced by genetics! What are the surprising results of the latest research?" Reference 6: https: / / ganjoho.jp / reg_stat / statistics / stat / summary.html, "Latest Cancer Statistics." Reference 7: Cancer Registration and Statistics, Cancer Information Services, National Cancer Center, Japan.

[0061] In this embodiment, a configuration has been described in which the test items of a user are determined based on both the user's constitution and the organization to which the user belongs, but the clinical test item determination device 1 of the embodiment may be configured to determine the test items based on either the constitution or the organization to which the user belongs.

[0062] The clinical test item determination device 1 may be configured to include an individual test item determination unit that determines individual test items from among predetermined test items, and a common test item determination unit that determines common test items from among the predetermined test items. In this case, the test item determination unit 15 may be configured to determine test items for each user based on the individual test items determined by the individual test item determination unit and the common test items determined by the common test item determination unit.

[0063] In addition, the clinical test item determination device 1 in the first embodiment selects test items as individual test items for diseases that are estimated to have a high possibility of onset based on both the incidence rate and the results of the epidemiological survey. This can be said to be a method of estimating a high possibility of onset based on the AND condition of the incidence rate and the results of the epidemiological survey. In contrast, the clinical test item determination device 1 may be configured to select test items as individual test items for diseases that are estimated to have a high possibility of onset based on both the incidence rate and the results of the epidemiological survey. Specifically, the clinical test item determination device 1 first selects diseases for which the user's age exceeds the onset age based on the results of the epidemiological survey, and selects these test items as individual test items. In addition to this, the clinical test item determination device 1 selects diseases with a high incidence rate based on the genetic information of the user, and selects these test items as individual test items. In this way, the clinical test item determination device 1 can select more test items based on the OR condition of the incidence rate and the results of the epidemiological survey, and can perform thorough tests by covering test items appropriate for age and test items with individual differences.

[0064] The clinical test item determination device 1 may have liquid biopsy as one of the options for the test item. Liquid biopsy is a test method that has attracted attention in recent years because it is capable of diagnosing multiple cancers at once. However, the types of cancer that can be detected by liquid biopsy vary depending on the method. Therefore, the clinical test item determination device 1 may be configured to select, as a test item, a liquid biopsy corresponding to a cancer that is estimated to have a high incidence rate. This makes it possible to determine a method that can test for cancer efficiently and effectively.

[0065] <Second embodiment> FIG. 9 is a block diagram showing a specific example of a functional configuration of the health behavior support device 2 in the second embodiment. The clinical test item decision device 1 in the first embodiment has a function of deciding items of clinical tests to be performed on the user, whereas the health behavior support device 2 in the second embodiment has a function of supporting the user's actions to promote health (hereinafter referred to as "health behavior"). The health behavior support device 2 includes a CPU, a memory, an auxiliary storage device, and the like connected by a bus, and executes a program. The health behavior support device 2 functions as a device including a database 21, a mission setting unit 22, a mission management application selection unit 23, an application utilization degree determination unit 24, and an action content determination unit 25 by executing the program. The health behavior support device 2 is communicably connected to a user terminal 3 used by each user. Here, the user terminal 3 is an electronic device capable of executing a health application described later. For example, the user terminal 3 is an information processing device such as a smartphone, a mobile phone, a tablet, or a personal computer.

[0066] All or part of the functions of the health behavior support device 2 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The program may be recorded on a computer-readable recording medium. Examples of computer-readable recording media include portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, and storage devices such as hard disks built into a computer system. The program may be transmitted via an electric communication line.

[0067] The database 21 is a database that stores various information necessary to support the health behavior of each user. In response to requests from other functional units, the database 21 registers various data, deletes registered data, and provides requested data.

[0068] The mission setting unit 22 (recommended behavior setting unit) has a function of setting recommended health behaviors for each user according to their respective genetic constitutions. Hereinafter, the health behaviors set for each user will be referred to as "missions." Each user installs an application program (hereinafter referred to as "health app") corresponding to the mission set for that user on the user terminal 3, and manages the missions using the health app. The health app may provide a certain incentive corresponding to the mission to a user who completes the mission.

[0069] Mission management application selection unit 23 selects a health application (hereinafter referred to as a "mission management application") that supports management of the set mission for each user for whom a mission has been set by mission setting unit 22. Mission management application selection unit 23 installs the health application selected as the mission management application in user terminal 3. Note that mission management application selection unit 23 may only notify user terminal 3 of the health application selected as the mission management application, and leave it to the user to decide whether or not to install the health application.

[0070] The application utilization level determination unit 24 has a function of determining the utilization level of a health application installed as a mission management application in each user terminal 3. The utilization level of the mission management application is an index for measuring the user's activity level for the set mission. The application utilization level determination unit 24 plays a role in improving the user's motivation to perform health behavior for the set mission by notifying the user terminal 3 according to the determined application utilization level.

[0071] The behavior content determination unit 25 has a function of determining the content of health behavior actually performed by the user. Specifically, the behavior content determination unit 25 acquires information on the health behavior performed by each user from each user terminal 3 (hereinafter referred to as "behavior information") via a health app, and determines the appropriateness of the performed health behavior based on the acquired behavior information. The behavior content determination unit 25 notifies the user terminal 3 according to the appropriateness of the health behavior performed by the user. In this way, the behavior content determination unit 25 plays a role in improving the quality of the health behavior performed by the user and increasing the motivation of the user to perform higher quality health behavior.

[0072] 10 is a diagram showing a specific example of a method for setting a mission in the second embodiment. First, the mission setting unit 22 acquires genetic information of the user from the database 21, and identifies genes possessed by the user based on the acquired genetic information. The mission setting unit 22 selects a mission for promoting the health of the user having a constitution suggested by the identified genes, and notifies the mission management application selection unit 23 of the selected mission. It is assumed that the genetic information of each user is registered in the database 21 in advance.

[0073] In addition, when information such as a medical questionnaire is acquired in advance, the mission setting unit 22 may be configured to filter the selected missions based on the information. For example, there is a possibility that the health behavior to be set as a mission has already been performed by the user. In such a case, if the health behavior already performed by the user can be grasped from the information such as a medical questionnaire, it is possible to avoid setting unnecessary health behaviors as missions for such a user. For example, it is possible to avoid setting the health behavior "refrain from smoking" for a user who has a risk of lung cancer but has never smoked. Such filtering has the effect of enabling a user who is recommended many health behaviors as missions to more easily grasp the recommended health behaviors.

[0074] Specifically, the genetic constitution information shown in FIG. 10 is registered in the database 21 in advance. The genetic constitution information is information indicating a correspondence relationship between a constitution suggested by a specific gene polymorphism and a health behavior that is desirable to be performed for that constitution. For example, the genetic constitution information in the example of FIG. 10 indicates that since a person having a gene polymorphism of β3AR tends to have a weak carbohydrate metabolism function, it is desirable to actively take vitamin B1 that promotes carbohydrate metabolism. When the user has any of the gene polymorphisms included in the genetic constitution information from the acquired genetic information, the mission setting unit 22 sets the health behavior associated with the gene polymorphism as the mission of the user. In addition, the mission setting unit 22 notifies the mission management application selection unit 23 of the behavior classification together with the set mission for setting a health application in the later stage.

[0075] Note that constitutions suggested by gene polymorphisms are not limited to those exemplified in Figure 10. It is desirable that genetic constitution information be updated from time to time with reference to research results on the relationship between gene polymorphisms and constitutions. For example, if in the future research clarifies the relationship between gene polymorphisms and constitutions related to lifestyle, such as tolerance to work load, quality of sleep, and affinity with clothing, health behaviors that promote health for these constitutions should be added to the genetic constitution information.

[0076] Fig. 11 is a diagram showing a specific example of a method for selecting a health application in the second embodiment. First, mission management application selection unit 23 acquires correspondence information indicating the correspondence between behavior categories and health applications from database 21, and selects a health application corresponding to the behavior category notified from mission setting unit 22 as a mission management application based on the acquired correspondence information. Mission management application selection unit 23 installs the selected mission management application in user terminal 3. Note that the correspondence information is assumed to be registered in database 21 in advance. Below, a diet management application and an exercise assistance application illustrated in Fig. 11 will be described as specific examples of health applications selected as mission management applications.

[0077] (1) Food management app As described above, people with the gene polymorphism "β3AR" tend to have a weak carbohydrate metabolism function. Such a constitution is a constitution that has a risk of easily gaining visceral fat (see, for example, Reference 7). Therefore, for people with such a constitution, a mission of healthy behavior is set to take more vitamin B1 than the standard, which supports carbohydrate metabolism. Therefore, as a mission management app for such a mission, a diet management app having a function of evaluating the intake of vitamin B1 is selected. For example, the diet management app has a function of analyzing image data of a dish eaten by a user, estimating the amount of vitamin B1 contained in the dish, and transmitting the estimated value to the health behavior support device 2. The diet management app may be configured to transmit image data to a server having an image data analysis function and obtain the analysis result of the image data from the server.

[0078] (2) Exercise support apps People with the S / S type of the gene polymorphism "PPARGC1A" tend to have a low increase in mitochondria through exercise and a weak function of energy production through exercise. Such a constitution is not suitable for endurance-requiring exercise that consumes a lot of energy (see, for example, Reference 8). Therefore, for people with such a constitution, a mission of healthy behavior is set to perform light exercise such as walking for a long period of time. Therefore, an exercise support application having a function of evaluating walking time is selected as a mission management application for such a mission. For example, the exercise support application has a function of acquiring measurement information of the amount of activity from an activity meter worn by the user and transmitting the acquired measurement information to the health behavior support device 2.

[0079] Note that the health behaviors that can be missions are not limited to those exemplified in Figure 10. Below, we will list some health behaviors that can be missions other than those exemplified in Figure 10 from the perspectives of exercise, weight, drinking, smoking, sleep, lifestyle rhythm, diet, and non-alcoholic beverages (e.g., coffee, tea).

[0080] [motion" Walk for at least 1 hour a day Walk for at least 7 hours a week [body weight] Don't gain too much weight Not too skinny [Drinking] · Avoid heavy drinking Avoid beer Avoid wine [coffee] Drink coffee every day Don't drink too much coffee [tea] Don't drink too much green tea Drink green tea Avoid hot tea [Tobacco] -Do not smoke Refrain from smoking immediately after waking up [sleep] Don't shorten your sleep time too much Don't sleep too long [Life rhythm] Don't work too long Avoid night shifts Avoid shift work [meal] Don't eat too many oranges · Take calcium and vitamin D Eat lots of tomatoes Eat nuts, fish and fruit vegetables Get plenty of Vitamin C · Limit fat intake ·Getting magnesium from food Limit soy and milk intake Eat a lot of soybeans · Limit carbohydrates Eat meat often · Eat lots of dairy products

[0081] FIG. 12 is a flowchart showing a specific example of a method for determining the application utilization level in the second embodiment. First, the application utilization level determination unit 24 acquires recommended frequency information of the mission management application selected for the user from the mission management application installed in the user terminal 3 (step S101). The recommended frequency information is information indicating a recommended frequency of use (hereinafter referred to as "recommended frequency of use") for each health application. The recommended frequency of use is the number of times or the duration of use of the mission management application in a predetermined unit period (for example, one day or one week). For example, the number of times of use may be the number of times the mission management application is started. The number of times of use may be the number of times a predetermined function is used in the mission management application. In addition, for example, the duration of use may be the time during which the mission management application is started. The duration of use may be the time during which the mission management application is operating in the foreground. Such a recommended frequency of use is preset to a frequency of use that allows the user to appropriately manage health activities to accomplish a mission.

[0082] Note that, although the recommended frequency information is assumed to be held in each health app here, the use frequency information may be registered in advance in the database 21. The recommended use frequency may be set for each health app, or may be set for each combination of a health app and a mission.

[0083] Next, the application utilization level determination unit 24 acquires from the user terminal 3 usage history information indicating a history of the user's use of the mission management application (step S102). Based on the acquired usage history information, the application utilization level determination unit 24 acquires the frequency at which the user actually used the mission management application (hereinafter referred to as "actual usage frequency") (step S103), and determines whether the actual usage frequency is equal to or greater than the recommended usage frequency (step S104). In order to compare the actual usage frequency with the recommended usage frequency, the usage history information only needs to include the actual usage frequency of the mission management application in a predetermined unit period, or information that allows the actual usage frequency to be ascertained.

[0084] In step S104, if the actual usage frequency is less than the recommended usage frequency (step S104-NO), the application utilization level determination unit 24 transmits a notification to the user terminal 3 to encourage further use of the mission management application (step S105). Instead of transmitting the notification to the user terminal 3, the application utilization level determination unit 24 may notify the user by displaying the notification on a health application or by sending an e-mail. In addition, in the case where a portal site for each user is provided as an example of a user interface provided by the health action support device 2 via the web, the application utilization level determination unit 24 may display the notification on a screen generated by each user logging in to the portal site.

[0085] In this case, the application utilization level determination unit 24 may notify the user of information indicating how much the actual usage frequency is short of the recommended usage frequency. On the other hand, in step S104, if the actual usage frequency is equal to or greater than the recommended usage frequency (step S104-YES), the application utilization level determination unit 24 gives the user a certain number of points as a reward for steadily completing the mission (step S106).

[0086] For example, when managing a user's meal-related missions using a meal management app, it is possible to set the recommended frequency of use to "3 times / day" corresponding to the three meals of breakfast, lunch, and dinner. In this case, if the actual frequency of use of the meal management app is 3 or more times / day, the app utilization determination unit 24 will give points to the user and send a message such as "You've earned points!" to the user terminal 3. On the other hand, if the actual frequency of use of the meal management app is 0 to 2 times / day, the app utilization determination unit 24 will send a message such as "Enter data into the app!" to the user terminal 3 as a notification encouraging further use of the meal management app.

[0087] FIG. 13 is a flowchart showing a specific example of a method for determining activity content in the second embodiment. Here, a method related to a dietary management app will be described as an example of a method for determining activity content. In this example, it is assumed that the user has registered image data of the food he or she has eaten (hereinafter referred to as "dietary image data") in the dietary management app as activity information in advance. In this case, the activity content determination unit 25 first acquires the dietary image data registered by the user from the user terminal 3 (step S201). The activity content determination unit 25 estimates the amount of calories and nutrients ingested by the user by analyzing the acquired dietary image data (step S202). For example, the technology described in Reference 9 can be used for such analysis of dietary images.

[0088] Next, the behavior content determination unit 25 acquires information regarding the mission set for the user (hereinafter referred to as "mission information") (step S203). The mission information is registered in the diet management app or database 21 of the user terminal 3 by the mission setting unit 22 when a mission is set for the user. Specifically, the mission information includes the health behavior set as the mission and a target value for the health behavior.

[0089] For example, in the example of FIG. 10, when the active intake of vitamin B1 is set as a mission for a user having the gene polymorphism "β3AR", the health behavior and the range of intake of nutrients (here, vitamin B1) and calories targeted in the health behavior (hereinafter referred to as "target range") are included. The target range may be defined in advance in association with the genetic constitution information exemplified in FIG. 10, or may be customized for each user in combination with the user's other constitutions. The behavior content determination unit 25 identifies the mission set for the user based on the acquired mission information (step S204), and specifies the target values ​​of the intake of calories and nutrients set for the mission (step S205).

[0090] Next, the activity content determination unit 25 determines whether the amount of calories and nutrients taken by the user (hereinafter simply referred to as "intake amount") is less than the lower limit of the target range (step S206). Here, the intake amount is obtained by analyzing the meal image data in step S202. In step S206, if the intake amount is less than the lower limit of the target range (step S206-YES), the activity content determination unit 25 notifies the user terminal 3 that the intake of calories and nutrients is insufficient (an example of advice) (step S207).

[0091] On the other hand, if the intake amount is equal to or greater than the target value in step S206 (NO in step S206), the activity content determination unit 25 determines whether or not the intake amount is equal to or less than the upper limit of the target range (step S208). If the intake amount is equal to or less than the upper limit of the target range in step S208 (YES in step S208), the activity content determination unit 25 gives a certain number of points to the user as a reward for steadily completing the mission (step S209). On the other hand, if the intake amount exceeds the upper limit of the target range in step S208 (NO in step S208), the activity content determination unit 25 notifies the user terminal 3 that the intake of calories and nutrients is excessive (an example of advice) (step S210).

[0092] Note that, although the case has been described where whether or not to award points is determined based on whether both calories and nutrients are within the target range, whether or not to award points may be determined separately for calories and nutrients.

[0093] According to the health behavior support device 2 of the second embodiment configured in this way, it is possible to promote health management that is more in line with individual characteristics. Specifically, it has been conventionally practiced to suggest health behaviors for health promotion to users, but in conventional methods, the suggested health behaviors were set uniformly and did not reflect the individual characteristics of the users. For this reason, there was a possibility that the suggested health behaviors were not necessarily effective for individual users.

[0094] In contrast, the health action support device 2 of the second embodiment can set health actions (missions) recommended for the user's health promotion according to the user's genetic constitution, and quantitatively monitor the user's behavioral status for the set missions. In addition, the health action support device 2 of the second embodiment can reward the user according to the user's behavioral status for the missions, and encourage the user to change his / her behavior. This allows the user to efficiently and effectively promote or maintain health according to his / her own constitution. In addition, since the genetic constitution is not necessarily recognized by the user, by executing a mission determined based on the genetic nature, the user can reduce health risks due to constitutions that the user is not aware of.

[0095] The locations of the reference documents introduced in the second embodiment are listed below. Reference 7: https: / / with-aging.com / column / 2258 / Reference 8: https: / / med.fjtex.co.jp / products / gene / exercise / Reference 9: https: / / www.asken.jp /

[0096] In the first and second embodiments, the health action support device 2 is configured as one device. However, the health action support device 2 may be implemented using a plurality of information processing devices communicably connected via a network. In this case, each functional unit of the health action support device 2 may be distributed and implemented in a plurality of information processing devices. For example, the database 11, the genetic model generation unit 12, the non-genetic model generation unit 13, the constitution estimation unit 14, and the test item determination unit 15 may be implemented in different information processing devices. In addition, for example, the database 21, the mission setting unit 22, the mission management application selection unit 23, the application utilization level determination unit 24, and the behavior content determination unit 25 may be implemented in different information processing devices. By adopting such a configuration, the health action support device 2 can be configured as a so-called cloud system.

[0097] For example, a configuration in which a mission setting unit on a cloud server sets a mission for each user, and a mission management app selected in response to the mission is installed on the user terminal and data is linked to the cloud server is one example of a configuration in which the mission management app obtains information indicating the evaluation results of the app utilization level and the action content from the app utilization level determination unit and the action content determination unit on the cloud server, and notifies the user.

[0098] Although an embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and designs that do not deviate from the gist of the present invention are also included. [Industrial Applicability]

[0099] The present invention can provide means to support the management, support or promotion of health to organizations such as companies that manage or support the health of their members, various medical institutions that manage or support the health of patients, and individuals who wish to manage or promote their own health. [Explanation of symbols]

[0100] 1... clinical test item determination device, 11... database, 12... genetic model generation unit, 13... non-genetic model generation unit, 14... constitution estimation unit, 15... test item determination unit, 2... health behavior support device, 21... database, 22... mission setting unit, 23... mission management application selection unit, 24... application utilization level determination unit, 25... action content determination unit, 3... user terminal

Claims

1. A recommended behavior setting unit sets, for the user, a health behavior that is a recommended behavior for improving the health of the user based on the genetic information of the user; an application selection unit that selects an application program executable on an electronic device used by the user, the application program being for supporting the user in implementing the health behavior in accordance with the health behavior set for the user; Equipped with The recommended behavior setting unit identifies a behavior category corresponding to the health behavior set for the user from a database that stores correspondence information between health behaviors and behavior categories, The application selection unit selects, based on the identified behavior category, a health application corresponding to the health behavior set for the user from a database that stores correspondence information between the behavior category and the health application. Health behavior support device.

2. an application utilization level determination unit that determines a utilization level of the application program by the user; a behavior content determination unit that notifies the user of advice regarding the health behavior or gives the user a reward according to the health behavior performed according to a degree of utilization of the application program; Further comprising: The health behavior support device according to claim 1 .

3. A computer comprising: A recommended behavior setting step of setting, for the user, a health behavior that is a behavior recommended for improving the health of the user based on the genetic information of the user; an application selection step of selecting an application program executable on an electronic device used by the user, the application program being for supporting the user in implementing the health behavior, in accordance with the health behavior set for the user; A health behavior support method for carrying out the above steps, In the step of setting the recommended behavior, a behavior classification corresponding to the health behavior set for the user is identified from a database that stores correspondence information between health behaviors and behavior classifications; In the application selection step, a health application corresponding to the health behavior set for the user is selected from a database that stores correspondence information between the behavior classification and the health application based on the identified behavior classification. Health behavior support methods.

4. A computer program for causing a computer to function as the health action support device according to claim 1 or 2.

Images