Information processing device, information processing method and program for supporting health care projects

Abstract

Provides useful information to insurers and other entities involved in health care services to take effective measures. [Solution] The program disclosed herein is a program that causes a computer to function as each means of an information processing device that supports health care projects, and the information processing device comprises: a prediction means that predicts the health risk of each of a plurality of subjects based on the health information of the subjects; an evaluation means that divides the plurality of subjects into two or more groups in relation to health care project measures, determines the health risk of each of the two or more groups, and evaluates the health risks of the two or more groups; and a presentation information generation means that generates presentation information to present to a user the effects of the health care project measures using the evaluation means.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program for supporting health care services. [Background technology]

[0002] Based on the guidelines for formulating data health plans provided by the Ministry of Health, Labor and Welfare, insurers (such as national health insurance associations, health insurance associations, and insurers under the Medical Care System for the Elderly, hereafter referred to as "insurers") are required to formulate common evaluation indicators and describe methods for setting and achieving goals for outcomes, etc. (Non-Patent Documents 1-3). Examples of outcomes include the implementation rate of specific health checkups, the implementation rate of specific health guidance, the reduction rate of people receiving specific health guidance due to specific health guidance, the proportion of people with an HbA1c of 8.0% or higher, the proportion of people who have exercise habits, and the proportion of young elderly people with a BMI of 20 kg / m 2 The percentage of people with good mastication is as follows:

[0003] Patent document 1 proposes a system that creates a model based on health checkup information including health checkup measurement values ​​and prescription information including medical expenses and disease names, and extracts subjects at high risk of developing the disease based on the subjects' health checkup information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-3882 [Non-patent literature]

[0005] [Non-Patent Document 1] Ministry of Health, Labour and Welfare, "Guidelines for Creating Data Health Plans (3rd revised edition) June 2023"<URL= https: / / www.mhlw.go.jp / content / 12400000 / 001223896.pdf> [Non-patent document 2] Ministry of Health, Labour and Welfare, "Guidelines for Developing Implementation Plans for National Health Insurance Programs (Data Health Plans) (revised May 18, 2023)"<URL= https: / / www.mhlw.go.jp / content / 12401000 / 001093634.pdf> [Non-patent document 3] Ministry of Health, Labour and Welfare, "Guidelines for Developing Implementation Plans for Elderly Health Care Programs (Data Health Plans) (revised March 30, 2023)"<URL= https: / / www.mhlw.go.jp / content / 12401000 / 001080623.pdf> Summary of the Invention [Problem to be solved by the invention]

[0006] The system proposed in Patent Document 1 can identify high-priority subjects for health guidance. However, it was not possible to quantitatively evaluate to what extent achieving outcomes would extend the average period of independence for subscribers, to what extent medical expenses related to lifestyle-related diseases and nursing care benefits could be optimized, or to what extent the onset and progression of dementia could be prevented, and to present effective measures that insurers operating health insurance programs should take.

[0007] The present invention has been made in view of the above-mentioned problems, and its purpose is to realize a technology that can provide useful information to insurers and others who run health care businesses so that they can take effective measures. [Means for solving the problem]

[0008] In order to solve this problem, for example, a program according to the present disclosure is a program that causes a computer to function as each means of an information processing device that supports health projects, and the information processing device includes a prediction means that predicts the health risk of each of a plurality of subjects based on the health information of the plurality of subjects, and a health project For each of the multiple measures, The plurality of subjects , including at least a group in which the one measure has been implemented and a group in which the measure has not been implemented.Dividing the subjects into two or more groups, determining the health risk of each of the two or more groups based on the health risk of each of the plurality of subjects predicted by the prediction means, and calculating the health risk of the two or more groups. The effect of one of the measures is calculated based on the difference or ratio. an evaluation means for evaluating; Evaluation results by the evaluation means for each of the plurality of measures for the health care business of Visualize it and a presentation information generation means for generating presentation information to be presented to the user, wherein the prediction means predicts health risks using a prediction model that learns from health information of subjects whose health status has changed from one period to the next. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide useful information for insurers and others who carry out health care services to take effective measures. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing an example of a health care project support system according to an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram showing an example of the functional arrangement of an information processing apparatus according to an embodiment. [Figure 3] FIG. 2 is a block diagram showing an example of the functional configuration of a terminal device according to the embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of the functional configuration of a health information database according to the embodiment. [Figure 5] 1 is a flowchart showing a series of processes related to health care project support according to an embodiment. [Figure 6] 1 is a flowchart showing a process for generating a prediction model according to an embodiment. [Figure 7] FIG. 10 is a diagram illustrating a process for generating a prediction model according to the embodiment. [Figure 8] FIG. 10 is a diagram illustrating the operation of a prediction model according to the embodiment. [Figure 9] 10 is a flowchart showing a process for evaluating the effectiveness of a health care project according to the embodiment. [Figure 10] FIG. 10 is a diagram for explaining the improvement in nursing care risk before and after improvement through a health care project according to an embodiment. [Figure 11] 10 is a setting screen for evaluating the effectiveness of a health project according to an embodiment. [Figure 12] 10 is a presentation screen showing the effects of a health project according to an embodiment. [Figure 13] 10 is a presentation screen visualizing the effect of extending the average period of independence for each goal of a health project in a certain region according to an embodiment. [Figure 14] 10 is a presentation screen that visualizes the effect of health guidance for each individual according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Furthermore, the same reference numerals are used for the same or similar components, and redundant explanations will be omitted.

[0012] <Configuration of the health business support system> The configuration of a health care project support system according to an embodiment of the present invention will be described with reference to Figure 1. The health care project support system 100 includes, for example, an information processing device 101, a database 102, and a terminal device 103 used by a user. Here, the user is assumed to be an employee of an insurer or the like, but is not limited to this. The information processing device 101, the health care information database 102, and the terminal device 103 are communicably connected via a network 104. The network may be any network, such as a LAN, a WAN, or the Internet. All or part of the network may be connected via wireless communication.

[0013] <Configuration of information processing device> The information processing device 101 is, for example, a server managed by an insurer or a server managed by a company that provides health data services to insurers. In the following explanation, no distinction is made between insurers, local governments, and service providers, and they will all be referred to as insurers, etc.

[0014] The terminal device 103 is, for example, a user terminal that an insurer or the like uses to access the information processing device 101 when obtaining information related to health guidance. In this embodiment, an example will be described in which the terminal device 103 is, for example, a desktop computer. However, the terminal device 103 is not limited to a desktop computer, and may be any other device that can access the information processing device 101, such as a laptop computer, a tablet terminal, or a smartphone.

[0015] The health information database 102 is a database that stores data related to various types of health information. Examples of health information include medical checkup data, medical treatment data, prescription data, and nursing care certification data, but it does not have to include all of these, and may also include other information. There may be multiple health information databases 102 for each type of data, or there may be only one. The health information database 102 may be owned by an insurer or other organization. It may be the health information database (NDB) of health insurance receipt information and specific health checkup information provided by the Ministry of Health, Labor and Welfare, a database (such as KDB) owned by an examination and payment organization (such as the Social Insurance Medical Fee Payment Fund, the National Health Insurance Association, and the National Health Insurance Federation), or another database owned by a private company. The information processing device 101 may also have a database.

[0016] <Functional configuration of information processing device> Next, an example of the functional configuration of the information processing device 101 will be described with reference to Fig. 2. Note that each of the functional blocks described may be integrated or separated, and the functions described may be realized by different blocks. Also, what is described as hardware may be realized by software, and vice versa.

[0017] The communication unit 201 includes a communication circuit that communicates with various devices via a network. The communication unit 201 receives information processed by the control unit 204 from a communication partner device (e.g., the terminal device 103, etc.), and transmits information processed by the control unit 204 to the communication partner device (e.g., the terminal device 103). The power supply unit 202 is a power supply that provides power required for the operation of the information processing device 101.

[0018] The storage unit 203 includes a non-volatile storage medium such as a hard disk or semiconductor memory, and stores various programs executed by the control unit 204 of the information processing device 101, various data used by the control unit 204, and a DB 230. The various programs include an operating system, frameworks, libraries, and the like, as well as a program for executing support for health care projects according to this embodiment. The various data include, for example, setting values ​​of the information processing device 101, data acquired from the health information database 102, data related to prediction models, learning data, and prediction result data. The storage unit 203 also stores parameters for each prediction model. Data acquired from the health information database 102 may be stored in the DB 230.

[0019] The control unit 204 includes a CPU 210, which is a central processing unit, and a RAM 211. The control unit 204 controls the operation of each unit within the control unit 204 and the operation of each unit of the information processing device 101 by expanding and executing a program stored in the storage unit 203 into the RAM 211. The control unit 204 also predicts and evaluates the effects of health care projects, which will be described later.

[0020] The RAM 211 includes a volatile storage medium such as a DRAM, and temporarily stores parameters and processing results for the control unit 204 to execute programs.

[0021] The control unit 204 has functional blocks that are implemented by the CPU 210 reading out a program stored in the storage unit 203 into the RAM 211. The control unit 204 has functional blocks of a prediction model unit 220, an evaluation unit 221, a learning unit 222, a data acquisition unit 223, a user interface (IF) unit 224, and a presentation information generation unit 225.

[0022] The prediction model unit 220 uses a prediction model to predict the future health status of an individual. For example, the nursing care risk prediction model has a function of inputting data from the health information database 102 into the prediction model and outputting the nursing care risk (probability) for the next year.

[0023] The evaluation unit 221 evaluates the effectiveness of measures taken by the insurer, etc., based on the prediction results of the prediction model unit 220. For example, it evaluates how much the average future period of independence will be extended and how much medical expenses can be reduced if a person is recommended to undergo a health checkup. The average period of independence is an index of the remaining period for which an independent life can be expected.

[0024] The learning unit 222 learns the prediction model, and generates and learns the prediction model using data acquired from the health information database 102.

[0025] The data acquisition unit 223 acquires data necessary for prediction and evaluation from the health information database 102 or other data sources. The data acquisition unit 223 may store the acquired data in the DB 230 of the storage unit 203.

[0026] The user IF unit 224 functions as an interface with the terminal device 103 of the insurer, etc. The user IF unit 224 displays an input screen and a setting screen on the terminal device 103, and accepts data input from the terminal device 103.

[0027] The presentation information generation unit 225 generates presentation information that visualizes and shows to the user the prediction results from the prediction model and the evaluation of the effectiveness of measures taken by the insurer, etc., by the evaluation unit 221. The generated presentation information is transmitted to the terminal device 103 by the user IF unit 224 and the communication unit 201, and is displayed on the display unit 304 of the terminal device 103.

[0028] <Configuration of terminal device> An example of the functional configuration of the terminal device 103 of the insurer or the like will be described with reference to Fig. 3. Note that each of the functional blocks described may be integrated or separated, and the described functions may be realized by different blocks. Also, what is described as hardware may be realized by software, and vice versa.

[0029] The communication unit 301 includes, for example, a communication circuit, and communicates with the information processing device 101 via mobile communication such as wired LAN or LTE, or via wireless communication such as WiFi, to send and receive the necessary data.

[0030] The operation unit 303 includes buttons and a touch panel provided in the communication device 103, and accepts operations by a user such as an insurer to display information related to health care services. The display unit 304 includes a display panel such as an LCD or OLED, and displays GUIs for various operations. For example, the display unit 304 displays presentation information generated by the presentation information generation unit 225 of the information processing device 101.

[0031] The storage unit 305 includes, for example, a nonvolatile memory such as an HDD or semiconductor memory, and stores programs executed by the control unit 502, etc.

[0032] The control unit 302 includes a CPU 310 and a RAM 311, and controls the operation of each functional block in the control unit 302 and each unit in the communication device 103 by the CPU 310 executing a program recorded in the storage unit 305, for example.

[0033] <Health information database configuration> Next, an example of the functional configuration of the health information database 102 will be described with reference to FIG. 4. The health information database 102 is a database server that stores various types of health information data according to this embodiment. The health information database 102 includes medical checkup data 420, dental examination (dental checkup) data 430, medical treatment data 440, prescription receipt data 450, nursing care certification data 460, and intervention data 470. The health information database 102 does not need to include all of these, and may also include other medical and health-related data. Each piece of data is recorded for each patient (insured person) in association with the date of diagnosis, etc. The medical treatment data 440 and prescription receipt data 450 can be acquired from medical fee receipt data. The medical treatment data 440 can be acquired from medical receipt, dental receipt, and nursing care receipt data. Medical receipts, dental receipts, and nursing care receipts are created for each patient and for each treatment month, separated by inpatient / outpatient status, etc. In recent years, with the use of My Number cards as health insurance cards, prescription data is recorded in association with the My Number (individual number). Therefore, by using the My Number, comprehensive data related to personal medical information can be obtained for each individual, such as health checkup data 420, dental checkup data 430, medical treatment data 440, prescription data 450, and nursing care certification data 460, as well as vital data obtained from wearable devices and electronic medical record data.

[0034] The health information database 102 may also acquire and use data from the Ministry of Health, Labor and Welfare's Health Insurance Claim Information and Specific Health Checkup Information Database (NDB), databases (such as the KDB) owned by screening and payment agencies (such as the Social Insurance Medical Fee Payment Fund, the National Health Insurance Association, and the National Health Insurance Federation), and other databases owned by private companies. The health information database 102 may also be the NDB, the KDB, or other databases owned by private companies. In the NDB, patient (insured) information is anonymized, but different types of patients are linked by the same hash ID. The data acquisition unit 223 of the information processing device 101 may also be configured to access the NDB to acquire data. The learning unit 222 and evaluation unit 221 of the information processing device 101 can use data from the NDB, the KDB, and other databases.

[0035] Each data item will be explained below. Health checkup data 420 is data on health checkups for a certain population. Municipalities and corporate health insurance associations conduct health checkups for their residents and members. The population of health checkup data 420 may be one municipality or one company. The population of health checkup data 420 may also be multiple municipalities or multiple companies. In the following, an example will be described in which the insurer is a company that provides health guidance services and uses health checkup data 420 after obtaining permission to use it from multiple municipalities and multiple health insurance associations. The same applies to the populations of dental checkup data 430, medical treatment data 440, prescription data 450, and nursing care certification data 460 described below.

[0036] The health checkup data 420 is data on health checkups that a subject has undergone, associated with the subject and accumulated by year. The health checkup data 420 stores information on whether the subject has undergone a health checkup, as well as measurement values ​​for each health checkup item. The health checkup data 420 includes interview (questionnaire) data that the subject answers in advance before the health checkup. The health checkup data includes specific health checkup data, which is data on the results of health checkups conducted for subjects aged 40 to 74 with a focus on metabolic syndrome, and late-stage elderly health checkup data conducted for subjects aged 75 or older. The health checkup data 420 may also include data on health checkups conducted by employers for their employees in accordance with the Industrial Safety and Health Act. The health checkup data 420 includes data such as examinee information, specific health checkup result information, interview (questionnaire) information (medication, smoking history, etc.), whether the subject meets the metabolic syndrome criteria, and whether the subject meets the eligibility criteria for specific health guidance. Of the 420 health checkup data of the subjects, specific health checkup test items include health questions (medication history, smoking history), questionnaires, anthropometric measurements (height, weight, BMI, waist circumference), physical examination (physical examination), urinalysis (urine glucose, urinary protein), blood tests (lipids (triglycerides, HDL cholesterol, LDL cholesterol), glucose metabolism (fasting blood glucose or hemoglobin A1C), and liver function (GOT, GPT, γ-GTP)), and additional items include anemia tests (red blood cell count, hemoglobin content, hematocrit value), electrocardiogram, fundus examination, and renal and urinary tract tests.

[0037] The dental examination data 430 is data on dental examinations that is associated with the subject and accumulated by year. The dental examination data 430 may also include data on dental examinations that are regular health checkups and specific health checkups. The dental examination data 430 accumulates whether the subject has undergone a dental examination or not, as well as the results of each dental examination item. The dental examination data 430 includes questionnaire data that the subject answers when undergoing a dental examination.

[0038] The medical data 440 is data that records the subject's visits to medical institutions and their admissions and discharges. It can be obtained from medical and dental receipt data created for each inpatient and outpatient visit. The medical data 440 includes the name of the medical institution, medical history, date of treatment, and name of medical procedure.

[0039] The dispensing receipt data 450 includes information on drugs dispensed at a dispensing pharmacy, information on the prescribing source, and information on the patient. The dispensing receipt data 450 is associated with each patient. The dispensing receipt data 450 includes the name of the medical institution or pharmacy, the dispensing date, the drug name, the ingredient name, the usage, the dosage, etc.

[0040] The nursing care certification data 460 is data of information related to nursing care certification. Nursing care certification is determined by a nursing care certification review board attached to a local government, based on an application for review, by calculating the standard time for nursing care certification etc. for five areas (direct assistance for daily living, indirect assistance for daily living, BPSD-related activities, functional training-related activities, and medical-related activities) and determining whether a person needs support level 1 to level 5 based on the total of the calculated time and the dementia surcharge. The nursing care certification data 460 may also include "independent," which is a state in which support such as nursing care services is not required for daily living. The nursing care certification data 460 may also include support level data.

[0041] Intervention data 470 includes data recording measures implemented by insurers, etc., correlating the implementer, implementation date, and details, personal medical data obtainable from electronic medical records, and vital data obtainable from wearable devices, etc. Interventions are divided into individual interventions and group interventions. An example of individual intervention is specific health guidance for those with metabolic syndrome or those at risk of metabolic syndrome. Examples of group interventions include encouraging those who have not yet undergone health checkups to undergo checkups, and health promotion efforts by insurers, etc. This health business support system handles both group and individual interventions.

[0042] <Machine learning model> In this embodiment, a machine learning model may be used as a prediction model for predicting the effects of health care projects. Various types of data in the health care information database 102 are used as explanatory variables. The data used in the health care information database 102 may be some types of data or all types of data.

[0043] The objective variables of the machine learning model include the effect of extending the average period of independence, the effect of delaying the onset of dementia, the effect of optimizing medical expenses, the effect of optimizing nursing care benefit expenses, the effect of preventing lifestyle-related diseases, and the improvement of test results.

[0044] <Outcomes> Next, outcome evaluation in this embodiment will be described. Outcome evaluation refers to evaluating the achievement status of health project goals, specifically, evaluating the degree of achievement of each item related to the implementation results of the project indicated by the evaluation index. The aforementioned effects of extending healthy life expectancy, delaying the onset of dementia, optimizing medical expenses, optimizing nursing care benefit expenses, preventing lifestyle-related diseases, and improving test results are targeted, and outcomes are indicators that represent these goals. For example, outcomes are specific indicators that serve as targets, such as improving those who qualify as malnourished to a state where they are not, or reducing a BMI of 25 or more to a BMI of less than 25. Outcome evaluation evaluates the extent to which the outcomes set at the time of planning were achieved after the fact. Outcomes include individual-level outcomes and group-level outcomes. This embodiment mainly deals with group-level outcomes, but can also be applied to individual-level outcomes.

[0045] <Overall flow of this system> The overall flow of this embodiment will be described with reference to Fig. 5. The flowchart in Fig. 5 is implemented by the CPU 210 of the information processing device 101 loading a program stored in the storage unit 203 into the RAM 211 and executing it. In the following, the step numbers of each process included in the flowchart are indicated by numbers beginning with "S". This also applies to the subsequent flowcharts.

[0046] In S501, the learning unit 222 of the information processing device 101 generates a prediction model. The prediction model is a model that receives input of medical examination data and the like for an individual subject and outputs the probability of the risk of developing a disease or the like in the future. Details of S501 will be described later.

[0047] Next, in S502, the prediction model unit 220 of the information processing device 101 performs processing to obtain the probability of future health risks of individual subjects for a certain population using a prediction model. Then, based on the individual's future health risks obtained by the prediction model unit 220, the evaluation unit 221 evaluates the effectiveness of measures implemented through health programs. For example, it evaluates how much the risk of developing a disease or the like can be reduced when health program measures are implemented for a certain group of subjects. Details of S502 will be described later. If the insurer, etc. is a local government, the subject is a resident, and if it is a health association, the subject is an insured person or association member. Here, the subject refers to a person targeted for health programs by the insurer, etc.

[0048] Finally, in S503, the presentation information generation unit 225 of the information processing device 101 generates presentation information of the evaluation of the effects of the health care project. Then, the user IF unit 224 transmits the generated presentation information to the terminal device 103. The terminal device 103 displays the presentation information on the display unit 304. By examining the presentation information showing the evaluation results, the insurer or the like can determine what measures are effective. Details of S503 will be described later.

[0049] <Generating a predictive model> Details of S501 in FIG. 5 will be described with reference to FIGS. 6 to 8. First, generation of a prediction model will be described with reference to the flowchart in FIG. 6 and the relationship between the data and the model in FIG. 7, using the effect of extending the mean independent life span as an example. The flowchart in FIG. 6 is implemented by the CPU 210 of the information processing device 101 loading a program stored in the storage unit 203 into the RAM 211 and executing it. Here, healthy life expectancy is evaluated by the mean independent life span, but healthy life expectancy may also be evaluated by other indicators. Healthy life expectancy may also be referred to as healthy life expectancy or active life expectancy. Here, the health checkup data 420, dental checkup data 430, medical care data 440, and prescription data 450 in the health information database 102 are used as learning data, but data may be selected appropriately from the health information database 102.

[0050] In S601, the data acquisition unit 223 of the information processing device 101 acquires the health checkup data 420, dental checkup data 430, medical treatment data 440, and prescription data 450 for fiscal year 2021 from the health information database 102 and stores them in the memory unit 203.

[0051] Next, in S602, the data acquisition unit 223 of the information processing device 101 acquires the nursing care certification data 470 for fiscal years 2021 and 2022 from the health information database 102 and stores it in the memory unit 203.

[0052] Next, in S603, the learning unit 222 of the information processing device 101 excludes data of subjects who have been certified as requiring nursing care from the health checkup data 420, dental checkup data 430, medical treatment data 440, and prescription prescription data 450 for fiscal year 2021 to create a population.

[0053] Next, in S604, the learning unit 222 identifies from the population those subjects who newly became care recipients of level 2 or higher in fiscal year 2022. Here, care recipients of level 2 or higher are considered to be care recipients of level 1 or higher, or care recipients of level 3 or higher. Furthermore, the level of support required may also be included. Furthermore, data on physical frailty may also be included.

[0054] Next, the learning unit 222 trains the prediction model on the patterns of health checkup values, questionnaires, medical history, and prescription medications in fiscal year 2021 of subjects who newly became level 2 or higher in nursing care requirement in fiscal year 2022 for the aforementioned population. In this way, the prediction model learns what characteristics subjects have that make them at high risk of needing nursing care. The learning algorithm uses the well-known gradient boosting, but the learning algorithm is not limited to this.

[0055] In training the above prediction model, health data from fiscal years 2021 and 2022 was used, but health data from any fiscal year can be used. Furthermore, the period does not have to be a fiscal year, as long as it is data from one period to the next. It can be a calendar year, or a period of two years or more. It can also be in monthly or several-month increments.

[0056] The medical interview (questionnaire) data included in the health checkup data 420 includes information on the subjects' responses to questions such as whether they use medication, blood pressure lowering medication, insulin injections or blood sugar lowering medication, cholesterol lowering medication, medical history such as stroke, heart disease, and kidney failure, smoking habits, weight gain since age 20, exercise habits, eating habits, drinking habits, and sleep status. This information in the medical interview (questionnaire) data is information that the subjects themselves acknowledge, and therefore serves as an index for creating prediction models and evaluating the effectiveness of health care projects.

[0057] FIG. 8 shows the operation of the prediction model generated by the learning unit 222. The nursing care risk prediction model generated by the flow of FIG. 6 outputs the nursing care risk (risk of becoming nursing care level 2 or higher) of a certain subject within one year when health checkup data, dental checkup data, medical data, and prescription data of the certain subject for a certain year are input. The input and output of the prediction model do not necessarily have to match the learning data used to train the prediction model. For example, the prediction model may be trained using five years' worth of data, and health information of a certain subject at a certain time may be input to output the nursing care risk for the following year (within one year).

[0058] <Dementia risk prediction model> Regarding the prediction model for predicting dementia risk, the learning unit 222 trains the prediction model by treating subjects who were not definitively diagnosed with dementia in fiscal year 2021 but were definitively diagnosed with dementia in fiscal year 2022 in the medical data as subjects who have newly developed dementia, instead of using the nursing care certification data. Learning may also be performed based on subjects whose dementia has become severe or the degree of recognition of forgetfulness.

[0059] <Lifestyle-related disease risk prediction model> For the prediction model that predicts lifestyle-related disease risk, the learning unit 222 trains the prediction model on subjects in the medical data who were not hospitalized for lifestyle-related diseases in fiscal year 2021 but were hospitalized for lifestyle-related diseases in fiscal year 2022, instead of the nursing care certification data, as subjects who were newly hospitalized for lifestyle-related diseases. Also, the prediction model may be trained on subjects in the medical data who were not treated for lifestyle-related diseases in fiscal year 2021 but were treated for lifestyle-related diseases in fiscal year 2022, as subjects who newly developed lifestyle-related diseases. Furthermore, the prediction model may be trained on subjects who showed an increase of more than a certain amount or a certain percentage in medical expenses related to lifestyle-related diseases between fiscal year 2021 and fiscal year 2022, as subjects who newly developed lifestyle-related diseases or whose lifestyle-related diseases became more severe.

[0060] <Evaluation of health project effectiveness> The detailed processing of S502 in Fig. 5 will be described with reference to Fig. 9. The flowchart in Fig. 9 is implemented by the CPU 210 of the information processing device 101 reading a program stored in the storage unit 203 into the RAM 211 and executing it.

[0061] This section explains the process of evaluating the extent to which the average period of independence can be extended as an evaluation of the effectiveness of health care projects. If the average period of independence can be extended, insurers etc. can reduce nursing care benefit costs and medical expenses. The evaluation of health care project effectiveness is necessary to consider whether the average period of independence can be effectively extended if insurers etc. implement health care projects as a measure.

[0062] By using the nursing care prediction model, by inputting a subject's health checkup data, dental checkup data, medical treatment data, and prescription prescription data for a given year, it is possible to calculate the risk (probability) of needing nursing care in the following year (within one year).

[0063] Here, the population used to evaluate the extension of the average period of independence does not necessarily have to be the same as the population of subjects used to generate the nursing care risk prediction model. Since accuracy is generally required for generating a prediction model, the more data there is, the better. Meanwhile, the evaluation of the extension of the average period of independence using a prediction model must take into account factors such as the size of each local government or health association and the composition of the subjects. Therefore, the target population for the evaluation of the extension of the average period of independence is the population for which the insurer, etc., provides health care services.

[0064] In S901, the prediction model unit 220 of the information processing device 101 uses a nursing care risk prediction model to first input health information for each individual for all members of a group of subjects such as an insurer, and calculates each individual's nursing care risk (probability of becoming level 2 or higher in nursing care) one year from now (within one year).

[0065] Next, in S902, the evaluation unit 221 of the information processing device 101 divides the subjects into two groups, for example, those who have undergone a health checkup and those who have not, and calculates the nursing care risk (probability of becoming nursing care level 2 or higher) of the group who have undergone a health checkup and the nursing care risk (probability of becoming nursing care level 2 or higher) of the group who have not undergone a health checkup by averaging the nursing care risk (probability of becoming nursing care level 2 or higher) of the subjects in the group. Here, the groups are divided into two, but they may be divided into three or more. Also, the average value of the subjects' probabilities within a group is calculated, but other values ​​such as the median or mode may be used. As a result of calculating the average values, it is assumed that the nursing care risk (probability of becoming nursing care level 2 or higher) of the group of people who have undergone a health checkup is 1.0%, and the nursing care risk (probability of becoming nursing care level 2 or higher) of the group who have not undergone a health checkup is 3.0%.

[0066] Next, in S903, the evaluation unit 221 of the information processing device 101 calculates the difference between the nursing care risk (probability of becoming care level 2 or higher) of 3.0% for the group who have not undergone a health checkup and the nursing care risk (probability of becoming care level 2 or higher) of 1.0% for the group who have undergone a health checkup. In this case, the difference is 2.0%. This difference means that if all people who have not undergone a health checkup start to undergo a health checkup, the nursing care risk (probability of becoming care level 2 or higher) will decrease by 2.0%.

[0067] Next, in S904, the evaluation unit 221 of the information processing device 101 calculates the rate of decrease in the average value. In the above example, the difference in the average values ​​is regarded as the extent of decrease in the average risk of needing care level 2 or higher. When the group that did not undergo health checkups starts to undergo health checkups, the probability of needing care level 2 or higher is deemed to decrease from 3.0% to 1.0%, and the risk of needing care is reduced by 66.7%. Therefore, it is evaluated that the risk of needing care has improved by 66.7% by having the subjects who did not undergo health checkups undergo health checkups.

[0068] In S903, the difference in the probability of the groups is obtained, and in S904, the improvement is evaluated based on the ratio of the difference to the probability when no measures are taken, but the evaluation can also be based on the ratio between the groups without using the difference.

[0069] Next, in S905, the information processing device 101 determines whether there are other groupings. In the example, the grouping is based on whether or not the person has undergone a health checkup, but various other groupings are possible, such as whether or not the person has undergone a dental checkup, or whether or not the person has an underlying disease. If there are no other groupings (if YES), the process ends. If there are other groupings (if NO), the processes of S902 to S904 are repeated for the other groupings.

[0070] Next, in S906, for example, the presentation information generation unit 225 of the information processing device 101 generates presentation information for visualizing and presenting to the user that if the group that has not undergone a health checkup starts to undergo a health checkup, the risk of needing nursing care will decrease by 66.7%. If there are other groupings, presentation information is generated in the same way. The generated presentation information can be stored in the storage unit 203 of the information processing device 101. In addition, the generated presentation information is provided to the terminal device 103 of the insurer, etc., via the user IF unit 224 and the communication unit 201, and presented to the user.

[0071] The grouping for evaluation performed by the evaluation unit 221 is related to health care services. For example, whether or not a person has undergone a health checkup leads to measures and health care services that the insurer or the like takes, such as encouraging the subject to undergo a health checkup. These measures may also be considered as intervention by the insurer or the like in the insured person.

[0072] <Acquisition of the average extension of the period of independence> The evaluation unit 221 of the information processing device 101 also performs processing to predict the extension of the average period of independence, etc. By having subjects who have not undergone health checkups undergo health checkups, the incidence of needing nursing care decreases by 66.7%. Assuming that this reduction continues until the age of 75 or older, the evaluation unit 221 calculates two remaining average periods of independence: one in the case where the subjects do not undergo health checkups, and one in the case where the subjects begin to undergo health checkups, and the difference between these is regarded as the extension of the average period of independence.

[0073] The presentation information generating unit 225 may generate a graph as shown in FIG. 10 showing a change in the care risk of the subject when the subject does not undergo a medical checkup and when the subject begins to undergo a medical checkup.

[0074] Figure 10 shows the average nursing care risk for subjects who do not undergo health checkups, and the average nursing care risk for subjects who do undergo health checkups. This shows that when people who do not undergo health checkups start to undergo health checkups, the nursing care risk improves. From this nursing care risk, it is possible to evaluate the extension of the average remaining period of independence at each age when health programs are implemented.

[0075] Strictly speaking, the average remaining independence period calculated using this method is not the actual effect of encouraging people to undergo health checkups, but it can be said to be an indicator that numerically represents the effect. By evaluating the effect of extending the average remaining independence period in this way, it is possible to evaluate the effect of health programs such as encouraging people to undergo health checkups conducted by insurers, etc.

[0076] Furthermore, if the average remaining period of independence is extended, the age at which people become dependent on care will increase, which will enable a reduction in nursing care benefits. The evaluation unit 221 can evaluate the monetary effect of the insurer, etc., encouraging people to undergo health checkups based on the average amount of nursing care benefits paid per person per year by the insurer, etc.

[0077] <Dementia delay effect> Other evaluation examples will be described. For example, this health project support system can evaluate the dementia delay effect of health projects. Regarding dementia, if a subject's medical data shows no definitive diagnosis of dementia in one year, but a definitive diagnosis of dementia in the following year's medical data, it can be said that the subject has newly developed dementia. It is also possible to evaluate the state of advanced dementia and forgetfulness. Based on the data of these subjects, the learning unit 222 can generate a dementia risk prediction model in the prediction model flow.

[0078] Once the dementia risk prediction model is generated, the prediction model unit 220 can predict the dementia risk of each individual subject as a probability. The evaluation unit 221 divides the subject population into two or more groups and obtains the average value of the risk (probability) of dementia onset for each individual subject in each group. The evaluation unit 221 can predict what kind of intervention can be implemented for each group to reduce the dementia risk, based on the percentage difference between the average values ​​of the risk (probability). For example, by dividing subjects into groups based on whether they have undergone dental checkups or not, and recommending dental checkups, the dementia delay effect can be evaluated in terms of years.

[0079] <Reduction of medical expenses for lifestyle-related diseases> This health care project support system makes it possible to evaluate not only the delay effect but also the effect of reducing medical costs. If a subject's medical data for one year shows no hospitalizations related to lifestyle-related diseases, but the medical data for the following year shows hospitalizations related to lifestyle-related diseases, the subject can be said to have newly developed a lifestyle-related disease. Furthermore, the severity of the subject's lifestyle-related disease can be assessed based on the amount and rate of increase in the subject's medical expenses. Based on this data, the learning unit 222 can generate a lifestyle-related disease risk prediction model in the prediction model generation flow.

[0080] Once the lifestyle-related disease risk prediction model is generated, the prediction model unit 220 can predict the lifestyle-related disease risk of each individual subject as a probability. The evaluation unit 221 divides the subject population into two or more groups and obtains the average risk (probability) of lifestyle-related disease for each individual subject in each group. From the percentage difference between the average risks, the evaluation unit 221 can predict what kind of intervention can be made for each group to reduce the lifestyle-related disease risk. For example, by dividing subjects into groups based on whether or not they have an exercise habit, and encouraging them to exercise, the reduction in lifestyle-related disease risk can be evaluated as a percentage.

[0081] Furthermore, since lifestyle-related diseases lead to an increase in medical expenses, the evaluation unit 221 calculates the average medical expenses per person when a lifestyle-related disease develops, and compares the medical expenses when exercise is not encouraged with those when exercise is encouraged, thereby making it possible to evaluate the effectiveness of the health program based on the amount of medical expense reduction in both cases.

[0082] <Visualization of the effects of health care projects> As described above, the health care project support system of this embodiment can calculate the extension of the average period of independence, the delay in the onset of dementia, the appropriate effect amount of nursing care benefit expenses, and the appropriate effect amount of hospitalization medical expenses for lifestyle-related diseases. In S503 of FIG. 5, the effects of health care projects that are candidates for implementation by insurers, etc. are visualized and presented. By examining the visualized effects of the health care projects, insurers, etc. can decide which health care projects to implement to achieve the greatest effect.

[0083] S503 in Fig. 5 will be described in detail. First, visualization of the effects of lifestyle disease countermeasures and nursing care countermeasures implemented by an insurer, etc. will be described with reference to Fig. 11 and Fig. 12. A setting screen 1100 in Fig. 11 and an effect display screen 1200 in Fig. 12 are displayed on the display unit 304 of the terminal device 103 by accessing the information processing device 101 from the terminal device 103 of the insurer, etc.

[0084] The setting screen 1100 in Fig. 11 is a setting screen on which an insurer or the like inputs setting values ​​to evaluate the effectiveness of a health care project. The setting screen 1100 has, as input items, a destination area 1101, a health care project goal 1102, and a target number of people 1103. These inputs may be input on a single screen, or may be input by sequentially switching between multiple screens.

[0085] In setting the destination area 1101, the user inputs the prefecture and city, ward, town, or village. The destination area may be set on a prefecture-by-prefecture basis. The user can select all prefectures by not selecting a city, ward, town, or village, or by providing "all" as an option and selecting "all." Although the setting screen 1100 uses a pull-down menu, the input is not limited to this and the user may also input a name or use another selection method.

[0086] Next, health project goals 1102 are set. In the example of Fig. 11, goals related to lifestyle-related diseases and nursing care measures are set, but this is not limited to these. In the example of Fig. 11, the insurer or the like sets the items they want to set as goals according to the health project, such as making health checkups a habit, reducing a BMI of 25.0 or more to 18.5 to 24.9, reducing an HbA1c of 7.0 or more to 6.9 or less, and not allowing an eGFR of 45 to 59.9 to fall below 45.

[0087] Health program goal 1102 includes an item called "Outcomes." This item allows for the setting of 10 outcomes to be addressed in data health planning. The following 10 outcomes can be set: malnutrition, oral health, polypharmacy, hypnotics, physical frailty, poor control, discontinued treatment for diabetes, etc., prevention of frailty due to underlying diseases, poor renal function, and individuals with unknown health status. Other items may also be set as outcomes, not limited to these. Each item has its own set of conditions. For example, malnutrition is defined as a BMI of less than 20 and quality (weight change). Oral health is defined as poor chewing and swallowing function and no dental visit in the past year. Polypharmacy is defined as 15 or more prescribed medications. Hypnotics is defined as prescription of hypnotics and a history of falls or both cognitive quality 10 (awareness of forgetfulness) and cognitive quality 11 (awareness of disorientation). Physical frailty is a state of physical decline due to aging, intermediate between a healthy state and a state requiring nursing care. Physical frailty refers to poor health, a slow walking speed, and a history of falls. Poorly controlled conditions refer to high blood sugar and blood pressure, but no history of diabetes or hypertension prescriptions for one year. Discontinued diabetes treatment refers to no health checkup history in the selected year, but a history of diabetes or hypertension medication prescriptions in the three years prior to the selected year, but no history of medication prescriptions in the selected year. Prevention of frailty with underlying diseases refers to diabetes treatment being ongoing or discontinued, or having cardiovascular disease such as heart failure or stroke, or high blood sugar levels, poor health, weight loss, falls, or frequency of going out. Poor renal function refers to poor kidney function values, detected urinary protein, and no medical treatment. Unknown health status refers to no health checkups, no prescription history (inpatient, outpatient, or dental) in the selected year or the year prior to the selected year, and no nursing care certification.

[0088] The items in the health program goal 1102 correspond to the groupings in the flow chart in Figure 9. For example, "making health checkups a habit" is set when considering the effect on health program management of encouraging people who have not yet had health checkups to do so and making health checkups a habit. Also, "reducing BMIs of people with a BMI of 25.0 or higher to 18.5-24.9" is a goal aimed at reducing the number of obese people. This is set when considering the effect on health program management, such as the reduction in lifestyle-related disease-related hospitalizations and the reduction in medical expenses, when health program measures such as dietary and exercise guidance are implemented to reduce BMIs of people with a BMI of 25.0 or higher to 18.5-24.9. "Reducing HbA1c levels of people with an HbA1c of 7.0 or higher to 6.9 or lower" is set when considering the effect on health program management of measures such as dietary and exercise guidance are implemented to prevent diabetes from worsening. In addition, the setting of not letting people with eGFR between 45 and 59.9 go below 45 is set when considering how much effect can be expected from the operation of a health project when dietary advice and the like are provided as a health project to maintain kidney function. The setting of the health project goal 1102 is not limited to those listed in Fig. 11, and any items may be set.

[0089] The target number 1103 setting is the number of people targeted by the insurer, etc. Generally, for a local government, it is the number of residents, and for an insurer, etc., it is the number of people targeted. The target number does not necessarily have to be everyone, and the target number may be changed depending on age or gender. Also, age groups and gender may be input.

[0090] FIG. 12 shows an effect display screen 1200 that displays the effect of health project measures according to the goals set on the setting screen 1100. The effect display screen 1200 displays the expected effect over a five-year period, as an example. The predicted effect period is not limited to five years, and may be one year or another period. A numerical value area 1201 shows the effect numerically. A graph area 1202 shows the effect graphically. A lifestyle-related disease-related medical expense reduction effect 1203 indicates that, compared to the case where health project measures are not implemented, lifestyle-related disease-related medical expenses can be reduced by 200,000,000 yen, resulting in a 50% reduction in lifestyle-related medical expenses. A graph 1206 on the left side of the graph area 1202 shows the case where health project measures are not implemented, and a graph 1207 on the right side shows the case where health project measures are implemented.

[0091] Nursing care benefit cost reduction effect 1204 indicates that the number of people who will become nursing care level 2 or higher will decrease compared to the case where health project measures are not implemented, and therefore nursing care benefit costs can be reduced by 100,000 yen, or 40%. Nursing care level 2 or higher requirement effect 1202 indicates that the number of people who will become nursing care level 2 or higher will decrease by 50, and the number of people who will become nursing care level 2 or higher will decrease by 28%, compared to the case where health project measures are not implemented.

[0092] <Second embodiment> Next, a second embodiment will be described. In the first embodiment, a goal for a health project is set and the effect of measures for the health project is evaluated. In the first embodiment, the user sets the goal for the health project, but there are cases where the user has no idea what kind of goal to set. In the second embodiment, what kind of measures should be taken as health projects to be effective are compared and presented.

[0093] Here, an example of displaying the effect of extending healthy lifespan will be described. The presentation information generation unit 225 generates the presentation screen 1300 of FIG. 13. The presentation screen 1300 visualizes and displays the effect of extending healthy lifespan for each goal of a health project in a certain area. The presentation screen 1300 visualizes the effect of extending healthy lifespan at ages 75, 80, and 85 for all or some of the items in the health project goal 1102 of FIG. 11. The graphs and numerical values ​​represent the number of years of extension expected if measures for each health project are implemented.

[0094] For example, if dietary guidance is provided to 75-year-old men as part of a health program, reducing the number of people with malnutrition by one will have the effect of extending healthy life expectancy by 1.4 years. In addition, increasing the BMI from 18.4 or less to 18.5-24.9 will have the effect of extending healthy life expectancy by 1.0 year. From this, it can be seen that in this region, if insurers provide nutritional and dietary guidance to men around 75 years old as part of a health program to ensure they get enough nutrition and do not become too thin, they can expect to be effective in extending healthy life expectancy.

[0095] A user such as an insurer can determine a target item based on the presentation screen 1300 in Fig. 13. Then, when the user inputs the determined target into the setting screen in Fig. 11, the user can evaluate the effect of reducing medical expenses, the effect of reducing nursing care benefit expenses, etc. on the result screen 1200 in Fig. 12. This health care project support system allows the user to evaluate what kind of health care project measures will be most effective.

[0096] <Third embodiment> Next, a third embodiment will be described. The first and second embodiments evaluated the effectiveness of health care project measures for all subjects of an insurer, etc. The third embodiment presents what kind of health guidance would be effective for each individual subject.

[0097] The presentation screen 1400 in Fig. 14 shows, in numerical form, what kind of health guidance would be effective for each individual. The graphs and numerical values ​​show the expected extension in the average healthy life expectancy of each individual if improvements and prevention are made regarding the following: making regular health checkups, making regular dental visits, improving malnutrition, improving oral health, reducing polypharmacy, reducing sleeping pill use, improving physical frailty, reducing discontinuation of diabetes treatment, and preventing frailty.

[0098] For example, it is known that improving the administration of sleeping pills for subject A will extend his healthy life expectancy by 1.7 years, so the insurer etc. can provide health guidance to subject A regarding the prescription of sleeping pills. This health project support system can not only evaluate the effects of health projects on a group, but also evaluate the effects of health guidance on an individual.

[0099] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0100] 101: Information processing device, 102: Health information database, 103: Terminal device

Claims

1. A program that causes a computer to function as each means of an information processing device that supports health care projects, the information processing device comprising: A prediction means for predicting the health risk of each of a plurality of subjects based on the health information of the plurality of subjects; an evaluation means for dividing the plurality of subjects into two or more groups, including at least a group in which the one measure has been implemented and a group in which the one measure has not been implemented, for each of the plurality of measures in the health project, determining the health risk of each of the two or more groups based on the health risk of each of the plurality of subjects predicted by the prediction means, and evaluating the effectiveness of the one measure based on the difference or ratio of the health risks of the two or more groups; a presentation information generating means for generating presentation information for visualizing the evaluation results of each of the plurality of measures of the health care service by the evaluation means and presenting the results to a user; the prediction means predicts health risks using a prediction model that learns from health information of subjects whose health conditions have changed from a given period to a next period; program.

2. The health risk of the two or more groups is the average of the health risks of each of the plurality of subjects belonging to the two or more groups. The program according to claim 1.

3. The prediction by the prediction means includes at least one of prediction of a nursing care risk, prediction of a dementia risk, and prediction of a lifestyle-related disease risk. The program according to claim 1.

4. The health information includes at least one of medical checkup data, medical receipt data, and prescription receipt data. The program according to claim 1.

5. The health checkup data includes medical interview (questionnaire) data. The program according to claim 4.

6. The evaluation result by the evaluation means includes at least one of the effect of extending the healthy life expectancy or independent period of the subject, the effect of reducing costs, and the number of people whose health condition has improved. The program according to claim 1.

7. The presented information further includes information visualizing the effects of each of a plurality of health project measures for each of the subjects. The program according to claim 1.

8. An information processing device for supporting health care projects, A prediction means for predicting the health risk of each of a plurality of subjects based on the health information of the plurality of subjects; an evaluation means for dividing the plurality of subjects into two or more groups, including at least a group in which the one measure has been implemented and a group in which the one measure has not been implemented, for each of the plurality of measures in the health project, determining the health risk of each of the two or more groups based on the health risk of each of the plurality of subjects predicted by the prediction means, and evaluating the effectiveness of the one measure based on the difference or ratio of the health risks of the two or more groups; a presentation information generating means for generating presentation information for visualizing the evaluation results of each of the plurality of measures of the health care service by the evaluation means and presenting the results to a user; the prediction means predicts health risks using a prediction model that learns from health information of subjects whose health conditions have changed from a given period to a next period; Information processing device.

9. An information processing method executed by an information processing device that supports health care services, a prediction step of predicting the health risk of each of a plurality of subjects based on the health information of the plurality of subjects; an evaluation step of dividing the plurality of subjects into two or more groups, including at least a group in which the one measure has been implemented and a group in which the one measure has not been implemented, determining the health risk of each of the two or more groups based on the health risk of each of the plurality of subjects predicted in the prediction step, and evaluating the effectiveness of the one measure based on the difference or ratio of the health risks of the two or more groups; a presentation information generating step of generating presentation information for visualizing the evaluation results of each of the plurality of measures of the health care service in the evaluation step and presenting the visualization results to a user; the prediction step predicts health risks using a prediction model that learns from health information of subjects whose health status has changed from a given period to a subsequent period; Information processing methods.

Images