Healthcare Business Support Server and Healthcare Business Support Method

Abstract

To generate appropriate data for executing analysis related to population approach measures for each group including an individual who misses health checkup data.SOLUTION: A health business support server holds individual attribute information showing an attribute of an individual belonging to a group and health information showing a checkup result of the individual, matches each of individuals of the group having no checkup are not included in checkup information among individuals belonging to the group with individuals of a group having checkup who are included in the checkup information among individuals belonging to the group on the basis of attributes shown by the individual attribute information, and substitutes checkup results of individuals of the group having checkup with successful matching as a checkup result of each of individuals of the group having no checkup with the successful matching.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a healthcare business support server and a healthcare business support method.

Background Art

[0002] Insurers including local governments are implementing measures such as healthcare services in order to maintain the health of insured persons and optimize medical and nursing care costs in response to the soaring medical and nursing care costs associated with the aging population.

[0003] In addition, upper-level local governments such as prefectures have a need for optimizing medical costs, such as wanting to reduce the difference in insurance premiums between lower-level local governments such as municipalities in order to promote the equalization of insurance premiums among lower-level local governments. Under such circumstances, insurers such as upper-level local governments and lower-level local governments are analyzing receipts, nursing care data, medical examination data, etc., and implementing measures such as the PDCA (Plan-Do-Check-Act) cycle of healthcare services.

[0004] As the background art of the present invention, there is Japanese Unexamined Patent Application Publication No. 2014-182472 (Patent Document 1). Patent Document 1 describes that "the control unit 21 of the health management support server 20 executes the registration process of receipt data and the registration process of medical examination result data. Then, the control unit 21 executes the calculation process of statistical indicators. Further, the control unit 21 executes the evaluation process of receipts, the evaluation process of medical examination results, and the evaluation process by comparing receipts and medical examination results. Further, it executes the monitoring process of outputting the medical visit status and medical examination visit status in medical institutions. Using receipt data and medical examination result data, it executes the future prediction process of predicting future medical costs and determining healthcare guidance corresponding thereto. Further, it executes the healthcare guidance support process of confirming the effect of healthcare guidance." (See the abstract).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] The technology described in Patent Document 1 identifies individuals at high risk of future diseases and other conditions based on data such as health check and receipt data, and implements health care measures through high-risk approach measures for the identified individuals. However, for individuals who have not undergone a health check or received medical treatment, there is no data such as health check or receipt data, the risk of future diseases and the like cannot be predicted, and they are not the targets of health care measures by high-risk approach measures.

[0007] Therefore, not only high-risk approach measures targeting only high-risk individuals, but also a population approach that provides measures in units of groups of individuals (for example, regional units) without limiting the targets to only high-risk individuals is important.

[0008] However, there is often no data for identifying the target individuals of population approach measures. In particular, population approach measures target individuals without health check data such as those who have not undergone a health check. Conventionally, individuals without health check data have not been the analysis targets for selecting population approach measures, and it has been difficult to select appropriate population approach measures for groups containing many individuals without health check data.

[0009] In addition, it has been difficult to realize the PDCA cycle for health care including population approach measures, such as it is difficult to evaluate the effects when implementing population approach measures for groups containing many individuals without health check data and the effects after implementing population approach measures.

[0010] Therefore, one aspect of the present invention generates appropriate data for performing analysis regarding population approach measures for a group including individuals with missing health check data.

Means for Solving the Problems

[0011] In order to solve the above problems, one aspect of the present invention adopts the following configuration. The health care business support server includes a processor and a memory. The memory holds personal attribute information indicating the attributes of individuals belonging to a group and health examination information indicating the health examination results of individuals. The processor matches each individual in the group without a health examination, which is not included in the health examination information, with an individual in the group with a health examination, which is included in the health examination information, based on the attributes indicated by the personal attribute information, and executes an assignment process of substituting, as the health examination results of each individual in the group without a health examination for which the matching is successful, the health examination results indicated by the health examination information of the individual in the group with a health examination for which the matching is successful.

Effect of the Invention

[0012] According to one aspect of the present invention, it is possible to generate appropriate data for performing an analysis regarding a population approach measure for a group including individuals with missing health examination data.

[0013] Problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Mode for Carrying Out the Invention

[0015] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In this embodiment, the same components are generally denoted by the same reference numerals, and repeated descriptions are omitted. It should be noted that this embodiment is merely an example for realizing the present invention and does not limit the technical scope of the present invention.

Example

[0016] FIG. 1 is a block diagram showing a configuration example of a health care business support system. The health care business support system includes, for example, a server 100, a database 200, and a terminal 300. The server 100 is connected to the database 200 and the terminal 300 via a network such as the Internet. Note that at least a part of the server 100, the database 200, and the terminal 300 may be integrated.

[0017] The server 100 includes, for example, a data classification unit 111, a missing value substitution unit 112, a population approach selection unit 113, a population approach effect calculation unit 114, and a visualization unit 115, all of which are functional units.

[0018] The data classification unit 111 classifies the whole individuals indicated by the personal attribute information 121 described later according to the presence or absence of health check-ups and the presence or absence of medical treatment. The missing value substitution unit 112 substitutes values for the missing values of the health check-ups. The population approach selection unit 113 selects population approach measures to be recommended for each region. The population approach effect calculation unit 114 calculates the effect of the implemented population approach measures. The visualization unit 115 generates data for generating a screen for visualizing the processes executed by each functional unit of the server 100.

[0019] The database 200 holds, for example, personal attribute information 121, regional attribute information 122, medical examination information 123, receipt information 124, high-risk approach information 125, population approach information 126, population approach effect model information 127, and population approach master information 128. Note that the server 100 may hold some or all of the information held by the database 200. Note that the database 200 does not necessarily have to hold the high-risk approach information 125.

[0020] The personal attribute information 121 holds information indicating the attributes of an individual. The regional attribute information 122 indicates the attributes of the region where the individual resides. The medical examination information 123 indicates the medical examination results of the individual. The receipt information 124 indicates the medical receipts of the individual.

[0021] The high-risk approach information 125 indicates the high-risk approach implemented for a region. The population approach information 126 indicates the population approach implemented for a region. The population approach effect model information 127 indicates an effect model for predicting the effect of population approach measures. The population approach master information 128 is the master data of population approach measures.

[0022] The terminal 300 includes, for example, a display unit 311 and an input unit 312, both of which are functional units. The display unit 311 displays information on an output device 105 (to be described later) of the terminal 300. The input unit 312 accepts input to an input device 104 (to be described later) of the terminal 300.

[0023] FIG. 2 is a block diagram showing a configuration example of a computer that constitutes each of the server 100, the database 200, and the terminal 300. The computer 400 is constituted by, for example, a computer having a CPU (Central Processing Unit) 101, a memory 102, an auxiliary storage device 103, an input device 104, an output device 105, and a communication device 106.

[0024] The CPU 101 includes a processor and executes programs stored in the memory 102. The memory 102 includes a ROM (Read Only Memory), which is a non-volatile memory element, and a RAM (Random Access Memory), which is a volatile memory element. The ROM stores unchangeable programs (such as the BIOS (Basic Input / Output System)). The RAM is a high-speed and volatile memory element such as a DRAM (Dynamic Random Access Memory), and temporarily stores the programs executed by the CPU 101 and the data used during program execution.

[0025] The auxiliary storage device 103 is a large-capacity and non-volatile storage device such as a magnetic storage device (HDD (Hard Disk Drive)) or a flash memory (SSD (Solid State Drive)), and stores the programs executed by the CPU 101 and the data used during program execution. That is, the programs are read from the auxiliary storage device 103, loaded into the memory 102, and executed by the CPU 101.

[0026] The input device 104 is a device that receives input from an operator, such as a keyboard or a mouse. The output device 105 is a device that outputs the execution results of a program in a form visible to the operator, such as a display device or a printer.

[0027] The communication device 106 is a network interface device that controls communication with other devices according to a predetermined protocol. Also, the communication device 106 includes a serial interface such as a USB (Universal Serial Bus).

[0028] Part or all of the program executed by the CPU 101 may be provided to the computer 400 via a network from a removable medium (such as a CD-ROM or flash memory), which is a non-transitory storage medium, or an external computer equipped with a non-transitory storage device, and stored in the non-volatile auxiliary storage device 103, which is a non-transitory storage medium. For this reason, the computer 400 may have an interface for reading data from the removable medium.

[0029] Each of the server 100, the database 200, and the terminal 300 is a computer system configured physically on one computer or on a plurality of computers configured logically or physically, and may operate in separate threads on the same computer or on a virtual computer built on a plurality of physical computer resources.

[0030] Each functional unit shown in FIG. 1 is included in the CPU 101 of the computer 400 that constitutes the device including the functional unit. For example, the CPU 101 included in the computer 400 that constitutes the server 100 functions as the data classification unit 111 by operating according to the data classification program loaded in the memory 102 included in the computer 400, and functions as the missing value substitution unit 112 by operating according to the missing value substitution program loaded in the memory 102.

[0031] Note that part or all of the functions performed by the functional units included in the CPU 101 of the computer 400 that constitutes each device included in the healthcare business support system may be realized by hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array).

[0032] The information possessed by each device shown in FIG. 1 is stored in the auxiliary storage device 103 of the computer 400 that constitutes the device. Note that part or all of the information stored in the auxiliary storage device 103 of the computer 400 that constitutes each device included in the healthcare business support system may be stored in the memory 102 of the computer 400, or may be stored in a database outside the healthcare business support system connected to the device.

[0033] Note that in the present embodiment, the information used by the healthcare business support system may be expressed in any data structure regardless of the data structure. In the present embodiment, the information is expressed in a table format. For example, a data structure appropriately selected from a list, a database, or a queue can store the information.

[0034] FIG. 3 is a diagram showing an example of the data configuration of the personal attribute information 121. The personal attribute information 121 includes, for example, a personal ID column 1211, a year column 1212, a region column 1213, a gender column 1214, and a birth date column 1215. The personal ID column 1211 holds a personal ID for identifying an individual. The year column 1212 holds information indicating the year. The attribute information indicated by each record of the personal attribute information 121 is the attribute information for the year indicated by the year column 1212 of the record.

[0035] The region column 1213, the gender column 1214, and the birth date column 1215 each hold information indicating the residential region, gender, and birth date of the individual. The information indicated by the region column 1213, the gender column 1214, and the birth date column 1215 are all examples of personal attribute information. The personal attribute information 121 may include, as personal attribute information, for example, information such as the occupation of the individual, the presence or absence of employment, and the family composition of the individual. Note that since the personal attribute information may include information that changes by year (such as the residential region), the personal attribute information 121 may hold records for each of a plurality of years for the same personal ID.

[0036] FIG. 4 is a diagram showing an example of the data configuration of the regional attribute information 122. The regional attribute information 122 includes, for example, a region ID column 1221, a year column 1222, a name column 1223, and a population column 1224. The region ID column 1221 holds a region ID for identifying a region. The year column 1212 holds information indicating the year. The attribute information indicated by each record of the regional attribute information 122 is the attribute information for the year indicated by the year column 1222 of the record.

[0037] The name column 1223 holds information indicating the name of the region. The population column 1224 holds information indicating the population of the region. The information indicated by the population column 1224 is an example of the regional attribute information. The regional attribute information 122 may include, as the regional attribute information, for example, the latitude and longitude of the region. The regional attribute information 122 may include, as other regional attribute information, for example, population density obtained by normalizing the population or population density per habitable area, indicators related to economic power such as a financial power index and income, indicators related to age composition such as the ratio of the elderly population, the aging rate, and the ratio of the working-age population, indicators related to industrial structure such as the employment population ratio of the primary industry, secondary industry, and tertiary industry, the number of medical institutions or hospital beds per population or area, and indicators related to medical and nursing resources such as the number of nursing facilities or their capacity and the number of doctors. Note that since the regional attribute information may include information that changes by year (for example, population), the regional attribute information 122 may hold records for each of a plurality of years for the same region ID.

[0038] FIG. 5 is a diagram showing an example of the data configuration of the health examination information 123. The health examination information 123 includes, for example, a health examination ID column 1231, a personal ID column 1232, a visit date column 1233, an age at visit column 1234, a waist circumference column 1235, a diastolic blood pressure column 1236, a systolic blood pressure column 1237, a blood glucose level column 1238, and a neutral fat column 1239. The health examination ID column 1231 holds an ID for identifying a health examination. The personal ID column 1232 holds the personal ID of the individual who underwent the health examination.

[0039] The visit date column 1233 holds information indicating the visit date of the medical check-up. The age at visit column 1234, abdominal circumference column 1235, diastolic blood pressure column 1236, systolic blood pressure column 1237, blood glucose level column 1238, and triglyceride column 1239 respectively indicate the age at visit and the examination values of abdominal circumference, diastolic blood pressure, systolic blood pressure, blood glucose level, and triglyceride in the medical check-up.

[0040] Note that the information indicated by the age at visit column 1234, abdominal circumference column 1235, diastolic blood pressure column 1236, systolic blood pressure column 1237, blood glucose level column 1238, and triglyceride column 1239 are all examples of information indicating the examination values of the medical check-up. Since an individual may undergo multiple medical check-ups, the medical check-up information 123 may hold records for each of the multiple medical check-ups for the same individual ID.

[0041] Figure 6 is a diagram showing an example of the data structure of the receipt information 124. The receipt information 124 includes, for example, a receipt ID column 1241, a region ID column 1242, a personal ID column 1243, a medical treatment year and month column 1244, a medical institution number column 1245, a disease name column 1246, a medical treatment act column 1247, a pharmaceutical column 1248, and a charge point column 1249. The receipt ID column 1241 holds an ID for identifying the receipt. The region ID column 1242 holds the region ID of the region where the medical institution that issued the receipt is located or the region ID of the region where the individual targeted by the receipt resides.

[0042] The personal ID column 1243 holds the personal ID of the individual targeted by the receipt. The medical treatment year and month column 1244 holds information indicating the year and month in which the medical treatment corresponding to the receipt was performed. The medical institution number column 1245 holds the medical institution number for identifying the medical institution (such as a hospital, dispensing pharmacy, or health institution, etc.) that issued the receipt.

[0043] The disease / Injury name column 1246, the medical treatment column 1247, the medicine column 1248, and the claim points column 1249 each hold information indicating the disease / Injury name, medical treatment, medicine, and claim points corresponding to the receipt. The information indicated by each of the medical treatment date column 1244, the medical institution number column 1245, the disease / Injury name column 1246, the medical treatment column 1247, the medicine column 1248, and the claim points column 1249 is an example of the information indicated by the receipt. Note that since an individual may receive multiple receipts, the receipt information 124 may hold records of each of the multiple receipts for the same individual ID.

[0044] Note that the disease / Injury name, medical treatment, and medicine are all examples of medical data. Note that the medical data included in the receipt information 124 is not limited to the above items, and other items such as the presence or absence of hospitalization and the presence or absence of surgery determined from the receipt classification, medical treatment, etc. may be included in place of or in addition to the above items.

[0045] Figure 7 is a diagram showing an example of the data configuration of the high-risk approach information 125. The high-risk approach information 125 includes, for example, a region ID column 1251, a measure ID column 1252, a measure name column 1253, a target person ID column 1254, a start date column 1255, and a target achievement flag column 1256. The region ID column 1251 holds the region ID of the region where the target person of the implemented high-risk approach measure resides. The measure ID column 1252 holds the measure ID that identifies the high-risk approach measure.

[0046] The measure name column 1253 holds information indicating the name of the high-risk approach measure. The target person ID column 1254 holds the target person ID that identifies the target person of the high-risk approach measure (for example, linked to the individual ID). The start date column 1255 holds information indicating the start date of the high-risk approach measure. The target achievement flag column 1256 holds the target achievement flag indicating whether the target person who has implemented the high-risk approach measure has achieved the target of the high-risk approach measure (if it is "1", the target is achieved; if it is "0", the target is not achieved).

[0047] Note that since multiple high-risk approach measures may be implemented for the same individual, the high-risk approach information 125 may hold records of multiple high-risk approach measures for the same subject ID.

[0048] Figure 8 is a diagram showing an example of the data configuration of the population approach information 126. The population approach information 126 includes, for example, a region ID column 1261, a measure ID column 1262, a measure name column 1263, a year column 1264, an assumed target number column 1265, and a participation number column 1266. The region ID column 1261 holds the region ID of the region where the population approach measure was implemented. The measure ID column 1262 holds the measure ID that identifies the population approach measure. The measure name column 1263 holds information indicating the name of the population approach measure.

[0049] The year column 1264 holds information indicating the year in which the population approach measure was implemented. The assumed target number column 1265 holds information indicating the assumed number of targets of the population approach measure. The participation number column 1266 holds information indicating the number of people who actually participated in the population approach measure.

[0050] Note that since multiple population approach measures may be implemented for the same region over multiple times and multiple years, the population approach information 126 may hold records of multiple population approach measures for the same region ID over multiple times and multiple years.

[0051] Figure 9 is a diagram showing an example of the data configuration of the population approach effect model information 127. The population approach effect model information 127 includes, for example, a measure ID column 1271, a measure name column 1272, a year column 1273, and a model formula column 1274. The measure ID column 1271 holds the measure ID of the population approach measure. The measure name column 1272 holds information indicating the name of the population approach measure.

[0052] The annual column 1273 holds information indicating the year to which the population approach effect model is applied. The model formula column 1274 holds information indicating the model formula of the population approach effect model.

[0053] Note that since the model formulas of population approach effect models may differ for different years, the population approach effect model information 127 may hold records of the population approach effect models for multiple years for the same measure ID.

[0054] FIG. 10 is a diagram showing an example of the data configuration of the population approach master information 128. The population approach master information 128 includes, for example, a measure ID column 1281, a measure name column 1282, a target person condition column 1283, an implementation index column 1284, and an effect index column 1285.

[0055] The measure ID column 1281 holds the measure ID of the population approach measure. The measure name column 1282 holds information indicating the measure name of the population approach measure. The target person condition column 1283 holds information indicating the conditions of the target persons of the population approach measure.

[0056] The implementation index column 1284 holds information indicating the calculation method of an implementation index, which is an index for evaluating the implementation status of the population approach measure, such as the number of implementations, the number of participants, the number of distributed materials, and the ratio of participants to the target persons. The larger the implementation index, the more widely the population approach measure is implemented. The effect index column 1285 holds information indicating the calculation method of an effect index, which is an index for evaluating the effect of the population approach measure when the population approach measure is implemented. The larger the effect index, the more effective the population approach measure is.

[0057] FIG. 11 is a flowchart showing an example of the population approach effect calculation process. Before the population approach effect calculation process starts, regional attribute information 122, individual attribute information 121, health examination information 123, receipt information 124, population approach information 126, and population approach master information 128 are preset. Note that, unless otherwise specified, in the process of FIG. 11, for information including items indicating the year (or year and month), information of the same year is used.

[0058] The data classification unit 111 divides the entire population of individuals registered in the individual attribute information 121 into those who are not registered or are registered in the receipt information 124 (medical absence group or medical presence group) (S101).

[0059] Also, in step S101, the data classification unit 111 further divides the entire population of individuals in the medical absence group into those who are not registered or are registered in the health examination information 123 (health examination absence / medical absence group and health examination presence / medical absence group), and divides the entire population of individuals in the medical presence group into those who are not registered or are registered in the health examination information 123 (health examination absence / medical presence group and health examination presence / medical presence group). Note that the data classification unit 111 may treat individuals with missing values in some test items of the health examination information 123 as being included in the health examination absence group or as being included in the health examination presence group.

[0060] Also, the data classification unit 111 may calculate the number of people in each of the health examination absence / medical absence group, health examination presence / medical absence group, health examination absence / medical presence group, and health examination presence / medical presence group, for example, for each attribute (for example, for each age class in 10-year increments). Further, the data classification unit 111 may also calculate the number of individuals who were included in the individual attribute information 121 in the current year but are not included m years later (m is a predetermined number), and the number of individuals who were not included in the individual attribute information 121 in the current year but are included m years later (m is a predetermined number).

[0061] For the group without medical treatment, the process proceeds to the process of step S103, and for the group with medical treatment, the process proceeds to the process of step S108 (S102). The missing value substitution unit 112 matches each individual in the group without health check and without medical treatment with an individual in the group with health check and without medical treatment using indicators such as attributes (gender, age, and region) (S103). The matching process in step S103 will be described later with reference to FIG. 12. Note that among the individuals in the group without health check and without medical treatment, there may be individuals who do not match any individual in the group with health check and without medical treatment in the matching process.

[0062] The missing value substitution unit 112 substitutes health check data for each individual in the group without health check and without medical treatment (S104), and proceeds to step S105. Specifically, for example, the missing value substitution unit 112 substitutes the inspection values of the health check indicated by the health check information 123 of the individual in the group with health check and without medical treatment who was matched with the individual in the group without health check and without medical treatment in step S103 for each individual in the group without health check and without medical treatment. Note that for an individual in the group without health check and without medical treatment who is matched with a plurality of individuals in the group with health check and without medical treatment, a statistic such as the average value of the inspection values of the health check of the plurality of individuals may be substituted.

[0063] The missing value substitution unit 112 matches each individual in the group without health check and with medical treatment with an individual in the group with health check and with medical treatment using attributes (gender, age, and region) and medical data indicated by the receipt information 124 such as the name of the injury or illness, medicine, presence or absence of hospitalization, and presence or absence of surgery (S108). The matching process in step S108 will be described later with reference to FIG. 12. Note that among the individuals in the group without health check and with medical treatment, there may be individuals who do not match any individual in the group with health check and with medical treatment in the matching process.

[0064] For the individuals in the group without health check and with medical treatment who were matched with the individuals in the group with health check and with medical treatment in step S108, the process proceeds to the process of step S110, and for the individuals in the group without health check and with medical treatment who were not matched with the individuals in the group with health check and with medical treatment in step S108, the process proceeds to the process of step S111 (S109).

[0065] The missing value substitution unit 112 substitutes the health check data for each individual in the group without health check but with medical treatment (S110), and then proceeds to step S105. Specifically, for example, the missing value substitution unit 112 substitutes the test values indicated by the health check information 123 of the individual in the group with health check and medical treatment who matched the individual in step S108 for each individual in the group without health check but with medical treatment. Note that for an individual in the group without health check but with medical treatment who matched multiple individuals in the group with health check and medical treatment, a statistic such as the average of the health check test values of the multiple individuals may be substituted.

[0066] Note that if an individual whose values of some test items in the health check information 123 are missing is treated as being included in the group without health check, in the substitution processes of step S104 and step S110, it is desirable that only the values of the some test items are substituted, and the values of other test items of the individual are used as they are.

[0067] Note that the missing value substitution unit 112 may calculate the detection rate (for example, the ratio of individuals whose predetermined test values in the health check satisfy the predetermined conditions) for each of the group without health check and no medical treatment, the group with health check and no medical treatment, the group without health check but with medical treatment, and the group with health check and medical treatment after the substitution processes of step S104 and step S109 (however, for individuals in the group without health check but with medical treatment who did not match in step S109, they are excluded from the calculation target of the detection rate).

[0068] Also, the missing value substitution unit 112 may execute the substitution processes of step S104 and step S109 according to the instruction of the user of the terminal 300.

[0069] The missing value substitution unit 112 treats the group consisting of individuals in the group without health check but with medical treatment who did not match the individuals in the group with health check and medical treatment in step S108 as a group for whom health check reception cannot be expected (S111). The missing value substitution unit 112 calculates the number of unmatched individuals, which is the number of individuals belonging to the group for whom health check reception cannot be expected (S112), and then proceeds to step S108.

[0070] Individuals in the group who are not expected to undergo a health check are assumed not to undergo a health check for reasons such as having a hospitalization history or a surgical history and having undergone tests during hospitalization or surgery. In addition, since individuals in the group who are not expected to undergo a health check are highly likely to have already received medical treatment for an illness or the like before being encouraged to undergo a health check, they are not subject to health checks or various health care programs, and health improvement or medical cost optimization through health care programs cannot be expected. Therefore, individuals in the group who are not expected to undergo a health check are excluded from processes such as the estimation of the population approach effect described later as individuals for whom test values cannot be estimated. Thus, the missing value substitution unit 112 calculates the number of unmatched persons in step S112.

[0071] In addition, the missing value substitution unit 112 can accurately estimate the tendency of the health check results as a group of the no-health-check / no-medical-treatment group and the no-health-check / medical-treatment group by substituting the health check results of similar individuals who have undergone a health check for individuals who have not undergone a health check through the processes of step S103, step S104, step S108, step S109, and step S110.

[0072] In particular, since there is a high possibility that the tendency of the health status differs between the no-medical-treatment group and the medical-treatment group, such as that there are likely to be more healthy individuals in the no-medical-treatment group than in the medical-treatment group, the missing value substitution unit 112 can estimate the tendency of the health check results with higher accuracy by performing matching separately for the no-medical-treatment group and the medical-treatment group. In the example of FIG. 9, matching processing and substitution processing of the health check results may be performed between the no-health-check group and the health-check group without dividing the entire population of individuals into the no-medical-treatment group and the medical-treatment group.

[0073] Subsequently, the population approach selection unit 113 selects a population approach measure and applies a population approach effect model to the no-health-check group (the no-health-check / no-medical-treatment group and the health-check / no-medical-treatment group) (S105). Details of the population approach selection process and the population approach effect model application process in step S105 will be described later with reference to FIG. 13.

[0074] The population approach effect calculation unit 114 estimates the effect when the population approach effect model measure is applied in step S105 (S106). Specifically, for example, the population approach effect calculation unit 114 refers to the population approach master information 128 to identify the target conditions, implementation indicators, and effect indicators of the selected population approach measure. The population approach effect calculation unit 114 refers to at least some of the information such as the individual attribute information 121, the medical examination information 123, and the receipt information 124, and identifies the number of targets that meet the target conditions of the identified population approach measure. The population approach effect calculation unit 114 obtains information necessary for calculating implementation indicators other than the identified number of targets (for example, estimated values such as the assumed number of participants) through input by the user of the terminal 300 or the like.

[0075] The population approach effect calculation unit 114 refers to the population approach master information 128, and calculates an estimated value of the implementation indicator based on the number of targets and the obtained information (estimated values such as the assumed number of participants). The population approach effect calculation unit 114 identifies the effect model of the selected population approach measure from the population approach effect model information 127, and substitutes the calculated estimated value of the implementation indicator into the identified effect model to estimate the value of the effect indicator.

[0076] The visualization unit 115 displays on the output device 105 a screen for visualizing the population approach measure selected in step S105, the population approach effect estimated in step S106, the classification result by the data classification unit 111, the substitution result by the missing value substitution unit 112, etc. (S107), and ends the population approach effect estimation process.

[0077] FIG. 12 is a flowchart showing an example of the matching process in step S102, step S103, and step S108. For the group without medical treatment, the process proceeds to the process of step S202, and for the group with medical treatment, the process proceeds to the process of step S201 (S201).

[0078] The missing value substitution unit 112 sets, for the group without medical treatment, each of the attributes (sex, age, and region) as an independent variable and the presence or absence of a medical examination indicated by whether it is registered in the medical examination information 123 as a dependent variable (S202). The missing value substitution unit 112 sets, for the group with medical treatment, each of the attributes (sex, age, and region), as well as each of the medical data such as the name of the injury or illness, medicines, presence or absence of hospitalization, and presence or absence of surgery, as an independent variable and the presence or absence of a medical examination indicated by whether it is registered in the medical examination information 123 as a dependent variable (S203).

[0079] The missing value substitution unit 112 generates, for each of the group with medical examination and without medical treatment and the group with medical examination and with medical treatment, a model (for example, a logistic regression model) for estimating the dependent variable from the independent variables based on the values of the dependent variable and the independent variables (S204). Although the logistic regression model has been described as an example, other methods may be used as long as they can be used for estimating the dependent variable from the independent variables, such as statistical models and machine learning techniques.

[0080] The missing value substitution unit 112 applies the model generated from the group with medical examination and without medical treatment to each individual in the group without medical treatment, applies the model generated from the group with medical examination and with medical treatment to each individual in the group with medical treatment, and calculates a propensity score for all individuals (S205).

[0081] The missing value substitution unit 112 matches, for each individual in the group without medical examination and without medical treatment, the individual in the group with medical examination and without medical treatment whose propensity score is the closest (or within a predetermined difference) (or a predetermined number of individuals in ascending order of the propensity score), and matches, for each individual in the group without medical examination and with medical treatment, the individual in the group with medical examination and with medical treatment whose propensity score is the closest (or within a predetermined difference) (or a predetermined number of individuals in ascending order of the propensity score) (S206), and ends the matching process.

[0082] Note that for individuals in the no-health-check / no-medical-treatment group for whom there are no individuals in the health-check / no-medical-treatment group with a propensity score within a predetermined difference, the missing value substitution unit 112 may handle them as having no matching partner. Similarly, for individuals in the no-health-check / medical-treatment group for whom there are no individuals in the health-check / medical-treatment group with a propensity score within a predetermined difference, the missing value substitution unit 112 may handle them as having no matching partner.

[0083] FIG. 13 is a flowchart showing an example of the population approach selection process and the population approach effect application process in step S105. The population approach selection unit 113 calculates a population approach implementation index and a population approach effect index for each region (i.e., for each group to which the population approach measures are to be implemented) (S301).

[0084] Specifically, for example, the population approach selection unit 113 identifies the implemented population approach measures by region with reference to the population approach information 126, and identifies the implementation index and the effect index corresponding to the identified population approach measures with reference to the population approach master information 128. Further, for example, the population approach selection unit 113 calculates the implementation index and the effect index of the implemented population approach measures for each region with reference to at least some of the information such as the attributes indicated by the individual attribute information 121, the test values indicated by the health check information 123, the medical data indicated by the receipt information 124, and the target person conditions indicated by the population approach master information 128.

[0085] Note that when using the test values indicated by the health check information 123 in calculating the implementation index and the effect index, the population approach selection unit 113 shall use the test values of the substituted health check data for individuals in the no-health-check group.

[0086] The population approach selection unit 113 generates an effect model, which is a model for calculating an effect index from an implementation index based on the implementation index and the effect index calculated in step S301 for each population approach measure, and stores it in the population approach effect model information 127 (S302). Specifically, for example, the population approach selection unit 113 creates a regression model by the least squares method from the relationship between the implementation index and the effect index for each population approach measure (that is, calculates the slope, intercept, correlation coefficient, etc. of the regression model). Note that the slope of the regression model indicates the relationship between the improvement of the value of the effect index and the increase in the value of the implementation index.

[0087] When the population approach selection unit 113 determines that the modeling of all population approach measures that have been implemented in any region has been completed (S303: YES), it transitions to step S304. When it determines that there is a population approach measure for which the modeling has not been completed among the population approach measures that have been implemented in any region (S303: NO), it executes the processes of steps S301 and S302 for the population approach measure.

[0088] Note that an effect model of the population approach measure may be given in advance. That is, the population approach effect model information 127 may be set in advance before the process of FIG. 13 starts. In this case, the processes of steps S301 to S303 are omitted.

[0089] The population approach selection unit 113 identifies a population approach measure corresponding to an effect model having a slope in the direction in which the value of the effect index improves with an increase in the value of the implementation index, and selects the population approach measure having the largest correlation coefficient (between the implementation index and the effect index) in the effect model among the identified population approach measure and the population approach measures not selected in step S304 (S304).

[0090] The population approach selection unit 113 uses the implementation index of the population measure being selected as the x-axis and the effect index as the y-axis. The positive direction in the x-axis direction is the direction in which the value of the implementation index increases, and the positive direction in the y-axis direction is the direction in which the value of the effect index deteriorates. It generates a coordinate plane with the median of the implementation index and the median of the effect index as the origin, and divides the generated coordinate plane into four quadrants (four regions) (S305). Although the origin of the coordinate plane is defined by the median, it may also be defined by other statistical quantities such as the average value or a predetermined value.

[0091] Hereinafter, the quadrant where the implementation index is smaller than its median (an example of the first condition) and the effect index is smaller than its median (an example of the second condition) is called quadrant (1), the quadrant where the implementation index is larger than its median and the effect index is smaller than its median is called quadrant (2), the quadrant where the implementation index is larger than its median and the effect index is larger than its median is called quadrant (3), and the quadrant where the implementation index is larger than its median and the effect index is larger than its median is called quadrant (4). Note that points on the x-axis and points on the y-axis belong to, for example, any of the quadrants adjacent to the point.

[0092] For the area where the recommended population approach measure has not been selected and belongs to quadrant (1) of the coordinate plane of the population approach measure being selected (that is, the point defined by the implementation index and the effect index belongs to quadrant (1)), the population approach selection unit 113 selects the population approach measure being selected as the recommended population approach measure (S307).

[0093] Note that the area where the combination of the values of the implementation index and the effect index of the population approach measure selected in step S304 belongs to quadrant (1) is an area where the implementation index may improve if the implementation index of the population approach measure is increased. Therefore, it is desirable to recommend the population approach measure in the area belonging to quadrant (1).

[0094] For regions where the combination of the implementation index and the effect index values of the population approach measures selected in step S304 belongs to quadrant (2), it is a region where the effect index has not improved despite the good implementation index of the population approach measures. Therefore, for regions belonging to quadrant (2), it is desirable not to recommend the population approach measures and to recommend other population approach measures.

[0095] For regions where the combination of the implementation index and the effect index values of the population approach measures selected in step S304 belongs to quadrant (3), it is a region where the effect index is good even though the implementation index of the population approach measures is poor. Therefore, for regions belonging to quadrant (3), it is desirable not to recommend the population approach measures and to recommend other population approach measures.

[0096] For regions where the combination of the implementation index and the effect index values of the population approach measures selected in step S304 belongs to quadrant (4), it is a region where the implementation index of the population approach measures is good and the effect index is also good, that is, a region where it is highly likely that the effects of the population approach measures are obtained. Therefore, for regions belonging to quadrant (4), it is desirable to praise the implementation of the population approach measures.

[0097] If there are regions where the recommended population approach measures have not been selected and it is determined that there are unselected measures among the population approach measures identified in step S304, the population approach selection unit 113 returns to step S304. If it is determined that there are no regions where the recommended population approach measures have not been selected or there are no unselected measures among the population approach measures identified in step S304, the population approach selection process and the population approach effect application process are terminated (S308).

[0098] In the example of FIG. 13, for each region, among the population approach measures identified in step S304 that belong to quadrant (1) for that region, the one with the largest correlation coefficient in the effect model is selected as the recommended population approach. However, all of the population approach measures identified in step S304 that belong to quadrant (1) for that region may be selected as the recommended population approach, or among the population approach measures identified in step S304 that belong to quadrant (1) for that region, those with a correlation coefficient in the effect model equal to or greater than a predetermined value or a predetermined number of those with the highest values may be selected as the recommended population approach.

[0099] For regions where no recommended population approach measure is selected in steps S304 to S308, for example, they are treated as if no population approach measure is recommended.

[0100] In the example of FIG. 13, the recommended population approach measure is automatically selected for each region. However, the process of step S305 is executed for all population approach measures (that is, the above-mentioned coordinate plane is generated for all population approach measures, and points defined by the combination of the implementation index and the effect index of each region are arranged on each coordinate plane), and the execution result of this process is displayed on the terminal 300 of each region, and the user of the terminal 300 may be allowed to select a population approach measure. Details of the population approach measure selection screen displayed in this case will be described later with reference to FIG. 15.

[0101] By the population approach selection process and the population approach effect application process shown in FIG. 13, for each region, it is possible to recommend a population approach measure in which the correlation between the implementation index and the effect index is large and the effect index is likely to be increased by increasing the implementation index. As a result, it is expected to improve the health status of individuals in each region and contribute to the suppression of medical expenses.

[0102] FIG. 14 is a flowchart showing an example of the population approach effect evaluation process. In the population approach effect evaluation process in the example of FIG. 14, the evaluation of the population approach measures implemented in the previous year is evaluated using the data of this year. Note that before the start of the population approach effect calculation process, the individual attribute information 121, the regional attribute information 122, the health examination information 123, the receipt information 124, and the population approach information 126 for the previous year and this year are preset. In addition, the population approach master information 128 is preset before the start of the population approach effect calculation process.

[0103] The processes of step S401, step S402, step S403, step S404, step S407, step S408, step S409, step S410, and step S411 are realized by executing the processes of step S101, step S102, step S103, step S104, step S108, step S109, step S110, step S111, and step S112 for the information of each of the previous year and this year, respectively. Also, the data generated in the processes of step S101, step S102, step S103, step S104, step S108, step S109, step S111, and step S112 may be reused.

[0104] The population approach effect calculation unit 114 calculates the implementation indicators and effect indicators of the implemented population approach measures by region (S405). Specifically, for example, the population approach effect calculation unit 114 executes the following processes by region.

[0105] The population approach effect calculation unit 114 refers to the population approach information 126 to identify the population approach measures implemented in the previous year, as well as the assumed number of target persons and the number of participants in the population approach measures implemented in the previous year.

[0106] The population approach effect calculation unit 114 refers to the population approach master information 128 to identify the target person conditions, implementation indicators, and effect indicators of the identified population approach measures. The population approach effect calculation unit 114 refers to the population approach master information 128 to calculate the value of the implementation indicator for the previous year.

[0107] The population approach effect calculation unit 114 refers to the personal attribute information 121, the health examination information 123, the receipt information 124, etc., to identify the target persons who meet the target person conditions for the previous year of the identified population approach measures, and calculates the value of the effect indicator for the current year of the target persons.

[0108] The visualization unit 115 outputs a screen for visualizing the population approach measures identified in step S405, the calculated values of the implementation indicators and effect indicators, etc. to the output device 105 (S412), and ends the population approach effect evaluation process.

[0109] FIG. 15 is a diagram showing an example of a population approach selection screen. The population approach selection screen 1500 includes, for example, an effect indicator display area 1501, an implementation indicator display area 1502, and a coordinate plane display area 1503.

[0110] In the effect index display area 1501, the types of effect indexes are displayed, and in the implementation index display area 1502, the combination of the population approach measures and the types of implementation indexes corresponding to the population approach measures is displayed.

[0111] For example, when any type of effect index is selected in the effect index display area 1501, the combination of the population approach measures corresponding to the selected effect index and the types of implementation indexes corresponding to the population approach measures in the population approach master information 128 is automatically selected in the implementation index display area 1502.

[0112] Also, for example, when any combination of the population approach measures and the types of implementation indexes is selected in the implementation index display area 1502, the effect index corresponding to the selected combination in the population approach master information 128 is automatically selected in the effect index display area 1501.

[0113] In the coordinate plane display area 1503, a coordinate plane (the coordinate plane generated by the method shown in step S304) showing the correlation between the implementation index and the effect index for the selected population approach measure is displayed. In the coordinate plane display area 1503, an area indicating quadrants (1) to (4) and points indicating the combination of the implementation index and the effect index for each region are displayed.

[0114] Also, in the coordinate plane display area 1503, for example, a point 1504 indicating the combination of the implementation index and the effect index for the region where the terminal 300 is used and a graph 1504 of the effect model of the population approach measure generated in step S304 are displayed.

[0115] In addition, when the point 1504 belongs to quadrant (1), a message indicating that the population approach measure is recommended (and that increasing the implementation index of the population approach measure has a high possibility of improving the effect index) may be further displayed.

[0116] When the point 1504 belongs to the quadrant (2), a message indicating that the population approach measure is not recommended (and that the implementation index of the population approach measure is high but the effect index is poor) may be further displayed.

[0117] When the point 1504 belongs to the quadrant (3), a message indicating that the population approach measure is not recommended (and that the effect index is good even without increasing the implementation index of the population approach measure) may be further displayed.

[0118] When the point 1504 belongs to the quadrant (4), a message indicating that the introduction of the population approach measure to other regions is recommended (and that the effect index may be high because the implementation index of the population approach measure is high) may be further displayed.

[0119] In step S105, when the recommended population approach measure is selected, on the population approach selection screen 1500, the selected population approach measure may be displayed so that the user of the terminal 300 can recognize it, or only the information of the selected population approach measure may be displayed.

[0120] The user of the terminal 300 can easily recognize the relationship between the implementation index and the effect index of the population approach measure through the population approach selection screen 1500 and can select a population approach with high effect.

[0121] FIG. 16 is a diagram showing an example of a population approach effect calculation result display screen. The population approach effect calculation result display screen 1600 includes, for example, an effect index display area 1601, an implementation index display area 1602, and a coordinate plane display area 1603.

[0122] In the effect index display area 1601, the types of effect indexes of the population approach measures selected as the recommended population approach measures are displayed. In the implementation index display area 1602, the combination of the selected population approach measures and the types of implementation indexes corresponding to the selected population approach measures is displayed. Also, in the implementation index display area 1602, the value of the implementation index of the region in the current situation (for example, this year) and the estimated value of the implementation index of the region used for the calculation of the effect index are displayed.

[0123] In the coordinate plane display area 1603, a coordinate plane (coordinate plane generated by the method shown in step S304) showing the correlation between the implementation index and the effect index for the selected population approach measure is displayed. In the coordinate plane display area 1603, an area indicating quadrants (1) to (4) and points indicating the combination of the implementation index and the effect index of each region are displayed.

[0124] Also, in the coordinate plane display area 1603, for example, a point 1604 indicating the combination of the current implementation index and the current effect index of the region using the terminal 300, a graph 1605 of the effect model of the population approach measure generated in step S304, and a point 1606 indicating the combination of the estimated value of the implementation index and the calculated value of the effect index of the region using the terminal 300 are displayed.

[0125] Note that also on the population approach effect calculation result display screen 1600, according to the quadrant to which the point 1604 belongs or the quadrant to which the point 1606 belongs, the above-described message in the explanation of the population approach selection screen 1500 may be displayed together.

[0126] The user of the terminal 300 can easily recognize the calculation result of the effect when the population approach measure is implemented by the population approach effect calculation result display screen 1600.

[0127] FIG. 17 is a diagram showing an example of a population approach effect evaluation screen. The population approach effect evaluation screen 1700 includes, for example, an effect index display area 1701, an implementation index display area 1702, and a coordinate plane display area 1703.

[0128] In the effect index display area 1701, the types of effect indexes of the population approach measures that are the targets of effect evaluation are displayed. In the implementation index display area 1702, the combination of the population approach measure and the types of implementation indexes corresponding to the population approach measure is displayed. Also, in the implementation index display area 1702, the value of the implementation index of the area in the previous year, the estimated value (estimated in the previous year) of the implementation index of the area used for the calculation of the effect index, and the value of the implementation index of the area in the current year are displayed.

[0129] In the coordinate plane display area 1703, a coordinate plane (coordinate plane generated by the method shown in step S304) showing the correlation between the implementation index and the effect index for the population approach measure is displayed. In the coordinate plane display area 1703, an area indicating quadrants (1) to (4) and points indicating the combination of the implementation index and the effect index of each area are displayed.

[0130] Also, in the coordinate plane display area 1703, for example, a point 1604 indicating the combination of the implementation index in the previous year and the current effect index of the area using the terminal 300, a graph 1605 of the effect model of the population approach measure generated in step S304, a point 1706 indicating the combination of the estimated value of the implementation index and the calculated value of the effect index of the area using the terminal 300 (estimated in the previous year), and a point 1707 indicating the combination of the implementation index and the effect index of the area using the terminal 300 in the current year are displayed.

[0131] Note that also in the population approach effect evaluation screen 1700, according to the quadrant to which the point 1707 belongs, the above-described message may be displayed together in the description of the population approach selection screen 1500.

[0132] With the population approach effect evaluation screen 1700, the user of the terminal 300 can easily recognize the effect of the implemented population approach and the deviation between the estimated result of the effect of the population approach and the effect of the implemented population approach.

[0133] FIG. 18 is a diagram showing an example of a missing value substitution screen. The missing value substitution screen 1800 includes, for example, a data classification result display area 1801, a first button 1802, a second button 1803, and a substitution result display section 1804.

[0134] In the data classification result display area 1801, the number of people for each individual's attribute (for example, age class in 10-year increments) of each group generated by the classification process by the data classification unit 111 is displayed. When the first button 1802 is selected, the process of step S104 is executed, and when the second button 1803 is selected, the process of step S110 is executed. Also, when the first button 1802 and the second button 1803 are selected, the substitution result display section 1804 is displayed.

[0135] In the substitution result display section 1804, the detection rates of each of the no check-up / no medical treatment group, check-up / no medical treatment group, no check-up / medical treatment group, and check-up / medical treatment group after the processes of step S104 and step S110 are executed are displayed.

[0136] Note that on the missing value substitution screen 1800, when the first button 1802 and the second button 1803 are selected, after the processes of step S104 and step S110 are executed, the distribution of the examination values of the check-up after substitution for each of the check-up / medical treatment group, check-up / no medical treatment group, no check-up / medical treatment group, and no check-up / no medical treatment group may be further displayed.

[0137] With the missing value substitution screen 1800, the user of the terminal 300 can easily recognize the data classification result of the area and the estimated results of information such as the detection rate after missing value substitution.

[0138] As described above, the health care business support system of this embodiment can execute the PDCA cycle of the health care business by the population approach measure by using the information supplemented by substituting the missing values of the health examination results to select the population approach measure, calculate the effect, and evaluate the effect.

[0139] Note that the present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Also, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add, delete, or replace other configurations for a part of the configuration of each embodiment.

[0140] In addition, each of the above configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, by an integrated circuit. Also, each of the above configurations, functions, etc. may be realized in software by a processor interpreting and executing a program for realizing each function. Information such as a program, table, file, etc. for realizing each function can be placed in a memory, a recording device such as a hard disk or an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

[0141] Also, the control lines and information lines show those considered necessary for explanation, and not necessarily all the control lines and information lines are shown on the product. In practice, it may be considered that almost all the configurations are interconnected.

Description of Reference Numerals

[0142] 100 Server, 101 CPU, 102 Memory, 103 Auxiliary storage device, 104 Input device, 105 Output device, 106 Communication device, 111 Data classification unit, 112 Missing value substitution unit, 113 Population approach selection unit, 114 Population approach effect calculation unit, 115 Visualization unit, 121 Regional attribute information, 122 Individual attribute information, 123 Health examination information, 124 Receipt information, 126 Population approach information, 127 Population approach effect model information, 128 Population approach master information, 200 Database

Claims

1. A health care business support server, comprising a processor and a memory, wherein the memory holds personal attribute information indicating the attributes of individuals belonging to a group and health examination information indicating the health examination results of individuals, and the processor matches each individual in the group who has not had a health examination and is not included in the health examination information, based on the attributes indicated by the personal attribute information, with an individual in the group who has had a health examination and is included in the health examination information, and executes an assignment process of substituting, as the health examination result of each individual in the group without a health examination for whom the matching is successful, the health examination result indicated by the health examination information of the individual in the group with a health examination for whom the matching is successful, wherein the memory holds population approach information indicating a plurality of population approaches, implementation indicators for evaluating the implementation status of each of the plurality of population approaches, and effect indicators for evaluating the effects of each of the plurality of population approaches, the implementation indicators and the effect indicators are defined by at least some information of the attributes and the health examination results, and the processor calculates the implementation indicators and the effect indicators of the group for each of the plurality of population approaches based on at least some information of the attributes indicated by the personal attribute information, the health examination results indicated by the health examination information, and the health examination results substituted in the assignment process, selects, as a recommended population approach, a population approach determined to have a calculated implementation indicator lower than a predetermined first condition and a calculated effect indicator lower than a predetermined second condition, and generates data for outputting information indicating the recommended population approach. A health care business support server.

2. The health care business support server according to claim 1, generates data for outputting information indicating that a population approach determined to have a calculated implementation indicator higher than a predetermined first condition and a calculated effect indicator lower than a predetermined second condition is not recommended, generates data for outputting information indicating that a population approach determined to have a calculated implementation indicator lower than a predetermined first condition and a calculated effect indicator higher than a predetermined second condition is not recommended. ​ A healthcare business support server that generates data for outputting information indicating that it is recommended to introduce a population approach determined to be high based on a predetermined first condition for the calculated implementation index and high based on a predetermined second condition for the calculated effect index to other groups.

3. The healthcare business support server according to claim 1, wherein the population approach information shows a prediction model indicating the relationship between the implementation index and the effect index for each of the plurality of population approaches, the processor, based on at least some of the information on the attributes indicated by the personal attribute information, the health examination results indicated by the health examination information, and the health examination results substituted in the substitution process, for each of the population approaches among the plurality of population approaches in which the effect index increases as the implementation index increases in the prediction model, calculates the implementation index and the effect index of the group, A healthcare business support server that selects, as the recommended population approach, a population approach determined to have a low calculated implementation index based on the first condition and a low calculated effect index based on the second condition among the population approaches, and having a high correlation coefficient between the implementation index and the effect index indicated by the prediction model based on a predetermined third condition.

4. The healthcare business support server according to claim 3, the processor, receives an input of a value for calculating an estimated value of the recommended population approach, calculates an estimated value of the implementation index of the recommended population approach based on the received input value and at least some of the information on the attribute and the health examination results, calculates an estimated value of the effect index of the recommended population approach based on the estimated value of the implementation index and the prediction model, A healthcare business support server that generates data for outputting the calculated effect index and the estimated value of the calculated effect index.

5. The healthcare business support server according to claim 1, wherein the personal attribute information indicates the attributes of individuals belonging to the group in the first period and the second period, the health examination information indicates the health examination results of individuals in the first period and the second period, the processor, Execute the matching and substitution processes based on the personal attribute information and the health examination results during the first period. Calculate the implementation indicators and effect indicators used for selecting the recommended population approach based on at least some of the information on the attributes indicated by the personal attribute information, the health examination results indicated by the health examination information, and the health examination results substituted in the substitution process during the first period, during the first period. For each individual in the no-health-examination group among the individuals belonging to the group during the second period who are not included in the health examination information during the second period, match them with the individuals in the health-examination group among the individuals belonging to the group during the second period who are included in the health examination information during the second period, based on the attributes indicated by the personal attribute information during the second period. Execute the substitution process during the second period, where for each individual in the no-health-examination group for whom the matching is successful, substitute the health examination results indicated by the health examination information of the individuals in the health-examination group for whom the matching is successful as their health examination results. Calculate the implementation indicators and effect indicators of the recommended population approach for the group during the second period based on at least some of the information on the attributes indicated by the personal attribute information, the health examination results indicated by the health examination information, and the health examination results substituted in the substitution process during the second period, during the second period. A health care business support server that generates data for outputting the implementation indicators and effect indicators of the recommended population approach during the first period, and the implementation indicators and effect indicators of the recommended population approach during the second period.

6. A health care business support server, including a processor and a memory, wherein the memory holds personal attribute information indicating the attributes of individuals belonging to a group, and health examination information indicating the health examination results of individuals, and the processor matches each individual in the no-health-examination group among the individuals belonging to the group who are not included in the health examination information, based on the attributes indicated by the personal attribute information, with the individuals in the health-examination group among the individuals belonging to the group who are included in the health examination information. Executes a substitution process of substituting, as the health examination results of each individual in the no-health-examination group for whom the matching is successful, the health examination results indicated by the health examination information of the individuals in the health-examination group for whom the matching is successful. The memory Holds population approach information indicating a plurality of population approaches, implementation indicators for evaluating the implementation status of each of the plurality of population approaches, and effect indicators for evaluating the effects of each of the plurality of population approaches. The implementation indicators and the effect indicators are defined by at least some information of the attributes and the health check results. The processor Based on at least some information of the attributes indicated by the personal attribute information, the health check results indicated by the health check information, and the health check results substituted in the substitution process, for each of the plurality of population approaches, calculate the implementation indicators and the effect indicators of the group. For each of the plurality of population approaches A first region, which is a region where the calculated implementation indicator is low based on a predetermined first condition and the calculated effect indicator is low based on a predetermined second condition. A second region, which is a region where the calculated implementation indicator is high based on a predetermined first condition and the calculated effect indicator is low based on a predetermined second condition. A third region, which is a region where the calculated implementation indicator is low based on a predetermined first condition and the calculated effect indicator is high based on a predetermined second condition. A fourth region, which is a region where the calculated implementation indicator is high based on a predetermined first condition and the calculated effect indicator is high based on a predetermined second condition. A health care business support server that generates data for outputting information indicating which quadrant among the first region, the second region, the third region, and the fourth region the calculated implementation indicator and the effect indicator belong to.

7. The health care business support server according to claim 1 or 6, wherein The memory Holds medical information indicating the results of medical treatment received by an individual. The processor Among the individuals in the group without a health check, identify a group without a health check and without medical treatment consisting of individuals not included in the medical information, and a group without a health check and with medical treatment consisting of individuals included in the medical information. Among the individuals in the group with a health check, identify a group with a health check and without medical treatment consisting of individuals not included in the medical information, and a group with a health check and with medical treatment consisting of individuals included in the medical information. Match each individual in the group without a health check and without medical treatment with an individual in the group with a health check and without medical treatment based on the attributes indicated by the personal attribute information. For each individual in the group without health check but with medical treatment, match them with the individuals in the group with health check and medical treatment based on the attributes indicated by the individual attribute information and the medical results indicated by the medical information. As the substitution process, As the health check results for each individual in the group without health check and without medical treatment for whom the matching is successful, a first substitution process of substituting the health check results indicated by the health check information of the individual in the group with health check and without medical treatment for whom the matching is successful, and As the health check results for each individual in the group without health check but with medical treatment for whom the matching is successful, a second substitution process of substituting the health check results indicated by the health check information of the individual in the group with health check and with medical treatment for whom the matching is successful, are executed by a health care business support server.

8. The health care business support server according to claim 1 or 6, wherein the processor generates data for outputting the health check results after the substitution process for the group without health check and information indicating the health check results of the group without health check.

9. A health care business support method by a health care business support server, wherein the health care business support server includes a processor and a memory, and the memory holds individual attribute information indicating the attributes of individuals belonging to a group, and health check information indicating the health check results of individuals, and the health care business support method includes the processor matching each individual in the group without health check not included in the health check information among the individuals belonging to the group with the individuals in the group with health check included in the health check information among the individuals belonging to the group based on the attributes indicated by the individual attribute information, the processor executing a substitution process of substituting, as the health check results for each individual in the group without health check for whom the matching is successful, the health check results indicated by the health check information of the individual in the group with health check for whom the matching is successful, the memory holds population approach information indicating a plurality of population approaches, implementation indicators for evaluating the implementation status of each of the plurality of population approaches, and effect indicators for evaluating the effects of each of the plurality of population approaches, wherein the implementation indicators and the effect indicators are defined by at least some information of the attributes and the health check results, and the health care business support method Based on at least some of the information on the attributes indicated by the personal attribute information, the health check results indicated by the health check information, and the health check results substituted in the substitution process, for each of the plurality of population approaches, the processor calculates the implementation index and the effect index of the group. The processor selects, as a recommended population approach, a population approach for which it is determined that the calculated implementation index is low based on a predetermined first condition and the calculated effect index is low based on a predetermined second condition. A health care business support method in which the processor generates data for outputting information indicating the recommended population approach. [

10. ] A health care business support method by a health care business support server, The health care business support server includes a processor and a memory. The memory holds personal attribute information indicating the attributes of individuals belonging to the group, and health check information indicating the health check results of individuals. The health care business support method For each individual in the group without a health check that is not included in the health check information, the processor matches each individual in the group without a health check with an individual in the group with a health check included in the health check information based on the attributes indicated by the personal attribute information. The processor executes a substitution process of substituting, as the health check result of each individual in the group without a health check for which the matching is successful, the health check result indicated by the health check information of the individual in the group with a health check for which the matching is successful. The memory holds population approach information indicating a plurality of population approaches, an implementation index for evaluating the implementation status of each of the plurality of population approaches, and an effect index for evaluating the effect of each of the plurality of population approaches. The implementation index and the effect index are defined by at least some of the information on the attributes and the health check results. The health care business support method Based on at least some of the information on the attributes indicated by the personal attribute information, the health check results indicated by the health check information, and the health check results substituted in the substitution process, for each of the plurality of population approaches, the processor calculates the implementation index and the effect index of the group. For each of the plurality of population approaches, the processor A first region, which is a region where the calculated implementation index is low based on a predetermined first condition and the calculated effect index is low based on a predetermined second condition; A second region, which is a region where the calculated implementation index is high based on a predetermined first condition and the calculated effect index is low based on a predetermined second condition; A third region, which is a region where the calculated implementation index is low based on a predetermined first condition and the calculated effect index is high based on a predetermined second condition; A fourth region, which is a region where the calculated implementation index is high based on a predetermined first condition and the calculated effect index is high based on a predetermined second condition; A health care business support method for generating data for outputting information indicating which quadrant among the first region, the second region, the third region, and the fourth region the calculated implementation index and the calculated effect index belong to.

Images