Risk analysis support system and risk analysis support method

Abstract

To appropriately determine the priority of health guidance for preventing changes in health conditions such as the onset or aggravation of diseases.SOLUTION: A risk analysis support system includes a processor and a storage device connected to the processor. The storage device holds health information about health of a plurality of persons, attribute information on the plurality of persons, and definition information on a plurality of health conditions. The processor builds a risk model for calculating a risk that the health conditions may change based on the health information, the attribute information, and the definition information on the plurality of health conditions, calculates a risk value indicating the risk that the health conditions of the plurality of persons may change based on the health information, the attribute information, and the risk model, and calculates the priority of health guidance for the plurality of persons based on the risk value.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technology for supporting analysis of the risk of changes in health status. [Background technology]

[0002] Health insurers, which operate based on health insurance premiums, strive to reduce medical expenses and improve future income and expenditures by implementing health programs that contribute to maintaining and improving the health of their subscribers. Maintaining and improving the health of subscribers requires securing the human resources to provide health guidance, and it is difficult to provide services to all subscribers. Therefore, in order to maximize cost-effectiveness with limited resources, it is necessary to identify and select recipients of guidance. Previously, technologies for identifying recipients using medical expense information have been disclosed.

[0003] For example, Japanese Patent Application Laid-Open Publication No. 2012-128670 (Patent Document 1) states, "A health business support system that selects health guidance recipients based on medical receipt information, health checkup information, and health guidance information, characterized by comprising: a medical expense model creation unit that creates a medical expense model showing predicted medical expenses for each severity and test value of the health insurance subscriber; a test value improvement model creation unit that creates a test value improvement model showing the amount of improvement for each severity and test value; a predicted medical expense reduction effect calculation unit that calculates the predicted amount of medical expense reduction due to health guidance for each severity and test value; and a target selection unit that selects health insurance subscribers who belong to the severity and test value with the highest predicted amount of medical expense reduction as health guidance recipients." [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-128670 Summary of the Invention [Problem to be solved by the invention]

[0005] The method described in Patent Document 1 uses a technique for estimating future expected medical expenses to calculate the expected reduction in medical expenses if test values ​​improve through health guidance, and selects recipients based on this value. However, this method uses medical expenses as the selection criterion and does not take into account risks of developing illness, hospitalization, or other events other than medical expenses. Therefore, in order to solve the above problem, the present invention aims to enable effective selection of recipients by prioritizing recipients of guidance in consideration of risks related to multiple diseases or multiple severity levels of diseases. [Means for solving the problem]

[0006] In order to solve at least one of the above problems, a representative example of the invention disclosed in the present application is a risk analysis support system, comprising: a processor; and a storage device connected to the processor, wherein the storage device holds health information relating to the health of a plurality of persons, attribute information of the plurality of persons, and definition information of a plurality of health states; the processor constructs a risk model for calculating a risk of a change in the health state based on the health information, the attribute information, and the definition information of the plurality of health states; calculates a risk value indicating a risk of a change in the health state of the plurality of persons based on the health information, the attribute information, and the risk model; and performs risk analysis on the plurality of persons based on the risk value. health Calculate instruction priorities the risk model includes a risk model for calculating, for each of the health states, a risk of a change to the health state occurring, the storage device holds a threshold for determining, for each of the health states, whether or not a change to the health state will occur based on the risk of the change to the health state occurring, and the processor calculates, for each of the health states, a risk value indicating the risk of a change to the health state occurring, corrects, for each of the health states, the risk value based on the threshold, and calculates priorities of health guidance for the plurality of persons based on the corrected risk value. It is characterized by: [Effects of the Invention]

[0007] According to one aspect of the present invention, it is possible to appropriately determine the priority of health guidance to prevent changes in health status such as the onset or worsening of disease. Objects, configurations, and effects other than those described above will become apparent from the following description of the examples. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing an example of the configuration of a risk analysis support system according to a first embodiment of the present invention. [Figure 2] FIG. 2 is an explanatory diagram showing an example of basic medical examination information managed by a medical examination history information management unit according to the first embodiment of the present invention. [Figure 3] FIG. 2 is an explanatory diagram showing an example of disease name information managed by a medical examination history information management unit according to the first embodiment of the present invention. [Figure 4] FIG. 2 is an explanatory diagram showing an example of medical treatment information managed by a medical treatment history information management unit according to the first embodiment of the present invention. [Figure 5] FIG. 2 is an explanatory diagram showing an example of medical checkup information managed by a medical checkup information management unit according to the first embodiment of the present invention. [Figure 6] FIG. 2 is an explanatory diagram illustrating an example of attribute information managed by an attribute information management unit according to the first embodiment of the present invention. [Figure 7] FIG. 2 is an explanatory diagram illustrating an example of severity definition information managed by an analysis data management unit according to the first embodiment of the present invention. [Figure 8] FIG. 2 is an explanatory diagram showing an example of severity assessment result information managed by an analysis data management unit according to the first embodiment of the present invention. [Figure 9] FIG. 2 is an explanatory diagram illustrating an example of training history information managed by an analysis data management unit according to the first embodiment of the present invention. [Figure 10] FIG. 2 is an explanatory diagram showing an example of risk model parameter information managed by a risk model information management unit according to the first embodiment of the present invention. [Figure 11] FIG. 2 is an explanatory diagram showing an example of subject extraction information managed by a subject extraction information management unit according to the first embodiment of the present invention. [Figure 12] 10 is a flowchart illustrating an example of a process executed by a state determination unit according to the first embodiment of the present invention. [Figure 13] 1 is a flowchart showing an example of processing executed by a risk model construction unit according to the first embodiment of the present invention. [Figure 14] 10 is a flowchart illustrating an example of processing executed by a risk value calculation unit according to the first embodiment of the present invention. [Figure 15] 10 is a flowchart illustrating an example of processing executed by a subject extraction unit according to the first embodiment of the present invention. [Figure 16]FIG. 2 is an explanatory diagram illustrating an example of a user interface corresponding to the processing of a state determination unit and a risk model construction unit according to the first embodiment of the present invention. [Figure 17] FIG. 2 is an explanatory diagram showing an example of a user interface corresponding to the processing of a risk value calculation unit and a subject extraction unit according to the first embodiment of the present invention. [Figure 18] FIG. 10 is a block diagram showing an example of the configuration of a risk analysis support system according to a second embodiment of the present invention. [Figure 19] FIG. 10 is an explanatory diagram showing an example of target disease definition information managed by an analysis data management unit according to a second embodiment of the present invention. [Figure 20] FIG. 10 is an explanatory diagram showing an example of severity assessment result information managed by an analysis data management unit according to the second embodiment of the present invention. [Figure 21] FIG. 10 is an explanatory diagram showing an example of model-specific discrimination threshold information managed by a risk model information management unit according to the second embodiment of the present invention. [Figure 22] FIG. 10 is an explanatory diagram showing an example of risk correction result information managed by a risk model information management unit according to the second embodiment of the present invention. [Figure 23] FIG. 10 is an explanatory diagram showing an example of subject extraction information managed by a subject extraction information management unit according to the second embodiment of the present invention. [Figure 24] 10 is a flowchart showing an example of processing executed by a risk model construction unit according to the second embodiment of the present invention. [Figure 25] 10 is a flowchart showing an example of processing executed by a subject extraction unit 114 and a risk value correction unit 115 according to the second embodiment of the present invention. [Figure 26] FIG. 10 is an explanatory diagram showing an example of a user interface corresponding to the processing of the state determination unit 112 and the risk model construction unit 111 according to the second embodiment of the present invention. [Figure 27] FIG. 10 is an explanatory diagram showing an example of a user interface corresponding to the processing of the risk value calculation unit, the subject extraction unit, and the risk value correction unit according to the second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. [Example]

[0010] FIG. 1 is a block diagram showing an example of the configuration of a risk analysis support system 101 according to the first embodiment of the present invention.

[0011] The risk analysis support system 101 is a computer system and includes an input unit 102 such as a keyboard and mouse, an output unit 103 representing a display that outputs display data, a CPU (Central Processing Unit) 104, a memory 105, a communication unit 108, and a storage medium 106.

[0012] The risk analysis support system 101 has a risk model construction unit 111, a state determination unit 112, a risk value calculation unit 113, and a subject extraction unit 114. The functions of each unit from the risk model construction unit 111 to the subject extraction unit 114 are realized by the CPU 104 executing a program stored in the storage medium 106. When these programs are executed by the CPU 104, at least a part of them may be copied to the memory 105 as necessary.

[0013] A database 107 is connected to the risk analysis support system 101. The database 107 has a medical examination history information management unit 120, a health checkup information management unit 121, an attribute information management unit 122, an analysis data management unit 123, a risk model information management unit 124, and a subject extraction information management unit 125. In this embodiment, the medical examination history information management unit 120 manages basic medical examination information 200 (FIG. 2), disease name information 300 (FIG. 3), and medical treatment information 400 (FIG. 4), which will be described later. The health checkup information management unit 121 manages health checkup information 500 (FIG. 5), which will be described later. The attribute information management unit 122 manages attribute information 600 (FIG. 6), which will be described later. The analysis data management unit 123 manages severity definition information 700 (FIG. 7), severity determination result information 800 (FIG. 8), and guidance history information 900 (FIG. 9), which will be described later. The risk model information management unit 124 manages risk model parameter information 1000 (FIG. 10) which will be described later. The subject extraction information management unit 125 manages subject extraction information (FIG. 11) which will be described later.

[0014] The database 107 may be stored in a storage system connected to the risk analysis support system 101 via a network, for example, or may be built into the risk analysis support system 101 (for example, by being stored in the storage medium 106). When the database 107 is stored in a system external to the risk analysis support system 101, at least a portion of its contents may be copied to the storage medium 106 or memory 105 as necessary. Furthermore, the entire system including the computer having the input unit 102, output unit 103, CPU 104, memory 105, and storage medium 106, and the database 107 may be referred to as the risk analysis support system.

[0015] 1, the risk analysis support system 101 may be realized by one computer having the configuration shown in Fig. 1, or may be realized by multiple computers. For example, the information held in the database 107 described above may be stored in a distributed manner in multiple storage media 106 or memories 105, and the functions of the risk analysis support system 101 described above may be executed in a distributed manner by multiple CPUs 104 of multiple computers.

[0016] FIG. 2 is an explanatory diagram showing an example of basic medical examination information 200 managed by the medical examination history information management unit 120 according to the first embodiment of the present invention.

[0017] The basic medical examination information 200 is information on the medical examination history of each person at a medical institution. This information may be collected from, for example, receipts prepared by the medical institution, but is not limited to this and any information that indicates when and who used the medical institution to receive medical treatment can be used.

[0018] The basic medical examination information 200 includes an individual ID 201 that identifies each person, a medical examination history ID 202 that identifies medical examinations each person has received in the past, a medical institution code 203 that indicates the medical institution where the examination was performed, a medical examination year and month 204 that indicates the year and month of the examination, a total points 205 that indicates information about the medical expenses corresponding to the examination, a medical examination type 206 that indicates information about the type of medical examination received (e.g., inpatient or outpatient), and a medical examination days 207 that indicates the number of days required for the examination. When the above-mentioned medical examination history information is collected from medical receipts, the medical examination history ID 202 may identify the medical receipts. With this information, it is possible to perform aggregation and analysis based on information indicating the medical examination history, such as medical receipts.

[0019] FIG. 3 is an explanatory diagram showing an example of the illness name information 300 managed by the medical examination history information management unit 120 according to the first embodiment of the present invention.

[0020] The injury / illness name information 300 is information about the injury or illness extracted from the medical history information, and includes the medical history 202 for identifying the medical treatment received, the injury / illness name 302 indicating the injury or illness for which treatment was given, the injury / illness code 303 corresponding to the injury / illness name, the main injury / illness flag 304 assigned to the illness that has required the most medical resources among multiple illnesses, and the suspicion flag 305 indicating that an examination has been conducted to confirm whether the patient has the injury or illness in question, and that the state is still undetermined.

[0021] In the example of Fig. 3, the value "1" of the main illness flag 304 indicates that the illness is the main illness, and the value "1" of the suspicion flag 305 indicates that the illness is suspected.

[0022] For example, if one patient receives medical treatment for multiple illnesses within a month, multiple sets of illness name 302, illness code 303, main illness flag 304, and suspicion flag 305 are associated with the same medical history ID 202. Furthermore, each record of the illness name information 300 is associated with the individual ID 201 via the medical history ID 202. Using the illness name information 300 makes it possible to perform analysis by illness.

[0023] FIG. 4 is an explanatory diagram showing an example of medical treatment information 400 managed by the medical treatment history information management unit 120 according to the first embodiment of the present invention.

[0024] The medical treatment information 400 is information about the medical treatment performed on the patient in each month, extracted from the medical treatment history information, and includes a medical treatment history ID 202 for identifying the treatment received, a medical treatment name 402 indicating the medical treatment performed on the patient, a medical treatment code 403 corresponding to the medical treatment, a medical treatment point number 404 determined for each medical treatment, and information 405 for the first day indicating the day the medical treatment was performed to information 408 for the 31st day. Each record of the medical treatment information 400 is associated with an individual ID 201 via the medical treatment history 202.

[0025] The information on the 1st day 405 to the information on the 31st day 408, which indicate the days on which the medical procedure was performed, is information indicating whether or not the medical procedure indicated by the medical procedure name 402 was performed on each day from the 1st to the 31st of the month. Figure 4 shows the information on the 1st day 405, the information on the 2nd day 406, the information on the 3rd day 407, and the information on the 31st day 408 as examples, but in reality, the information on the 4th to the 30th days is also included. This information makes it possible to perform analysis by medical procedure.

[0026] FIG. 5 is an explanatory diagram showing an example of the medical checkup information 500 managed by the medical checkup information management unit 121 according to the first embodiment of the present invention.

[0027] The medical checkup information 500 is information about the results of a medical checkup (health check) taken by each person, and includes an individual ID 201, a medical checkup ID 502 that identifies the medical checkup, a medical checkup year 503 that indicates the year the medical checkup was taken, a BMI (Body Mass Index) 504, fasting blood glucose 505, HbA1c 506, creatinine 507, and medical interview results 508. The medical interview results 508 may include, for example, information indicating whether or not the person has a drinking habit or an exercise habit. The above BMI 504 to creatinine 507 are representative examples of information obtained as a result of a medical checkup. In reality, the medical checkup information 500 does not need to include at least one of these, and may also include information on other items (e.g., systolic blood pressure, diastolic blood pressure, etc.). This information enables analysis based on health status.

[0028] FIG. 6 is an explanatory diagram illustrating an example of attribute information 600 managed by the attribute information management unit 122 according to the first embodiment of the present invention.

[0029] Attribute information 600 is information about the attributes of each person, and includes personal ID 201, gender 602, date of birth 603, enrollment date 604 indicating the date of enrollment in health insurance for each person, and withdrawal date 605 indicating the date of withdrawal from health insurance. This information enables analysis according to each person's age, gender, number of years of follow-up, etc.

[0030] FIG. 7 is an explanatory diagram showing an example of severity definition information 700 managed by the analysis data management unit 123 according to the first embodiment of the present invention.

[0031] The severity definition information 700 is definition information for determining the severity of a disease based on each person's medical history information, health checkup information, etc., and includes a definition ID 701, definition content 702, and judgment level 703. When information obtained from a person's medical history, health checkup results, etc. corresponds to the value of the definition content 702, the value of the judgment level 703 is determined as the severity of the disease for that person. In this embodiment, four severity levels are defined, ranging from "0" indicating no onset to "3" indicating the most severe symptoms.

[0032] For example, the first line of the severity definition information 700 shown in FIG. 7 indicates that the severity level is determined to be "0" when the fasting blood glucose level is less than 126 and the HbA1c level is less than 6.5. The second line indicates that the severity level is determined to be "1" when the fasting blood glucose level is 126 or more and the HbA1c level is 6.5 or more. The third line indicates that the severity level is determined to be "2" when there are diabetic complications. The fourth line indicates that the severity level is determined to be "3" when there are chronic renal failure. For example, each person's fasting blood glucose and HbA1c may be obtained from the medical examination information 500, and whether each person has diabetic complications and whether each person has chronic renal failure may be obtained from the basic medical examination information and the disease name information. The severity definition information 700 enables the severity of each person to be determined based on medical examination history information, medical examination information, etc.

[0033] FIG. 8 is an explanatory diagram showing an example of severity assessment result information 800 managed by the analysis data management unit 123 according to the first embodiment of the present invention.

[0034] The severity assessment result information 800 is information showing the results of assessing the severity based on each person's medical history information, health checkup information, etc., and the severity definition information 700, and includes personal ID 201, target year 802, whether or not the person is eligible for severity level 0 803, whether or not the person is eligible for severity level 1 804, whether or not the person is eligible for severity level 2 805, whether or not the person is eligible for severity level 3 806, and assessment result 807.

[0035] Individual ID 201 is information that identifies a person. Target year 802 indicates the target year for severity determination. Severity level 0 applicability 803 to severity level 3 applicability 806 indicate whether or not information such as medical examination history and medical checkup results for each person in the target year corresponds to severity levels 0 to 3 defined by severity definition information 700. In the example of FIG. 8, "1" indicates applicability and "0" indicates non-applicability. Determination result 807 indicates the severity level determined based on the information on severity level 0 applicability 803 to severity level 3 applicability 806.

[0036] For example, the first line of the severity assessment result information 800 shown in FIG. 8 indicates that the medical examination history and health check results for the person with personal ID "P001" in 2018 correspond to severity level 0, not to severity levels 1 to 3, and as a result, the severity level for that person for that year was determined to be "0." Furthermore, lines 10 to 12 indicate the assessment results for the person with personal ID "P003" from 2019 to 2021. In 2019, the medical examination history and health check results correspond to severity level 1, not to severity levels 2 or 3, and as a result, the highest of the corresponding severity levels, "1," was determined as the severity level for that person for that year. In 2020, the medical examination history and health check results correspond to severity levels 1 and 2, not to severity level 3, and as a result, the highest of the corresponding severity levels, "2," was determined as the severity level for that person for that year. In fiscal year 2021, the medical history and health checkup results corresponded to severity levels 1 to 3, and as a result, the highest severity level, "3," was determined as the severity level for the person in question for that year.

[0037] FIG. 9 is an explanatory diagram showing an example of the training history information 900 managed by the analysis data management unit 123 according to the first embodiment of the present invention.

[0038] The guidance history information 900 is information that manages the history of health guidance provided to each person in the past, and includes the personal ID 201, the target year 902, whether or not guidance was provided for severity level 1 903, whether or not guidance was provided for severity level 2 904, whether or not guidance was provided for severity level 3 905, a flag indicating that the person is not eligible for guidance 906, and reasons for determining whether or not the person is eligible for guidance 907.

[0039] The individual ID 201 is information for identifying a person. The target year 902 indicates the year in which the person is the target of health guidance. The severity level 1 guidance implementation status 903 to severity level 3 guidance implementation status 905 indicate whether or not health guidance corresponding to each severity level has been provided to each person. The non-guideline target flag 906 indicates whether or not each person has health The reason for determining whether or not a person is subject to guidance is 907. health If it is determined that the student is not eligible for guidance, the reason for this will be indicated.

[0040] For example, the first line of the training history information 900 shown in FIG. 9 indicates which severity level corresponds to the person with personal ID “P001” in 2020. health Also, the fourth line shows that the person with personal ID "P002" was assigned severity level 1 in 2019. health The guidance was given to the person and the same guidance was given to the person over several years. health The fifth line indicates that the person with personal ID "P003" is currently not subject to health guidance because the guidance has been given. health This indicates that guidance has been given and that the person is no longer subject to health guidance because treatment has already begun for the person at a medical institution.

[0041] health If the purpose of guidance is to reduce medical costs by preventing the onset and worsening of illness, it is expected that guidance will be more effective when given to individuals who have not yet received guidance, rather than giving the same guidance to the same individual multiple times. Also, for individuals whose condition has already progressed to a severe stage and who have begun treatment at a medical institution, the purpose of reducing medical costs has already been lost. For this reason, in such cases, health By excluding them from the scope of guidance, we can contribute to reducing medical costs by utilizing limited resources.

[0042] FIG. 10 is an explanatory diagram showing an example of risk model parameter information 1000 managed by the risk model information management unit 124 according to the first embodiment of the present invention.

[0043] The risk model parameter information 1000 includes a model ID 1001 that identifies the model (risk model) that assesses risk, a model name 1002 that indicates what type of model each model is, and model parameters 1003 that indicate the structure and parameters of the model.

[0044] For example, the risk model construction unit 111 generates one or more models for calculating a risk value of a change in the health condition of each person from the values ​​of at least one of the items of the person's medical examination history, medical examination results, and attributes, based on the basic examination information 200, illness name information 300, medical treatment information 400, health check information 500, attribute information 600, severity definition information 700, and severity determination result information 800. The type, structure, and parameters of the generated risk model are stored in risk model parameter information 1000.

[0045] Here, the risk value of a change in health status may be, for example, a value indicating the risk of developing any disease, or a value indicating the risk of a change (particularly worsening) in the severity of any disease. That is, the risk model parameter information 1000 may hold, for example, a risk model for calculating the risk of developing each type of disease, or a risk model for calculating the risk of a change in the severity of a specific disease. In this embodiment, a risk model for calculating the risk of developing and a change in the severity of a specific disease (e.g., diabetes) is held. Hereinafter, this embodiment will be described using an example in which the risk of developing and a change in the severity of a specific disease is calculated; however, it goes without saying that this embodiment can also be applied to, for example, calculating the risk of developing each type of disease.

[0046] In the example of Fig. 10, a model for calculating the risk of a person who has not yet developed a specific disease (for example, diabetes) developing the disease at severity level 1 or higher is held as a risk model with model ID "1." In this example, parameters of a model with age, fasting blood glucose, etc. as explanatory variables and the probability of developing the disease at severity level 1 or higher as a response variable are registered.

[0047] Similarly, a model for calculating the risk of a person with severity level 1 or less developing a disease with severity level 2 or higher is stored as a risk model with model ID "2." In this example, parameters of a model with age, sex, fasting blood glucose, creatinine, etc. as explanatory variables and the probability of developing a disease with severity level 2 or higher as the objective variable are registered. Furthermore, a model for calculating the risk of a person with severity level 2 or less developing a disease with severity level 3 or higher is stored as a risk model with model ID "3." In this example, parameters of a model with age, sex, urinary protein, creatinine, etc. as explanatory variables and the probability of developing a disease with severity level 3 or higher as the objective variable are registered.

[0048] While this example shows a model for calculating the probability of developing a disease with a severity level of a certain level or higher, a model for calculating the probability of developing a disease with a specific level of severity may also be created, such as a model for calculating the probability of developing a disease with a severity level of 1. Furthermore, while parameters of a regression model, for example, may be registered as model parameters, parameters of other models may also be registered as long as they are models that can predict risk values. This information makes it possible to calculate the risk of developing a disease for each severity level for each person.

[0049] FIG. 11 is an explanatory diagram showing an example of subject extraction information 1100 managed by the subject extraction information management unit 125 according to the first embodiment of the present invention.

[0050] The subject extraction information 1100 is information that manages the risk of disease development of each person calculated based on the risk model parameter information 1000 and the intervention priority calculated based on the risk. Fig. 11 shows, as an example, the subject extraction information 1100 made up of tables 1110, 1120, and 1130.

[0051] Table 1110 holds the probability of a person whose current severity level is "2" developing a severity level of 3 or higher, and the priority of intervention such as health guidance calculated based on the probability. Specifically, individual ID 1111 is information for identifying each person. Current level 1112 indicates the current severity level of each person (level "2" in this example). Level 3 or higher development probability 1113 indicates the probability of each person developing a severity level of 3 or higher, calculated using, for example, a risk model with model ID "3" in the risk model parameter information 1000. Intervention priority 1114 indicates the priority of intervention for each person. health This shows the priority of intervention such as guidance. In this example, a high intervention priority is given to people with a high probability of developing the disease.

[0052] Table 1120 holds the probability of developing a severity level of 2 or higher for a person whose current severity level is "1", and the intervention priority calculated based on the probability. Specifically, individual ID 1121 is information for identifying each person. Current level 1122 indicates the current severity level of each person (level "1" in this example). Level 2 or higher development probability 1123 indicates the probability of developing a severity level of 2 or higher for each person calculated using, for example, a risk model with model ID "2" in the risk model parameter information 1000. Intervention priority 1124 indicates the priority of intervention for each person. health This shows the priority of intervention such as guidance. In this example, a high intervention priority is given to people with a high probability of developing the disease.

[0053] Table 1130 holds the probability of developing a severity level of 1 or higher for a person whose current severity level is "0" (i.e., not yet developed), and the intervention priority calculated based on the probability. Specifically, individual ID 1131 is information for identifying each person. Current level 1132 indicates the current severity level of each person (level "0" in this example). Level 1 or higher development probability 1133 indicates the probability of developing a severity level of 1 or higher for each person calculated using, for example, a risk model with model ID "1" in the risk model parameter information 1000. Intervention priority 1134 is the priority for each person. healthThis shows the priority of intervention such as guidance. In this example, a high intervention priority is given to people with a high probability of developing the disease.

[0054] In the example of Fig. 11, because an intervention priority is set for each table, there may be, for example, multiple people with the highest intervention priority. In this case, the person with the highest severity level for intervention can ultimately be determined based on, for example, the type and amount of medical resources for treatment and the type and amount of resources for health guidance. For example, a person with a high intervention priority based on the probability of developing severity level 3 may be given top priority.

[0055] 11, the subject extraction information 1100 is divided into three tables for the sake of explanation, but in reality it may be a single table. For example, a single table including the personal ID of each person, the current severity level of each person, the onset probability of the severity level one level higher than the current severity level of each person, and the intervention priority of each person calculated based on the above may be held as the subject extraction information 1100.

[0056] FIG. 12 is a flowchart showing an example of processing executed by the state determination unit 112 according to the first embodiment of the present invention.

[0057] When the process starts (step 1201), the condition determination unit 112 reads the attribute information, medical checkup information, medical examination history information, and severity definition (steps 1202 to 1205). As a result, for example, the attribute information 600, medical checkup information 500, basic medical examination information 200, injury / illness name information 300, medical treatment information 400, and severity definition information 700 are read.

[0058] Next, the condition determination unit 112 generates a severity flag for each year for each person based on the read information (step 1206). As a result, for example, values ​​of severity level 0 applicable / unapplicable 803 to severity level 3 applicable / unapplicable 806 of the severity determination result information 800 are generated.

[0059] Next, the condition determination unit 112 generates severity determination result information for each year for each person based on the severity flag generated in step 1206 (step 1207). As a result, for example, a value of the determination result 807 of the severity determination result information 800 is generated, and the severity determination result information 800 is completed.

[0060] This completes the process (step 1208).

[0061] FIG. 13 is a flowchart showing an example of processing executed by the risk model construction unit 111 according to the first embodiment of the present invention.

[0062] When the process starts (step 1301), the risk model construction unit 111 sets the conditions for constructing a risk model (step 1302), which sets, for example, the time ranges of the explanatory variables and the objective variables, the age range of the target person, etc.

[0063] Next, the risk model construction unit 111 reads the attribute information, medical checkup information, medical examination history information, and severity assessment result (steps 1303 to 1306). As a result, for example, the attribute information 600, medical checkup information 500, basic medical examination information 200, injury / illness name information 300, medical treatment information 400, and severity assessment result information 800 are read.

[0064] Next, the risk model construction unit 111 creates an analysis data set (step 1307) based on the information read in steps 1303 to 1306 and the conditions set in step 1302. For example, the risk model construction unit 111 extracts information that meets the conditions set in step 1302 from the information read in steps 1303 to 1306, and compares it based on the person's ID, thereby creating an analysis data set that includes the value of the objective variable (in this example, the severity assessment result) and the corresponding value of the explanatory variable.

[0065] Next, the risk model construction unit 111 extracts data for model construction based on the analysis data set created in step 1307 (step 1308), and constructs a risk model (step 1309). The parameters of the constructed model are held as risk model parameter information 1000.

[0066] This completes the process (step 1310).

[0067] FIG. 14 is a flowchart showing an example of processing executed by the risk value calculation unit 113 according to the first embodiment of the present invention.

[0068] When the process starts (step 1401), the risk value calculation unit 113 reads the attribute information, medical checkup information, and medical examination history information (steps 1402 to 1404). As a result, for example, the attribute information 600, medical checkup information 500, basic medical examination information 200, disease name information 300, and medical treatment information 400 are read.

[0069] Next, the risk value calculation unit 113 constructs an evaluation data set based on the read information (step 1405). For example, the risk value calculation unit 113 extracts data corresponding to the explanatory variables of each person whose risk value is to be evaluated and whose intervention priority is to be determined from the information read in steps 1402 to 1404, and constructs data to be input into the risk model.

[0070] Next, the risk value calculation unit 113 determines the current severity level of each person based on the constructed evaluation data set, and determines the risk model to be applied to each person (step 1406).

[0071] Next, the risk value calculation unit 113 calculates the risk value for each severity level (i.e., the probability of onset of each severity level) for each target person by applying the risk model determined in step 1406 to the evaluation dataset constructed in step 1405 (step 1407).

[0072] Next, the risk value calculation unit 113 stores the risk value calculated in step 1407 (step 1408). For example, the calculated risk value is stored in any one of the level 3 or higher onset probability 1113, the level 2 or higher onset probability 1123, and the level 1 or higher onset probability 1133 in the subject extraction information 1100.

[0073] This completes the process (step 1409).

[0074] FIG. 15 is a flowchart showing an example of processing executed by the subject extraction unit 114 according to the first embodiment of the present invention.

[0075] When the process starts (step 1501), the subject extraction unit 114 sets extraction conditions (step 1502). For example, the age range of the target persons may be set, or conditions may be set such as how many people with the highest intervention priority should be extracted, how many people should be extracted for each severity level, and whether to give priority to people with high or low severity levels.

[0076] Next, the subject extraction unit 114 reads the risk assessment result (step 1503). For example, the probability of onset of each severity level for each person calculated by the risk value calculation unit 113 is read.

[0077] Next, the subject extraction unit 114 assigns priorities for providing interventions such as health guidance to the risk assessment results read in step 1503 (step 1504). For example, when risk assessment results such as the level 3 or higher onset probability 1113, the level 2 or higher onset probability 1123, and the level 1 or higher onset probability 1133 in the subject extraction information 1100 are read, priorities such as intervention priorities 1114, 1124, and 1134 are assigned.

[0078] Next, the subject extraction unit 114 stores the priority assigned in step 1504 as subject extraction information 1100 (step 1505).

[0079] This completes the process (step 1506). As a result, for example, a person with a high risk value is given a high priority. health Guidance will be given.

[0080] The subject extraction unit 114 may identify trends in risk value changes based on previously calculated risk values ​​and newly calculated risk values, in addition to the newly calculated risk values ​​as described above, and may reflect these results in determining the priority. For example, the subject extraction information management unit 125 may manage past risk value calculation results and increase the intervention priority for individuals whose risk value increases beyond a predetermined condition based on past risk values ​​and newly calculated risk values. In this way, a high priority may be assigned to individuals whose current risk value is not particularly high but whose risk value is increasing significantly.

[0081] Next, an example of a user interface provided by the risk analysis support system 101 when executing the processes shown in FIGS. 12 to 15 will be described with reference to FIGS.

[0082] FIG. 16 is an explanatory diagram showing an example of a user interface corresponding to the processing of the state determination unit 112 and the risk model construction unit 111 according to the first embodiment of the present invention.

[0083] The risk model construction screen 1600 shown in Figure 16 is an example of display data output by the risk analysis support system 101, and includes, for example, a data reading section 1601, a model construction condition setting section 1602, a model construction process execution button 1603, an analysis dataset creation result display section 1604, and a model construction result display section 1605.

[0084] Note that this display data may be output as an image by the output unit 103, or may be output by the communication unit 108. In the latter case, the display data may be transferred from the communication unit 108 via a network (not shown) to an external device (for example, a terminal device used by a user, not shown) and output as an image by the external device. In this case, information input via the screen is input using an input unit (not shown) of the external device, and input to the risk analysis support system 101 via the network and the communication unit 108. The same applies to other screens described later.

[0085] The conditions for data to be read for determining the condition are specified in the data reading unit 1601. For example, it is possible to specify the definition of the conditions for determining the health condition (specifically, for example, the conditions for determining the severity level), attribute information of the subject person, the subject's medical checkup results, the subject's medical history, etc. Based on the conditions specified here, reading is performed in steps 1202 to 1205.

[0086] Conditions for constructing a risk model are set in model construction condition setting section 1602. For example, the time range of data used as explanatory variables, the time range of data used as objective variables, and the age range of the target person can be specified. These conditions are specified in step 1302, and data that meets the specified conditions is read in steps 1303 to 1306.

[0087] When the model construction process execution button 1603 is operated, the processes of the state determination section 112 and the risk model construction section 111 are executed in accordance with the conditions designated in the data reading section 1601 and the model construction condition setting section 1602 .

[0088] The analysis dataset creation result display section 1604 displays the analysis dataset created in step 1307. Specifically, for each person, for example, the severity level as an explanatory variable, attributes such as gender and age, information such as BMI and interview results obtained from medical checkup results, the presence or absence of a pre-existing condition obtained from medical examination history information, and the severity level as a target variable are displayed.

[0089] The model construction result display section 1605 displays information about the model constructed by the risk model construction section 111. For example, information equivalent to the risk model parameter information 1000 may be displayed.

[0090] FIG. 17 is an explanatory diagram showing an example of a user interface corresponding to the processing of the risk value calculation unit 113 and the subject extraction unit 114 according to the first embodiment of the present invention.

[0091] The subject extraction screen 1700 shown in Figure 17 is an example of display data output by the risk analysis support system 101, and includes, for example, a data reading section 1701, a subject extraction condition setting section 1702, a subject extraction execution button 1703, and a subject extraction result display section 1704.

[0092] The data reading unit 1701 is the same as the data reading unit 1601 in FIG.

[0093] The conditions for extracting subjects of intervention are set in the subject extraction condition setting section 1702. For example, the time range of data used as explanatory variables and the age range of the target persons can be specified.

[0094] When the subject extraction execution button 1703 is operated, the processes of the risk value calculation unit 113 and the subject extraction unit 114 are executed according to the conditions designated in the subject extraction condition setting unit 1702 .

[0095] The subject extraction result display section 1704 displays the results of the processing by the risk value calculation section 113 and the subject extraction section 114. For example, information equivalent to the subject extraction information 1100 may be displayed.

[0096] According to the above-described first embodiment, it is possible to appropriately determine the priority of health guidance for preventing changes in health conditions such as the onset or worsening of a disease. For example, it is possible to appropriately select and prioritize people who are at high risk of onset or worsening of a disease. healthBy providing guidance, we can hope to utilize limited resources and curb the rise in medical costs. [Example]

[0097] Next, a description will be given of a second embodiment of the present invention. Except for the differences described below, the components of the system of the second embodiment have the same functions as the components of the first embodiment shown in Figures 1 to 17 and denoted by the same reference numerals, and therefore, the description thereof will be omitted.

[0098] FIG. 18 is a block diagram showing an example of the configuration of a risk analysis support system 101 according to the second embodiment of the present invention.

[0099] In the risk analysis support system 101 of Example 2, the storage medium 106 further includes a risk value correction unit 115. There are differences in the processing of the risk model construction unit 111 and the subject extraction unit 114, as will be described later. There are also differences in the information managed by the analysis data management unit 123, the risk model information management unit 124, and the subject extraction information management unit 125 in the database 107, as will be described later. The function of the risk value correction unit 115, like the functions of the other units, is realized by the CPU 104 executing a program stored in the storage medium 106.

[0100] Furthermore, in Example 1, the risk of onset of a specific disease for each severity level of each person was calculated, and intervention priority was calculated based on the calculated risk. In contrast, in Example 2, the risk of onset of multiple diseases for each person is calculated, and intervention priority is calculated based on the calculated risk. The risk of onset of a specific disease for each severity level in Example 1 and the risk of onset of each disease in Example 2 are both examples of the risk of changes in a person's health condition. It goes without saying that Example 2 below can also be applied to the risk of onset of a specific disease for each severity level.

[0101] FIG. 19 is an explanatory diagram showing an example of target disease definition information 1900 managed by the analysis data management unit 123 according to the second embodiment of the present invention.

[0102] The target disease definition information 1900 is definition information for determining whether each person has developed a disease based on each person's medical history information, health checkup information, etc., and includes a definition ID 1901 that identifies each definition, a target disease name 1902 that identifies the disease that the definition targets, and an ICD10 definition 1903 that indicates the content of the definition. The ICD10 definition 1903 describes a code of the International Classification of Diseases (ICD10), 10th Revision. For example, codes indicating information defining type 2 diabetes, cardiovascular disease, cerebrovascular disease, etc. are described as the ICD10 definition 1903. For the sake of explanation, the second embodiment focuses on the above three diseases. However, in reality, the target disease definition information 1900 can include definition information for more diseases, and the presence or absence of the onset of many diseases can be determined in the processing described below. The target disease definition information 1900 makes it possible to determine whether each person has developed each disease based on medical history information, health checkup information, etc.

[0103] FIG. 20 is an explanatory diagram showing an example of severity assessment result information 2000 managed by the analysis data management unit 123 according to the second embodiment of the present invention.

[0104] The severity assessment result information 2000 is information showing the results of assessing whether or not each person has developed a disease based on each person's medical history information, health checkup information, etc., and the target disease definition information 1900, and includes personal ID 201, target year 2002, whether or not type 2 diabetes is present 2003, whether or not cardiovascular disease is present 2004, and whether or not cerebrovascular disease is present 2005.

[0105] Individual ID 201 is information that identifies a person. Target year 2002 indicates the year that is the target of the judgment. Type 2 diabetes mellitus applicable / not applicable 2003, cardiovascular disease applicable / not applicable 2004, and cerebrovascular disease applicable / not applicable 2005 indicate whether information such as medical examination history and health check results for each person in the target year corresponds to type 2 diabetes, cardiovascular disease, or cerebrovascular disease, respectively, as defined by target disease definition information 1900. In the example of FIG. 20, "1" indicates applicable, and "0" indicates non-applicable.

[0106] FIG. 21 is an explanatory diagram showing an example of model-specific discrimination threshold information 2100 managed by the risk model information management unit 124 according to the second embodiment of the present invention.

[0107] The model-specific discrimination threshold information 2100 includes a model ID 2101 that identifies the risk model, a model name 2102 that indicates what type of model each model is, model parameters 2103 that indicate the structure and parameters of the model, and a discrimination threshold 2104 that determines whether or not each disease has developed based on the risk value calculated by the risk model.

[0108] For example, the risk model construction unit 111 generates one or more models for calculating a risk value of a change in health condition of each person (onset of each disease in the second embodiment) from the values ​​of at least one item of each person's medical examination history, medical examination results, and attributes, based on the basic medical examination information 200, illness name information 300, medical treatment information 400, health check information 500, attribute information 600, target disease definition information 1900, and severity assessment result information 2000. The type, structure, parameters, etc. of the generated risk model are stored in model-specific identification threshold information 2100.

[0109] In the example of Figure 21, a model for calculating the risk of developing type 2 diabetes is held as a risk model with model ID "1." In this example, model parameters are registered with age, sex, fasting blood glucose, HbA1c, etc. as explanatory variables and the probability of developing type 2 diabetes as the objective variable, and 0.19 is also registered as the discrimination threshold. This indicates that if the probability of development calculated by the model exceeds 0.19, it is determined that type 2 diabetes has developed.

[0110] Similarly, a model for calculating the risk of developing cardiovascular disease is stored as a risk model with model ID "2." In this example, parameters of a model with age, sex, systolic blood pressure, diastolic blood pressure, etc. as explanatory variables and the probability of developing cardiovascular disease as the objective variable are registered, and 0.20 is registered as the discrimination threshold. Furthermore, a model for calculating the risk of developing cerebrovascular disease is stored as a risk model with model ID "3." In this example, parameters of a model with age, sex, systolic blood pressure, triglyceride, etc. as explanatory variables and the probability of developing cerebrovascular disease as the objective variable are registered, and 0.02 is registered as the discrimination threshold.

[0111] Although there are no limitations on the method for setting the value of the discrimination threshold 2104, it is desirable to set it so that discrimination performance is maximized. As an example, the point where sensitivity + specificity - 1 is maximized on an ROC (Receiver Operating Characteristic) curve may be set as the threshold. The model-specific discrimination threshold information 2100 makes it possible to calculate the risk of developing each disease for each person.

[0112] FIG. 22 is an explanatory diagram showing an example of risk correction result information 2200 managed by the risk model information management unit 124 according to the second embodiment of the present invention.

[0113] The risk correction result information 2200 is information indicating the result of calculating the risk of developing each disease for each person based on the risk model and the result of correcting the calculated risk based on the discrimination threshold. Specifically, the risk correction result information 2200 includes an individual ID 201, a type 2 diabetes development risk value 2202, a cardiovascular disease development risk value 2203, a cerebrovascular disease development risk value 2204, an adjusted type 2 diabetes development risk value 2205, an adjusted cardiovascular disease development risk value 2206, an adjusted cerebrovascular disease development risk value 2207, and a disease with the highest development risk 2208.

[0114] The individual ID 201 is information for identifying an individual. The type 2 diabetes onset risk value 2202, the cardiovascular disease onset risk value 2203, and the cerebrovascular disease onset risk value 2204 are values ​​indicating the risk of each individual developing type 2 diabetes (e.g., onset probability), the risk of developing cardiovascular disease (e.g., onset probability), and the risk of developing cerebrovascular disease (e.g., onset probability), respectively, calculated based on the corresponding risk model.

[0115] The adjusted type 2 diabetes onset risk value 2205, the adjusted cardiovascular disease onset risk value 2206, and the adjusted cerebrovascular disease onset risk value 2207 are values ​​obtained by adjusting the type 2 diabetes onset risk value 2202, the cardiovascular disease onset risk value 2203, and the cerebrovascular disease onset risk value 2204, respectively, based on the corresponding discrimination thresholds. The disease with the highest onset risk 2208 indicates the disease that is determined to have the highest onset risk based on the adjusted risk values.

[0116] For example, the first line of the risk correction result information 2200 shown in Fig. 22 indicates that the type 2 diabetes risk value calculated using the risk model for the person with personal ID "P001" is "0.25," and the risk value corrected based on the corresponding discrimination threshold of "0.19" is "0.06." In this example, the correction is performed by subtracting the discrimination threshold from the onset risk value calculated using the risk model.

[0117] Similarly, the first line indicates that the cardiovascular disease risk value of "0.24" for the person with personal ID "P001" is corrected to "0.04" based on the discrimination threshold of "0.20," and the cerebrovascular disease risk value of "0.23" is corrected to "0.21" based on the discrimination threshold of "0.02." As a result, the disease with the highest risk for the person with personal ID "P001" is determined to be cerebrovascular disease based on the corrected risk values.

[0118] Generally, for diseases with low incidence rates, the probability of onset, which is the output of a risk model, is lower than for diseases with high incidence rates, making it difficult to assess risk by simply comparing onset probabilities between diseases. However, if the onset probability is low, the discrimination threshold for determining whether or not a disease will develop is also low. Therefore, by using a value obtained by correcting the onset probability using the discrimination threshold as the risk value, it becomes possible to compare onset risks between diseases.

[0119] For example, in the above example, the risk values ​​of type 2 diabetes and cardiovascular disease for the person with personal ID "P001" are both slightly higher than the discrimination threshold, but the risk value of cerebrovascular disease is significantly higher than the discrimination threshold. From this, it can be determined that the person in question has the highest risk of developing cerebrovascular disease among these three diseases (i.e., the risk of developing cerebrovascular disease is high). health However, if we simply compare the incidence probability output from the risk model, it is determined that the risk of developing type 2 diabetes is the highest, and there is no need for intervention such as guidance. health Guidance will be provided.

[0120] In contrast to this, in this embodiment, by using the value obtained by correcting the incidence probability using the discrimination threshold as described above as the risk value, it is possible to determine that the risk of developing cerebrovascular disease is highest.

[0121] In the above example, correction is performed by subtracting the discrimination threshold from the onset risk value calculated using the risk model, but this is one example of a correction method, and at least one of the following corrections may be performed: a correction to lower the onset risk value of a disease with a relatively high discrimination threshold, or a correction to increase the onset risk value of a disease with a relatively low discrimination threshold.

[0122] FIG. 23 is an explanatory diagram showing an example of subject extraction information 2300 managed by the subject extraction information management unit 125 according to the second embodiment of the present invention.

[0123] The subject extraction information 2300 is information that manages the onset risk of each person calculated based on the risk model parameter information 1000, the onset risk corrected based on the discrimination threshold, and the intervention priority calculated based on the corrected onset risk. Fig. 23 shows, as an example, the subject extraction information 2300 made up of tables 2310, 2320, and 2330.

[0124] Table 2310 holds the risk of developing type 2 diabetes, the risk of developing type 2 diabetes corrected based on the discrimination threshold, and the priority of intervention such as health guidance calculated based on the corrected risk of developing type 2 diabetes. Specifically, individual ID 2311 is information for identifying each person. Target disease 2312 indicates the disease (in this example, type 2 diabetes) that is the target of calculation of the risk of developing type 2 diabetes and the intervention priority based on the risk of developing type 2 diabetes. Onset risk 2313 indicates the probability of developing type 2 diabetes for each person calculated using, for example, the risk model with model ID "1" in the model-specific discrimination threshold information 2011. Corrected onset risk 2314 indicates the risk of developing type 2 diabetes for each person corrected using the value "0.19" of the discrimination threshold 2104 for that model. Intervention priority 2315 indicates the priority of intervention for each person. health This shows the priority of interventions such as education. In this example, a high intervention priority is assigned to individuals with a high adjusted risk of developing the disease.

[0125] Table 2320 holds the risk of developing cardiovascular disease, the risk of developing cardiovascular disease corrected based on the discrimination threshold, and the priority of intervention such as health guidance calculated based on the corrected risk of developing cardiovascular disease. Specifically, individual ID 2321 is information for identifying each person. Target disease 2322 indicates the disease (cardiovascular disease in this example) that is the target of calculation of the risk of developing cardiovascular disease and the intervention priority based on the risk of developing cardiovascular disease. Onset risk 2323 indicates the probability of developing cardiovascular disease for each person calculated using, for example, the risk model with model ID "2" in the model-specific discrimination threshold information 2011. Corrected onset risk 2324 indicates the risk of developing cardiovascular disease for each person corrected using the value "0.20" of the discrimination threshold 2104 for that model. Intervention priority 2325 indicates the priority of intervention for each person. healthThis shows the priority of interventions such as education. In this example, a high intervention priority is assigned to individuals with a high adjusted risk of developing the disease.

[0126] Table 2330 holds the risk of developing cerebrovascular disease, the risk of developing cerebrovascular disease corrected based on the discrimination threshold, and the priority of intervention such as health guidance calculated based on the corrected risk of developing. Specifically, individual ID 2331 is information for identifying each person. Target disease 2332 indicates the disease (cerebrovascular disease in this example) that is the target of calculation of the risk of developing and the intervention priority based on the risk of developing cerebrovascular disease. Onset risk 2333 indicates the probability of developing cerebrovascular disease for each person calculated using, for example, the risk model with model ID "3" in the model-specific discrimination threshold information 2011. Corrected onset risk 2334 indicates the risk of developing cerebrovascular disease for each person corrected using the value "0.02" of the discrimination threshold 2104 for that model. Intervention priority 2335 indicates the priority of intervention for each person. health This shows the priority of interventions such as education. In this example, a high intervention priority is assigned to individuals with a high adjusted risk of developing the disease.

[0127] Table 2310 may include only information about individuals who have been determined to have the highest risk of developing type 2 diabetes based on the corrected risk of developing the disease. Similarly, table 2320 may include only information about individuals who have been determined to have the highest risk of developing cardiovascular disease based on the corrected risk of developing the disease, and table 2330 may include only information about individuals who have been determined to have the highest risk of developing cerebrovascular disease based on the corrected risk of developing the disease.

[0128] Next, the processing executed by the risk analysis support system 101 of the second embodiment will be described with reference to a flowchart. The processing executed by the state determination unit 112 of the second embodiment is the same as that of the first embodiment (see FIG. 12). However, the state determination unit 112 reads the target disease definition information 1900 in step 1205, determines whether each disease is applicable in step 1206, and stores the result as severity determination result information 2000.

[0129] FIG. 24 is a flowchart showing an example of processing executed by the risk model construction unit 111 according to the second embodiment of the present invention.

[0130] When the process starts (step 2401), the risk model construction unit 111 sets conditions for constructing a risk model (step 2402) and reads attribute information, medical checkup information, and medical examination history information (steps 2403 to 2405). These are the same as steps 1302 to 1305 (FIG. 13) in the first embodiment.

[0131] Next, the risk model construction unit 111 reads the severity determination result information 2000 (step 2406).

[0132] Next, the risk model construction unit 111 creates an analysis data set (step 2407) based on the information read in steps 2403 to 2406 and the conditions set in step 2402. For example, the risk model construction unit 111 extracts information that meets the conditions set in step 2402 from the information read in steps 2403 to 2406, and compares this information based on the person's ID, thereby creating an analysis data set that includes the values ​​of the objective variables (in this example, whether or not each disease is present) and the values ​​of the explanatory variables corresponding to those values.

[0133] Next, the risk model construction unit 111 extracts data for model construction based on the analysis data set created in step 2407 (step 2408), and constructs a risk model (step 2409). The parameters of the constructed model are held as model parameters 2103 in the model-specific discrimination threshold information 2100.

[0134] Next, the risk model construction unit 111 calculates a discrimination threshold (step 2410). As mentioned above, the method for calculating this threshold is not limited, but it is desirable to set it so as to maximize discrimination performance. The calculated discrimination threshold is stored as discrimination threshold 2104 in model-specific discrimination threshold information 2100.

[0135] This completes the process (step 2411).

[0136] The risk value calculation unit 113 of the second embodiment calculates risk values ​​using the risk model constructed by the above-mentioned processing in Fig. 24. The procedure is the same as in the first embodiment, so a description thereof will be omitted (see Fig. 14). The calculated risk values ​​are held, for example, as type 2 diabetes onset risk value 2202 to cerebrovascular disease onset risk value 2204 in the risk correction result information 2200.

[0137] FIG. 25 is a flowchart showing an example of processing executed by the subject extraction unit 114 and the risk value correction unit 115 according to the second embodiment of the present invention.

[0138] When the process starts (step 2501), the subject extraction unit 114 sets extraction conditions (step 2502). This process is the same as step 1502 (FIG. 15) in the first embodiment.

[0139] Next, the subject extraction unit 114 reads the risk assessment result (step 2503). Here, the risk of developing each disease for each person calculated by the risk value calculation unit 113 (for example, the type 2 diabetes development risk value 2202 to the cerebrovascular disease development risk value 2204 in the risk correction result information 2200) is read.

[0140] Next, the risk value corrector 115 corrects the risk values ​​read in step 2503 (step 2504). This correction is performed, for example, by the method described with reference to Fig. 22. The risk values ​​after correction are held, for example, as the corrected type 2 diabetes onset risk value 2205 to the corrected cerebrovascular disease onset risk value 2207 in the risk correction result information 2200.

[0141] Next, the subject extraction unit 114 assigns priorities for providing interventions such as health guidance based on the risk values ​​corrected in step 2504 (step 2505). For example, when corrected risk values ​​such as corrected onset risks 2314, 2324, and 2334 of the subject extraction information 2300 are read, priorities such as intervention priorities 2315, 2325, and 2335 are assigned. At this time, the subject extraction unit 114 may select individuals to whom priorities are assigned based on the corrected onset risks so that only information about individuals determined to have the highest risk of developing type 2 diabetes is included in table 2310, only information about individuals determined to have the highest risk of developing cardiovascular disease is included in table 2320, and only information about individuals determined to have the highest risk of developing cerebrovascular disease is included in table 2330.

[0142] Next, the subject extraction unit 114 stores the priority assigned in step 2305 as subject extraction information 2300 (step 2506).

[0143] This completes the process (step 2507).

[0144] Next, an example of a user interface provided by the risk analysis support system 101 according to the second embodiment will be described with reference to FIGS.

[0145] FIG. 26 is an explanatory diagram showing an example of a user interface corresponding to the processing of the state determination unit 112 and the risk model construction unit 111 according to the second embodiment of the present invention.

[0146] 26 is an example of display data output by the risk analysis support system 101, and includes, for example, a data reading section 2601, a model building condition setting section 2602, a model building process execution button 2603, an analysis dataset creation result display section 2604, and a model building result display section 2605. These are the same as the data reading section 1601, the model building condition setting section 1602, the model building process execution button 1603, the analysis dataset creation result display section 1604, and the model building result display section 1605 of the risk model building screen 1600 of Example 1, except for the following differences. The differences will be explained below.

[0147] The analytical dataset creation result display section 2604 displays the analytical dataset created in step 2407. Specifically, for each person, for example, attributes such as gender and age, which serve as explanatory variables, information such as BMI and interview results obtained from health checkup results, the presence or absence of a medical history obtained from medical examination history information, and onset diseases, which serve as objective variables, are displayed.

[0148] The model construction result display section 2605 displays information about the model constructed by the risk model construction section 111. For example, information corresponding to the model ID 2101, model name 2102, and model parameters 2103 included in the model-specific discrimination threshold information 2100 may be displayed.

[0149] FIG. 27 is an explanatory diagram showing an example of a user interface corresponding to the processing of the risk value calculation unit 113, the subject extraction unit 114, and the risk value correction unit 115 according to the second embodiment of the present invention.

[0150] 27 is an example of display data output by the risk analysis support system 101, and includes, for example, a data reading section 2701, a subject extraction condition setting section 2702, a subject extraction execution button 2703, and a subject extraction result display section 2704. These are similar to the data reading section 1701, subject extraction condition setting section 1702, subject extraction execution button 1703, and subject extraction result display section 1704 of the subject extraction screen 1700 in Example 1, except for the following differences. The differences will be explained below.

[0151] The subject extraction result display section 2704 displays the results of processing by the risk value calculation section 113, the subject extraction section 114, and the risk value correction section 115. For example, information equivalent to the subject extraction information 2300 may be displayed.

[0152] According to the above-described second embodiment, it is possible to appropriately determine the priority of health guidance for preventing changes in health status, such as the onset or worsening of a disease. In particular, even when the frequency of occurrence of a change in health status varies depending on the type of change in health status, it is possible to appropriately compare the risks of changes in health status and determine the priority, thereby preventing the risk of a disease or the like with a low occurrence frequency from being overlooked.

[0153] Furthermore, the system according to the embodiment of the present invention may be configured as follows.

[0154] (1) A risk analysis support system, comprising a processor (e.g., CPU 104) and a storage device connected to the processor (e.g., at least one of memory 105, storage medium 106, and other storage medium storing database 107), wherein the storage device holds health information relating to the health of a plurality of persons (e.g., information managed by medical examination history information management unit 120 and medical examination information management unit 121), attribute information of the plurality of persons (e.g., information managed by attribute information management unit 122), and definition information of a plurality of health conditions (e.g., at least one of severity definition information 700 and target disease definition information 1900), and the processor constructs a risk model for calculating the risk of a change in the health condition based on the health information, attribute information, and definition information of the plurality of health conditions (e.g., step 1309 or step 2409), calculates a risk value indicating the risk of a change in the health condition of the plurality of persons based on the health information, attribute information, and risk model (e.g., step 1407), and calculates a risk value for the plurality of persons based on the risk value. health The instruction priority is calculated (eg, step 1504 or step 2505).

[0155] This makes it possible to appropriately determine the priority of health guidance to prevent changes in health status such as the onset or worsening of disease.

[0156] (2) In (1) above, the definition information of the multiple health conditions includes information defining multiple severity levels of a specific disease (e.g., severity definition information 700), and the risk model includes a model for calculating the risk of the health condition changing from each severity level to a higher severity level (e.g., risk model parameter information 1000). The processor calculates the current severity levels of the multiple persons based on the health information and the definition information of the multiple health conditions (e.g., steps 1206 and 1207), calculates the risk of the health conditions of the multiple persons changing from the current severity level to a higher severity level as a risk value based on the health information, attribute information, and risk model (e.g., step 1407), and ranks the multiple persons for each current severity level such that the higher the risk of the health condition changing from the current severity level to a higher severity level, the higher the ranking. health Calculate the instruction priority (eg, step 1504).

[0157] (3) In (1) above, the definition information for the multiple health conditions includes information defining the onset of multiple diseases (e.g., target disease definition information 1900), and the risk model includes a model for calculating the risk of developing each of the multiple diseases (e.g., a risk model included in model-specific discrimination threshold information 2100), and the processor calculates the risk of multiple people developing each of the multiple diseases as a risk value based on the health information, attribute information, and risk model (e.g., step 1407), and ranks the multiple people for each disease so that the higher the risk of developing the disease, the higher the ranking. health Calculate the instruction priority (eg, step 2505).

[0158] (4) In the above (1), the storage device stores history information of health guidance provided to a plurality of people in the past (e.g., guidance history information 900), and the processor performs the following based on the history information: health Those who are judged not to require guidance health Exclude from instruction priority calculations.

[0159] (5) In the above (4), the processor executes the same program as that executed a predetermined number of times or more in the past based on the history information. health It is determined that no guidance is necessary.

[0160] (6) In the above (4), the history information includes information indicating whether treatment by a medical institution has been started for each of the plurality of persons, and the processor, based on the history information, determines whether treatment by a medical institution has been started for each of the persons. health It is determined that no guidance is necessary.

[0161] (7) In the above (1), the storage device stores risk values ​​calculated in the past for a plurality of people, and the processor calculates risk values ​​for the plurality of people based on a trend of change in the risk values ​​identified from the risk values ​​calculated in the past and the newly determined risk value. health Calculate instructional priorities.

[0162] (8) In (1) above, the health information includes at least one of information indicating the medical examination history of multiple persons at medical institutions (e.g., information managed by the medical examination history information management unit 120) and information indicating the results of health examinations taken by multiple persons (e.g., information managed by the health examination information management unit 121).

[0163] (9) In (1) above, the risk model includes a risk model (e.g., a risk model included in the model-specific discrimination threshold information 2100) for calculating, for each health state, the risk of a change to the health state occurring, and the storage device holds, for each health state, a threshold (e.g., discrimination threshold 2104 included in the model-specific discrimination threshold information 2100) for determining whether or not a change to the health state will occur based on the risk of the change to the health state occurring. The processor calculates, for each health state, a risk value indicating the risk of the change to the health state occurring (e.g., step 1407), corrects the risk value based on the threshold for each health state (e.g., step 2504), and performs risk assessments for multiple people based on the corrected risk values. health Calculate the instruction priority (eg, step 2505).

[0164] (10) In the above (9), the processor corrects the risk value by at least one of lowering the risk value of a health state with a high threshold and raising the risk value of a health state with a low threshold.

[0165] (11) In (9) above, the definition information for the multiple health conditions includes information defining the onset of multiple diseases (e.g., target disease definition information 1900), the risk model includes a model for calculating the risk of developing each of the multiple diseases (e.g., a risk model included in model-specific discrimination threshold information 2100), and the threshold is a threshold for determining whether or not each of the multiple diseases will develop. The processor calculates the risk of multiple people developing each of the multiple diseases as a risk value based on the health information, attribute information, and risk model (e.g., step 1407), and for each of the multiple people, identifies the disease with the highest corrected risk value as the disease with the highest onset risk, and ranks the multiple people so that, for each disease, the higher the corrected risk value, the higher the ranking of the people with the highest onset risk of the disease. health Calculate the instruction priority (eg, step 2505).

[0166] The present invention is not limited to the above-described embodiments, but includes various modifications. For example, the above-described embodiments have been described in detail to facilitate a better understanding of the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0167] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The above-described configurations, functions, etc. may also be implemented in software, with a processor interpreting and executing a program that implements each function. Information such as the programs, tables, and files that implement each function can be stored in storage devices such as nonvolatile semiconductor memory, hard disk drives, and solid-state drives (SSDs), or in computer-readable, non-transitory data storage media such as IC cards, SD cards, and DVDs.

[0168] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it can be considered that almost all components are interconnected. [Explanation of symbols]

[0169] 101 Risk Analysis Support System 102 Input section 103 Output section 104 CPU 105 memory 106 Storage medium 107 Database 108 Communications Department 111 Risk Model Construction Department 112 Status determination unit 113 Risk Value Calculation Unit 114 Subject Extraction Unit 115 Risk Value Correction Unit 120 Medical History Information Management Department 121 Health Checkup Information Management Department 122 Attribute information management department 123 Analysis Data Management Department 124 Risk Model Information Management Department 125 Target Extraction Information Management Department

Claims

1. A risk analysis support system, a processor and a storage device connected to the processor; the storage device holds health information relating to the health of a plurality of people, attribute information of the plurality of people, and definition information of a plurality of health conditions; The processor: constructing a risk model for calculating a risk of a change in the health state based on the health information, the attribute information, and definition information of the plurality of health states; calculating a risk value indicating a risk of a change in the health state of the plurality of persons based on the health information, the attribute information, and the risk model; calculating a priority order of health guidance for the plurality of persons based on the risk values; the risk model includes, for each of the health states, a risk model for calculating a risk of a change to the health state occurring; the storage device holds, for each of the health states, a threshold value for determining whether or not a change to the health state will occur based on a risk of the change to the health state occurring; The processor: Calculating a risk value for each of the health conditions that indicates the risk of a change to the health condition occurring; correcting the risk value for each of the health conditions based on the threshold; A risk analysis support system characterized by calculating priorities of health guidance for the plurality of individuals based on the risk values ​​after correction.

2. 2. The risk analysis support system according to claim 1, the plurality of health condition definition information includes information defining a plurality of severity levels of a particular disease; the risk model includes a model for calculating the risk of the health condition changing from each severity level to a higher severity level; The processor: Calculating a current severity level for the plurality of persons based on the health information and the definition information of the plurality of health conditions; calculating, as the risk value, a risk that the health state of the plurality of persons will change from a current severity level to a higher severity level based on the health information, the attribute information, and the risk model; A risk analysis support system characterized by calculating, for each of the plurality of persons' current severity levels, the priority of health guidance for the plurality of persons, such that the higher the risk that the health condition will change from the current severity level to a higher severity level, the higher the ranking.

3. 2. The risk analysis support system according to claim 1, The definition information of the plurality of health conditions includes information defining the onset of a plurality of diseases, the risk model includes a model for calculating a risk of developing each of the plurality of diseases; The processor: calculating a risk of the plurality of persons developing each of the plurality of diseases as the risk value based on the health information, the attribute information, and the risk model; A risk analysis support system characterized by calculating, for each of the diseases, the priority of health guidance for the plurality of people so that the higher the risk of developing the disease, the higher the priority.

4. 2. The risk analysis support system according to claim 1, the storage device stores history information of health guidance provided to the plurality of persons in the past; The risk analysis support system is characterized in that the processor excludes the person who is determined not to require health guidance based on the history information from the calculation of the priority of health guidance.

5. 5. The risk analysis support system according to claim 4, The risk analysis support system is characterized in that the processor determines, based on the history information, that the health guidance that has been given a predetermined number of times in the past is unnecessary.

6. 5. The risk analysis support system according to claim 4, the history information includes information indicating whether treatment has been started by a medical institution for each of the plurality of persons; The risk analysis support system is characterized in that the processor determines, based on the history information, that the health guidance is unnecessary for a person who has started treatment at a medical institution.

7. 2. The risk analysis support system according to claim 1, the storage device holds the risk values ​​previously calculated for the plurality of persons; The processor calculates health guidance priorities for the plurality of individuals based on trends in changes in the risk values ​​identified from risk values ​​calculated in the past and newly calculated risk values.

8. 2. The risk analysis support system according to claim 1, A risk analysis support system characterized in that the health information includes at least one of information indicating the medical institution visit history of the multiple persons and information indicating the results of health examinations undergone by the multiple persons.

9. A risk analysis support system according to claim 1, A risk analysis support system characterized in that the processor corrects the risk value by at least one of lowering the risk value of the health state for which the threshold is high and raising the risk value of the health state for which the threshold is low.

10. A risk analysis support system according to claim 1, The definition information of the plurality of health conditions includes information defining the onset of a plurality of diseases, the risk model includes a model for calculating a risk of developing each of the plurality of diseases; the threshold is a threshold for determining whether or not each of the plurality of diseases will develop, The processor: calculating a risk of the plurality of persons developing each of the plurality of diseases as the risk value based on the health information, the attribute information, and the risk model; For each of the plurality of people, the disease with the highest corrected risk value is identified as the disease with the highest risk of developing; A risk analysis support system characterized by calculating the priority of health guidance for the multiple individuals among those with the highest risk of developing the disease for each of the diseases, so that the higher the corrected risk value, the higher the ranking.

11. A risk analysis support method executed by a computer system, comprising: the computer system includes a processor and a storage device connected to the processor; the storage device holds health information relating to the health of a plurality of people, attribute information of the plurality of people, and definition information of a plurality of health conditions; The risk analysis support method includes: a first step in which the processor constructs a risk model for calculating a risk of a change in the health state based on the health information, the attribute information, and definition information of the plurality of health states; a second step of calculating a risk value indicating a risk of a change in the health state of the plurality of persons based on the health information, the attribute information, and the risk model; a third step of calculating priorities of health guidance for the plurality of persons based on the risk values, the risk model includes, for each of the health states, a risk model for calculating a risk of a change to the health state occurring; the storage device holds, for each of the health states, a threshold value for determining whether or not a change to the health state will occur based on a risk of the change to the health state occurring; the second step includes a step of the processor calculating, for each of the health states, a risk value indicating a risk of a change to the health state occurring; The risk analysis support method further includes a step of correcting the risk value for each of the health states based on the threshold value by the processor; The risk analysis support method, wherein the third step includes a step of the processor calculating priorities of health guidance for the plurality of people based on the corrected risk values.

Images