JP6863591B2 - Risk analysis system and risk analysis method - Google Patents

Description

The present invention relates to a technique for analyzing risks related to the health of a subject.

Even healthy people have a non-zero risk of developing the disease. In order to maintain a healthy and secure life, you should accurately understand your own health risks and their factors, take appropriate measures such as lifestyle improvement and necessary treatment, and in addition, in the future. As a precaution, it is important to take out medical insurance and make the necessary savings. By the way, when considering medical insurance and savings plans, estimate how much medical expenses will be incurred in the future (hereinafter referred to as "future medical expenses"), and make sure that there is no excess or deficiency in preparation. Should be. However, it is not easy for the general public to predict future medical expenses. Also, even if you consult with a specialist such as a financial planner, you may know the average future medical expenses, but it is not accurate because it is not a value that considers the health condition and health risks of each individual.

On the other hand, insurers who provide medical insurance also have a strong need to predict the health risks and future medical expenses of those who wish to take out insurance as accurately as possible. This is to help in the underwriting assessment of medical insurance and the design of contract conditions (insurance plan, insurance amount, special contract, etc.). However, at present, there is no mechanism that can predict future medical expenses with high reliability in consideration of the health condition and health risk of each individual.

As related prior art, for example, in Patent Document 1, the age, gender, content of life insurance (death insurance amount, type of insurance, type of special contract, etc.), result of medical examination (blood pressure, BMI, etc.) A system that automatically assesses whether or not life insurance can be underwritten and contract conditions is disclosed when a uric acid level, etc. is entered. In Patent Document 2, blood pressure measurement data of the insured is collected through a network, and the amount of insurance for the insured is determined according to the number of days of blood pressure measurement in the past 3 months and the ratio of blood pressure within the standard value. A system that fluctuates (such as hospitalization benefits) is disclosed. In Patent Document 3, medical expenses for each injury and illness in the case where a plurality of injuries and illnesses occur together are analyzed from the receipt information accumulated in a certain period, and the insured person whose medical expenses are rapidly increasing. A system that is useful for discovery and health guidance for the insured is disclosed. However, none of the documents disclose forecasts of future medical costs.

Japanese Unexamined Patent Publication No. 2003-31127 Japanese Unexamined Patent Publication No. 2016-4430 Japanese Unexamined Patent Publication No. 2011-39653

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technique for predicting the amount of medical expenses incurred in the future with high reliability.

The risk analysis system according to the present invention analyzes a risk related to the health of the subject based on a storage device that stores the subject data including information related to the health of the subject and the subject data acquired from the storage device. The analysis device includes an analysis device for estimating the event occurrence risk of the target person based on the target person data, and the risk estimation unit, which includes an output device for outputting the analysis result by the analysis device. It is characterized by having a medical expense prediction unit that predicts future medical expenses that the subject will spend in the future based on the event onset risk estimated by the department and the target person data.

According to this configuration, the subject's risk of developing an event is first estimated, and the subject's future medical expenses are predicted based on that risk. Therefore, it is possible to predict highly reliable future medical expenses in consideration of the subject's own health condition and health risks. Here, the "event" means an event that adversely affects health, and is typically a "disease". The word "event onset" may be read as "disease onset."

The risk estimation unit estimates the probability of the subject developing a disease as the event onset risk, and the medical cost prediction unit estimates the case where the subject develops the disease based on the subject data. It is advisable to calculate the medical expenses required for the medical expenses and predict the future medical expenses of the subject based on the medical expenses and the onset probability.

According to this configuration, future medical expenses can be predicted with high reliability by a relatively simple algorithm. In other words, since "medical expenses required when a disease develops" does not depend on the individual, it is possible to easily obtain the average amount of medical expenses from past receipt data or statistical data of the Ministry of Health, Labor and Welfare, for example. it can. Then, by combining this average medical cost with the individual-dependent "probability of developing a disease in the subject", the future medical cost is calculated in consideration of the subject's own health condition and health risk. can do.

The medical cost prediction unit may calculate the inpatient medical cost required for hospitalization and the outpatient medical cost required for outpatient treatment as the medical cost required when the subject develops the disease. For example, the total of inpatient medical expenses and outpatient medical expenses may be used as the medical expenses of the subject. According to this configuration, since medical expenses for both hospitalization and outpatient care are calculated, it is possible to predict medical expenses according to the actual situation.

The risk estimation unit estimates the onset probability for each of the plurality of diseases, and the medical cost prediction unit predicts the future medical cost for each of the plurality of diseases and calculates the predicted future medical cost. By totaling, it is advisable to calculate the total future medical expenses of the subject. The subject is not limited to one disease that can develop. Multiple diseases can develop in the same subject, for example, cerebrovascular disease and coronary artery disease. Therefore, according to this configuration, it is possible to predict the medical cost according to the actual situation by estimating the onset probability for each of the plurality of diseases.

By estimating the amount of insurance premiums to be paid when the subject person takes out medical insurance and comparing the predicted future medical expenses with the estimated amount of the insurance premiums, the subject person takes out the medical insurance. It is advisable to have an insurance adequacy judgment unit that determines the suitability of doing so. In addition, the output device may output medical insurance conditions and / or insurance premiums suitable for the target person based on the determination result of the insurance participation suitability determination unit. According to this configuration, it is possible to easily and highly reliablely determine the suitability of taking out medical insurance. The result of the suitability judgment may be used as reference information when the subject himself / herself considers taking out medical insurance.

The output device may generate and output a graph showing the yearly transition of future medical expenses of the subject. Since the risk of developing an event changes over time (usually the risk increases over time), future medical costs will also change over time. By outputting a graph like the one above, it is possible to easily confirm changes in medical expenses over time in the future. This graph may be used, for example, as a reference for a financial plan when the subject himself / herself considers medical insurance coverage or savings plan.

The analyzer has a plurality of types of analysis algorithms according to race and / or residential area, and it is preferable to change the type of analysis algorithm according to the race and / or residential area of the target person. Different races have different genetic risks that lead to different risk of developing an event. In addition, even if they are of the same race, if they live in different areas, the risk of developing an event will differ due to differences in lifestyle. In addition, if the area of residence is different, the medical system and prices will be different, and the medical expenses will also be different. Therefore, by adopting a configuration in which an appropriate analysis algorithm is selected according to race and / or residential area as described above, it is possible to accurately estimate the risk of event onset and predict future medical expenses.

The analyzer further has a hypertension determination unit that determines the hypertension of the subject based on the subject data, and the risk estimation unit uses the determination result of the hypertension determination unit as one of the risk factors. It is advisable to estimate the risk of developing an event in the subject. Hypertension is known to increase the risk of developing vascular events. Therefore, the reliability of risk estimation can be improved by considering hypertension as one of the risk factors when estimating the risk of developing an event.

When the hypertension determination unit determines that the patient has hypertension, the medical expense prediction unit may predict the future medical expenses of the subject in consideration of the medical expenses required for the treatment of hypertension. For example, hypertension may require continuous treatment, such as hospital visits or medication. Therefore, by considering the medical expenses required for the treatment of hypertension, the prediction accuracy of future medical expenses can be further improved.

The present invention can be regarded as a risk analysis system having at least a part of the above-mentioned configuration or function. The present invention can also be regarded as a risk analysis method including at least a part of the above processing. The present invention may also be regarded as a program for executing each step of the risk analysis method including at least a part of the above processing, or a computer-readable recording medium in which such a program is recorded non-temporarily. it can. Further, the present invention can also be regarded as a display device or a terminal that displays the analysis result output by the risk analysis system or the risk analysis method. Each of the above configurations and processes can be combined with each other to construct the present invention as long as there is no technical contradiction.

According to the present invention, the amount of medical expenses incurred in the future can be predicted with high reliability.

FIG. 1 is a diagram showing an overall configuration of a risk analysis system according to an embodiment of the present invention. FIG. 2 is a block diagram showing a functional configuration of the analyzer. FIG. 3 is a flowchart showing a specific flow of future medical cost prediction processing. FIG. 4 is a flowchart showing a specific flow of the insurance coverage determination process. 5A to 5C are display examples of the results of insurance coverage determination. FIG. 6 is an example of a screen displaying a list of risk analysis information of a plurality of target persons. 7A-7F are examples of detailed display of individual risk analysis information of the subject. 8A and 8B are display examples of future medical expenses.

A preferred embodiment of the present invention will be described below with reference to the drawings. However, the description of each configuration described below should be appropriately changed depending on the configuration of the device to which the invention is applied and various conditions, and is not intended to limit the scope of the invention to the following description. Absent.

FIG. 1 schematically shows the overall configuration of the risk analysis system according to the embodiment of the present invention.

The risk analysis system 1 analyzes and analyzes risks related to the health of the subject (risk of hypertension, risk of developing an event, etc.) based on information related to the health of the subject (hereinafter referred to as "subject data"). It is a system that generates output according to the purpose based on the result. The risk analysis system 1 of the present embodiment is roughly configured to include a database 10, an analysis device 11, a medication support device 12, and an output device 13.

The database 10 is a large-capacity storage device that collects and manages target person data. The target person data includes, for example, receipt (statement of medical fees) data, medical examination data, vital data such as blood pressure, medication information, environmental data (dwelling structure, climate of place of residence or work, family composition, etc.) Information about the surrounding environment that may affect the risk of developing an event) may be included.

The analyzer 11 is a functional unit that analyzes risks related to the health of the subject based on the subject data. The medication support device 12 is a functional unit that determines a medication method suitable for the pathological condition of the subject based on the subject data and the result of risk analysis. It is preferable that the analyzer 11 and the medication support device 12 perform risk analysis and determination of medication method based on evidence (for example, academic society guidelines, papers, opinions of KOLs (Key Opinion Leaders), etc.). Further, the output device 13 is a functional unit that generates a report based on the analysis result of the analyzer 11 and a report based on the processing result of the medication support device 12 and provides the report to the target person or the user of the system 1. The information provided by the output device 13 is displayed on, for example, a display device of the terminal of the target person, a display device of the system 1, or the like. As the target person's terminal, for example, a personal computer, a smartphone, a tablet terminal, a mobile phone, or the like can be used.

This system 1 is used, for example, for the purpose of individual health management and self-checking of risks, and doctors, nurses, public health nurses, etc. analyze the health condition of patients and create treatment policies and guidance contents. It can be used for the purpose. In addition, the insurance company objectively analyzes the health condition and health risks of the customer (insurance applicant), and uses the analysis results to propose insurance products suitable for the customer, determine whether or not to take out insurance, and contract conditions. This system 1 can also be preferably applied for the purpose of using it for setting and the like.

The risk analysis system 1 can be configured by a general-purpose computer including a CPU (processor), a memory, a large-capacity storage, an input device (keyboard, mouse, touch panel, etc.), a display device, a communication I / F, and the like. In this case, the risk analysis system 1 may be configured by one computer, or the risk analysis system 1 may be realized by the cooperation of a plurality of computers. For example, it is also desirable to build a robust and highly convenient system by using distributed computing and cloud computing technologies. When composed of a plurality of computers, those computers may be installed in one base or may be distributed in a plurality of bases (may be different countries). Each function of the risk analysis system 1 of the present embodiment is realized by executing a program required by the CPU. However, it is also possible to configure a part or all of the functions with a circuit such as an ASIC or FPGA.

(Analysis equipment)
FIG. 2 is a block diagram showing a functional configuration of the analyzer 11. The analyzer 11 has a data acquisition unit 110, a hypertension determination unit 111, a risk estimation unit 112, a medical expense prediction unit 113, and an insurance coverage suitability determination unit 114 as its functions. The data acquisition unit 110 is a function of acquiring necessary subject data from the database 10, and the hypertension determination unit 111 is a function of determining hypertension based on the subject data. The risk estimation unit 112 is a function of estimating the risk of developing a cerebrovascular event or a coronary artery event based on the result of the hypertension determination unit 111 and the subject data. The medical cost prediction unit 113 is a function of predicting future medical costs (referred to as “future medical costs”) to the subject based on the results of the hypertension determination unit 111 and the risk estimation unit 112. The insurance enrollment suitability determination unit 114 is a function of determining the suitability of the subject to enroll in medical insurance by comparing the predicted future medical expenses with the amount of insurance premiums.

Hereinafter, a specific example of the processing of the analyzer 11 will be described.

(1) Acquisition of Target Person Data The data acquisition unit 110 acquires target person data necessary for risk analysis from the database 10. In the present embodiment, at least the blood pressure data and the health diagnosis data of the subject are used as the subject data.

As blood pressure data, it is desirable to obtain both the examination room blood pressure measured at a hospital or the like and the home blood pressure measured at home or the like. Further, as home blood pressure, it is preferable to be able to acquire three types of data: morning blood pressure, evening blood pressure, and nighttime blood pressure. The morning blood pressure is the blood pressure measured within 1 hour after waking up, after urination, and before breakfast, and the evening blood pressure is the blood pressure measured before going to bed. The nighttime blood pressure is the blood pressure measured during bedtime. It is advisable to use data for 1 to 2 weeks for blood pressure in the morning and evening, and data for 1 to 2 days (measurement of 3 to 4 points per day) for blood pressure at night.

In addition to the subject's basic data such as age, gender, height, and weight, the health examination data includes obesity (BMI), HDL cholesterol, LDL cholesterol, estimated glomerular filtration rate (eGFR), fasting blood glucose, and HbA1c. It is advisable to include such test data as well as reference data such as pre-existing diseases, diseases being treated, medicines being taken, and lifestyle-related habits (smoking habits, amount of drinking, sleeping hours, etc.).

(2) Determination of hypertension The hypertension determination unit 111 determines the hypertension of the subject based on the blood pressure data of the subject. Specifically, the hypertension determination unit 111 determines whether the blood pressure measured from the subject is normal blood pressure or hypertension, and in the case of hypertension, determines the level. It is desirable that the procedure and criteria for determining hypertension follow reliable evidence. The hypertension determination unit 111 of the present embodiment determines the blood pressure level according to the classification shown in Table 1 according to the “Hypertension Treatment Guideline 2014 (JSH2014)” published by the Japanese Society of Hypertension. Although systolic blood pressure is used for determination in the present embodiment, diastolic blood pressure may be used, or both systolic blood pressure and diastolic blood pressure may be used.

Further, when the subject data includes data of both the examination room blood pressure and the home blood pressure, the hypertension determination unit 111 can also determine the type of hypertension according to the criteria shown in Table 2.

White coat hypertension is a state in which the blood pressure measured in the examination room is high blood pressure, but the blood pressure outside the examination room (home blood pressure, etc.) indicates normal blood pressure. Masked hypertension is the opposite, and the blood pressure measured in the examination room is normal blood pressure, but the blood pressure outside the examination room (home blood pressure, etc.) indicates high blood pressure. Since there are three pathological conditions of masked hypertension: early morning hypertension, daytime hypertension, and nighttime hypertension, the hypertension determination unit 111 determines which of the early morning / daytime / nighttime hypertension conditions is based on the time when the home blood pressure exceeds 135 mmHg. To do.

Further, the hypertension determination unit 111 can also determine an abnormality in blood pressure based on the diurnal variation of blood pressure. For example, non-dipper type nighttime hypertension and riser type nighttime hypertension can be detected based on fluctuations in nighttime blood pressure. Non-dipper type nocturnal hypertension is a state in which blood pressure does not decrease at night (normal people have a decrease in blood pressure at night), and riser type nocturnal hypertension is a state in which blood pressure increases at night.

(3) Risk estimation The risk estimation unit 112 estimates the risk of developing cerebrovascular events and coronary artery events based on the subject data. At this time, the risk estimation unit 112 may consider the determination result of the hypertension determination unit 111 as one of the risk factors. This is because hypertension is a factor that increases the probability of developing cerebrovascular events and coronary artery events.

It is desirable that the risk estimation process in the risk estimation unit 112 follows reliable evidence. In this embodiment, for example, "Suita Score" developed by the National Cardiovascular Research Center, "Multipurpose Cohort Study (JPHC Study)", "NIPPON DATA 80/90", etc. of the National Cancer Center are used.

The Fukida score is a risk score that predicts the 10-year risk of developing coronary events (eg, ischemic heart disease such as myocardial infarction and angina). Entering age, gender, smoking habits, diabetes, hypertension levels, LDL cholesterol, HDL cholesterol, and chronic kidney disease (CKD) levels (eGFR values) as risk factors will cause 10 years of coronary event development. The probability can be predicted. In addition, using a predictive model developed as one of the outcomes of JPHC Stroke, risk factors include age, gender, smoking habits, body mass index (BMI), diabetes, hypertension, and oral antihypertensive drugs. Is entered to predict the onset probability of cerebrovascular events (eg, stroke, cerebral infarction, etc.) for 10 years. Since these risk scores are publicly known, detailed explanations are omitted here.

(4) Forecasting Future Medical Expenses A specific flow of future medical expenses forecasting processing by the medical expense forecasting unit 113 of the present embodiment will be described with reference to the flowchart of FIG.

First, the medical expense prediction unit 113 includes the hypertension level (normal range / I degree hypertension / II degree hypertension / III degree hypertension) determined by the hypertension determination unit 111, and the coronary artery event and cerebrovascular disease estimated by the risk estimation unit 112. The onset probability of each event and the subject data are acquired (steps S300 to S302). As the subject data, at least information on the gender and age of the subject is used.

The medical expense prediction unit 113 calculates the inpatient medical expenses required when a coronary artery disease develops and the inpatient medical expenses required when a cerebrovascular disease develops (step S303). Inpatient medical expenses are the total medical expenses required for hospitalization due to illness, and are calculated by the following formula.

Inpatient medical expenses = 1 medical expenses + 1 day inpatient medical expenses x length of stay

"One-time medical expenses" are medical expenses for medical treatment that occur only once during hospitalization. In the present embodiment, the total of medical expenses for the three medical activities of "first / re-examination", "surgery", and "anesthesia" is regarded as one medical expense. "One-day hospitalized medical expenses" is the medical expenses required for one day of hospitalization. In this embodiment, there are eight medical treatments per day: "medical management, etc.", "examination", "imaging diagnosis", "medication", "injection", "treatment", "rehabilitation", "hospitalization fee, etc." The total medical expenses shall be the one-day inpatient medical expenses. Regarding the amount of medical expenses for each medical practice, it is advisable to obtain an average amount in advance based on statistical information. For example, the Ministry of Health, Labor and Welfare's statistics by social medical practice summarizes the number of cases for each disease, the actual number of medical treatment days, the number of cases of each medical practice, the number of times, the score, and the total number. Using these statistical information, it is possible to calculate the average medical cost for each medical practice.

The "stay of hospital" is determined based on the subject's gender and age and the type of illness. In the present embodiment, Table 3 (male table) and Table 4 (female table) are prepared in advance, and the length of hospital stay corresponding to the sex and age of the subject and the type of disease is acquired. For the values of the length of stay in these tables, it is advisable to use average values based on statistical information. For example, the table below is an example created based on the 2014 Patient Survey by the Ministry of Health, Labor and Welfare.

In addition, the medical cost prediction unit 113 calculates the annual outpatient medical expenses required for the treatment of coronary artery disease, the annual outpatient medical expenses required for the treatment of cerebrovascular disease, and the annual outpatient medical expenses required for the treatment of hypertension, respectively. (Step S304). The annual outpatient medical expenses are the total medical expenses required for one year's outpatient visits, and are calculated by the following formula.

Annual outpatient medical expenses = 1 outpatient medical expenses x annual outpatient days

"One-time outpatient medical expenses" are medical expenses required per day of outpatient visits. In this embodiment, 9 of "first / re-examination", "medical management, etc.", "examination", "imaging diagnosis", "medication", "injection", "treatment", "rehabilitation", "hospitalization fee, etc." The total daily medical expenses for one medical practice shall be the one-time outpatient medical expenses. As for the amount of medical expenses for each medical practice, it is advisable to obtain an average amount in advance based on statistical information, as in the case of inpatient medical expenses. However, for hypertensive diseases, considering that the dosage varies depending on the hypertensive level, the medical cost of "medication" is multiplied by a coefficient according to the hypertensive level.

The "annual hospital visits" will be determined based on the subject's gender and age and the type of illness. Table 5 is a table that defines the average medical care interval for each disease and age in men, and FIG. 6 is a table that defines the average medical care interval for each disease and age in women. Using the average medical treatment interval obtained from these tables, the annual number of hospital visits can be calculated by the following formula.

Annual hospital visits = 365 / average consultation interval

As for the value of the average medical treatment interval, it is preferable to use the average value based on the statistical information. For example, the table below is an example created based on the 2014 Patient Survey by the Ministry of Health, Labor and Welfare.

Next, based on the inpatient medical expenses calculated in step S303 and the onset probability for each disease, the medical expense prediction unit 113 calculates the future inpatient medical expenses, which are the inpatient medical expenses that will be incurred in the subject in the future, by the following formula. Calculate (step S305).

Future hospitalization medical expenses = probability of developing coronary artery disease x hospitalization medical expenses for coronary artery disease
＋ Cerebrovascular disease onset probability × Cerebrovascular disease hospitalization medical expenses

In addition, based on the annual outpatient medical expenses calculated in step S304 and the onset probability for each disease, the medical expense prediction unit 113 uses the following formula to calculate future outpatient medical expenses, which are future outpatient medical expenses to be incurred by the subject. Calculate (step S306).

Future outpatient medical expenses = probability of developing coronary artery disease x annual outpatient medical expenses for coronary artery disease
＋ Cerebrovascular disease onset probability × Annual outpatient medical expenses for cerebrovascular disease
＋ Annual outpatient medical expenses for hypertensive diseases

Next, the medical cost prediction unit 113 calculates the total medical cost expected value for 10 years (step S307). The expected value of total medical expenses for 10 years indicates how much medical expenses will be required if it is assumed that the disease will develop once in 10 years. Assuming that hospitalization is only once due to the onset of the disease, the expected value of total medical expenses for 10 years is calculated by the following formula.

Expected total medical expenses for 10 years = future inpatient medical expenses + (future outpatient medical expenses x 10) / 2

Through the above processing, future inpatient medical expenses, future outpatient medical expenses, and expected total medical expenses for 10 years can be calculated.

(5) Appropriateness of Insurance Enrollment Judgment A specific flow of the insurance enrollment suitability determination process by the insurance enrollment suitability determination unit 114 of the present embodiment will be described with reference to the flowchart of FIG.

First, the insurance enrollment suitability determination unit 114 sets the contract conditions (insurance plan, guarantee amount, special contract, contract period, etc.) of the target medical insurance (step S400). The contract conditions may be input or selected by the target person himself, or the insurance coverage suitability determination unit 114 may automatically set recommended conditions according to the target person's age, gender, desire, and the like.

Next, the insurance enrollment suitability determination unit 114 estimates the amount of insurance premiums to be paid when the target person enrolls in medical insurance based on the set contract conditions and information such as the age and gender of the target person (step S401). The insurance premium amount may be calculated for each single year, or the amount for the entire contract period may be calculated. In this embodiment, the total amount of insurance premiums to be paid in 10 years is estimated for comparison with future medical expenses.

Next, the insurance adequacy determination unit 114 compares the insurance premium amount estimated in step S401 with the future medical cost predicted by the medical cost prediction unit 113 (for example, the total medical cost expected value for 10 years). Therefore, the suitability of the subject to take out medical insurance is determined (step S402), and the determination result is output (step S403).

The logic of the suitability determination differs depending on who uses the system 1 for what purpose. That is, when the target person (insurance applicant) uses this system 1 for the purpose of examining medical insurance suitable for him / her, the interest of the target person should be prioritized, so the insurance premium amount is 10. It is advisable to output the judgment result of "subscription: appropriate" when the annual total medical cost is less than the expected value, and "subscription: inappropriate" when the insurance premium is equal to or more than the 10-year total medical cost expected value. FIG. 5A is a display example of the determination result presented to the insurance applicant.

On the other hand, when an insurer who provides medical insurance uses this system 1 for the purpose of underwriting assessment of the target person (insurance applicant), the interest of the insurer should be prioritized, so the insurance premium It is advisable to output the judgment result of "subscription: suitable" when the amount is larger than the expected value of the total medical expenses for 10 years, and "subscription: inappropriate" when the amount of insurance premium is less than the expected value of the total medical expenses for 10 years. FIG. 5B is a display example of the determination result of acceptance / rejection presented to the insurer.

The determination logic and display example illustrated here are just examples, and other logics and criteria may be used. It is also preferable to output the medical insurance conditions and the amount of insurance premiums suitable for the target person (insurance applicant) based on the determination result of the insurance participation suitability determination unit 114. For example, from a plurality of contract conditions, the optimum contract condition that balances the insurance premium amount and the expected value of total medical expenses for 10 years may be selected and recommended to the target person (insurance applicant) or the insurer. .. FIG. 5C is an example of the recommendation output by the output device 13. Alternatively, a plurality of stages of determination results may be output, such as optimum / appropriate / unsuitable, instead of two choices of appropriate / unsuitable. This kind of output has the advantage that it will be easier for those who are considering taking out insurance to select an insurance product with the conditions that suit them, while for the insurer as well, medical insurance. There is a merit that you can expect to increase the chances of joining the insurance.

(Display example of risk analysis results)
An example of displaying the risk analysis result by the output device 13 will be described.

FIG. 6 is an example of a screen for displaying a list of risk analysis information of a plurality of subjects. Each line shows the risk analysis information for one subject. In the example of FIG. 6, as risk analysis information, information such as the user ID, age, gender, blood pressure trend, examination room blood pressure, home blood pressure, blood vessel age, and total risk of the subject is output. As the blood pressure trend, for example, it is preferable to display a weekly change (graph) of systolic blood pressure, a weekly mean value, a maximum value, a minimum value, and the like. Comprehensive risk is an index that comprehensively determines the risk of developing cerebrovascular events and coronary artery events. In the example of FIG. 6, “Low”, “Middle”, “High”, and “Very” are used.
It is shown in four stages of "High". In addition, an alert icon is displayed for the target person whose overall risk is determined to be "Very High".

7A to 7F are examples of detailed display of risk analysis information of individual subjects. FIG. 7A is a display example of blood pressure stratification. The horizontal axis represents the time of day (0:00 to 24:00), and the vertical axis represents the blood pressure value. The data plotted with a triangle (Δ) is the blood pressure measured during the day (morning and evening blood pressure), and the data plotted with a square (□) is the blood pressure measured at night (night blood pressure). In the graph of FIG. 7A, the blood pressure ranges of normal blood pressure, I-degree hypertension, II-degree hypertension, and III-degree hypertension are shown in different colors, and it is easy to confirm which blood pressure range the subject's blood pressure value is classified into. You can do it. In FIG. 7A, the systolic blood pressure in the range of 140-159 is defined as I-degree hypertension, the range of 160-179 is defined as II-degree hypertension, and the systolic blood pressure of 180 or more is defined as III-degree hypertension.

In addition, when white coat hypertension, masked hypertension, abnormal diurnal blood pressure fluctuation (non-dipper type nighttime hypertension, riser type nighttime hypertension, etc.) are detected from the blood pressure data of the subject, it is advisable to output such information as well.

FIG. 7B is another display example of blood pressure stratification. The horizontal axis represents the examination room blood pressure, and the vertical axis represents the home blood pressure. Also in the graph of FIG. 7B, the blood pressure ranges of normal blood pressure, I-degree hypertension, II-degree hypertension, and III-degree hypertension are shown in different colors. The data plotted in circles (◯) show the statistical values of blood pressure values measured in a predetermined period. Specifically, the center of the circle represents the mean value of blood pressure, and the size (diameter) of the circle represents the variation (standard deviation, variance, etc.) of the blood pressure value. According to such a display, it is possible to easily confirm which blood pressure range the subject's blood pressure value belongs to by observing the position of the circle. In addition, if the classification based on the examination room blood pressure (horizontal axis) and the classification based on the home blood pressure (vertical axis) do not match, it can be seen that there is a suspicion of white coat hypertension or masked hypertension. In addition, by looking at the size of the circle, it is possible to intuitively grasp whether the blood pressure value is stable or fluctuates greatly.

FIG. 7C is a display example of cerebrovascular risk. It shows a comparison between the scores of subjects and the average scores of the same age group for five risk factors: blood pressure, body mass index (BMI), smoking habits, diabetes, and antihypertensive drugs. In addition, FIG. 7D is a display example of coronary artery risk. It shows a comparison between the scores of subjects and the average scores of the same age group for six risk factors: blood pressure, chronic kidney disease (estimated glomerular filtration rate eGFR), smoking habits, diabetes, HDL cholesterol, and LDL cholesterol. By looking at the charts of FIGS. 7C and 7D, it is possible to easily grasp the presence or absence of cerebrovascular risk and coronary artery risk (whether or not they deviate from the average), items to be improved, and the like.

FIG. 7E is a display example of the onset risk of each of the cerebrovascular event and the coronary artery event. The vertical axis represents the probability of developing an event within 10 years. By comparing and displaying the event onset risk of the subject and the average event onset risk of the same age, it is possible to easily evaluate the high / low event onset risk of the subject himself / herself. In addition, FIG. 7F is a display example of the total risk that combines the risk of developing a cerebrovascular event and the risk of developing a coronary artery event. For example, the risk of developing a cerebrovascular event and the risk of developing a coronary artery event are weighted and added, and a score normalized in the range of 0 (minimum risk) to 100 (maximum risk) can be used as the total risk.

(Example of display of future medical expenses)
8A and 8B show an example of displaying future medical expenses by the output device 13. FIG. 8A is an example of a screen for presenting the expected value of the total medical cost for 10 years predicted by the medical cost prediction unit 113 to the subject.

FIG. 8B is a screen example showing a graph of the predicted value of future medical expenses for each year. The annual medical expenses can be estimated as follows, for example.

When the 10-year onset probability of a certain disease estimated by the risk estimation unit 112 is p {p | 0 ≦ p ≦ 1} and the calculation year is y {y | 1 ≦ y ≦ 10}, in each year y The disease incidence rate P (y) is calculated as follows, for example. Although a simple model for linearly predicting the probability of disease onset is used here, a non-linear model may be used.

ここで、追加医療費Ｃｐは、医療費予測部１１３によって計算された入院医療費と年間通院医療費の合計である。 Assuming that the additional medical expenses in case of developing a disease are Cp [yen] and the basic annual medical expenses incurred regardless of the disease are Cn [yen / year], the average medical expenses μ (y) and medical care in each year y The variance σ (y) of the cost is obtained as follows.

Here, the additional medical cost Cp is the total of the inpatient medical cost and the annual outpatient medical cost calculated by the medical cost prediction unit 113.

Graph A of FIG. 8B shows the average when the onset probability of the disease is p = 0.1, the additional medical cost Cp = 10,000,000 [yen], and the basic annual medical cost Cn = 10,000 [yen / year]. This is the transition of medical expenses μ (y). Graphs B, C, and D are graphs showing more pessimistic predictions than graph A, and graphs B, C, and D are μ (y) + σ (y), μ (y) + 2σ (y), and μ, respectively. (Y) + 3σ (y). By looking at such a graph, you can forecast medical expenses for each year and
It is possible to grasp the range of variation (probability distribution) of predicted values. This graph may be used, for example, as a reference for a financial plan when the target person himself / herself considers a medical insurance subscription or a savings plan, or an insurer who provides medical insurance is a target person (insurance applicant). ) May be used as reference information when making an underwriting assessment or planning contract terms.

(Advantages of this embodiment)
According to the configuration of the present embodiment described above, the risk of event occurrence of the subject is first estimated, and the future medical expenses of the subject are predicted based on the risk. Therefore, it is possible to predict future medical expenses in consideration of the subject's own health condition and health risks. Moreover, since risk estimation and medical cost prediction are performed based on reliable evidence and statistical data of public institutions (Ministry of Health, Labor and Welfare, etc.), high reliability and accuracy can be expected.

Further, in the present embodiment, an algorithm is adopted in which the future medical expenses are predicted based on the medical expenses required when the disease develops and the probability of the onset of the disease. Since the "medical expenses required when a disease develops" does not depend on the individual, the average amount of medical expenses can be easily obtained from, for example, past receipt data or statistical data of the Ministry of Health, Labor and Welfare. Then, by combining this average medical cost with the "probability of onset" that depends on the individual, it is possible to calculate the future medical cost in consideration of the subject's own health condition and health risk.

Further, in the present embodiment, since both the inpatient medical expenses and the outpatient medical expenses are taken into consideration, it is possible to predict the medical expenses according to the actual situation. Further, in the present embodiment, since risk estimation and future medical cost prediction are performed for two types of diseases, coronary artery event and cerebrovascular event, the accuracy of medical cost prediction can be improved. Furthermore, in this embodiment, since the future medical expenses of the subject are predicted in consideration of the medical expenses required for the treatment of hypertension, it is possible to consider outpatients and medications for the treatment of hypertension, and the prediction accuracy of future medical expenses can be improved. Can be improved further.

In addition, in this embodiment, a function is provided to automatically determine the suitability of insurance based on future medical expenses and insurance premiums, so it is easy for applicants and insurers to take out medical insurance. And it can be judged with high reliability.

<Other Embodiments>
The configuration of the above-described embodiment is merely a specific example of the present invention. The scope of the present invention is not limited to the above-described embodiment, and various modifications can be made within the scope of the technical idea.

For example, in the above embodiment, evidence based on research results in Japan such as Suita score and JPHC Study was used, but when the target person of this system 1 is non-Japanese or lives outside Japan, , It is desirable to use evidence that matches the person's race and area of residence. This is because different races have different risk of developing an event due to differences in genes, and even if they are of the same race, different races have different risks of developing events due to differences in lifestyle. In addition, if the area of residence is different, the medical system and prices will be different, and the medical expenses will also be different. Therefore, it is advisable to change the algorithm for predicting medical expenses for each area of residence of the target person.

Specifically, a plurality of types of analysis algorithms (programs, tables, etc.) are prepared for each race type and / or residential area, and the risk estimation unit 112 and the medical cost prediction unit 113 are assigned to the target person's race and / or It is advisable to change the type of analysis algorithm according to the area of residence. Information on race and residential area can be given as target person data. In this way, having the function of adaptively changing the algorithm according to the race and residential area of the target person is advantageous for system operation in a country where various races are mixed, such as the United States.

1: Risk analysis system 10: Database, 11: Analyzer, 12: Medication support device, 13: Output device 110: Data acquisition unit, 111: High blood pressure determination unit, 112: Risk estimation unit, 113: Medical cost prediction unit, 114 : Insurance Appropriateness Judgment Department

Claims (15)

A storage device that stores subject data including information related to the subject's health,
An analyzer that analyzes risks related to the health of the subject based on the subject data acquired from the storage device, and an analyzer that analyzes the risk related to the health of the subject.
An output device for outputting the analysis result by the analyzer is provided.
The subject data includes blood pressure data of a plurality of subjects measured in a predetermined period.
The analyzer
A hypertension determination unit that calculates the blood pressure statistical value of the subject from the blood pressure data of the plurality of times and determines the hypertension level of the subject based on the blood pressure statistical value.
A risk estimation unit that estimates the event development risk of the subject based on the subject data and the level of hypertension,
Based on the event occurrence risk estimated by the risk estimation unit and the target person data, the medical cost prediction unit that predicts the future medical cost, which is the future medical cost to be incurred by the target person,
A calculation unit that estimates the amount of insurance premiums to be paid when the subject takes out the medical insurance based on the set medical insurance conditions.
Have,
The output device is a risk analysis system characterized in that the conditions of the medical insurance, the premium amount, and the future medical expenses are presented to the target person. The risk estimation unit estimates the probability of the subject developing the disease as the event onset risk, and determines the onset probability.
The medical expense prediction unit calculates the medical expenses required when the subject develops the disease based on the subject data, and the future medical expenses of the subject based on the medical expenses and the onset probability. The risk analysis system according to claim 1, wherein the risk analysis system is characterized in that. Claim 2 is characterized in that the medical cost prediction unit calculates inpatient medical expenses required for hospitalization and outpatient medical expenses required for outpatients as the medical expenses required when the subject develops the disease. The risk analysis system described in. The risk estimation unit estimates the probability of onset for each of a plurality of diseases,
The medical cost prediction unit predicts future medical costs for each of the plurality of diseases, and calculates the total future medical costs of the subject by totaling the predicted future medical costs. The risk analysis system according to claim 2 or 3. It is characterized by having an insurance adequacy determination unit that determines the suitability of the subject to take out the medical insurance by comparing the predicted future medical expenses with the estimated insurance premium amount. The risk analysis system according to any one of claims 1 to 4. The fifth aspect of the present invention is that the output device presents the medical insurance conditions and / or the premium amount suitable for the target person to the target person based on the determination result of the insurance participation suitability determination unit. Described risk analysis system. The insurance coverage suitability determination unit is characterized in that when the estimated premium amount is less than the predicted future medical expenses, it is determined that the target person is suitable for taking out the medical insurance. The risk analysis system according to claim 5 or 6. The risk analysis system according to any one of claims 1 to 7, wherein the medical insurance conditions are input or selected by the subject. The risk analysis system according to any one of claims 1 to 8, wherein the output device generates and outputs a graph showing a yearly transition of future medical expenses of the subject. The analyzer has a plurality of types of analysis algorithms for each race and / or residential area, and is characterized in that the type of analysis algorithm is changed according to the race and / or residential area of the subject. The risk analysis system according to any one of claims 1 to 9. The analyzer further includes a hypertension determination unit that determines the hypertension of the subject based on the subject data.
The risk estimation unit uses the determination result of the hypertension determination unit as one of the risk factors to estimate the event onset risk of the subject according to any one of claims 1 to 10. Described risk analysis system. When the hypertension determination unit determines that the patient has hypertension, the medical cost prediction unit predicts the future medical expenses of the subject in consideration of the medical expenses required for the treatment of hypertension. Item 11. The risk analysis system according to item 11. The acquisition step in which the computer acquires the subject data including information related to the subject's health,
An analysis step in which a computer analyzes the health-related risks of the subject based on the subject data,
The computer has an output step for outputting the analysis result by the analysis step.
The subject data includes blood pressure data of a plurality of subjects measured in a predetermined period.
The analysis step
The computer calculates the blood pressure statistics of the subject from the blood pressure data for the plurality of times.
, The step of determining the hypertension level of the subject based on the blood pressure statistics, and
A step in which a computer estimates the subject's risk of developing an event based on the subject data and the level of hypertension.
A step in which a computer predicts future medical expenses, which are future medical expenses incurred by the subject, based on the estimated risk of event occurrence and the subject data.
A step in which the computer calculates the amount of insurance premium to be paid when the subject takes out the medical insurance based on the set medical insurance conditions.
The output step includes a risk analysis method including a step in which a computer presents the conditions of the medical insurance and the premium amount and the future medical expenses to the target person. A program for causing a computer to execute each step of the risk analysis method according to claim 13. A display device that displays the analysis result output by the risk analysis method according to claim 13.

Images