JP6894063B2 - A basic system for generating health management intervention support information, and a drug management intervention support information generation system using this basic system - Google Patents

Description

The present invention relates to a basic system for generating various health management intervention support information for supporting a health management intervention for an insured person by an insurer, and a drug management support intervention information generation system using the basic system.

In recent years, medical expenses in Japan have increased by about 1 trillion yen every year, and according to government statistics, it exceeded 40 trillion yen in 2014 and is expected to continue increasing in the future. Under these circumstances, the Health and Medical Strategy Promotion Law (Law No. 48 of May 30, 2006) was enacted, and the Health and Medical Strategy Promotion Headquarters was established based on this law, and 2014. On July 22, 2014, the "Health and Medical Strategy" prepared by the Promotion Headquarters was approved by the Cabinet.

The "Health and Medical Strategy" decided by the Cabinet includes policies for strategic measures against various issues facing Japan from a wide range of perspectives, with the aim of optimizing medical expenses. As a result, various medical information data about the insured person, including the receipt, is analyzed, and after extracting the health issues of the insured person, the insured person's health for the insured person should be carried out. Insurers are required to formulate a plan "data health plan" that includes the content of management intervention.

However, looking at the current situation of local governments and health insurance associations that are insurers, there are major restrictions on the formulation and execution of plans required by the government in terms of personnel and finance, and from the vast amount of information on insured persons. , It is extremely difficult to pinpoint insured persons who have various health problems or are likely to have them in the future, and to give appropriate guidance and advice (these are called interventions) to each person. It is in.

Conventionally, it is caused by duplication of prescribed drugs based on the receipt data of individual patients (insured persons) and medical examination information, that is, the presence or absence of so-called multiple drugs, and the taking of drugs prescribed at multiple hospitals. Patent Documents 1 to 6 and the like have proposed techniques such as automatically determining the presence or absence of side effects by a system and notifying the patient of the result.

However, most of these conventional technologies are merely systems that patients themselves use on their own initiative, and insurers cannot grasp the actual conditions of individual insured persons, let alone insure the actual conditions of the insured persons as a whole. It cannot be grasped statistically by a person.

At present, various tools for extracting descriptive epidemiological issues at the group level are being developed using various medical information data of the insured held by the insurer. However, even for an insured person who is worried about his / her health, for example, the degree of risk in the future and the degree of risk of side effects vary greatly depending on whether or not he / she is making daily changes in his / her physical condition and improving his / her lifestyle. That is, the receipt data and the data of the medical examination result are only past data, and it is difficult to accurately predict the problems and dangers that occur now or in the future using only this data.

Japanese Unexamined Patent Publication No. 2015-015020 Japanese Unexamined Patent Publication No. 2015-170019 JP 2015-084132 Japanese Unexamined Patent Publication No. 2015-07492 Japanese Unexamined Patent Publication No. 2014-174786 Japanese Unexamined Patent Publication No. 2013-137775

When implementing the government's "health and medical strategy" mentioned above, the insurer should be specific at the right time for the insured who has health or drug problems or is likely to have them in the future. There is a need for how to create useful information that can be used for traditional health care interventions.

In the present invention, based on the "health / medical strategy", the insured person who has various health problems or is likely to have in the future is pinpointed by the insured local government or each health insurance association. In addition to various medical information data of the insured insured, daily changing health-related data such as blood pressure, weight, and exercise amount of the insured can be provided so that appropriate guidance and advice can be given to each. The purpose is to provide a system for generating appropriate health care intervention support information for individual insured persons by acquiring real-time data and comprehensively analyzing these data.

In order to achieve the above object, the first invention of the present application is a basic system for generating information for supporting various health management interventions for the insured by the insurer, and is a receipt information about the insured and health. An insurer database that records medical information including diagnosis result information, cancer screening result information, and interview result information, and at least one of an IoT weight scale, a wearable terminal, and an information communication terminal used by the insured. , The insured person is classified and predicted by machine learning based on the insured person's medical information recorded in the insured person database, and it is determined whether or not the insured person is subject to guidance. If the IoT scales, the wearable terminal, based on information transmitted from at least one of said information communication terminal, and intervening support information generating system for generating a health management intervention support information, the intervention support It consists of a server on which an information generation system is constructed and a display terminal that displays the health management intervention support information generated by the intervention support information generation system. The server, the IoT weight scale, the wearable terminal, and the information communication. It is characterized in that it is connected to the terminal through an Internet line.

The second invention of the present application is a consultation frequency management intervention support information generation system that generates consultation frequency management intervention support information using the above-mentioned basic system, and the consultation frequency management intervention support information generation system is the insurance. Based on the medical information of the insured person recorded in the person database, the insured person is classified and predicted by machine learning, and it is determined whether or not the insured person is subject to guidance. IoT scales, the wearable terminal, based on information transmitted from the information communication terminal, a consultation frequency determination means for consultation frequency to determine whether it is within the appropriate range, by the visit frequency determination means The determination result is displayed on the display means.

Further, the third invention of the present application is a drug management intervention support information generation system that generates drug management intervention support information using the above-mentioned basic system, and the drug management intervention support information generation system is recorded in the insurer database. Based on the medical information of the insured person, the insured person is classified and predicted by machine learning, and it is determined whether or not the insured person is subject to guidance . It is a side effect occurrence risk calculation means for calculating the side effect occurrence risk due to a drug based on the information transmitted from the wearable terminal and the information communication terminal, and is characterized in that the side effect occurrence risk is displayed on the display terminal. And.

Further, the fourth invention of the present application is a drug management intervention support information generation system that generates drug management intervention support information using the above-mentioned basic system, and the drug management intervention support information generation system is recorded in the insurer database. Based on the medical information of the insured person, the insured person is classified and predicted by machine learning, and it is determined whether or not the insured person is subject to guidance . the wearable device, based on information transmitted from the information communication terminal, presence or absence of frequent administration, optimal drug load, among the adherence and prediction residual drug number, and calculating at least one information, the calculation result It is characterized in that it is displayed on the display terminal.

According to the first invention of the present application, various medical information data about the insured person possessed by the insured person and health-related data of the insured person updated in real time are used to optimize various health management for each insured person. By generating accurate intervention support information, the insurer can provide various types of efficient and effective intervention support at the optimal timing, with limited personnel and budget, based on the health management intervention support information. Can be carried out. Insured persons who are the target of intervention support can solve their own health problems and prevent serious illnesses by receiving appropriate guidance and advice from the insurer, and as a result, Japan. It is possible to optimize the overall medical expenses.

Further, according to the first invention of the present application, the problem situation of the insured as a whole held by the insurer can be acquired as macro statistical data, and can be used for policy planning for each local government or health insurance association. it can.

As described above, the first invention of the present application is a basic system for generating various intervention support information, and as long as this basic system is constructed, each of them can be appropriately incorporated by incorporating an individual application program according to the purpose. Optimal intervention support information can be generated. Specific examples of various intervention support information according to the purpose include the drug management intervention support information according to the second and third inventions of the present application described below, dietary habit improvement management intervention support information, and living behavior improvement management intervention. Support information, diet management intervention support information, health examination consultation management intervention support information, specific health guidance management intervention support information, dental examination consultation management intervention support information, examination consultation management intervention support information on specific diseases such as cancer, etc. Various intervention support information related to health management can be mentioned.

The second invention of the present application is a consultation frequency management intervention support information generation system that calculates whether or not the consultation frequency is appropriate by utilizing the first invention. When the insured is worried about his / her health condition, he / she wants to go to the hospital frequently, but he / she becomes in good health based on the information transmitted from the IoT scale, the wearable terminal, and the information / communication terminal. On the other hand, it is determined whether or not the number of hospital visits is appropriate, and if it is determined that the number of hospital visits is excessive, a message to that effect is displayed. This allows the insurer to advise, for example, the insured who visits the hospital three times a week that this may be reduced to once. On the contrary, if the number of hospital visits is extremely small with respect to the daily health condition, it is possible to encourage the number of hospital visits to be increased before it becomes serious. As a result, the overall medical expenses can be optimized.

The third invention of the present application is a system for generating drug management intervention support information by utilizing the first invention, and in particular, calculates the risk of occurrence of side effects. In the prior art, this is simply displayed based on the risk of side effects due to swallowing set by the Ministry of Health, Labor and Welfare, etc., but the present invention uses insured person's health-related data updated in real time. However, taking into account changes in physical condition and eating habits, not only the risk of side effects due to swallowing, but also lifestyle information such as the insured's lifestyle and dietary content, even if only one type of medicine is taken. The risk of side effects is calculated from. As a result, the insurer can obtain information that the risk of side effects of a specific insured person is increasing, and can give the insured person extremely specific guidance such as refraining from taking the corresponding drug. As a result, the appropriate amount of the drug prescribed for the insured person from the next time onward can be adjusted, and side effects that occur in the insured person can be prevented. As a result, the overall medical expenses are optimized. be able to.

The fourth invention of the present invention is a drug management intervention support information generation system using the first invention as in the third invention, whereas the third invention is an invention for calculating the risk of side effects. The fourth invention is to calculate the presence or absence of frequent administration, the optimum drug amount, adherence and the predicted number of remaining drugs. Based on the information transmitted from the IoT scale, the wearable terminal, and the information communication terminal, whether the prescribed drug is frequently administered, whether the prescribed drug is in an appropriate amount, or adherence. (Whether or not the drug is taken as prescribed), and the predicted number of remaining drugs is calculated. As a result, the insurer can give very specific advice to a specific insured person, such as the fact that about half of the current prescription drug is sufficient. As a result, the amount of the drug prescribed from the next time onward can be derived to an appropriate level, and as a result, the overall medical cost can be optimized.

Basic system configuration diagram of the present invention An example of an algorithm for determining the risk of diabetes An example of a diabetes risk factor identification algorithm An example of an algorithm for determining the risk of stroke recurrence An example of an algorithm that determines whether the frequency of consultations is appropriate (Part 1) An example of an algorithm that determines whether the frequency of consultations is appropriate (Part 2) An example of an algorithm that calculates the risk of side effects for drugs taken by diabetics An example of an algorithm to calculate the optimal drug dose An example of an algorithm that calculates whether or not there is residual drug

Embodiments of the present invention will be described in detail with reference to FIGS. 1 to 9. Needless to say, each embodiment is not intended to limit the scope of the invention of the present application, and may be appropriately implemented based on the content described in the claims and the purpose of the invention. The present embodiment described below will be described as an example of a system that is assumed to be implemented within one health insurance association (hereinafter, health insurance association).

FIG. 1 is a system configuration diagram which is the basis of the present invention. 1 in the figure is a medical information database (insurer) that records individual receipt data, health examination result data, cancer screening result data, and interview result data for all members (all insured persons) who join the health insurance association. Database), and 2 to 4 in the figure are IoT weight scales, wearable terminals, and information and communication terminals (smartphones, etc.) used by the insured, respectively. The medical information database 1 records all the medical-related data of the insured individual held by the health insurance association.

10 in the figure compares the information recorded in the medical information database 1 with the daily data transmitted from the IoT weight scale 2, the wearable terminal 3, and the information communication terminal 4, and requires health management support information. It is a health management intervention support information generation system that generates information. 20 in the figure is a health insurance association terminal that displays various health management intervention support information generated by the health management intervention support information generation system.

The IoT weight scale 2, the wearable terminal 3, and the information and communication terminal 4 are distributed to all insured persons regardless of the presence or absence of illness or the presence or absence of hospital visits, and all of them use them daily, record necessary information, and record the recorded data. It is to be sent.

The present invention records all medical-related data of the insured individual held by the health insurance association in the medical information database 1 created as a basic system, and changes in the insured individual's daily weight, blood pressure, pulse, etc. By acquiring daily meal contents, daily activities, etc. as real-time data, necessary data is extracted and compared according to the purpose, and the health management intervention support information for the insured required by the health insurance association is appropriate. It is generated at the timing and with specific contents.

(First Embodiment)
The first embodiment of the present invention generates health management intervention support information for a person who has never visited the hospital (record) or has a history of hospital visits and has only undergone a regular health checkup conducted annually at the company. It is a system.

In the case of an insured person who has no experience (record) of visiting the hospital in the past, there is no receipt data in the medical information database 1, and only the result data of the medical examination (including cancer screening) and the interview data are recorded. There is. As a result of the medical examination, if there is a possibility of a specific illness or if the person has metabolic syndrome, he / she will be subject to detailed examination instructions and specific health guidance, but if he / she is not healthy, he / she will be subject to detailed examination instructions. All you have to do is get a medical examination.

However, since health examinations are generally performed only once a year, there are cases in which a person suffers from a specific illness or develops metabolic syndrome without being aware of it until the next year's health examination. As a result, these cannot be prevented.

In the first embodiment of the present invention, in order to solve the above-mentioned problems, the insured person's daily weight, body temperature, blood pressure, pulse, etc. In addition to measuring at least one of the amount of exercise and the degree of snoring, daily activities include sleep time, meal content, supplements taken, over-the-counter drugs taken, working hours, working hours, and driving a car. By asking them to answer the time, etc., it is possible to judge the risk of suffering from a specific disease and the possibility of obesity as it is.

The daily weight described above is measured by the IoT weight scale 2 and transmitted to the health management intervention support information generation system 10 via the Internet line. Further, the daily body temperature, blood pressure, pulse rate, amount of exercise, and degree of snoring described above are automatically measured by the wearable terminal 2 and transmitted to the health management intervention support information generation system 10 via the Internet line. In addition, sleep time, meal content, supplements taken, over-the-counter medicines taken, working hours, working hours, and driving time as daily activities are answered by the answer application downloaded to smartphone 4. , The answer result is transmitted to the health management intervention support information generation system 10 via the Internet line.

The health management intervention support information generation system 10 according to the first embodiment compares the height, weight, blood pressure, pulse and interview results of the insured measured at the time of the health examination with daily measurement data and daily answers. If one continues to live as it is, for example, the risk of suffering from hypertension or diabetes, the risk of developing metabolic syndrome, the risk of developing sleep apnea, etc. are judged.

2 and 3 are examples of algorithms for determining the risk of developing diabetes. Known medical research results on the onset of diabetes, test values (health examination results) such as blood glucose level (HbA1c) accumulated in the medical information database 1, individual information of the insured such as family history, past medical history, age, etc. , Daily eating habits transmitted from smartphone 4, daily weight transmitted from IoT weight scale 2, daily activity amount transmitted from wearable terminal 3 are analyzed as input information, and after 1, 3, 5 years, etc. In the future, we will calculate the risk factors for developing diabetes (HbA1c will be above the diabetes reference value).

Known medical studies show that people without exercise habits are more than twice as likely to develop diabetes in 7 years as those with habits. For example, as a result of regular health examination, a male insured person in his 50s with a blood sugar level of 5.4 is currently healthy, but his father has diabetes as a family history, he has no exercise habits, and he has no exercise habits. It is assumed that there was a person who drank a carbonated drink containing a large amount of sugar every day even in his eating habits and showed an increasing tendency by daily weight measurement. In this case, if the above information is calculated as input information, it is possible to predict that the blood glucose level in the next year will be 5.8, 3 years later will be 7.3, and 5 years later will be 7.7.

The HbA1c test value for the next year of the insured can be predicted with high accuracy, especially in the threshold classification, by using the age, gender, past medical examination history, health intention in the questionnaire answer, medication history, test value, and the like. In the present invention, whether or not the insured person is subject to guidance by performing classification prediction by machine learning using the questionnaire and the numerical values of the test values from the data of the specific medical examination results of the insured person for the past 5 years. To judge. The method used in machine learning is to design an optimal predictive model by combining random forest, gradient boosting, support vector machine, logistic regression, deep learning, etc. in a complex manner. In addition, as with the consultation rate prediction algorithm, it is possible to design a more accurate prediction result by using the data set accumulated in the local government that was carried out in the past for learning.

In addition, this system has a system structure in which medical information data is accumulated in the health management intervention support information generation system 10 each time the insured uses this system, so that the accuracy is further improved. The algorithm is just an example, and the risk can be determined by various other methods.

The result of the above judgment is transmitted to the health insurance association terminal 20 as health management intervention support information, and the specific content is displayed on the terminal, so that the health instructor or the like gives the insured person daily meals and daily life. Specific alerts can be given to change behavior, and illness and obesity can be prevented. In some cases, it is possible to give advice to undergo a detailed examination at an early stage and prevent it from becoming serious. The judgment result may be transmitted to the insured person's terminal (smartphone 4, etc.).

In the present embodiment, in addition to the determination of the specific disease, metabolic syndrome, etc. described above, it is also possible to generate consultation reminder intervention support information for the insured who does not undergo a medical examination (including dental examination and cancer screening) in the first place. be able to. In this case, the implementation date data of various health examinations to be carried out by the health insurance association is separately input, and if there is no data of the health examination consultation after the health examination implementation date, the health examination consultation prompting intervention support information is generated.

(Second Embodiment)
The second embodiment of the present invention is a system for generating health management intervention support information for a person who has visited the hospital in the past (record) or has a history of illness but is now recovering. The pre-existing illness includes those who have been determined to have metabolic syndrome in the past and have succeeded in dieting through specific health guidance.

The system configuration of the second embodiment is basically the same as that of the first embodiment shown in FIG. 1, but the health management intervention support information generation system 10 according to the present embodiment particularly determines the risk of recurrence of a pre-existing disease. It is a thing.

FIG. 4 is an example of an algorithm for determining the risk of recurrence of an insured person who has suffered a stroke in the past. The risk of stroke is known to be hypertension, blood pressure, lipid abnormalities, etc., but the results of known medical research and the test values of blood pressure, blood pressure, lipids, etc. of the insured stored in the medical information database 1 Information such as lifestyle-related habits transmitted from the smartphone 4 and daily blood pressure and pulse transmitted from the wearable terminal 3 is analyzed as input information to determine the risk of stroke recurrence. The algorithm is just an example, and the risk of recurrence can be determined by various other methods.

The result of the above judgment is transmitted to the health insurance association terminal 20 as health management intervention support information, and the specific content is displayed on the terminal, so that the health instructor or the like can prevent the insured from recurrence of the pre-existing disease. It is possible to give specific attention to the situation and prevent recurrence. In some cases, it is possible to give advice to undergo a detailed examination at an early stage and prevent it from becoming serious. The judgment result may be transmitted to the insured person's terminal (smartphone 4, etc.).

Known medical studies show that about 5% of people who have had a stroke in the past relapse annually. For example, from a medical information database, a man in his 60s who suffered a stroke two years ago had an abnormal lipid test value as a result of a regular medical examination, and although he was taking medication, the daily blood pressure sent from a wearable terminal was It is assumed that the high price is continuously shown for one month. In such a state, if the medical institution's consultation history is not confirmed on the medical information database for more than half a year after the regular medical examination, it is judged that the risk of recurrence is high. The result of the determination can be transmitted to the health insurance association terminal 20 and also to the terminal (smartphone 4, etc.) of the person himself / herself to recommend early medical treatment to the medical institution.

Further, in the above example, the risk of recurrence of the pre-existing disease is the main subject, but the risk determination other than the pre-existing disease can be carried out by adopting the same algorithm as in the first embodiment.

(Third Embodiment)
In the third embodiment of the present invention, the basic system shown in FIG. 1 is used to determine whether or not the consultation frequency is appropriate as health management intervention support information, and this is transmitted to the health insurance association terminal 20. Is. The insured person to which the third embodiment is applied is an insured person who has a plurality of hospital visit records most recently in the medical information database 1, that is, a sick person who is currently visiting the hospital.

When the insured is worried about his / her health condition, he / she wants to go to the hospital frequently, but he / she is in good health based on the information transmitted from the IoT scale 2, the wearable terminal 3, and the information communication terminal 4. It is determined whether or not the number of hospital visits is appropriate, and if it is determined that the number of hospital visits is excessive, a message to that effect is displayed. On the contrary, if the number of hospital visits is extremely small with respect to the daily health condition, it is possible to encourage the number of hospital visits to be increased before it becomes serious.

FIG. 5 is an example of an algorithm for calculating whether or not the consultation frequency is appropriate. Grasp changes in physical condition from insured person's outpatient information, medical information of receipt data, medical examination result information, daily data sent from IoT weight scale 2 and wearable terminal 3 stored in medical information database 1. However, even though there is no major change in physical condition, if the actual number of days for two or more receipts is 15 days or more from the monthly receipt data, it is judged to be frequent visits.

Further, FIG. 6 is an example of an algorithm for determining the necessity of early consultation because, contrary to the above frequency, consultation is not confirmed even though consultation with a medical institution is required. If there is a medical abnormality in the past history accumulated in the receipt data and the numerical value from the medical examination result, and there is no outpatient information from the receipt data even though you have visited the hospital regularly in the past, you need to go to the hospital. Judge.

The result of the above judgment is transmitted to the health insurance association terminal 20 as health management intervention support information, and the specific content is displayed so that the health instructor or the like can reduce the number of hospital visits or visit the insured person. Can be instructed. The above algorithm is just an example, and the necessity of frequent consultations or outpatient visits can be determined by various other methods.

(Fourth Embodiment)
In the fourth embodiment of the present invention, the basic system shown in FIG. 1 is used to calculate the risk of side effects caused by drugs as health management intervention support information, and this is transmitted to the health insurance association terminal 20. .. As in the third embodiment, the insured person to which the fourth embodiment is applied is basically the insured person in which the latest drug receipt data is recorded in the medical information database 1, that is, the insured person who is currently visiting the hospital. He is a sick person who is insured and is taking prescription drugs.

Side effects caused by drugs are caused by various factors such as the constitution, physical condition, lifestyle, and ingestion with other drugs of the person taking the drug. Of course, the risk of developing side effects differs depending on whether you have a standard constitution, standard physical condition, or standard life, or not.

In this fourth embodiment, the risk of side effects caused by the drug being taken is calculated based on the current disease name, dietary content, lifestyle, etc., and the risk is transmitted to the health insurance association terminal 20. It enables guidance by public health nurses.

FIG. 7 is an example of an algorithm for calculating the risk of side effects of a drug taken by a diabetic patient. From the receipt information stored in the medical information database 1, it is possible to identify whether or not the insured person is a diabetic patient, and if the insured person is a diabetic patient, the drug information that can be grasped from the receipt and the insured transmitted from the smartphone 4. The occurrence of side effects is predicted from the lifestyle-related situation of the insurer, and avoidance measures and the like are displayed on the health insurance association terminal 20 in advance.

Specifically, it is known that the risk of hypoglycemia caused by sulfonylurea drugs is likely to occur during excessive exercise or on an empty stomach, and the insured's dietary status and exercise that are sent daily. From information on physical activity such as, it is determined that the side effects of hypoglycemia may be more likely to occur in the future. When there is a possibility of hypoglycemia, the health insurance association terminal 20 is informed that the insured person should take glucose and rest. If there is an urgency, the insured person's smartphone 4 may be notified directly.

Further, even when hypoglycemia does not occur, the subject may be asked to confirm whether side effects have occurred through the smartphone 4 and the occurrence status of the side effects may be monitored. The insured person should show the doctor, pharmacist, etc. the contents displayed on the smartphone 4 (image like a medicine notebook) the next time he / she visits a medical institution for the status of taking these medications and the occurrence of side effects. Information can be shared and used for the treatment of insured persons.

The risk of side effects may be displayed stepwise according to the degree of risk, or may be displayed as a probability. Specifically, based on the side effect information reported in the above algorithm, a general index used in drug epidemiology such as ROR (Reporting odds ratio) and PRR (Proportional Reporting ratio) can be used to obtain the relevant drug. The probability that side effects are likely to occur may be calculated, and the degree of risk may be displayed based on the numerical value. The above algorithm is just an example, and the risk of side effects can be determined by various other methods.

(Fifth Embodiment)
In the fifth embodiment of the present invention, as in the fourth embodiment, the insured person to which the insured person is applied basically records the latest drug receipt data in the medical information database 1, that is, the insured person who is currently going to the hospital. A sick person who is taking prescription drugs.

The difference between the health management intervention support information generated in the fifth embodiment and that in the fourth embodiment is that at least one of the presence / absence of frequent administration, the optimum drug amount, adherence, and the predicted number of remaining drugs is calculated. It is a point. Adherence is a term that means whether or not the prescribed drug is taken correctly according to the instructions of a doctor.

In this fifth embodiment, the current disease name, the weight, body temperature, blood pressure, and pulse sent from the IOT scale 2 and the wearable terminal 3, and the daily actions sent from the smartphone 4 are the prescription drugs. By comparing the dose and the number of doses, the presence or absence of frequent administration, the optimum drug amount, adherence, and the predicted number of remaining drugs are calculated.

FIG. 8 is an example of an algorithm for determining whether or not the dose or frequency of administration of the insured person taking the drug is appropriate. From the insured person's receipt data accumulated in the medical information database 1, the drug currently being taken is identified, and the insured person is erroneously taking a large amount of the drug instead of the prescribed usage, etc. Is grasped from the answer from the smartphone 4, and the health insurance association terminal 20 is notified that the possibility of side effects will increase in the case of taking a large amount or taking a large number of times.

Further, FIG. 9 is an example of an algorithm for calculating whether or not residual drug is generated. From the insured person's receipt data stored in the medical information database 1, the medical institution that received the treatment, the consultation date, and the number of medication days can be identified, and the insured person visits the clinic again before the prescribed number of medication days. Judging the possibility of residual drug from the response results such as when taking medication, the number of meals is not three meals, or not taking the drug according to the response from the smartphone 4, the health insurance association terminal 20 is notified to that effect. Notify. The algorithm is just an example, and the appropriateness of the consultation frequency can be determined by various other methods.

The optimum drug amount, adherence, and predicted residual drug number can also be calculated based on the same concept as each of the above algorithms, and the calculated data is transmitted to the health insurance association terminal 20 as health management intervention support information. It can be used as basic information for guidance and intervention by public health nurses. The calculated data may be transmitted to the insured individual's smartphone 4.

In the fourth and fifth embodiments, the drug management intervention support information generation system checks whether the drug being taken is a multidrug with overlapping efficacy and / or whether it is a contraindicated drug in combination. It may have a drug check system. Normally, a drug prescribed by the same doctor is not a multi-drug or contraindicated drug, but as a result of going to multiple hospitals or being diagnosed by multiple doctors, the drugs prescribed respectively are multi-drug or concomitant. May be a contraindicated drug.

In this case, when the drug check system determines from the drug receipt data that the drug is a multidrug and / or a contraindicated drug in combination, the determination result is displayed on the health insurance association terminal 20. In addition, the determination result may be transmitted to the insured person's individual smartphone 4 and the result displayed on the screen may be presented to the pharmacist of the prescription pharmacy to directly solve the problem of multiple drugs or contraindicated drugs. ..

As described above, according to the present invention, all the medical-related data of the insured individual possessed by the health insurance association is recorded in the medical information database 1 created as the basic system, and the IOT weight scale 2, the wearable terminal 3, and the information terminal 4 are recorded. By acquiring real-time data such as daily changes in weight, blood pressure, pulse, etc. of the insured individual, daily dietary content, living behavior, etc., necessary data is extracted and compared according to the purpose. , Health management intervention support information for insured persons required by the health insurance association can be generated at the optimum timing and concretely.

1 Medical information database (insurer database)
2 IOT scale 3 Wearable terminal 4 Information and communication terminal (smartphone)
10 Health management intervention support information generation system 20 Health insurance association terminal

Claims (11)

A basic system that generates information to support various health care interventions by insurers for insureds.
An insurer database that records medical information including receipt information about the insured, health examination result information, cancer screening result information, and interview result information,
At least one of the IoT scale, wearable terminal, and information and communication terminal used by the insured,
Based on the medical information of the insured recorded in the insurer database, the insured is classified and predicted by machine learning, and it is determined whether or not the insured is subject to guidance. the IoT scales, the wearable terminal, based on information transmitted from at least one of said information communication terminal, and intervening support information generating system for generating a health management intervention support information,
The server on which the intervention support information generation system was built and
It consists of a display terminal that displays the health management intervention support information generated by the intervention support information generation system.
The server, the IoT weight scale, the wearable terminal, and the information communication terminal are connected to each other via an internet line.
A basic system for generating health management intervention support information. The wearable terminal measures at least one of the insured's daily body temperature, blood pressure, pulse, exercise amount, and snoring, and transmits the measurement result data to the server.
The basic system for generating the health management intervention support information according to claim 1. The information communication terminal records the answer result to the question about the insured person's daily behavior, and transmits the answer result data to the server.
The basic system for generating the health management intervention support information according to claim 1. The daily activities include sleep time, meal content, dose and frequency of prescription drugs, supplements taken, over-the-counter drugs taken, working hours, working hours, and driving hours.
The basic system for generating the health management intervention support information according to claim 3. The health management intervention support information includes dietary habits improvement management intervention support information, lifestyle improvement management intervention support information, diet management intervention support information, health examination consultation management intervention support information, consultation frequency management intervention support information, and drug management intervention support information. , Specific health guidance management intervention support information, dental examination consultation management intervention support information, medical examination consultation management intervention information on specific diseases such as cancer, at least one of them,
The basic system for generating the health management intervention support information according to any one of claims 1 to 4. It is a consultation frequency management intervention support information generation system that generates consultation frequency management intervention support information using the basic system according to any one of claims 1 to 4.
The consultation frequency management intervention support information generation system is
Based on the medical information of the insured recorded in the insurer database, the insured is classified and predicted by machine learning, and it is determined whether or not the insured is subject to guidance. the IoT scales, the wearable terminal, based on information transmitted from the information communication terminal, a consultation frequency determination means for consultation frequency to determine whether it is within the appropriate range,
The determination result by the consultation frequency determination means is displayed on the display means.
This is a consultation frequency management intervention support information generation system. A drug management intervention support information generation system that generates drug management intervention support information using the basic system according to any one of claims 1 to 4.
The drug management intervention support information generation system is
Based on the medical information of the insured recorded in the insurer database, the insured is classified and predicted by machine learning, and it is determined whether or not the insured is subject to guidance. , The side effect risk calculation means for calculating the side effect occurrence risk due to the drug based on the information transmitted from the IoT weight scale, the wearable terminal, and the information communication terminal.
The risk of side effects is displayed on the display terminal.
A drug management intervention support information generation system characterized by this. The risk of occurrence of the side effect is displayed by probability or risk rank.
The drug management intervention support system according to claim 7. The drug management intervention support information generation system further has a drug check system for checking whether or not the drug being taken is a multidrug with overlapping efficacy and / or whether or not it is a contraindicated drug for concomitant use.
When the drug check system determines that the drug is a multidrug and / or a contraindicated drug in combination, the determination result is displayed on the display terminal.
The drug management intervention support system according to claim 7 or 8. A drug management intervention support information generation system that generates drug management intervention support information using the basic system according to any one of claims 1 to 4.
The drug management intervention support information generation system is
Based on the medical information of the insured recorded in the insurer database, the insured is classified and predicted by machine learning, and it is determined whether or not the insured is subject to guidance. the IoT scales, the wearable terminal, based on information transmitted from the information communication terminal, presence or absence of frequent administration, optimal drug load, among the adherence and prediction residual drug number, calculating at least one of information And
The calculation result is displayed on the display terminal.
A drug management intervention support information generation system characterized by this. The drug management intervention support information generation system further has a drug check system for checking whether or not the drug being taken is a multidrug with overlapping efficacy and / or whether or not it is a contraindicated drug for concomitant use.
When the drug check system determines that the drug is a multidrug and / or a contraindicated drug in combination, the determination result is displayed on the display terminal.
The drug management intervention support system according to claim 10.

Images