JP5982949B2 - Health guidance target person selection condition decision support device - Google Patents

Description

  The present invention relates to an apparatus that supports an insurer's health guidance business, and more particularly, to an apparatus that supports an insurer's work for determining conditions for selecting a health guidance target person.

  In recent years, an increase in medical expenses that an insurer bears on an insured person has put pressure on the insurer's finances, and there is an urgent need to create measures for reducing medical expenses. As one of the measures, the insurer is providing health guidance for health promotion of the insured. A certain standard (health guidance standard) is set for the health check result of the insured, and health guidance is given to those who meet the standard (applicable person). For example, the standards are set so that people who need to improve their lifestyle to improve their health, or who have a high risk of future sickness fall under this category. On the other hand, for those who do not meet the criteria (non-applicable people), it is determined that there is no need to improve their lifestyle habits and health guidance is not provided.

  From April 2008, insurers (National Health Insurance and Employee Insurance) are obliged to conduct health checkup and health guidance business focusing on visceral fat obesity for insured persons and dependents over 40 years old. ing. The Ministry of Health, Labor and Welfare has established the health guidance standards used in this project.

  However, since the characteristics of the insured person are different for each insurer, it is considered that there is a large difference in effect when the health guidance target persons are narrowed down under uniform conditions. For this reason, it is considered desirable to provide health guidance for insured persons who meet their standards by setting their own standards separately from those targeted by the government. Since health promotion measures are costly, insurers select a group of insured persons who have a large medical cost reduction effect through health guidance, and want to take measures only for the selected limited group.

  In order to meet the demands of insurers, a selection support system for health guidance subjects has been developed. For example, the technology described in Patent Document 1 outputs the predicted value of the medical cost reduction effect when the insurer provides guidance for the health guidance target group satisfying the condition by setting the selection conditions for the subject. Provides the function to do. By using this support system, the insurer can know the reduction effect when a specific selection condition is set.

JP 2007-257565 A

  However, the technique described in Patent Document 1 requires an operation in which an insurer person in charge specifies a selection condition, so that it takes a very long time to select a selection condition having a large effect. In addition, the insurer is required to select the one having the maximum effect as a result of designating many selection conditions (preferably exhaustively). If the technique described in Patent Document 1 is used, the insurer's person in charge must manually set a number of selection condition candidates for comparison / evaluation. There was a problem. In addition, the insurer sets a lower limit for the number of people targeted for health guidance. This is because even if the medical cost reduction effect per person for the health guidance corresponding to the selection target group is high, if the number of persons is two, there will be no significant effect as a whole. It was difficult to extract conditions for selecting a health guidance target group that satisfies the lower limit value requirement for the target number of people and has a high medical cost reduction effect from among many selection condition candidates.

  The object of the present invention is to select conditions for selecting a health guidance target group that satisfies the above-described problem, that is, satisfies the requirements of the lower limit value for the target number of people and has a high medical cost reduction effect, from among a large number of selection condition candidates. An object of the present invention is to provide a health guidance target person selection condition determination support device that solves the problem that it is difficult to extract.

The health guidance target person selection condition determination support device according to one aspect of the present invention is:
Includes health checkup data for the candidate for health guidance one year before the base year, multiple selection condition candidates, the minimum number of candidates, and information on medical expenses for the base year for the candidate for health guidance A storage unit for storing receipt data and a label value indicating whether or not the candidate for health guidance participated in health guidance one year before the reference year;
A processor connected to the storage unit,
The processor
Based on the plurality of selection condition candidates and the health diagnosis data for each health guidance target candidate, out of all the combinations of the selection condition candidates, the health guidance target persons equal to or greater than the minimum number of selection candidates are A combination that can be selected from candidate candidates for guidance is determined as a selection condition candidate set,
For each selection condition candidate set, based on the health check data, the label value, and the receipt data, satisfy all the selection conditions in the selection condition candidate set among the candidates for health guidance and participate in health guidance Calculate the difference between the average medical cost of the individual who did not and the average medical cost of the individual who participated in the health guidance as the medical cost reduction effect,
It is programmed to output the selection condition candidate set and the medical cost reduction effect.

  Since the present invention has the above-described configuration, a selection condition for selecting a health guidance target group that satisfies the lower limit value requirement for the target number of people and has a high medical cost reduction effect is extracted from a large number of selection condition candidates. can do.

It is a block diagram of a 1st embodiment of the present invention. It is a figure which shows an example of the selection condition candidate in the 1st Embodiment of this invention. It is a flowchart which shows the process example of the 1st Embodiment of this invention. It is a flowchart which shows the process example of the selection condition candidate set determination part in the 1st Embodiment of this invention. It is a figure which shows an example of the medical examination data in the 1st Embodiment of this invention. It is a flowchart which shows the process example of the medical cost reduction effect calculation part in the 1st Embodiment of this invention.

Next, embodiments of the present invention will be described in detail with reference to the drawings.
[First embodiment]
Referring to FIG. 1, the health guidance target person selection condition determination support device 1 according to the first embodiment of the present invention satisfies the lower limit requirement for the number of target persons from among a large number of selection condition candidates and has a medical cost. It has a function to extract selection conditions for selecting a health guidance target group with a high reduction effect.

  In the present embodiment, it is assumed that the medical cost reduction effect by the health guidance appears in the year following the year of receiving the health guidance, and the medical care in the base year of the person who received the health guidance in the year one year before the base year. The difference between the average value of expenses and the average value of medical expenses in the base year for those who did not receive health guidance in the year one year before the base year is defined as the medical cost reduction effect. In addition, although health guidance focusing on built-in fat type obesity is taken as an example, it goes without saying that the present invention is not limited to such an example.

  The health guidance target person selection condition determination support device 1 includes a communication interface unit (communication I / F unit) 11, an operation input unit 12, a screen display unit 13, a storage unit 14, and a processor 15 as hardware.

  The communication I / F unit 11 includes a dedicated data communication circuit, and has a function of performing data communication with various devices (not shown) connected via a communication line (not shown). The operation input unit 12 includes an operation input device such as a keyboard and a mouse, and has a function of detecting an operator operation and outputting the operation to the processor 15. The screen display unit 13 includes a screen display device such as an LCD or a PDP, and has a function of displaying various information such as an operation menu and a determination result on the screen in response to an instruction from the processor 15.

  The storage unit 14 includes a storage device such as a hard disk or a semiconductor memory, and has a function of storing processing information and programs 14P necessary for various processes in the processor 15. The program 14P is a program that realizes various processing units by being read and executed by the processor 15, and is read by an external device (not shown) or a computer via a data input / output function such as the communication I / F unit 11. It is read in advance from a possible storage medium (not shown) and stored in the storage unit 14. As main processing information stored in the storage unit 14, health check data 14A, receipt data 14B, a participation flag 14C, a selection condition candidate list 14D, a minimum selection number E, a selection condition candidate set 14F, There is a medical cost reduction effect of 14G.

  The health check data 14A is composed of health check data of an individual who is an insured person. The medical checkup data 14A exists for each individual who is a candidate for health guidance. Each individual's health checkup data includes a personal ID that uniquely identifies the individual, personal information such as year of visit, age of visit, sex, smoking habits, height, weight, waist circumference, minimum blood pressure, maximum blood pressure, blood glucose level In addition, various test values such as triglycerides and information such as determination on wounds and diseases as a determination result determined by a doctor from the test result are included. The medical examination data 14A is medical examination data one year before the reference year.

  The receipt data 14B is a description of medical expenses that the medical institution charges the insurer for the medical care received by the patient, and exists for each individual. One individual's receipt data includes information such as a personal ID for identifying a patient, a date of medical treatment, a name of a disease for which medical treatment has been performed, and a medical remuneration score serving as a standard for medical expenses. The receipt data 14B is receipt data in the reference year.

  The participation flag 14C is a label value for each individual indicating whether or not the individual selected as the health guidance target person participated in the health guidance conducted one year before the reference year. In general, health guidance is conducted continuously multiple times. The participation flag 14C is set to a value indicating participation when participating in health guidance even once, and set to a value indicating non-participation when not participating in health guidance once.

  The selection condition candidate list 14 </ b> D is a list of candidate conditions that serve as criteria for selecting a health guidance target person. FIG. 2 is a configuration example of the selection condition candidate list 14D. In this example, each selection condition candidate is managed by giving an ID. Individual selection condition candidates are created based on the items described in the personal information of the insured person described in the medical examination data and the test results. For example, “male” and “female” are selection condition candidates created from the gender described in the personal information. “60-64 years”, “30-34 years”, “50-54 years”, “55-59 years”, and “40-44 years” are selection condition candidates created from the ages described in the personal information. “BMI = 1”, “abdominal circumference = 1”, and “blood pressure = 1” are selection condition candidates created from the examination results. The selection condition candidate created from the inspection result is expressed by binarizing the inspection result using a predetermined threshold value, not the inspection result itself. For example, BMI = 1 corresponds to, for example, BMI ≧ 25. As the threshold value, for example, a health guidance determination standard set by the Ministry of Health, Labor and Welfare can be used.

  The minimum number of selected persons 14E is a lower limit value regarding the target number of persons determined for the health guidance target group selected by the insurer.

  The selection condition candidate set 14 </ b> F is a combination of one or more selection condition candidates that can select health guidance target persons equal to or more than the minimum number of selection candidates from the health guidance target candidates. One selection condition candidate set 14F includes a set ID and an ID of a selection condition candidate constituting the set.

  The medical cost reduction effect 14G is an average value of medical costs that can be reduced per insured by health guidance, and exists for each selection condition candidate set 14F. One medical cost reduction effect 14G includes the ID of the corresponding selection condition candidate set and the medical cost reduction amount.

  The processor 15 has a microprocessor such as a CPU and its peripheral circuits, and reads and executes the program 14P from the storage unit 14, thereby causing the hardware and the program 14P to cooperate to implement various processing units. have. As main processing units realized by the processor 15, there are an input unit 15A, a selection condition candidate set determination unit 15B, a medical cost reduction effect calculation unit 15C, and an output unit 15D.

  The input unit 15A inputs the health check data 14A, the receipt data 14B, the participation flag 14C, the selection condition candidate list 14D, and the minimum number of selected users 14E from the communication I / F unit 11 or the operation input unit 12, and the storage unit 14 has a function of storing.

  The selection condition candidate set determination unit 15B reads the health check data 14A for each individual, the selection condition candidate list 14D, and the minimum selection number 14E from the storage unit 14, and uses these data to select the selection condition candidate. A combination capable of selecting a health guidance target person with a minimum selection number of 14E or more from all the combinations from among health guidance target candidate candidates is determined as a selection condition candidate set 14F and stored in the storage unit 14. It has a function.

  The medical cost reduction effect calculation unit 15C reads the health check data 14A, the receipt data 14B, the participation flag 14C, and the selection condition candidate set 14F for each individual from the storage unit 14, and uses these data to select the selection condition candidate set. The medical cost reduction effect 14G for each 14F is calculated and stored in the storage unit 14. In calculating the medical cost reduction effect 14G, the medical cost reduction effect calculating unit 15C satisfies all the conditions of the selection condition candidates in the selection condition candidate set 14F among the health guidance target candidates and does not participate in the health guidance The medical cost reduction effect 14G is obtained by subtracting the average medical cost of the individual who participated in the health guidance from the average medical cost of the health guidance target candidate who satisfies all the conditions of the selection condition candidate in the selection condition candidate set 14F. The function to calculate as follows.

  The output unit 15 </ b> D has a function of reading the selection condition candidate set 14 </ b> F and the medical cost reduction effect 14 </ b> G from the storage unit 14, outputting them to the screen display unit 13, or outputting them to the outside through the communication I / F unit 11.

  Next, with reference to FIG. 3, operation | movement of the health guidance subject selection condition determination assistance apparatus 1 concerning this embodiment is demonstrated.

  First, the input unit 15A receives, from the communication I / F unit 11 or the operation input unit 12, the health diagnosis data 14A, the receipt data 14B, the participation flag 14C, the selection condition candidate list 14D, and the minimum for each health guidance target candidate. The number 14E selected is input and stored in the storage unit 14 (step S1).

  Next, the selection condition candidate set determination unit 15B determines the selection condition candidate set 14F using the health diagnosis data 14A for each health guidance target candidate, the selection condition candidate list 14D, and the minimum number of selection persons 14E. Then, it is stored in the storage unit 14 (step S2).

  Next, the medical cost reduction effect calculation unit 15C uses the health diagnosis data 14A, the receipt data 14B, the participation flag 14C for each health guidance target candidate, and the selection condition candidate set 14F for each selection condition candidate set 14F. Is calculated and stored in the storage unit 14 (step S3).

  Next, the output unit 15D outputs the selection condition candidate set 14F and the medical cost reduction effect 14G as selection results to the screen display unit 13 or outputs them to the outside through the communication I / F unit 11 (step S4). At that time, the output unit 15D may rearrange the selection condition candidate set 14F in the descending order of the medical cost reduction effect 14G and output it. At that time, only the upper predetermined number or predetermined ratio selection condition candidate set 14F of the medical cost reduction effect may be output.

  Next, the process of step S2 for calculating the selection condition candidate set will be described in detail.

  FIG. 4 is a detailed flowchart of step S2. First, the selection condition candidate set determination unit 15B initializes a variable n indicating the size of the selection condition candidate set, that is, the number of selection condition candidates included, to 0 (step S11). Next, the selection condition candidate set determination unit 15B selects a set satisfying the minimum number 14E of selection condition candidate sets of size n + 1, that is, size 1 (step S12). The selection condition candidate set of size 1 corresponds to a set including only one selection condition candidate described in the selection condition candidate list 14D. Whether or not the set satisfies the minimum number of selected persons 14E is determined by examining whether or not the health diagnosis data 14A satisfying the conditions indicated by the selection condition candidates included in the set is greater than or equal to the minimum number of selected persons 14E. .

  Next, the selection condition candidate set determination unit 15B determines whether or not one or more selection condition candidate sets have been selected (step S13). If one or more selection condition candidate sets are selected, the process proceeds to step S14. If no selection condition candidate set has been selected, the processing in FIG. 4 ends.

  In step S14, the selection condition candidate set determination unit 15B stores the set selected in the immediately preceding step S12 in the storage unit 14 as a part of the selection condition candidate set 14F. Subsequently, the selection condition candidate set determination unit 15B increments n by 1 (step S15), and generates a set of size n + 1 from a size n set that satisfies the minimum number of selected users 14E (step S16). Then, it is determined whether or not one or more sets of size n + 1 have been generated (step S17). If they can be generated, the process returns to step S12 and the same process as described above is repeated. On the other hand, if it could not be generated, the process of FIG.

  FIG. 5 is an example of health check data 14A for five persons. Hereinafter, the procedure for calculating the selection condition candidate set will be described using the health diagnosis data of the five insured persons shown in FIG. 5 as an example. Note that the minimum number of selected persons 14F is three, and the selection condition candidate list 14D has the contents shown in FIG.

  First, a set satisfying three persons as the minimum number of selected persons is selected from a set of size 1 (step S12). As a result, a total of four selection condition candidate sets of {1}, {2}, {7}, and {9} are selected. Here, {} indicates one selection condition candidate set. The numerical value in {} indicates the ID of the selection condition candidate included in the selection condition candidate set. For example, {1} indicates a set having “male” as a selection condition candidate.

  The four selected sets {1}, {2}, {7}, {9} are stored in the storage unit 14 as a part of the selection condition candidate set 14F (step S14).

  Next, from the four sets {1}, {2}, {7}, {9} of the selected size 1, the size 2 sets {1, 2}, {1, 7}, { 1, 9}, {2, 7}, {2, 9}, {7, 9} are generated (step S16). Then, from these six sets, a set that satisfies three persons as the minimum number of selected persons is selected (step S12). As a result, a total of four selection condition candidate sets of {1, 7}, {1, 9}, {2, 9}, {7, 9} are selected.

  The four selected sets {1, 7}, {1, 9}, {2, 9}, {7, 9} are stored in the storage unit 14 as part of the selection condition candidate set 14F ( Step S14).

  Next, from the four sets {1, 7}, {1, 9}, {2, 9}, {7, 9} of the selected size 1, the size 3 set {1, 7, 9}, {1, 2, 9}, {1, 7, 9}, {2, 7, 9} are generated (step S16). Then, from these four sets, a set that satisfies three persons as the minimum number of selected persons is selected (step S12). As a result, one selection condition candidate set {1, 7, 9} is selected.

  The selected one set {1, 7, 9} is stored in the storage unit 14 as a part of the selection condition candidate set 14F (step S14).

  Since there is only one set of size 3, a set of size 4 is not generated, and the process of FIG. 4 ends.

  In the method shown in FIG. 4, if the item sets I and J are I⊂J, when “I = {E}, J = {C, E}: I⊂J”, “frequency of I ≧≧ J It uses the fact that “degree” always holds. As a result, it can be seen that the same result as in the case of exhaustively investigating enormous selection condition candidates can be obtained even if the calculation is excluded for combinations that do not satisfy the minimum number of selected persons even if the size is increased.

  Next, the process of step S3 for calculating the medical cost reduction effect will be described in detail.

  FIG. 6 is a detailed flowchart of step S3. First, the medical cost reduction effect calculation unit 15C pays attention to one of the selection condition candidate sets 14F (step S21).

  Next, the average medical expenses of individuals who satisfy all of the selection conditions of the selection candidate set 14F that is attracting attention among the candidates for health guidance and have not participated in the health guidance, and the selection that is attracting attention among the candidates for health guidance An average medical cost of an individual who satisfies all the selection conditions of the condition candidate set 14F and participates in the health guidance is calculated (step S22). More specifically, for example, the following is performed.

  First, a counter C1 that counts the number of individuals who have not participated in health guidance, a counter C2 that counts the number of individuals who have participated in health guidance, and a register R1 that stores the total medical expenses of individuals who have not participated in health guidance The registers R2 for storing the total medical expenses of the individuals who participated in the health guidance are initialized to 0, respectively.

  Next, for each health diagnosis data 14A, it is determined whether or not all selection condition candidates included in the selection condition candidate set 14F under attention are satisfied. The following processing is performed only when it is satisfied. First, it is determined whether the participation flag 14C corresponding to the insured person ID in the health check data 14A is “participation” or “non-participation”. If it is “non-participation”, the counter C1 is incremented by 1, and the medical cost determined by the receipt data 14B corresponding to the insured person ID in the health check data 14A is added to the register R1. On the other hand, if it is “participation”, the counter C2 is incremented by 1, and the medical cost determined by the receipt data 14B corresponding to the insured person ID in the health check data 14A is added to the register R2. When the processing for all the health diagnosis data 14A is completed, the medical cost held in the register R1 is divided by the value of the counter C1, and the average medical cost of the individual who did not participate in the health guidance is calculated. Further, the medical cost held in the register R2 is divided by the value of the counter C2, and the average medical cost of the individual who participated in the health guidance is calculated.

  Subsequently, the medical cost reduction effect calculation unit 15C calculates the medical cost reduction effect by subtracting the average medical cost of the individual who participated in the health guidance from the average medical cost of the individual who did not participate in the health guidance ( Step S23). Then, the calculated medical cost reduction effect is stored in the storage unit 14 in association with the ID of the selection condition candidate set under attention (step S24).

  When the medical cost reduction effect calculation unit 15C finishes the processing for the selection condition candidate set under attention, the medical cost reduction effect calculation unit 15C determines whether or not there remains another selection condition candidate set that has not yet received attention (step S25). If there remains an unprocessed selection condition candidate set, attention is shifted to one of the selection condition candidate sets (step S26), the process returns to step S22, and the same process as described above is repeated. On the other hand, if there remains no unprocessed selection condition candidate set, the processing in FIG.

  As described above, according to the present embodiment, a selection condition for selecting a health guidance target group that satisfies the lower limit requirement for the target number of people and has a high medical cost reduction effect is extracted from a large number of selection condition candidates. can do. The reason for this is to calculate the medical cost reduction effect for each selection condition candidate set after determining the combination that satisfies the requirements for the minimum number of selected persons from all the combinations of selection condition candidates as the selection condition candidate set. is there.

  In addition, according to the present embodiment, selection conditions for selecting a health guidance target group that satisfies the requirements of the lower limit value for the target number of people and has a high medical cost reduction effect can be efficiently extracted. The reason is that the medical cost reduction effect is calculated only for the combinations that can select the number of health guidance target candidates from the candidates for health guidance among all the combinations of selection condition candidates. is there. On the other hand, in the technique described in Patent Document 1 in which it is not known whether the requirement for the minimum number of selections is satisfied unless the medical cost reduction effect is calculated, the medical cost reduction effect is obtained for all combinations of selection condition candidates. Need to be calculated.

[Other embodiments]
The present invention is not limited to the above embodiment, and various other additions and changes can be made. For example, the following embodiments are also possible.

  For example, in the above-described embodiment, for each selection condition candidate, a future medical cost prediction means for predicting a predetermined medical cost for a predetermined injury or illness of the insured group corresponding to the selection condition candidate, and an insurer Future medical expenses forecast output means to output selection condition candidates that meet the requirements of the health guidance target of the future in a ranking format that is sorted by the magnitude of the difference between the future medical expenses forecast and the medical expenses of the base year It may be.

  In the above embodiment, for each selection condition candidate, there may be provided a function for predicting a predetermined medical cost for injury and illness after A years of the insured group corresponding to the selection condition candidate. Good. That is, the medical expenses after A year may be predicted according to the gender age of the insured group corresponding to the selection condition candidates. For example, when the insured group corresponding to the selection condition candidate is male, 50-54 years old, the method of predicting the annual total medical cost of injury and illness = hypertension 10 years later is hypertension of 50-54 years old. Estimate by replacing the annual medical cost per person by symptom, blood pressure, treatment rate with findings, treatment rate without findings, and per capita presence / absence with the values of 60-64 years of base year. The reason for limiting the findings to those of blood pressure is that blood pressure is the test item that most affects hypertension. The name of the wound and the test item that has the most influence on the name of the wound are obtained from a database that stores the list of information corresponding to the name of the wound that appears in the reception and the test item of the health check that most affects each wound and disease. To do. A prediction example is shown below.

(Example 1)
Among men who meet condition items other than the age of selection conditions, there are blood pressure findings in the 60-64 years, treatment rate of hypertension x men in the insured group who falls under the selection condition candidates, 50-54 years Among men who meet items other than age in the selection conditions, blood pressure findings in the 60-64 age group, annual medical expenses per person with hypertension +
Among men who meet condition items other than the age of selection conditions, blood pressure stations in the 60-64 age group are considered, the treatment rate of hypertension x men in the insured group who fall under the selection condition candidates, 50-54 age group Among men who meet items other than the age of selection conditions, blood pressure stations in the 60-64 age group are considered, annual medical expenses per person for hypertension = men in the insured group that meet the selection conditions, Total medical expenses for hypertension 10 years after age 50-54

  In the above predicting means, among men who satisfy items other than the age of the selection conditions, blood pressure findings in the 60-64 age group are present / absent, hypertension treatment rate, and items other than the age are satisfied in the selection conditions Among men who have blood pressure findings in their 60s to 64s and who need annual medical expenses per person for hypertension, 60- Although it is necessary to extract health checkup data and receipt data for the 64-year-olds, this support system narrows down the selection condition candidates. Therefore, only the narrowed selection condition candidates need medical examination data. And receipt data can be extracted from the entire database at once. On the other hand, in the conventional method, after the insurer's person in charge decides the selection conditions, the health diagnosis data and the receipt data that match the conditions are extracted from the database and prediction is performed. Since the selection conditions are not determined in advance, and it is necessary to extract data from the database every time the conditions are set, the number of accesses to the database increases. In this case, it is considered that it takes time to output the medical cost reduction effect and the predicted value as compared with the support system of the present invention.

  Furthermore, in the conventional method, in order to predict a future medical cost, receipt data for a plurality of past years is necessary to learn a prediction model. In the medical cost prediction method of the present invention, one year of receipt data is required. Makes it possible to predict medical expenses. Therefore, it is considered that the requirements for introducing the support system are relaxed and it is easy for the insurer to introduce this support system.

  The above example is an example of hypertension, but it is also possible to calculate the future predicted medical expenses such as diabetes and hyperlipidemia, which are called lifestyle-related diseases.

  Further, in the support system of the present invention, the insurer's person in charge of the health guidance can output the predicted value of the future medical cost of the insured group satisfying each selection condition and the medical cost reduction effect by the health guidance side by side. This may be useful when considering a plan. For example, if there is a large discrepancy between the predicted value after 10 years and the current predicted value, it will be possible to reduce medical costs in the future by taking measures to reduce the difference as much as possible. By selecting a selection condition that has a large divergence and a large medical cost reduction effect, it is considered possible to select a health guidance target group for the future over a long span.

DESCRIPTION OF SYMBOLS 1 ... Health guidance object selection condition determination support apparatus 11 ... Communication I / F part 12 ... Operation input part 13 ... Screen display part 14 ... Memory | storage part 14A ... Health examination data 14B ... Receipt data 14C ... Participation flag 14D ... Selection condition candidate List 14E ... Minimum number of selected persons 14F ... Selection condition candidate set 14G ... Medical cost reduction effect 14P ... Program 15 ... Processor 15A ... Input unit 15B ... Selection condition candidate set determination unit 15C ... Medical cost reduction effect calculation unit 15D ... Output unit

Claims (5)

Includes health checkup data for the candidate for health guidance one year before the base year, a plurality of selection condition candidates, the minimum number of selectable persons, and medical expenses for the base year for the candidate for health guidance A storage unit for storing receipt data and a label value indicating whether the candidate for health guidance participated in health guidance one year before the reference year;
A processor connected to the storage unit,
The processor is
Based on the plurality of selection condition candidates and the health diagnosis data for each of the health guidance target candidates, out of all combinations of the selection condition candidates, the health guidance target persons equal to or greater than the minimum selection number are selected as the health A combination that can be selected from candidate candidates for guidance is determined as a selection condition candidate set,
For each selection condition candidate set, based on the health check data, the label value, and the receipt data, satisfy all the selection conditions in the selection condition candidate set among the candidates for health guidance and participate in health guidance Calculate the difference between the average medical cost of the individual who did not and the average medical cost of the individual who participated in the health guidance as the medical cost reduction effect,
Output the selection condition candidate set and the medical cost reduction effect ,
In determining the selection condition candidate set,
When the number of the selection condition candidates included in the selection condition candidate set is referred to as a size, in order from the selection condition candidate set having a size of 1, the number of health guidance subjects equal to or greater than the minimum number of selection candidates Select a combination of the selection condition candidates that can be selected from the candidates,
In determining the selection condition candidate set having a size of n (≧ 2), a combination of the selection condition candidates having a size of n is generated from the selection condition candidate set having a size of n−1 already determined, Health guidance that is programmed to select a combination of candidate selection conditions that can select health guidance target candidates equal to or greater than the minimum number of candidates from among the generated combinations. Target selection condition decision support device. The processor is
2. The health guidance target person selection condition determination support apparatus according to claim 1, wherein the selection is made by rearranging the selection condition candidate sets in the order of magnitude of the medical cost reduction effect. 3. The health according to claim 1, wherein each of the selection condition candidates includes two types of values obtained by binarizing item data included in the health check data with a threshold as separate selection condition candidates. Training target selection condition decision support device. Includes health checkup data for the candidate for health guidance one year before the base year, a plurality of selection condition candidates, the minimum number of selectable persons, and medical expenses for the base year for the candidate for health guidance A storage unit that stores receipt data and a label value that indicates whether the candidate for health guidance participated in health guidance one year before the reference year; and a processor connected to the storage unit. A health guidance target person selection condition determination support method executed by the health guidance target person selection condition determination support device,
The processor is
Based on the plurality of selection condition candidates and the health diagnosis data for each of the health guidance target candidates, out of all combinations of the selection condition candidates, the health guidance target persons equal to or greater than the minimum selection number are selected as the health A combination that can be selected from candidate candidates for guidance is determined as a selection condition candidate set,
For each selection condition candidate set, based on the health check data, the label value, and the receipt data, satisfy all the selection conditions in the selection condition candidate set among the candidates for health guidance and participate in health guidance Calculate the difference between the average medical cost of the individual who did not and the average medical cost of the individual who participated in the health guidance as the medical cost reduction effect,
Output the selection condition candidate set and the medical cost reduction effect ,
In determining the selection condition candidate set,
When the number of the selection condition candidates included in the selection condition candidate set is referred to as a size, in order from the selection condition candidate set having a size of 1, the number of health guidance subjects equal to or greater than the minimum number of selection candidates Select a combination of the selection condition candidates that can be selected from the candidates,
In determining the selection condition candidate set having a size of n (≧ 2), a combination of the selection condition candidates having a size of n is generated from the selection condition candidate set having a size of n−1 already determined, Health guidance target person selection condition determination support for selecting a combination of selection condition candidates that can select health guidance target persons from the generated combination among the health guidance target candidates. Method. Includes health checkup data for the candidate for health guidance one year before the base year, a plurality of selection condition candidates, the minimum number of selectable persons, and medical expenses for the base year for the candidate for health guidance To a processor connected to a storage unit that stores receipt data and a label value indicating whether or not the candidate for health guidance participated in health guidance one year before the reference year,
Based on the plurality of selection condition candidates and the health diagnosis data for each of the health guidance target candidates, out of all combinations of the selection condition candidates, the health guidance target persons equal to or greater than the minimum selection number are selected as the health Determining combinations that can be selected from the candidate candidates for instruction as a selection condition candidate set;
For each selection condition candidate set, based on the health check data, the label value, and the receipt data, satisfy all the selection conditions in the selection condition candidate set among the candidates for health guidance and participate in health guidance Calculating the difference between the average medical cost of the individual who did not and the average medical cost of the individual who participated in the health guidance as a medical cost reduction effect,
Outputting the selection condition candidate set and the medical cost reduction effect ,
In the step of determining as the selection condition candidate set,
When the number of the selection condition candidates included in the selection condition candidate set is referred to as a size, in order from the selection condition candidate set having a size of 1, the number of health guidance subjects equal to or greater than the minimum number of selection candidates Selecting a combination of the selection condition candidates that can be selected from candidates;
In determining the selection condition candidate set having a size of n (≧ 2), a combination of the selection condition candidates having a size of n is generated from the selection condition candidate set having a size of n−1 already determined, A step of selecting a combination of candidate selection conditions capable of selecting, from among the generated combinations, health guidance target persons equal to or greater than the minimum number of candidates from among the health guidance target candidates; and
Because of the program to perform the.

Images