Program, information processing device, method, and system

The system addresses the challenge of identifying optimal medical examination recommendation methods by using a machine learning model to analyze past data and determine personalized intervention patterns, enhancing health checkup participation and reservation rates.

JP2024156305AActive Publication Date: 2024-11-06JMDC CO LTD

Patent Information

Application Number
JP2023070661
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-24
Publication Date
2024-11-06
Estimated Expiration
2043-04-24

AI Technical Summary

Technical Problem

Existing technologies, such as those described in Patent Document 1, are unable to effectively compare multiple screening recommendation methods and identify the optimal method for recommending medical examinations, limiting the effectiveness of health checkup notifications.

Method used

A system and method that utilizes a machine learning model to analyze past medical examination recommendation history data, generate intervention patterns, and determine the best combination of intervention measures for individual subjects or groups to maximize health checkup attendance rates through personalized recommendations.

Benefits of technology

The system effectively identifies the optimal intervention pattern for each subject, increasing the likelihood of health checkup participation and reservation rates, thereby optimizing the effectiveness of health checkup recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024156305000001_ABST
    Figure 2024156305000001_ABST
Patent Text Reader

Abstract

To provide a program, an information processing device, a method, and a program for specifying optimal means for recommending reception of medical examination for a subject to whom medical examination is to be recommended.SOLUTION: In a system for studying means for recommending reception of medical examination in which a terminal device and a server are capable of communicating with each other via a network, a program that operates the server causes the server to execute: acquiring medical examination recommendation history data (S900); generating at lease one intervention pattern including at least one intervention measure which is means for recommending reception of medical examination (S903); generating, for each intervention pattern, teacher data in which results of recommendation for receiving medical examination are output for input of the intervention pattern from the medical examination recommendation history data (S904); generating a machine learning model for each intervention pattern by using the teacher data (S905); inputting the intervention pattern to the machine learning model and thereby acquiring an output for each subject which is an inference result of the machine learning model (S906); and determining the best intervention pattern for each subject on the basis of the output (S908).SELECTED DRAWING: Figure 9
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a program, an information processing device, a method, and a system. [Background technology]

[0002] A technology disclosed in Patent Document 1 is known as a technology for sending recommendation notices to subjects of specific health checkups, etc. The technology disclosed in Patent Document 1 relates to a method for optimizing the timing of recommendation notices to encourage insured persons to undergo various medical procedures and health checkups implemented by medical insurance institutions, and calculates the optimal timing of the recommendation notice for each insured person as an objective variable, or calculates a score indicating the magnitude of the recommendation effect for each timing as an objective variable, by using explanatory variables extracted from multiple feature amounts related to the insured person and regression analysis or machine learning based on the explanatory variables. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-157307 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology disclosed in Patent Document 1 uses a machine learning model to optimize the timing of notification of recommendations to insured persons, and is not able to compare multiple screening recommendation means or identify the optimal screening recommendation means.

[0005] Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide a technology that makes it possible to identify optimal means of encouraging people to undergo screening to those who are recommended to undergo screening. [Means for solving the problem]

[0006] A program for operating a computer having a processor, the program instructs the processor to execute the following steps: a first step of acquiring screening recommendation history data including at least personal information of a subject who is recommended to undergo a screening, the subject's past screening results, and the results of the screening recommendation for the subject; a second step of generating at least one intervention pattern including at least one intervention measure that is a means of recommending the subject to undergo a screening; a third step of generating teacher data for each intervention pattern from the screening recommendation history data, the teacher data being the intervention pattern generated in the second step as input and the results of the screening recommendation as output; a fourth step of generating a machine learning model for each intervention pattern using the teacher data generated in the third step; a fifth step of inputting the intervention pattern into the machine learning model generated in the fourth step to obtain an output for each subject, which is an inference result of the machine learning model; and a sixth step of determining the best intervention pattern for each subject based on the output obtained in the fifth step. Effect of the Invention

[0007] According to the present disclosure, it is possible to identify the optimal means of encouraging a person to undergo a medical examination to be recommended for a medical examination. [Brief description of the drawings]

[0008] [Figure 1] 1 is a diagram showing an overall configuration of a system according to an embodiment; [Diagram 2] FIG. 2 is a diagram illustrating a functional configuration of a terminal device according to an embodiment. [Diagram 3] FIG. 2 is a diagram illustrating a functional configuration of a server according to an embodiment. [Figure 4] FIG. 2 is a diagram showing a data structure of a medical examination recommendation history database according to an embodiment. [Diagram 5] FIG. 2 is a diagram illustrating an example of a data structure of an intervention database according to an embodiment. [Figure 6] FIG. 13 is a diagram illustrating an example of a data structure of an intervention pattern database according to an embodiment. [Figure 7]FIG. 13 is a diagram illustrating an example of a data structure of an individual improvement rate database according to an embodiment. [Figure 8] FIG. 13 is a diagram illustrating an example of a data structure of a defined intervention pattern database according to an embodiment. [Figure 9] 11 is a flowchart illustrating an example of a processing flow in a system according to an embodiment. [Figure 10] FIG. 1 illustrates an example of an intervention in a system according to an embodiment. [Figure 11] FIG. 11 is a diagram showing an example of a method for recommending a medical checkup in a system according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In all the drawings explaining the embodiment, the same reference numerals are given to common components, and repeated explanations are omitted. Note that the following embodiment does not unduly limit the contents of the present disclosure described in the claims. In addition, not all of the components shown in the embodiment are essential components of the present disclosure. In addition, each figure is a schematic diagram and is not necessarily illustrated strictly.

[0010] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be a single-core or multi-core.

[0011] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application specific integrated circuit (ASIC)) that performs part or all of the processing.

[0012] In the following explanation, information that gives an output for an input may be described using an expression such as "xxx table", but this information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, the "xxx table" may be called "xxx information".

[0013] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0014] In addition, in the following explanation, the processing may be described with the "program" as the subject, but since the program is executed by a processor to perform a specified processing step by appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may be the processor (or a device such as a controller having the processor).

[0015] The program may be installed in a device such as a computer, or may be, for example, in a program distribution server or a computer-readable (e.g., non-transitory) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0016] In the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may be used instead.

[0017] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference signs (or common signs among the reference signs) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference signs) of the elements may be used.

[0018] In the following description, the control lines and information lines are those that are considered necessary for the description, and not all control lines and information lines in the product are necessarily shown. All components may be connected to each other.

[0019] <0 System Overview> The system disclosed herein seeks to provide a means of encouraging people to undergo health checkups, to maximize the effectiveness of such notifications sent by health insurance associations, local governments, etc. to people who are eligible to undergo health checkups (hereinafter simply referred to as "targets"), such as insured persons and dependents of the health insurance association.

[0020] Entities that recommend undergoing health checkups (hereinafter referred to as "health insurance organizations") include health insurance associations and local governments, but the system according to the present disclosure does not intend to limit the entities to these health insurance associations, etc. Furthermore, targets of recommendations for undergoing health checkups include mainly insured persons and dependents of health insurance associations, or residents who have an address or residence in a local government, but the system according to the present disclosure does not intend to limit the targets to these members, etc. Furthermore, health insurance targeted by health insurance associations may include all health insurances included in the medical insurance systems implemented in the countries targeted by the system according to the present disclosure, such as so-called national health insurance, seamen's insurance, and mutual aid associations.

[0021] The health checkups that the subject is recommended to undergo are conducted by the health insurance organization (including cases where the examination is outsourced to another organization). Generally, such health checkups are conducted repeatedly on an annual basis. The subject is recommended to undergo a health checkup within the relevant fiscal year. The health checkups that the subject is recommended to undergo include health checkups called general health checkups, health checkups called specific health checkups, gynecological health checkups for women, etc. There are often conditions regarding the subject's age for those who are eligible to undergo these health checkups, but in the system of the present disclosure, conditions regarding the subject's age are not mandatory. Similarly, there is no intention to limit the type of health checkup in the system of the present disclosure.

[0022] For health insurance organizations that conduct (or are in charge of) health checkups, it is important for subjects to undergo health checkups to properly understand their own health conditions and preferably receive appropriate medical treatment, from the perspective that subjects will pay appropriate medical expenses (which will ultimately lead to the optimization of expenses paid by the health insurance organization). From this perspective, health insurance organizations recommend that subjects undergo health checkups. Therefore, health insurance organizations have an incentive to increase the rate of subjects responding to the recommendation to undergo a health checkup that they have conducted (this includes the rate at which subjects read the recommendation notice, searched for an institution that conducts the health checkup based on the recommendation notice, and even made an appointment to undergo the health checkup with that institution), and have an incentive to take measures to increase the rate.

[0023] Therefore, in the system disclosed herein, historical data on medical check-up recommendation including the results of past recommendations to the subject is obtained, and a combination of means for encouraging the subject to undergo a health check-up is set, the relationship between these is inferred using a machine learning model, and the best combination of means for encouraging the subject to undergo a health check-up is determined from among several combinations of means for encouraging the subject to undergo a health check-up.

[0024] When selecting the "best combination of means for encouraging medical examinations," parameters are required to determine which is best. In short, it can be considered that the combination of means for encouraging medical examinations that maximizes the rate of improvement in the subjects' medical examination attendance is the best combination. However, it can also be considered that the recommendation to receive a medical examination is effective if the rate of appointments for a medical examination can be maximized, and it can also be considered that the recommendation to receive a medical examination is effective if the response rate of the subjects to the recommendation to receive a medical examination (such as seeing the message for recommendation to receive a medical examination) can be maximized. The operator of the system according to the present disclosure can decide what parameters to set, but in the following explanation, the combination of means for encouraging medical examinations that maximizes the rate of appointments for a medical examination is considered to be the "best combination of means for encouraging medical examinations."

[0025] Furthermore, in the system disclosed herein, the "best combination of means of encouraging medical examinations" is determined for each subject. Therefore, at the individual subject level, the combination of means of encouraging medical examinations that maximizes the rate of appointments made for a health checkup corresponds to the "best combination of means of encouraging medical examinations" when that subject makes an appointment for a health checkup. Subjects may also be grouped based on the characteristics of the subjects (e.g., health insurance group, place of residence, etc.), and the "best combination of means of encouraging medical examinations" may be determined for this group. In this case, the combination of means of encouraging medical examinations that maximizes the rate of appointments made for a health checkup becomes the "best combination of means of encouraging medical examinations."

[0026] In this specification, a means of encouraging a subject to undergo a health checkup is referred to as an "intervention measure," and a combination of intervention measures including at least one intervention measure is referred to as an "intervention pattern." An example of an intervention measure is shown in FIG. 10. In the example shown in FIG. 10, the intervention measures are classified into several categories (e.g., message content, approach means, etc.). An intervention pattern is generated by selecting any one of the intervention measures classified into each category. It is not necessary to select multiple intervention measures classified into a certain category to generate an intervention pattern. For example, it is not necessary to select direct mail and telephone as intervention measures classified into approach means to generate an intervention pattern. In addition, an intervention pattern can be generated by selecting one intervention measure classified into one category, and it is not necessary to select intervention measures classified into multiple categories individually to generate an intervention pattern. Furthermore, an intervention pattern that does not include any intervention measures may be generated as an intervention pattern in the system according to the present disclosure. This is because, in selecting the best intervention pattern, it is preferable to compare with the case where the subject is not encouraged to undergo a health checkup.

[0027] The system according to the present disclosure is naturally applicable not only to recommending a person to undergo a health checkup, but also to diagnosing the presence or absence of a specific disease, such as cancer screening. In this specification, the term "screening" is used as a concept that includes health checkups and screening. However, except when it is necessary to distinguish between a health checkup and screening such as cancer screening, the terms "health checkup" and "medical examination" may be used for ease of understanding. Even in this case, the system according to the present disclosure should not be interpreted as being applicable only to "health checkups" and "medical examinations."

[0028] <One embodiment> <1 Overall system configuration> FIG. 1 is a diagram showing the overall configuration of a consultation recommendation means consideration system 1 (hereinafter simply referred to as system 1) of this embodiment. As shown in FIG. 1, the system 1 includes a plurality of terminal devices (terminal device 10a and terminal device 10b are shown in FIG. 1. Hereinafter, they may be collectively referred to as "terminal device 10"), a server 20, and an external data server 30. The terminal device 10 and the server 20 are connected to each other so as to be able to communicate with each other via a network 80. The network 80 is configured as a wired or wireless network. In this embodiment, the server 20 is a server having a function as a Web server (including a cloud server), and exchanges information with the terminal device 10 through Web pages. In addition, a Web page browser for viewing Web pages is installed in the terminal device 10, but a dedicated application for providing the services of the server 20 may be installed and configured to be viewable through the dedicated application.

[0029] Since the hardware configuration of the terminal device 10a and the hardware configuration of the terminal device 10b are common, the hardware configuration of the terminal device 10a will be described and a description of the hardware configuration of the terminal device 10 will be omitted.

[0030] The terminal device 10 is a device operated by a user who is considering the recommendation of undergoing a health check. The terminal device 10 is realized by a stationary PC (Personal Computer), a laptop PC, or the like. In addition, the terminal device 10 may be, for example, a tablet compatible with a mobile communication system, a mobile terminal such as a smartphone, or the like.

[0031] The terminal device 10 is communicatively connected to the server 20 via a network 80. The terminal device 10 is connected to the network 80 by communicating with communication devices such as a wireless base station 81 compatible with communication standards such as 4G, 5G, and LTE (Long Term Evolution), and a wireless LAN router 82 compatible with wireless LAN (Local Area Network) standards such as IEEE (Institute of Electrical and Electronics Engineers) 802.11. As shown in FIG. 1, the terminal device 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19.

[0032] The communication IF 12 is an interface for inputting and outputting signals so that the terminal device 10 can communicate with an external device. The input device 13 is an input device (e.g., a keyboard, a touch panel, a touch pad, a pointing device such as a mouse, etc.) for receiving an input operation from a user. The output device 14 is an output device (a display, a speaker, etc.) for presenting information to a user. The memory 15 is for temporarily storing a program and data processed by the program, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for saving data, and is, for example, a flash memory or a HDD (Hard Disc Drive). The processor 19 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, etc.

[0033] The server 20 is managed by an administrator of the system 1 of this embodiment, and the stored contents are appropriately modified / added / deleted by the user of the terminal device 10 .

[0034] The server 20 is a computer connected to a network 80. The server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29.

[0035] The communication IF 22 is an interface for inputting and outputting signals so that the server 20 can communicate with an external device. The input / output IF 23 functions as an interface with an input device for receiving an input operation from a user and an output device for presenting information to a user. The memory 25 is for temporarily storing programs and data processed by the programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage 26 is a storage device for saving data, such as a flash memory or a HDD (Hard Disc Drive). The processor 29 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, etc.

[0036] The external data server 30 is a server that stores personal information of a subject who is recommended to undergo a medical examination (including a health check), past medical examination results (including health check results) of the subject, and medical examination recommendation history data including at least the results of the recommendation to undergo a medical examination (including a health check). As such a server, a combination of a server that stores so-called medical receipt data owned by a health insurance organization and a server that stores the results of past medical examination recommendations is considered. Usually, these servers are considered to be configured as separate entities. Therefore, the external data server 30 shown in FIG. 1 may be configured with multiple servers. In addition, personal information may also be configured as a server that stores past medical examination results and a server that stores the results of medical examination recommendations. In addition, the external data server 30 does not need to provide all of the data related to medical receipts and the data related to the results of past medical examination recommendations to the system 1 according to this embodiment, and may provide necessary data from these data based on a request from the system 1 according to this embodiment, or may prepare a server that stores only the necessary data and allow the system 1 according to this embodiment to access this server.

[0037] <1.1 Functional configuration of the terminal device 10> Fig. 2 is a block diagram showing an example of a functional configuration of the terminal device 10 shown in Fig. 1. The terminal device 10 shown in Fig. 2 is realized by, for example, a PC, a mobile terminal, or a wearable terminal. As shown in Fig. 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. The blocks included in the terminal device 10 are electrically connected by, for example, a bus or the like.

[0038] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on a signal generated by the control unit 190 and transmits the signal to the outside (for example, the server 20). The communication unit 120 performs reception processing on a signal received from the outside and outputs the signal to the control unit 190.

[0039] The input device 13 is a device for inputting instructions or information by a user who operates the terminal device 10. The input device 13 may be realized by, for example, a keyboard, a mouse, a reader, or the like. When the terminal device 10 is a mobile terminal or the like, the input device 13 is realized by, for example, a touch-sensitive device 131 in which an instruction is input by touching an operation surface. The input device 13 converts an instruction input by a user into an electrical signal, and outputs the electrical signal to the control unit 190. The input device 13 may include, for example, a receiving port that receives an electrical signal input from an external input device.

[0040] The output device 14 is a device for presenting information to a user who operates the terminal device 10. The output device 14 is realized, for example, by a display 141 or the like. The display 141 displays data according to the control of the control unit 190. The display 141 is realized, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display or the like.

[0041] The audio processing unit 17 performs, for example, digital-analog conversion processing of an audio signal. The audio processing unit 17 converts a signal provided from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is realized, for example, by a processor for audio processing. The microphone 171 accepts audio input and provides an audio signal corresponding to the audio input to the audio processing unit 17. The speaker 172 converts the audio signal provided from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0042] The storage unit 180 is realized by, for example, the memory 15 and the storage unit 16, and stores data and programs used by the terminal device 10.

[0043] The control unit 190 is realized by the processor 19 reading the application program 181 stored in the storage unit 180 and executing instructions included in the application program 181. The control unit 190 controls the operation of the terminal device 10. The control unit 190 operates in accordance with the application program 181 stored in the storage unit 180, thereby fulfilling the functions of an operation reception unit 191, a transmission / reception unit 192, a data processing unit 193, and a presentation control unit 194.

[0044] The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 receives information based on instructions input from a keyboard, a mouse, or the like.

[0045] Furthermore, the operation reception unit 191 receives voice instructions input from the microphone 171. Specifically, for example, the operation reception unit 191 receives a voice signal input from the microphone 171 and converted into a digital signal by the voice processing unit 17. For example, the operation reception unit 191 analyzes the received voice signal and extracts a predetermined noun, thereby acquiring an instruction from the user.

[0046] The transmitting / receiving unit 192 performs processing for the terminal device 10 to transmit and receive data to and from an external device such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits the business content input by the user to the server 20. In addition, the transmitting / receiving unit 192 receives information about the user from the server 20.

[0047] The data processing unit 193 performs calculations on the data that the terminal device 10 accepts as input in accordance with the application program 181, and performs processing to output the calculation results to the memory 15 or the like.

[0048] The presentation control unit 194 controls the output device 14 to present the information provided by the server 20 to the user. Specifically, for example, the presentation control unit 194 causes the display 141 to display the information transmitted from the server 20. In addition, the presentation control unit 194 causes the speaker 172 to output the information transmitted from the server 20.

[0049] <1.2 Functional configuration of server 20> 3 is a diagram showing an example of a functional configuration of the server 20. As shown in FIG. 3, the server 20 fulfills the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0050] The communication unit 201 performs processing for the server 20 to communicate with external devices.

[0051] The memory unit 202 includes, for example, a medical examination recommendation history DB (DataBase) 2022, an intervention measure DB 2023, an intervention pattern DB 2024, an individual improvement rate DB 2025, a confirmed intervention pattern DB 2026, teacher data 2027, a learning model 2028, and the like.

[0052] The medical examination recommendation history DB2022 is a database in which medical examination recommendation history data acquired from the external data server 30 is stored. As already explained, the medical examination recommendation history data includes at least personal information of the subject who is recommended to undergo a medical examination (including a health checkup), the subject's past medical examination (including a health checkup) results, and the results of the recommendation to undergo a medical examination (including a health checkup) for the subject, but may also include other data. For example, if the external data server 30 includes a server that stores data related to medical receipts, data constituting the medical receipt data may be stored in the medical examination recommendation history DB2022 as medical examination recommendation history data. The medical examination recommendation history data stored in the medical examination recommendation history DB2022 is stored by the medical examination recommendation history acquisition module 2033 described later, and is added, deleted, and updated as appropriate. Details will be described later.

[0053] The intervention DB2023 is a database that stores interventions that can be performed on subjects in the system 1 according to this embodiment. It is preferable that the data stored in the intervention DB2023 is stored in advance by an operator of the system 1 according to this embodiment, and that the data is added, deleted, and updated as appropriate. Details will be described later.

[0054] The type of intervention to be stored in the intervention DB 2023 is also related to whether an intervention pattern, which will be described later, will effectively encourage a patient to undergo medical examination. One possible method is to first set the categories shown in Figure 10 as intervention measures, and then set detailed intervention measures for the categories that effectively encourage a patient to undergo medical examination.

[0055] The intervention pattern DB 2024 is a database in which intervention patterns to be considered for implementation on a subject in the system 1 according to this embodiment are stored. The data stored in the intervention pattern DB 2024 is generated and stored by an intervention pattern generation module 2035 (described later), and is appropriately added, deleted, and updated. Details will be described later.

[0056] The individual improvement rate DB2025 is a database storing, for each intervention pattern, the improvement rate of a parameter related to medical examination attendance that is estimated (inferred by the learning model 2028) by adopting this intervention pattern. Here, the parameter related to medical examination attendance may be appropriately determined by the operator of the system 1 according to this embodiment, but in the system 1 according to this embodiment, as described above, the parameter related to medical examination attendance is mainly the appointment rate for medical examinations (including health checkups). The data stored in the individual improvement rate DB2025 is calculated and stored by the individual improvement rate calculation module 2037 described later, and is appropriately added, deleted, and updated. Here, the individual improvement rate calculation module 2037 calculates an individual improvement rate for each subject. Details will be described later.

[0057] The confirmed intervention pattern DB 2026 is a database that stores information indicating an intervention pattern that is confirmed to be implemented for each subject based on the calculated individual improvement rate. The confirmed intervention pattern DB 2026 is determined (confirmed) and stored by an intervention pattern determination module 2038, which will be described later, and is appropriately added, deleted, and updated.

[0058] The teacher data 2027 is teacher data that inputs an intervention pattern stored in the intervention pattern DB 2024 and outputs the result of a recommendation to undergo a medical examination (including a health checkup). The teacher data 2027 is generated for each subject by a learning model generation module 2036 described later, and is added, deleted, and updated as appropriate.

[0059] The learning model 2028 is obtained by performing machine learning based on the above-mentioned teacher data 2027 in accordance with the model learning program not shown. When a specific intervention pattern is input to this learning model 2028, a recommendation to undergo a medical examination (including a health check) is obtained as an inference result. The learning model 2028 is generated for each subject by a learning model generation module 2036 described later, and is added, deleted, and updated as appropriate. Therefore, the output of the learning model 2028 is also output for each subject.

[0060] The learning model 2028 according to this embodiment is, for example, a parameterized composite function in which a plurality of functions are combined. The parameterized composite function is defined by a combination of a plurality of adjustable functions and parameters. The prediction model according to this embodiment may be any parameterized composite function that satisfies the above requirements, but is assumed to be a multi-layered network model (hereinafter referred to as a multi-layered network). A prediction model using a multi-layered network has an input layer, an output layer, and at least one intermediate layer or hidden layer provided between the input layer and the output layer. The prediction model is expected to be used as a program module that is a part of artificial intelligence software.

[0061] As the multi-layered network according to the present embodiment, for example, a deep neural network (DNN) that is a multi-layered neural network that is the subject of deep learning may be used. As the DNN, for example, a convolution neural network (CNN) that targets images may be used.

[0062] In addition, the above is merely an example of a prediction model, and the prediction model may have other configurations. For example, the prediction model may be a rule-based model described by a function in which the intervention pattern and the result of the recommendation for a health check are variables and each variable is assigned a coefficient derived from past performance.

[0063] The control unit 203 is realized by the processor 29 reading the application program 2021 stored in the storage unit 202 and executing instructions included in the application program 2021. The control unit 203 operates in accordance with the application program 2021 to perform functions shown as a reception control module 2031, a transmission control module 2032, a medical examination recommendation history acquisition module 2033, an intervention measure selection module 2034, an intervention pattern generation module 2035, a learning model generation module 2036, an individual improvement rate calculation module 2037, an intervention pattern determination module 2038, and a medical examination recommendation implementation module 2039.

[0064] The reception control module 2031 controls the process in which the server 20 receives a signal from an external device in accordance with a communication protocol.

[0065] The transmission control module 2032 controls the process in which the server 20 transmits signals to external devices in accordance with a communication protocol.

[0066] The medical examination recommendation history acquisition module 2033 acquires medical examination recommendation history data from, for example, the external data server 30. The medical examination recommendation history data includes at least personal information of the subject who is recommended to undergo a health checkup, the subject's past health checkup results, and the results of the recommendation to undergo the health checkup for the subject. The medical examination recommendation history acquisition module 2033 does not need to acquire all data stored in the external data server 30, and only needs to acquire data necessary to obtain the best intervention pattern for each subject, which will be described later. In addition, since the data stored in the external data server 30 may include data corresponding to personal information (e.g., name, address), it is preferable that the medical examination recommendation history acquisition module 2033 replaces such personal information with identification information and stores it in the medical examination recommendation history DB2022.

[0067] Since the data stored in the external data server 30 is likely to be updated as appropriate, it is preferable that the screening recommendation history acquisition module 2033 periodically accesses the external data server 30 and acquires the screening recommendation history data. The screening recommendation history acquisition module 2033 stores the acquired screening recommendation history data in the screening recommendation history DB2022, and also adds to, deletes, and updates the recorded contents of the screening recommendation history DB2022 as appropriate.

[0068] The intervention measure selection module 2034 extracts an intervention measure that is the basis of an intervention pattern generated by an intervention pattern generation module 2035 described later from the intervention measure DB 2023, and provides the extracted intervention measure to the intervention pattern generation module 2035. The intervention measure selection module 2034 may select a single intervention measure or multiple intervention measures.

[0069] There is no particular limitation on the method by which the intervention selection module 2034 selects an intervention from the intervention DB 2023. When providing an intervention to the intervention pattern generation module 2035, a single intervention may be initially provided, and then multiple interventions including an intervention that effectively encourages consultation may be provided to the intervention pattern generation module 2035. Alternatively, it is possible to cause the intervention pattern generation module 2035 to generate an intervention pattern that gives a certain meaning to the intervention pattern by combining multiple interventions.

[0070] The intervention pattern generation module 2035 generates an intervention pattern including at least one intervention based on the intervention provided by the intervention selection module 2034. Preferably, the intervention pattern generation module 2035 also generates an intervention pattern that does not include an intervention, that is, does not recommend consultation at all. The intervention pattern generation module 2035 stores the generated intervention pattern in the intervention pattern DB 2024.

[0071] As with the intervention measures selected by the intervention measure selection module 2034, the type of intervention pattern generated by the intervention pattern generation module 2035 is important for effective consultation recommendation. Although there is no particular limitation on the intervention pattern generation method by the intervention pattern generation module 2035, one example is a method of generating an intervention pattern by trial and error, in which an intervention pattern having a single intervention measure is generated at first, and then, when the examination recommendation history data is updated, an intervention measure is appropriately added to an intervention pattern having a large improvement rate of the parameter related to examination attendance calculated by the individual improvement rate calculation module 2037 (i.e., the effect of examination recommendation is high).

[0072] From the viewpoint of trial and error, it is preferable that the intervention measure selection module 2034 and the intervention pattern generation module 2035 periodically select an intervention measure and generate an intervention pattern. In particular, since the medical examination recommendation history acquisition module 2033 periodically acquires and updates the medical examination recommendation history data, it is preferable to select an intervention measure and generate an intervention pattern according to the timing of updating the medical examination recommendation history data.

[0073] The learning model generation module 2036 generates teacher data for each subject using the intervention pattern generated by the intervention pattern generation module 2035 as input and the result of the recommendation to undergo a health check included in the medical examination recommendation history data as output, and stores the teacher data 2027 in the memory unit 202. Next, the learning model generation module 2036 generates a learning model for each subject by performing machine learning using the generated teacher data 2027, and stores the learning model 2028 in the memory unit 202. Preferably, the learning model generation module 2036 recreates the teacher data 2027 in accordance with the timing of updating the medical examination recommendation history data, and re-learns the learning model 2028.

[0074] The individual improvement rate calculation module 2037 inputs an intervention pattern into the learning model 2028 generated by the learning model generation module 2036, and obtains the result of recommendation to undergo a medical examination (including health checkup), which is the inference result of this learning model 2028, for each subject. Then, the individual improvement rate calculation module 2037 calculates an improvement rate of a parameter related to undergoing a medical examination based on the result of recommendation to undergo a medical examination (including health checkup), which is the output from the learning model 2028, and stores the calculated result in the individual improvement rate DB2025. It is preferable that the individual improvement rate calculation module 2037 also calculates the improvement rate in accordance with the timing of re-learning of the learning model 2028 by the learning model generation module 2036, and updates the individual improvement rate DB2025.

[0075] The intervention pattern determination module 2038 determines the best intervention pattern for each subject based on the improvement rate calculated by the individual improvement rate calculation module 2037. The "best intervention pattern" here refers to, as an example, the maximum number of appointments for medical checkups (including health checkups) that are the result of recommendations to receive medical checkups (including health checkups) as a result of implementing the intervention pattern.

[0076] The checkup recommendation implementation module 2039 recommends the subject to undergo a checkup (including a health checkup) based on the optimal intervention pattern for each subject determined by the intervention pattern determination module 2038.

[0077] An example of the medical checkup recommendation performed by the medical checkup recommendation implementation module 2039 will be described with reference to FIG.

[0078] The medical examination recommendation implementation module 2039 refers to the personal information of the subject included in the medical examination recommendation history data, acquires detailed personal information of the subject from the external data server 30 as necessary, and sends a postcard 1101 to the address of the subject or sends an SMS (short message) 1102 to the mobile terminal of the subject. The postcard 1101 displays a two-dimensional barcode 1103 containing link information for accessing the system 1 according to this embodiment, including identification information (ID) that can identify the subject. Similarly, the SMS 1102 contains link information 1104 for accessing the system 1 according to this embodiment, including identification information (ID) that can identify the subject. The postcard 1101 and the SMS 1102 are also examples of the above-mentioned intervention measures and intervention patterns. A subject who has received a postcard 1101 or an SMS 1102 accesses the system 1 according to this embodiment by using a two-dimensional barcode 1103 or by using a method of access based on link information 1104. The medical examination recommendation implementation module 2039 that has been accessed displays a screen 1105 for transitioning to a questionnaire page on a mobile terminal or the like carried by the subject. The content written on this screen 1105 is also an example of the above-mentioned intervention measure or intervention pattern. Next, the subject performs an operation input by, for example, touching a button 1106 displayed at the bottom of the screen 1105. The operation input of the button 1106 can also be taken in as part of the medical examination recommendation history data and used as data for determining the best intervention pattern.

[0079] <2 Data Structure> Figures 4 to 8 are diagrams showing the data structures of the databases stored in the server 20. Note that Figures 4 to 8 are merely examples, and do not exclude data that is not shown.

[0080] The databases shown in Figures 4 to 8 are relational databases, which are used to manage data sets called tables in a tabular format structurally defined by rows and columns, by associating them with each other. In a database, a table is called a table, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables can be set and associated.

[0081] Usually, a column that serves as a primary key for uniquely identifying a record is set in each table, but setting a primary key to a column is not essential. The control unit 203 of the server 20 can cause the processor 29 to add, delete, or update records in a specific table stored in the storage unit 202 according to various programs.

[0082] FIG. 4 is a diagram showing the data structure of the medical examination recommendation history DB2022. As shown in FIG. 4, each record of the medical examination recommendation history DB2022 includes, for example, an item "subject ID", an item "insurance group ID", an item "city ID", an item "age", an item "sex", an item "medical examination recommendation type", an item "past medical examination result", an item "medical examination recommendation message ID", an item "approach means", an item "approach date and time", an item "reward", an item "medical examination recommendation input", and an item "whether or not medical examination was taken". Each item of the medical examination recommendation history DB2022 is input by the medical examination recommendation history acquisition module 2033 when the medical examination recommendation history acquisition module 2033 acquires medical examination recommendation history data from the external data server 30. The information stored in the medical examination recommendation history DB2022 can be changed and updated as appropriate.

[0083] The item "Subject ID" is an ID for identifying a health check subject who is a subject to be examined by the system 1 (particularly the server 20) according to this embodiment. The item "Insurance organization ID" is an ID for identifying a health insurance organization (insurance organization) that is the operator of the health check, which is the entity that uses the best intervention pattern for each subject identified by the system 1 according to this embodiment. The item "City, ward, town, village ID" is an ID for identifying the city, ward, town, village to which the address or residence of the subject identified by the subject ID belongs, and is an ID for identifying the city, ward, town, village that is the area under the jurisdiction of the health insurance organization identified by the insurance agency. The item "Age" is information indicating the age of the subject identified by the subject ID. The item "Gender" is information indicating the gender of the subject identified by the subject ID. The item "Type of health check recommendation" is information indicating the type of health check recommended for the subject identified by the subject ID. The item "Past health check results" is information indicating the results of health checks recommended for the subject identified by the subject ID. The item "medical checkup recommendation message ID" is an ID for identifying the message included in the recommendation to check a medical examination when the recommendation was made to the subject identified by the subject ID. The item "approach means" is information indicating the means used to recommend a medical examination when the recommendation was made to the subject identified by the subject ID. The item "approach date and time" is information indicating the date and time when the recommendation to check a medical examination was made to the subject identified by the subject ID. The item "reward" is information indicating whether or not a reward was given to the subject identified by the subject ID when the recommendation to check a medical examination was made. The item "whether or not the subject underwent a medical examination" is information indicating whether or not the subject identified by the subject ID underwent a medical examination as a result of the recommendation to check a medical examination.

[0084] Fig. 5 is a diagram showing a data structure of the intervention measure DB2023. As shown in Fig. 5, each record of the intervention measure DB2023 includes, for example, an item "intervention measure ID", an item "intervention measure", an item "intervention measure content ID", and an item "intervention measure". Each item of the intervention measure DB2023 is input in advance as appropriate by the operator of the system 1 according to this embodiment. Information stored in the intervention measure DB2023 can be changed and updated as appropriate.

[0085] The item "Intervention Measure ID" is an ID for identifying a category of intervention measures (see FIG. 10) that may be implemented in the system 1 of this embodiment. The item "Intervention Measure" is information indicating the name of the category of intervention measures identified by the intervention measure ID. The item "Intervention Measure Content ID" is an ID for identifying a specific intervention measure that belongs to the category of intervention measures identified by the intervention measure ID. The item "Intervention Measure Content" is information indicating the name of a specific intervention measure identified by the intervention measure content ID.

[0086] In addition, in Fig. 5, "-" indicates that there is no information. As shown in Fig. 5, the intervention DB 2023 includes interventions for which there is no intervention, that is, no recommendation for screening, as indicated by the intervention ID "I0004."

[0087] Fig. 6 is a diagram showing a data structure of the intervention pattern DB 2024. As shown in Fig. 6, each record of the intervention pattern DB 2024 includes, for example, an item "intervention pattern ID", an item "intervention measure ID", and an item "intervention measure content ID". Each item of the intervention pattern DB 2024 is input by the intervention pattern generation module 2035 when the intervention pattern generation module 2035 generates an intervention pattern. Information stored in the intervention pattern DB 2024 can be changed and updated as appropriate.

[0088] The item "intervention pattern ID" is an ID for identifying an intervention pattern, which is a combination of means of encouraging a subject to undergo medical examination in system 1 according to this embodiment. The item "intervention ID" is an ID for identifying a category of intervention that can be implemented in system 1 according to this embodiment, and is common to the item "intervention ID" in intervention DB2023 shown in FIG. 5. The item "intervention content ID" is an ID for identifying a specific intervention that belongs to the category of intervention identified by the intervention ID, and is common to the item "intervention content ID" in intervention DB2023 shown in FIG. 5.

[0089] Fig. 7 is a diagram showing the data structure of the individual improvement rate DB2025. As shown in Fig. 7, each record of the individual improvement rate DB2025 includes, for example, an item "subject ID", an item "intervention pattern ID", and an item "improvement rate". Each item of the individual improvement rate DB2025 is input by the individual improvement rate calculation module 2037 when the individual improvement rate calculation module 2037 calculates the improvement rate of a parameter related to medical examination attendance for an intervention pattern for each subject. The information stored in the individual improvement rate DB2025 can be changed and updated as appropriate.

[0090] The item "Subject ID" is an ID for identifying a health check subject who is to undergo a health check by the system 1 of this embodiment, and is the same as the item "Subject ID" in the health check recommendation history DB2022 shown in FIG. 4. The item "Intervention pattern ID" is an ID for identifying an intervention pattern which is a combination of means of recommending examination to a subject in the system 1 of this embodiment, and is the same as the item "Intervention pattern ID" in the determined intervention pattern DB2026 shown in FIG. 7. The item "Improvement rate" is information regarding the improvement rate of a parameter related to examination attendance calculated by the individual improvement rate calculation module 2037.

[0091] Fig. 8 is a diagram showing the data structure of the confirmed intervention pattern DB 2026. As shown in Fig. 8, each record of the confirmed intervention pattern DB 2026 includes, for example, an item "subject ID", an item "intervention pattern ID", and an item "confirmation date". Each item of the confirmed intervention pattern DB 2026 is input by the individual improvement rate calculation module 2037 when the intervention pattern confirmation module 2038 determines an intervention pattern to be performed for each subject, in other words, the best intervention pattern for each subject. Information stored in the confirmed intervention pattern DB 2026 can be changed and updated as appropriate.

[0092] The item "Subject ID" is an ID for identifying a health check subject who is to undergo a health check by the system 1 of this embodiment, and is the same as the item "Subject ID" in the health check recommendation history DB2022 shown in FIG. 4. The item "Intervention pattern ID" is an ID for identifying an intervention pattern which is a combination of means of recommending examination to a subject in the system 1 of this embodiment, and is the same as the item "Intervention pattern ID" in the confirmed intervention pattern DB2026 shown in FIG. 7. The item "Confirmation date" is information indicating the date on which the intervention pattern determination module 2038 determined (confirmed) that the intervention pattern identified by the item "Intervention pattern ID" is best for the subject identified by the item "Subject ID".

[0093] <3 Example of operation> An example of the operation of the server 20 will now be described.

[0094] FIG. 9 is a flowchart showing an example of the main operation of the server 20.

[0095] In step S900, the control unit 203 acquires medical examination recommendation history data from the external data server 30. Specifically, for example, the control unit 203 acquires medical examination recommendation history data required for the operation of the system 1 according to this embodiment from the external data server 30 using the reception control module 2031 and the medical examination recommendation history acquisition module 2033.

[0096] Next, in step S901, the control unit 203 selects an intervention measure for generating an intervention pattern from the intervention measure DB 2023. Specifically, for example, the control unit 203 selects an intervention measure for generating an intervention pattern from the intervention measure DB 2023 by the intervention measure selection module 2034.

[0097] In step S902, the control unit 203 generates an intervention pattern using the intervention measure selected in step S901. Specifically, for example, the control unit 203 generates an intervention pattern using the intervention measure selected in step S901 by the intervention pattern generation module 2035. The generated intervention pattern is stored in the intervention pattern DB 2024.

[0098] In step S903, the control unit 203 determines a result of the recommendation to undergo a health checkup, which is to be output in the teacher data 2027 and the learning model 2028 generated in step S904 and thereafter. Specifically, for example, the control unit 203 determines, by the learning model generation module 2036, a result of the recommendation to undergo a health checkup, which is to be output in the teacher data 2027 and the learning model 2028 generated in step S904 and thereafter.

[0099] In step S904, the control unit 203 generates teacher data 2027 having the result of the recommendation to undergo a health check determined in step S903 as an output and the intervention pattern generated in step S902 as an input. Specifically, for example, the control unit 203 generates teacher data 2027 by the learning model generation module 2036, having the result of the recommendation to undergo a health check determined in step S903 as an output and the intervention pattern generated in step S902 as an input. The generated teacher data 2027 is stored in the memory unit 202 of the server 20.

[0100] In step S905, the control unit 203 performs machine learning using the teacher data 2027 generated in step S904 to generate a learning model 2028. Specifically, for example, the control unit 203 performs machine learning using the teacher data 2027 generated in step S904 by the learning model generation module 2036 to generate a learning model 2028. The generated learning model 2028 is stored in the storage unit 202 of the server 20.

[0101] In step S906, the control unit 203 selects an intervention pattern from the intervention pattern DB2024, selects the learning model 2028 stored in the memory unit 202, and inputs the intervention pattern to the selected learning model 2028 to obtain the result of the recommendation to undergo a health check, which is the output of the learning model 2028 as an inference result. Specifically, for example, the control unit 203 selects an intervention pattern from the intervention pattern DB2024 by the individual improvement rate calculation module 2037, selects the learning model 2028 stored in the memory unit 202, and inputs the intervention pattern to the selected learning model 2028 to obtain the result of the recommendation to undergo a health check, which is the output of the learning model 2028 as an inference result. The obtained output is temporarily stored in the memory unit 202. The output acquisition operation in step S906 is repeatedly executed for each subject by changing the intervention pattern and the learning model 2028 in various ways.

[0102] In step S907, the control unit 203 calculates an improvement rate of the parameter related to attending a medical examination based on the output which is the inference result acquired in step S906. Specifically, for example, the control unit 203 calculates an improvement rate of the parameter related to attending a medical examination based on the output which is the inference result acquired in step S906 by the individual improvement rate calculation module 2037. The calculated improvement rate is stored in the individual improvement rate DB 2025. The improvement rate calculation operation in step S907 is executed for each subject.

[0103] In step S908, the control unit 203 determines the best intervention pattern to be implemented for each subject based on the improvement rate calculated in step S907. Specifically, for example, the control unit 203 determines the best intervention pattern to be implemented for each subject based on the improvement rate calculated in step S907 by the intervention pattern determination module 2038. The determined best intervention pattern for each subject is stored in the determined intervention pattern DB 2026.

[0104] After that, although not shown in the figure, the control unit 203, for example, by the checkup recommendation implementation module 2039, recommends the subject to undergo a health checkup based on the optimal intervention pattern determined in step S908.

[0105] <5. Effects of one embodiment> As described above in detail, the system 1 according to this embodiment can identify the optimal means of encouraging a person to undergo medical examination to undergo medical examination.

[0106] The technology disclosed in the above-mentioned Patent Document 1 predicts the probability of undergoing a medical checkup after a recommendation is made. However, this technology does not predict the effect of the recommendation to undergo a medical checkup.

[0107] On the other hand, the system 1 according to the present embodiment predicts the degree of increase in the probability of undergoing a medical checkup due to the recommendation. Furthermore, the system 1 according to the present embodiment predicts the degree of increase (improvement rate) in the recommendation for a medical checkup for each pattern (intervention pattern) of the recommendation for a medical checkup for each subject, identifies the pattern with the largest degree of increase, and determines this intervention pattern as the best intervention pattern for each subject.

[0108] Therefore, according to the system 1 of this embodiment, the improvement rates resulting from multiple intervention patterns are compared for each subject, and as a result of the comparison, the best intervention pattern for each subject is determined, making it possible to identify the optimal means of encouraging those who are recommended to undergo screening to receive screening.

[0109] <6 Notes> In addition, the above-described embodiments are described in detail to clearly explain the present disclosure, and are not necessarily limited to those including all of the described configurations. In addition, some of the configurations of each embodiment can be added to, deleted from, or replaced with other configurations.

[0110] As an example, in the system 1 according to the embodiment described above, the teacher data 2027 and the learning model 2028 are uniformly generated for the medical examination recommendation history data acquired by the system 1, but the teacher data 2027 and the learning model 2028 may be generated for each health insurance group and for each area in which the subject lives, and the teacher data 2027 and the learning model 2028 may be selected according to the health insurance group to which the subject belongs and the area in which the subject lives.

[0111] In addition, in the system 1 according to the embodiment described above, the best intervention pattern is obtained for each subject, but the subjects may be grouped based on the characteristics of the subjects (e.g., the subject's residential area), and the teacher data 2027 and the learning model 2028 may be generated for each group, and the best intervention pattern may be obtained for each group. Alternatively, the subjects may be grouped, and then the best intervention pattern may be obtained for each group using the common teacher data 2027 and learning model 2028.

[0112] Furthermore, various parameters can be selected as the results of the medical checkup recommendation in the output of the learning model 2028 in the system 1 according to the embodiment described above. One example is whether or not a medical checkup appointment has been made, but other parameters that can be selected include whether or not the medical checkup recommendation message has been read, transition to a medical checkup appointment page, and medical checkup attendance rate.

[0113] In addition, the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that realizes the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-mentioned embodiments, and the program code itself and the storage medium storing it constitute the present invention. Examples of storage media for supplying such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, etc.

[0114] Furthermore, the program code for realizing the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, Java (registered trademark), and the like.

[0115] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed over a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read out and execute the program code stored in the storage means or storage medium.

[0116] The matters described in the above embodiments will be supplemented below.

[0117] (Appendix 1) A program (2021) for operating a computer (20) having a processor (29), the program (2021) causes the processor (29) to execute a first step (S900) of acquiring screening recommendation history data including at least personal information of a subject who is recommended to undergo a screening, past screening results of the subject, and a result of a screening recommendation for the subject; a second step (S902) of generating at least one intervention pattern including at least one intervention measure that is a means of recommending the subject to undergo a screening; and a program (2021) for inputting the intervention pattern generated in the second step (S902) and outputting a result of the screening recommendation. A program (2021) that executes a third step (S904) of generating teacher data for each intervention pattern from checkup recommendation history data, a fourth step (S905) of generating a machine learning model for each intervention pattern using the teacher data generated in the third step (S904), a fifth step (S906) of inputting the intervention pattern into the machine learning model generated in the fourth step (S905) to obtain an output, which is the inference result of the machine learning model, for each subject, and a sixth step (S908) of determining the best intervention pattern for each subject based on the output obtained in the fifth step (S906). (Appendix 2) The intervention patterns include those that do not include any intervention measures, as described in Appendix 1 (2021). (Appendix 3) The best intervention pattern for each subject is the program described in Appendix 1 or 2 (2021) that includes the intervention pattern that results in the greatest number of appointments for screening due to the intervention pattern. (Appendix 4) A program (2021) described in any of Appendices 1 to 3, which causes the processor (29) to execute a first step (S900) and a third step (S904) at a predetermined timing, thereby performing re-learning of a machine learning model for each intervention pattern using the teacher data generated in the third step (S904). (Appendix 5) A program (2021) described in any of Appendices 1 to 4, which generates training data for at least one of the health insurance organization to which the subject belongs and the subject's place of residence in a third step (S904), and generates a machine learning model for at least one of the health insurance organization to which the subject belongs and the subject's place of residence in a fourth step (S905). (Appendix 6) A program (2021) described in any of Appendices 1 to 5, which classifies subjects into multiple groups based on the characteristics of the subjects included in the screening recommendation history data in a third step (S904), generates teacher data for each of the groups, and in a fourth step (S905), generates a machine learning model for each group. (Appendix 7) The program (2021), further comprising causing the processor (29) to execute a seventh step of encouraging the subject to undergo a medical examination based on the best intervention pattern determined in the sixth step (S908), is a program (2021) described in any of Appendices 1 to 6. (Appendix 8) The program (2021) described in Appendix 7, in which in the seventh step, the recommendation to undergo medical examination is carried out by mailing the subject a mail piece displaying a barcode including a link containing identification information for each subject, or by sending a message including a link containing identification information to a mobile device owned by the subject. (Appendix 9) The program (2021) further causes the processor (29) to execute an eighth step of obtaining whether or not the subject has accessed the link based on the link using the identification information, and in the first step (S900), includes whether or not the subject has accessed the link as checkup recommendation history data. The program (2021) described in Appendix 8. (Appendix 10) The information processing device includes a processor (29), and the processor (29) performs a first step (S900) of acquiring medical examination recommendation history data including at least personal information of a subject who is recommended to undergo a medical examination, past medical examination results of the subject, and results of medical examination recommendation for the subject; a second step (S902) of generating at least one intervention pattern including at least one intervention measure that is a means of recommending the subject to undergo a medical examination; and a second step (S902) of searching, for each intervention pattern, teacher data in which the intervention pattern generated in the second step (S902) is input and the results of the medical examination recommendation are output. An information processing device that executes a third step (S904) of generating a machine learning model for each intervention pattern from medical recommendation history data, a fourth step (S905) of generating a machine learning model for each intervention pattern using the training data generated in the third step (S904), a fifth step (S906) of inputting the intervention pattern into the machine learning model generated in the fourth step (S905) to obtain an output, which is an inference result of the machine learning model, for each subject, and a sixth step (S908) of determining the best intervention pattern for each subject based on the output obtained in the fifth step (S906). (Appendix 11) The method is executed by a computer (20) having a processor (29), the processor (29) includes a first step (S900) of acquiring medical examination recommendation history data including at least personal information of a subject who is recommended to undergo a medical examination, past medical examination results of the subject, and results of medical examination recommendation to the subject; a second step (S902) of generating at least one intervention pattern including at least one intervention measure that is a means of recommending the subject to undergo a medical examination; and teacher data in which the intervention pattern generated in the second step (S902) is input and the results of the medical examination recommendation are output. A method comprising: a third step (S904) of generating an intervention pattern for each intervention pattern from checkup recommendation history data; a fourth step (S905) of generating a machine learning model for each intervention pattern using the training data generated in the third step (S904); a fifth step (S906) of inputting the intervention pattern into the machine learning model generated in the fourth step (S905) to obtain an output, which is the inference result of the machine learning model, for each subject; and a sixth step (S908) of determining the best intervention pattern for each subject based on the output obtained in the fifth step (S906). (Appendix 12) The system comprises: a means (2033) for acquiring screening recommendation history data including at least personal information of a subject who is recommended to undergo a screening, past screening results of the subject, and results of screening recommendations for the subject; a means (2035) for generating at least one intervention pattern including at least one intervention measure which is a means for recommending the subject to undergo a screening; a means (2036) for generating teacher data for each intervention pattern from the screening recommendation history data, the teacher data being an input of the intervention pattern generated by the means for generating intervention pattern (2035) and an output of the recommendation to undergo a screening, a means (2036) for generating a machine learning model for each intervention pattern using the teacher data generated by the means for generating teacher data (2036); a means (2037) for acquiring an output, which is an inference result of the machine learning model, for each subject by inputting the intervention pattern into the machine learning model generated by the means for generating a machine learning model (2036); and a means (2038) for determining the best intervention pattern for each subject based on the output acquired by the means for acquiring output (2037). [Explanation of symbols]

[0118] 1...System for considering medical examination recommendation means 10...Terminal device 20...Server 25...Memory 26...Storage 29...Processor 30...External data server 202...Storage unit 203...Control unit 2021...Application program 2022...Medical examination recommendation history DB 2023...Intervention measure DB 2024...Intervention pattern DB 2025...Individual improvement rate DB 2026...Determined intervention pattern DB 2027...Teacher data 2028...Learning model 2031...Reception control module 2032...Transmission control module 2033...Medical examination recommendation history acquisition module 2034...Intervention measure selection module 2035...Intervention pattern generation module 2036...Learning model generation module 2037...Individual improvement rate calculation module 2038...Intervention pattern determination module 2039...Medical examination recommendation implementation module

Claims

1. A program for operating a computer having a processor, The program causes the processor to: A first step of acquiring screening recommendation history data including at least personal information of a subject who is recommended to undergo a screening, past screening results of the subject, and results of the screening recommendation for the subject; A second step of generating at least one intervention pattern including at least one intervention measure that is a means for recommending the medical examination; A third step of generating teacher data from the medical examination recommendation history data for each intervention pattern, the teacher data being an input of the intervention pattern generated in the second step and an output of the result of the medical examination recommendation; A fourth step of generating a machine learning model for each intervention pattern using the teacher data generated in the third step; A fifth step of inputting the intervention pattern into the machine learning model generated in the fourth step to obtain the output, which is an inference result of the machine learning model, for each subject; A sixth step of determining the best intervention pattern for each subject based on the output obtained in the fifth step; A program to execute.

2. The program according to claim 1 , wherein the intervention patterns include those that do not include the intervention measure.

3. The program according to claim 1 , wherein the best intervention pattern for each subject includes the intervention pattern with the greatest number of appointments for the medical examination according to the intervention pattern.

4. The program according to claim 1, wherein the program causes the processor to execute the first step and the third step at a predetermined timing, thereby performing re-learning of the machine learning model for each intervention pattern using the teacher data generated in the third step.

5. In the third step, the teacher data is generated for at least one of a health insurance group to which the subject belongs and a place of residence of the subject; In the fourth step, the machine learning model is generated for at least one of the health insurance group to which the subject belongs and the place of residence of the subject. The program according to claim 1.

6. In the third step, the subjects are classified into a plurality of groups based on the characteristics of the subjects included in the medical examination recommendation history data, and the teacher data is generated for each of the groups; In the fourth step, the machine learning model is generated for each of the groups. The program according to claim 1.

7. The program further causes the processor to The program according to claim 1 , further comprising a seventh step of encouraging the subject to undergo the medical examination based on the optimal intervention pattern determined in the sixth step.

8. In the seventh step, the recommendation to receive medical treatment is implemented by mailing to the subject a mail piece on which a barcode including a link including the identification information for each of the subjects is displayed, or by sending a message including a link including the identification information to a mobile device owned by the subject. The program according to claim 7.

9. The program further causes the processor to An eighth step of acquiring whether or not the target person has accessed the link using the identification information; In the first step, the medical examination recommendation history data includes the presence or absence of the access by the subject. The program according to claim 8.

10. An information processing device including a processor, The processor, A first step of acquiring screening recommendation history data including at least personal information of a subject who is recommended to undergo a screening, past screening results of the subject, and results of the screening recommendation for the subject; A second step of generating at least one intervention pattern including at least one intervention measure that is a means for recommending the medical examination; A third step of generating teacher data from the medical examination recommendation history data for each intervention pattern, the teacher data being an input of the intervention pattern generated in the second step and an output of the result of the medical examination recommendation; A fourth step of generating a machine learning model for each intervention pattern using the teacher data generated in the third step; A fifth step of inputting the intervention pattern into the machine learning model generated in the fourth step to obtain the output, which is an inference result of the machine learning model, for each subject; A sixth step of determining the best intervention pattern for each subject based on the output obtained in the fifth step; An information processing device that executes the above.

11. 1. A method implemented by a computer having a processor, comprising: The processor, A first step of acquiring screening recommendation history data including at least personal information of a subject who is recommended to undergo a screening, past screening results of the subject, and results of the screening recommendation for the subject; A second step of generating at least one intervention pattern including at least one intervention measure that is a means for recommending the medical examination; A third step of generating teacher data from the medical examination recommendation history data for each intervention pattern, the teacher data being an input of the intervention pattern generated in the second step and an output of the result of the medical examination recommendation; A fourth step of generating a machine learning model for each intervention pattern using the teacher data generated in the third step; A fifth step of inputting the intervention pattern into the machine learning model generated in the fourth step to obtain the output, which is an inference result of the machine learning model, for each subject; A sixth step of determining the best intervention pattern for each subject based on the output obtained in the fifth step; A method for performing.

12. A means for acquiring medical examination recommendation history data including at least personal information of a subject who is recommended to undergo a medical examination, past medical examination results of the subject, and results of the recommendation to undergo the medical examination for the subject; A means for generating at least one intervention pattern including at least one intervention measure which is a means for recommending the medical examination; a means for generating teacher data from the medical examination recommendation history data for each intervention pattern, the teacher data being an input of the intervention pattern generated by the means for generating the intervention pattern and an output of the result of the medical examination recommendation; A means for generating a machine learning model for each of the intervention patterns using the teacher data generated by the means for generating teacher data; a means for inputting the intervention pattern into the machine learning model generated by the means for generating the machine learning model, and acquiring the output, which is an inference result of the machine learning model, for each subject; A means for determining the best intervention pattern for each of the subjects based on the output acquired by the means for acquiring the output; A system comprising:

Citation Information

Patent Citations

  • Document creation device, method and program

    JP2020086858A

  • Recommendation notification optimal timing calculation method and recommendation notification optimal timing calculation system

    JP2021157307A

  • Recommendation notification optimal timing calculation method and recommendation notification optimal timing calculation system

    JP2021157778A

Cited By

  • Evaluation and proposal system for measures to increase the participation rate of specific health checkups

    JP7812061B1