Information processing apparatus, information processing system, information processing method, control program, generation apparatus, and generation method

An information processing system uses a trained model to analyze glucose metabolism indices and background information to provide personalized recommendations for preventing or improving postprandial hyperglycemia, addressing the inefficiencies of existing detection methods and reducing disease risks.

JP2024167628APending Publication Date: 2024-12-04SUNTORY HLDG LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2023083838
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-22
Publication Date
2024-12-04

AI Technical Summary

Technical Problem

Existing methods for detecting and managing postprandial hyperglycemia in healthy individuals are burdensome and lack accuracy, making it difficult to effectively prevent or manage this condition, which is a risk factor for diseases like diabetes and dementia.

Method used

An information processing system that utilizes a trained model to analyze glucose metabolism indices and background information to provide personalized recommendations for preventing, improving, or halting the progression of postprandial hyperglycemia, including dietary and exercise suggestions based on individual characteristics.

Benefits of technology

The system accurately suggests measures to prevent or improve postprandial hyperglycemia, reducing the risk of associated diseases by providing tailored advice based on individual glucose metabolism and background information, enhancing health management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024167628000001_ABST
    Figure 2024167628000001_ABST
Patent Text Reader

Abstract

To provide an information processing apparatus, information processing system, information processing method, control program, generation apparatus, and generation method capable of more accurately proposing prevention, improvement, and / or progression inhibition of postprandial hyperglycemia to a subject.SOLUTION: An information processing apparatus comprises: a storage unit that stores a learned model learned so as to output information related to the prevention, improvement, and / or progression inhibition of postprandial hyperglycemia of a subject when information on a glucose metabolism indicator of the subject and background information of the subject are input; an acquisition unit that acquires the information on the glucose metabolism indicator of the subject and the background information of the subject; a specification unit that inputs the acquired information on the glucose metabolism indicator of the subject and the background information of the subject to the learned model to specify information related to the prevention, improvement, and / or progression inhibition of postprandial hyperglycemia of the subject; and an output unit that outputs the specified information.SELECTED DRAWING: Figure 6
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

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

[0002] Even healthy people who are not diabetic patients may have symptoms of postprandial hyperglycemia. Postprandial hyperglycemia is a concept proposed in the "Guidelines for the Management of Postprandial Hyperglycemia" (International Diabetes Federation (IDF)). It is difficult to detect postprandial hyperglycemia in a general health check (fasting blood sampling), and in order to detect postprandial hyperglycemia, an oral glucose tolerance test (OGTT), which involves physical burdens and risks, must be performed. A healthy person who is not a diabetic patient is one whose fasting blood glucose level and HbA1c are normal, high normal, or borderline, and whose blood glucose level 120 minutes after glucose loading in an oral glucose tolerance test (OGTT) is less than 200 mg / dl. The oral glucose tolerance test (OGTT) is a test in which a subject takes a sugar solution containing 75 g of glucose under fasting conditions without breakfast, and then blood is sampled at multiple time points and the blood glucose level of the sampled blood is measured to measure the time change in blood glucose level.

[0003] Since postprandial hyperglycemia is a risk factor for the development of diseases such as diabetes and dementia, it is desirable to take appropriate measures against postprandial hyperglycemia.

[0004] Non-Patent Document 1 discloses a technique for outputting messages of support, encouragement, praise, and caution when measurement data of weight, blood pressure, and number of steps (activity amount) and self-evaluation of behavior such as diet are input.

[0005] Non-Patent Document 2 discloses a method in which lifestyle improvements that are thought to be effective in improving postprandial blood glucose levels are recorded in a record sheet, and blood glucose levels are measured and recorded in the record sheet. [Prior art documents] [Non-patent literature]

[0006] [Non-Patent Document 1] "Research on developing logic for the 'Seven Lucky Gods App' according to the target based on IoT information" (Aichi Health Forest Health Science Center, Japan Agency for Medical Research and Development, FY2019 IoT-based Behavior Change Research Project Results Reporting Session) [Non-Patent Document 2] "An example of how a flash glucose monitoring (FGM) program was effective in managing blood glucose levels in busy employees: How to utilize the FGM program in a health management office" (Sanin Hygiene Journal 2021; 63(6): 304-309) Summary of the Invention [Problem to be solved by the invention]

[0007] There is a demand for more accurate suggestions to subjects on how to prevent, improve, and / or prevent the progression of postprandial hyperglycemia.

[0008] The purpose of the information processing device, information processing system, information processing method, control program, generation device and generation method is to make it possible to more accurately suggest to a subject ways to prevent, improve and / or prevent the progression of postprandial hyperglycemia. [Means for solving the problem]

[0009] The information processing device of the embodiment has a memory unit that stores a trained model trained to output information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject when information regarding the glucose metabolism index of the subject and background information of the subject are input, an acquisition unit that acquires information regarding the glucose metabolism index of the subject and the background information of the subject, an identification unit that identifies information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the acquired information regarding the glucose metabolism index of the subject and the subject's background information into the trained model, and an output unit that outputs the identified information.

[0010] In the information processing device of the embodiment, information regarding the glucose metabolism index of the subject includes measurement values ​​of the subject's HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR (Time in Range), or a postprandial hyperglycemia type estimated based on the measurement values.

[0011] In the information processing device according to the embodiment, the postprandial hyperglycemia type includes whether or not the type is one in which postprandial blood glucose level is likely to rise and / or whether or not the type is one in which postprandial blood glucose level is unlikely to fall.

[0012] In the information processing device according to the embodiment, the background information of the subject includes any one of the subject's sex, age, BMI, eating habits, exercise habits, and health checkup values.

[0013] In the information processing device of the embodiment, the trained model is trained to further output risk information regarding disease development when information regarding the subject's glucose metabolism index and background information regarding the subject are input, and the identification unit identifies the subject's risk information regarding disease development by inputting the acquired information regarding the subject's glucose metabolism index and the subject's background information into the trained model, and the output unit further outputs the risk information identified by the identification unit.

[0014] In the information processing device of the embodiment, information regarding the prevention, improvement and / or prevention of progression of a subject's postprandial hyperglycemia includes a method for selecting a food for specified health use or a food with functional claims, setting a target intake amount of nutritional components derived from food, setting a target amount of exercise, or setting a target amount of sleep.

[0015] The information processing device according to the embodiment further includes an implementation record information acquisition unit that acquires implementation record information for the prevention, improvement and / or progression prevention of postprandial hyperglycemia implemented in accordance with the identified information, and a judgment unit that judges whether the implementation record information satisfies a predetermined condition with respect to the identified information and outputs the judgment result.

[0016] The information processing system of the embodiment has a memory unit that stores a trained model trained to output information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject when information regarding the glucose metabolism index of the subject and background information of the subject are input, an acquisition unit that acquires information regarding the glucose metabolism index of the subject and the background information of the subject, an identification unit that identifies information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the acquired information regarding the glucose metabolism index of the subject and the subject's background information into the trained model, and an output unit that outputs the identified information.

[0017] The information processing device of the embodiment has an acquisition unit that acquires information regarding the glucose metabolism index of the subject and background information of the subject, an identification unit that identifies information regarding the prevention, improvement and / or prevention of progression of the subject by inputting the acquired information regarding the glucose metabolism index of the subject and the background information of the subject into a trained model that is trained to output information regarding the prevention, improvement and / or prevention of progression of the subject's postprandial hyperglycemia when the information regarding the glucose metabolism index of the subject and the background information of the subject are input, and an output unit that outputs the identified information.

[0018] The information processing method of the embodiment acquires information regarding a subject's glucose metabolism index and background information of the subject, and inputs the acquired information regarding the subject's glucose metabolism index and the subject's background information into a trained model that has been trained to output information regarding the prevention, improvement and / or prevention of progression of the subject's postprandial hyperglycemia when the information regarding the subject's glucose metabolism index and the subject's background information are input, thereby identifying information regarding the prevention, improvement and / or prevention of progression of the subject's postprandial hyperglycemia, and outputting the identified information from an output unit.

[0019] The control program of the embodiment is a control program for a computer having an output unit, which acquires information regarding a subject's glucose metabolism index and background information of the subject, and inputs the acquired information regarding the subject's glucose metabolism index and the subject's background information into a trained model trained to output information regarding the prevention, improvement and / or prevention of progression of the subject's postprandial hyperglycemia when the information regarding the subject's glucose metabolism index and the subject's background information are input, thereby causing the computer to identify information regarding the prevention, improvement and / or prevention of progression of the subject's postprandial hyperglycemia, and output the identified information from the output unit.

[0020] The generating device according to the embodiment has an acquisition unit that acquires implementation record information of the prevention, improvement and / or prevention of progression of postprandial hyperglycemia carried out by a subject corresponding to information on a specified glucose metabolism index and background information, and effect information based on the implementation record information, and a generation unit that uses the information on the glucose metabolism index, the background information, the implementation record information and the effect information as teacher data to generate a trained model that can output information regarding effective prevention, improvement and / or prevention of progression of postprandial hyperglycemia when information on the glucose metabolism index and the background information are input.

[0021] The generation method of the embodiment acquires implementation record information of the prevention, improvement and / or prevention of progression of postprandial hyperglycemia carried out by a subject corresponding to information on a specified glucose metabolism index and background information, and effect information based on the implementation record information, and generates a trained model that can output information regarding effective prevention, improvement and / or prevention of progression of postprandial hyperglycemia when information on the glucose metabolism index and background information are input, using the information on the glucose metabolism index, background information, implementation record information and effect information as training data.

[0022] The control program of the embodiment causes a computer to acquire implementation record information of the prevention, improvement and / or prevention of progression of postprandial hyperglycemia carried out by a subject corresponding to information on a specified glucose metabolism index and background information, and effect information based on the implementation record information, and to generate a trained model that can output information regarding effective prevention, improvement and / or prevention of progression of postprandial hyperglycemia when information on the glucose metabolism index and background information are input, using the information on the glucose metabolism index, background information, implementation record information and effect information as training data.

[0023] The information processing device of the embodiment has a memory unit that stores a trained model trained to output information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject when information regarding the glucose metabolism index of the subject and background information of the subject are input, a first acquisition unit that acquires information regarding the glucose metabolism index of the subject and the background information of the subject, an identification unit that identifies information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the acquired information regarding the glucose metabolism index of the subject and the background information of the subject into the trained model, a second acquisition unit that acquires implementation record information of the prevention, improvement and / or prevention of progression of postprandial hyperglycemia implemented in accordance with the identified information and effect information based on the implementation record information, and a re-learning unit that re-learns the trained model using the implementation record information and the effect information.

[0024] The information processing system of the embodiment has a memory unit that stores a trained model that has been trained to output information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject when information regarding the glucose metabolism index of the subject and background information of the subject are input, a first acquisition unit that acquires information regarding the glucose metabolism index of the subject and the background information of the subject, an identification unit that identifies information regarding the prevention, improvement and / or prevention of progression of the subject by inputting the acquired information regarding the glucose metabolism index of the subject and the background information of the subject into the trained model, a second acquisition unit that acquires implementation record information of the prevention, improvement and / or prevention of progression of postprandial hyperglycemia implemented in accordance with the identified information and effect information based on the implementation record information, and a re-learning unit that re-learns the trained model using the implementation record information and the effect information.

[0025] In an information processing method according to an embodiment, a trained model is stored in a memory unit, the trained model being trained to output information relating to the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject when information relating to the subject's glucose metabolic index and background information of the subject are input, information relating to the subject's glucose metabolic index and background information of the subject are acquired, and the acquired information relating to the subject's glucose metabolic index and background information of the subject are input into the trained model to identify information relating to the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject, and implementation record information and effect information based on the implementation record information when prevention, improvement and / or prevention of progression of postprandial hyperglycemia is implemented in accordance with the identified information are acquired, and the trained model is re-trained using the implementation record information and effect information.

[0026] A control program according to an embodiment is a control program for a computer having a memory unit, which causes the computer to execute the following steps: store in the memory a trained model trained to output information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject when information regarding the glucose metabolic index of a subject and background information of the subject are input; acquire information regarding the glucose metabolic index of the subject and background information of the subject; input the acquired information regarding the glucose metabolic index of the subject and background information of the subject into the trained model to identify information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject; acquire implementation record information when prevention, improvement and / or prevention of progression of postprandial hyperglycemia is implemented in accordance with the identified information, and effect information based on the implementation record information; and re-train the trained model using the implementation record information and effect information. Effect of the Invention

[0027] The information processing device, information processing system, information processing method, control program, generation device, and generation method can more accurately suggest to a subject how to prevent, improve, and / or prevent the progression of postprandial hyperglycemia. [Brief description of the drawings]

[0028] [Figure 1] 1 is a diagram showing a schematic configuration of an information processing system 1 according to an embodiment. [Diagram 2] 1 is a diagram illustrating a schematic configuration of a terminal device 100. [Diagram 3] 2 is a schematic diagram showing an example of the data structure of a management table 112. FIG. [Figure 4] FIG. 2 is a diagram illustrating a schematic configuration of a server device 200. [Diagram 5] 13 is a flowchart showing an example of an operation of a learning process. [Figure 6] 13 is a flowchart illustrating an example of an operation of a specification process. [Figure 7] 13 is a flowchart showing an example of the operation of a support process. [Figure 8] 13 is a flowchart illustrating an example of an operation of an update process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] Hereinafter, an information processing device, an information processing system, an information processing method, a control program, a generating device, and a generating method according to one aspect of the embodiment will be described with reference to the drawings. However, it should be noted that the technical scope of the present invention is not limited to the embodiment, but extends to the invention described in the claims and their equivalents.

[0030] FIG. 1 is a diagram showing a schematic configuration of an information processing system 1 according to an embodiment.

[0031] As shown in Fig. 1, the information processing system 1 includes one or more terminal devices 100 and a server device 200. The terminal devices 100 and the server device 200 are connected to each other via a network N so as to be able to communicate with each other. Furthermore, the terminal devices 100 and the server devices 200 are connected to a diagnosis result registration device A1, a measurement device A2, and / or an information input device A3, etc., via the network N so as to be able to communicate with each other. The network N is a wired network such as the Internet or an intranet. The network N may be a wireless network such as a wireless LAN (Local Area Network).

[0032] The information processing system 1 is used for managing the health of subjects by an administrator different from the subjects. In particular, the information processing system 1 is used for the purpose of promoting health management. For example, the administrator is a company or a health insurance association, and the subjects are employees of the company. Alternatively, the administrator is an insurance company, and the subjects are insured persons. Alternatively, the administrator is a local government, a railway company, or a real estate company (urban development worker), and the subjects are residents who live along the local government, railway line, or in an area developed by the real estate company (urban development worker).

[0033] The diagnostic result registration device A1 is a device into which glucose metabolism index information, background information and / or onset information of each subject is input and registered after a general health checkup of one or more subjects is performed. The glucose metabolism index information is an example of information related to the glucose metabolism index of the subject. The glucose metabolism index information registered in the diagnostic result registration device A1 includes HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level, or TIR (Time in Range) measurement value, which are diagnostic results in the general health checkup of each subject. The background information includes any one of the subject's gender, age, BMI, eating habits, exercise habits, or health checkup value. The health checkup values ​​are diagnostic values ​​measured in a general health checkup, such as height, weight, vision, hearing, urinary protein, urinary sugar, GOT, GPT, γ-GTP, HDL cholesterol, LDL cholesterol, total cholesterol, triglyceride, white blood cells, red blood cells, hemoglobin, hematocrit value, blood pressure, heart rate waveform, chest X-ray values ​​or images, etc. The onset information indicates whether or not the subject has developed a disease such as diabetes, obesity, dementia, myocardial infarction, dyslipidemia, etc. within a predetermined period (e.g., 5 years), and / or the period until the subject develops a disease.

[0034] The measuring device A2 is a device that measures glucose metabolism indexes of one or more subjects in real time and / or continuously, inputs background information and / or onset information of each subject, and stores the glucose metabolism index information, background information, and / or onset information of each subject. The measuring device A2 is, for example, FreeStyle Libre manufactured by Abbott. The glucose metabolism index information stored in the measuring device A2 includes measurement results of glucose metabolism indexes of each subject, such as HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level, or TIR measurement value.

[0035] The information input device A3 is a device to which any investigation result, background information and / or onset information of one or more subjects based on a questionnaire or the like regarding the glucose metabolism index is input, and the glucose metabolism index information, background information and / or onset information of each subject is registered. The information input device A3 specifies the investigation result based on a questionnaire input using, for example, an operation device (not shown). The information input device A3 may identify the investigation result by recognizing characters from an image of the questionnaire captured by an imaging device (not shown) using OCR (Optical character recognition) technology. The glucose metabolism index information registered in the information input device A3 includes postprandial hyperglycemia type, which is an investigation result regarding the glucose metabolism index of each subject. The postprandial hyperglycemia type is information for specifying a classification of postprandial hyperglycemia, and is a category or class of the state of postprandial hyperglycemia. The postprandial hyperglycemia type includes whether or not the type is one in which postprandial blood glucose level is likely to increase and / or whether or not the type is one in which postprandial blood glucose level is unlikely to decrease.

[0036] FIG. 2 is a diagram showing a schematic configuration of the terminal device 100. As shown in FIG.

[0037] The terminal device 100 is an example of an information processing device and a generating device. The terminal device 100 is an information processing device such as a personal computer, a notebook PC, a tablet PC, a multi-function mobile phone (a so-called smartphone), etc. The terminal device 100 includes an input device 101, a display device 102, a first communication device 103, a first storage device 110, and a first processing device 120, etc. The input device 101, the display device 102, the first communication device 103, the first storage device 110, and the first processing device 120 are connected to each other via a CPU (Central Processing Unit) bus or the like.

[0038] The input device 101 has an input device such as a touch panel type input device, a keyboard, or a mouse, and an interface circuit for acquiring signals from the input device, and outputs an operation signal in response to an input operation by a user.

[0039] The display device 102 is an example of an output unit. The display device 102 has a display including a liquid crystal display, an organic EL (Electro-Luminescence) display, or the like, and an interface circuit that outputs image data to the display, and displays the image data on the display.

[0040] The first communication device 103 is an example of an output unit. The first communication device 103 has a wired communication interface circuit according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol). The first communication device 103 is communicatively connected to the network N according to a communication standard such as Ethernet (registered trademark). The first communication device 103 sends data received from the server device 200, the diagnosis result registration device A1, the measurement device A2, and / or the information input device A3, etc., via the network N to the first processing device 120. The first communication device 103 also transmits data received from the first processing device 120 to the server device 200, the diagnosis result registration device A1, the measurement device A2, and / or the information input device A3, etc., via the network N. The first communication device 103 may have an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit according to a communication protocol such as wireless LAN, and may be communicatively connected to the network N according to a communication standard such as wireless LAN.

[0041] The first storage device 110 is an example of a storage unit. The first storage device 110 has a memory device such as a RAM (Random Access Memory) or a ROM (Read Only Memory), a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk or an optical disk. The first storage device 110 also stores computer programs, databases, tables, and the like used for various processes of the terminal device 100. The computer programs may be installed in the first storage device 110 from a computer-readable portable recording medium using a known setup program or the like. The portable recording medium is, for example, a CD-ROM (compact disc read only memory), a DVD-ROM (digital versatile disc read only memory), or the like. The computer programs may be stored in a recording medium possessed by a specific server and installed via a network N.

[0042] The first storage device 110 stores a trained model 111, a management table 112, and the like as data. The trained model 111 is a model for identifying information relating to the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of a subject. The trained model 111 is generated by the first processing device 120 or the server device 200. The management table 112 stores information about each subject for one or more subjects. Details of the management table 112 will be described later.

[0043] The first processing device 120 operates based on a program stored in advance in the first storage device 110. The first processing device 120 is, for example, a CPU. As the first processing device 120, a DSP (digital signal processor), an LSI (large scale integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or the like may be used. The first processing device 120 is connected to the input device 101, the display device 102, the first communication device 103, the first storage device 110, and the like, and controls each device. The first processing device 120 generates a trained model 111, and uses the generated trained model 111 to identify information related to the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject.

[0044] The first processing device 120 reads a computer program stored in the first storage device 110 and operates according to the read computer program. As a result, the first processing device 120 functions as a first teacher data acquisition unit 121, a generation unit 122, a subject information acquisition unit 123, an identification unit 124, an output control unit 125, a performance record information acquisition unit 126, a judgment unit 127, a support unit 128, a second teacher data acquisition unit 129, and a re-learning unit 130. The first teacher data acquisition unit 121 is an example of an acquisition unit. The subject information acquisition unit 123 is an example of an acquisition unit and a first acquisition unit. The second teacher data acquisition unit 129 is an example of a second acquisition unit.

[0045] FIG. 3 is a schematic diagram showing an example of the data structure of the management table 112. As shown in FIG.

[0046] In the management table 112, the identification number (subject ID), glucose metabolism index information, background information, proposal information, implementation record information, effect information, onset information, etc. of each subject are stored in association with each other for one or more subjects.

[0047] The first teacher data acquiring unit 121 receives a registration request signal specifying the subject ID, glucose metabolism index information, background information and / or onset information of each subject from the diagnosis result registration device A1 or the measurement device A2 via the first communication device 103. The first teacher data acquiring unit 121 associates the subject ID, glucose metabolism index information, background information and / or onset information specified in the received registration request signal and stores them in the first storage device 110. The first teacher data acquiring unit 121 may estimate the postprandial hyperglycemia type based on the diagnosis result or measurement result (HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR measurement value) included in the glucose metabolism index information specified in the registration request signal. For example, a relational expression or a table showing the correspondence between the measurement values ​​of HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR and the postprandial hyperglycemia type is set in advance by the administrator and stored in the first storage device 110. The first teacher data acquisition unit 121 refers to the relational expression or table stored in the first storage device 110 and identifies the postprandial hyperglycemia type corresponding to the diagnosis result or measurement result included in the glucose metabolism index information specified by the registration request signal.

[0048] Alternatively, the first teacher data acquisition unit 121 may identify the postprandial hyperglycemia type by a trained model that has been trained in advance to output the postprandial hyperglycemia type when the fasting blood glucose level, the postprandial blood glucose level, the post-glucose load blood glucose level, the average blood glucose level, the maximum blood glucose level, or the TIR measurement value is input. This trained model is trained in advance using a plurality of sets of each measurement value and the postprandial hyperglycemia type corresponding to each measurement value by supervised learning such as a neural network or a support vector machine, and is stored in advance in the first storage device 110. The first teacher data acquisition unit 121 inputs the diagnosis result or the measurement result included in the glucose metabolism index information specified by the registration request signal into the trained model, and acquires the postprandial hyperglycemia type output from the trained model to identify the postprandial hyperglycemia type.

[0049] Alternatively, the first teacher data acquiring unit 121 receives a registration request signal specifying the subject ID, glucose metabolism index information, background information and / or onset information of each subject from the information input device A3 via the first communication device 103. The first teacher data acquiring unit 121 associates the subject ID, glucose metabolism index information, background information and / or onset information specified in the received registration request signal and stores them in the first storage device 110.

[0050] The subject ID may not be specified by the registration request signal, but may be newly generated by the first teacher data acquiring unit 121 when the first teacher data acquiring unit 121 receives the registration request signal.

[0051] The proposed information indicates the proposed contents of prevention, improvement and / or prevention of progression of postprandial hyperglycemia proposed to each subject based on each glucose metabolism index information and background information. The proposed contents are, for example, the nutritional components derived from specified health foods, functional foods or meals that each subject should take in a predetermined period (for example, one week) and the intake amount thereof, the type of exercise that each subject should perform and the amount of exercise, and / or the sleep time that each subject should take. The nutritional components derived from meals include carbohydrates, proteins, lipids, dietary fiber, etc. The types of exercise include aerobic exercise such as walking and jogging, or resistance exercise such as squats, abdominal push-ups, back exercises, and heel raises. The amount of exercise includes the number of times, time, number of steps, etc. The proposed information is identified by the identification unit 124 in the identification process described later and set in the management table.

[0052] The implementation record information is an example of information regarding the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of a subject. The implementation record information indicates an implementation record of the prevention, improvement and / or prevention of progression of postprandial hyperglycemia implemented by each subject based on the proposal information. The implementation record is, for example, the specific health food, functional food or nutritional components derived from meals taken by each subject during a specified period and the amount of intake thereof, the type of exercise performed by each subject and the amount of exercise, and / or the sleep time taken by each subject. The implementation record information is identified by the implementation record information acquisition unit 126 in the support process described later and set in the management table.

[0053] The effect information indicates the degree of the improvement effect of postprandial hyperglycemia when each subject performs the prevention, improvement and / or progression prevention of postprandial hyperglycemia as shown in the implementation record information. For example, a relational expression or a table indicating the correspondence between the degree of change of HbA1c, fasting blood glucose level, postprandial blood glucose level, glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR and the degree of the improvement effect of postprandial hyperglycemia is set in advance by the administrator and stored in the first storage device 110. The first teacher data acquisition unit 121 calculates the difference or ratio of the average value of HbA1c, fasting blood glucose level, postprandial blood glucose level, glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR before and after the prevention, improvement and / or progression prevention of postprandial hyperglycemia is performed as the degree of change. The first teacher data acquisition unit 121 refers to the relational expression or the table stored in the first storage device 110, specifies the degree of the improvement effect corresponding to the calculated degree of change, and stores it in the management table.

[0054] In addition, the first teacher data acquisition unit 121 may acquire the subject ID, glucose metabolism index information, background information, proposal information, implementation record information, effect information and / or onset information of each subject specified by the user using the input device 101 or an information processing device not shown by receiving it from the input device 101 or the first communication device 103, and store it in a management table.

[0055] FIG. 4 is a diagram showing a schematic configuration of the server device 200. As shown in FIG.

[0056] The server device 200 is an example of a generating device. The server device 200 includes a second communication device 201, a second storage device 210, and a second processing device 220. The second communication device 201, the second storage device 210, and the second processing device 220 are connected to each other via a CPU bus or the like.

[0057] The second communication device 201 has a wired communication interface circuit according to a communication protocol such as TCP / IP. The second communication device 201 is communicatively connected to the network N according to a communication standard such as Ethernet (registered trademark). The second communication device 201 sends data received from the terminal device 100, the diagnosis result registration device A1, the measurement device A2, and / or the information input device A3, etc., via the network N to the second processing device 220. The second communication device 201 transmits data received from the second processing device 220 to the terminal device 100, the diagnosis result registration device A1, the measurement device A2, and / or the information input device A3, etc., via the network N. The second communication device 201 may have an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit according to a communication protocol such as wireless LAN, and may be communicatively connected to the network N according to a communication standard such as wireless LAN.

[0058] The second storage device 210 includes a memory device such as a RAM or a ROM, a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk or an optical disk. The second storage device 210 also stores computer programs, databases, tables, and the like used for various processes of the server device 200. The computer programs may be installed in the second storage device 210 from a computer-readable portable recording medium such as a CD-ROM or a DVD-ROM using a known setup program or the like. The computer programs may be stored in a recording medium possessed by a specific server and installed via the network N.

[0059] The second processing device 220 operates based on a program stored in advance in the second storage device 210. The second processing device 220 is, for example, a CPU. A DSP, an LSI, an ASIC, an FPGA, or the like may be used as the second processing device 220. The second processing device 220 is connected to the second communication device 201, the second storage device 210, and the like, and controls each device.

[0060] FIG. 5 is a flowchart showing an example of the operation of the learning process of the terminal device 100.

[0061] An example of the operation of the learning process of the terminal device 100 will be described below with reference to the flowchart shown in Fig. 5. Note that the flow of the operation described below is executed mainly by the first processing device 120 in cooperation with each element of the terminal device 100 based on a program stored in advance in the first storage device 110.

[0062] First, the first teacher data acquisition unit 121 acquires teacher data for generating the trained model 111 (step S101). The teacher data includes glucose metabolism index information, background information, implementation record information, effect information, and / or onset information of one or more subjects. That is, the teacher data includes predetermined glucose metabolism index information and background information, implementation record information of prevention, improvement, and / or progression prevention of postprandial hyperglycemia performed by each subject corresponding to the glucose metabolism index information and background information, and effect information based on the implementation record information. This implementation record information is implementation record information when various prevention, improvement, and / or progression prevention of postprandial hyperglycemia are performed on various subjects having various postprandial hyperglycemia types and background information. The first teacher data acquisition unit 121 reads out the glucose metabolism index information, background information, implementation record information, effect information, and / or onset information of each subject from the management table and acquires them as teacher data.

[0063] Next, the generation unit 122 generates the trained model 111 using the teacher data acquired by the first teacher data acquisition unit 121, and stores it in the first storage device 110 (step S102), thereby completing the series of steps.

[0064] The trained model 111 is pre-trained by supervised learning such as a neural network and a support vector machine. The generation unit 122 trains the trained model 111 so as to output implementation record information and / or risk information of disease onset of the subject corresponding to effect information with a high degree of improvement effect when glucose metabolism index information and background information of the subject are input. That is, the generation unit 122 trains the trained model 111 so as to output implementation record information and / or risk information corresponding to effect information with a high degree of improvement effect when the measurement value and background information of the subject's HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level, or TIR are input. Alternatively, the generation unit 122 trains the trained model 111 so as to output implementation record information and / or risk information corresponding to effect information with a high degree of improvement effect when the postprandial hyperglycemia type of the subject is input. The risk information indicates the degree of likelihood that a subject will develop a disease such as diabetes, obesity, dementia, myocardial infarction, dyslipidemia, etc. within a specified period (e.g., five years) and / or the estimated period in which the subject will develop the disease.

[0065] In this way, the generation unit 122 generates the trained model 111 capable of outputting information relating to favorable prevention, improvement, and / or prevention of progression of postprandial hyperglycemia when glucose metabolism index information and background information are input. This allows the information processing system 1 to use the trained model 111 to easily and appropriately propose prevention, improvement, and / or prevention of progression according to the glucose metabolism index and background of each subject.

[0066] The trained model 111 is also trained to output disease onset risk information when glucose metabolism index information and background information are input. This allows the information processing system 1 to use the trained model 111 to easily and appropriately estimate the risk of each subject developing diseases such as diabetes, obesity, dementia, myocardial infarction, and dyslipidemia.

[0067] FIG. 6 is a flowchart showing an example of the operation of the identification process of the terminal device 100.

[0068] An example of the operation of the specific processing of the terminal device 100 will be described below with reference to the flowchart shown in Fig. 6. Note that the flow of the operation described below is executed mainly by the first processing device 120 in cooperation with each element of the terminal device 100 based on a program stored in advance in the first storage device 110.

[0069] First, the subject information acquiring unit 123 acquires glucose metabolism index information and background information of the subject and stores them in the management table (step S201). The subject information acquiring unit 123 acquires the subject ID, glucose metabolism index information, and background information of a new subject by receiving them from the diagnosis result registration device A1 or the measurement device A2 via the first communication device 103. In this case, the subject information acquiring unit 123, like the first teacher data acquiring unit 121, may estimate the postprandial hyperglycemia type based on the diagnosis result or measurement result (HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level, or TIR measurement value) included in the received glucose metabolism index information.

[0070] Alternatively, the subject information acquiring unit 123 acquires the subject ID, glucose metabolism index information, and background information of each subject by receiving them from the information input device A3 via the first communication device 103. Alternatively, the subject information acquiring unit 123 acquires the subject ID, glucose metabolism index information, and background information of a subject designated by a user using the input device 101 or an information processing device (not shown) by receiving them from the input device 101 or the first communication device 103. The subject information acquiring unit 123 stores the acquired subject ID, glucose metabolism index information, and background information in a management table in association with each other. Note that the subject information acquiring unit 123 may acquire onset information in addition to the glucose metabolism index information and background information and store it in the management table.

[0071] Next, the identification unit 124 inputs the glucose metabolism index information and background information of the subject acquired by the subject information acquisition unit 123 to the trained model 111, and acquires (identifies) the implementation record information and risk information output from the trained model 111. The identification unit 124 identifies (discriminates) the content of prevention, improvement and / or progression prevention of postprandial hyperglycemia indicated in the acquired implementation record information as the content of prevention, improvement and / or progression prevention of postprandial hyperglycemia that should be performed by the subject. In addition, the identification unit 124 identifies (discriminates) the degree or period indicated in the acquired risk information as the degree of possibility that the subject will develop a disease such as diabetes, obesity, dementia, myocardial infarction, dyslipidemia, etc. within a predetermined period, or the period during which the subject is estimated to develop a disease (step S202). The identification unit 124 stores the identified implementation record information as proposal information in the management table in association with the subject ID, glucose metabolism index information, and background information of the subject.

[0072] In this way, the identification unit 124 identifies (discriminates) information related to prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the glucose metabolism index information and background information of the subject acquired by the subject information acquisition unit 123 into the trained model 111. This allows the information processing system 1 to use the trained model 111 to simply and appropriately propose prevention, improvement, and / or prevention of progression according to the glucose metabolism index and background of each subject.

[0073] Furthermore, the identification unit 124 identifies risk information of disease onset of the subject by inputting the glucose metabolism index information and background information of the subject acquired by the subject information acquisition unit 123 into the trained model 111. In this way, the information processing system 1 can use the trained model 111 to easily and appropriately estimate the risk of each subject developing a disease such as diabetes, obesity, dementia, myocardial infarction, and dyslipidemia.

[0074] Next, the output control unit 125 outputs the implementation record information (proposal information) and risk information identified by the identification unit 124 by displaying them on the display device 102 or by transmitting them to another device via the first communication device 103 (step S203), and then ends the series of steps.

[0075] The output control unit 125 outputs the specified health food or functional food indicated in the identified implementation record information and its intake amount as a selection method of the subject for the specified health food or functional food. The output control unit 125 may output the specified health food or functional food indicated in the identified implementation record information as a measurement instruction for the subject's intake amount of the specified health food or functional food.

[0076] The output control unit 125 also outputs the dietary nutritional components and their intake amounts indicated in the identified implementation record information as a target setting for the subject's dietary nutritional component intake amount. The output control unit 125 may output the dietary nutritional components indicated in the identified implementation record information as a measurement instruction for the subject's dietary nutritional component intake amount.

[0077] The output control unit 125 outputs the type of exercise and the amount of exercise indicated in the identified implementation record information as a target setting for the amount of exercise of the subject. The output control unit 125 may output the type of exercise indicated in the identified implementation record information as an instruction to measure the amount of exercise of the subject.

[0078] The output control unit 125 also outputs the sleep time indicated in the identified implementation record information as a target setting for the subject's sleep time. The sleep time output as the target setting may be limited to a predetermined range, such as 6 hours or more and less than 8 hours per day. The output control unit 125 may output an instruction to measure the subject's sleep time.

[0079] As a result, the information processing system 1 can propose to each subject appropriate prevention, improvement and / or prevention of progression according to the glucose metabolic index and background of the subject.

[0080] FIG. 7 is a flowchart showing an example of the operation of the support process of the terminal device 100.

[0081] An example of the operation of the support process of the terminal device 100 will be described below with reference to the flowchart shown in Fig. 7. The flow of the operation described below is executed mainly by the first processing device 120 in cooperation with each element of the terminal device 100 based on a program stored in advance in the first storage device 110.

[0082] First, the implementation record information acquiring unit 126 acquires the proposed information output by the output control unit 125, i.e., the implementation record information of the prevention, improvement and / or progress prevention of postprandial hyperglycemia implemented according to the proposed information identified by the identifying unit 124 (step S301). The implementation record information acquiring unit 126 acquires the subject ID and the implementation record information designated by the subject using the input device 101 or an information processing device (not shown) by receiving them from the input device 101 or the first communication device 103. The information processing device is, for example, a multi-function mobile phone (so-called smartphone) owned by the subject. The implementation record information acquiring unit 126 stores the acquired implementation record information in association with the acquired subject ID registered in the management table.

[0083] The implementation record information acquisition unit 126 may receive the name of the meal menu specified by the subject using the input device 101 or the information processing device from the input device 101 or the first communication device 103, and identify the food for specified health use, food with functional claims, or nutritional components derived from the meal and / or their intake amount from the received name. In this case, a table showing the correspondence between the name of the meal menu and the food for specified health use, food with functional claims, or nutritional components derived from the meal and / or their intake amount is set in advance by the administrator and stored in the first storage device 110. The implementation record information acquisition unit 126 refers to the table stored in the first storage device 110 and identifies the food for specified health use, food with functional claims, or nutritional components derived from the meal and / or their intake amount corresponding to the name of the received meal menu.

[0084] The implementation record information acquisition unit 126 may also receive an image captured by the subject using an imaging device or information processing device (not shown) from the imaging device or the first communication device 103, and identify the specific health food, functional food, or nutritional components derived from the meal and / or their intake from the received image. In this case, the implementation record information acquisition unit 126 uses a known image processing technique to identify the food contained in the image or the nutritional components contained in the food and / or their intake. Alternatively, the implementation record information acquisition unit 126 may identify the specific health food, functional food, or nutritional components derived from the meal and / or their intake by a trained model that has been trained in advance to output the food contained in the input image or the nutritional components contained in the food and / or their intake when an image is input. This trained model is trained in advance using a plurality of sets of images containing a specific food and the food contained in the image or the nutritional components contained in the food and / or their intake by supervised learning such as a neural network or a support vector machine, and is stored in the first storage device 110 in advance. The first teacher data acquisition unit 121 inputs the received image into the trained model and acquires the food or the nutritional components and / or their intake amount contained in the food output from the trained model, thereby identifying the specified health food, functional food, or nutritional components and / or their intake amount derived from the diet.

[0085] The implementation record information acquiring unit 126 may also acquire the subject ID and implementation record information designated by the subject using the information input device A3 from the first communication device 103. In this case, the implementation record information acquiring unit 126 may receive an image of the survey form captured using the imaging device of the information input device A3, recognize characters using OCR technology, and identify the implementation record information.

[0086] The exercise record information acquiring unit 126 may also acquire the amount of exercise by receiving the number of steps measured using a pedometer (not shown).

[0087] Next, the judgment unit 127 judges whether the implementation record information acquired by the implementation record information acquisition unit 126 satisfies a judgment condition that is predetermined for the proposed information output in step S203 of FIG. 6 (step S302). The judgment condition is an example of a predetermined condition. For example, the judgment condition is set to that the intake amount of each food indicated in the acquired implementation record information is equal to or greater than the intake amount of each food indicated in the proposed information output to the subject or a correction amount thereof. The correction amount is set to, for example, a value obtained by adding or subtracting a predetermined margin from a reference value (intake amount) or a value multiplied by a predetermined coefficient. The judgment condition may be set to that the intake amount of a nutritional component indicated in the acquired implementation record information is equal to or greater than the intake amount of a nutritional component indicated in the proposed information output to the subject or a correction amount thereof. The judgment condition may be set to that the exercise amount of each exercise indicated in the acquired implementation record information is equal to or greater than the exercise amount of each exercise indicated in the proposed information output to the subject or a correction amount thereof. The judgment condition may be set such that the sleep time indicated in the acquired implementation record information is equal to or greater than the sleep time or a correction amount thereof indicated in the proposal information output to the subject.

[0088] The judgment condition may be that a predetermined number or ratio of the above conditions is satisfied. The judgment condition may be that a statistical value (average, median, minimum, maximum, etc.) of the difference or ratio between each value (intake amount, exercise amount, sleep time) shown in the implementation record information and each value (intake amount, exercise amount, sleep time) shown in the proposal information is equal to or greater than a predetermined threshold.

[0089] Next, the determination unit 127 outputs the determination result by displaying it on the display device 102 or by transmitting it to another device via the first communication device 103. In this way, the information processing system 1 can present to the subject whether or not the suggestion shown in the suggestion information has been appropriately implemented, and promote the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia.

[0090] If the acquired implementation record information satisfies the judgment condition, the support unit 128 ends the series of steps without executing any particular process.

[0091] On the other hand, if the acquired implementation record information does not satisfy the judgment condition, the support unit 128 outputs the support strengthening information by displaying it on the display device 102 or by transmitting it to another device via the first communication device 103 (step S303), and ends the series of steps. For example, the support unit 128 outputs a ranking of the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of each subject as the support strengthening information. Alternatively, the support unit 128 may output a comparison result of the proposal information and the implementation record information of each subject as the support strengthening information. In this way, the information processing system 1 can improve the motivation of the subject to implement the proposal shown in the proposal information, and promote the prevention, improvement, and / or progression prevention of postprandial hyperglycemia.

[0092] FIG. 8 is a flowchart showing an example of the operation of the update process of the terminal device 100.

[0093] An example of the operation of the update process of the terminal device 100 will be described below with reference to the flowchart shown in Fig. 8. Note that the flow of the operation described below is executed mainly by the first processing device 120 in cooperation with each element of the terminal device 100 based on a program stored in advance in the first storage device 110.

[0094] First, the second teacher data acquisition unit 129 receives the subject ID of each subject and glucose metabolism index information after prevention, improvement and / or prevention of progression of postprandial hyperglycemia from the diagnosis result registration device A1 or the measurement device A2 via the first communication device 103. As described above, a relational expression or table showing the correspondence between the degree of change in HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR and the degree of improvement effect of postprandial hyperglycemia is stored in advance in the first storage device 110. The second teacher data acquisition unit 129 calculates the difference or ratio of the average value of HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR before and after prevention, improvement and / or prevention of progression of postprandial hyperglycemia as the degree of change. The second teacher data acquisition unit 129 refers to the relational expression or table stored in the first storage device 110, identifies the degree of improvement effect corresponding to the calculated degree of change, and stores it in a management table (step S401). The second teacher data acquisition unit 129 receives glucose metabolism index information after prevention, improvement, and / or progression prevention of postprandial hyperglycemia at any timing, and sets the degree of improvement effect.

[0095] Next, the first processing device 120 executes the learning process shown in Fig. 5 (step S402), and ends the series of steps. However, in step S101, the second teacher data acquisition unit 129 acquires teacher data. Also, in step S102, the re-learning unit 130 re-learns the trained model 111 stored in the first storage device 110 using the teacher data acquired by the second teacher data acquisition unit 129, and updates the trained model 111. This allows the information processing system 1 to update the trained model 111 based on the implementation results of prevention, improvement, and / or progression prevention of postprandial hyperglycemia of each subject, and allows the subject's state of postprandial hyperglycemia to be identified with higher accuracy.

[0096] An example of a proposal for preventing, improving, and / or preventing the progression of postprandial hyperglycemia by the information processing system 1 according to this embodiment will be described below. Each subject shown below was selected from healthy individuals with a blood glucose level of 140 mg / dL or more and less than 200 mg / dL two hours after a meal containing about 75 g of carbohydrates, or healthy individuals with a HbA1c measurement value of 5.6% or more and less than 6.5% in a health checkup.

[0097] Subject A is a 34-year-old man with a BMI of 18.4. Subject A's postprandial hyperglycemia type was one in which blood glucose levels after meals tended to rise and fall easily. By inputting subject A's postprandial hyperglycemia type and background information into the trained model 111, suggested information was output that suggested that the intake of carbohydrates per day as the intake of nutritional components derived from food be 130 g or less. As a result of subject A taking the measures for three months, the blood glucose level two hours after ingesting 200 g of cooked rice (approximate carbohydrate amount: 70 to 75 g) improved from 150 mg / dL to 135 mg / dL.

[0098] Subject B is a 52-year-old woman with a BMI value of 26.2. Subject B's postprandial hyperglycemia type was a type in which blood glucose levels after meals do not easily rise or fall. By inputting subject B's postprandial hyperglycemia type and background information into the trained model 111, proposal information was output that suggests that the subject should increase the number of steps in aerobic exercise by 1000 steps per day from the average value in the past month as the amount of exercise to be performed. As a result of subject B carrying out the countermeasure for three months, the blood glucose level two hours after ingesting 200 g of cooked rice changed (slightly increased) from 160 mg / dL to 162 mg / dL. Subject B did not originally exhibit symptoms of postprandial hyperglycemia, and even if the countermeasure was carried out according to the proposal information, no effect was obtained. In this case, the trained model 111 is retrained using the implementation record information and effect information indicating a low degree of improvement effect, so that the information processing system 1 can improve the accuracy with which the trained model 111 outputs appropriate proposal information.

[0099] Subject C is a 46-year-old man with a BMI of 24.2. Subject C's postprandial hyperglycemia type was one in which blood glucose levels after meals tended to rise and did not fall easily. By inputting subject C's postprandial hyperglycemia type and background information into the trained model 111, suggested information was output that suggested performing resistance exercise consisting of 30 push-ups or sit-ups three times a week and consuming bottled drinks that suppress blood glucose level rises along with meals. As a result of subject A taking the measures for three months, the measured HbA1c value decreased (improved) from 5.7% (high normal) to 5.5% (normal range).

[0100] As described above in detail, the information processing system 1 identifies prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject using the trained model 111 generated based on the glucose metabolism index information and background information of the subject. This enables the information processing system 1 to more simply and accurately suggest prevention, improvement, and / or prevention of progression of postprandial hyperglycemia to the subject.

[0101] Furthermore, the information processing system 1 generates a trained model 111 capable of outputting information regarding favorable prevention, improvement, and / or prevention of progression of postprandial hyperglycemia based on implementation record information of prevention, improvement, and / or prevention of progression of postprandial hyperglycemia implemented by a subject corresponding to predetermined glucose metabolism index information and background information. This enables the information processing system 1 to more simply and accurately suggest prevention, improvement, and / or prevention of progression of postprandial hyperglycemia to the subject.

[0102] Furthermore, the information processing system 1 re-learns the trained model 111 that outputs information regarding the prevention, improvement, and / or prevention of progress of postprandial hyperglycemia based on implementation record information of the prevention, improvement, and / or prevention of progress of postprandial hyperglycemia implemented by the subject corresponding to the predetermined glucose metabolism index information and background information. This enables the information processing system 1 to more simply and accurately suggest the prevention, improvement, and / or prevention of progress of postprandial hyperglycemia to the subject.

[0103] For example, "Eur Rev Med Pharmacol Sci 2022. 26: 2765-2774. Characteristics of the glycometabolic categories based on the oral glucose tolerance test results in Japanese adults without diabetes (T Uchida, T Teramoto, S Fukizawa, H Kato, Y Nonaka, M Suematsu, N Murayama)" shows experimental results that, among healthy subjects whose blood glucose health check values ​​were normal as a result of an oral glucose tolerance test (OGTT), approximately 50% of subjects may be classified as having postprandial hyperglycemia. For those who may exhibit symptoms of postprandial hyperglycemia despite having normal blood glucose health check values, postprandial hyperglycemia may not be detected in a general health check. Postprandial hyperglycemia is a risk factor for diseases such as diabetes, and it is essential to take appropriate measures from the healthy stage before the onset of diabetes.

[0104] The information processing system 1 uses the trained model 111 generated based on the glucose metabolism index information and background information of the subject to identify the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject. As a result, the information processing system 1 can suggest appropriate measures against postprandial hyperglycemia to the subject from a healthy stage before the onset of diseases such as diabetes or dementia. The subject can prevent the onset of each disease by implementing the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia according to the suggestions from the information processing system 1. In addition, the information processing system 1 can suggest appropriate measures to each subject according to the condition of each subject for a large number of subjects. As a result, the information processing system 1 can reduce human resources for supporting the subjects.

[0105] In addition, for each type of postprandial hyperglycemia, measures are required according to the mechanism believed to be the cause (insulin secretion reduction / resistance), particularly depending on whether the type is prone to postprandial blood glucose levels increasing and / or whether the type is difficult to reduce postprandial blood glucose levels. Since postprandial blood glucose level fluctuations are controlled by insulin, a hormone secreted from pancreatic β cells and acting in the liver, muscles, etc., the main causes of postprandial hyperglycemia are believed to be insulin secretion reduction and insulin resistance.

[0106] The main mechanism that causes postprandial blood glucose levels to rise easily is a decrease in insulin secretion from pancreatic beta cells, and the appropriate measure for postprandial blood glucose levels to rise easily is dietary management. For postprandial blood glucose levels to rise easily, it is necessary to moderate the postprandial sugar absorption to suppress a sudden rise in blood glucose levels and maintain pancreatic beta cell function.

[0107] The main mechanism causing difficulty in lowering postprandial blood glucose levels is the progression of insulin resistance, and appropriate measures for this type of condition are exercise and sleep management. For this type of condition, it is necessary to improve insulin resistance by increasing muscle mass through resistance exercise to promote glucose metabolism, and by reducing body weight and body fat through aerobic exercise.

[0108] The information processing system 1 can propose measures more suitable for the subject by proposing prevention, improvement and / or prevention of progression of postprandial hyperglycemia according to the subject's postprandial hyperglycemia type. In particular, the information processing system 1 can propose measures more suitable for the subject by proposing prevention, improvement and / or prevention of progression of postprandial hyperglycemia according to whether the subject is a type in which postprandial blood glucose levels are likely to rise and / or whether the subject is a type in which postprandial blood glucose levels are unlikely to fall.

[0109] In addition, the information processing system 1 can also propose measures suitable for the subject when proposing prevention, improvement and / or prevention of progression of postprandial hyperglycemia according to the subject's HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level or TIR measurement value. Furthermore, the information processing system 1 can propose measures more suitable for the subject by proposing prevention, improvement and / or prevention of progression of postprandial hyperglycemia according to the subject's background (gender, age, BMI, eating habits, exercise habits or health checkup values).

[0110] Moreover, the information processing system 1 can calculate appropriate proposal information for various combinations of various types of parameters such as glucose metabolism index information and background information with high accuracy and efficiency by using the trained model 111. Furthermore, the information processing system 1 can specify proposal information without storing corresponding proposal information for various combinations of various types of parameters by using the trained model 111, thereby reducing the storage capacity of the storage device. Furthermore, the information processing system 1 can specify proposal information without performing complex judgments according to various combinations of various types of parameters by using the trained model 111, thereby reducing the processing time and processing load of the specification process.

[0111] The learning process shown in FIG. 5 and / or the update process shown in FIG. 8 may be executed by the server device 200 instead of the terminal device 100. In that case, the server device 200 has a first teacher data acquisition unit, a generation unit, a second teacher data acquisition unit, and / or a relearning unit similar to the first teacher data acquisition unit 121, the generation unit 122, the second teacher data acquisition unit 129, and / or the relearning unit 130. The server device 200 also stores a management table similar to the management table 112 in the second storage device 210. The management table stored in the second storage device 210 may not store the proposal information. In step S102, the generation unit and / or the relearning unit stores the generated or re-learned trained model in the second storage device 210 and transmits it to one or more terminal devices 100 via the second communication device 201. Each terminal device 100 receives the trained model from the server device 200 via the first communication device 103 and stores it in the first storage device 110.

[0112] In this case, the server device 200 may acquire teacher data (glucose metabolism index information, background information, implementation record information, effect information, and / or onset information of each subject) from each of the multiple terminal devices 100 to generate a trained model. This allows the information processing system 1 to generate a highly accurate trained model using a wide variety of teacher data. Furthermore, the information processing system 1 can centrally manage the trained models used by each terminal device 100 in the server device 200, making it possible to suppress variation in accuracy of the trained models used by each terminal device 100.

[0113] Further, the terminal device 100 may acquire the implementation record information and risk information using a learning model stored in the server device 200 instead of using the learning model stored in the terminal device 100. In that case, in step S201 of FIG. 6, the subject information acquisition unit 123 transmits the glucose metabolism index information and background information of the subject to the server device 200 via the first communication device 103. The second processing device 220 of the server device 200 receives the glucose metabolism index information and background information from the terminal device 100 via the second communication device 201, inputs them to the learned model stored in the second storage device 210, and acquires the implementation record information and risk information output from the learned model. The second processing device 220 transmits the acquired implementation record information and risk information to the terminal device 100 via the second communication device 201, and the identification unit 124 acquires the implementation record information and risk information by receiving them from the server device 200 via the first communication device 103.

[0114] The terminal device 100 can use the trained model stored in the server device 200 to suggest to the subject prevention, improvement, and / or prevention of progression of postprandial hyperglycemia using the latest trained model updated by the server device 200. Furthermore, the information processing system 1 can reduce the storage capacity of each terminal device 100. Meanwhile, the terminal device 100 can use the trained model 111 stored in itself to suggest to the subject prevention, improvement, and / or prevention of progression of postprandial hyperglycemia even in a state where the communication connection with the server device 200 is disconnected. Furthermore, the information processing system 1 can reduce the amount of communication between the terminal device 100 and the server device 200.

[0115] Furthermore, in the information processing system 1, a plurality of terminal devices 100 and / or a plurality of server devices 200 may cooperate to share the respective steps of the above-mentioned processes. [Explanation of symbols]

[0116] 1 Information processing system, 100 Terminal device, 110 First storage device, 111 Trained model, 121 First teacher data acquisition unit, 122 Generation unit, 123 Subject information acquisition unit, 124 Identification unit, 125 Output control unit, 126 Implementation record information acquisition unit, 127 Judgment unit, 128 Support unit, 129 Second teacher data acquisition unit, 130 Re-learning unit, 200 Server device, 210 Second storage device

Claims

1. a memory unit that stores a trained model that has been trained to output information related to the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of a subject when information related to the glucose metabolism index of the subject and background information of the subject are input; An acquisition unit that acquires information regarding the glucose metabolism index of the subject and background information of the subject; an identification unit that inputs the acquired information about the glucose metabolism index of the subject and background information about the subject into the trained model to identify information about the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of the subject; an output unit that outputs the specified information; 13. An information processing device comprising:

2. 2. The information processing device according to claim 1, wherein the information regarding the glucose metabolism index of the subject includes measured values ​​of HbA1c, fasting blood glucose level, postprandial blood glucose level, post-glucose load blood glucose level, average blood glucose level, maximum blood glucose level, or TIR (Time in Range) of the subject, or a postprandial hyperglycemia type estimated based on the measured values.

3. The information processing device according to claim 2 , wherein the postprandial hyperglycemia type includes whether or not the type is one in which postprandial blood glucose levels are likely to rise and / or whether or not the type is one in which postprandial blood glucose levels are unlikely to fall.

4. The information processing apparatus according to claim 1 , wherein the background information of the subject includes any one of the subject's sex, age, BMI, eating habits, exercise habits, and health checkup values.

5. The trained model is trained to further output disease onset risk information when information on the glucose metabolic index of the subject and background information on the subject are input, The identification unit inputs the acquired information on the glucose metabolic index of the subject and background information on the subject into the trained model, thereby identifying risk information of the subject for developing a disease; The information processing device according to claim 1 , wherein the output unit further outputs risk information identified by the identification unit.

6. 3. The information processing device of claim 1, wherein the information regarding the prevention, improvement and / or prevention of progression of the subject's postprandial hyperglycemia includes a method for selecting a food for specified health uses or a food with functional claims, setting a target intake amount of nutritional components derived from food, setting a target amount of exercise, or setting a target amount of sleep.

7. an implementation record information acquiring unit that acquires implementation record information of the prevention, amelioration, and / or progression prevention of postprandial hyperglycemia implemented in accordance with the specified information; The information processing apparatus according to claim 1 , further comprising a determination unit that determines whether or not the implementation record information satisfies a predetermined condition with respect to the specified information, and outputs a determination result.

8. a memory unit that stores a trained model that has been trained to output information related to the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of a subject when information related to the glucose metabolism index of the subject and background information of the subject are input; An acquisition unit that acquires information regarding the glucose metabolism index of the subject and background information of the subject; an identification unit that inputs the acquired information about the glucose metabolism index of the subject and background information about the subject into the trained model to identify information about the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of the subject; an output unit that outputs the specified information; An information processing system comprising:

9. An acquisition unit that acquires information regarding the glucose metabolism index of the subject and background information of the subject; an identification unit that identifies information relating to the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the acquired information relating to the glucose metabolic index of the subject and the background information of the subject into a trained model that has been trained to output information relating to the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject when information relating to the glucose metabolic index of the subject and background information of the subject are input; an output unit that outputs the specified information; 13. An information processing device comprising:

10. Obtaining information on the subject's glucose metabolism indicators and background information on the subject; Identifying information relating to the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the acquired information relating to the glucose metabolic index of the subject and the background information of the subject into a trained model that has been trained to output information relating to the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject when information relating to the glucose metabolic index of the subject and background information of the subject are input; outputting the specified information from an output unit; 23. An information processing method comprising:

11. A control program for a computer having an output unit, Obtaining information on the subject's glucose metabolism indicators and background information on the subject; Identifying information relating to the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject by inputting the acquired information relating to the glucose metabolic index of the subject and the background information of the subject into a trained model that has been trained to output information relating to the prevention, improvement and / or prevention of progression of postprandial hyperglycemia of the subject when information relating to the glucose metabolic index of the subject and background information of the subject are input; outputting the specified information from the output unit; A control program that causes a computer to execute the above steps.

12. an acquisition unit that acquires implementation record information of the prevention, improvement, and / or progression prevention of postprandial hyperglycemia performed by a subject corresponding to information on a predetermined glucose metabolism index and background information, and effect information based on the implementation record information; a generation unit that generates a trained model capable of outputting information related to the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia when the information related to the glucose metabolic index and the background information are input, using the information related to the glucose metabolic index, the background information, the implementation record information, and the effect information as training data; A generating device comprising:

13. Obtaining implementation record information of the prevention, improvement, and / or progression prevention of postprandial hyperglycemia implemented by the subject corresponding to information on a predetermined glucose metabolism index and background information, and effect information based on the implementation record information; generating a trained model capable of outputting information regarding effective prevention, improvement, and / or prevention of progression of postprandial hyperglycemia when the information regarding the glucose metabolic index and the background information are input, using the information regarding the glucose metabolic index, the background information, the implementation record information, and the effect information as training data; A generating method comprising:

14. Obtaining implementation record information of the prevention, improvement, and / or progression prevention of postprandial hyperglycemia implemented by the subject corresponding to information on a predetermined glucose metabolism index and background information, and effect information based on the implementation record information; generating a trained model capable of outputting information regarding effective prevention, improvement, and / or prevention of progression of postprandial hyperglycemia when the information regarding the glucose metabolic index and the background information are input, using the information regarding the glucose metabolic index, the background information, the implementation record information, and the effect information as training data; A control program that causes a computer to execute the above steps.

15. a memory unit that stores a trained model that has been trained to output information related to the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of a subject when information related to the glucose metabolism index of the subject and background information of the subject are input; A first acquisition unit that acquires information regarding the glucose metabolic index of the subject and background information regarding the subject; an identification unit that inputs the acquired information about the glucose metabolism index of the subject and background information about the subject into the trained model to identify information about the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of the subject; a second acquisition unit that acquires implementation record information of the prevention, improvement, and / or progression prevention of postprandial hyperglycemia implemented in accordance with the specified information and effect information based on the implementation record information; A re-learning unit that re-learns the trained model using the implementation record information and the effect information; 13. An information processing device comprising:

16. a memory unit that stores a trained model that has been trained to output information related to the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of a subject when information related to the glucose metabolism index of the subject and background information of the subject are input; A first acquisition unit that acquires information regarding the glucose metabolic index of the subject and background information regarding the subject; an identification unit that inputs the acquired information about the glucose metabolism index of the subject and background information about the subject into the trained model to identify information about the prevention, improvement, and / or progression prevention of postprandial hyperglycemia of the subject; a second acquisition unit that acquires implementation record information of the prevention, improvement, and / or progression prevention of postprandial hyperglycemia implemented in accordance with the specified information and effect information based on the implementation record information; A re-learning unit that re-learns the trained model using the implementation record information and the effect information; An information processing system comprising:

17. storing a trained model in a storage unit, the trained model being trained to output information relating to prevention, improvement and / or progression prevention of postprandial hyperglycemia of a subject when information relating to the subject's glucose metabolic index and background information of the subject are input; Obtaining information on the subject's glucose metabolism indicators and background information on the subject; inputting the acquired information about the glucose metabolism index of the subject and background information about the subject into the trained model, thereby identifying information about the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject; obtaining implementation record information when the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia is implemented in accordance with the specified information, and effect information based on the implementation record information; The trained model is retrained using the implementation record information and the effect information.

23. An information processing method comprising:

18. A control program for a computer having a storage unit, storing a trained model in the storage unit, the trained model being trained to output information relating to prevention, improvement and / or progression prevention of postprandial hyperglycemia of a subject when information relating to the subject's glucose metabolic index and background information of the subject are input; Obtaining information on the subject's glucose metabolism indicators and background information on the subject; inputting the acquired information about the glucose metabolism index of the subject and background information about the subject into the trained model, thereby identifying information about the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia of the subject; obtaining implementation record information when the prevention, improvement, and / or prevention of progression of postprandial hyperglycemia is implemented in accordance with the specified information, and effect information based on the implementation record information; The trained model is retrained using the implementation record information and the effect information. A control program that causes a computer to execute the above steps.

Citation Information

Patent Citations

  • Inspection assist device, method and program

    JP2022037880A

  • Blood component monitoring device, blood component monitoring program, and blood component monitoring system

    JP2022155173A

  • Intermittent Monitoring

    JP2022514646A