Health support system, server device, health support method, and program

Abstract

Accurately assess the risk of target diseases and encourage appropriate behavioral changes. [Solution] The health support system is equipped with a prediction processing unit that predicts the disease risk of a target disease from a user's medical history information based on a trained model generated by performing machine learning using the past medical history information of multiple people as learning data, and that predicts the disease risk, which is the risk of onset and worsening of the target disease, and an intervention processing unit that classifies the target disease into risk groups based on the disease risk predicted by the prediction processing unit, and performs an approach processing for the user to reduce the disease risk according to the classified risk group of the target disease.

Description

[Technical Field]

[0001] The present invention relates to a health support system, a server device, a health support method, and a program. [Background technology]

[0002] In recent years, a system has become known that statistically examines the merits and demerits of intervention methods using electronic medical records for medical care and nursing care (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-82092 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional technology systems search for intervention methods by evaluating group classifications according to the intervention method, and it is difficult to, for example, accurately determine the risk of the target disease and encourage behavioral change in high-risk individuals. Also, there is a problem that general recommendations for consultation from local governments and the like are unlikely to lead to behavioral change in high-risk individuals.

[0005] The present invention has been made to solve the above problems, and its purpose is to provide a health support system, server device, health support method, and program that can accurately determine the risk of a target disease and encourage appropriate behavioral changes. [Means for solving the problem]

[0006] In order to solve the above problem, one aspect of the present invention is a trained model that is generated by performing machine learning using the past medical history information of a plurality of people as training data, and that predicts disease risk, which is the risk of onset and aggravation of a target disease that is a disease that progresses without subjective symptoms, including at least one of osteoporosis and dementia, based on the trained model, and The aforementioned and an intervention processing unit that classifies the target disease into risk groups based on the disease risk predicted by the prediction processing unit, and executes an approach process for reducing the disease risk for the user according to the classified target disease risk group. The medical history information is data generated in association with use of a medical institution and includes at least health checkup results, the learning data is supervised learning data including a diagnosis history of the target disease, and the prediction processing unit predicts the disease risk of the target disease from the medical history information of the user based on the trained model generated by performing machine learning using the supervised learning data. It is a health support system.

[0007] Furthermore, one aspect of the present invention is a trained model generated by performing machine learning using past medical history information of a plurality of people as training data, the trained model predicting disease risk, which is the risk of onset and aggravation of a target disease that progresses without subjective symptoms, including at least one of osteoporosis and dementia, based on the trained model. The aforementioned and an intervention processing unit that classifies the target disease into risk groups based on the disease risk predicted by the prediction processing unit, and executes an approach process for reducing the disease risk for the user according to the classified target disease risk group. The medical history information is data generated in association with use of a medical institution and includes at least health checkup results, the learning data is supervised learning data including a diagnosis history of the target disease, and the prediction processing unit predicts the disease risk of the target disease from the medical history information of the user based on the trained model generated by performing machine learning using the supervised learning data. It is a server device.

[0008] In one aspect of the present invention, a prediction processing unit is configured to predict a disease risk, which is a risk of onset and aggravation of a target disease that progresses without subjective symptoms and includes at least one of osteoporosis and dementia, from a user's medical history information based on a trained model generated by performing machine learning using past medical history information of a plurality of people as training data. The aforementioneda prediction processing step of predicting a disease risk; and an intervention processing step of classifying a risk group of the target disease based on the disease risk predicted by the prediction processing step, and executing an approach processing for reducing the disease risk for the user according to the classified risk group of the target disease. the medical history information is data generated in association with use of a medical institution and includes at least health checkup results, the learning data is supervised learning data including a diagnosis history of the target disease, and in the prediction processing step, the prediction processing unit predicts the disease risk of the target disease from the medical history information of the user based on the trained model generated by performing machine learning using the supervised learning data. It is a health support method.

[0009] In one aspect of the present invention, a computer is provided that performs machine learning on past medical history information of a plurality of people as learning data, and generates a trained model that predicts disease risk, which is the risk of onset and aggravation of a target disease that progresses without subjective symptoms, including at least one of osteoporosis and dementia. The trained model predicts the risk of the target disease from the medical history information of a user. The aforementioned a prediction processing step of predicting a disease risk, and an intervention processing step of classifying a risk group of the target disease based on the disease risk predicted by the prediction processing step, and executing an approach processing for reducing the disease risk for the user in accordance with the classified risk group of the target disease; wherein the medical history information is data generated in association with use of a medical institution and includes at least health checkup results, the learning data is supervised learning data including a diagnosis history of the target disease, and in the prediction processing step, the program predicts the disease risk of the target disease from the medical history information of the user based on the trained model generated by performing machine learning using the supervised learning data. is. [Effects of the Invention]

[0010] According to the present invention, it is possible to accurately determine the risk of a target disease and encourage appropriate behavioral modification. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a functional block diagram showing an example of a health support system according to an embodiment of the present invention. [Figure 2] FIG. 4 is a diagram illustrating an example of data stored in a resident information storage unit according to the present embodiment. [Figure 3] FIG. 10 is a diagram showing an example of data in a risk result storage unit in this embodiment. [Figure 4] FIG. 10 is a diagram showing an example of an input screen for extraction conditions for risk results in this embodiment. [Figure 5]FIG. 10 is a diagram showing an example of a display screen of extracted risk results in this embodiment. [Figure 6] 4 is a flowchart showing an example of the operation of the health support system according to the present embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of the operation of a health management application according to the present embodiment. [Figure 8] FIG. 10 is a diagram showing an example of an operation for generating output information of the health support system according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] A health support system, a server device, a health support method, and a program according to an embodiment of the present invention will be described below with reference to the drawings.

[0013] FIG. 1 is a functional block diagram showing an example of a health support system 1 according to this embodiment. As shown in FIG. 1, health support system 1 includes health support server 10, administrator terminal 20, and user terminal 30.

[0014] Health support server 10, administrator terminal 20, and user terminal 30 are capable of communicating with each other via network NW1. The health support system 1 can be connected to an external system 40 via a network NW1.

[0015] The external system 40 is a variety of systems that can communicate with the health support system 1 via the network NW1, such as the National Health Insurance Database (KDB) system, medical systems such as electronic medical records from hospitals and medical facilities, receipts (medical fee statements), and corporate sites that provide information on health equipment and health foods.

[0016] Health support server 10 (an example of a server device) predicts disease risk, which is the risk of developing and worsening a target disease such as osteoporosis, extracts high-risk subjects for the target disease, and provides these high-risk subjects with various information to encourage behavioral changes to reduce the disease risk. Health support server 10, for example, serves as a BI (Business Intelligence) tool to visualize the disease risk of a target disease such as osteoporosis and extract high-risk subjects. Health support server 10 also includes NW (network) communication unit 11, server storage unit 12, and server control unit 13.

[0017] The target diseases of the health support system 1 according to this embodiment include osteoporosis, stroke, and dementia, but in the description of this embodiment, osteoporosis will be mainly described as the target disease.

[0018] The NW communication unit 11 is, for example, a network adapter that can be connected to the network NW1 via a wired LAN or the like, and can be connected to the administrator terminal 20, the user terminal 30, and the external system 40 via the network NW1.

[0019] Server storage unit 12 is a storage unit realized by, for example, a RAM (Random Access Memory), an SSD (Solid State Drive), or an HDD (Hard Disk Drive), which are not shown, and stores various information used by health support server 10. The server memory unit 12 includes a resident information memory unit 121, a model memory unit 122, a medical history information memory unit 123, a risk result memory unit 124, a test result memory unit 125, a recommended information memory unit 126, and an output information memory unit 127.

[0020] The resident information storage unit 121 stores resident information about residents of the local government who are users of the health support system 1. The resident information includes, for example, information such as the name, address, age, sex, telephone number, and email address of the resident (user). Here, an example of data stored in the resident information storage unit 121 will be described with reference to FIG. 2.

[0021] FIG. 2 is a diagram showing an example of data stored in the resident information storage unit 121 in this embodiment. As shown in FIG. 2, the resident information storage unit 121 stores resident information in which a resident number, a name, an age, a sex, an address, a telephone number, and an email address are associated with each other.

[0022] Here, the resident number is an example of user identification information that identifies a resident (user), and a unique number is assigned to each resident (each user). For example, in the example shown in Figure 2, the resident with the resident ID number "U00001" has the name "Taro XX", age "60 years old", and gender "male". The resident's address is "XXX-XX, XX Ward, Tokyo", and the telephone number is "080-XXXX-XXXX". The resident's email address (email address) is also shown to be "xxxx@abcd.com".

[0023] Returning to the explanation of FIG. 1, the model storage unit 122 stores a trained model, which is a prediction model that predicts the disease risk of a target disease from the medical history information of a target resident. The trained model is, for example, a model generated by performing machine learning using the past medical history information of multiple people as training data. The medical history information includes, for example, medical record data, medical receipts, medical treatment data, health checkup results, medication information, etc., and the training data is supervised training data that includes the diagnosis history of the target disease.

[0024] In addition, when the model storage unit 122 supports multiple target diseases, it may store a trained model for each target disease. In addition, in this embodiment, the trained model is assumed to be created, for example, by a learning processing server (not shown) and stored in advance in the model storage unit 122.

[0025] The medical history information storage unit 123 stores medical history information (e.g., medical record data, medical receipts, medical examination data, health check results, medication information, etc.) corresponding to a resident (user) acquired from an external system 40 such as a KDB system, a hospital or medical institution system, etc. The medical history information storage unit 123 stores, for example, a resident number (user identification information) and medical history information in association with each other.

[0026] The risk result storage unit 124 stores the results of risk determination (risk results), which are the processing results of the treatment history determination unit 133, prediction processing unit 134, and intervention processing unit 135, which will be described later. The risk result storage unit 124 stores the risk result for each target resident. Here, an example of data in the risk result storage unit 124 will be described with reference to FIG. 3.

[0027] FIG. 3 is a diagram showing an example of data in the risk result storage unit 124 in this embodiment. As shown in FIG. 3, the risk result storage unit 124 stores, for example, a resident number, a risk prediction value, a risk category, a treatment history, a high risk, a test kit, and an application provision in association with each other.

[0028] Here, the risk prediction value is a predicted value of disease risk predicted by the prediction processing unit 134, and the risk classification is an example of a risk group classified by the intervention processing unit 135 based on the risk prediction value, and is classified (categorized) according to the risk prediction value into less than 40%, 40% or more but less than 60%, 60% or more but less than 80%, and 80% or more. Also, the treatment history is treatment history information determined by the treatment history determination unit 133, such as untreated, under treatment, or treatment interrupted.

[0029] Furthermore, "high risk" is information indicating whether or not the subject is at high risk for disease, i.e., a certain level or higher ("○" or "×"), and "test kit" is information indicating whether or not a test kit for osteoporosis, etc. has been sent. Furthermore, "application provision" is information indicating whether or not a health management application, which will be described later, has been provided.

[0030] In the example shown in Figure 3, the resident (user) with the resident ID number "U00001" has a risk prediction value of "20.7%," a risk classification of "less than 40%," and a medical history of "untreated." The resident (user) is also marked "x" for high risk, test kit availability, and app availability.

[0031] Additionally, the resident (user) with the resident ID number "U00002" has a risk prediction value of "85.5%," a risk classification of "80% or more," and a treatment history of "treatment discontinued." The resident (user) also has a high risk rating, test kit availability, and app availability all marked "○."

[0032] 1, the test result storage unit 125 stores the test results obtained by the test kit described above. The test result storage unit 125 stores, for example, the resident number and the test result in association with each other.

[0033] The recommended information storage unit 126 stores recommendation information (recommended information) of health tools, health foods, etc. for reducing disease risk, acquired from an external system 40 such as a server device of a cooperating company. The recommended information storage unit 126 may store recommendation information (recommended information) for each risk category and each target disease, for example.

[0034] The output information storage unit 127 stores output information generated by the output processing unit 137, which will be described later. The output information is, for example, display information such as a list of risk results extracted from the risk results in response to a request (extraction condition) from the administrator terminal 20.

[0035] Server control unit 13 is a functional unit realized, for example, by causing a CPU (Central Processing Unit) (not shown) to execute a program stored in server storage unit 52, and comprehensively controls health support server 10. Server control unit 13 executes various processes executed by health support server 10. The server control unit 13 includes a medical history information acquisition unit 131 , a resident extraction unit 132 , a treatment history determination unit 133 , a prediction processing unit 134 , an intervention processing unit 135 , an AP processing unit 136 , and an output processing unit 137 .

[0036] The medical history information acquisition unit 131 acquires medical history information from the external system 40. The medical history information acquisition unit 131 acquires medical history information (for example, medical record data, medical receipts, medical treatment data, health checkup results, medication information, etc.) from the external system 40 via the NW communication unit 11, associates the acquired medical history information with the resident number, and stores the information in the medical history information storage unit 123.

[0037] The resident extraction unit 132 extracts, for example, from the resident information storage unit 121, residents who are to be subject to risk assessment.

[0038] The treatment history determination unit 133 determines treatment for a target disease (e.g., osteoporosis) from the medical history information. The treatment history determination unit 133 determines whether the treatment history is untreated, under treatment, or treatment interrupted, for example, from history information and medication information related to the target disease in the medical history information.

[0039] The prediction processing unit 134 predicts the disease risk of a target disease from the medical history information of the target resident (user) based on the trained model described above. The prediction processing unit 134 acquires the medical history information corresponding to the target resident (user) from the medical history information storage unit 123, and calculates a predicted value, such as the risk predicted value shown in FIG. 3, from the acquired medical history information using the trained model stored in the model storage unit 122.

[0040] The intervention processing unit 135 classifies the target disease into risk groups based on the disease risk predicted by the prediction processing unit 134, and executes an approach process for reducing the disease risk for the user according to the classified target disease risk group. The intervention processing unit 135 classifies the target disease into risk groups such as risk categories based on the risk prediction values ​​shown in Figure 3, for example.

[0041] The intervention processing unit 135 also extracts users in a high-risk group (high-risk subjects) whose disease risk is higher than a certain level, and performs an approach process to encourage users in the high-risk group to change their behavior to reduce their disease risk. For example, the intervention processing unit 135 extracts target residents whose risk category shown in Figure 3 is "80% or higher" as high-risk subjects.

[0042] As an approach process, the intervention processing unit 135 sends the high-risk subject a result notification indicating that the subject is a high-risk subject (high-risk group) or a notification encouraging behavioral change (for example, a notification such as "exercise regularly"). The intervention processing unit 135 acquires a telephone number or email address corresponding to the high-risk subject from the resident information storage unit 121, and sends a notification to the telephone number or email address of the high-risk subject. The intervention processing unit 135 may also send the result notification or the notification encouraging behavioral change to the high-risk subject by mail.

[0043] Furthermore, the intervention processing unit 135 transmits a test kit for the target disease to the high-risk subject (a user in the high-risk group) as an approach process. For example, the intervention processing unit 135 arranges for a test kit for osteoporosis to be mailed to the address of the high-risk subject obtained from the resident information storage unit 121.

[0044] Furthermore, the intervention processing unit 135 provides high-risk subjects with a health management application that supports the health management of target residents (users) as an approach process. The intervention processing unit 135 provides the health management application to the high-risk subjects by notifying them, for example, by mail or email of a URL (Uniform Resource Locator) at which the health management application can be downloaded.

[0045] The intervention processing unit 135 stores the disease risk assessment results (risk results) of the target residents in the risk result storage unit 124. The intervention processing unit 135 stores the risk results in the risk result storage unit 124, for example, as shown in FIG. 3.

[0046] The intervention processing unit 135 may send different notifications to the target residents depending on the risk category (risk group). Furthermore, the intervention processing unit 135 may classify risk categories (risk groups) or extract high-risk subjects based on the risk prediction value and the treatment history of the target disease. For example, even if the risk prediction value is high, if the treatment history is "under treatment", the subject may be classified into a risk category (risk group) with a low disease risk, or if the treatment history is "untreated", the subject may be extracted as a high-risk subject even if the low risk category (risk group) is "60% or more but less than 80%".

[0047] AP processing unit 136 (an example of an application processing unit) provides a health management support service via a health management application. AP processing unit 136 performs, for example, visualization of risk results and provision of recommendation information (recommended information) on health tools, supplements, etc. to user terminal 30 connected to health support server 10 via NW communication unit 11.

[0048] The AP processing unit 136 outputs output information (e.g., risk results) including disease risk, medical history information, and risk group of the target disease to, for example, the high-risk subject (user terminal 30). The AP processing unit 136 generates output information based on the risk results stored in the risk result storage unit 124, transmits the generated output information to the user terminal 30 via the NW communication unit 11, and causes the user terminal 30 to display the output information.

[0049] Furthermore, the AP processing unit 136 provides, for example, information on health tools or health foods for reducing disease risk to high-risk subjects (user terminals 30). The AP processing unit 136 collects information on health tools or health foods from the external system 40 via the NW communication unit 11 and stores it in the recommended information storage unit 126. The AP processing unit 136 acquires recommendation information (recommended information) according to the risk category (risk group) of the target resident (user), transmits it to the user terminal 30 via the NW communication unit 11 as information on health tools or health foods, and displays the recommendation information (recommended information) on the user terminal 30.

[0050] The output processing unit 137 generates output information including the disease risk for each target resident (user), the risk group for the target disease, and the treatment history of the target disease, in response to a request from, for example, the administrator terminal 20. The output processing unit 137 transmits the generated output information to the administrator terminal 20 via the NW communication unit 11, and causes the administrator terminal 20 to display the output information (display information).

[0051] Here, the output information output by the output processing unit 137 will be described with reference to FIGS. FIG. 4 is a diagram showing an example of an input screen for the extraction conditions of the risk result in this embodiment. FIG. 5 is a diagram showing an example of a display screen of extracted risk results in this embodiment.

[0052] The output processing unit 137 displays, for example, a display screen G1 as shown in FIG. 4 on the manager terminal 20, and acquires the extraction conditions for the risk result from the manager terminal 20 via the NW communication unit 11.

[0053] Furthermore, the output processing unit 137 extracts risk results from the risk result storage unit 124 in accordance with the risk result extraction conditions, and generates output information such as the display screen G2 shown in Fig. 5. The output processing unit 137 transmits the output information (display screen G2) to the manager terminal 20 via the NW communication unit 11, and causes the manager terminal 20 to display the output information (display screen G2).

[0054] Returning to the explanation of Fig. 1, administrator terminal 20 is a terminal device owned by the administrator of health support system 1, and is, for example, a personal computer (PC), a tablet terminal, a smartphone, etc. Administrator terminal 20 includes NW communication unit 21, input unit 22, display unit 23, terminal control unit 24, and terminal storage unit 25.

[0055] NW communication unit 21 is a network adapter that can be connected to network NW1 via, for example, a wired LAN or a wireless LAN, and can be connected to health support server 10 via network NW1.

[0056] The input unit 22 is an input device such as a keyboard, a mouse, or a touch panel, and receives various information from the administrator.

[0057] Display unit 23 is a display device such as a liquid crystal display device, an organic EL (Electro Luminescence) display, etc. Display unit 23 displays various information for managing health support system 1.

[0058] Terminal control unit 24 is a functional unit realized, for example, by causing a CPU (not shown) to execute a program stored in terminal storage unit 25, and comprehensively controls administrator terminal 20. Terminal control unit 24 executes various processes for managing health support system 1.

[0059] The terminal storage unit 25 is a storage unit realized by, for example, a RAM, an SSD, an HDD, etc. (not shown), and stores various information used by the administrator terminal 20.

[0060] User terminal 30 is a terminal device owned by a user (target resident) of health support system 1, and is, for example, a personal computer (PC), a tablet terminal, a smartphone, etc. User terminal 30 includes a NW communication unit 31, an input unit 32, a display unit 33, a terminal control unit 34, and a terminal storage unit 35.

[0061] NW communication unit 31 is a network adapter that can be connected to network NW1 via, for example, a wired LAN or a wireless LAN, and can be connected to health support server 10 via network NW1.

[0062] The input unit 32 is an input device such as a keyboard, a mouse, or a touch panel, and receives various information from the administrator.

[0063] Display unit 33 is, for example, a display device such as a liquid crystal display device, an organic EL (Electro Luminescence) display, etc. Display unit 33 displays various information when using the health management application described above.

[0064] The terminal control unit 34 is a functional unit realized, for example, by causing a CPU (not shown) to execute a program stored in the terminal storage unit 35, and performs overall control of the user terminal 30. The terminal control unit 34 executes various processes when using the above-mentioned health management application, for example.

[0065] Terminal storage unit 35 is a storage unit realized by, for example, a RAM, SSD, HDD, etc. (not shown), and stores various information used by user terminal 30. In terminal storage unit 35, for example, a health management application program provided by health support system 1 is installed and stored.

[0066] Although FIG. 1 shows health support system 1 with one user terminal 30, health support system 1 may include multiple user terminals 30 depending on the users.

[0067] Next, the operation of health support system 1 according to this embodiment will be described with reference to the drawings. FIG. 6 is a flowchart showing an example of the operation of the health support system 1 according to this embodiment.

[0068] In the health support system 1, for example, the health support server 10 starts assessing the risk of a target disease (e.g., osteoporosis) in response to a request from the administrator terminal 20 or when a predetermined execution condition (e.g., every certain period of time) is met.

[0069] As shown in Figure 6, health support server 10 of health support system 1 first acquires medical history information (step S101). Medical history information acquisition unit 131 of health support server 10 acquires medical history information (for example, medical record data, medical receipts, medical treatment data, health check results, medication information, etc.) from external system 40 via NW communication unit 11. Medical history information acquisition unit 131 associates the acquired medical history information with the resident number and stores it in medical history information storage unit 123.

[0070] Next, the resident extraction unit 132 of the health support server 10 extracts target residents whose disease risk is to be assessed from the resident information storage unit 121 (step S102). The resident extraction unit 132 may extract target residents in response to a request from the administrator terminal 20, for example, or may extract target residents who meet predetermined conditions.

[0071] Next, the medical history determination unit 133 of the health support server 10 determines the medical history from the medical history information corresponding to the target resident (step S103). The medical history determination unit 133 acquires the medical history information corresponding to the target resident from the medical history information storage unit 123, and determines the medical history (either untreated, under treatment, or treatment interrupted) from, for example, the medical information and medication information (medication information) on the prescription.

[0072] Next, the prediction processing unit 134 of the health support server 10 predicts the disease risk from the medical history information corresponding to the target resident using the trained model (step S104). The prediction processing unit 134 acquires the medical history information corresponding to the target resident from the medical history information storage unit 123, and calculates a predicted value, such as the risk prediction value shown in Fig. 3, from the acquired medical history information using the trained model stored in the model storage unit 122.

[0073] Next, the intervention processing unit 135 of the health support server 10 classifies the target resident into a disease risk category (for example, the risk category shown in FIG. 3) based on the predicted disease risk value (step S105).

[0074] Next, the intervention processing unit 135 extracts high-risk subjects from the target residents based on the risk category and treatment history (step S106). The intervention processing unit 135 extracts high-risk subjects by taking into account, for example, the risk category and treatment history (either untreated, under treatment, or treatment interrupted).

[0075] Next, the intervention processing unit 135 notifies the high-risk subject of the disease risk assessment result and sends a disease test kit (step S107). The intervention processing unit 135 acquires the high-risk subject's telephone number or email address from the resident information storage unit 121, and notifies the high-risk subject of the disease risk assessment result using the telephone number or email address. The intervention processing unit 135 also acquires the high-risk subject's address from the resident information storage unit 121, and arranges for, for example, an osteoporosis test kit to be mailed to the high-risk subject's address.

[0076] Next, the intervention processing unit 135 provides the health management application to the high-risk subject (step S108). The intervention processing unit 135 provides the health management application to the high-risk subject by, for example, notifying the high-risk subject of a URL where the health management application can be downloaded by mail or email.

[0077] Next, the intervention processing unit 135 acquires the test results from the test kit (step S109). The intervention processing unit 135 acquires, for example, the test results from the osteoporosis test kit from the external system 40 via the NW communication unit 11. The intervention processing unit 135 stores, for example, a risk result as shown in FIG. 3 in the risk result storage unit 124.

[0078] After obtaining the test results from the test kit, the intervention processing unit 135 may again take the test results into consideration and determine the disease risk again. After the process of step S109, the intervention processing unit 135 ends the process.

[0079] Next, the operation of the health management application according to this embodiment will be described with reference to FIG. FIG. 7 is a diagram showing an example of the operation of the health management application according to this embodiment.

[0080] 7, first, user terminal 30 executes access processing for the health support application to health support server 10 (step S201). Terminal control unit 34 of user terminal 30 executes the health management application installed in terminal storage unit 35, and starts access processing with health support server 10 via NW communication unit 31.

[0081] Next, user terminal 30 transmits an output request for the disease risk determination result to health support server 10 (step S202). For example, in response to reception of input information from input unit 32, terminal control unit 34 transmits the output request for the disease risk determination result to health support server 10 via NW communication unit 31.

[0082] Next, in response to the request to output the disease risk assessment result, the health support server 10 transmits the disease risk assessment result to the user terminal 30 (step S203). The AP processing unit 136 of the health support server 10 acquires the risk result (disease risk assessment result) of the target resident corresponding to the user terminal 30 from the risk result storage unit 124, and transmits the acquired risk result (disease risk assessment result) of the target resident to the user terminal 30 via the NW communication unit 11.

[0083] Next, user terminal 30 displays the risk assessment result on display unit 33 (step S204). Terminal control unit 34 displays the risk result (disease risk assessment result) received from health support server 10 via NW communication unit 31 on display unit 33, thereby visualizing the risk result.

[0084] Next, the health support server 10 determines whether the user is at high risk (step S205). The AP processing unit 136 determines whether the user (target resident) is at high risk (high-risk subject) depending on whether the high risk included in the risk result of the user (target resident) is "○". If the user (target resident) is at high risk (high-risk subject) (step S205: YES), the AP processing unit 136 proceeds to step s206. If the user (target resident) is not at high risk (high-risk subject) (step S205: NO), the AP processing unit 136 proceeds to step s208.

[0085] In step S206, the AP processing unit 136 transmits a notification of a treatment alert (step S2-6). The AP processing unit 136 transmits, for example, a warning message urging the user to receive treatment as a treatment alert to the user terminal 30 via the NW communication unit 11.

[0086] Next, the terminal control unit 34 of the user terminal 30 displays the treatment alert on the display unit 33 (step S207). The terminal control unit 34 causes the display unit 33 to display the treatment alert notification (e.g., a warning message) received from the health support server 10 via the NW communication unit 31.

[0087] In step S208, the AP processing unit 136 extracts recommendation information according to the disease risk. The AP processing unit 136 extracts, for example, information on health tools or health foods (supplements, etc.) as recommendation information (recommended information) according to the risk category (risk group) of the target resident (user).

[0088] Next, the AP processing unit 136 transmits the recommendation information to the user terminal 30 (step S209). The AP processing unit 136 transmits the recommendation information to the user terminal 30 via the NW communication unit 11.

[0089] Next, the user terminal 30 displays the recommendation information on the display unit 33 (step S210). The terminal control unit 34 causes the display unit 33 to display the recommendation information on health tools, supplements, etc. received from the health support server 10 via the NW communication unit 31.

[0090] Next, the operation of generating output information in health support system 1 according to this embodiment will be described with reference to FIG. FIG. 8 is a diagram showing an example of the operation of generating output information in health support system 1 according to this embodiment.

[0091] 8, first, administrator terminal 20 executes a login process to health support server 10 (step S301). Terminal control unit 24 of administrator terminal 20 executes the login process with health support server 10 via NW communication unit 21.

[0092] Next, health support server 10 transmits the management menu information to administrator terminal 20 (step S302). Output processing unit 137 of health support server 10 transmits the management menu information to administrator terminal 20 via NW communication unit 11.

[0093] Next, administrator terminal 20 displays the management menu on display unit 23 (step S303). Terminal control unit 24 of administrator terminal 20 causes display unit 23 to display the management menu based on the management menu information received from health support server 10 via NW communication unit 21.

[0094] Next, the terminal control unit 24 receives the menu selection information and extraction conditions from the input unit 22 (step S304).

[0095] Next, terminal control unit 24 transmits the extraction request (menu selection information and extraction conditions) to health support server 10 (step S305). Terminal control unit 24 transmits the extraction request including the menu selection information and extraction conditions received from input unit 22 to health support server 10 via NW communication unit 21.

[0096] Next, in response to the extraction request, output processing unit 137 of health support server 10 extracts risk determination results that match the extraction conditions from the risk determination results and generates output information (step S306). Output processing unit 137 generates output information such as the display screen G2 shown in FIG.

[0097] Next, the output processing unit 137 transmits the output information to the manager terminal 20 (step S307). The output processing unit 137 transmits the output information to the manager terminal 20 via the NW communication unit 11.

[0098] Next, terminal control unit 24 displays the output information on display unit 23 (step S308). Terminal control unit 24 causes display unit 23 to display the output information received from health support server 10 via NW communication unit 21 (for example, display screen G2 shown in FIG. 5).

[0099] As described above, the health support system 1 according to this embodiment includes a prediction processing unit 134 and an intervention processing unit 135. The prediction processing unit 134 predicts the disease risk of a target disease from the medical history information of a user (target resident) based on the trained model, which is generated by performing machine learning using multiple people's past medical history information (e.g., medical record data, medical receipts, medical data, health checkup results, medication information, etc.) as training data. The trained model predicts the disease risk, which is the risk of onset and worsening of a target disease (e.g., osteoporosis). The intervention processing unit 135 classifies the target disease into risk groups (e.g., risk categories) based on the disease risk predicted by the prediction processing unit 134, and performs an approach process for reducing the disease risk of the user (target resident) according to the classified risk group (e.g., risk category) of the target disease.

[0100] As a result, the health support system 1 according to this embodiment predicts disease risk based on a trained model generated by machine learning using multiple people's past medical history information (e.g., medical record data, medical receipts, medical data, health checkup results, medication information, etc.) as training data, and can therefore accurately determine the risk of a target disease. Furthermore, the health support system 1 according to this embodiment executes an approach process to reduce disease risk according to a risk group (e.g., risk category) based on the disease risk, making target residents (users) aware of their disease risk and encouraging appropriate behavioral changes. Therefore, the health support system 1 according to this embodiment can accurately determine the risk of a target disease and encourage appropriate behavioral changes, such as improving lifestyle habits or visiting a medical institution.

[0101] In addition, in this embodiment, the intervention processing unit 135 extracts users (high-risk subjects) in a high-risk group whose disease risk is higher than a certain level, and performs an approach process to encourage users in the high-risk group to change their behavior to reduce their disease risk.

[0102] As a result, the health support system 1 of this embodiment executes an approach process that encourages users in the high-risk group to change their behavior to reduce their disease risk, thereby making the target residents (users) aware of their disease risk and encouraging them to change their behavior more appropriately.

[0103] Furthermore, in this embodiment, the intervention processing unit 135 transmits, as approach processing, to users in the high-risk group (high-risk subjects), a result notification indicating that they are in the high-risk group or a notification encouraging them to change their behavior.

[0104] As a result, the health support system 1 of this embodiment can make the target residents (users) aware that they are in the high-risk group by sending them a result notification indicating that they are in the high-risk group or a notification encouraging them to change their behavior, thereby more appropriately encouraging them to change their behavior.

[0105] Furthermore, in this embodiment, the intervention processing unit 135 transmits (for example, by mail) a test kit for the target disease to users in the high-risk group (high-risk subjects) as approach processing.

[0106] As a result, the health support system 1 according to this embodiment can make target residents (users) aware of their disease risk by sending (for example, by mail) a test kit for the target disease, and can further encourage appropriate behavioral changes.

[0107] Furthermore, in this embodiment, the intervention processing unit 135 provides, as approach processing, a health management application that supports the health management of users in the high-risk group (high-risk subjects).

[0108] As a result, the health support system 1 according to this embodiment can make target residents (users) aware of disease risks and encourage more appropriate behavioral changes by providing a health management application.

[0109] Furthermore, health support system 1 according to this embodiment includes AP processing unit 136 (application processing unit) that provides health management support services via a health management application. AP processing unit 136 provides information on health tools or health foods for reducing disease risk to users in the high-risk group (high-risk subjects).

[0110] As a result, the health support system 1 of this embodiment provides information on health equipment or health foods for reducing the risk of disease via a health management application, thereby raising the health management awareness of target residents (users) and reducing the risk of disease.

[0111] In addition, in this embodiment, the AP processing unit 136 outputs output information (for example, risk results) including disease risk, medical history information, and the risk group of the target disease to users in the high-risk group (high-risk subjects).

[0112] As a result, the health support system 1 of this embodiment can make target residents (users) aware of their disease risks and encourage more appropriate behavioral changes by outputting output information (e.g., risk results) including disease risks, medical history information, and risk groups for the target disease.

[0113] In this embodiment, the target diseases include osteoporosis, stroke, and dementia. As a result, the health support system 1 of this embodiment can make target residents (users) aware of their disease risks for osteoporosis, stroke, and dementia, which are diseases that progress without noticeable symptoms, and can encourage appropriate behavioral changes.

[0114] Furthermore, health support server 10 (server device) according to this embodiment includes a prediction processing unit 134 and an intervention processing unit 135. Prediction processing unit 134 predicts the disease risk of a target disease from the medical history information of a user (target resident) based on the trained model, which is generated by performing machine learning using the past medical history information of multiple people as learning data and which predicts the disease risk, which is the risk of onset and worsening of a target disease (e.g., osteoporosis). Intervention processing unit 135 classifies the target disease into a risk group (e.g., risk category) based on the disease risk predicted by the prediction processing unit 134, and executes an approach process for reducing the disease risk of the user according to the classified risk group (e.g., risk category) of the target disease.

[0115] As a result, health support server 10 (server device) according to this embodiment can achieve the same effects as health support system 1 described above, and can accurately determine the risk of a target disease and encourage appropriate behavioral modification.

[0116] The health support method according to this embodiment also includes a prediction processing step and an intervention processing step. In the prediction processing step, the prediction processing unit 134 predicts the disease risk of a target disease from the user's medical history information based on a trained model generated by performing machine learning using the past medical history information of multiple people as learning data, the trained model predicting disease risk, which is the risk of onset and worsening of the target disease. In the intervention processing step, the intervention processing unit 135 classifies the target disease into risk groups based on the disease risk predicted in the prediction processing step, and performs an approach process for reducing the disease risk of the user according to the classified risk group of the target disease.

[0117] As a result, the health support method according to this embodiment can achieve the same effects as the health support system 1 and health support server 10 described above, and can accurately determine the risk of a target disease and encourage appropriate behavioral changes.

[0118] The present invention is not limited to the above-described embodiment, and can be modified within the scope of the present invention. For example, in the above embodiment, examples of the target diseases are described as osteoporosis, stroke, and dementia, but the target diseases are not limited to these and may be other diseases (or disorders) as long as they progress without any noticeable symptoms.

[0119] In the above embodiment, health support server 10 is implemented by a single server device, but this is not limiting and health support server 10 may be implemented by multiple server devices. For example, AP processing unit 136 may be provided in an application server. Also, for example, a storage server may be provided with part or all of server storage unit 12.

[0120] Furthermore, in the above embodiment, an example has been described in which the output information (e.g., a list of risk results) generated by the output processing unit 137 is displayed by the administrator terminal 20, but this is not limited thereto, and for example, output information (e.g., a list of risk results) resulting from a risk assessment of residents may be provided to a local government. In this case, the health support system 1 may, for example, assess the disease risk of residents on behalf of the local government, extract high-risk subjects, provide a list of high-risk subjects, and provide a proxy service in which various approaches to encourage behavioral change are carried out in exchange for payment.

[0121] Furthermore, in the above embodiment, an example of a risk group has been described in which a risk category is used in which the predicted value of disease risk is divided into a predetermined range, but this is not limited to this, and the health support system 1 may use other risk groups, such as a risk level or risk rank that takes into account other items such as treatment history in the predicted value of disease risk.

[0122] Each component of the health support system 1 and health support server 10 described above has an internal computer system. A program for realizing the functions of each component of the health support system 1 and health support server 10 described above may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed to perform processing in each component of the health support system 1 and health support server 10 described above. Here, "reading a program recorded on a recording medium into a computer system and executing it" includes installing the program into a computer system. The "computer system" referred to here includes hardware such as an OS and peripheral devices. Furthermore, a "computer system" may include multiple computer devices connected via a network, including communication lines such as the Internet, WAN, LAN, and dedicated lines. Furthermore, a "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into a computer system. Thus, the recording medium storing the program may be a non-transitory recording medium such as a CD-ROM.

[0123] The recording medium also includes internal or external recording media accessible from a distribution server for distributing the program. The program may be divided into multiple parts, downloaded at different times, and then combined by the components of health support system 1 and health support server 10, or each divided program may be distributed by a different distribution server. Furthermore, the term "computer-readable recording medium" also includes a medium that stores a program for a certain period of time, such as volatile memory (RAM) within a computer system that serves as a server or client when a program is transmitted over a network. The program may also be a medium that realizes part of the above-described functions. Furthermore, the program may be a so-called differential file (differential program) that can realize the above-described functions in combination with a program already stored in the computer system.

[0124] Furthermore, some or all of the above-described functions may be realized as an integrated circuit such as an LSI (Large Scale Integration). Each of the above-described functions may be individually implemented as a processor, or some or all of the functions may be integrated into a processor. Furthermore, the integrated circuit implementation method is not limited to LSI, and may be implemented using a dedicated circuit or a general-purpose processor. Furthermore, if an integrated circuit implementation technology that can replace LSI emerges due to advances in semiconductor technology, an integrated circuit based on that technology may be used. [Explanation of symbols]

[0125] 1. Health support system 10 Health support server 11, 21, 31 Network Communications Department 12 Server storage unit 13 Server control unit 20 Administrator terminal 22, 32 Input section 23, 33 Display section 24, 34 Terminal control unit 25, 35 Terminal memory section 40 External Systems 121 Resident information storage section 122 Model Memory Unit 123 Medical history information storage unit 124 Risk Result Memory Unit 125 Test result storage unit 126 Recommendation information storage unit 127 Output information storage unit 131 Medical History Information Acquisition Department 132 Resident Selection Department 133 Treatment History Assessment Unit 134 Prediction processing unit 135 Intervention Processing Unit 136 AP processing unit 137 Output Processing Unit

Claims

1. a prediction processing unit that predicts the disease risk of a target disease from the medical history information of a user based on the trained model, which is a trained model generated by performing machine learning using past medical history information of a plurality of people as training data, and which predicts the disease risk, which is the risk of onset and aggravation of a target disease that progresses without subjective symptoms, including at least one of osteoporosis and dementia; and an intervention processing unit that classifies the target disease into risk groups based on the disease risk predicted by the prediction processing unit, and executes an approach processing for reducing the disease risk for the user in accordance with the classified target disease risk group; Equipped with The medical history information is data generated in association with use of a medical institution, and includes at least the results of a medical examination; the learning data is supervised learning data including a diagnosis history of the target disease, The prediction processing unit predicts the disease risk of the target disease from medical history information of the user based on the trained model generated by performing machine learning using the supervised training data. Health support system.

2. The intervention processing unit extracts the users in a high-risk group whose disease risk is higher than a certain level, and executes the approach processing to encourage the users in the high-risk group to change their behavior to reduce the disease risk. The health support system according to claim 1 .

3. The intervention processing unit transmits, as the approach processing, to the user in the high-risk group, a result notification indicating that the user is in the high-risk group or a notification encouraging the user to change their behavior. The health support system according to claim 2 .

4. the target disease is osteoporosis, The intervention processing unit transmits the osteoporosis test kit to the user in the high-risk group as the approach process. The health support system according to claim 2 .

5. the target disease is osteoporosis, The intervention processing unit provides, as the approach processing, a health management application for supporting health management of the user in the high-risk group. The health support system according to claim 2 .

6. an application processing unit that provides the health management support service via the health management application; The application processing unit provides the user in the high-risk group with information about health tools or health foods for reducing the disease risk. The health support system according to claim 5 .

7. The application processing unit outputs output information including the disease risk, the medical history information, and the risk group of the target disease to the user in the high-risk group. The health support system according to claim 6.

8. The intervention processing unit classifies the target disease into a risk group based on the disease risk and the treatment history of the target disease. The health support system according to any one of claims 1 to 7.

9. an output processing unit that generates output information including the disease risk for each user, a risk group for the target disease, and a treatment history for the target disease; The health support system according to claim 8.

10. a prediction processing unit that predicts the disease risk of a target disease from the medical history information of a user based on the trained model, which is a trained model generated by performing machine learning using past medical history information of a plurality of people as training data, and which predicts the disease risk, which is the risk of onset and aggravation of a target disease that progresses without subjective symptoms, including at least one of osteoporosis and dementia; and an intervention processing unit that classifies the target disease into risk groups based on the disease risk predicted by the prediction processing unit, and executes an approach processing for reducing the disease risk for the user in accordance with the classified target disease risk group; Equipped with The medical history information is data generated in association with use of a medical institution, and includes at least the results of a medical examination; the learning data is supervised learning data including a diagnosis history of the target disease, The prediction processing unit predicts the disease risk of the target disease from medical history information of the user based on the trained model generated by performing machine learning using the supervised training data. Server device.

11. a prediction processing step in which a prediction processing unit predicts the disease risk of a target disease from the medical history information of a user based on the trained model, which is a trained model generated by performing machine learning using past medical history information of a plurality of people as learning data, and which predicts the disease risk, which is the risk of onset and aggravation of a target disease that progresses without noticeable symptoms, including at least one of osteoporosis and dementia; an intervention processing step in which an intervention processing unit classifies a risk group of the target disease based on the disease risk predicted by the prediction processing step, and executes an approach processing for reducing the disease risk for the user in accordance with the classified risk group of the target disease; Including, The medical history information is data generated in association with use of a medical institution, and includes at least the results of a medical examination; the learning data is supervised learning data including a diagnosis history of the target disease, In the prediction processing step, the prediction processing unit predicts the disease risk of the target disease from medical history information of the user based on the trained model generated by performing machine learning using the supervised training data. Health support methods.

12. On the computer, a prediction processing step of predicting the disease risk of a target disease from the medical history information of a user based on the trained model, which is a trained model generated by performing machine learning using past medical history information of a plurality of people as training data, and which predicts the disease risk, which is the risk of onset and aggravation of a target disease that progresses without subjective symptoms, including at least one of osteoporosis and dementia; an intervention processing step of classifying the target disease into risk groups based on the disease risk predicted by the prediction processing step, and executing an approach processing for reducing the disease risk on the user in accordance with the classified target disease risk group; It is a program for executing The medical history information is data generated in association with use of a medical institution, and includes at least the results of a medical examination; the learning data is supervised learning data including a diagnosis history of the target disease, In the prediction processing step, the disease risk of the target disease is predicted from medical history information of the user based on the trained model generated by performing machine learning using the supervised training data. program.

Images