Health checkup system, health checkup result processing program, and health checkup result processing method

Abstract

To provide a health check system that predicts a future risk of a subject using existing health check information without conducting special measurement and presents it in a way that helps the subject themselves assume their future image.SOLUTION: Provided is a health check system 101 for creating a report in which a predicted physical activity level and an action plan are correlated and presenting it to a subject, said system comprising an inspection information acquisition unit 3, a future prediction unit 4, an action plan creation unit 5, an action plan database 6, and a report creation unit 7. The inspection information acquisition unit 3 reads out the health diagnosis inspection result of prescribed items of the subject. The future prediction unit 4 predicts the physical activity level. The action plan creation unit 5 creates an action plan to be exercised by the subject based on a future prediction result obtained by the future prediction unit 4.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a system for presenting risk prediction results based on the medical examination results of a subject and countermeasures therefor. [Background technology]

[0002] With the rapid aging of the population in recent years, there is a social issue of an increasing number of elderly people who cannot walk independently due to disorders of the musculoskeletal system. For example, musculoskeletal function can decline due to aging-related muscle weakness, joint and spinal diseases, and osteoporosis, leading to the need for nursing care or becoming bedridden. In addition, there are known conditions such as locomotive syndrome (hereinafter referred to as locomo), which indicates a state of high risk of decline in musculoskeletal function, and sarcopenia, which indicates a state in which muscle mass decreases with age and muscle strength of the entire body decreases. In recent years, in order to prevent locomo and sarcopenia, risk estimation has been carried out by making combined use of bioinformation obtained from various measuring devices and information on each individual's lifestyle habits.

[0003] Patent Document 1 proposes a system that acquires the characteristics of a subject's posture (the coordinates of the head, neck, waist, and feet) and external factors (walking speed, stride length, stride width, and walking angle), and presents the subject with numerical values ​​regarding their risk of falling and risk of developing dementia. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-146435 A Summary of the Invention [Problem to be solved by the invention]

[0005] Patent Document 1 describes that the posture of the subject (the coordinates of the "head", "neck", "waist", and "feet") and external factors ("walking speed", "step length", "step width", and "walking angle") are collected during regular medical examinations, but does not describe a specific collection method. Therefore, it is presumed that special measurements must be performed during regular medical examinations, such as by taking a video of the subject while walking to extract the coordinates of the "head", "neck", "waist", and "feet" and to calculate the "walking speed", "step length", "step width", and "walking angle". Since such measurements are not performed during normal health checkups, if they are to be performed during normal health checkups, special measurement items must be newly added.

[0006] In addition, in order to prevent locomotive syndrome and sarcopenia, subjects need to be careful about their daily behavior and lifestyle habits, so it is important to clearly inform subjects of the risks of falling and dementia, and the actions they should take in their daily lives to avoid these risks (exercise, gymnastics, nutritional precautions, etc.), and to motivate them to take these actions. However, in the case of a system that expresses the results of risk prediction as numerical values, as in Patent Document 1, it is difficult for subjects to intuitively grasp the results, and they cannot receive information on the next action to be taken. Therefore, a technology is desired that utilizes the prediction results in daily life to improve the effect of reducing the risk of falling and becoming certified in the future.

[0007] An object of the present invention is to predict a subject's future risks using existing health checkup information without special measurements, and to present the results in a manner that allows the subject to easily imagine his or her own future. [Means for solving the problem]

[0008] In order to achieve the above object, the present invention provides a health checkup system having a test information acquisition unit that reads out test results of a predetermined item of a subject from a storage device storing the health checkup results, a future prediction unit that predicts the subject's future physical activity level, an action plan creation unit that creates an action plan to be taken by the subject, and a report creation unit that creates a report to be presented to the subject. The future prediction unit includes a learned learning model, inputs the test results of the predetermined items into the learning model, and receives the subject's future physical activity level predicted by the learning model. The action plan creation unit includes an action plan database in which a plurality of action plans are stored in advance for a plurality of physical activity levels, and selects an action plan corresponding to the subject's future physical activity level predicted by the future prediction unit. The report creation unit creates a report that displays the physical activity level predicted by the future prediction unit in correspondence with the action plan selected by the action plan creation unit. Effect of the Invention

[0009] According to the present invention, a subject's future can be predicted using test information from existing health checkups without special measurements, and the future image can be presented to the subject at an easily predictable level, namely, physical activity level. Furthermore, a specific action plan can be proposed to the subject, allowing the subject to intuitively grasp his or her own risks. [Brief description of the drawings]

[0010] [Figure 1] 1 is a functional block diagram of a health check system according to an embodiment of the present invention. [Diagram 2] 1 is a block diagram showing a hardware configuration of a health check system according to an embodiment of the present invention. [Diagram 3] 4 is a flowchart showing the process flow of the health check system of the first embodiment. [Figure 4] 4 is a flowchart showing the process flow of the health check system of the first embodiment. [Diagram 5] 4 is a flowchart showing the process flow of the health check system of the first embodiment. [Figure 6] 4 is a flowchart showing the process flow of the health check system of the first embodiment. [Figure 7] 4 is a flowchart showing the process flow of the health check system of the first embodiment. [Figure 8] FIG. 2 is an explanatory diagram of icons indicating physical activity levels used in a report of the health check system of the first embodiment. [Figure 9] 3 is an example of a table in an action plan database 6 of the health checkup system of embodiment 1. [Figure 10] FIG. 2 is an explanatory diagram showing an example of a report of the medical examination system of the first embodiment. [Figure 11] 10 is a flowchart showing the process flow of the health check system of the second embodiment. [Figure 12] 10 is a flowchart showing the process flow of the health check system of the second embodiment. [Figure 13] 10 is a flowchart showing the process flow of the health check system of the second embodiment. [Figure 14] 10 is a flowchart showing the process flow of the health check system of the second embodiment. [Figure 15] 10 is a flowchart showing the process flow of the health check system of the second embodiment. [Figure 16] FIG. 11 is an explanatory diagram showing an example of a prediction result of the spinal curvature prediction model of the health examination system of the embodiment 2. [Figure 17] FIG. 13 is an explanatory diagram of icons indicating the level of risk of developing locomotor syndrome used in a report of the health check system of embodiment 2. [Figure 18] 13 is an example of a table in an action plan database 6 of the health checkup system of embodiment 2. [Figure 19] FIG. 11 is an explanatory diagram showing an example of a report of the medical checkup system of the second embodiment. [Figure 20] 11 is a flowchart showing the process flow of the health check system of the third embodiment. [Figure 21] FIG. 13 is an explanatory diagram showing an example of a report of the medical checkup system of the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0012] Fig. 1 shows the functional configuration of a medical examination system 101 according to this embodiment. Fig. 2 shows the hardware configuration of the medical examination system 101.

[0013] As shown in FIG. 1 and FIG. 2, the health checkup system 101 of this embodiment is configured to include a future prediction and presentation system 1 and a risk prediction model learning system 2. As shown in FIG. 2, the future prediction and presentation system 1 and the risk prediction model learning system 2 are connected to an in-facility network 103, and are connected to a medical information storage 105 in which health checkup results are stored and a medical information system 104 that manages the same via the in-facility network 103. In addition, devices that perform tests for health checkup items, such as a blood and urine test device 125, and imaging devices such as an X-ray CT device 126, an MRI device, and an ultrasonic imaging device, are connected to the in-facility network 103. In addition, the health checkup system 101 is connected to a large-scale health checkup result database 121 in which past health checkup results of many subjects are accumulated, and a subject terminal 122 such as a smartphone, via an external network 120.

[0014] First, the functions of the future prediction and presentation system 1 and the risk prediction model learning system 2 will be described with reference to FIG.

[0015] The future prediction and presentation system 1 includes a test information acquisition unit 3, a future prediction unit 4, an action plan creation unit 5, an action plan database 6, and a report creation unit 7. The risk prediction model learning system 2 includes a learning data collection unit 8, a learning database 9, and a model learning unit 10.

[0016] In the future prediction and presentation system 1, the examination information acquisition unit 3 reads out examination results for specific items of the subject from the medical information storage 105 in which the medical examination results are stored, and inputs the examination results to the future prediction unit 4.

[0017] The future prediction unit 4 predicts at least the future physical activity level as a future risk prediction of the subject, using the trained learning model generated by the risk prediction model learning system 2. Specifically, the future prediction unit 4 inputs the test results of the predetermined items acquired by the test information acquisition unit 3 to the learning model, and receives the subject's future physical activity level, etc., predicted by the learning model.

[0018] The action plan creation unit 5 creates an action plan to be taken by the subject based on the future prediction result obtained by the future prediction unit 4. A plurality of action plans are stored in advance for each physical activity level in the action plan database 6. The action plan creation unit 5 selects an action plan from the action plan database 6 that corresponds to the subject's future physical activity level predicted by the future prediction unit 4.

[0019] That is, the report creation unit 7 creates a report to be presented to the subject. The report creation unit 7 generates and outputs a report in a predetermined format that displays the prediction results of the physical activity level, etc., predicted by the future prediction unit and the action plan selected by the action plan creation unit 5 in association with each other.

[0020] In the risk prediction model learning system 2, the learning data collection unit 8 collects test results of predetermined items of a large number of subjects and information (learning data) indicating the physical activity levels of these subjects from the large-scale health check result database 121, and stores the information in the learning database 9. The model learning unit 10 uses the information stored in the learning database 9 to learn the learning model and generate a trained learning model to be used by the future prediction unit 4.

[0021] The hardware configuration of the future prediction and presentation system 1 and the risk prediction model learning system 2 will be described with reference to FIG.

[0022] The future prediction and presentation system 1 and the risk prediction model learning system 2 comprise a CPU 106, a main memory 107, a storage device 108, a learning database 9, a communication device 115, a common bus 116, a display memory 109, a display device 110, a controller 111, a mouse 112, a keyboard 113, and a printing device 114.

[0023] The memory device 108 pre-stores a learning data collection program 123, a model learning program, a future prediction program 117, an action plan creation program 118, a report creation program 119, an operating system (OS), programs for device drives of peripheral devices, etc.

[0024] CPU 106 is connected to other components via common bus 116. CPU 106 reads out learning data collection program 123, model learning program, future prediction program 117, action plan creation program 118, and report creation program 119 from storage device 108, and executes them by expanding them in main memory 107, thereby realizing the functions of learning data collection unit 8, model learning unit 10, future prediction unit 4, action plan creation unit 5, and report creation unit 7 through software.

[0025] Further, the CPU 106 controls the operation of each of the components, namely, the main memory 107, the storage device 108, the display memory 109, the controller 111, the keyboard 113, the printer 114, and the communication device 115. The main memory 107 is used as a storage area for a control program, or as a work area when the program is executed. The display device 110 displays an image on the display device 110 based on data received from the display memory 109. The mouse 112 and the keyboard 113 are input devices for an operator. The controller 111 enables the operator to perform input operations using the mouse 112 by outputting a signal including the position of the mouse pointer of the mouse 112 to the CPU 106, for example. The printer 114 outputs a report. The communication device 115 is connected to the in-facility network 103 and the external network 120.

[0026] The medical information system 104 is an existing system such as an electronic medical record or image management system, and receives medical examination result data such as electronic medical record data, image data captured by an imaging device such as an X-ray CT scanner, and test result data from a blood / urine testing device, and stores it in the medical information storage 105.

[0027] [[Embodiment 1]] Next, the first embodiment of the present invention will be described with reference to the flowcharts of Figures 3 to 7 and Figures 8 to 10. Figure 8 shows icons for intuitively presenting a physical activity level in a report, and Figure 9 shows an example of a table stored in the action plan database 6. Figure 10 shows an example of a report.

[0028] First, the processing of the future prediction and presentation system 1 will be described with reference to FIG.

[0029] <<Step S1>> In step S1, the test information acquisition unit 3 acquires test information such as the subject's height, weight, BMI, blood test results, and urine test results from the medical information storage 105. The blood test results and urine test results use bone metabolism markers serum BAP, serum P1NP, serum NTX, serum CTX, serum TRACP-5b, serum ucOC, urinary DPD, urinary NTX, and urinary CTX (see "Guidelines for the Prevention and Treatment of Osteoporosis 2015 Edition"). Note that the items acquired by the test information acquisition unit 3 as test information are not limited to the above, and only some of the above items may be used as necessary, or other items may be added.

[0030] <<Step S2>> In step S2, the future prediction unit 4 performs future prediction using the test information acquired in step S1. In the first embodiment, the future physical activity level and accumulated cost of the subject are predicted. As for the physical activity level, as shown in Figs. 8 and 9, it is predicted whether the subject falls into one of four levels, namely "bedridden", "wheelchair", "needs a cane", and "ambulatory". As for the accumulated cost, it is predicted the accumulated cost of medical expenses and / or nursing care expenses required in the future of the subject. These will be described in detail later with reference to Fig. 4 etc.

[0031] <<Step S3>> In step S3, the action plan creation unit 5 creates a specific action plan for the subject based on the physical activity level and cumulative cost predicted in step S2 by the future prediction unit 4. The optimal action plan is obtained from the action plans stored in advance in the action plan database 6 in FIG.

[0032] In the action plan database 6, for example, as shown in Fig. 9, action plans are stored in advance in the form of a table or the like for each combination of accumulated cost and a plurality of physical activity levels. The action plan creation unit 5 selects an action plan by selecting from the table of Fig. 9 an action plan corresponding to a combination of the subject's future accumulated cost and physical activity level predicted by the future prediction unit 4. The action plan is a plan that recommends exercise and nutritional intake suitable for the subject in order to improve the future physical activity level and reduce the accumulated cost, and for example, walking for 30 minutes / day, radio calisthenics once / day, muscle training three times / week, etc. are set.

[0033] <<Step S4>> In step S4, the report creation unit 7 creates a report that displays the physical activity level and accumulated cost predicted by the future prediction unit 4 in steps S2 and S3 in correspondence with the action plan selected by the action plan creation unit 5.

[0034] An example of the report is shown in Figure 10. In the example in Figure 10, the physical activity level is displayed intuitively and easily as either "bedridden," "wheelchair bound," "needs a cane," or "walkable" using the icons and text shown in Figure 8. In addition, action plans corresponding to the physical activity level and accumulated costs are displayed as "recommended action plans." Furthermore, the results of blood and urine tests from the health check are also displayed.

[0035] This report may be output on paper by printing using a printer 114, or may be output by being sent as electronic data to a terminal (smartphone, tablet, PC, etc.) 122 owned by the subject.

[0036] <<Future predictions>> The detailed process of the future prediction in step S2 in FIG. 3 will be described with reference to FIG.

[0037] <Step S21> In step S21, the future prediction unit 4 uses the learning model for predicting a physical activity level generated by the risk prediction model learning system 2 to predict a physical activity level.

[0038] <Step S22> In step S22, the future prediction unit 4 uses the learning model for predicting accumulated costs generated by the risk prediction model learning system 2 to predict the accumulated costs.

[0039] <<Creating a learning model>> Here, a process of generating a learning model for predicting a physical activity level and a learning model for predicting an accumulated cost by the risk prediction model learning system 2 will be described with reference to Fig. 5. The learning model for predicting a physical activity level and the learning model for predicting an accumulated cost are generated by previously training a learning model such as a known neural network using a supervised learning method among machine learning algorithms.

[0040] <Step S201> First, in step S201, the learning data collection unit 8 collects, for a large number of people from the large-scale health check result database 121, the same test items as those acquired by the test information acquisition unit 3 in step S1 of Figure 3, predetermined data indicating the subject's physical condition in the future (e.g., 10 years from now), and predetermined data for calculating the actual medical costs and nursing care costs of the subject in the future (e.g., the period up to 10 years from the health check), and stores them in the learning database 9.

[0041] <Step S202> In step S202, the learning data collecting unit 8 processes the collected information into a format that can be used for learning. Specifically, the units of the values ​​of the test information are unified, and the values ​​are normalized.

[0042] In addition, the physical activity level is determined from predetermined data indicating the subject's future physical condition (for example, 10 years from now), and the process of classifying the subject into four levels - bedridden, wheelchair-bound, needing a cane, or ambulatory - is performed based on predetermined calculations.

[0043] Furthermore, the amounts of medical expenses and nursing care expenses that the subject will actually incur in the future (for example, for a period up to 10 years after the health check) are calculated based on predetermined formulas, etc., from predetermined data for calculating the medical expenses and nursing care expenses that the subject will actually incur in the future (for example, for a period up to 10 years after the health check).

[0044] <Step S203> In step S203, the model learning unit 10 generates a physical activity prediction model. A classification algorithm among existing supervised machine learning is used to learn the physical activity prediction model. Specifically, the model learning unit 10 uses the test item data collected in step S201 as input data for the learning model, and learns using the physical activity level (either bedridden, wheelchair, needing a cane, or walkable) obtained in step S202 as correct answer data, and constructs a model so that when the test item data is input, the correct physical activity level (either bedridden, wheelchair, needing a cane, or walkable) is output.

[0045] <Step S204> In step S204, the model learning unit 10 generates a cumulative cost prediction model. To learn the cumulative cost prediction model, a regression algorithm from existing supervised learning is used. Specifically, the model learning unit 10 uses the test item data collected in step S201 as input data for the learning model, and learns using the medical expenses and nursing care expenses amounts calculated in step S202 as correct answer data, and constructs a model so that when the test item data is input, the correct medical expenses and nursing care expenses amounts are output.

[0046] <<<Prediction of physical activity level>>> Next, the physical activity level prediction by the future prediction unit 4 in step S21 of FIG. 4 will be described in detail with reference to FIG.

[0047] (Step S211) In step S211, the future prediction unit 4 reads the physical activity level prediction model that has been trained in step S203 of FIG.

[0048] (Step S212) In step S212, the future prediction unit 4 inputs the data on the examination items of the subject acquired by the examination information acquisition unit 3 in step S1 of FIG. 3 into the physical activity level prediction model.

[0049] (Step S212) In step S213, the future prediction unit 4 receives the physical activity level (either bedridden, wheelchair bound, needing a cane, or ambulatory) output by the physical activity level prediction model, and outputs it as a prediction result.

[0050] <<<Cumulative cost forecast>>> The cumulative cost prediction by the future prediction unit 4 in step S22 of FIG. 4 will be described in detail with reference to FIG.

[0051] (Step S221) In step S221, the future prediction unit 4 reads the accumulated cost prediction model that has been trained in step S204 of FIG.

[0052] (Step S222) In step S222, the subject's examination information is input to the model.

[0053] (Step S223) In step S223, the future prediction unit 4 outputs the amount of the accumulated costs (medical expenses, nursing care expenses) output by the accumulated cost prediction model.

[0054] As described above, the health check system of the first embodiment presents the subject's future image, such as the physical activity level and cumulative cost, in a manner that is easy for the subject to imagine, and also proposes a specific action plan for improving the physical activity level and reducing the cumulative cost. This allows the subject to intuitively grasp the risk, which leads to increased motivation for the subject to execute the action plan.

[0055] [[Embodiment 2]] Next, the second embodiment will be described with reference to the flowcharts of Figs. 11 to 15 and Figs. 16 to 19. Fig. 16 shows an image of the vertebral region and spinal curvature line predicted by the future prediction unit 4. Fig. 17 shows an icon for intuitively presenting the level of risk of developing locomotion syndrome in a report. Fig. 18 is an example of a table showing the correspondence between the risk of developing locomotion syndrome (hereinafter referred to as locomotion risk) and the action plan stored in the action plan database 6. Fig. 19 shows an example of a report.

[0056] In the medical examination system 101 of the second embodiment, the examination results of a predetermined item of the subject that the examination information acquisition unit 3 reads from the medical information storage 105 include a two-dimensional or three-dimensional image of a predetermined area of ​​the subject. The examination information acquisition unit 3 calculates feature quantities of a predetermined configuration of the internal organs and / or tissues that make up the subject from the acquired images. The future prediction unit 4 predicts whether the physical activity level falls into one of four levels, "bedridden," "wheelchair-bound," "needs a cane," or "ambulatory," and also predicts the shape of the future spinal curvature and one of multiple predetermined levels of risk of developing locomo. A specific description will be given below.

[0057] First, the processing of the future prediction and presentation system 1 will be described with reference to FIG.

[0058] <<Step S11>> 11, the examination information acquisition unit 3 acquires an X-ray CT image of a predetermined range (for example, from the clavicle to the hip joint) including the chest and abdomen captured in a chest CT examination of the subject from the medical information storage 105. Note that, although an example of acquiring an X-ray CT image will be described here, any two-dimensional or three-dimensional image of the subject may be used, and an MRI image or an ultrasound image may also be used.

[0059] <<Step S12>> In step S12, the examination information acquisition unit 3 extracts at least one of the vertebral body region, the subject's muscle at a predetermined position, and the subject's fat region at a predetermined position in two or three dimensions using the image acquired in step S11. Here, the examination information acquisition unit 3 extracts the vertebral body region and automatically extracts the muscle and fat region (three-dimensional data) at the navel position. A known calculation method using machine learning or the like is used for the extraction.

[0060] <<Step S13>> In step S13, the examination information acquisition unit 3 determines whether or not the automatic extraction result in step S12 needs to be corrected. Specific examples of when correction is necessary include a case where the subject's vertebral body has a different shape or bone quality from normal due to osteoporosis or the like and is not automatically extracted as a vertebral body region, or a case where the subject has a small muscle mass and the muscle is not extracted or is erroneously extracted, etc.

[0061] <<Step S14>> If it is determined in step S13 that correction is necessary, the examination information acquiring unit 3 displays a message in step S14 prompting the operator to manually correct the extracted region, and accepts manual correction by the operator.

[0062] <<Step S15>> In step S15, the examination information acquisition unit 3 calculates the bone mineral density (BMD) of each vertebra using the three-dimensional data of the vertebral region extracted in step S12. The existing quantitative CT method (Quantitative Computer Tomography) is used to measure the BMD value. From the BMD value, the Young Adult Mean (YAM), which is the osteoporosis diagnostic standard, is calculated. The YAM is calculated as a percentage compared to the subject's BMD value, with the average BMD value (reference value) for young people set at 100%.

[0063] Furthermore, the examination information acquiring unit 3 calculates the current spinal curvature line from the three-dimensional data of the vertebral body region extracted in step S12, and creates an image depicting the vertebral body region and the curvature line.

[0064] <<Step S16>> In step S16, the examination information acquisition unit 3 extracts at least one CT value from the X-ray CT image from the vertebral body region, the subject's muscle at a predetermined position, and the subject's fat region at a predetermined position. That is, the examination information acquisition unit 3 calculates the areas of visceral fat and subcutaneous fat, the areas of erector spinae and psoas major muscles, and the average CT value using the muscle and fat region extracted in step S12. The CT value is a value expressed as a relative value to the origin water of the X-ray absorption value of a material photographed by CT under conditions where water is set to 0 and air is set to -1000.

[0065] <<Step S17>> In step S17, the test information acquisition unit 3 acquires predetermined test information such as the subject's height, weight, BMI, blood test results, and urine test results from the medical information storage 105. As blood test results and urine test results, bone metabolism markers such as serum BAP, serum P1NP, serum NTX, serum CTX, serum TRACP-5b, serum ucOC, urinary DPD, urinary NTX, and urinary CTX are used (see "Guidelines for the Prevention and Treatment of Osteoporosis 2015 Edition"). Note that the items acquired by the test information acquisition unit 3 as test information are not limited to the above, and only some of the above items may be used as necessary, or other items may be added.

[0066] <<Step S18>> In step S18, the future prediction unit 4 performs future prediction using the information calculated in steps S15 and S16 and the examination information acquired in step S17. Here, the future prediction unit 4 predicts whether the physical activity level will fall into one of four levels, "bedridden," "wheelchair-bound," "needs a cane," or "ambulatory," and also predicts the shape of the future spinal curvature and one of several predetermined levels of risk of developing locomotor syndrome. These will be described in detail later using FIG. 12, etc.

[0067] <<Step S19>> In step S19, the action plan creation unit 5 creates a specific action plan for the subject based on the results of the prediction made in step S18. The action plan database 6 prestores action plans corresponding to multiple levels of risk of developing locomo as shown in Fig. 18, and action plans corresponding to combinations of accumulated costs and multiple physical activity levels as shown in Fig. 9 of the first embodiment.

[0068] The action plan creation unit 5 selects an action plan corresponding to the subject's future risk level of developing sarcopenia predicted by the future prediction unit 4, and an action plan corresponding to the combination of accumulated cost and physical activity level, from Figures 18 and 9, respectively.

[0069] <<Step S20>> In step S20, a report is created that displays the risk of developing sarcopenia, the future shape of the spinal curvature, the physical activity level, and the accumulated cost predicted by the future prediction unit 4 in steps S18 and S19, in correspondence with the action plan selected by the action plan creation unit 5.

[0070] FIG. 19 shows an example of the report. In the example of FIG. 10, the risk of developing locomotor syndrome is displayed intuitively and easily by the icons and characters shown in FIG. 17. The future shape of the spine curvature is displayed clearly by an image. As in the first embodiment, the physical activity level is displayed intuitively and easily as either "bedridden", "wheelchair", "needs a cane", or "walkable" by the icons and characters shown in FIG. 8. In addition, an action plan corresponding to the physical activity level and the accumulated cost is displayed as a "recommended action plan". In addition, an image showing the current shape of the spine curvature used in the prediction, bone density, fat and muscle areas, and the YAM value of the diagnostic criteria for osteoporosis are also displayed.

[0071] <<Future predictions>> Here, the future prediction in step S18 in FIG. 11 will be described in detail with reference to FIG.

[0072] <Steps S181 to S184> The future prediction unit 4 performs spinal curvature prediction in step S181, locomotor syndrome development risk prediction in step S182, physical activity level prediction in step S183, and accumulated cost prediction in step S184, each using the learning model generated by the risk prediction model learning system 2.

[0073] <<Creating a learning model>> Here, the process of generating a learning model by the risk prediction model learning system 2 will be described.

[0074] The process of generating the learning model for predicting a physical activity level used in step S183 and the learning model for predicting a cumulative cost used in step S184 is similar to the process in FIG. 5 in the first embodiment, and therefore a description thereof will be omitted.

[0075] A method for learning the learning model for predicting spinal curvature used in step S181 and the learning model for predicting the risk of developing locomotive syndrome used in step S182 will be described with reference to FIG.

[0076] <<Step S1801>> First, in step S1801, the learning data collection unit 8 collects the same items as the images of the vertebral body, muscle, and fat area acquired by the examination information acquisition unit 3 in step S12 of FIG. 11, the vertebral body information acquired in step S15, the muscle and fat information acquired in step S16, and the examination information acquired in step S17 for a large number of people from the large-scale health check result database 121, and stores them in a learning database.

[0077] In addition, the learning data collection unit 8 collects information from the large-scale health checkup result database 121 that can extract the spinal curvature state from the subject's future (e.g., 10 years from now) health checkup data, and predetermined information that can determine whether the subject has developed locomotive syndrome, and stores this in the learning database 9.

[0078] <<Step S1802>> In step S1802, the learning data collecting unit 8 processes the collected information into a format that can be used for learning. Specifically, the units of values ​​of the examination information are unified, and the values ​​are normalized. If the information acquired in step S1801 is an X-ray CT image, the vertebral body, muscle, and fat regions are extracted, and vertebral body information is calculated by the same process as that performed by the examination information acquiring unit 3 in steps S16 and S17.

[0079] Also, the system generates a spinal curvature shape from predetermined data that indicates the subject's future (e.g., 10 years from now) spinal curvature state. Furthermore, the system determines whether the future subject will develop locomotive syndrome and the risk of developing it, and classifies the risk into four levels of locomotive syndrome development: very high, high, low, and very low, based on a predetermined calculation.

[0080] <<Step S1803>> In step S1803, the model learning unit 10 generates a spinal curvature prediction model. For learning the spinal curvature prediction model, a machine learning algorithm for image generation is used among existing supervised learning. Specifically, the model learning unit 10 uses the image of the vertebral region, vertebral information, muscle and fat information, and examination information collected in step S1802 as input data for the learning model, and uses the vertebral region and spinal curvature line in the future (for example, 10 years from now) as correct answer data for learning. As a result, when the image of the vertebral region of the subject, vertebral information, muscle and fat information, and examination information are input, a vertebral curvature prediction model is constructed that outputs the vertebral region and spinal curvature line of the subject in 10 years from now. FIG. 16 shows an example of the vertebral region and spinal curvature line to be output.

[0081] <<Step S1804>> In step S1804, model learning unit 10 generates a locomo onset risk prediction model. For learning the locomo onset risk prediction model, a machine learning algorithm for classification is used among existing supervised learning. Specifically, model learning unit 10 uses the vertebral body information, muscle and fat information, and examination information collected in step S1802 as input data for the learning model, and causes learning using the four-stage level of locomo onset risk in the future (for example, 10 years from now) calculated in step S1802 (see FIG. 17) as correct answer data. In this way, a locomo onset risk prediction model is constructed that outputs the level of the subject's locomo onset risk in 10 years from now when an image of the vertebral body region of the subject, vertebral body information, muscle and fat information, and examination information are input.

[0082] <<<Prediction of spinal curvature>>> Next, the spinal curvature prediction by the future prediction unit 4 in step S181 of FIG. 12 will be described in detail with reference to FIG.

[0083] (Step S1811) In step S1811, the future prediction unit 4 reads the spinal curvature prediction model that has been trained in step S1803 of FIG.

[0084] (Step S1812) In step S1812, the future prediction unit 4 inputs the vertebral body image, vertebral body information, muscle and fat information, and examination information of the subject acquired by the examination information acquisition unit 3 in steps S15 to S17 of FIG. 11 into the spinal curvature prediction model.

[0085] (Step S1813) In step S1813, the future prediction unit 4 receives and outputs the prediction results of the future vertebral regions and spinal curvature lines of the subject predicted by the spinal curvature model.

[0086] <<<Predicting the risk of developing locomotor syndrome>>> Next, the locomotive syndrome development risk prediction by the future prediction section 4 in step S182 of FIG. 12 will be described in detail with reference to FIG.

[0087] (Step S1821) In step S1821, future prediction unit 4 reads the locomotive syndrome development risk prediction model that has been trained in step S1804 of FIG.

[0088] (Step S1822) In step S1822, future prediction section 4 inputs the vertebral body information, muscle and fat information, and examination information of the subject acquired by examination information acquisition section 3 in steps S15 to S17 of FIG. 11 into the locomotive syndrome development risk prediction model.

[0089] (Step S1823) In step S1823, future prediction section 4 receives and outputs the prediction result of the locomotive syndrome development risk level (FIG. 17) output by the locomotive syndrome development risk prediction model.

[0090] The prediction of the physical activity level and the cumulative cost in steps S183 and S184 in FIG. 12 are similar to those in the first embodiment, and therefore the description thereof will be omitted.

[0091] According to the above-mentioned embodiment 2, by using existing images taken by chest CT examination, future risks can be estimated at the time of medical examination without special measurements. In addition, risks related to muscles and bones, which are important elements of the locomotor system, can be estimated at the same time.

[0092] Although the above describes an example in which chest and abdominal images taken in a chest CT examination are used, images of each body part taken in a whole-body CT examination can also be used. In this case, for example, muscle and bone information according to the body part, such as the upper body and the lower body, can be obtained, and future predictions (for example, 10 years from now) can be presented for each body part. Based on this, it becomes possible to create an action plan according to the differences depending on the body part. This improves the accuracy of the action plan presented to the subject, and further improves the effectiveness of preventing locomotive syndrome for the subject.

[0093] In this embodiment, the examination information acquisition unit 3 is configured to calculate the features of internal organs and structures from images of the subject, but it may also be configured to have an external computing device calculate the features and receive the calculation results.

[0094] [[Embodiment 3]] Next, the medical examination system of the third embodiment will be described with reference to the flow chart of FIG. 20 and the report diagram of FIG.

[0095] In the third embodiment, the future prediction unit 4 is configured to store the predicted physical activity level, etc. of the subject in a connected storage unit (e.g., the medical information storage 105, etc.). Thus, after predicting the physical activity level, etc. based on the current medical checkup result, the future prediction unit 4 reads out the predicted result calculated for the same subject based on the previous medical checkup result from the connected storage unit, calculates the difference between the current and previous physical activity levels and the accumulated cost, and outputs it to the report creation unit.

[0096] <<Step S31>> In step S31 of FIG. 20, the future prediction unit 4 reads the prediction results of the previous physical activity level and accumulated cost of the subject from a storage unit (for example, the medical information storage 105, etc.).

[0097] <<Step S32>> In step S32, the future prediction unit 4 acquires test information such as the subject's current height, weight, BMI, blood test results, and urine test results, similar to step S1 in FIG. 3 of the first embodiment.

[0098] <<Step S33>> In step S33, the future prediction unit 4 uses the examination information acquired in step S32 to perform future prediction of the physical activity level and the accumulated cost in the same manner as in step S2 of FIG. 3 in the first embodiment.

[0099] <<Step S34>> In step S34, the future prediction unit 4 calculates the difference between the accumulated cost obtained in the future prediction in step S33 and the accumulated cost obtained from the past accumulated cost acquired in step S31.

[0100] <<Step S35>> In step S35, the action plan creation unit 5 creates a specific action plan for the subject from the physical activity level and accumulated cost predicted in step S32, similarly to step S3 in FIG. 3 of the first embodiment.

[0101] <<Step S36>> In step S36, the report creation unit creates a report as shown in Fig. 21, which clearly shows the changes by comparing the current risk prediction result with the previous risk prediction result. In Fig. 21, the physical activity levels are shown compared between the previous and current levels, and the accumulated costs are shown compared, with the difference between them also being displayed.

[0102] According to the third embodiment, risk prediction is performed again after a certain period of time, and changes over time from the previous time are presented, which is expected to encourage the subject to take proactive preventive measures and thereby reduce risk. Although the first to third embodiments of the present invention have been described above, the present invention is not limited to these. [Explanation of symbols]

[0103] 1 presentation system, 2 risk prediction model learning system, 3 examination information acquisition unit, 4 future prediction unit, 5 action plan creation unit, 6 action plan database, 7 report creation unit, 8 learning data collection unit, 9 learning database, 10 model learning unit, 101 health check system, 103 facility network, 104 medical information system, 105 medical information storage, 107 main memory, 108 storage device, 109 display memory, 110 display device, 111 controller, 112 mouse, 113 keyboard, 114 printing device, 115 communication device, 116 common bus, 117 future prediction program, 118 action plan creation program, 119 report creation program, 120 external network, 121 large-scale health check result database, 122 subject terminal, 123 learning data collection program, 125 urine test device, 126 X-ray CT device

Claims

1. a test information acquisition unit that reads out test results of predetermined items of a subject from a storage device in which the medical examination results are stored; A future prediction unit that predicts a future physical activity level of the subject; an action plan creation unit that creates an action plan to be taken by the subject; A report creation unit that creates a report to be presented to the subject, the future prediction unit includes a trained learning model, inputs the test results of the predetermined items into the learning model, and receives the future physical activity level of the subject predicted by the learning model; the action plan creation unit includes an action plan database in which a plurality of action plans are stored in advance for each of the plurality of physical activity levels, and selects an action plan corresponding to the subject's future physical activity level predicted by the future prediction unit; A health checkup system characterized in that the report creation unit creates a report that displays the physical activity level predicted by the future prediction unit in correspondence with the action plan selected by the action plan creation unit.

2. The health examination system according to claim 1, the test information acquisition unit reads out a blood test result and / or a urine test result as a test result for the predetermined item of the subject, The health checkup system is characterized in that the future prediction unit predicts which of four levels the physical activity level will be, namely, "bedridden," "wheelchair-bound," "requires a cane," or "ambulatory."

3. 3. The health checkup system according to claim 2, wherein the future prediction unit predicts a cumulative cost of medical expenses and / or nursing care expenses required in the future of the subject.

4. 4. The health checkup system according to claim 3, wherein the action plan database prestores an action plan for each combination of the accumulated cost and a plurality of the physical activity levels, A health checkup system characterized in that the action plan creation unit selects an action plan corresponding to a combination of the subject's future accumulated cost and physical activity level predicted by the future prediction unit.

5. The medical examination system according to claim 2, The test results of the predetermined items of the subject that are read out by the test information acquisition unit from the storage device include a two-dimensional or three-dimensional image of a predetermined area of ​​the subject, the examination information acquisition unit calculates a feature amount of a predetermined configuration of the internal organs and / or tissues constituting the subject from the image, or causes an external calculation device to calculate the feature amount, and receives the calculation result; The health checkup system is characterized in that the future prediction unit predicts whether the physical activity level falls into one of the four levels of "bedridden," "wheelchair-bound," "requires a cane," or "ambulatory," as well as predicting the future shape of the spinal curvature and / or the risk of developing locomotive syndrome into one of several predetermined levels.

6. The medical examination system according to claim 5, The future prediction unit predicts a cumulative cost of medical expenses and / or nursing care expenses required in the future of the subject, The action plan database stores in advance action plans corresponding to a plurality of levels of the locomotive syndrome onset risk and action plans corresponding to combinations of the accumulated cost and a plurality of the physical activity levels; The health checkup system is characterized in that the action plan creation unit selects an action plan that corresponds to the level of the subject's future risk of developing locomotive syndrome predicted by the future prediction unit, and an action plan that corresponds to a combination of the accumulated cost and the physical activity level.

7. 6. The health checkup system according to claim 5, wherein the examination information acquisition unit extracts at least one of a vertebral region, a muscle of the subject at a predetermined position, and a fat region of the subject at a predetermined position from the image in two dimensions or three dimensions.

8. 8. The health checkup system according to claim 7, wherein the previous image is an X-ray CT image, and the examination information acquisition unit extracts from the X-ray CT image at least one CT value of a vertebral region, a muscle of the subject at a predetermined position, and a fat region of the subject at a predetermined position.

9. 2. The health checkup system according to claim 1, wherein the future prediction unit stores the predicted physical activity level for the subject in a connected memory unit, predicts the physical activity level based on the results of the current health checkup, and then reads out from the connected memory unit the physical activity level calculated for the same subject based on the results of a previous health checkup, calculates the difference between the current and previous physical activity levels, and outputs the result to the report creation unit.

10. On the computer, A first step of reading out test results of a predetermined item of a subject from a storage device in which the health examination results are stored; A second step of predicting a future physical activity level of the subject. A third step of creating an action plan for the subject to take; and a fourth step of creating a report to be presented to the subject. In the second step, the test results of the predetermined items are input into a trained learning model, and a future physical activity level of the subject predicted by the learning model is received; In the third step, an action plan corresponding to the predicted future physical activity level of the subject is selected from an action plan database in which a plurality of action plans are stored for each of the plurality of physical activity levels, A health check result processing program characterized in that in the fourth step, a report is created that displays the physical activity level predicted in the second step in correspondence with the action plan selected in the third step.

11. A first step of reading out test results of a predetermined item of a subject from a storage device in which the health examination results are stored; A second step of predicting a future physical activity level of the subject. A third step of creating an action plan for the subject to take; A fourth step of creating a report to be presented to the subject, In the second step, the test results of the predetermined items are input into a trained learning model, and a future physical activity level of the subject predicted by the learning model is received; In the third step, an action plan corresponding to the predicted future physical activity level of the subject is selected from an action plan database in which a plurality of action plans are stored for each of the plurality of physical activity levels, A health check result processing method characterized in that in the fourth step, a report is created that displays the physical activity level predicted in the second step in correspondence with the action plan selected in the third step.

Images