Health management system and health management method

Abstract

A health management system (100) comprises: an acquisition unit (31) that acquires an electrocardiogram signal of a user which was measured using an electrode of a toilet seat device (10); an analysis unit (34) that calculates an RR interval with respect to a section of part of the acquired electrocardiogram signal, said analysis unit (34) changing the section and calculating a plurality of RR intervals; a 3H risk estimation unit (35) that, on the basis of the plurality of calculated RR intervals, calculates a plurality of 3H risk estimation values, each of which is an estimation value of the risk that the user has at least one of hypertension, hyperglycemia, and hyperlipidemia; and a blood vessel adjustment degree estimation unit (37) that, on the basis of the plurality of calculated 3H risk estimation values, estimates a blood vessel adjustment degree which indicates a heart rate adjustment function by blood vessel contraction, and that outputs information for a presentation relating to the estimated blood vessel adjustment degree.

Description

Technical Field

[0001] The present invention relates to a health management system.

Background Art

[0002] Various techniques related to health management have been proposed. Patent Document 1 discloses a system that collects biological information according to the user's life behavior and optimally uses the data for health diagnosis, health management, etc.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present invention provides a health management system or the like that can present information related to health risks.

Means for Solving the Problems

[0005] A health management system according to an aspect of the present invention includes an acquisition unit that acquires an electrocardiogram signal of a user measured using the electrodes by a toilet seat device including the electrodes, and an analysis unit that calculates an RR interval for a part of an interval of the acquired electrocardiogram signal, the analysis unit calculating the RR interval for a plurality of times by changing the interval, and an estimation unit that calculates a plurality of 3H risk estimation values, which are estimated values of risks corresponding to at least one of hypertension, hyperglycemia, and hyperlipidemia for the user, based on the calculated RR intervals for a plurality of times. The estimation unit estimates a vascular regulation degree indicating a heart rate adjustment function due to vasoconstriction based on the calculated plurality of 3H risk estimation values, and outputs information for presenting information related to the estimated vascular regulation degree.

[0006] A health management method according to an aspect of the present invention is a health management method executed by a computer, comprising: a first acquisition step of acquiring an electrocardiogram signal of a user measured using electrodes by a toilet seat device provided with the electrodes; an analysis step of calculating an RR interval for a part of the acquired electrocardiogram signal, the analysis step of calculating RR intervals for a plurality of times by changing the interval; a first estimation step of calculating a plurality of 3H risk estimation values, which are estimation values of risks corresponding to at least one of hypertension, hyperglycemia, and hyperlipidemia, based on the calculated RR intervals for a plurality of times; a second estimation step of estimating a vascular regulation degree indicating a heart rate adjustment function due to blood vessel constriction based on the calculated plurality of 3H risk estimation values; and a first output step of outputting information for presenting a presentation regarding the estimated vascular regulation degree.

[0007] A program according to an aspect of the present invention is a program for causing a computer to execute the health management method.

Effects of the Invention

[0008] The health management system and the like of the present invention can present information regarding health risks.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

MODE FOR CARRYING OUT THE INVENTION

[0010] Hereinafter, embodiments will be specifically described with reference to the drawings. Note that each of the embodiments described below shows general or specific examples. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, etc. shown in the following embodiments are merely examples and are not intended to limit the present invention. In addition, among the components in the following embodiments, components not described in the independent claims are described as optional components.

[0011] Note that each figure is a schematic diagram and is not necessarily drawn precisely. Also, in each figure, substantially the same configuration is denoted by the same reference numeral, and duplicate explanations may be omitted or simplified.

[0012] (Embodiment 1) [Configuration] Hereinafter, the configuration of the health management system according to Embodiment 1 will be described. FIG. 1 is a diagram showing the configuration of the health management system according to Embodiment 1. The health management system 100 is a system that can simply estimate the 3H risk, etc. of a user based on an electrocardiogram signal (ECG Signal: Electrocardiogram Signal) measured while the user (person) is sitting on the toilet seat device 10, and display the estimation result on the information terminal 40. The 3H risk comprehensively defines the risk that the user corresponds to at least one of hypertension, hyperglycemia, and hyperlipidemia (dyslipidemia). The 3H risk estimation value is useful as an indicator (guideline) for whether the user has a tendency to develop lifestyle-related diseases.

[0013] As shown in FIG. 1, the health management system 100 includes a toilet seat device 10, a server device 30, and an information terminal 40. First, the toilet seat device 10 will be described with reference to FIG. 2 in addition to FIG. 1. FIG. 2 is an external view of the toilet seat device 10. The toilet seat device 10 measures the electrocardiogram signal of the user sitting on the toilet seat device 10. The user can unconsciously receive the measurement of the electrocardiogram signal just by sitting on the toilet seat device 10. Here, the electrocardiogram signal refers to an electrical signal from the heart.

[0014] As shown in FIG. 2, the toilet seat device 10 includes, for example, a toilet seat 20, a first electrode 21, a second electrode 22, and a body earth electrode 23. The toilet seat device 10 may be a device that is replaced with a toilet seat attached to an existing toilet and attached to the existing toilet, or may be a device integrally formed with the toilet.

[0015] The toilet seat 20 is a portion of the toilet seat device 10 on which the user sits when using it. The toilet seat 20 is a member formed of a white resin material and also functions as a holding member for holding other components. The first electrode 21, the second electrode 22, and the body earth electrode 23 are provided on the surface of the toilet seat 20.

[0016] The first electrode 21 is an electrode provided on the surface of the toilet seat 20 and functions as a measurement electrode for measuring an electrocardiogram signal. Specifically, the first electrode 21 is formed of a metal material such as silver. Preferably, the first electrode 21 is a silver-silver chloride electrode. As shown in FIG. 2, the first electrode 21 is provided at a portion of the toilet seat 20 where the left thigh of the user sitting on the toilet seat 20 is located and contacts the left thigh.

[0017] The second electrode 22 is an electrode provided on the surface of the toilet seat 20 and functions as a reference electrode for measuring an electrocardiogram signal. Specifically, the second electrode 22 is formed of a metal material such as silver. Preferably, the second electrode 22 is a silver-silver chloride electrode. As shown in FIG. 2, the second electrode 22 is provided at a portion of the toilet seat 20 where the right thigh of the user sitting on the toilet seat 20 is located and contacts the right thigh.

[0018] The body earth electrode 23 is an electrode for applying the body earth potential to the user sitting on the toilet seat 20. At least a part of the body earth electrode 23 is provided on the surface of the toilet seat 20 and contacts the right thigh of the user sitting on the toilet seat 20. The body earth electrode 23 is formed of a metal material such as silver, for example. Preferably, the body earth electrode 23 is a silver-silver chloride electrode.

[0019] In the example of FIG. 2, the first electrode 21, the second electrode 22, and the body earth electrode 23 are provided on the toilet seat 20. However, when the toilet seat device 10 is provided with a handrail, the first electrode 21, the second electrode 22, and the body earth electrode 23 may be provided on the handrail. FIG. 3 is an external view of the toilet seat device 10 in which the first electrode 21, the second electrode 22, and the body earth electrode 23 are provided on the handrail.

[0020] Next, the server device 30 in FIG. 1 will be described. The server device 30 is a cloud server that estimates the 3H risk etc. of the user based on the electrocardiogram signal of the user measured by the toilet seat device 10.

[0021] The server device 30 can acquire (receive) the electrocardiogram signal measured by the toilet seat device 10 from the toilet seat device 10 by communicating via a wide-area communication network such as the Internet. Further, the server device 30 can acquire (receive) the user's attribute information input to the information terminal 40 and output (transmit) the presentation information to the information terminal 40 by communicating via a wide-area communication network such as the Internet. Note that the presentation information is information for presenting (visualizing) the determination result of the 3H risk and various estimation results described later to the user.

[0022] Specifically, the server device 30 includes an acquisition unit 31, a preprocessing unit 32, a storage unit 33, an analysis unit 34, a 3H risk estimation unit 35, a determination unit 36, and a blood vessel regulation degree estimation unit 37. Each of the acquisition unit 31, the preprocessing unit 32, the analysis unit 34, the 3H risk estimation unit 35, the determination unit 36, and the blood vessel regulation degree estimation unit 37 is a functional component realized by one or a plurality of processors (hardware) included in the server device 30 executing a computer program (software) stored in a memory such as the storage unit 33.

[0023] The acquisition unit 31 acquires the electrocardiogram signal of the user measured by the toilet seat device 10 using the first electrode 21, the second electrode 22, and the body earth electrode 23. Further, the acquisition unit 31 acquires the user's attribute information. The attribute information includes, for example, information indicating the user's gender, the user's height, and the user's weight. Note that the attribute information may include the value of BMI (Body Mass Index: BMI = weight [kg] / (height [m])^2) instead of the information indicating the user's height and the user's weight.

[0024] The preprocessing unit 32 performs preprocessing on the electrocardiogram signal acquired by the acquisition unit 31. The preprocessing includes processing for restricting the frequency band of the electrocardiogram signal, processing for excluding a period during which the amplitude of the electrocardiogram signal becomes equal to or greater than a predetermined value, and processing for dividing the electrocardiogram signal into predetermined time units and storing it in the storage unit 33.

[0025] In the memory unit 33, the electrocardiogram signals are stored by the preprocessing unit 32 at predetermined time intervals. Specifically, the memory unit 33 is implemented by an HDD (Hard Disk Drive) or a semiconductor memory.

[0026] The analysis unit 34 reads out from the memory unit 33 the electrocardiogram signals acquired by the acquisition unit 31 and preprocessed by the preprocessing unit 32, and calculates the RR intervals from the read electrocardiogram signals. The RR interval is the interval from one QRS wave to the next QRS wave in the waveform of the electrocardiogram signal. The analysis unit 34 calculates the RR intervals for a partial section of the electrocardiogram signal, and when the 3H risk estimation values are calculated for multiple times, the above section is changed to calculate the RR intervals for multiple times.

[0027] The 3H risk estimation unit 35 calculates multiple 3H risk estimation values, which are the estimation values of the risk that the user corresponds to at least one of hypertension, hyperglycemia, and hyperlipidemia, based on the calculated RR intervals for multiple times. More specifically, the 3H risk estimation unit 35 calculates multiple 3H risk estimation values based on the calculated RR intervals for multiple times and the attribute information acquired by the acquisition unit 31, but it is not essential that the attribute information be used.

[0028] The determination unit 36 determines whether the user has a 3H risk based on the multiple 3H risk estimation values calculated by the 3H risk estimation unit 35. The determination unit 36 defines the maximum value of the calculated multiple 3H risk estimation values as the representative estimation value. The determination unit 36 determines that the user has a 3H risk when the representative estimation value is greater than the threshold value, and determines that the user does not have a 3H risk when the representative estimation value is less than or equal to the threshold value. In addition, the determination unit 36 outputs information (hereinafter also referred to as presentation information) for presenting the determination result of the presence or absence of the 3H risk.

[0029] The blood vessel regulation degree estimation unit 37 estimates the user's blood vessel regulation degree based on the 3H risk estimation values for multiple times calculated by the 3H risk estimation unit 35. Specifically, the blood vessel regulation degree estimation unit 37 estimates the user's blood vessel regulation degree based on the difference between the maximum value and the minimum value of the 3H risk estimation values for multiple times. In addition, the blood vessel regulation degree estimation unit 37 outputs information (hereinafter also referred to as presentation information) for presenting the estimated blood vessel regulation degree.

[0030] Next, the information terminal 40 will be described. The information terminal 40 receives the presentation information from the server device 30 and displays the content of the received presentation information on the display unit 41. The information terminal 40 is, for example, a portable information terminal such as a smartphone or a tablet terminal, but may also be a stationary information terminal such as a personal computer. Further, the information terminal 40 is realized by installing a dedicated application program of the health management system 100 in a general-purpose device, but may also be a dedicated device of the health management system 100. The display unit 41 included in the information terminal 40 is realized by a display panel such as a liquid crystal panel or an organic EL (Electro Luminescence) panel.

[0031] [Operation Example] Next, an operation example of the health management system 100 will be described. FIG. 4 is a flowchart of an operation example of the health management system 100.

[0032] First, the acquisition unit 31 of the server device 30 acquires the user's electrocardiogram signal and the user's attribute information (S11). The user's electrocardiogram signal is measured by the toilet seat device 10 using the first electrode 21, the second electrode 22, and the body earth electrode 23, and is transmitted from the toilet seat device 10 to the server device 30. The user's attribute information is, for example, input to the information terminal 40 and is transmitted from the information terminal 40 to the server device 30. The user's attribute information is, for example, information indicating the user's gender, the user's height, and the user's weight.

[0033] Note that the acquisition path of the attribute information is not particularly limited. For example, when the user's attribute information is registered in the remote controller of the toilet seat device 10, the user's attribute information may be transmitted from the remote controller or the toilet seat device 10 to the server device 30 and acquired by the acquisition unit 31.

[0034] Next, the preprocessing unit 32 performs preprocessing on the electrocardiogram signal acquired in step S11 (S12). The preprocessing is a process of making the electrocardiogram signal suitable for calculating the RR interval. The preprocessing unit 32, for example, limits the frequency band of the electrocardiogram signal to a band of 5 Hz or more and 30 Hz or less by applying a filter to the electrocardiogram signal acquired in step S11. Also, in the case of the toilet seat device 10 provided with electrodes on the handrail as shown in FIG. 3, the frequency band of the electrocardiogram signal is limited to a band of 1 Hz or more and 20 Hz or less.

[0035] Further, the preprocessing unit 32 excludes the period during which the amplitude of the electrocardiogram signal becomes equal to or greater than a predetermined value. The exclusion here means not considering it as valid data. By this process, the period during which the electrocardiogram signal was appropriately measured due to the user's body movement or the like during defecation is excluded. When electrodes are provided on the toilet seat 20 as shown in FIG. 2, the predetermined value is, for example, 150 μV, but it may be appropriately determined empirically or experimentally according to the specifications of the toilet seat device 10. When electrodes are provided on the handrail as shown in FIG. 3, the predetermined value is, for example, 2 mV or the like.

[0036] Also, in step S12, the preprocessing unit divides the electrocardiogram signal after the above two types of preprocessing into time units of a predetermined time and stores (stores) it in the storage unit 33. The predetermined time unit is, for example, a time unit corresponding to 10 seconds.

[0037] Next, the analysis unit 34 sets a count value i for managing the number of times of calculating the 3H risk estimation value to i = 0 and initializes it (S13). The analysis unit 34 extracts electrocardiogram signals stored in the storage unit 33 in 7 consecutive time units (10 seconds × 7 = 70 seconds) (S14), and calculates the RR interval for each of the extracted 7-unit electrocardiogram signals (S15). When the electrocardiogram signal can be measured correctly, about 8 to 10 RR intervals are calculated from 1 unit (10 seconds).

[0038] In step S15, in order to calculate the RR interval, the analysis unit 34 detects the R wave of the electrocardiogram signal using a predetermined peak detection algorithm (for example, Hamilton algorithm), and calculates the RR interval based on the detected R wave. Further, the calculated RR intervals in the range of 0.4 seconds or more and 2 seconds or less (when converted to heart rate, 30 to 150 bpm) are adopted.

[0039] Next, the analysis unit 34 determines whether the total (total time) of the RR intervals calculated in step S15 is 60 seconds or more (S16). This determination is made to improve the accuracy of the 3H risk estimation value. When the analysis unit 34 determines that the total (total time) of the RR intervals is less than 60 seconds (No in S16), it replenishes the electrocardiogram signal (S17). For example, one or more electrocardiogram signals immediately after the 7 units extracted in step S14 are extracted from the storage unit 33, and the RR interval is calculated in the extracted one or more electrocardiogram signals, so that the total of the RR intervals becomes 60 seconds or more.

[0040] Note that the method for replenishing the electrocardiogram signal in step S17 is not particularly limited. Among the 7 units extracted in step S14, units with a small subtotal (subtotal time) of the calculated RR intervals (for example, 80% of 10 seconds, units less than 8 seconds) may be excluded, and then the electrocardiogram signal may be replenished.

[0041] When it is determined by the analysis unit 34 that the total of the RR intervals (total time) is 60 seconds or more (Yes in S16), and when the electrocardiogram signal is replenished (S17), the 3H risk estimation unit 35 calculates a feature quantity related to heartbeat variability based on the RR intervals of 60 seconds or more in total (S18). The feature quantity related to heartbeat variability may sometimes be called a heartbeat variability parameter or the like. The feature quantity related to heartbeat variability includes at least one of the average of the RR intervals of 60 seconds or more in total, the variance of the RR intervals of 60 seconds or more in total, the standard deviation, LF, HF, LF / HF, RMSSD (Root Mean Square of Successive Differences), Shannon Entropy, and Fisher Information. Note that LF is an abbreviation for Low Frequency and corresponds to the power spectrum of 0.05 Hz to 0.15 Hz. HF is an abbreviation for High Frequency and corresponds to the power spectrum of the frequency component of 0.15 Hz to 0.40 Hz.

[0042] Next, the 3H risk estimation unit 35 calculates a 3H risk estimation value (S19). The 3H risk estimation unit 35 calculates the 3H risk estimation value using, for example, a machine learning model. This machine learning model is, for example, a model to which logistic regression is applied, and is a learned model constructed using, as learning data (teacher data), data in which the determination results (risk present: 1, risk absent: 0) of the presence or absence of 3H risk by a doctor or the like are associated with the attribute information and the feature quantity related to electrocardiogram variability of a large number of subjects. When the attribute information acquired in step S11 and the feature quantity related to heartbeat variability calculated in step S18 are input to the machine learning model, a numerical value between 0 and 1 is output as the 3H risk estimation value. The 3H risk estimation value approaches 1 as the 3H risk is higher, and approaches 0 as the 3H risk is lower, for example.

[0043] Next, the analysis unit 34 increments the count value i (i = i + 1) (S20), and determines whether the incremented count value has reached n (n is a natural number of 2 or more) (S21). n is a numerical value corresponding to the number of times of calculating the 3H risk estimation value.

[0044] When it is determined by the analysis unit 34 that the incremented count value has not reached n (No in S21), the processes of steps S14 to S20 are performed again. Here, assuming that an electrocardiogram signal corresponding to the section from 0 seconds to 70 seconds of the entire electrocardiogram signal is extracted in the first step S14, in the second step S14, for example, an electrocardiogram signal corresponding to the section from 10 seconds to 80 seconds of the entire electrocardiogram signal, where 1 unit of time (10 seconds) is shifted backward, is extracted. That is, the analysis unit 34 changes the section of the electrocardiogram signal to calculate the RR intervals for a plurality of times in order to calculate the 3H risk estimation values for a plurality of times. Since there is a limit to the time length of the electrocardiogram signal measured by the toilet seat device 10 (there are few cases where the electrocardiogram signal can be measured for a sufficiently long time), a configuration means for providing an overlapping section between the first section and the second section is useful.

[0045] When it is determined by the analysis unit 34 that the incremented count value has reached n (Yes in S21), the determination unit 36 determines whether the user has a 3H risk based on the 3H risk estimation values for n times calculated by the 3H risk estimation unit 35 (S22). The determination unit 36, for example, uses the maximum value of the calculated 3H risk estimation values for n times as the representative estimation value, and determines that the user has a 3H risk when the representative estimation value is greater than the threshold value, and determines that the user does not have a 3H risk when the representative estimation value is less than or equal to the threshold value. The threshold value is, for example, 0.6, but it may be appropriately determined empirically or experimentally. The representative estimation value may be a statistic (for example, the minimum value, the average value, or the median, etc.) of the calculated 3H risk estimation values for n times.

[0046] FIG. 5 is a diagram showing the determination results of the 3H risk by the health management system 100. The horizontal axis in FIG. 5 indicates the subject numbers. Subjects 1 to 4 are subjects who have been previously determined by a doctor or an inspection institution, etc. to have a 3H risk, and subjects 5 to 7 are subjects who have been previously determined by a doctor or an inspection institution, etc. to have no 3H risk.

[0047] One point in FIG. 5 indicates the 3H risk estimated value calculated based on the operation of FIG. 4. When a plurality of points are plotted for one subject, it means that the 3H risk estimated value has been calculated multiple times for the subject based on the operation of FIG. 4.

[0048] As shown in FIG. 5, for subjects 1 to 4 with a 3H risk, the maximum value (representative estimated value) of the 3H risk estimated value all exceeds the threshold value (0.6), and for subjects 5 to 7 without a 3H risk, the maximum value (representative estimated value) of the 3H risk estimated value is all below the threshold value (0.6). Thus, the determination unit 36 can determine whether the user has a 3H risk.

[0049] Next, the blood vessel regulation degree estimation unit 37 estimates the blood vessel regulation degree of the user based on the multiple 3H risk estimated values calculated by the 3H risk estimation unit 35 (S23). The blood vessel regulation degree is a parameter indicating the heart rate adjustment function due to blood vessel contraction. When the blood vessels are soft (flexible and easy to contract), it becomes a large numerical value, meaning that the heart rate adjustment function due to blood vessel contraction is high. Also, when the blood vessels are hard (close to the arterial effect), it becomes a small numerical value, meaning that the heart rate adjustment function due to blood vessel contraction is low. The blood vessel regulation degree is a concept close to the so-called blood vessel age (the flexibility of the outside of the blood vessels), but it is a concept that includes not only the blood vessel age but also the smoothness of the blood flow inside the blood vessels.

[0050] When the blood vessel regulation degree of the subject is high (the heart rate regulation function due to blood vessel constriction is high), the characteristic quantity related to the heart rate variation calculated in step S18 is likely to change due to the influence of breathing or the like, and as a result, the 3H risk estimation value is likely to vary. When the blood vessel regulation degree of the subject is low (the heart rate regulation function due to blood vessel constriction is low), the characteristic quantity related to the heart rate variation calculated in step S18 is unlikely to change due to the influence of breathing or the like, and as a result, the 3H risk estimation value is unlikely to vary.

[0051] Therefore, specifically, the blood vessel regulation degree estimation unit 37 uses the difference between the maximum value and the minimum value of the 3H risk estimation values for a plurality of times (corresponding to the double-headed arrow in FIG. 5) as the numerical value (scale of relative change) of the user's blood vessel regulation degree. For example, for subject No. 2 in FIG. 5, since the maximum value of the 3H risk estimation value is 0.74 and the minimum value is 0.66, the blood vessel regulation degree is 0.08. For subject No. 3, since the maximum value of the 3H risk estimation value is 0.98 and the minimum value is 0.95, the blood vessel regulation degree is 0.03.

[0052] For subject No. 5 in FIG. 5, since the maximum value of the 3H risk estimation value is 0.53 and the minimum value is 0.50, the blood vessel regulation degree is 0.03. For subject No. 7, since the maximum value of the 3H risk estimation value is 0.58 and the minimum value is 0.48, the blood vessel regulation degree is 0.10.

[0053] Next, the determination unit 36 outputs information for presenting the determination result of the presence or absence of the 3H risk in step S22, and the blood vessel regulation degree estimation unit 37 outputs information for presenting the blood vessel regulation degree estimated in step S23. As a result, presentation information including these two pieces of information is output from the server device 30 (S24).

[0054] The prompt information is transmitted from the server device 30 to the information terminal 40. The information terminal 40 (display unit 41) displays a display screen showing the determination result of the presence or absence of the 3H risk in step S22 and the estimation result of the blood vessel adjustment degree in step S23 based on the received prompt information. FIG. 6 is a diagram showing an example of such a display screen. As shown in FIG. 6, the blood vessel adjustment degree is displayed, for example, after being qualitatively segmented step by step according to the numerical value of the blood vessel adjustment degree. The blood vessel adjustment degree is qualitatively segmented into, for example, three levels: good, normal, and poor blood vessel adjustment degree.

[0055] As described above, the health management system 100 can determine the presence or absence of the 3H risk of the user and estimate the blood vessel adjustment degree of the user.

[0056] (Embodiment 2) [Configuration] Hereinafter, the configuration of the health management system according to Embodiment 2 will be described. FIG. 7 is a diagram showing the configuration of the health management system according to Embodiment 2. The health management system 100a includes a toilet seat device 10, a server device 30a, and an information terminal 40. The difference from the health management system 100 according to Embodiment 1 lies in the functional components of the server device 30a.

[0057] Specifically, in addition to the acquisition unit 31, the preprocessing unit 32, the storage unit 33, the analysis unit 34, the 3H risk estimation unit 35, the determination unit 36, and the blood vessel adjustment degree estimation unit 37, the server device 30a includes a blood pressure contribution degree estimation unit 38 and a carbohydrate excess degree estimation unit 39a. Each of the blood pressure contribution degree estimation unit 38 and the carbohydrate excess degree estimation unit 39a is a functional component realized by one or a plurality of processors (hardware) provided in the server device 30a executing a computer program (software) stored in a memory such as the storage unit 33.

[0058] In the health management system 100a, the acquisition unit 31 acquires the blood pressure value of the user in addition to the electrocardiogram signal of the user and the attribute information of the user.

[0059] Based on the acquired blood pressure value of the user, the blood pressure contribution degree estimation unit 38 estimates the blood pressure contribution degree indicating the degree to which blood pressure contributes to the representative estimated value of the user's 3H risk (the maximum value of the 3H risk estimated values for multiple times).

[0060] The excessive sugar degree estimation unit 39a estimates the excessive sugar degree based on the difference between the representative estimated value of the user's 3H risk and the estimated blood pressure contribution degree. In addition, the excessive sugar degree estimation unit 39a outputs information for presenting the estimated excessive sugar degree.

[0061] [Operation Example] Next, an operation example of the health management system 100a will be described. FIG. 8 is a flowchart of the operation example of the health management system 100a.

[0062] First, the acquisition unit 31 of the server device 30a acquires the blood pressure value of the user in addition to the electrocardiogram signal of the user and the attribute information of the user (S11a). The blood pressure value of the user includes the systolic blood pressure value (so-called upper blood pressure value) and the diastolic blood pressure value (so-called lower blood pressure value). The blood pressure value of the user is, for example, input to the information terminal 40 and transmitted from the information terminal 40 to the server device 30a. The acquisition path of the blood pressure value of the user is not particularly limited. The blood pressure value of the user may be transmitted from a blood pressure sensor or a server device that manages the blood pressure value of the user to the server device 30a and acquired by the acquisition unit 31.

[0063] The processing from step S12 to step S23 is the same as the operation example (FIG. 4) of the first embodiment.

[0064] Next to step S23, the blood pressure contribution degree estimation unit 38 estimates the blood pressure contribution degree indicating the degree to which blood pressure contributes to the representative estimated value of the user's 3H risk (the maximum value of the 3H risk estimated values for multiple times) based on the acquired blood pressure value of the user (S25). The blood pressure contribution degree is a numerical value corresponding to a part of the representative estimated value of the user's 3H risk, and is a parameter indicating the degree of risk of vascular factors in the representative estimated value. The blood pressure contribution degree has a correlation with the mean blood pressure value [mmHg], which is the average of the acquired blood pressure values (systolic blood pressure value [mmHg] / diastolic blood pressure value [mmHg]), and the higher the mean blood pressure value, the higher the blood pressure contribution degree.

[0065] The inventor considered the order relationship between the mean blood pressure value (described later) of the user and the 3H risk (Figure 10) from the nature of calculating the 3H risk estimated value using the machine learning model. Assuming that the blood pressure contribution degree is a linear function of the mean blood pressure value, the blood pressure contribution degrees are set for the normal blood pressure value 120 / 80 (mean blood pressure value 100 [mmHg]), the blood pressure value in the guidance required range 130 / 85 (mean blood pressure value 107.5 [mmHg]), and the diagnostic standard blood pressure value 140 / 90 (mean blood pressure value 115 [mmHg]), and thus the estimation formula (regression formula) y = 0.0133x - 0.8333 as shown in Figure 9 is obtained. Figure 9 is a diagram showing the estimation formula of the blood pressure contribution degree. Note that such an estimation formula is an example, and the estimation formula may be determined appropriately empirically or experimentally.

[0066] The blood pressure contribution degree estimation unit 38 estimates the blood pressure contribution degree by substituting the mean blood pressure value determined by the blood pressure value acquired in step S11a into such an estimation formula. For example, the blood pressure value of subject No. 3 in Figure 5 is 126 / 91. The blood pressure contribution degree estimation unit 38 can estimate the blood pressure contribution degree of subject No. 3 to be 0.62 (the square mark on the right side of Figure 9). Also, the blood pressure value of subject No. 4 in Figure 5 is 117 / 70. The blood pressure contribution degree estimation unit 38 can estimate the blood pressure contribution degree of subject No. 4 to be 0.41 (the square mark on the left side of Figure 9).

[0067] Next, the carbohydrate excess degree estimation unit 39a estimates the carbohydrate excess degree based on the difference between the representative estimated value of the user's 3H risk and the estimated blood pressure contribution degree (S26a). The carbohydrate excess degree is a numerical value corresponding to a part of the representative estimated value of the user's 3H risk other than that. While the blood pressure contribution degree is a parameter indicating the risk of vascular factors in the representative estimated value, the carbohydrate excess degree is a parameter indicating the risk of blood factors in the representative estimated value.

[0068] More specifically, the carbohydrate excess degree is a parameter indicating the degree of risk caused by excessive carbohydrates (glucose) in the blood in the representative estimated value. It can be said that the carbohydrate excess degree indicates the degree of excess of blood glucose and glycogen in the user's body when the user ingests carbohydrates from food. Also, the carbohydrate excess degree can be considered as a parameter indicating the viscosity (stickiness) of the blood. Since the sugar in the blood passes through glycogen and the excess part is converted into neutral fat, the carbohydrate excess degree can also be considered as a concept indicating a state common to both hyperglycemia and hyperlipidemia.

[0069] Specifically, the carbohydrate excess degree estimation unit 39a estimates the difference between the representative estimated value of the user's 3H risk and the estimated blood pressure contribution degree as the numerical value of the carbohydrate excess degree. For example, the blood pressure contribution degree and the carbohydrate excess degree of Subject No. 3 and Subject No. 4 in FIG. 5 are estimated as shown in FIG. 10. FIG. 10 is a diagram showing an example of the estimation of the blood pressure contribution degree and the carbohydrate excess degree.

[0070] As shown in FIG. 10, the representative estimated value of the 3H risk of Subject No. 3 is 0.97, and the blood pressure contribution degree is 0.62. Then, the carbohydrate excess degree of Subject No. 3 is 0.97 - 0.62 = 0.35. Also, the representative estimated value of the 3H risk of Subject No. 5 is 0.72, and the blood pressure contribution degree is 0.41. Then, the carbohydrate excess degree of Subject No. 3 is 0.72 - 0.41 = 0.31.

[0071] Next, the determination unit 36 outputs information for presenting the determination result regarding the presence or absence of the 3H risk in step S22, and the blood vessel adjustment degree estimation unit 37 outputs information for presenting the estimated blood vessel adjustment degree in step S23. Further, the carbohydrate excess degree estimation unit 39a outputs information for presenting the estimated carbohydrate excess degree in step S26a. As a result, presentation information including these three pieces of information is output from the server device 30a (S27a).

[0072] The presentation information is transmitted from the server device 30a to the information terminal 40, and the information terminal 40 (display unit 41) displays a display screen showing the determination result regarding the presence or absence of the 3H risk in step S22, the estimation result of the blood vessel adjustment degree in step S23, and the estimation result of the carbohydrate excess degree in step S26a based on the received presentation information. FIG. 11 is a diagram showing an example of such a display screen. As shown in FIG. 11, the carbohydrate excess degree is displayed after being qualitatively determined step by step according to, for example, the numerical value of the carbohydrate excess degree. The carbohydrate excess degree is qualitatively determined, for example, into three stages: excessive, slightly excessive, and normal in terms of carbohydrate intake. Thereby, the health management system 100a can give an opportunity to prevent the user from unconsciously over-consuming carbohydrates. Note that the information terminal 40 may display a display screen prompting the user to take specific improvement actions according to the estimation result. For example, the information terminal 40 may display a display screen prompting the user to change the carbohydrates consumed at lunch to vegetables (such as broccoli).

[0073] As described above, the health management system 100a can estimate the carbohydrate excess degree of the user.

[0074] (Embodiment 3) [Configuration] Hereinafter, the configuration of the health management system according to Embodiment 3 will be described. FIG. 12 is a diagram showing the configuration of the health management system according to Embodiment 3. The health management system 100b includes a toilet seat device 10, a server device 30b, and an information terminal 40. The difference from the health management system 100a according to Embodiment 2 lies in the functional components of the server device 30b.

[0075] Instead of the glucosity excess estimation unit 39a included in the server device 30a, the server device 30b includes a metabolic abnormality degree estimation unit 39b. The metabolic abnormality degree estimation unit 39b is a functional component realized by one or more processors (hardware) included in the server device 30b executing a computer program (software) stored in a memory such as the storage unit 33.

[0076] The metabolic abnormality degree estimation unit 39b estimates the metabolic abnormality degree based on the difference between the representative estimated value of the 3H risk of the user and the estimated blood pressure contribution degree. In addition, the metabolic abnormality degree estimation unit 39b outputs information for presenting regarding the estimated metabolic abnormality degree.

[0077] [Operation Example] Next, an operation example of the health management system 100b will be described. FIG. 13 is a flowchart of the operation example of the health management system 100b.

[0078] The processes of step S11a, steps S12 to S23, and step S25 are the same as those in the operation example (FIG. 8) of the second embodiment.

[0079] Next to step S25, the metabolic abnormality degree estimation unit 39b estimates the metabolic abnormality degree based on the difference between the representative estimated value of the 3H risk of the user and the estimated blood pressure contribution degree (S26b). The metabolic abnormality degree is a numerical value corresponding to a part other than the representative estimated value of the 3H risk of the user. While the blood pressure contribution degree is a parameter indicating the risk of vascular factors in the representative estimated value, the metabolic abnormality degree is a parameter indicating the risk of blood factors in the representative estimated value.

[0080] The state where the glucide (glucose) in the blood is excessive described in the second embodiment is considered to reflect a state where there is an abnormality in metabolism (the metabolic function is inferior to that of a healthy person). That is, the glucosity excess degree in the second embodiment can also be considered as the metabolic abnormality degree. Therefore, the metabolic abnormality degree estimation unit 39b estimates the metabolic abnormality degree.

[0081] The method for estimating the degree of metabolic abnormality is the same as the method for estimating the degree of carbohydrate excess. Specifically, the metabolic abnormality degree estimation unit 39b estimates the difference between the representative estimated value of the 3H risk of the user and the estimated blood pressure contribution degree as the numerical value of the metabolic abnormality degree.

[0082] Next, the determination unit 36 outputs information for presenting the determination result of the presence or absence of the 3H risk in step S22, and the blood vessel adjustment degree estimation unit 37 outputs information for presenting the estimated blood vessel adjustment degree in step S23. Further, the metabolic abnormality degree estimation unit 39b outputs information for presenting the estimated metabolic abnormality degree in step S26b. As a result, presentation information including these three pieces of information is output from the server device 30b (S27b).

[0083] The presentation information is transmitted from the server device 30b to the information terminal 40, and the information terminal 40 (display unit 41) displays a display screen showing the determination result of the presence or absence of the 3H risk in step S22, the estimated result of the blood vessel adjustment degree in step S23, and the estimated result of the metabolic abnormality degree in step S26b based on the received presentation information. FIG. 14 is a diagram showing an example of such a display screen. As shown in FIG. 14, the metabolic abnormality degree is displayed, for example, after being qualitatively divided step by step according to the numerical value of the metabolic abnormality degree. The metabolic abnormality degree is qualitatively divided into, for example, three stages: bad, slightly bad, and normal, in terms of the metabolic state. Thereby, the health management system 100b can give a trigger to improve the user's metabolism. Note that the information terminal 40 may display a display screen prompting the user to take specific improvement actions according to the estimation result. For example, the information terminal 40 may display a display screen prompting the user to increase the number of steps per day by 2000 steps, or may display a display screen prompting the user to perform simple in-room muscle training (such as 7-second squats).

[0084] As described above, the health management system 100b can estimate the degree of metabolic abnormality of the user.

[0085] (Effects, etc.) As described above, the health management system 100 includes an acquisition unit 31 that acquires an electrocardiogram signal of a user measured using electrodes by a toilet seat device 10 having electrodes, and an analysis unit 34 that calculates an RR interval for a partial section of the acquired electrocardiogram signal, the analysis unit 34 calculating RR intervals for a plurality of times by changing the section, and an estimation unit that calculates 3H risk estimation values, which are estimation values of risks corresponding to at least one of hypertension, hyperglycemia, and hyperlipidemia, for a plurality of times based on the calculated RR intervals for a plurality of times. The estimation unit estimates a vascular regulation degree indicating a heart rate adjustment function due to blood vessel constriction based on the calculated 3H risk estimation values for a plurality of times, and outputs information for presenting a presentation regarding the estimated vascular regulation degree. The estimation unit here corresponds to the 3H risk estimation unit 35 and the vascular regulation degree estimation unit 37 of the above-described embodiment.

[0086] Such a health management system 100 can present information regarding health risks. Specifically, the health management system 100 can present information regarding the vascular regulation degree.

[0087] Also, for example, the estimation unit estimates the vascular regulation degree of the user based on the difference between the maximum value and the minimum value of the plurality of 3H risk estimation values.

[0088] Such a health management system 100 can present information regarding the vascular regulation degree.

[0089] Also, for example, in the health management system 100a or the health management system 100b, the acquisition unit 31 further acquires the blood pressure value of the user. The estimation unit uses the maximum value of the plurality of 3H risk estimation values as a representative estimation value of the 3H risk of the user, and estimates a blood pressure contribution degree indicating the degree to which the blood pressure contributes to the representative estimation value based on the acquired blood pressure value. The estimation unit here corresponds to the blood pressure contribution degree estimation unit 38 of the above-described embodiment.

[0090] Such a health management system 100a can estimate the blood pressure contribution degree.

[0091] Further, for example, in the health management system 100a, the estimation unit further estimates the degree of carbohydrate excess based on the difference between the representative estimated value and the estimated blood pressure contribution degree, and outputs information for presenting the estimated degree of carbohydrate excess. The estimation unit here corresponds to the carbohydrate excess estimation unit 39a in the above embodiment.

[0092] Such a health management system 100a can present information regarding the degree of carbohydrate excess.

[0093] Further, for example, in the health management system 100b, the estimation unit further estimates the degree of metabolic abnormality based on the difference between the representative estimated value and the estimated blood pressure contribution degree, and outputs information for presenting the estimated degree of metabolic abnormality. The estimation unit here corresponds to the metabolic abnormality estimation unit 39b in the above embodiment.

[0094] Such a health management system 100b can present information regarding the degree of metabolic abnormality.

[0095] Further, for example, the health management system 100 further includes a preprocessing unit 32 that preprocesses the acquired electrocardiogram signal. The analysis unit 34 calculates the RR interval for a partial section of the acquired electrocardiogram signal that has been preprocessed. The preprocessing includes a process of restricting the frequency band and a process of excluding a period during which the amplitude is equal to or greater than a predetermined value.

[0096] Such a health management system 100 can improve the estimation accuracy of the 3H risk estimated value by preprocessing the electrocardiogram signal.

[0097] Further, for example, the health management system 100 further includes a determination unit 36 that determines that the user has a 3H risk when the maximum value of the calculated 3H risk estimated values for a plurality of times is greater than a threshold value, and determines that the user does not have a 3H risk when the maximum value of the calculated 3H risk estimated values for a plurality of times is equal to or less than the threshold value. The determination unit 36 outputs information for presenting the determination result regarding the presence or absence of the 3H risk.

[0098] Such a health management system 100 can present information regarding the determination result of the presence or absence of 3H risks.

[0099] Also, for example, the acquisition unit 31 further acquires the user's attribute information. The estimation unit calculates a plurality of 3H risk estimation values based on the calculated RR intervals for a plurality of times and the acquired attribute information. The estimation unit here corresponds to the 3H risk estimation unit 35 in the above embodiment.

[0100] Such a health management system 100 can calculate a 3H risk estimation value in consideration of the user's attribute information.

[0101] Also, for example, the health management system 100 further includes a toilet seat device 10 and a display unit 41 that displays an image based on information for presenting a presentation regarding the output blood vessel regulation degree.

[0102] Such a health management system 100 can present an image regarding the blood vessel regulation degree.

[0103] Also, a health management method executed by a computer such as the health management system 100 includes a first acquisition step S11 of acquiring an electrocardiogram signal of a user measured using electrodes by a toilet seat device 10 having electrodes, an analysis step S15 of calculating an RR interval for a part of the acquired electrocardiogram signal, the analysis step S15 of calculating a plurality of RR intervals by changing the interval, a first estimation step S19 of calculating a plurality of 3H risk estimation values, which are estimation values of risks corresponding to at least one of hypertension, hyperglycemia, and hyperlipidemia, based on the calculated RR intervals for a plurality of times, a second estimation step S23 of estimating a blood vessel regulation degree indicating a heart rate adjustment function due to blood vessel contraction based on the calculated plurality of 3H risk estimation values, and a first output step S24 of outputting information for presenting a presentation regarding the estimated blood vessel regulation degree.

[0104] Such a health management method can present information regarding vascular regulation degree.

[0105] Also, for example, the health management method further includes a second acquisition step S11a of acquiring the user's blood pressure value, a third estimation step S25 of setting the maximum value of the 3H risk estimation values for a plurality of times as the representative estimation value of the user's 3H risk, and estimating a blood pressure contribution degree indicating the degree to which blood pressure contributes to the representative estimation value based on the acquired blood pressure value, a fourth estimation step S26a of estimating the degree of carbohydrate excess based on the difference between the representative estimation value and the estimated blood pressure contribution degree, and a second output step S27a of outputting information for presenting regarding the estimated degree of carbohydrate excess.

[0106] Such a health management method can present information regarding the degree of carbohydrate excess.

[0107] (Other embodiments) Although the embodiments have been described above, the present invention is not limited to such embodiments.

[0108] For example, in the above embodiment, the electrocardiogram signal is measured by the toilet seat device, but it may be measured by other devices such as an electrocardiograph. That is, the health management system may estimate the 3H risk or the like based on the electrocardiogram signal measured by a device other than the toilet seat device.

[0109] Also, in the above embodiment, the health management system is realized by a plurality of devices. In this case, the functional components included in the health management system described in the above embodiment may be distributed among the plurality of devices in any manner. For example, the preprocessing unit may be provided by the toilet seat device instead of the server device, and the acquisition unit of the server device may acquire the preprocessed electrocardiogram signal from the toilet seat device.

[0110] In addition, in the above-described embodiment, the processing executed by a specific processing unit may be executed by another processing unit. Also, the order of a plurality of processes may be changed, or a plurality of processes may be executed in parallel. For example, the estimation of the degree of blood vessel regulation and the estimation of the degree of carbohydrate excess (or metabolic abnormality) may be performed sequentially or in parallel.

[0111] Furthermore, the general or specific aspects of the present invention may be implemented by a system, an apparatus, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM. Also, it may be implemented by any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

[0112] For example, the present invention may be implemented as the server device according to the above-described embodiment. The present invention may be implemented as a health management method executed by a computer such as a health management system. Also, the present invention may be implemented as a program for causing a computer to execute such a health management method, or may be implemented as a computer-readable non-transitory recording medium on which such a program is recorded.

[0113] In addition, as long as it does not depart from the gist of the present invention, various modifications conceived by those skilled in the art applied to this embodiment, or forms constructed by combining components in different embodiments may also be included within the scope of one or more aspects.

Description of Reference Numerals

[0114] 10 Toilet seat device 20 Toilet seat 21 First electrode 22 Second electrode 23 Body earth electrode 30, 30a, 30b Server device 31 Acquisition unit 32 Pretreatment unit 33 Storage unit 34 Analysis unit 35 3H risk estimation unit 36 Judgment unit 37 Vascular adjustment degree estimation unit 38 Blood pressure contribution degree estimation unit 39a Carbohydrate excess degree estimation unit 39b Metabolic abnormality degree estimation unit 40 Information terminal 41 Display unit 100, 100a, 100b Health management system

Claims

1. An acquisition unit that acquires an electrocardiogram signal of a user measured using the electrode by a toilet seat device having the electrode; An analysis unit that calculates an RR interval for a partial section of the acquired electrocardiogram signal, the analysis unit calculating the RR interval a plurality of times by changing the section; An estimation unit that calculates a plurality of 3H risk estimation values, which are estimated values of the risk that the user corresponds to at least one of hypertension, hyperglycemia, and hyperlipidemia, by inputting a feature quantity related to heartbeat variation obtained from the plurality of calculated RR intervals into a machine learning model; and The estimation unit estimates that the difference between the maximum value and the minimum value of the plurality of calculated 3H risk estimation values is a vascular regulation degree indicating a function of adjusting the heartbeat due to vasoconstriction, and outputs information for presenting the estimated vascular regulation degree. A health management system.

2. The acquisition unit further acquires a blood pressure value of the user. The estimation unit uses the maximum value of the plurality of 3H risk estimation values as a representative estimation value of the 3H risk of the user, and estimates a blood pressure contribution degree indicating the degree to which blood pressure contributes to the representative estimation value based on the acquired blood pressure value. The health management system according to claim 1.

3. The estimation unit further estimates a degree of excessive sugar based on the difference between the representative estimation value and the estimated blood pressure contribution degree, and outputs information for presenting the estimated degree of excessive sugar. The health management system according to claim 2.

4. The estimation unit further estimates a degree of metabolic abnormality based on the difference between the representative estimation value and the estimated blood pressure contribution degree, and outputs information for presenting the estimated degree of metabolic abnormality. The health management system according to claim 2.

5. Further provided with a preprocessing unit that performs preprocessing on the acquired electrocardiogram signal, The analysis unit calculates the RR interval for a partial section of the acquired electrocardiogram signal on which the preprocessing has been performed, The preprocessing includes a process of restricting a frequency band and a process of excluding a period in which an amplitude becomes equal to or greater than a predetermined value. The health management system according to claim 1.

6. Further, when the maximum value of the calculated 3H risk estimation values for a plurality of times is greater than a threshold value, it is determined that the user has a 3H risk, and when the maximum value of the calculated 3H risk estimation values for a plurality of times is equal to or less than the threshold value, it is determined that the user does not have a 3H risk, and it includes a determination unit for making such a determination. The determination unit outputs information for presenting a determination result regarding the presence or absence of a 3H risk. The health management system according to claim 1.

7. The acquisition unit further acquires attribute information of the user. The estimation unit calculates 3H risk estimation values for a plurality of times based on the calculated RR intervals for a plurality of times and the acquired attribute information. The health management system according to claim 1.

8. Furthermore, a toilet seat device; and a display unit that displays an image based on the information for presenting the output blood vessel adjustment degree. The health management system according to claim 1.

9. A health management method executed by a computer, a first acquisition step of acquiring an electrocardiogram signal of a user measured using electrodes by a toilet seat device provided with the electrodes; an analysis step of calculating an RR interval for a part of an interval of the acquired electrocardiogram signal, and the analysis step of calculating RR intervals for a plurality of times by changing the interval; a first estimation step of calculating 3H risk estimation values for a plurality of times, which are estimation values of risks corresponding to at least one of hypertension, hyperglycemia, and hyperlipidemia of the user, by inputting a feature amount related to heartbeat variation obtained from the calculated RR intervals for a plurality of times into a machine learning model; a second estimation step of estimating that the difference between the maximum value and the minimum value of the calculated 3H risk estimation values for a plurality of times is the blood vessel adjustment degree indicating the adjustment function of the heartbeat due to blood vessel contraction; and a first output step of outputting information for presenting the estimated blood vessel adjustment degree. Health management method.

10. Furthermore, a second acquisition step of acquiring a blood pressure value of the user; a third estimation step of using the maximum value of the 3H risk estimation values for a plurality of times as a representative estimation value of the 3H risk of the user, and estimating a blood pressure contribution degree indicating the degree to which blood pressure contributes to the representative estimation value based on the acquired blood pressure value; a fourth estimation step of estimating a degree of excessive sugar based on the difference between the representative estimation value and the estimated blood pressure contribution degree. including a second output step of outputting information for presenting the presumed degree of carbohydrate excess The health management method according to claim 9.

11. A program for causing a computer to execute the health management method according to claim 9 or 10.

Images