Model determination device, water metabolism index estimation device, health status estimation device, model determination method, water metabolism index estimation method, health status estimation method, and program

Abstract

The water metabolism index estimation system (1) comprises a body information acquisition unit (13) and a water metabolism index estimation unit (14). The body information acquisition unit (13) acquires second body information that numerically indicates the body characteristics of a target person to be estimated. The water metabolism index estimation unit (14) acquires a model, the model being obtained by, for a plurality of target persons to be memorized, mapping one or more first body information numerically indicating the body characteristics of each target person to be memorized with a first water metabolism index indicating the degree of water metabolism of the target person to be memorized within a preset period, and the model being an index model for deriving a water metabolism index indicating the degree of water metabolism from the body information indicating the body characteristics, and applying the second body information to the index model to determine a second water metabolism index indicating the degree of water metabolism of the target person to be estimated.

Description

[Technical Field]

[0001] This disclosure relates to a model determination device, a water metabolism index estimation device, a health status estimation device, a model determination method, a water metabolism index estimation method, a health status estimation method, and a program. [Background technology]

[0002] As an example of health management, technologies have been developed to prevent dehydration in individuals under health management. One example of this type of technology is a dehydration management system that estimates the dehydration status of a subject, disclosed in Patent Document 1. The dehydration management system disclosed in Patent Document 1 estimates the dehydration status of a subject from blood flow data, the amount of water supplied by a water supply device, and environmental conditions. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-42721 [Overview of the project] [Problems that the invention aims to solve]

[0004] To prevent dehydration, it is necessary to encourage individuals under health management to consume an appropriate amount of fluids. While the dehydration management system disclosed in Patent Document 1 can estimate the dehydration level of an individual, it cannot indicate the amount of fluids the individual needs to prevent dehydration.

[0005] The amount of water that should be consumed can be determined from an indicator of the degree of water metabolism, specifically from the water balance, which is the amount of water replaced in the body per day. One method for determining the water balance, or in other words, water turnover, is the doubly labeled water method. The doubly labeled water method uses stable isotopes of hydrogen. 2 Stable isotopes of H and oxygen 18This method involves administering water containing oxygen (O) to the subject and analyzing the decay rate of stable isotopes in the subject's body fluids over a measurement period of, for example, two weeks. From the excretion rates of the two stable isotopes obtained, body water content, total energy expenditure, water balance, etc., can be determined.

[0006] While the doubly labeled water method can be used to determine water balance, it requires water containing stable isotopes and equipment to analyze stable isotopes. Furthermore, as mentioned above, it is necessary to measure the body fluids of the subjects over the measurement period, thus requiring special equipment and time. In other words, the estimation process of water balance using the doubly labeled water method is complex and time-consuming, making it difficult to routinely determine water balance for each of the many individuals being monitored for health.

[0007] This disclosure is made in view of the circumstances described above, and aims to provide a model determination device, a water metabolism index estimation device, a health status estimation device, a model determination method, a water metabolism index estimation method, a health status estimation method, and a program that enable the simple determination of water metabolism indexes. [Means for solving the problem]

[0008] To achieve the above objectives, the model determination device relating to the first aspect of this disclosure is: For multiple memory subjects, one or more first physical information items that numerically represent the physical characteristics of the memory subjects and , determined based on the double-labeled water method, A storage unit that stores a first water metabolism index indicating the degree of water metabolism of the person to be stored over a specified period, in association with the data. A determination unit determines an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, based on the correspondence between the first physical information and the first water metabolism index of each of the aforementioned memory subjects, It is equipped with.

[0009] Preferably, the determination unit obtains one or more first parameters for obtaining the water metabolism index by weighting each of the physical information variables through regression analysis with the first physical information as the explanatory variable and the first water metabolism index as the objective function.

[0010] Preferably, the determination unit learns the first physical information and the first water metabolism index, and obtains the index model, which is a neural network model that takes the physical information as input and outputs the water metabolism index.

[0011] Preferably, the memory unit stores, in association with the plurality of individuals to be stored, the first physical information, the first water metabolism index, and one or more pieces of first environmental information that numerically represent the environmental conditions surrounding the individuals to be stored.

[0012] Preferably, the determination unit determines the index model for deriving the water metabolism index from the physical information and environmental information that numerically represents the environmental state, based on the correspondence between the first physical information, the first water metabolism index, and the first environmental information of each of the memory subjects.

[0013] Preferably, the determination unit obtains a plurality of first parameters for obtaining the water metabolism index by weighting the physical information and the environmental information, using regression analysis with the first physical information and the first environmental information as explanatory variables and the first water metabolism index as the objective function.

[0014] Preferably, the determination unit determines the plurality of first parameters by multiple regression analysis using the first physical information, consisting of physical activity level, weight, gender, athlete level, and age, and the first environmental information, consisting of temperature, humidity, and human development index, as explanatory variables, and the first water metabolism index as the objective function.

[0015] Preferably, the determination unit learns the first body information, the first water metabolism index, and the first environmental information, and obtains the index model, which is a neural network model that outputs the water metabolism index using the body information and the environmental information as inputs.

[0017] The water metabolism index estimation device according to the second aspect of the present disclosure includes a body information acquisition unit that acquires one or more pieces of second body information numerically indicating the physical characteristics of the estimation target person, one or more pieces of first body information numerically indicating the physical characteristics of the storage target person for a plurality of storage target persons, and , determined based on the double-labeled water method, a water metabolism index estimation unit that obtains a model obtained from the association between the first body information and the first water metabolism index indicating the degree of water metabolism of the storage target person during a predetermined period, and acquires an index model for deriving a water metabolism index indicating the degree of water metabolism from the body information indicating the physical characteristics, and obtains a second water metabolism index indicating the degree of water metabolism of the estimation target person by applying the second body information to the index model. It is provided with.

[0018] Preferably, the body information acquisition unit acquires one or more pieces of the second body information that are measurement values of the physical characteristics of the estimation target person and one or more other pieces of the second body information estimated from the second body information.

[0019] Preferably, the body information acquisition unit acquires one or more pieces of the second body information that are measurement values of the physical characteristics of the estimation target person and one or more other pieces of the second body information whose values are predetermined in advance.

[0020] Preferably, the physical characteristics are composed of at least any one of gender, age, weight, fat-free mass, physical activity level, total energy consumption, socioeconomic status, and athlete level indicating daily exercise intensity.

[0021] Preferably, The water metabolism index estimation device further comprises an environmental information acquisition unit that acquires one or more second environmental information items that numerically represent the environmental conditions surrounding the person to be estimated. The water metabolism index estimation unit obtains an index model for which the water metabolism index is derived from the correspondence between the first physical information of the plurality of memory subjects, the first water metabolism index, and one or more first environmental information that numerically represents the environmental conditions around the memory subjects, and obtains the index model for which the water metabolism index is derived from the physical information and environmental information that represents the environmental conditions, and obtains the second water metabolism index by applying the second physical information and the second environmental information to the index model.

[0022] Preferably, the environmental information acquisition unit acquires one or more of the second environmental information, which are measured values ​​of the environmental conditions around the estimated subject, and one or more other second environmental information estimated from the second environmental information.

[0023] Preferably, the environmental information acquisition unit acquires one or more of the second environmental information, which are measured values ​​of the environmental conditions around the estimated subject, and one or more other second environmental information, which have predetermined values.

[0024] Preferably, the environmental conditions consist of at least one of temperature, humidity, latitude, altitude, and the Human Development Index.

[0025] The health status estimation device relating to the third aspect of this disclosure is The above-mentioned water metabolism index estimation device, A health status estimation unit that determines metabolic health status by weighting the second water metabolism index and the second physical information with a predetermined second parameter, It is equipped with.

[0026] The model determination method relating to the fourth aspect of this disclosure is: A model determination method performed by a model determination device, One or more first physical information items that numerically represent the physical characteristics of multiple memory subjects and , determined based on the double-labeled water method,By correlating the data with a first water metabolism index that indicates the degree of water metabolism of the subject of memory over a specified period, an index model is determined for deriving a water metabolism index that indicates the degree of water metabolism from physical information that shows physical characteristics.

[0027] The method for estimating water metabolism indicators relating to the fifth aspect of this disclosure is: A method for estimating water metabolism indicators performed by a water metabolism indicator estimation device, Obtain one or more second-party physical information items that represent the physical characteristics of the estimated subject numerically, One or more first physical information items that numerically represent the physical characteristics of multiple memory subjects and , determined based on the double-labeled water method, A model obtained by associating the memory subject with a first water metabolism index indicating the degree of water metabolism of the memory subject over a specified period, wherein an index model is obtained for deriving a water metabolism index indicating the degree of water metabolism from physical information indicating physical characteristics, and a second water metabolism index indicating the degree of water metabolism of the estimated subject is obtained by applying the second physical information to the index model.

[0028] The health estimation method relating to the sixth aspect of this disclosure is: A health status estimation method performed by a health status estimation device, Obtain one or more second-party physical information items that represent the physical characteristics of the estimated subject numerically, One or more first physical information items that numerically represent the physical characteristics of multiple memory subjects and , determined based on the double-labeled water method, A model obtained by associating with a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, wherein an index model is obtained for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and a second water metabolism index that indicates the degree of water metabolism of the estimated subject is obtained by applying the second physical information to the index model, Metabolic health is determined by weighting the second water metabolism index and the second physical information using a predetermined second parameter.

[0029] The program relating to the seventh aspect of this disclosure is: Computers, For multiple memory subjects, one or more first physical information items that numerically represent the physical characteristics of the memory subjects and , determined based on the double-labeled water method, A storage unit that stores a first water metabolism index indicating the degree of water metabolism of the person to be stored over a specified period, in association with the data, and A determination unit determines an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, based on the correspondence between the first physical information and the first water metabolism index of each of the aforementioned memory subjects. To make it function as such.

[0030] The program relating to the eighth aspect of this disclosure is Computers, A body information acquisition unit that acquires one or more second body information items that numerically represent the physical characteristics of the estimated target person, and One or more first physical information items that numerically represent the physical characteristics of multiple memory subjects and , determined based on the double-labeled water method, A model obtained by associating with a first water metabolism index that indicates the degree of water metabolism of the person to be stored over a specified period, wherein an index model is obtained for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and a water metabolism index estimation unit obtains a second water metabolism index that indicates the degree of water metabolism of the person to be estimated by applying the second physical information to the index model, To make it function as such.

[0031] The program relating to the ninth aspect of this disclosure is Computers, A body information acquisition unit that acquires one or more second body information items that numerically represent the physical characteristics of the estimated subject. One or more first physical information items that numerically represent the physical characteristics of multiple memory subjects and , determined based on the double-labeled water method,A model obtained by associating with a first water metabolism index that indicates the degree of water metabolism of the person to be stored over a specified period, the water metabolism index estimation unit obtains an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and obtains a second water metabolism index that indicates the degree of water metabolism of the person to be stored by applying the second physical information to the index model, and A health status estimation unit that determines metabolic health status by weighting the second water metabolism index and the second physical information with a predetermined second parameter. To make it function as such. [Effects of the Invention]

[0032] According to this disclosure, it is possible to easily determine water metabolism indicators based on an indicator model for deriving water metabolism indicators from physical information. [Brief explanation of the drawing]

[0033] [Figure 1] Block diagram of the model determination device, water metabolism index estimation device, and health status estimation device according to Embodiment 1. [Figure 2] This figure shows examples of water metabolism indicators and first body information stored in the memory unit of the model determination device according to Embodiment 1. [Figure 3] A diagram showing an example of the correlation between physical activity level and fluid balance in Embodiment 1. [Figure 4] A diagram showing an example of the correlation between lean body mass and water balance in Embodiment 1. [Figure 5] A diagram showing an example of the relationship between athlete level and fluid balance in Embodiment 1. [Figure 6] This figure shows the hardware configuration of the model determination device, water metabolism index estimation device, and health status estimation device according to Embodiment 1. [Figure 7] A flowchart showing an example of the water metabolism index estimation process performed by the water metabolism index estimation device according to Embodiment 1. [Figure 8] A flowchart showing an example of the health status estimation process performed by the health status estimation device according to Embodiment 1. [Figure 9] Block diagram of the model determination device, water metabolism index estimation device, and health status estimation device according to Embodiment 2. [Figure 10] This figure shows examples of water metabolism indicators, first physical information, and first environmental information stored in the memory unit of the model determination device according to Embodiment 2. [Figure 11] A diagram showing an example of the relationship between temperature and moisture balance in Embodiment 2. [Figure 12] A diagram showing an example of the relationship between the Human Development Index and water balance in Embodiment 2. [Figure 13] A flowchart showing an example of the water metabolism index estimation process performed by the water metabolism index estimation device according to Embodiment 2. [Figure 14] Block diagram of modified examples of the model determination device, water metabolism index estimation device, and health status estimation device according to the embodiment. [Figure 15] This figure shows a modified example of the hardware configuration of the model determination device, water metabolism index estimation device, and health status estimation device according to the embodiment. [Modes for carrying out the invention]

[0034] Hereinafter, the model determination device, water metabolism index estimation device, health status estimation device, model determination method, water metabolism index estimation method, health status estimation method, and program according to embodiments of this disclosure will be described in detail with reference to the drawings. In the drawings, the same or equivalent parts are denoted by the same reference numerals.

[0035] (Embodiment 1) Embodiment 1 describes a model determination device 10 for determining an index model for deriving water metabolism indices from physical information, a water metabolism index estimation device 1 for estimating a water metabolism index that indicates the degree of water metabolism of a person who is the subject of health management, and a health status estimation device 2 for estimating the health status of the person based on the estimated water metabolism index. Physical information is information that indicates physical characteristics, and water metabolism indices are information that indicates the degree of water metabolism.

[0036] The model determination device 10 shown in Figure 1 includes a memory unit 11 that stores, in association with one or more first physical information items and a first water metabolism index for each of several memory subjects, which are subjects of water metabolism analysis, specifically, multiple people who are subjects of analysis based on the doubly-labeled water (DLW) method. The first physical information items represent the physical characteristics of the memory subject in numerical form. The first water metabolism index is an index that shows the degree of water metabolism of each memory subject over a defined period.

[0037] The model determination device 10 further includes a determination unit 12 that determines an index model for deriving a water metabolism index from physical information. The determination unit 12 determines one or more first parameters for obtaining a water metabolism index by weighting each of the physical information, for example, by regression analysis.

[0038] The water metabolism index estimation device 1 determines a second water metabolism index that indicates the degree of water metabolism of a target individual, which is a different individual from the memory target individual whose water metabolism is being analyzed. Specifically, the water metabolism index estimation device 1 determines the second water metabolism index by applying one or more second physical information items, which numerically represent the physical characteristics of the target individual, to the index model determined by the model determination device 10 described above. The water metabolism index estimation device 1 comprises a physical information acquisition unit 13 that acquires one or more second physical information items, and a water metabolism index estimation unit 14 that determines the second water metabolism index by applying the second physical information items to the index model. The water metabolism index estimation unit 14 determines the second water metabolism index by weighting each of the second physical information items with a first parameter obtained by the determination unit 12 of the model determination device 10, for example.

[0039] The health status estimation device 2 comprises a water metabolism index estimation device 1 having the above configuration, and a health status estimation unit 21 that determines the metabolic health status of the subject by weighting the second physical information and the second water metabolism index obtained by the water metabolism index estimation unit 14 of the water metabolism index estimation device 1 with a second parameter.

[0040] The details of each part of the model determination device 10 will be described below. The storage unit 11 stores, as the first water metabolism index, the water input and output amount, which is the amount of water in the body replaced per day, in other words, Water Turnover (unit: L / day or mL / day). The physical characteristics are composed of at least any one of age, gender, weight, fat-free mass (FFM), physical activity level (PAL), total energy expenditure (TEE), socioeconomic status (SES), and athlete level indicating daily exercise intensity.

[0041] In Embodiment 1, as shown in FIG. 2, the storage unit 11 stores the water input and output amount WT of each storage target person in association with the age, gender, weight, fat-free mass, physical activity level, total energy expenditure, socioeconomic status, and athlete level that constitute the first body information. In FIG. 2, the athlete level is shown as Athlete. Each record in the table shown in FIG. 2 is data corresponding to each storage target person.

[0042] The water input and output amount WT is a value obtained based on the doubly labeled water method. The table shown in FIG. 2 may be composed of data obtained from the publicly available DLW database, in which values obtained based on the doubly labeled water method are stored.

[0043] In the doubly labeled water method, water containing the stable isotope 2 H of hydrogen and the stable isotope 18 O of oxygen is administered to the measurement subject. By analyzing the attenuation rate of the stable isotopes in the body fluid of the measurement subject over a determined period, for example, a two-week measurement period, the excretion rate k of the stable isotope 2 [[ID=I8]]H of hydrogen, the excretion rate k of the stable isotope D O of oxygen, the dilution volume N of the stable isotope 18 H of hydrogen, and the dilution volume N of the stable isotope O O of oxygen are obtained. 2 H of hydrogen, and the dilution volume N of the stable isotope D O of oxygen are obtained. 18 O of oxygen, and the dilution volume N of the stable isotope O are obtained.

[0044] The rH2O represented by the following equation (1) shall be used as the water balance WT. In the following equation (1), N is the average of the dilution volumes and is represented by the following equation (2). rH2O = 1.04k D N ···(1) N=(N D / 1.043+N O / 1.007) / 2 ···(2)

[0045] As described above, part of the first body information, which is associated with the water balance WT obtained by the doubly labeled water method, is derived from the data obtained by the doubly labeled water method. In detail, the stable isotopes of hydrogen 2 Dilution volume N of H D , and stable isotopes of oxygen 18 Dilution volume N of O O From this, the total body water (TBW) can be obtained, and by assuming that the hydration rate in the adult body is 73.2%, lean body mass can be obtained from the total body water.

[0046] Body water content, stable isotopes of hydrogen 2 H discharge rate k D , and stable isotopes of oxygen 18 O emission rate k O From this, the carbon dioxide emission rate can be determined. Using de Weir's formula for indirect calorimetry, the total energy expenditure can be determined from the carbon dioxide emission rate. By dividing the total energy expenditure by the basal energy expenditure (BEE), the physical activity level can be obtained. The basal energy expenditure can be determined, for example, from height, weight, and age using the Harris-Benedict formula.

[0047] The DLW database stores information about the physical characteristics of the person being measured, specifically, gender, age, weight, socioeconomic status, and athlete level. The memory unit 11 stores first physical information representing these physical characteristics, associated with the water balance WT. Gender takes a value of either 0, indicating male, or 1, indicating female. Socioeconomic status takes a value of either 1, indicating a high standard of living, 2, indicating an average standard of living, or 3, indicating a low standard of living. Athlete level takes a value of either 1, indicating an athlete, specifically a person with a high level of exercise on a daily basis, or 0, indicating not to be an athlete.

[0048] The determination unit 12 shown in Figure 1 acquires the water balance WT of each individual stored in the memory unit 11 as a first water metabolism index, as shown in Figure 2, and acquires the first physical information of each individual stored in the memory unit 11. The determination unit 12 weights each piece of physical information to obtain a plurality of first parameters for obtaining the water metabolism index, and sends the first parameters to the water metabolism index estimation device 1. In detail, the determination unit 12 obtains the first parameters by regression analysis with each piece of first physical information as an explanatory variable and the first water metabolism index as the dependent variable. The determination unit 12 sends the first parameters to the water metabolism index estimation unit 14.

[0049] The determination unit 12 preferably performs a multiple regression analysis using the first physical information, which has a high correlation with the first water metabolism index, as the explanatory variable to determine the first parameter. Figure 3 shows an example of the correlation between physical activity level PAL and water balance WT (unit: L / day), which is an example of the first physical information. The left side of the figure shows the relationship between physical activity level PAL and water balance WT for women, and the right side shows the relationship between physical activity level PAL and water balance WT for men. The horizontal axis represents physical activity level PAL, and the vertical axis represents water balance WT. In the analysis performed to determine the correlation in Figure 3, the p-value was less than 0.001, indicating that physical activity level PAL and water balance WT have a high correlation with each other.

[0050] Figure 4 shows an example of the correlation between lean body mass (FFM) (unit: kg) and water balance (WT) (unit: L / day), which are examples of primary body information. The left side of the figure shows the relationship between lean body mass (FFM) and water balance (WT) in women, and the right side shows the relationship between lean body mass (FFM) and water balance (WT) in men. The horizontal axis represents lean body mass (FFM), and the vertical axis represents water balance (WT). In the analysis performed to determine the degree of correlation in Figure 4, the p-value was less than 0.001, indicating that lean body mass (FFM) and water balance (WT) have a high correlation with each other.

[0051] Figure 5 shows an example of the relationship between athlete level, which is an example of primary physical information, and water balance (WT) (unit: L / day). The vertical axis represents water balance (WT). Figure 5 is a box plot showing the variability of water balance (WT) according to athlete level and gender. From left to right, the graphs show the water balance (WT) of each memory subject, corresponding to female athletes, female non-athletes, male athletes, and male non-athletes. Non-athletes are those who are not athletes, i.e., those with a low daily exercise load. As shown in Figure 5, in both the case of women and men, the box corresponding to the water balance (WT) of athletes is higher than the box corresponding to the water balance (WT) of non-athletes. In other words, athlete level has a positive correlation with water balance (WT).

[0052] To accurately determine the water balance (WT), it is preferable to perform multiple regression analysis using first physical information that has a high correlation with the water balance (WT), such as the physical activity level, lean body mass, and athlete level mentioned above. For example, the determination unit 12 uses first physical information consisting of sex, age, weight, physical activity level, and athlete level as explanatory variables and performs multiple regression analysis with the water balance (WT) as the dependent variable to determine a first parameter for obtaining the water balance by weighting the physical information.

[0053] The model determination device 10 shown in Figure 1 is composed of data acquired from the DLW database as described above. It determines a first parameter for determining the water metabolism index by weighting the body information from the water balance WT and first body information stored in the storage unit 11, and sends the first parameter as the index model to the water metabolism index estimation device 1.

[0054] The following describes the details of the water metabolism index estimation device 1, which obtains the first parameter as an index model from the model determination device 10 described above and calculates the water metabolism index of the person to be estimated. The person to be estimated is a different individual from the person to be stored in the data stored in the storage unit 11 of the model determination device 10, and is the person to be subjected to the water metabolism index estimation process.

[0055] The body information acquisition unit 13 of the water metabolism index estimation device 1 acquires the physical characteristics of the person to be estimated. Specifically, the body information acquisition unit 13 acquires one or more second body information items that represent the physical characteristics of the person to be estimated numerically, and sends the acquired second body information to the water metabolism index estimation unit 14 and the health status estimation unit 21. The physical characteristics acquired by the body information acquisition unit 13 consist of the physical characteristics indicated by the first body information stored in the memory unit 11. The items of the second body information are the same as the items of the first body information, but while the first body information indicates the physical characteristics of the memory subject that is the subject of water analysis, the second body information indicates the physical characteristics of the person to be estimated.

[0056] The physical information acquisition unit 13 receives input information about the socioeconomic status of the person to be estimated via an input / output device. The physical information acquisition unit 13 also acquires second physical information, which is measured value of the physical characteristics of the person to be estimated, and other second physical information estimated from the second physical information. For example, the physical information acquisition unit 13 acquires the age, sex, weight, and body fat percentage of the person to be estimated, which are input into the body composition analyzer, from the body composition analyzer. The physical information acquisition unit 13 calculates lean body mass from weight and body fat percentage. The physical information acquisition unit 13 acquires the heart rate of the person to be estimated from the heart rate monitor, estimates exercise load from the acquired heart rate, and estimates physical activity level and athlete level. The physical information acquisition unit 13 uses the Harris-Benedict formula to calculate basal energy consumption from height, weight, and age, and calculates total energy consumption by multiplying basal energy consumption by the estimated physical activity level.

[0057] The water metabolism index estimation unit 14 weights each of the second physical information obtained from the physical information acquisition unit 13 with a first parameter obtained from the determination unit 12 of the model determination device 10 to determine the water balance WT as a second water metabolism index indicating the degree of water metabolism of the subject to be estimated. For example, the water metabolism index estimation unit 14 weights the first physical information, which consists of sex, age, weight, physical activity level, and athlete level, with a first parameter based on equation (3) below to determine the water balance WT (unit: mL / day). The weight coefficients a1, a2, a3, a4, a5 in equation (3) below are the first parameters. For example, the weight coefficients a1, a2, a3, a4, a5 are positive numbers. In equation (3) below, age is shown as age. WT=a1*PAL+a2*Weight+a3*Gender+a4*Athlete-a5*age ···(3)

[0058] The water metabolism index estimation unit 14 sends the calculated second water metabolism index to the health status estimation unit 21. The water metabolism index estimation unit 14 may also send the second water metabolism index to an output device (not shown), and the output device may output the second water metabolism index by displaying it, outputting an audible message, etc., thereby encouraging the person being estimated to take in an appropriate amount of water.

[0059] The health estimation unit 21 determines metabolic health from at least a portion of the second water metabolism index obtained from the water metabolism index estimation unit 14 and the second body information obtained from the body information acquisition unit 13. Metabolic health is an index based on factors that determine total energy expenditure and indicates whether metabolism is functioning adequately. Factors that determine total energy expenditure include, for example, physical activity level, lean body mass, athlete level, body fat percentage, and age. Metabolic health can be expressed, for example, by equation (4) below. In equation (4) below, the weight coefficients b1, b2, b3, b4, and b5 are positive coefficients. In equation (4) below, body fat percentage is shown as BFP. Metabolic health=b1*PAL+b2*FFM+b3*Athlete-b4*BFP-b5*age ···(4)

[0060] The health estimation unit 21 estimates metabolic health by weighting the factors that determine total energy expenditure but are not used to estimate water balance, along with the water balance, using a second parameter. For example, water balance is determined by weighting the physical activity level, athlete level, and age, among the factors that determine total energy expenditure as described above. In this case, the health estimation unit 21 determines metabolic health by weighting lean body mass and body fat percentage, along with water balance, among the factors that determine total energy expenditure as described above, using a second parameter, as shown in equation (5) below. The weight coefficients c1, c2, and c3 in equation (5) below are the second parameter. For example, the weight coefficients c1, c2, and c3 are positive numbers. The health estimation unit 21 is assumed to have prior information on the second parameter. Metabolic health = c1*WT+c2*FFM-c3*BFP (5)

[0061] For example, the health estimation unit 21 only needs to store information about one or more first physical information of the person to be stored in the memory unit 11, a first water metabolism index, and a second parameter obtained from the actual metabolic health level set according to the first water metabolism index. The actual metabolic health level can be determined according to the ratio of the first water metabolism index to a target water metabolism index predetermined according to gender and age. For example, if the first water metabolism index exceeds the target water metabolism index, the actual metabolic health level will be high, and if the first water metabolism index falls below the target water metabolism index, the actual metabolic health level will be low. In this case, a second parameter for obtaining metabolic health level can be obtained by weighting the physical information and the water metabolism index respectively through regression analysis with the first physical information and the first water metabolism index as explanatory variables and the actual metabolic health level as the target variable. The health estimation unit 21 only needs to store the second parameter determined as described above in advance.

[0062] As metabolic health improves, a person can be considered to be in better health. For example, if target metabolic health levels are predetermined according to gender and age, a person can be considered healthy if the metabolic health level calculated using formula (5) above is equal to or greater than the target metabolic health level.

[0063] Figure 6 shows the hardware configuration of the model determination device 10, the water metabolism index estimation device 1, and the health status estimation device 2 having the above configuration. The model determination device 10, the water metabolism index estimation device 1, and the health status estimation device 2 each include a processor 81, a memory 82, and an interface 83. The processor 81, the memory 82, and the interface 83 are connected to each other by a bus 80. The functions of each part of the model determination device 10, the water metabolism index estimation device 1, and the health status estimation device 2 are realized by software, firmware, or a combination of software and firmware. The software and firmware are written as programs and stored in the memory 82. The functions of each part are realized by the processor 81 reading and executing the programs stored in the memory 82. That is, the memory 82 stores programs for executing the processing of each part of the model determination device 10, the water metabolism index estimation device 1, and the health status estimation device 2.

[0064] Memory 82 includes, for example, non-volatile or volatile semiconductor memories such as RAM (Random Access Memory), ROM (Read-Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), and EEPROM (Electrically Erasable and Programmable Read-Only Memory), as well as magnetic disks, flexible disks, optical disks, CDs (Compact Discs), MiniDiscs, DVDs (Digital Versatile Discs), etc.

[0065] The model determination device 10 is connected to the water metabolism index estimation device 1 via interface 83. The water metabolism index estimation device 1 is connected to input / output devices, specifically body composition analyzers, heart rate monitors, etc., via interface 83. The health status estimation device 2 is connected to a display device that shows metabolic health status, etc., via interface 83. Interface 83 has one or more interface modules conforming to standards, depending on the connection destination.

[0066] The water metabolism index estimation process performed by the water metabolism index estimation unit 14 of the water metabolism index estimation device 1 having the above configuration will be explained below with reference to Figure 7. The water metabolism index estimation device 1 performs the water metabolism index estimation process for the subject at a timing independent of the process in which the model determination device 10 determines the index model. When the water metabolism index estimation device 1 is activated, it starts the process shown in Figure 7. While the second physical information of the subject has not been acquired (step S11; No), the water metabolism index estimation unit 14 repeats the process of step S11.

[0067] When the water metabolism index estimation unit 14 obtains the second physical information of the subject to estimation (step S11; Yes), it obtains the index model, specifically the first parameter, from the determination unit 12 (step S12). If the first parameter, which is the index model, has not been obtained (step S12; No), the water metabolism index estimation unit 14 repeats the process of step S11.

[0068] When the water metabolism index estimation unit 14 obtains the first parameter, which is an index model (step S12; Yes), it applies the second body information to the index model, specifically by weighting each of the second body information with the first parameter to obtain the second water metabolism index (step S13). Once the processing in step S13 is completed, the above processing is repeated from step S11.

[0069] The health estimation process performed by the health estimation unit 21 of the health estimation device 2 having the above configuration will be explained below with reference to Figure 8. When the health estimation device 2 is activated, it starts the process shown in Figure 8. The health estimation unit 21 acquires second physical information from the physical information acquisition unit 13 and second water metabolism index from the water metabolism index estimation unit 14 (step S21). If at least one of the second physical information and the second water metabolism index has not been acquired (step S21; No), the health estimation unit 21 repeats the process in step S21.

[0070] When the health estimation unit 21 obtains the second physical information and the second water metabolism index (step S21; Yes), it weights the water balance and the second physical information using the second parameter to determine metabolic health (step S22). Once the processing in step S22 is completed, the process described above is repeated from step S21.

[0071] As described above, the water metabolism index estimation device 1 according to Embodiment 1 determines a first parameter, which is a weighting coefficient for determining the water metabolism index by weighting the physical information, from the first water metabolism index and first physical information of the person to be stored. Then, the second water metabolism index of the person to be estimated is estimated by weighting each of the second physical information of the person to be estimated using the first parameter. As a result, a second water metabolism index indicating the degree of the person's water metabolism can be obtained simply by inputting the physical characteristics of the person to be estimated into the water metabolism index estimation device 1.

[0072] The water metabolism index estimation device 1 determines a first parameter from the first water metabolism index and first physical information of the subject, which are composed of data obtained from the DLW database, and then obtains a second water metabolism index by weighting the second physical information, which indicates the physical characteristics of the subject, with the first parameter. Therefore, it is not necessary to measure the water balance WT based on the doubly labeled water method each time the second water metabolism index is obtained for the subject, and the second water metabolism index can be easily determined.

[0073] (Embodiment 2) The configuration of the water metabolism index estimation device 1 is not limited to the example described above. Embodiment 2 describes a water metabolism index estimation device 3 that determines a second water metabolism index based on the physical characteristics of the subject as well as the surrounding environmental conditions of the subject.

[0074] The water metabolism index estimation device 3 shown in Figure 9 further includes an environmental information acquisition unit 15 that acquires second environmental information indicating the environmental conditions around the person being estimated, in addition to the configuration of the water metabolism index estimation device 1 according to Embodiment 1.

[0075] The DLW database also stores information indicating the environmental conditions surrounding the subject being measured. Based on the data obtained from the DLW database, the storage unit 11 stores, in association with the first physical information of each subject, the first water metabolism index of each subject, and one or more first environmental information items that numerically represent the environmental conditions surrounding each subject. The environmental conditions consist of at least one of the following: temperature, humidity, latitude, altitude, and Human Development Index (HDI). Temperature and humidity are, for example, the average values ​​of temperature and humidity over the measurement period during which the analysis based on the doubly labeled water method was performed. Latitude and altitude indicate the latitude and altitude of the location where the analysis based on the doubly labeled water method was performed, respectively. The Human Development Index is determined according to the country in which the analysis based on the doubly labeled water method was performed, based on indices calculated by the United Nations Development Programme for each country according to life expectancy, education, literacy, and income indices. For example, the Human Development Index used in Embodiment 2 is one of the following values: 1, indicating that the above indicators are high; 2, indicating that the above indicators are moderate; and 3, indicating that the above indicators are low.

[0076] As shown in Figure 10, the memory unit 11 stores the first physical information, first water metabolism index, and first environmental information of each person being stored, in association with each other. In the example in Figure 10, the first environmental information consists of temperature, humidity, latitude, altitude, and the Human Development Index (HDI). In Figure 10, the Human Development Index is shown as HDI. Each record in the table shown in Figure 10 is data corresponding to each person being stored.

[0077] The determination unit 12 acquires the water balance (WT), first physical information, and first environmental information of each data subject stored in the memory unit 11. The determination unit 12 weights the physical information and environmental information to obtain a plurality of first parameters for obtaining a water metabolism index, and sends the first parameters to the water metabolism index estimation device 3. In detail, the determination unit 12 obtains the first parameters by multiple regression analysis with the first physical information and first environmental information as explanatory variables and the first water metabolism index as the dependent variable. The determination unit 12 sends the first parameters to the water metabolism index estimation unit 14 of the water metabolism index estimation device 3.

[0078] The determination unit 12 preferably performs multiple regression analysis using the first physical information and the first environmental information, which have a high correlation with the first water metabolism index, as explanatory variables to determine the first parameter. Figure 11 shows an example of the relationship between temperature (unit: °C), which is an example of the first environmental information, and water balance WT (unit: L / day). The vertical axis represents water balance WT. Figure 11 is a box plot showing the variation in water balance WT for each temperature. The left side of the figure is a graph showing the water balance WT for each memory subject when the temperature is 18 °C. The right side of the figure is a graph showing the water balance WT for each memory subject when the temperature is 29 °C. As shown in Figure 11, the box corresponding to the water balance WT when the temperature is 29 °C is higher than the box corresponding to the water balance WT when the temperature is 18 °C. That is, temperature has a positive correlation with water balance WT.

[0079] Figure 12 shows an example of the relationship between the Human Development Index (HDI), an example of the first environmental information, and water balance WT (unit: L / day). The vertical axis represents water balance WT. Figure 12 is a box plot showing the variability of water balance WT for each Human Development Index. From left to right, the graphs show the water balance WT for each memory subject corresponding to HDI=1 (female), HDI=2 (female), HDI=3 (female), HDI=1 (male), HDI=2 (male), and HDI=3 (male). As shown in Figure 12, the position of the box corresponding to water balance WT rises as the HDI value increases. In other words, HDI has a positive correlation with water balance WT.

[0080] To accurately determine the water balance (WT), it is preferable to perform multiple regression analysis using first physical information and first environmental information that have a high correlation with the water balance (WT). As an example, the determination unit 12 determines the first parameter by performing multiple regression analysis with first physical information consisting of gender, age, weight, physical activity level, and athlete level, and first environmental information consisting of temperature, humidity, human development index, and altitude as explanatory variables, and the first water metabolism index as the dependent variable.

[0081] The model determination device 10 shown in Figure 9 is composed of data acquired from the DLW database as described above. From the water balance WT, first body information, and first environmental information stored in the storage unit 11, it determines a first parameter for determining the water metabolism index by weighting the body information and environmental information, and sends the first parameter as the index model to the water metabolism index estimation device 3.

[0082] The following describes the details of the water metabolism index estimation device 3, which obtains a first parameter as an index model from the model determination device 10 described above and determines the water metabolism index of the person to be estimated. Similar to Embodiment 1, the person to be estimated is a different individual from the person to be stored in the data stored in the storage unit 11 of the model determination device 10, and is the person to be subjected to the water metabolism index estimation process.

[0083] The environmental information acquisition unit 15 acquires the environmental conditions surrounding the person being estimated. More specifically, the environmental information acquisition unit 15 acquires one or more second environmental information items that numerically represent the environmental conditions surrounding the person being estimated, and sends the acquired second environmental information to the water metabolism index estimation unit 14. The environmental conditions acquired by the environmental information acquisition unit 15 consist of the environmental conditions indicated by the first environmental information stored in the storage unit 11.

[0084] The environmental information acquisition unit 15 acquires the location information of the estimated subject from, for example, a GPS (Global Positioning System) receiver worn by the estimated subject, and determines the Human Development Index from the location information. The environmental information acquisition unit 15 is assumed to have in advance information on the correspondence between location information and the Human Development Index defined for each country. The environmental information acquisition unit 15 uses the GPS altitude included in the estimated subject's location information as the altitude that constitutes the second environmental information.

[0085] The environmental information acquisition unit 15 acquires weather data for the location where the estimated subject is located from an external device based on the estimated subject's location information, and uses the temperature and humidity of the location obtained from the weather data as the temperature and humidity that constitute the second environmental information.

[0086] The water metabolism index estimation unit 14 weights the second physical information obtained from the physical information acquisition unit 13 and the second environmental information obtained from the environmental information acquisition unit 15 with a first parameter obtained from the determination unit 12 to determine the water balance as a second water metabolism index that indicates the degree of water metabolism of the subject being estimated. The water metabolism index estimation unit 14 sends the determined second water metabolism index to the health status estimation unit 21.

[0087] The water metabolism index estimation unit 14 calculates the water balance WT (unit: mL / day) by weighting each of the second physical information, consisting of sex, age, weight, physical activity level, and athlete level, and the second environmental information, consisting of temperature, humidity, human development index, and altitude, with a first parameter, based on equation (6) below. In equation (6) below, weight is expressed in kg, temperature in Celsius, humidity in percent, and altitude in meters. The weighting coefficients a1, a2, a3, a4, a5, a6, a7, a8, a9 in equation (6) below are the first parameters. For example, the weighting coefficients a1, a2, a3, a4, a5, a6, a7, a8, a9 are positive numbers. WT=a1*PAL+a2*Weight+a3*Gender+a4*Athlete-a5*age+a6*Temperature+a7*Humidity+a8*HDI+a9*Altitude...(6)

[0088] As an example, the water balance WT can be calculated by weighting the second physical information and the second environmental information with the first parameter, as shown in equation (7) below. WT=1020*PAL+14.26*Weight+395.5*Gender+30.39*Temperature+6.129*Humidity+896.0*Athlete+229.2*HDI+0.2654*Altitude-13.05*age...(7)

[0089] The weighted second physical information shall include numerical values ​​obtained by performing calculations on the second physical information, for example, powers of the second physical information. Similarly, the weighted second environmental information shall include numerical values ​​obtained by performing calculations on the second environmental information, for example, powers of the second environmental information. The water balance WT is not limited to equation (7) above, but may also be obtained by weighting the second physical information and the second environmental information with the first parameter, as shown in (8) below. In equation (8) below, (age)^2 represents the square of age, and (temperature)^2 represents the square of temperature. In equation (8) below, -713.1 is a constant. WT = 1076 * PAL + 14.34 * Weight + 374.9 * Gender + 5.823 * Humidity + 1070 * Athlete + 104.6 * HDI + 0.4726 * Altitude - 0.3529 * (age)^2 + 24.78 * Age + 1.865 * (Temperature)^2 - 19.66 * Temperature - 713.1 ... (8)

[0090] The hardware configuration of the water metabolism index estimation device 3 having the above configuration is the same as that of the water metabolism index estimation device 1 according to Embodiment 1. The water metabolism index estimation process performed by the water metabolism index estimation unit 14 of the water metabolism index estimation device 3 having the above configuration will be described below with reference to Figure 13. The water metabolism index estimation device 3 performs the water metabolism index estimation process for the person to be estimated at a timing independent of the process in which the model determination device 10 determines the index model. When the water metabolism index estimation device 3 is activated, it starts the process shown in Figure 13. As long as at least one of the second physical information and second environmental information of the person to be estimated has not been acquired (step S31; No), the water metabolism index estimation unit 14 repeats the process of step S31.

[0091] When the water metabolism index estimation unit 14 acquires the second physical information and second environmental information of the person to be estimated (step S31; Yes), it acquires the index model, specifically the first parameter, from the determination unit 12 (step S12). The processing from step S12 onward is the same as the processing performed by the water metabolism index estimation device 1 according to Embodiment 1 shown in Figure 7.

[0092] As described above, the water metabolism index estimation device 3 according to Embodiment 2 determines a first parameter, which is a weighting coefficient for obtaining the water metabolism index by weighting the physical information and environmental information, from the first water metabolism index, first physical information, and first environmental information of the person to be stored. The second water metabolism index of the person to be estimated is then estimated by weighting the second physical information and second environmental information of the person to be estimated using the first parameter. As a result, a second water metabolism index indicating the degree of water metabolism of the person to be estimated can be obtained simply by inputting the physical characteristics and surrounding environmental conditions of the person to be estimated into the water metabolism index estimation device 3.

[0093] Similar to Embodiment 1, it is not necessary to measure the water balance (WT) based on the double-labeled water method each time the second water metabolism index is determined for the estimated subject, making it possible to easily determine the second water metabolism index. By determining the second water metabolism index based on the environmental conditions surrounding the estimated subject in addition to the subject's physical characteristics, the second water metabolism index can be obtained with greater accuracy.

[0094] This disclosure is not limited to the examples described above. The first physical information and first environmental information stored in the storage unit 11 are not limited to the examples described above, and can be any data obtained from the DLW database or data derived from the data obtained from the DLW database.

[0095] The method for determining the first parameter in the determination unit 12 is not limited to the example described above. For example, the determination unit 12 may determine the first parameter by simple linear regression analysis using one type of first physical information as the explanatory variable and the water balance WT as the objective function.

[0096] As another example, the decision unit 12 learns the first body information and water balance WT stored in the memory unit 11, and obtains an index model, which is a neural network model that takes the body information as input and outputs a water metabolism index. In detail, the decision unit 12 learns training data consisting of the first body information and water balance WT, takes the body information as input values ​​and the water balance as output values, and generates a neural network model having an input layer, a hidden layer, and an output layer. Based on the training data consisting of the first body information and water balance WT, the decision unit 12 adjusts the weights between the input layer and the hidden layer, the weights between the hidden layers, and the weights between the hidden layer and the output layer.

[0097] As another example, the decision unit 12 learns the first physical information, water balance WT, and first environmental information stored in the memory unit 11, and obtains an index model, which is a neural network model that takes the physical information and environmental information as inputs and outputs a water metabolism index. In detail, the decision unit 12 learns training data consisting of the first physical information, water balance WT, and first environmental information, takes the physical information and environmental information as input values ​​and the water balance as output values, and generates a neural network model having an input layer, a hidden layer, and an output layer. Based on the training data consisting of the first physical information, water balance WT, and first environmental information, the decision unit 12 adjusts the weights between the input layer and the hidden layer, the weights between the hidden layers, and the weights between the hidden layer and the output layer.

[0098] Indicators of the degree of water metabolism are not limited to water balance. For example, the water metabolism ratio obtained by dividing water balance by body water volume may be used as an indicator of water metabolism.

[0099] The physical information acquisition unit 13 may acquire second physical information, which is a measured value of the physical characteristics of the person to be estimated, and other second physical information, which is an estimated value estimated from the measured value. For example, the physical information acquisition unit 13 may estimate the body fat percentage from the height and weight obtained from the body composition analyzer.

[0100] As shown in Figure 14, the physical information acquisition unit 13 and the environmental information acquisition unit 15 may acquire the estimated subject's heart rate, location information, etc., from an external device 31 capable of measuring the estimated subject's biometric information and the surrounding environmental conditions, such as a smartwatch.

[0101] The method for estimating metabolic health is not limited to the examples described above. Based on either equation (4) or (5) above, metabolic health estimated from the first physical information and water balance WT of each person being stored may be stored in the storage unit 11. In this case, the health estimation unit 21 may obtain a health model for deriving metabolic health from physical information and water metabolism indicators from the correspondence between the first physical information, water balance WT, and metabolic health stored in the storage unit 11. The health estimation unit 21 may also obtain metabolic health by applying second physical information to the health model.

[0102] The hardware configuration and flowchart described above are examples and can be changed and modified as needed. The central part that performs control processing, which includes a processor 81, memory 82, and interface 83, can be implemented using a normal computer system, not a dedicated system. For example, a computer program for performing the above operations may be stored on a computer-readable recording medium (flexible disk, CD-ROM (Compact Disc-Read Only Memory), DVD-ROM (Digital Versatile Disc-Read Only Memory), etc.) and distributed, and the model determination device 10, water metabolism index estimation devices 1 and 3, and health status estimation device 2 that perform the above processing may be configured by installing the computer program on a computer. Alternatively, the computer program may be stored on a storage device of a server device on a communication network, and the model determination device 10, water metabolism index estimation devices 1 and 3, and health status estimation device 2 may be configured by downloading it from a normal computer system.

[0103] If the functions of the model determination device 10, the water metabolism index estimation devices 1 and 3, and the health status estimation device 2 are realized through a division of labor between the OS (Operating System) and application programs, or through collaboration between the OS and application programs, then only the application program portion may be stored on a recording medium or storage device.

[0104] It is also possible to superimpose a computer program onto a carrier wave and distribute it via a communication network. For example, the computer program could be posted on a bulletin board system (BBS) on a communication network and distributed via the network. This computer program could then be launched and executed under the control of the OS, similar to other application programs, thereby enabling the execution of the aforementioned processes.

[0105] The hardware configuration of the model determination device 10, the water metabolism index estimation devices 1 and 3, and the health status estimation device 2 is not limited to the example described above. The model determination device 10, the water metabolism index estimation devices 1 and 3, and the health status estimation device 2 may be implemented by a processing circuit 84, as shown in Figure 15. The processing circuit 84 is connected to input / output devices, etc., via an interface circuit 85.

[0106] If the processing circuit 84 is dedicated hardware, it may be, for example, a single circuit, a composite circuit, a processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The model determination device 10, the water metabolism index estimation devices 1 and 3, and the health status estimation device 2 may be implemented by individual processing circuits 84 or by a common processing circuit 84.

[0107] Some functions of the model determination device 10, the water metabolism index estimation devices 1 and 3, and the health status estimation device 2 may be implemented by dedicated hardware, while other functions may be implemented by software or firmware. For example, in the water metabolism index estimation device 1 according to Embodiment 1, the body information acquisition unit 13 may be implemented by the processing circuit 84 shown in Figure 15, and the water metabolism index estimation unit 14 may be implemented by the processor 81 shown in Figure 6 reading and executing a program stored in memory 82.

[0108] The embodiments described above are for illustrative purposes only and do not limit the scope of the disclosure. That is, the scope of the disclosure is defined by the claims, not by the embodiments. Various modifications made within the scope of the claims and the equivalent scope of the invention are considered to be within the scope of the disclosure.

[0109] This application is based on Japanese Patent Application No. 2022-132055, filed on 22 August 2022. The entire specification, claims, and drawings of Japanese Patent Application No. 2022-132055 are incorporated herein by reference. [Explanation of symbols]

[0110] 1,3 Water metabolism index estimator 2 Health level estimation device 10 Model Determination Devices 11 Storage section 12. Decision Section 13 Physical information acquisition department 14 Water metabolism index estimation section 15 Environmental Information Acquisition Department 21 Health Level Estimation Department 31 External equipment 80 bus 81 processors 82 memory 83 Interfaces 84 Processing Circuit 85 Interface Circuit

Claims

1. A memory unit that stores, for multiple individuals to be stored, one or more first physical information items that numerically represent the physical characteristics of the individuals to be stored, and a first water metabolism index that indicates the degree of water metabolism of the individuals to be stored over a specified period, determined based on the doubly labeled water method, in association with each other. A determination unit determines an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, based on the correspondence between the first physical information and the first water metabolism index of each of the memory subjects, A model determination device equipped with the following features.

2. The determination unit determines one or more first parameters for obtaining the water metabolism index by weighting each of the physical information variables through regression analysis, with the first physical information as the explanatory variable and the first water metabolism index as the objective function. The model determination device according to claim 1.

3. The determination unit learns the first physical information and the first water metabolism index, and obtains the index model, which is a neural network model that takes the physical information as input and outputs the water metabolism index. The model determination device according to claim 1.

4. The memory unit stores, for each of the multiple individuals to be stored, the first physical information, the first water metabolism index, and one or more pieces of first environmental information that numerically represent the environmental conditions surrounding each individual. The model determination device according to claim 1.

5. The determination unit determines the index model for deriving the water metabolism index from the physical information and environmental information that numerically represents the environmental state, based on the correspondence between the first physical information, the first water metabolism index, and the first environmental information of each of the individuals to be stored. The model determination device according to claim 4.

6. The determination unit uses the first physical information and the first environmental information as explanatory variables and the first water metabolism index as the objective function to perform a regression analysis to obtain a plurality of first parameters for obtaining the water metabolism index by weighting the physical information and the environmental information respectively. The model determination device according to claim 5.

7. The determination unit uses the first physical information, consisting of physical activity level, weight, gender, athlete level, and age, and the first environmental information, consisting of temperature, humidity, and human development index, as explanatory variables, and determines the plurality of first parameters by multiple regression analysis with the first water metabolism index as the objective function. The model determination device according to claim 6.

8. The determination unit learns the first physical information, the first water metabolism index, and the first environmental information, and obtains the index model, which is a neural network model that takes the physical information and the environmental information as input and outputs the water metabolism index. The model determination device according to claim 5.

9. A physical information acquisition unit that acquires one or more second physical information items that represent the physical characteristics of the estimated subject in numerical form, A model obtained by associating one or more first physical information items that numerically represent the physical characteristics of multiple memory subjects with a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, which is determined based on the doubly labeled water method, and comprising a water metabolism index estimation unit that obtains an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and obtains a second water metabolism index that indicates the degree of water metabolism of the estimated subject by applying the second physical information to the index model, A device for estimating water metabolism indicators, equipped with the following features.

10. The physical information acquisition unit acquires one or more second physical information items which are measured values ​​of the physical characteristics of the estimated subject, and one or more other second physical information items which are estimated from the second physical information items. The water metabolism index estimation device according to claim 9.

11. The physical information acquisition unit acquires one or more second physical information items which are measured values ​​of the physical characteristics of the estimated subject, and one or more other second physical information items whose values ​​are predetermined. The water metabolism index estimation device according to claim 9.

12. The aforementioned physical characteristics consist of at least one of the following: sex, age, weight, lean body mass, physical activity level, total energy expenditure, socioeconomic status, and athlete level indicating the intensity of daily exercise. A water metabolism index estimation device according to any one of claims 9 to 11.

13. The system further includes an environmental information acquisition unit that acquires one or more second environmental information items that numerically represent the environmental conditions surrounding the estimated target person, The water metabolism index estimation unit obtains an index model obtained from the correspondence between the first physical information of the plurality of memory subjects, the first water metabolism index, and one or more first environmental information that numerically represents the environmental state around the memory subjects, and obtains the index model for deriving the water metabolism index from the physical information and environmental information representing the environmental state, and obtains the second water metabolism index by applying the second physical information and the second environmental information to the index model. A water metabolism index estimation device according to any one of claims 9 to 11.

14. The environmental information acquisition unit acquires one or more of the second environmental information, which are measured values ​​of the environmental conditions around the estimated subject, and one or more other second environmental information estimated from the second environmental information. The water metabolism index estimation device according to claim 13.

15. The environmental information acquisition unit acquires one or more of the second environmental information, which are measured values ​​of the environmental conditions around the estimated subject, and one or more other second environmental information, which have predetermined values. The water metabolism index estimation device according to claim 13.

16. The aforementioned environmental conditions consist of at least one of the following: temperature, humidity, latitude, altitude, and the Human Development Index. The water metabolism index estimation device according to claim 13.

17. A water metabolism index estimation device according to any one of claims 9 to 11, A health status estimation unit that determines metabolic health status by weighting the second water metabolism index and the second physical information with a predetermined second parameter, A health status estimation device equipped with the following features.

18. A model determination method performed by a model determination device, A model is determined for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, based on the correspondence between one or more first physical information items that numerically represent the physical characteristics of multiple memory subjects and a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, which is determined based on the doubly labeled water method. Model selection method.

19. A method for estimating a water metabolism index performed by a water metabolism index estimation device, Obtain one or more second physical information items that represent the physical characteristics of the estimated subject in numerical form, A model obtained by associating one or more first physical information items that numerically represent the physical characteristics of multiple memory subjects with a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, which is determined based on the doubly labeled water method, wherein an index model is obtained for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and a second water metabolism index that indicates the degree of water metabolism of the estimated subject is obtained by applying the second physical information to the index model. Method for estimating water metabolism index.

20. A method for estimating health status performed by a health status estimation device, Obtain one or more second physical information items that represent the physical characteristics of the estimated subject in numerical form, A model obtained by associating one or more first physical information items that numerically represent the physical characteristics of multiple memory subjects with a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, which is determined based on the doubly labeled water method, wherein an index model is obtained for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and a second water metabolism index that indicates the degree of water metabolism of the estimated subject is obtained by applying the second physical information to the index model, Metabolic health is determined by weighting the second water metabolism index and the second physical information with a predetermined second parameter. Health level estimation method.

21. Computers, A memory unit that stores, for multiple individuals, one or more first physical information items that numerically represent the physical characteristics of the individuals to be stored, and a first water metabolism index that indicates the degree of water metabolism of the individuals to be stored over a specified period, determined based on the double-labeled water method, in association with each other, and A determination unit determines an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, based on the correspondence between the first physical information and the first water metabolism index of each of the aforementioned memory subjects. A program that makes it function as such.

22. Computers, A body information acquisition unit that acquires one or more second body information items that numerically represent the physical characteristics of the estimated target person, and A model obtained by associating one or more first physical information items that numerically represent the physical characteristics of multiple memory subjects with a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, which is determined based on the doubly labeled water method, wherein a water metabolism index estimation unit obtains an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and obtains a second water metabolism index that indicates the degree of water metabolism of the estimated subject by applying the second physical information to the index model, A program that makes it function as such.

23. Computers, A physical information acquisition unit that acquires one or more second physical information items that represent the physical characteristics of the estimated subject in numerical form. A model obtained by associating one or more first physical information items that numerically represent the physical characteristics of multiple memory subjects with a first water metabolism index that indicates the degree of water metabolism of the memory subject over a specified period, which is determined based on the doubly labeled water method, and comprising a water metabolism index estimation unit that obtains an index model for deriving a water metabolism index that indicates the degree of water metabolism from physical information that indicates physical characteristics, and obtains a second water metabolism index that indicates the degree of water metabolism of the estimated subject by applying the second physical information to the index model, and A health status estimation unit that determines metabolic health status by weighting the second water metabolism index and the second physical information with a predetermined second parameter. A program that makes it function as such.

Images