JP7065550B1 - Information processing system, server, information processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing system, a server, a method and a program for providing frail index information indicating a frail state, based on measurement data, via a frail index information generation unit. SOLUTION: A management server in an information processing system having a management server, a user terminal and a measuring device is predetermined based on change information of biometric data within a determination period in which the time when exercise intensity of a predetermined value or higher occurs is used as reference time information. Based on the responsiveness index information showing how the biometric data responds to the generation of the above exercise intensity, and the change information of the biometric data from the response state or the operating state to the resting state, the exercise intensity of the predetermined or higher The user's A frail index information generation unit for generating frail index information for indicating a frail state is provided. [Selection diagram] Fig. 1

Description

The present disclosure relates to an information processing system, a server, an information processing method and a program that generate frail index information based on measurement data acquired from a measuring device.

It is said that increasing muscle strength is useful for preventing diseases associated with senility such as dementia, and it is important to prevent frailty syndrome by actively exercising on a daily basis.

The determination of frailty is also important. For example, Patent Document 1 discloses a determination method for asking a question to a subject and calculating the total score of answers, and Patent Document 2 discloses an interview with a recipient. A frailty medical examination system that outputs the result of the frailty examination based on the result and the result of the balance measurement test in the standing posture is disclosed.

Japanese Unexamined Patent Publication No. 2021-177282 Japanese Patent No. 6943395

However, as wearable device technology has been developed in recent years, a method for determining frailty based on daily operations is desired.

Therefore, in the present disclosure, an information processing system, a server, an information processing method, and a program that generate frail index information based on measurement data acquired from a measuring device worn by a user will be described.

The information processing system according to one aspect of the present disclosure is an information processing system that receives measurement data from a measuring device worn by a user via a network and generates biometric data and frail index information from the measured data. Based on the change information of the biological data within the judgment period using the time when the above exercise intensity occurs as the reference time information, the response showing how the biological data responds to the occurrence of the predetermined or higher exercise intensity. At least of the recoverability index information indicating how the person recovers from the response due to the generation of exercise intensity equal to or higher than the predetermined value based on the sex index information or the change information of the biological data from the response state or the operating state to the resting state. Frail index information generation that generates any of them and generates frail index information for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. It is equipped with a department.

The server in one aspect of the present disclosure is a server that receives measurement data from a measuring device worn by a user via a network and generates biometric data and frail index information from the measured data, and is a server having a predetermined or higher exercise intensity. Responsiveness index information indicating how the biometric data responds to the occurrence of exercise intensity equal to or higher than the predetermined value, based on the change information of the biometric data within the determination period using the time when the occurrence of the above is used as the reference time information. Alternatively, based on the change information of the biometric data from the response state or the operating state to the resting state, at least one of the recoverability index information indicating how the response is recovered from the response due to the generation of the predetermined or higher exercise intensity is generated. Then, a frail index information generation unit that generates frail index information for indicating the frail state of the user based on at least one of the responsiveness index information or the recoverability index information and the correspondence information stored in advance. Be prepared.

The information processing method according to one aspect of the present disclosure is an information processing method that receives measurement data from a measuring device worn by a user via a network and generates biometric data and frail index information from the measured data. Based on the change information of the biometric data within the judgment period in which the time when the exercise intensity of the predetermined value or more occurs is used as the reference time information by the index information generation unit, how the biometric data is generated for the generation of the exercise intensity of the predetermined value or more. Based on the responsiveness index information indicating whether or not the patient is responding, or the change information of the biometric data from the response state or the operating state to the resting state, how the person recovers from the response due to the generation of exercise intensity equal to or higher than the predetermined value. Frail index information for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the resiliency index information to be shown and at least one of the responsiveness index information or the recoverability index information. Includes steps to generate.

The program in one aspect of the present disclosure causes an information processing system to execute an information processing method that receives measurement data from a measuring device worn by a user via a network and generates biometric data and frail index information from the measured data. In the program, the information processing method is based on the change information of the biological data within the determination period in which the time when the exercise intensity of the predetermined value or more is generated is used as the reference time information by the frail index information generation unit, and the exercise of the predetermined value or more is performed. Based on the responsiveness index information showing how the biometric data responds to the generation of intensity, or the change information of the biometric data from the response state or the operating state to the resting state, the exercise intensity of the predetermined or higher Based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information, which is generated, at least one of the recoverability index information indicating how the recovery is made from the response due to the occurrence. A step of generating frail index information for indicating the frail state of the user is included.

According to the present disclosure, the information processing system according to the present embodiment generates frail index information relating to a user's frail state, based on measurement data or biometric data, via a frail index information generation unit 133. This makes it possible to grasp the frail state of the person to be measured, for example.

It is a block block diagram which shows the information processing system which concerns on one Embodiment of this disclosure. It is a figure which shows the hardware configuration of the management server 100 of FIG. It is a block diagram illustrating the function of the storage unit 120 and the control unit 130 of FIG. It is a schematic diagram which shows the example of the tag information associated with the measurement data of FIG. It is a figure for demonstrating the example of the electrocardiographic waveform and the pulse waveform measured by the measuring apparatus 300 of FIG. It is a flowchart which shows the example of the processing of the information processing system 1 of FIG.

The contents of the embodiments of the present invention will be described in a list. The system according to the embodiment of the present invention has the following configurations.

[Item 1]
An information processing system that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frail index information from the measurement data.
Based on the change information of the biometric data within the judgment period using the time when the exercise intensity of the predetermined or higher occurs as the reference time information, it shows how the biometric data responds to the occurrence of the exercise intensity of the predetermined or higher. Resilience index information indicating how the response is recovered from the response due to the generation of exercise intensity higher than the predetermined value based on the response index information or the change information of the biological data from the response state or the operating state to the resting state. Frail index information that generates at least one of them and generates frail index information for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. With a generator,
An information processing system characterized by this.
[Item 2]
The frailty index information generation unit uses cardiovascular information including at least one of heart rate information and blood pressure information as biometric data within the determination period.
The information processing system according to item 1, wherein the information processing system is characterized by the above.
[Item 3]
The frailty index information generation unit performs clustering based on the exercise intensity information indicating the exercise intensity associated with at least one of the responsiveness index information and the recoverability index information, and corresponds to each clustered exercise intensity information. Generate the frailty index information based on the relationship information,
The information processing system according to item 1 or 2, wherein the information processing system is characterized by the above.
[Item 4]
The exercise intensity is an index based on data obtained from the inertial sensor of the measuring device.
The information processing system according to any one of items 1 to 3, characterized in that.
[Item 5]
A server that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frailty index information from the measurement data.
Based on the change information of the biometric data within the judgment period using the time when the exercise intensity of the predetermined or higher occurs as the reference time information, it shows how the biometric data responds to the occurrence of the exercise intensity of the predetermined or higher. Resilience index information indicating how the response is recovered from the response due to the generation of exercise intensity higher than the predetermined value based on the response index information or the change information of the biological data from the response state or the operating state to the resting state. Frail index information that generates at least one of them and generates frail index information for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. With a generator,
A server that features that.
[Item 6]
It is an information processing method that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frailty index information from the measurement data.
Based on the change information of the biometric data within the judgment period in which the time when the exercise intensity of the predetermined value or more occurs is used as the reference time information by the frail index information generation unit, how the biometric data is for the generation of the exercise intensity of the predetermined value or more. Based on the responsiveness index information indicating whether or not the patient is responding to, or the change information of the biological data from the response state or the operating state to the resting state, how to recover from the response due to the generation of exercise intensity higher than the predetermined value. A frail index for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. Including steps to generate information,
An information processing method characterized by that.
[Item 7]
A program that causes an information processing system to execute an information processing method that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frail index information from the measurement data.
The information processing method is
Based on the change information of the biometric data within the judgment period in which the time when the exercise intensity of the predetermined value or more occurs is used as the reference time information by the frail index information generation unit, how the biometric data is for the generation of the exercise intensity of the predetermined value or more. Based on the responsiveness index information indicating whether or not the patient is responding to, or the change information of the biological data from the response state or the operating state to the resting state, how to recover from the response due to the generation of exercise intensity higher than the predetermined value. A frail index for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. Including steps to generate information,
A program characterized by that.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The embodiments described below do not unreasonably limit the contents of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure. In addition, the features shown in each embodiment can be applied to other embodiments as long as they do not contradict each other.

(Embodiment 1)
<Structure>
FIG. 1 is a block configuration diagram showing an information processing system 1 according to the first embodiment of the present disclosure. The information processing system 1 receives, for example, the user's measurement data from the measurement device 300 via the network NW on the management server 100, and generates biometric data by performing a predetermined calculation on the measurement data. It is a system that generates frail index information based on the biometric data.

The information processing system 1 has a management server 100, a user terminal device 200, a measuring device 300, and a network NW. The management server 100 and the user terminal device 200 are connected via the network NW. The network NW is composed of the Internet, an intranet, a blockchain network, a wireless LAN (Local Area Network), a WAN (Wide Area Network), and the like.

The management server 100 is, for example, a device that receives user's measurement data from the measurement device 300 via a network via the user terminal device 200 and calculates the measurement data into biometric data, for example, various Web services. It consists of the server equipment provided.

The user terminal device 200 is an information processing device possessed by the user, such as a personal computer, a tablet terminal, a smartphone, a smart watch, a mobile phone, a PHS, or a PDA. It is used to display by a waveform graph or the like, or to display the data generated based on biometric data (details will be described later). User information such as a user's identification number, date of birth, gender, height, and weight is registered in the user terminal device 200 in advance, and user information including the age calculated from the date of birth is associated with the measurement data. Is transmitted to the management server 100 via the network NW.

Further, the user terminal device 200 may use a touch panel or the like to input a state in which the user acquires data by the measuring device 300. The user terminal device 200 can input the "state for acquiring data" as tag information such as "running" when running and "mealing" when eating. In this case, the user terminal device 200 transmits the measurement data received from the measuring device 300 at a predetermined periodic timing to the management server 100 via the network NW in association with the tag information.

The measuring device 300 is a device that measures the user's measurement data, and the measuring device 300 uses a known method to obtain data of, for example, the user's electrocardiogram, pulse wave, skin temperature (body temperature), acceleration, and angular velocity. It is a device for measuring at periodic timing. The predetermined cycle may be preset or may be arbitrarily set by the user. More specifically, for example, a time cycle in seconds may be set, or the same may be set depending on the frequency. The user of the user terminal device 200 and the user (measured person) of the measuring device 300 may be the same or different.

As an example of the specific configuration of the measuring device 300, a device may be configured in which two electrodes are brought into contact with the skin and the electrocardiogram is acquired as electrocardiographic waveform data from the time change of the difference in the detected potential. The radio wave type may be data acquired by a galvanic skin reaction. In addition, each light is radiated to the skin from LEDs that emit green, red, and infrared light, and the pulse wave is generated by the change in the volume of the blood vessel caused by the heartbeat of the user's heart due to the time change of the intensity of the light received by the photodiode. It may be configured by a device that acquires pulse waveform data, and the pulse waveform that can be detected by this method is a photoelectric volume pulse waveform. Further, the device may be configured to acquire the user's skin temperature as data by a temperature sensor in contact with the user's skin. Further, it may be configured by a 3-axis acceleration sensor that detects the variation state of each of the orthogonal XYZ axes, and the user's motion is acquired as acceleration data, and for example, the measuring device 300 is attached to the user's wrist, arm, or the like. In this case, the measuring device 300 acquires acceleration data as an acceleration in which the swing of the wrist, arm, or the like and the movement of the whole body are combined. Further, it may be configured by a gyro sensor (angular velocity sensor) that detects the rotational angular velocity in each of the orthogonal XYZ axes, and acquires the user's motion as angular velocity data, for example, the measuring device 300 is attached to the user's wrist, arm, or the like. If so, the measuring device 300 acquires the angular velocity data as the angular velocity in which the rotation of the wrist, the arm, or the like and the movement of the whole body are combined.

Between the user terminal device 200 and the measuring device 300, Bluetooth (registered trademark), Near Field radio Communication (NFC), Afero (registered trademark), Zigbee (registered trademark), Z-Wave (registered trademark). ) Or is connected using a wireless LAN or the like. In addition, instead of such a wireless connection, a wired connection may be made. Further, the user terminal device 200 and the measuring device 300 may be an integrated device. For example, the measuring device 300 may be provided with a communication function so as to be able to directly communicate with the management server 100. May be good.

There are one or a plurality of user terminal devices 200, and they are connected to the network NW for the number of users who use the measuring device 300. There are one or a plurality of measuring devices 300, and they are connected to the number of user terminal devices 200 used by one user. When one user uses a plurality of measuring devices 300, the plurality of measuring devices 300 are connected to one user terminal device 200.

<Management server 100>
FIG. 2 is a diagram showing a hardware configuration of the management server 100. FIG. 3 is a block diagram illustrating the functions of the storage unit 120 and the control unit 130. The configuration shown in the figure is an example, and may have other configurations.

The management server 100 includes a communication unit 110, a storage unit 120, a control unit 130, and an input / output unit 140. These functional units are realized by executing a predetermined program for the management server 100.

The communication unit 110 is a communication interface for communicating with the user terminal device 200, and communication is performed according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol).

The storage unit 120 stores programs for executing various control processes and functions in the control unit 130, input data, and the like, and is composed of a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. To. Further, as shown in FIG. 3, the storage unit 120 associates the measurement data DB 121, which stores the measurement data by the measuring device 300 with the user information, and the biometric data calculated from the measurement data with the user information. The biometric data DB 122 to be stored, the frail index information DB 123 to store the frail index information generated based on the measurement data or the biometric data in association with the user information, the user information DB 124 to store the user information including the user identification information, and the user information DB 124. Remember. Further, the user identification information may be account information generated by the data management unit 131, application identification information of an application downloaded to the user terminal device 200, or user terminal identification information of the user terminal device. good. Further, the storage unit 120 temporarily stores the data that has communicated with the user terminal device 200. The data structure of the DB is not limited to this, and a part of the above-mentioned DB may be stored in the user terminal device 200 or the measuring device 300.

The control unit 130 controls the overall operation of the management server 100, and is composed of a CPU (Central Processing Unit) and the like. Further, as shown in FIG. 3, the control unit 130 includes functional units such as a data management unit 131, a biological data generation unit 132, a frail index information generation unit 133, and a data output unit 134.

The data management unit 131 sets user identification information for each user who uses the measuring device 300. For example, when the user identification information is account information, the account information is generated when the user who uses the measuring device 300 registers the account information on the user terminal device 200. Therefore, the data management unit 131 controls whether or not the user terminal device 200 of the user can access various DBs in the storage unit 120 for each account. The data management unit 131 stores various data such as measurement data, biometric data, and frail index information in association with user information including user identification information in a corresponding DB. Further, at this time, the data management unit 131 may associate the measurement data with predetermined tag information and store it.

FIG. 4 is a schematic diagram showing an example of tag information associated with the measurement data of FIG. The data D1 shown in FIG. 4 is the measurement data of the measuring device 300. The tag T1 is tag information associated with the data D1, and for example, the time information in which the measuring device 300 measures the data D1 or the time information in which the data D1 is transmitted from the measuring device 300 to the user terminal device 200 is time-series. It is stored as data. Alternatively, both the measured time information and the transmitted time information may be associated. For example, in the first line of the tag T1 shown in FIG. 4, "20180620120746144" is stored, but it indicates 12:07:46:144 ms on June 20, 2018. Such time information can be obtained from the communication log. This makes it possible to grasp which time zone the measurement data belongs to.

It should be noted that the association of measurement data with such tag information is not limited to time information, and even if the user is allowed to freely enter physical information and behavior information indicating the user's physical condition and behavior content and stored as tag information. It is good, and the user is made to select from a predetermined option (for example, in response to the question "How are you currently feeling?", One of "1: good, 2: normal, 3: bad" is selected. Etc.), the selected answer may be memorized. Furthermore, for example, based on other measurement data and biological data (for example, walking speed information, stride information, motion information of the wearing site, posture information, position information of the center of gravity, heartbeat information, etc.), predetermined actions (for example, sitting position, standing position, etc.) , Lying, walking, running, sleeping, waking up, going to bed, eating, driving, resting, etc.) may be estimated by a known method and associated with biometric data or the like as tag information (behavior type information). At this time, for example, the learning model may be estimated by a learning model learned based on the measurement data for teachers, or the learning model may be personalized by performing additional learning based on the result of the above-mentioned recording by the user. As a result, when the control unit 150 generates biometric data such as blood pressure information, by associating the tag information with the biometric data, more accurate biometric data can be generated and generated based on the tag information. The frail index information to be generated can also be more personalized data.

The biometric data generation unit 132 performs a predetermined operation on the measurement data stored in the measurement data DB 121 to generate biometric data. The generation of biometric data is not limited to the one directly generated by calculating the measurement data, and new biometric data may be generated based on one or more generated biometric data separately generated. The biometric data includes, for example, user's blood pressure information, heartbeat information, blood oxygen level information, maximum oxygen intake information, electrocardiographic information, respiratory rate, body temperature information, blood glucose level information, step count information, stride length information, and center of gravity position information. Data such as posture information, action type information, stress information, exercise amount information, exercise load information, movement distance information, walking speed information, activity amount information, movement information of hands or legs, etc. Although it is calculated, it is not limited to these. The biometric data generated by the calculation is stored in the biometric data DB 122.

In addition, for example, measurement data by a known learning device, biometric data generated based on the measurement data (for example, heartbeat information, blood pressure information, etc.) and positive biometric data (for example, heartbeat information based on known medical equipment, etc.) A learning model is created in advance based on the teacher data associated with the correspondence (for example, information indicating the degree and range of the error may be included) with the blood pressure information, etc., and the biological data generation unit 132. May generate biometric data using the determination using the learning model as the above-mentioned predetermined calculation (analysis).

Here, a method of calculating the maximum blood pressure and the minimum blood pressure, which are biological data, from the measurement data will be exemplified. FIG. 5 is a diagram for explaining an example of an electrocardiographic waveform and a pulse wave measured by the measuring device 300 of FIG. 1, and is a diagram for explaining an example of the electrocardiographic waveform measured by the measuring device 300 and stored in the storage unit 120. And the photoelectric volume pulse waveform, the velocity pulse waveform in which the photoelectric volume pulse waveform is first-order differentiated by time, and the acceleration pulse waveform in which the photoelectric volume pulse waveform is second-order differentiated by time are shown. FIG. 5 shows an electrocardiographic waveform, a photoelectric volume pulse waveform, a velocity pulse waveform, and an acceleration pulse waveform in order from the top. The vertical axis shows the intensity of each waveform, and the electrocardiographic waveform and the photoelectric volume pulse waveform are represented by MV indicating the potential. The horizontal axis shows the passage of time, and shows the passage of time from left to right.

An electrocardiographic waveform is a waveform showing a periodic change in an electrical signal that causes a person's heart to beat. In the electrocardiographic waveform, the names of P wave, Q wave, R wave, S wave, and T wave are assigned to the turning points of the shape, respectively, and indicate one cycle of the heartbeat. The P wave represents the atrial contraction, the Q wave, the R wave, and the S wave represent the state of ventricular contraction, and the T wave represents the start of ventricular dilation.

The photoelectric volume pulse waveform is a waveform showing changes in blood pressure and volume in the peripheral vascular system accompanying the beating of the human heart. In the photoelectric volume pulse waveform, the names of A wave, P wave, V wave, and D wave are assigned to the inflection points of the shape, respectively, and indicate one cycle of the heartbeat. Using the A wave as the reference point at the time when the arterial pulse wave is generated, the P wave is the Percussion wave (shock wave) generated by the ejection of the left ventricle, the V wave is the Valley wave (wave due to the overlapping uplift) generated when the aortic valve is closed, and the D wave. Indicates a Dicrotic wave (overlapping wave) which is a reflected vibration wave.

The velocity pulse waveform is the first derivative of the photoelectric volume pulse waveform with respect to time. The acceleration pulse waveform is a first-order derivative of the velocity pulse waveform, that is, a second-order derivative of the photoelectric volume pulse waveform. As shown in FIG. 5, the acceleration pulse waveform has a wave (initial contraction positive wave), b wave (initial contraction negative wave), c wave (middle contraction re-rise wave), and d wave (contraction) at each peak of the waveform. The names of the late re-descending wave), the e wave (extended early positive wave), and the f wave (extended early negative wave) are assigned.

The ratio of the intensity of the b wave to the intensity of the a wave and the ratio of the intensity of the f wave to the intensity of the e wave are parameters indicating the elasticity, that is, the elasticity of the blood vessel, respectively. The main vascular components are vascular endothelium (Endothelium), elastic fibers (Elastin), proteins (Collagen), and smooth muscle (Smooth Muscle). These components have different properties, and Collagen and Elastin have a strong influence on the elasticity of blood vessels at the maximum blood pressure and the minimum blood pressure, respectively. Therefore, the elasticity that differs depending on the blood pressure value is indicated by the parameters of the ratio of the intensity of the b wave to the intensity of the a wave (b / a) and the ratio of the intensity of the f wave to the intensity of the e wave (f / e). These values also fluctuate depending on the influence of age, gender, and environment variables. Therefore, the values of (b / a) and (f / e) can be calculated as the characteristic information of the acceleration pulse waveform.

As shown in FIG. 5, the time difference between the time Tr at which the R wave is generated and the time Tp at which the P wave is generated is the ventricular systolic pulse wave propagation time PTT_SYS. The time of the difference between the time Tt in which the T wave is generated and the time Td in which the D wave is generated is the ventricular diastolic pulse wave propagation time PTT_DIA. That is, as shown by Eqs. (1) and (2) from the time Tr of the R wave and the time Tt of the T wave of the electrocardiographic waveform, and the time Tp of the T wave and the time Td of the D wave of the photoelectric systolic waveform. In addition, the ventricular systolic pulse wave propagation time PTT_SYS and the ventricular diastolic pulse wave propagation time PTT_DIA can be calculated.

PTT_SYS = Tp-Tr ... (1)

PTT_DIA = Td-Tt ... (2)

The first and second electrodes for measuring the electrocardiographic waveform and the optical sensor module for measuring the photoelectric volumetric pulse waveform are opposed to each other via the wrist, and the arrangement distance is separated from the detection site of the electrocardiographic waveform. The measurement site of the formula volume pulse waveform will be separated. Therefore, by causing a time lag in which each characteristic waveform is generated, the absolute calculation time of the ventricular systolic pulse wave propagation time PTT_SYS and the ventricular diastolic pulse wave propagation time PTT_DIA can be lengthened. Therefore, when the change information of the ventricular systolic pulse wave propagation time PTT_SYS and the ventricular diastolic pulse wave propagation time PTT_DIA is obtained, the accuracy of the change information can be improved.

Here, the formula for calculating blood pressure will be described.

From the following equation (3) of pulse wave velocity (Moens-Korteweg equation), the relationship between the pulse wave velocity and the Young's modulus of the arterial wall is shown.

L / T_PTT = √ (E ・ h / (2 ・ r ・ ρ)) ・ ・ ・ (3)

Each parameter of the formula (3) is L: distance between measurements, T_PTT: pulse wave propagation time, r: blood vessel inner diameter, E: blood vessel Young's modulus, h: blood vessel thickness, ρ: blood density.

It is known that Young's modulus and blood pressure value are correlated.

E = E ₀・ exp (α ・ P) ・ ・ ・ (4)

Can be indicated by. Here, P: blood pressure value, α: constant, E ₀ : initial value.

From equations (3) and (4)

P = (-2 ・ ln (T_PTT) + ln (2 ・ r ・ ρ ・ L ² / (E ₀・ h))) / α ・ ・ ・ (5)

Can be derived. ln indicates the natural logarithm. At this time, since "r · ρ" is proportional to the blood volume at the measurement site, it can be indicated by a high value (Vp, Vd) indicated by the photoelectric volume pulse waveform. Further, since "E ₀ · h" is a value proportional to the elasticity of the blood vessel, it can be replaced by using the parameters (b / a) and (f / e) indicating the elasticity.

Therefore, the systolic blood pressure BP_SYS (Blood Pressure_Systic) and the diastolic blood pressure BP_DIA (Blood Pressure_Diastolic) can be represented by the following equations (6) and (7).

BP_SYS = A1 · ln (PTT_SYS) + A2 · ln (Vp) + A3 · ln (b / a) + A4 ... (6)

BP_DIA = A5 · ln (PTT_DIA) + A6 · ln (Vd) + A7 · ln (f / e) + A8 ... (7)

A1 to A8 are constants determined by conditions. The systolic blood pressure BP_SYS that can be calculated by Eq. (6) is the natural logarithm of the ventricular systolic pulse wave propagation time PTT_SYS multiplied by the constant A1 and the natural logarithm of the intensity Vp of the P wave multiplied by the constant A2. It can be obtained by multiplying the natural logarithm of (b / a) by the constant A3 and the sum of the constants A4. The diastolic blood pressure BP_SYS that can be calculated by Eq. (7) is the natural logarithm of the ventricular systolic pulse wave propagation time PTT_DIA multiplied by the constant A5 and the natural logarithm of the intensity Vd of the D wave multiplied by the constant A6. It can be obtained by multiplying the natural logarithm of (f / e) by the constant A7 and the sum of the constants A8. It is possible to obtain the systolic blood pressure BP_SYS and the diastolic blood pressure BP_DIA by obtaining each constant depending on the characteristics of the device and the person to be measured. However, when confirming the changes in the systolic blood pressure BP_SYS and the diastolic blood pressure BP_DIA, it is not necessary to determine all the constants, and while substituting the provisional numerical values, the information on the systolic blood pressure BP_SYS and the information on the diastolic blood pressure BP_DIA are used. It is possible to get a value. The natural logarithm of the intensity Vp of the P wave and the natural logarithm of the intensity Vd of the D wave are terms in consideration of the influence of blood density. Further, the natural logarithm of (b / a) and the natural logarithm of (f / e) are terms in consideration of the influence of the Young's modulus of the arterial wall. Therefore, depending on the measurement conditions, information on the systolic blood pressure BP_SYS and information on the diastolic blood pressure BP_DIA may be calculated by selecting one of the terms and making the other term constant.

Further, the biological data generation unit 132 can obtain temperature information as biological data from the skin temperature information of the subject measured by, for example, a temperature sensor (thermista or the like) of the measuring device 300 worn by the subject. ..

In addition, a method of calculating walking speed information, which is biological data, from measurement data will be exemplified. For example, a known calculation method or the like from the waveform data of the acceleration data measured by the measuring device 300 worn by the user on the wrist may be used alone or in combination (for example, averaging or weighting). The walking speed information can be obtained by, for example, the walking speed information is calculated by integrating the acceleration data at predetermined time intervals. In addition to this, the user terminal device 200 or the measuring device 300 is provided with a GPS function, and more accurate walking speed information is referred to by referring to the position information by GPS and the walking speed information calculated from the time information related to the position information. May be obtained. However, GPS accuracy generally deteriorates, especially when it is indoors or underground or when the travel distance is relatively short (for example, within a few meters). Therefore, for example, the user operates the user terminal device 200 by GPS. It may be possible to select whether to use the information in combination (or to use it instead of the calculation by the acceleration sensor), or to use the GPS reception sensitivity information in the user terminal device 200 or the distance calculated by the GPS or the acceleration sensor. You may choose whether to use the GPS information based on the information or the like. By calculating the walking speed information in this way, it is easy (especially on a daily basis) to measure "walking speed", which is one of the known indexes for measuring human muscle mass that needs to be grasped in frailty prevention and the like. It is possible. In addition, although smartphones and mobile phones also have an accelerometer, it is a device that makes it difficult to identify where the body is moving, so a measuring device worn by the user on the wrist, etc., such as a wearable device. By using the 300, it is possible to easily track the behavior information.

In addition, a method of calculating stride information, which is biological data, from measurement data will be exemplified. For example, a known calculation method or the like from the waveform data of acceleration data measured by the measuring device 300 worn by the user on the wrist may be used alone or in combination (for example, averaging or weighting). For example, when walking, the hand is waved like a pendulum, so that the information of the above-mentioned acceleration sensor (for example, the timing at which the acceleration component in the traveling direction is the smallest or the timing at which the acceleration component is switched in the opposite direction, or the progress) can be obtained. Since the interval of one step can be determined based on the timing when the acceleration component in the direction perpendicular to the direction is the smallest or the timing when the top and bottom are switched), the stride information can be obtained by further using the time information. Alternatively, for example, when the ground is kicked out, the acceleration component in the kicking direction is synthesized, so that it is also possible to determine the interval of one step at the timing of occurrence of the acceleration component in the direction. By calculating the stride information in this way, it is possible to accurately grasp the timing at which the stride begins to shorten and the degree of variation in the stride, which is considered to be useful for estimating the degree of progression of dementia. Further, the deterioration of the sense of balance may be calculated by calculating the amount of left and right shaking during walking (for example, the shaking width and the shaking speed) from the above-mentioned acceleration data.

Further, the exercise amount information calculated based on the distance information calculated by the above-mentioned GPS or the acceleration sensor, the above-mentioned stride information and the step count information (for example, can be obtained by a known method based on the information from the acceleration sensor) is also living body. It may be calculated as data.

Further, in the biological data generation unit 132, for example, from the acceleration data and the angular velocity data measured by the measuring device 300 worn by the person to be measured, the portion where the measuring device 300 is worn (for example, wrist or ankle) is determined. It is possible to obtain motion information as biometric data, such as how fast and at what angle it is moving.

Further, the biological data generation unit 132 frequency-analyzes the acceleration data measured by, for example, the measuring device 300 worn by the person to be measured, and for example, the high and low frequencies are associated with the high and low activity frequencies, and the frequency is equal to or higher than a predetermined frequency. Activity amount information can be obtained as biometric data by calculating according to predetermined conditions such as what percentage of the day the activity occupies.

Further, since the biological data generation unit 132 can specify the acceleration data during exercise including walking by a known calculation method or the like from the acceleration data measured by the measuring device 300 worn by the person to be measured, for example. For example, the amount of exercise information can be obtained as biometric data by calculating under predetermined conditions using frequency analysis or the like. Further, by further using additional information such as angular velocity information, it is possible to obtain more accurate momentum information.

Further, the biological data generation unit 132 has, for example, heart rate information that increases with an exercise load with respect to the activity amount information and the exercise amount information derived from the acceleration data measured by the measuring device 300 worn by the person to be measured. By weighting more, exercise load information can be obtained as biometric data. Further, for example, if vector information of acceleration data is added, state information such as walking environment (hill, stairs, etc.) and posture (standing position, sitting position, etc.) can be specified, and the state information may be further used. Further, by further using additional information such as angular velocity information, it is possible to obtain more accurate exercise load amount information.

Further, the biological data generation unit 132 uses heart rate information, for example, to obtain maximum oxygen uptake information by a known formula such as VO ₂ max = 15 × (220-age) ÷ heart rate (particularly resting heart rate). It can be obtained as biometric data.

In addition, for example, measurement data by a known learning device, biometric data generated based on the measurement data (for example, heartbeat information, blood pressure information, etc.) and positive biometric information (for example, heartbeat information based on known medical equipment, etc.) A machine learning model is created in advance based on the teacher data associated with the correspondence with the blood pressure information (for example, information indicating the degree and range of the error may be included), and the biological data generation unit 132. May generate biometric data using the determination using the machine learning model as the above-mentioned predetermined calculation (analysis).

The frail index information generation unit 133 uses the time when exercise intensity above a predetermined value occurs as the reference time information for the change information of the biological data (particularly, cardiovascular information such as heart rate information and / or blood pressure information) within the determination period. Based on this, it generates responsiveness index information indicating how the biometric data responds to the occurrence of exercise intensity above a predetermined level, and / or biometric data from the response state or operating state to the resting state (particularly). , Heart rate information and / or cardiovascular-related information such as blood pressure information), and generates recoverability index information indicating how the patient is recovering from the response due to the occurrence of exercise intensity above a predetermined level. Then, the frailty index information generation unit 133 performs clustering based on the exercise intensity information indicating the exercise intensity associated with at least one of the responsiveness index information and the recoverability index information. Then, the frail index information generation unit 133 classifies each of the clustered exercise intensity information by at least one of the responsiveness index information or the recoverability index information and the reference frail index information (for example, at least two or more classifications can be made). For example, the responsiveness index information or recovery of the subject is referred to by referring to the correspondence relationship information (including the one by machine learning) in which the correspondence relationship with the healthy subject group and the frail group (which may include at least the healthy subject group) is stored in advance. Based on at least one of the sexual index information, the frail index information for indicating the frail state of the user is determined. The frailty index information may indicate, for example, a probability value such as which classification of the reference frailty index information has a high probability, or indicates one classification finally determined from the probability value or the like. It may be information.

In addition, the frail index information generation unit 133 evaluates the frail state of the user according to the determined frail index information, and determines the evaluation information (for example, frail symptom evaluation information (healthy or frail, etc.) or frail symptom). As reference information to be supported, frailty symptom reference evaluation information such as positive or negative, which may correspond to the above-mentioned reference frailty index information) may be generated, for example, determined. The user's frailty state may be evaluated for each exercise corresponding to each exercise intensity by using the frailty index information as it is, or instead of this, or in addition, the frailty index determined for each exercise within a predetermined period. The information is used as is (especially when it is a probability value) or scored (for example, 0 when showing a healthy group, 1 when showing a frail group, etc.), for example, an average value or a total within a predetermined period. The aggregated value such as the value and the corresponding reference value (for example, if it is an average value, it is a half price such as 0.5, if it is a total value, it is half the value of the total value when all are 1, or it is collected before the comparison. The median value, the most frequent value, etc. of the reference data) may be compared, and the frail state of the user in a predetermined period may be evaluated according to the comparison result to generate evaluation information. At this time, the aggregated value of the scoring data of all the frail index information within the predetermined period may be used for comparison with the reference value, or a value less than the first quartile or a value less than the third quartile. Aggregated values of scoring data with at least one of the larger values removed or outliers removed may be used.

The exercise intensity may be clustered (classified) based on change information (particularly transition information) of acceleration data or angular velocity data obtained from, for example, an inertial sensor (acceleration sensor, gyro sensor) of the measuring device 300. It is clustered (classified) based on at least one of walking speed information, stride information, exercise amount information, motion information of the wearing site, activity amount information, and exercise load information generated using acceleration data and angular velocity data. May be good. Alternatively, after clustering, an index expressed by a numerical value, classification, rank, etc. according to the degree of exercise may be set. For example, the behavior information estimated from the above-mentioned behavior information is associated with the exercise intensity index. It may be set, or it may be converted into a known index (for example, METS).

As an example of a more specific exercise intensity clustering method, for example, at least one of measurement data (particularly data obtained from an inertial sensor) or biometric data signal with a predetermined time interval, frequency component, or stationary signal. It may be a method of clustering using feature information. Alternatively, for example, between the measured data (especially the data obtained from the inertial sensor) in the window frame width for a certain period of time (for example, the determination period described above) or the correlation value between the signal information of the biometric data and the power spectral density. It may be a method of clustering those having a correlation value of a predetermined value or more. Alternatively, it may be a method of calculating using a learning model in which machine learning is performed featuring the entire signal waveform of measurement data (particularly data obtained from an inertial sensor) or biometric data for each predetermined time window frame.

The determination period is, for example, a period set at least one before or after the reference time, and may be arbitrarily set in advance for several minutes, several tens of seconds, several seconds, etc. before or after the reference time, or before or after. The period set to is may be set differently, or may be set to several minutes, several tens of seconds, several seconds, or the like after the reference time.

The response state is a state in which exercise intensity equal to or higher than a predetermined value is generated, or biometric data (particularly, cardiovascular information such as heart rate information and / or blood pressure information) is equal to or higher than a predetermined value, or fluctuation information is present. It is a state in which the indicated fluctuation is equal to or greater than a predetermined value.

The action state is a state in which the action type information indicates some action.

The resting state is a state in which exercise intensity below a predetermined value is generated, or biometric data (particularly, cardiovascular information such as heart rate information and / or blood pressure information) is less than a predetermined value, or fluctuation information. Is a state in which the fluctuation indicated by is less than a predetermined value.

As the correspondence information, for example, the correspondence between at least one of the responsiveness index information or the resilience index information and the frailty index information is stored for each clustered exercise intensity information according to the result of a previous experiment or the like. May be good. As a more specific example, the subject is classified based on a known reference frail index such as the J-CHS standard or the Rockwood fraction index, and the measurement data of the measuring device 300 worn by the subject or the biometric data calculated from the measurement data. The correspondence relationship between at least one of the exercise intensity information and the responsiveness index information or the recovery index information based on the subject and the reference frail index of the subject (particularly, the correspondence relationship for each clustered exercise intensity information) is stored in the storage unit 120. In particular, it may be trained as a learning model by machine learning.

When storing the correspondence information as a learning model, a model that can be binary classified may be created by using a known learning method such as SVM, decision tree, gradient boosting, and logistic regression. When using this model, whether the determined frail index information (frail evaluation information) is positive or negative as frail symptom information (healthy or frail) or reference information to assist in determining frail symptoms. It can be two estimated information such as. Further, when storing the correspondence information as a learning model, a Transformer model using Self-Attention may be created. This learning model improves the architecture of the RNN system, and by using the same Tensor for all of the input (quary) and memory (key, value) of the Attention structure, the efficiency of learning to discontinuous sample information and the overall This is an improvement in learning performance. It is possible to acquire the sequence structure and the anaphoric relationship by using Self-Attention, and it is possible to efficiently learn the discontinuous sample information. This Transformer structure has a function of extracting the summary information of the input information in the Encoder unit and replacing the summary information with the sequence information in the Decoder unit. By constructing a model architecture that uses only the Encoder part such as BERT in language comprehension and BEiT in image comprehension, we will learn to understand sequence information. When the learning model (Encoder model) created by this method is used, the sequence information of the measurement data (especially the data obtained from the inertial sensor) is processed, and the vector information derived from the first limb token is used as the summary information of the sequence information. By making it possible to handle, the frail index information (frail evaluation information) indicating the progress of the frail symptom is determined from the vector information derived here.

The data output unit 134 outputs measurement data, biometric data, frailty index information, etc. to the user terminal device 200 (the user here may be a person to be measured, or another person (for example, a close relative, a doctor, a caregiver, a caregiver)). It may be a person, a researcher, etc.)). In the user terminal device 200, the output data may be displayed on the screen via, for example, a dedicated application so that the user can easily confirm the data.

The input / output unit 140 is an information input device such as a keyboard and a mouse, and an output device such as a display.

<Processing flow>
The processing flow of the data support method executed by the information processing system 1 will be described with reference to FIG. FIG. 6 is a flowchart showing an example of processing of the information processing system 1 of FIG.

As a process of step S101, the data management unit 131 generates account information for each user who uses the measuring device 300, and acquires predetermined user information from the user terminal device 200 or the like. The registered user information is stored in the user information DB 124 by the data management unit 131. The process of step S101 may be performed as a pre-process for the user to use the measuring device 300, or may be performed when the user uses the measuring device 300 for the first time.

When the user uses the measuring device 300 as the process of step S102, the measurement data is transmitted from the measuring device 300 to the management server 100 via the user terminal device 200 and received via the communication unit 110. The data management unit 131 stores the measurement data associated with the user information in the measurement data DB 121 of the storage unit 120.

As the process of step S103, the measurement data is read by the biometric data generation unit 132, and the biometric data is generated by a predetermined operation or the like. The generated biometric data is stored in the biometric data DB 122 by the data management unit 131.

As the process of step S104, the measurement data or the biological data is read by the frail index information generation unit 133, and the frail index information is generated by referring to the correspondence information. The generated frail index information is stored in the frail index information DB 123 by the data management unit 131.

As the process of step S105, at least one of the measurement data, the biometric data, and the frailty index information is read by the data output unit 134 and output to the user terminal device 200.

<Effect>
As described above, the information processing system according to the present embodiment generates frail index information regarding the user's frail state, based on the measurement data or biometric data, via the frail index information generation unit 133. This makes it possible to grasp the frail state of the person to be measured, for example.

Although the embodiments related to the disclosure have been described above, these can be implemented in various other embodiments, and can be implemented by making various omissions, substitutions, and changes. These embodiments and modifications, as well as those omitted, replaced or modified, are included in the technical scope of the claims and the equivalent scope thereof.

1 Information processing system 100 Management server 200 User terminal device 300 Measuring device NW network

Claims (7)

An information processing system that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frail index information from the measurement data.
Based on the change information of the biometric data within the judgment period using the time when the exercise intensity of the predetermined or higher occurs as the reference time information, it shows how the biometric data responds to the occurrence of the exercise intensity of the predetermined or higher. Resilience index information indicating how the response is recovered from the response due to the generation of exercise intensity higher than the predetermined value based on the response index information or the change information of the biological data from the response state or the operating state to the resting state. Frail index information that generates at least one of them and generates frail index information for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. With a generator,
An information processing system characterized by this. The frailty index information generation unit uses cardiovascular information including at least one of heart rate information and blood pressure information as biometric data within the determination period.
The information processing system according to claim 1. The frailty index information generation unit performs clustering based on the exercise intensity information indicating the exercise intensity associated with at least one of the responsiveness index information and the recoverability index information, and corresponds to each clustered exercise intensity information. Generate the frailty index information based on the relationship information,
The information processing system according to claim 1 or 2, wherein the information processing system is characterized by the above. The exercise intensity is an index based on data obtained from the inertial sensor of the measuring device.
The information processing system according to any one of claims 1 to 3, wherein the information processing system is characterized by the above. A server that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frailty index information from the measurement data.
Based on the change information of the biometric data within the judgment period using the time when the exercise intensity of the predetermined or higher occurs as the reference time information, it shows how the biometric data responds to the occurrence of the exercise intensity of the predetermined or higher. Resilience index information indicating how the response is recovered from the response due to the generation of exercise intensity higher than the predetermined value based on the response index information or the change information of the biological data from the response state or the operating state to the resting state. Frail index information that generates at least one of them and generates frail index information for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. With a generator,
A server that features that. It is an information processing method that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frail index information from the measurement data by a computer .
Based on the change information of the biometric data within the judgment period in which the time when the exercise intensity of the predetermined value or more occurs is used as the reference time information by the frail index information generation unit, how the biometric data is for the generation of the exercise intensity of the predetermined value or more. Based on the responsiveness index information indicating whether or not the patient is responding to, or the change information of the biological data from the response state or the operating state to the resting state, how to recover from the response due to the generation of exercise intensity higher than the predetermined value. A frail index for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. Including steps to generate information,
An information processing method characterized by that. A program that causes an information processing system to execute an information processing method that receives measurement data from a measurement device worn by a user via a network and generates biometric data and frail index information from the measurement data.
The information processing method is
Based on the change information of the biometric data within the judgment period in which the time when the exercise intensity of the predetermined value or more occurs is used as the reference time information by the frail index information generation unit, how the biometric data is for the generation of the exercise intensity of the predetermined value or more. Based on the responsiveness index information indicating whether or not the patient is responding to, or the change information of the biological data from the response state or the operating state to the resting state, how to recover from the response due to the generation of exercise intensity higher than the predetermined value. A frail index for indicating the frail state of the user based on the correspondence information stored in advance with at least one of the responsiveness index information or the recoverability index information. Including steps to generate information,
A program characterized by that.

Images