Disease risk estimation device, disease risk estimation system, disease risk estimation method, and program

Abstract

In order to estimate the risk of occurrence of a disease using sensor data measured in accordance with leg movement, this disease risk estimation device comprises: an acquisition unit that acquires sensor data measured in accordance with movement of the legs of a subject person who is the subject of disease risk estimation; a risk estimation unit that estimates a disease risk related to a specific disease using the acquired sensor data; and an output unit that outputs disease risk information corresponding to the estimated disease risk.

Description

Disease risk estimation device, disease risk estimation system, disease risk estimation method, and recording medium

[0001] The present disclosure relates to a disease risk estimation device, a disease risk estimation system, a disease risk estimation method, and a recording medium.

[0002] With growing interest in healthcare, services that provide information based on gait patterns are gaining attention. For example, technology has been developed to analyze gait patterns using sensor data measured by sensors mounted on footwear such as shoes. Time-series data from sensor data reveals characteristics associated with walking events related to physical conditions. If a subject's disease risk can be estimated based on the characteristics associated with walking events, early detection and prevention of disease will become possible.

[0003] Patent Document 1 discloses a walking condition measuring device for checking the walking condition of elderly people. The walking condition measuring device of Patent Document 1 includes a walking condition acquisition unit formed as a shoe insole. The walking condition acquisition unit acquires acceleration data related to the up and down directions of the wearer's feet and elevation and depression angle data of the toes. The walking condition measuring device of Patent Document 1 acquires the acceleration data and elevation and depression angle data as data on the wearer's walking condition. The walking condition measuring device of Patent Document 1 also determines the swing phase, in which the foot is not in contact with the ground, based on pressure data applied to the shoe sole.

[0004] Japanese Patent Application Laid-Open No. 2019-217182

[0005] The method of Patent Document 1 checks the walking state of the wearer based on data measured by a sensor. The method of Patent Document 1 can obtain information that can be used as a factor for determining the wearer's muscle strength level based on the data measured by the sensor. However, the method of Patent Document 1 cannot estimate the wearer's risk of developing a disease.

[0006] The object of the present disclosure is to provide a disease risk estimation device, a disease risk estimation system, a disease risk estimation method, and a recording medium that can estimate the risk of developing a disease using sensor data measured according to foot movement.

[0007] A disease risk estimation device according to one aspect of the present disclosure includes an acquisition unit that acquires sensor data measured according to the foot movements of a subject whose disease risk is to be estimated, a risk estimation unit that estimates the disease risk of a specific disease using the acquired sensor data, and an output unit that outputs disease risk information according to the estimated disease risk.

[0008] In one aspect of the disease risk estimation method of the present disclosure, sensor data measured according to the foot movements of a subject whose disease risk is to be estimated is acquired, the acquired sensor data is used to estimate the disease risk for a specific disease, and disease risk information according to the estimated disease risk is output.

[0009] A program according to one aspect of the present disclosure causes a computer to perform the following processes: acquiring sensor data measured according to the foot movements of a subject whose disease risk is to be estimated; estimating the disease risk of a specific disease using the acquired sensor data; and outputting disease risk information according to the estimated disease risk.

[0010] According to the present disclosure, it is possible to provide a disease risk estimation device, a disease risk estimation system, a disease risk estimation method, and a recording medium that can estimate the risk of developing a disease using sensor data measured according to foot movement.

[0011] FIG. 1 is a block diagram showing an example of the configuration of a disease risk estimation system according to the present disclosure. FIG. 1 is a block diagram showing an example of the configuration of a measurement device provided in the disease risk estimation system according to the present disclosure. FIG. 2 is a conceptual diagram showing an example of the arrangement of the measurement device of the disease risk estimation system according to the present disclosure. FIG. 3 is a conceptual diagram showing an example of a coordinate system set in the measurement device of the disease risk estimation system according to the present disclosure. FIG. 4 is a conceptual diagram showing an example of a human body surface used in describing the present disclosure. FIG. 1 is a block diagram showing an example of the configuration of a disease risk estimation device provided in the disease risk estimation system according to the present disclosure. FIG. 2 is a conceptual diagram showing an example of a gait cycle used in describing the present disclosure. FIG. 3 is a conceptual diagram showing an example of estimation by a physical ability estimation model used by the physical ability estimation section of the disease risk estimation system according to the present disclosure. FIG. 4 is a conceptual diagram showing an example of estimation by a disease risk estimation model used by the disease risk estimation section of the disease risk estimation system according to the present disclosure. FIG. 5 is a flowchart showing an example of the operation of the disease risk estimation system according to the present disclosure. FIG. 6 is a conceptual diagram showing an application example of the disease risk estimation system according to the present disclosure. FIG. 7 is a block diagram showing an example of the configuration of a measurement device provided in the disease risk estimation system according to the present disclosure. FIG. 8 is a flowchart for explaining an example of the operation of the disease risk estimation system according to the present disclosure. FIG. 9 is a block diagram showing an example of a hardware configuration for executing control and processing according to the present disclosure.

[0012] Hereinafter, embodiments for carrying out the present disclosure will be described with reference to the drawings. In this disclosure, the drawings used in describing each embodiment relate to one or more embodiments. Furthermore, elements included in each drawing may apply to one or more embodiments. The embodiments described below are limited in a manner that is technically preferable for carrying out the present disclosure, but this does not limit the scope of the disclosure to the following. In all drawings used in describing the following embodiments, similar parts are designated by the same reference numerals unless otherwise specified. In the following embodiments, repeated description of similar configurations and operations may be omitted. The direction of arrows in the drawings is an example and does not limit the direction of data, signals, etc.

[0013] First Embodiment First, an example of a disease risk estimation system according to the present disclosure will be described with reference to the drawings. The disease risk estimation system of this embodiment estimates the disease risk of a specific disease using sensor data related to foot movement according to a user's walking. In this embodiment, an example is given in which a disease risk score indicating the degree of disease risk for a specific disease is estimated.

[0014] (Configuration) FIG. 1 is a block diagram showing an example of the configuration of a disease risk estimation system 1 according to the present disclosure. The disease risk estimation system 1 includes a measurement device 10 and a disease risk estimation device 13. For example, the measurement device 10 is attached to the footwear of a subject (user) whose disease risk is to be estimated. For example, the functions of the disease risk estimation device 13 are installed in a mobile device carried by the subject (user). Below, the configurations of the measurement device 10 and the disease risk estimation device 13 will be described separately.

[0015] [Measurement Device] Fig. 2 is a block diagram showing an example of the configuration of the measurement device 10. The measurement device 10 has a sensor 110, a control unit 113, a communication unit 115, and a power supply 117. The sensor 110 has an acceleration sensor 111 and an angular velocity sensor 112. The sensor 110 may include sensors other than the acceleration sensor 111 and the angular velocity sensor 112. Description of sensors other than the acceleration sensor 111 and the angular velocity sensor 112 that may be included in the sensor 110 will be omitted.

[0016] The acceleration sensor 111 is a sensor that measures acceleration in three axial directions (also called spatial acceleration). The acceleration sensor 111 measures acceleration (also called spatial acceleration) as a physical quantity related to foot movement. The acceleration sensor 111 outputs the measured acceleration to the control unit 113. For example, a piezoelectric, piezo-resistive, or capacitance type sensor can be used as the acceleration sensor 111. There are no limitations on the sensor used as the acceleration sensor 111 as long as it can measure acceleration.

[0017] The angular velocity sensor 112 is a sensor that measures angular velocity (also called spatial angular velocity) around three axes. The angular velocity sensor 112 measures angular velocity (also called spatial angular velocity) as a physical quantity related to foot movement. The angular velocity sensor 112 outputs the measured angular velocity to the control unit 113. For example, a vibration type or capacitance type sensor can be used as the angular velocity sensor 112. There are no limitations on the sensor used as the angular velocity sensor 112 as long as it can measure angular velocity.

[0018] The sensor 110 is realized by, for example, an inertial measurement unit (IMU) that measures acceleration and angular velocity. An example of an inertial measurement unit is an IMU (Inertial Measurement Unit). The IMU includes an acceleration sensor 111 that measures acceleration in three axial directions and an angular velocity sensor 112 that measures angular velocity around three axes. The sensor 110 may be realized by an inertial measurement unit such as a VG (Vertical Gyro) or an AHRS (Attitude Heading Reference System). The sensor 110 may also be realized by a GPS / INS (Global Positioning System / Inertial Navigation System). The sensor 110 may be realized by a device other than an inertial measurement unit as long as it can measure physical quantities related to foot movement.

[0019] FIG. 3 is a conceptual diagram showing an example in which the measurement device 10 is placed inside the shoes 100 of both feet. In the example of FIG. 3, the measurement device 10 is placed at a position corresponding to the back of the arch of the foot. For example, the measurement device 10 is placed in an insole inserted into the shoe 100. For example, the measurement device 10 may be placed on the bottom of the shoe 100. For example, the measurement device 10 may be embedded in the body of the shoe 100. The measurement device 10 may be detachable from the shoe 100 or may not be detachable from the shoe 100. The measurement device 10 may be placed at a position other than the back of the arch of the foot as long as it can measure sensor data related to foot movement. The measurement device 10 may also be placed in socks worn by the user or in an accessory such as an anklet worn by the user. The measurement device 10 may also be attached directly to the foot or embedded in the foot. The measurement device 10 may also be placed inside one of the shoes 100 as long as it can measure data that can be used to estimate disease risk.

[0020] In the example of FIG. 3 , a local coordinate system is set with the measurement device 10 (sensor 110) as the reference, and includes an x-axis in the left-right direction, a y-axis in the front-back direction, and a z-axis in the up-down direction. FIG. 3 shows an example in which the same coordinate system is set for the left foot and the right foot. For example, if sensors 110 manufactured to the same specifications are placed in left and right shoes 100, the up-down orientation (Z-axis orientation) of the sensors 110 placed in the left and right shoes 100 is the same. In this case, the three axes of the local coordinate system set for the sensor data derived from the left foot and the three axes of the local coordinate system set for the sensor data derived from the right foot are the same for the left and right. In the present disclosure, the x-axis is positive to the left, the y-axis is positive to the rear, and the z-axis is positive to the up.

[0021] FIG. 4 is a conceptual diagram illustrating a local coordinate system (x-axis, y-axis, z-axis) set in the measurement device 10 (sensor 110) installed on the back of the foot arch, and a world coordinate system (x-axis, y-axis, z-axis) set relative to the ground. FIG. 4 shows an example in which different coordinate systems are set for the left and right feet. In the world coordinate system (x-axis, y-axis, z-axis), when a user is standing upright facing the direction of travel, the x-axis direction corresponds to the user's side, the y-axis direction corresponds to the user's back, and the z-axis direction corresponds to the direction of gravity. Note that the example in FIG. 4 conceptually illustrates the relationship between the local coordinate system (x-axis, y-axis, z-axis) and the world coordinate system (x-axis, y-axis, z-axis), and does not accurately illustrate the relationship between the local coordinate system and the world coordinate system, which changes depending on the user's walking.

[0022] FIG. 5 is a conceptual diagram illustrating planes (also referred to as human body planes) set for the human body. In this embodiment, a sagittal plane that divides the body into left and right, a coronal plane that divides the body into front and back, and a horizontal plane that divides the body horizontally are defined. Note that, as shown in FIG. 5 , when the user is standing upright with the centerline of the feet pointing in the direction of travel, the world coordinate system and the local coordinate system are assumed to coincide. FIG. 5 shows an example in which different coordinate systems are set for the left and right feet. In this embodiment, a rotation in the sagittal plane about the X-axis (x-axis) as the axis of rotation is defined as roll, a rotation in the coronal plane about the Y-axis (y-axis) as the axis of rotation is defined as pitch, and a rotation in the horizontal plane about the Z-axis (z-axis) as the axis of rotation is defined as yaw. Furthermore, a rotation angle in the sagittal plane about the X-axis (x-axis) as the axis of rotation is defined as roll angle, a rotation angle in the coronal plane about the Y-axis (y-axis) as the axis of rotation is defined as pitch angle, and a rotation angle in the horizontal plane about the Z-axis (z-axis) as the axis of rotation is defined as yaw angle.

[0023] The control unit 113 (control means) causes the acceleration sensor 111 and the angular velocity sensor 112 to measure sensor data. For example, the control unit 113 causes the acceleration sensor 111 and the angular velocity sensor 112 to start measurement in response to a measurement start signal transmitted from the disease risk estimation device 13. For example, the control unit 113 may cause the acceleration sensor 111 and the angular velocity sensor 112 to start measurement in response to detection of the user walking. For example, the control unit 113 starts measuring the step width starting from the point in time when it is detected that either the left or right foot has started to move in the direction of travel after both feet have remained at the same vertical height for a predetermined period of time. The control unit 113 may also be configured to start measuring the step width at a predetermined timing.

[0024] The control unit 113 acquires acceleration in three axial directions from the acceleration sensor 111. The control unit 113 also acquires angular velocities around three axes from the angular velocity sensor 112. For example, the control unit 113 performs analog-to-digital conversion (AD) on the acquired physical quantities (analog data) such as angular velocity and acceleration. The physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted to digital data by each of the acceleration sensor 111 and the angular velocity sensor 112. For example, an AD conversion circuit that AD converts the physical quantities (analog data) such as angular velocity and acceleration may be provided. The control unit 113 outputs the converted digital data (also referred to as sensor data) to the communication unit 115. For example, the control unit 113 may temporarily store the sensor data in a storage unit (not shown).

[0025] The sensor data includes at least acceleration data converted into digital data and angular velocity data converted into digital data. The acceleration data includes acceleration vectors in three axial directions. The angular velocity data includes angular velocity vectors around three axes. The acceleration data and angular velocity data are associated with the time at which they were acquired. The control unit 113 may also apply corrections, such as corrections for mounting errors, temperature corrections, and linearity corrections, to the acceleration data and angular velocity data.

[0026] For example, the control unit 113 may calculate at least one of the gait indices described below. In this case, the measurement device 10 outputs the calculated gait indices to the disease risk estimation device 13. For example, the control unit 113 may calculate feature amounts used to estimate physical ability described below. In this case, the measurement device 10 outputs the calculated feature amounts to the disease risk estimation device 13.

[0027] For example, the control unit 113 is realized by a microcomputer or microcontroller that performs overall control and data processing of the measuring device 10. For example, the control unit 113 includes a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc.

[0028] The communication unit 115 acquires sensor data from the control unit 113. The communication unit 115 transmits the acquired sensor data to the disease risk estimation device 13. The sensor data transmitted from the communication unit 115 is received by the disease risk estimation device 13. The timing of transmitting the sensor data is not particularly limited. For example, the communication unit 115 transmits the sensor data at a preset transmission timing. For example, the communication unit 115 transmits the sensor data in real time in response to measurement of the sensor data. For example, the communication unit 115 may store sensor data measured over a predetermined period and transmit the stored sensor data all at once at a preset timing. For example, the communication unit 115 (communication means) may be configured to receive a measurement start signal from the disease risk estimation device 13. In this case, the communication unit 115 outputs the received measurement start signal to the control unit 113.

[0029] For example, the communication unit 115 transmits the sensor data to the disease risk estimation device 13 via wireless communication. For example, the communication unit 115 transmits the sensor data to the disease risk estimation device 13 via a wireless communication function (not shown) conforming to standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). The communication function of the communication unit 115 may be conforming to standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark). The communication unit 115 may transmit the sensor data to the disease risk estimation device 13 via a wired connection such as a cable.

[0030] The power supply 117 is a battery that supplies power for operating the measuring device 10. For example, the power supply 117 may be a thin battery, such as a coin or button type. For example, the power supply 117 may be a primary battery, such as a lithium primary battery, a silver oxide battery, an alkaline button battery, or a zinc-air battery. When the power supply 117 is a primary battery, it is preferable that the power supply 117 be a long-life battery. The power supply 117 may also be a rechargeable secondary battery. When the power supply 117 is a secondary battery, the power supply 117 may be a battery that can be charged via a wired connection or a battery that can be powered wirelessly. If the power supply 117 is capable of wireless power supply, a wireless power supply device may be placed in a location where footwear is kept, such as an entrance or a shoe locker. By placing footwear equipped with the measuring device 10 on the wireless power supply device, the measuring device 10 can be charged appropriately when not in use.

[0031] [Disease Risk Estimation Device] Fig. 6 is a block diagram showing an example of the configuration of the disease risk estimation device 13. The disease risk estimation device 13 has an acquisition unit 131, a waveform processing unit 132, a gait index calculation unit 133, a storage unit 134, a physical ability estimation unit 135, a disease risk estimation unit 136, and an output unit 137. The waveform processing unit 132, the gait index calculation unit 133, the physical ability estimation unit 135, and the disease risk estimation unit 136 constitute the risk estimation unit 15. The waveform processing unit 132 and the gait index calculation unit 133 constitute the calculation unit 130. The physical ability estimation unit 135 and the disease risk estimation unit 136 constitute the estimation unit 140.

[0032] The acquisition unit 131 acquires sensor data from the measurement device 10. The acquisition unit 131 receives the sensor data from the measurement device 10 via wireless communication. For example, the acquisition unit 131 receives the sensor data from the measurement device 10 via a wireless communication function (not shown) conforming to standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). Note that the communication function of the acquisition unit 131 may conform to standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark) as long as it can communicate with the measurement device 10. The acquisition unit 131 may receive the sensor data from the measurement device 10 via a wired connection such as a cable. For example, the acquisition unit 131 may acquire gait indices or feature amounts calculated by the measurement device 10.

[0033] The acquisition unit 131 also acquires physical information (attributes) of the user. The physical information includes gender, date of birth, height, and weight. The date of birth is converted to age. For example, the physical information is input via an input device (not shown). For example, the physical information is input via a mobile terminal used by the user. For example, the physical information may be stored in advance in the storage unit 134. The physical information may be updated at any timing in response to input by the user.

[0034] The waveform processing unit 132 (extraction means) acquires sensor data from the acquisition unit 131. The waveform processing unit 132 extracts time series data for one walking cycle from the time series data of acceleration in three axial directions and angular velocity around three axes included in the sensor data. The time series data for one walking cycle is also called walking waveform data. The waveform processing unit 132 extracts walking waveform data based on the timing of walking events detected from the time series data of the sensor data. For example, the waveform processing unit 132 extracts walking waveform data that starts at the timing of a heel strike and ends at the timing of the next heel strike.

[0035] FIG. 7 is a conceptual diagram illustrating a step cycle based on the right foot. The step cycle based on the left foot is similar to that of the right foot. The horizontal axis of FIG. 7 represents one step cycle of the right foot, starting from the point when the heel of the right foot hits the ground and ending from the point when the heel of the right foot hits the ground again. The horizontal axis of FIG. 7 is normalized with the step cycle set to 100%. Normalizing one step cycle to 100% is called first normalization. One step cycle of one foot is broadly divided into a stance phase, in which at least a portion of the sole of the foot is in contact with the ground, and a swing phase, in which the sole of the foot is off the ground. The stance phase is the period in which at least a portion of the sole of the foot is in contact with the ground. The stance phase is further divided into an early stance phase T1, a mid-stance phase T2, a final stance phase T3, and an early swing phase T4. The swing phase is the period in which the sole of the foot is off the ground. The swing phase is further divided into an early swing phase T5, a mid-swing phase T6, and a final swing phase T7. The horizontal axis in Figure 7 is normalized so that the stance phase is 60% and the swing phase is 40%. Normalizing gait waveform data so that the stance phase is 60% and the swing phase is 40% is called second normalization. Note that the periods shown in Figure 7 are merely examples and do not limit the periods that make up a gait cycle or the names of those periods.

[0036] As shown in Figure 7, multiple events occur during walking. These events are also referred to as walking events. P1 represents an event in which the heel of the right foot touches the ground (heel strike) (HS). P2 represents an event in which the toe of the left foot leaves the ground (opposite toe off) while the sole of the right foot remains on the ground (oto). P3 represents an event in which the heel of the right foot rises (heel rise) while the sole of the right foot remains on the ground (HR). P4 represents an event in which the heel of the left foot touches the ground (opposite heel strike) (OHS). P5 represents an event in which the toe of the right foot leaves the ground (toe off) while the sole of the left foot remains on the ground (TO). P6 represents an event in which the left and right feet cross (foot crossing) with the sole of the left foot touching the ground (FA: Foot Adjacent). P7 represents an event in which the tibia of the right foot is approximately perpendicular to the ground (TV: Tibia Vertical) with the sole of the left foot touching the ground. P8 represents an event in which the heel of the right foot touches the ground (heel strike) (HS: Heel Strike). P8 corresponds to the end point of the walking cycle that begins with P1 and the start point of the next walking cycle. Note that the walking events shown in Figure 7 are merely examples and do not limit the events that occur during walking or the names of these events.

[0037] The timing of heel strike is the timing of the minimum peak immediately after the maximum peak that appears in the time series data of forward acceleration (Y-direction acceleration). The maximum peak that marks the heel strike timing corresponds to the maximum peak of the walking waveform data for one step cycle. The section between consecutive heel strikes corresponds to one step cycle. The timing of toe lift is the timing of the rise of the maximum peak that appears after the stance phase period in which no fluctuations appear in the time series data of forward acceleration (Y-direction acceleration). The timing midway between the timing of the minimum roll angle and the timing of the maximum roll angle corresponds to the mid-stance phase.

[0038] The waveform processing unit 132 normalizes (first normalization) the time of the extracted walking waveform data for one step cycle to a walking cycle of 0 to 100% (percent). The timing of 1%, 10%, or the like included in the 0 to 100% walking cycle is also referred to as a walking phase. Furthermore, the waveform processing unit 132 normalizes (second normalization) the first-normalized walking waveform data for one step cycle so that the stance phase is 60% and the swing phase is 40%. Second-normalizing the walking waveform data can reduce discrepancies in the walking phases from which feature values ​​are extracted. The waveform processing unit 132 outputs the normalized walking waveform data to the gait index calculation unit 133.

[0039] For example, the waveform processing unit 132 extracts and normalizes gait waveform data for one walking cycle using the forward acceleration (Y-direction acceleration). With regard to accelerations / angular velocities other than the forward acceleration (Y-direction acceleration), the waveform processing unit 132 extracts and normalizes gait waveform data for one walking cycle in accordance with the gait cycle of the forward acceleration (Y-direction acceleration). The waveform processing unit 132 may also generate time series data of angles around three axes by integrating time series data of angular velocities around three axes. In this case, the waveform processing unit 132 extracts and normalizes gait waveform data for one walking cycle for angles around three axes in accordance with the gait cycle of the forward acceleration (Y-direction acceleration).

[0040] The waveform processor 132 may extract / normalize gait waveform data for one step gait cycle using acceleration / angular velocity other than forward acceleration (Y-direction acceleration). For example, the waveform processor 132 may detect heel strike and toe lift from time series data of vertical acceleration (Z-direction acceleration) (not shown). The timing of heel strike is the timing of a steep minimum peak that appears in the time series data of vertical acceleration (Z-direction acceleration). At the timing of the steep minimum peak, the value of vertical acceleration (Z-direction acceleration) becomes approximately zero. The minimum peak that marks the timing of heel strike corresponds to the minimum peak of the gait waveform data for one step gait cycle. The interval between consecutive heel strikes is a gait cycle. The timing of toe lift is the timing of an inflection point in the time series data of vertical acceleration (Z-direction acceleration) during a gradual increase after a period of small fluctuation following a maximum peak immediately after heel strike. The waveform processing unit 132 may also extract / normalize gait waveform data for one walking cycle using both forward acceleration (Y-direction acceleration) and vertical acceleration (Z-direction acceleration).The waveform processing unit 132 may also extract / normalize gait waveform data for one walking cycle using acceleration, angular velocity, angle, etc. other than forward acceleration (Y-direction acceleration) and vertical acceleration (Z-direction acceleration).

[0041] The waveform processing unit 132 extracts feature quantities (physical ability feature quantities) used to estimate physical abilities from the walking waveform data. The waveform processing unit 132 extracts physical ability feature quantities used to estimate at least one physical ability. For example, the waveform processing unit 132 extracts physical ability feature quantities used to estimate at least one of physical abilities such as grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. For example, the waveform processing unit 132 extracts physical ability feature quantities for each walking phase cluster according to preset conditions. A walking phase cluster is a cluster that integrates temporally consecutive walking phases. A walking phase cluster includes at least one walking phase. A walking phase cluster may also include a single walking phase. The waveform processing unit 132 outputs the extracted physical ability feature quantities to the physical ability estimation unit 135.

[0042] The gait index calculation unit 133 acquires normalized gait waveform data from the waveform processing unit 132. The gait index calculation unit 133 uses the normalized gait waveform data to calculate gait indices used to estimate physical ability. There are no particular limitations on the gait indices to be calculated, as long as they can be calculated using normalized gait waveform data. For example, the gait index calculation unit 133 calculates gait indices related to distance, height, angle, speed, time, frailty level, CPEI (Center of Pressure Exclusion Index), etc. Representative gait indices are listed below. Specific methods for calculating the following gait indices will not be described.

[0043] For example, the gait index calculation unit 133 calculates indices related to distance and height as gait indices. For example, the gait index calculation unit 133 calculates a stride length, a turning distance, a foot lift height, FTC (Foot Clearance), and MTC (Minimum Toe Clearance). The stride length indicates the distance between the front foot and the rear foot while walking. The turning distance indicates the maximum distance that the foot is separated outward in the direction of travel during the swing phase. The foot lift height indicates the maximum distance between the measurement device 10 (sensor 110) and the ground during the swing phase. The FTC indicates the maximum distance between the heel and the ground during the swing phase. The MTC indicates the minimum distance between the toe and the ground during the swing phase.

[0044] For example, the gait index calculation unit 133 calculates angle-related indices as gait indices. For example, the gait index calculation unit 133 calculates the contact angle, the takeoff angle, the toe direction, the heel-strike roll angle, the toe-off roll angle, the swing leg peak angular velocity, and the hallux angle. The contact angle indicates the maximum value of the angle between the sole of the foot and the ground at heel-strike. The takeoff angle indicates the angle between the sole of the foot and the ground during the swing phase. The toe direction indicates the average value of the orientation of the toe relative to the direction of forward motion during the swing phase. The heel-strike roll angle is the angle between the ankle and the ground at heel-strike, as viewed from a rear perspective. The toe-off roll angle is the angle between the ankle and the ground at push-off, as viewed from a rear perspective. The swing leg peak angular velocity is the angular velocity in the ankle dorsiflexion direction during the period from immediately after push-off until the toe comes closest to the ground. The hallux angle indicates the angle at which the big toe is tilted toward the index toe. Specifically, the hallux angle is the angle between the center line of the first metatarsal and the center line of the first proximal phalanx.

[0045] For example, the gait index calculation unit 133 calculates an index related to speed as a gait index. For example, the gait index calculation unit 133 calculates walking speed, cadence, and maximum swing speed. Walking speed indicates the walking speed. Cadence indicates the number of steps per minute. Maximum swing speed indicates the speed at which the leg is swung out during the swing phase.

[0046] For example, the gait index calculation unit 133 calculates time-related indices as gait indices. For example, the gait index calculation unit 133 calculates stance time, load time, sole contact time, push-off time, swing time, and DST (Double Support Time). Stance time indicates the time during which the foot is in contact with the ground during walking. Stance time is the sum of load time, sole contact time, and push-off time. Load time is the time during the stance phase from when the heel contacts the ground to when the toe contacts the ground. Sole contact time is the time during the stance phase when the entire sole of the foot is in contact with the ground and is horizontal to the ground. Push-off time is the time during the stance phase from when the sole is in contact with the ground to when the toe pushes off the ground. Swing time indicates the time during which the foot is off the ground during walking. DST is divided into DST1 and DST2. DST1 indicates the time during which the foot equipped with the measuring device 10 (sensor 110) is in front of the other foot during a period when both feet are in contact with the ground at the same time, and DST2 indicates the time during which the foot equipped with the measuring device 10 (sensor 110) is behind the other foot during a period when both feet are in contact with the ground at the same time.

[0047] For example, the gait index calculation unit 133 calculates a frailty level or a center of pressure exclusion index (CPEI) as a gait index. The frailty level is an estimated value of a frailty state according to a walking state. For example, the gait index calculation unit 133 estimates an index such as a judgment result R1 indicating health, a judgment result R2 indicating a possibility of frailty, or a judgment result R3 indicating a high possibility of frailty as a frailty level. The CPEI indicates an estimated value of the rate of expansion of the movement of the center of foot pressure acting on the ground during the stance phase.

[0048] The storage unit 134 stores a physical ability estimation model (described below) that estimates physical ability using physical ability feature amounts extracted from the walking waveform data. For example, the physical ability is at least one of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance. The physical ability may include other features besides grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance. The storage unit 134 stores physical ability estimation models trained for multiple subjects. For example, the physical ability estimation model outputs an index of physical ability (physical ability score) in response to input of physical ability feature amounts extracted from the walking waveform data.

[0049] The memory unit 134 also stores a disease risk estimation model (described below) that estimates disease risk using physical information, gait indices, and physical ability scores. The disease risk indicates the risk of contracting a specific disease. For example, specific diseases include gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia. For example, specific diseases include lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, and Parkinson's syndrome. The specific diseases may also include diseases other than those listed above. The memory unit 134 stores disease risk estimation models trained on multiple subjects. For example, the disease risk estimation model outputs a disease risk index (disease risk score) in response to input physical information, gait indices, and physical ability scores.

[0050] For example, the physical ability estimation model and the disease risk estimation model may be stored in the storage unit 134 when the product is shipped from the factory. The physical ability estimation model and the disease risk estimation model may also be stored in the storage unit 134 at a timing such as during calibration before the disease risk estimation device 13 is used by a user. For example, a physical ability estimation model and a disease risk estimation model stored in a storage device (not shown) such as an external server may be used. In this case, the physical ability estimation model and the disease risk estimation model may be accessed via an interface (not shown) connected to the storage device. The storage unit 134 also stores the user's physical information (attributes). The physical information includes gender, date of birth, height, and weight. The date of birth is converted to age. The physical information may be updated at any time.

[0051] The physical ability estimation unit 135 acquires physical ability feature quantities extracted from the walking waveform data from the waveform processing unit 132. The physical ability estimation unit 135 also acquires physical information (attributes) stored in the memory unit 134. The physical ability estimation unit 135 estimates a physical ability score using the physical ability feature quantities and the physical information (attributes). The physical ability estimation unit 135 inputs the physical ability feature quantities and the user's physical information (attributes) into a physical ability estimation model stored in the memory unit 134. For example, the physical ability estimation unit 135 estimates a physical ability score related to at least one of the physical abilities of grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance. The estimation of the physical ability score by the physical ability estimation unit 135 will be described later. The physical ability estimation unit 135 outputs the physical ability score output from the physical ability estimation model to the disease risk estimation unit 136.

[0052] For example, the physical ability estimation unit 135 may estimate physical information (attributes) using gait indices calculated by the gait index calculation unit 133. For example, the physical ability estimation unit 135 estimates physical information (attributes) using gait indices correlated with the physical information (attributes). For example, when muscle strength decreases with aging, walking speed, cadence, and the like decrease. Therefore, by using walking speed, cadence, and the like, it is possible to estimate a generation, even if it is not possible to estimate an exact age. For example, there is also a correlation between height and stride length. Therefore, by using stride length, it is possible to estimate a generation, even if it is not possible to estimate an exact age. Furthermore, by combining specific gait indices, it is possible to estimate age more accurately. With this configuration, it is possible to estimate physical information using sensor data measured by the measurement device 10 without inputting any of the physical information, such as height, weight, age, and gender. It is also possible that some users do not want to input information such as age, weight, BMI (Body Mass Index), or shoe size. In order to estimate such a user's disease risk, it is useful to estimate physical information (attributes) using gait indices. For example, the physical ability estimation unit 135 may compare the input value of the physical information (attributes) with the estimated value. If there is a large discrepancy between the input value of the physical information (attributes) and the estimated value, there is a possibility that the input value entered by the user contains an error. In such a case, a notification or warning prompting confirmation of the input value of the physical information (attributes) may be sent to the user's terminal device, etc.

[0053] For example, the estimated values ​​of the physical information (attributes) are stored in the storage unit 134. The physical information (attributes) may be estimated by any one of the waveform processing unit 132, the gait index calculation unit 133, the physical ability estimation unit 135, and the disease risk estimation unit 136 that constitute the risk estimation unit 15. For example, a component that estimates the physical information (attributes) may be added to the disease risk estimation device 13. For example, the acquisition unit 131 may acquire estimated values ​​of the physical information (attributes) estimated by an external estimation device (not shown).

[0054] Next, an example of a physical ability score estimated by the physical ability estimation unit 135 will be described. Here, an example of feature amounts used to estimate grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance will be described. Note that the examples given below do not limit the physical abilities estimated by the physical ability estimation unit 135. The physical abilities estimated by the physical ability estimation unit 135 may be selected appropriately depending on the disease for which the disease risk is to be estimated.

[0055] <Grip strength (total muscle strength of the whole body)> Grip strength, which is one of the physical abilities, is correlated with total muscle strength of the whole body. Grip strength is also correlated with knee extension strength. For example, an estimated value of grip strength is an index of total muscle strength. For example, a score based on the estimated value of grip strength (also called a total muscle strength score) is an index of total muscle strength. The total muscle strength score is a value obtained by scoring grip strength, which is an index of total muscle strength, according to a preset standard. Grip strength is affected by attributes such as gender, age, and height. Therefore, the total muscle strength score may be scored according to a standard for each attribute. In particular, grip strength is affected by gender. Therefore, the total muscle strength score may be scored according to different standards depending on gender. Note that the index of total muscle strength is not limited to grip strength as long as it is possible to score total muscle strength.

[0056] The gait phases from which the features used to estimate grip strength are extracted differ depending on gender. For men, there is a correlation between quadriceps activity and grip strength. Therefore, to estimate men's grip strength, features extracted from gait phases that reveal the characteristics of quadriceps activity are used. For women, there is a correlation between grip strength and the activities of the vastus lateralis, vastus intermedius, and vastus medialis quadriceps. Therefore, to estimate women's grip strength, features extracted from gait phases that reveal the characteristics of vastus lateralis, vastus intermedius, and vastus medialis quadriceps activity are used.

[0057] Feature quantities AM1, AM2, AM3, and AM4 are used to estimate the male's grip strength. Feature quantity AM1 is extracted from the 3% section of the walking phase of gait waveform data related to time-series data of forward acceleration (Y-direction acceleration). The 3% walking phase is included in the initial stance phase T1. Feature quantity AM1 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis, which are quadriceps muscles. Feature quantity AM2 is extracted from the 59% to 62% section of the walking phase of gait waveform data related to time-series data of forward acceleration (Y-direction acceleration). The 59% to 62% walking phase is included in the early swing phase T4. Feature quantity AM2 mainly includes features related to the movement of the rectus femoris, which is one of the quadriceps muscles. Feature quantity AM3 is extracted from the 59% to 62% section of the walking phase of gait waveform data related to time-series data of vertical acceleration (Z-direction acceleration). The early swing phase T4 comprises 59 to 62% of the walking phase. Feature AM3 mainly includes features relating to the movement of the rectus femoris, one of the quadriceps muscles. Feature AM4 is the proportion of the period from heel-strike to toe-off of the opposite foot (DST1) during the period when both feet are simultaneously in contact with the ground. DST1 is the proportion of the period from heel-strike to toe-off of the opposite foot during a stride cycle. Feature AM4 mainly includes features attributable to the quadriceps muscles.

[0058] Feature AF1, feature AF2, and feature AF3 are used to estimate the grip strength of women. Feature AF1 is extracted from a 13% section of the walking phase of gait waveform data related to time-series data of lateral acceleration (X-direction acceleration). The 13% walking phase is included in the mid-stance phase T2. Feature AF1 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis, which are quadriceps muscles. Feature AF2 is extracted from a 7% to 10% section of the walking phase of gait waveform data related to time-series data of angular velocity (pitch angular velocity) in the coronal plane (around the Y-axis). The 7% to 10% walking phase is included in the initial stance phase T1. Feature AF2 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis. Feature AF3 is the proportion of the period from heel-contact to toe-off of the opposite foot to the period during which both feet are simultaneously on the ground (DST2). DST2 is the proportion of the period from heel contact to toe-off of the opposite foot in a gait cycle. The sum of DST1 and DST2 corresponds to the period in a gait cycle during which both feet are simultaneously in contact with the ground. Feature AF3 mainly includes features related to the movements of the vastus lateralis, vastus intermedius, and vastus medialis.

[0059] <Dynamic Balance> Dynamic balance, which is one of the physical abilities, can be evaluated by the performance of the Functional Reach Test (FRT). In the present disclosure, the performance of the FRT is evaluated based on the distance between the fingertips (also referred to as the functional reach distance) when the subject stands with both hands raised 90 degrees relative to the horizontal and then moves the upper limbs as far forward as possible. The functional reach distance (hereinafter referred to as the FR distance) is the performance value of the FRT. The larger the FR distance, the higher the performance of the FRT. Dynamic balance may also be evaluated by a method other than the FRT performed with both hands. For example, dynamic balance may be evaluated based on the performance of the FRT performed with one hand or other variations of the FRT.

[0060] The dynamic balance index is the FR distance. For example, an estimated value of the FR distance is the dynamic balance index. For example, a score corresponding to the estimated value of the FR distance (also referred to as the dynamic balance score) is the dynamic balance index. The dynamic balance score is a value obtained by scoring the FR distance, which is an index of dynamic balance, based on a preset criterion. Dynamic balance is affected by attributes such as height. Therefore, the dynamic balance score may be scored based on a criterion for each attribute. Note that the dynamic balance index is not limited to the FR distance as long as it can score dynamic balance. The FR distance is correlated with the activity of the gluteus medius, iliacus, hamstrings (long head of biceps femoris), tibialis anterior, etc., and the magnitude of the compensatory movement of turning the toes outward. Therefore, feature quantities extracted from walking phases in which these features appear are used to estimate the FR distance.

[0061] Feature B1, feature B2, feature B3, feature B4, and feature B5 are used to estimate the FR distance. Feature B1 is extracted from the 75-79% gait phase section of gait waveform data related to time-series data of forward acceleration (Y-direction acceleration). The 75-79% gait phase is included in the mid-swing phase T6. Feature B1 mainly includes features related to the movement of the tibialis anterior and the short head of the biceps femoris. Feature B2 is extracted from the 62% gait phase section of gait waveform data related to time-series data of vertical acceleration (Z-direction acceleration). The 62% gait phase is included in the early swing phase T5. Feature B2 mainly includes features related to the movement of the iliacus muscle. Feature B3 is extracted from the 7-8% gait phase section of gait waveform data related to time-series data of angular velocity in the coronal plane (around the Y-axis). The 7-8% gait phase is included in the early stance phase T1. Feature B3 mainly includes features related to the movement of the gluteus medius muscle. Feature B4 is extracted from the section of the walking phase 57-58% of the gait waveform data related to time-series data of angles (postural angles) in the horizontal plane (around the Z-axis). The walking phase 57-58% is included in the early swing phase T4. Feature B4 mainly includes features related to compensatory movements. Compensatory movements are movements that change the foot angle to achieve stability in order to compensate for the decline in balance ability and muscle function that occurs with aging. Feature B5 is the average value of the foot angle in the horizontal plane during the swing phase. For example, feature B5 is the average value of the gait waveform data during the swing phase. In other words, feature B5 is the integrated value of the gait waveform data related to time-series data of angular velocity in the horizontal plane (around the Z-axis). Feature B5 mainly includes features related to compensatory movements.

[0062] <Lower limb muscle strength> Lower limb muscle strength, which is one of the physical abilities, can be evaluated by the results of a chair stand test. In the present disclosure, the results of the 5-chair stand test, in which a subject stands up and sits down from a chair five times, are evaluated. The 5-chair stand test is also called the SS-5 (Sit to Stand-5) test. The results of the 5-chair stand test are evaluated based on the time it takes to stand up and sit down from a chair five times (also called the sit-to-stand time). The sit-to-stand time is the score value of the SS-5 test. The shorter the sit-to-stand time, the higher the score of the SS-5 test. Lower limb muscle strength may also be evaluated based on the results of a 30-second chair stand (CS-30) test, which measures the number of times the subject stands up and sits down from a chair in 30 seconds.

[0063] An indicator of lower limb muscle strength is the stand-sit time. For example, an estimated value of the stand-sit time five times is an indicator of lower limb muscle strength. For example, a score corresponding to the estimated stand-sit time (also referred to as a lower limb muscle strength score) is an indicator of lower limb muscle strength. The lower limb muscle strength score is a value obtained by scoring the stand-sit time, which is an indicator of lower limb muscle strength, based on a preset standard. Lower limb muscle strength is affected by attributes such as age. Therefore, the lower limb muscle strength score may be scored based on a standard for each attribute. Note that the indicator of lower limb muscle strength is not limited to the stand-sit time, as long as the lower limb muscle strength can be scored. The stand-sit time is correlated with the quadriceps, hamstrings, tibialis anterior, and gastrocnemius. Therefore, feature quantities extracted from walking phases in which these features are present are used to estimate the stand-sit time.

[0064] The estimation of lower limb muscle strength includes feature values ​​C1, C2, C3, and C4. Feature value C1 is extracted from the gait phase 42-54% section of gait waveform data related to time series data of angular velocity in the sagittal plane (around the X-axis). The gait phase 42-54% corresponds to the section from the end of stance phase T3 to the early swing phase T4. Feature value C1 mainly includes features related to the movement of the gastrocnemius muscle. Feature value C2 is extracted from the gait phase 99-100% section of gait waveform data related to time series data of angular velocity in the coronal plane (around the Y-axis). The gait phase 99-100% corresponds to the end of the end of swing phase T7. Feature value C2 mainly includes features related to the movement of the quadriceps, hamstrings, and tibialis anterior. Feature C3 is extracted from the 10% to 12% walking phase section of gait waveform data related to time series data of angular velocity in the coronal plane (around the Y-axis). The 10% to 12% walking phase corresponds to the beginning of mid-stance phase T2. Feature C3 mainly includes features related to the movements of the quadriceps, hamstrings, and gastrocnemius. Feature C4 is extracted from the 99% walking phase section of gait waveform data related to time series data of angles (postural angles) in the horizontal plane (around the Z-axis). The 99% walking phase corresponds to the end of end-swing phase T7. Feature C4 mainly includes features related to the movements of the quadriceps, hamstrings, and tibialis anterior.

[0065] <Mobility> Mobility, which is one of physical abilities, can be evaluated by the results of a TUG (Time Up and Go) test. In the present disclosure, the results of the TUG test are evaluated based on the time it takes to stand up from a chair, walk to a landmark 3 meters away, change direction, and sit back down in the chair (also referred to as the TUG time). The TUG time is the score value of the TUG test. The shorter the TUG time, the higher the score on the TUG test. Mobility may also be evaluated by the results of a mobility test other than the TUG test.

[0066] The mobility index is the time required for TUG. For example, an estimated value of the TUG time is the mobility index. For example, a score (also referred to as a mobility score) according to the estimated value of the TUG time is the mobility index. The mobility score is a value obtained by scoring the TUG time, which is an index of mobility, based on a preset standard. Mobility is affected by attributes such as age. Therefore, the mobility score may be scored based on a standard for each attribute. Note that the mobility index is not limited to the TUG time as long as it can score mobility. The TUG time is correlated with the quadriceps, gluteus medius, and tibialis anterior. Therefore, feature quantities extracted from walking phases in which these features appear are used to estimate the TUG time.

[0067] Feature values ​​D1, D2, D3, D4, D5, and D6 are used to estimate mobility. Feature value D1 is extracted from the 64-65% walking phase section of gait waveform data related to time-series data of lateral acceleration (X-direction acceleration). The 64-65% walking phase is included in the initial swing phase T5. Feature value D1 mainly includes features related to the movement of the quadriceps during standing-to-sitting movements. Feature value D2 is extracted from the 57-58% walking phase section of gait waveform data related to time-series data of angular velocity in the sagittal plane (around the X-axis). The 57-58% walking phase is included in the early swing phase T4. Feature value D2 mainly includes features related to the movement of the quadriceps related to foot kick-off velocity. Feature value D3 is extracted from the 19-20% walking phase section of gait waveform data related to time-series data of angular velocity in the coronal plane (around the Y-axis). The gait phase 19-20% is included in the mid-stance phase T2. The feature D3 mainly includes features related to the movement of the gluteus medius muscle during changes of direction. The feature D4 is extracted from the section of the gait phase 12-13% of the gait waveform data related to the time series data of angular velocity in the horizontal plane (around the Z-axis). The gait phase 12-13% corresponds to the beginning of the mid-stance phase T2. The feature D4 mainly includes features related to the movement of the gluteus medius muscle during changes of direction. The feature D5 is extracted from the section of the gait phase 74-75% of the gait waveform data related to the time series data of angular velocity in the horizontal plane (around the Z-axis). The gait phase 74-75% corresponds to the beginning of the mid-swing phase T6. The feature D5 mainly includes features related to the movement of the tibialis anterior muscle during standing up and sitting down and changes of direction. Feature D6 is extracted from the section of the walking phase 76-80% of the walking waveform data related to the time-series data of angles (postural angles) in the coronal plane (around the Y-axis). The walking phase 76-80% is included in the mid-swing phase T6. Feature D6 mainly includes features related to the movement of the tibialis anterior muscle when standing up and sitting down and changing direction.

[0068] <Static Balance> Static balance, which is one of the physical abilities, can be evaluated by the performance of a single-leg standing test. In the present disclosure, the performance of the single-leg standing test is evaluated based on the time (also referred to as single-leg standing time) that a subject maintains with one leg raised 5 cm (centimeters) from the ground with their eyes closed. The single-leg standing time is a static balance performance value. The longer the single-leg standing time, the higher the static balance performance. Static balance may also be evaluated by performance other than the eyes-closed single-leg standing test. For example, static balance may be evaluated by a single-leg standing test with the eyes open (eyes-open single-leg standing test) or other variations of the single-leg standing test.

[0069] An index of static balance is the single-leg standing time. For example, an estimated value of the single-leg standing time is an index of static balance. For example, a score (also called a static balance score) corresponding to the estimated value of the single-leg standing time is an index of static balance. The static balance score is a value obtained by scoring the single-leg standing time, which is an index of static balance, based on a preset criterion. Static balance is affected by attributes such as age and height. Therefore, the static balance score may be scored based on a criterion for each attribute. Note that the index of static balance is not limited to the single-leg standing time as long as it can score static balance. The single-leg standing time is correlated with the gluteus medius, adductor longus, sartorius, and abductor / adductor muscle groups. Therefore, feature quantities extracted from gait phases in which these features appear are used to estimate the single-leg standing time.

[0070] Feature values ​​E1, E2, E3, E4, E5, E6, and E7 are used to estimate static balance. Feature value E1 is extracted from the 13-19% gait phase section of gait waveform data related to time series data of lateral acceleration (X-direction acceleration). Gait phase 13-19% is included in mid-stance phase T2. Feature value E1 mainly includes features related to the movement of the gluteus medius muscle. Feature value E2 is extracted from the 95% gait phase section of gait waveform data related to time series data of vertical acceleration (Z-direction acceleration). Gait phase 95% is the final stage of end-swing phase T7. Feature value E2 mainly includes features related to the movement of the gluteus medius muscle. Feature value E3 is extracted from the 64-65% gait phase section of gait waveform data related to time series data of angular velocity in the coronal plane (around the Y-axis). The 64-65% gait phase is included in the early swing phase T5. Feature E3 mainly includes features related to the movement of the adductor longus and sartorius muscles. Feature E4 is extracted from the 11-16% gait phase section of gait waveform data related to time series data of angular velocity in the horizontal plane (around the Z-axis). The 11-16% gait phase section is included in mid-stance phase T2. Feature E4 mainly includes features related to the movement of the gluteus medius muscles. Feature E5 is extracted from the 57-58% gait phase section of gait waveform data related to time series data of angular velocity in the horizontal plane (around the Z-axis). The 57-58% gait phase section is included in early swing phase T4. Feature E5 mainly includes features related to the movement of the adductor longus and sartorius muscles. Feature E6 is extracted from the 100% gait phase section of gait waveform data related to time series data of angles (postural angles) in the horizontal plane (around the Z-axis). The 100% walking phase corresponds to the timing of heel contact, when the phase switches from the final swing phase T7 to the initial stance phase T1. The feature value of the walking waveform data at the 100% walking phase corresponds to the foot angle when the sole of the foot is in contact with the ground. The feature value E6 mainly includes features related to the movement of the gluteus medius. The feature value E7 is the distance between the axis of forward movement and the foot (circumflexion amount) at the timing when the central axis of the foot is farthest from the axis of forward movement during the swing phase. The feature value E7 is the circular movement amount normalized by the height of the subject. The feature value E7 mainly includes features related to the movement of the abductor and adductor muscles.

[0071] FIG. 8 is a conceptual diagram illustrating an example of a physical ability estimation model 150 that estimates physical ability. Feature quantities extracted from gait waveform data are input to the physical ability estimation model 150 that estimates physical ability. Furthermore, in addition to the feature quantity data extracted from the gait waveform data, the user's physical information (attributes) is also input. In FIG. 8 , the physical information (attributes) input to the physical ability estimation model 150 is omitted. In response to the input of the physical ability feature quantities extracted from the gait waveform data, the physical ability estimation model 150 outputs a physical ability score related to the physical ability. In the example of FIG. 8 , the physical ability estimation model 150 includes a grip strength estimation model 151, a dynamic balance estimation model 152, a lower limb strength estimation model 153, a mobility estimation model 154, and a static balance estimation model 155. Each of the grip strength estimation model 151, the dynamic balance estimation model 152, the lower limb strength estimation model 153, the mobility estimation model 154, and the static balance estimation model 155 outputs a score for each estimation target of the model. The physical ability estimation model 150 may be configured by a single model rather than by a model for each physical ability. Furthermore, the physical ability estimation model 150 may be configured by a physical ability value such as grip strength, FR distance, stand-up / sit-down time, TUG time, or one-leg standing time instead of a physical ability score.

[0072] The grip strength estimation model 151 outputs a grip strength score S1 related to grip strength (total muscle strength of the entire body) in response to input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a model that outputs grip strength in response to input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a model that outputs grip strength in response to input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a model that outputs grip strength in response to input of the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3. For example, the grip strength estimation model 151 may be a model that estimates grip strength using attribute data such as age and height in addition to the feature amounts AM1 to AM4 or the feature amounts AF1 to AF3.

[0073] The dynamic balance estimation model 152 outputs a dynamic balance score S2 related to dynamic balance in response to input of the feature quantities B1 to B5. There are no limitations on the estimation results of the dynamic balance estimation model 152 as long as an estimation result related to a dynamic balance index is output in response to input of the physical ability feature quantities for estimating dynamic balance. For example, the dynamic balance estimation model 152 may be a model that outputs an FR distance in response to input of the feature quantities B1 to B5. For example, the dynamic balance estimation model 152 may be a model that estimates dynamic balance using attribute data such as height in addition to the feature quantities B1 to B5.

[0074] The lower limb muscle strength estimation model 153 outputs a lower limb muscle strength score S3 related to lower limb muscle strength in response to input of the feature quantities C1 to C4. There are no limitations on the estimation results of the lower limb muscle strength estimation model 153, as long as an estimation result related to a lower limb muscle strength index is output in response to input of the physical ability feature quantities for estimating lower limb muscle strength. For example, the lower limb muscle strength estimation model 153 may be a model that outputs a lower limb muscle strength score S3 related to lower limb muscle strength in response to input of the feature quantities C1 to C4. For example, the lower limb muscle strength estimation model 153 may be a model that estimates dynamic balance using attribute data such as age in addition to the feature quantities C1 to C4.

[0075] The mobility estimation model 154 outputs a mobility score S4 related to mobility in response to input of the feature quantities D1 to D6. There are no limitations on the estimation results of the mobility estimation model 154, as long as an estimation result related to a mobility index is output in response to input of the physical ability feature quantities for estimating mobility. For example, the mobility estimation model 154 may be a model that outputs a TUG required time in response to input of the feature quantities D1 to D6. For example, the mobility estimation model 154 may be a model that estimates mobility using attribute data such as age in addition to the feature quantities D1 to D6.

[0076] The static balance estimation model 155 outputs a static balance score S5 related to static balance in response to input of the feature quantities E1 to E7. There are no limitations on the estimation results of the static balance estimation model 155 as long as an estimation result related to a static balance index is output in response to input of the physical ability feature quantities for estimating static balance. For example, the static balance estimation model 155 may be a model that outputs a one-leg standing time in response to input of the feature quantities E1 to E7. For example, the static balance estimation model 155 may be a model that estimates static balance using attribute data such as age and height in addition to the feature quantities E1 to E7.

[0077] The physical ability estimation model 150 may be stored in an external storage device constructed on a cloud, a server, or the like. In this case, the physical ability estimation unit 135 uses the physical ability estimation model 150 via an interface (not shown) connected to the storage device. The physical ability estimation model 150 is a machine learning model. For example, the physical ability estimation model 150 is a model trained using a dataset in which physical information (attributes) and gait indices of multiple subjects are used as explanatory variables and a physical ability score is used as a response variable, as training data. The physical ability estimation model 150 may also be a model trained using a dataset in which physical information (attributes) and gait waveform data of multiple subjects are used as explanatory variables and a physical ability score is used as a response variable, as training data. For example, the physical ability estimation model 150 may be a model trained using training data in which gait waveform data of acceleration in three axial directions, angular velocity around three axes, and angles around three axes (posture angles) are used as explanatory variables.

[0078] For example, the physical ability estimation model 150 may be generated by learning using a linear regression algorithm. For example, the physical ability estimation model 150 may be generated by learning using a support vector machine (SVM) algorithm. For example, the physical ability estimation model 150 may be generated by learning using a Gaussian process regression (GPR) algorithm. For example, the physical ability estimation model 150 may be generated by learning using a random forest (RF) algorithm. For example, the physical ability estimation model 150 may be generated by unsupervised learning that classifies the subject from which the physical ability feature was generated in accordance with the input of the physical ability feature. There are no particular limitations on the algorithm used to train the physical ability estimation model 150.

[0079] The disease risk estimation unit 136 acquires the estimation result of the physical ability (physical ability score) estimated by the physical ability estimation unit 135. The disease risk estimation unit 136 also acquires the gait index from the gait index calculation unit 133. Furthermore, the disease risk estimation unit 136 acquires physical information (attributes) of the user from the storage unit 134. The disease risk estimation unit 136 estimates the disease risk using the physical ability score, the gait index, and the physical information (attributes).

[0080] FIG. 9 is a conceptual diagram showing an example of a disease risk estimation model 160 that estimates disease risk. The disease risk estimation unit 136 inputs physical information, gait index, and physical ability score used to estimate the disease risk for a specific disease into the disease risk estimation model 160. The physical information, gait index, and physical ability score used to estimate the disease risk for a specific disease are input to the disease risk estimation model 160. In response to the input physical information, gait index, and physical ability score, the disease risk estimation model 160 outputs a disease risk score for the specific disease. The disease risk estimation unit 136 generates disease risk information according to the disease risk score output from the disease risk estimation model 160. In the example of FIG. 9, a disease risk score is estimated for each of a plurality of diseases. The disease risk estimation model 160 may be configured as a model for each disease, or as a single model. As the amount of data used for estimation increases, the accuracy of the disease risk score estimation by the disease risk estimation model 160 improves.

[0081] For example, the disease risk estimation model 160 outputs a disease risk score for a specific disease such as a lifestyle-related disease. For example, the disease risk estimation model 160 outputs a disease risk score for a specific disease such as gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia. For example, the disease risk estimation model 160 includes lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, Parkinson's syndrome, and the like. Note that the disease risk estimation model 160 may be configured to output a disease risk score for a disease other than those described above. For example, the disease risk estimation model 160 may be configured to estimate a disease risk score including test item data from a health checkup.

[0082] The disease risk estimation model 160 may be stored in an external storage device constructed on a cloud, a server, or the like. In this case, the disease risk estimation unit 136 uses the disease risk estimation model 160 via an interface (not shown) connected to the storage device. The disease risk estimation model 160 is a machine learning model. For example, the disease risk estimation model 160 is a model trained using training data in which physical information (attributes), gait indices, and physical abilities of multiple subjects are used as explanatory variables and a disease risk score for a specific disease is used as a target variable. For example, the disease risk estimation model 160 may be a model trained using training data in which gait waveform data of acceleration in three axial directions, angular velocity around three axes, and angles around three axes (posture angles) are used as explanatory variables.

[0083] For example, the disease risk estimation model 160 is generated by learning using a linear regression algorithm. For example, the disease risk estimation model 160 is generated by learning using a support vector machine (SVM) algorithm. For example, the disease risk estimation model 160 is generated by learning using a Gaussian process regression (GPR) algorithm. For example, the disease risk estimation model 160 is generated by learning using a random forest (RF) algorithm. For example, the disease risk estimation model 160 may be generated by unsupervised learning that classifies the subjects that generated the feature data according to the feature data. There are no particular limitations on the algorithm used to train the disease risk estimation model 160.

[0084] For example, the disease risk estimation model 160 may be a machine learning model such as an incomplete heterogeneous variational autoencoder or a random forest. The incomplete heterogeneous variational autoencoder can estimate the disease risk of a subject even if there are some deficiencies in features such as physical information (attributes), gait indicators, and physical information.

[0085] For example, the disease risk estimation model may be a model that outputs the average annual number of medical receipts issued in response to inputs of physical information, gait index, and physical ability score. The average annual number of medical receipts issued corresponds to the number of times an individual visits the hospital per year for treatment of a specific disease. In this case, the disease risk estimation unit 136 calculates the disease risk score using the average annual number of medical receipts issued. For example, the disease risk estimation model is generated by learning using a dataset in which physical information (attributes), gait index, and physical ability of multiple subjects are used as explanatory variables and the average annual number of medical receipts related to a specific disease is used as a target variable.

[0086] FIG. 10 is a conceptual diagram showing an example of a disease risk estimation model 165 that estimates the average annual number of medical receipts issued. The disease risk estimation unit 136 inputs physical information, gait index, and physical ability score to the disease risk estimation model 165. The disease risk estimation model 165 receives input of physical information, gait index, and physical ability score used to estimate the disease risk for a specific disease. In response to the input of the physical information, gait index, and physical ability score, the disease risk estimation model 165 outputs the average annual number of medical receipts issued for the specific disease. In the example of FIG. 10, the average annual number of medical receipts issued is estimated for each of a plurality of diseases. The disease risk estimation unit 136 calculates the disease risk score using the average annual number of medical receipts issued output from the disease risk estimation model 165.

[0087] Here, an example will be described in which the disease risk estimation unit 136 calculates a disease risk score using the average annual number of medical receipts issued. Three calculation examples will be given below. It is assumed that the average annual number of medical receipts issued μ for a typical person has been obtained in advance. The disease risk estimation model 165 outputs the average annual number of medical receipts μ for a specific disease in response to input physical information, gait index, and physical ability score related to a person whose disease risk is to be estimated.

[0088] In the first method, the disease risk estimation unit 136 calculates the disease risk score by calculating the ratio of the average annual number of medical receipts issued for a typical person μ to the average annual number of medical receipts issued μ estimated for the user. The disease risk estimation unit 136 calculates the disease risk score RS using the following equation 1: In the second method, the disease risk estimation unit 136 calculates the disease risk score under the assumption that the average annual number of medical receipts issued for a specific disease follows a Poisson distribution. In the second method, the disease risk estimation unit 136 calculates the disease risk score as the ratio of the probability mass function P(X=k) of the average annual number of medical receipts issued for a typical person to the probability mass function P(X=k) of the average annual number of medical receipts issued estimated for the user (k is a natural number). The disease risk estimation unit 136 calculates the disease risk score RS using the following equation 2: In the third method, the disease risk estimation unit 136 calculates the odds ratio of the average annual number of medical receipts issued for a specific disease. The disease risk estimation unit 136 calculates the disease risk score RS3 using the following Equation 3. The above three calculation examples are merely examples and do not limit the method of calculating the disease risk score using the average annual number of medical receipts issued. The disease risk estimation unit 136 may be configured to calculate the disease risk score using an index other than the average annual number of medical receipts issued.

[0089] The output unit 137 outputs disease risk information according to the disease risk score estimated by the disease risk estimation unit 136. For example, the output unit 137 displays the disease risk information on the screen of the subject's (user's) mobile terminal. For example, the output unit 137 outputs the disease risk information to an external system that uses the disease risk information. There are no particular limitations on how the output disease risk information can be used. For example, the disease risk information can be used for statistical analysis, research on disease prevention, and the like.

[0090] For example, the disease risk estimation device 13 is connected to an external system, such as a cloud or server, via a mobile device (not shown) carried by the subject (user). The mobile device (not shown) is a portable communication device. For example, the mobile device is a mobile communication device with a communication function, such as a smartphone, a smart watch, or a mobile phone. For example, the disease risk estimation device 13 is connected to the mobile device via wireless communication. For example, the disease risk estimation device 13 is connected to the mobile device via a wireless communication function (not shown) conforming to standards such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). Note that the communication function of the disease risk estimation device 13 may conform to standards other than Bluetooth (registered trademark) or Wi-Fi (registered trademark). For example, the disease risk estimation device 13 may be connected to the mobile device via a wired connection, such as a cable. The disease risk information may be used by an application installed on the mobile device. In this case, the mobile device performs processing using the disease risk information using application software, etc. installed on the mobile device.

[0091] (Operation) Next, the operation of the disease risk estimation system 1 will be described with reference to the drawings. The operation of the disease risk estimation device 13 included in the disease risk estimation system 1 will be described below. FIG. 11 is a flowchart for explaining an example of the operation of the disease risk estimation device 13. In describing the processing according to the flowchart of FIG. 11, the components of the disease risk estimation device 13 will be described as the actors performing the operations. The actor performing the processing according to the flowchart of FIG. 11 may be the disease risk estimation device 13.

[0092] 11 , first, the acquisition unit 131 acquires time-series data of sensor data measured by the measurement device 10 mounted on the footwear (step S11). The sensor data includes accelerations in three axial directions and angular velocities around three axes.

[0093] Next, the waveform processing unit 132 extracts walking waveform data from the time-series data of the sensor data (step S12). The walking waveform data corresponds to the time-series data of the sensor data for one walking cycle.

[0094] Next, the waveform processing unit 132 normalizes the extracted walking waveform data (step S13). The waveform processing unit 132 performs first normalization on the walking waveform data so that the step period is 100%. The waveform processing unit 132 also performs second normalization on the walking waveform data so that the stance phase is 60% and the swing phase is 40%.

[0095] Next, the gait index calculation unit 133 calculates gait indices used for estimating physical ability using the normalized walking waveform data (step S14). For example, the gait index calculation unit 133 calculates gait indices related to distance, height, angle, speed, time, frailty level, CPEI, etc.

[0096] Next, the physical ability estimation unit 135 estimates physical ability using the physical information and gait indices (step S15). For example, the physical ability estimation unit 135 estimates physical ability scores such as grip strength (total muscle strength of the entire body), dynamic balance, lower limb muscle strength, mobility, and static balance.

[0097] Next, the disease risk estimation unit 136 estimates a disease risk for a specific disease using the physical information, gait index, and physical ability (step S16). The disease risk estimation unit 136 estimates a disease risk score for a specific disease. For example, the disease risk estimation unit 136 estimates disease risk scores for diseases such as gout, diabetes, hypertension, nephrolithiasis, liver cirrhosis, arteriosclerosis, thromboembolism, dyslipidemia, hypercholesterolemia, and hyperlipidemia. For example, the disease risk estimation unit 136 estimates disease risk scores for diseases such as lower back pain, sleep apnea syndrome, insomnia, depression, osteoarthritis of the knee, and Parkinson's syndrome.

[0098] Next, the output unit 137 outputs disease risk information regarding the estimated disease risk (step S17). For example, the output unit 137 displays the disease risk information on the screen of the subject (user)'s mobile terminal. For example, the output unit 137 outputs the disease risk information to an external system or the like that uses the disease risk information.

[0099] (Application Examples) Next, application examples according to the present disclosure will be described with reference to the drawings. In the following application examples, an example of estimating disease risk using feature amount data measured by a measurement device 10 placed on a shoe is shown. For example, the functions of the disease risk estimation device 13 are installed on a mobile device carried by a user. The functions of the disease risk estimation device 13 may be implemented on a server or cloud connected to the mobile device carried by the user so as to enable data communication.

[0100] 12 is a conceptual diagram showing an example of displaying a disease risk score estimated by the disease risk estimation device 13 on the screen of a mobile terminal 170 carried by a user walking while wearing shoes 100 on which a measuring device 10 is placed. In the example of FIG. 12, disease risk information estimated using sensor data measured while the user is walking is displayed on the screen of the mobile terminal 170. The disease risk information estimated for each user is optimized for each user and displayed on the screen of the mobile terminal 170.

[0101] FIG. 12 shows an example in which disease risk information according to a disease risk score is displayed on the screen of the mobile device 170. In the example of FIG. 12, a disease risk score for each disease, such as "Disease A: XX, Disease B: YY, ..., Disease C: ZZ," is displayed on the screen of the mobile device 170. In addition, in the example of FIG. 12, disease risk information including advice according to the disease risk, such as "You are at high risk of contracting Disease A. We recommend that you exercise," is displayed on the screen of the mobile device 170 according to the disease risk score. For example, the advice according to the disease risk is generated by applying it to a predetermined document format. For example, the advice according to the disease risk may be generated using a large-scale language model.

[0102] A user who checks the disease risk information displayed on the display unit of the mobile device 170 can check the disease risk information, including the disease risk score and advice, and recognize their own disease risk. The disease risk information may be provided to a party other than the user. For example, the disease risk information may be output to a terminal device (not shown) used by a doctor or trainer who manages the user's physical condition, or by the user's family, etc. For example, the disease risk information may be recorded in a database (not shown) constructed for purposes such as health management. There are no particular limitations on the output destination or use of the disease risk information.

[0103] As described above, the disease risk estimation system of this embodiment includes a measurement device and a disease risk estimation device. The measurement device is attached to footwear of a user whose disease risk information is to be estimated. The measurement device measures spatial acceleration and spatial angular velocity. The measurement device generates sensor data using the measured spatial acceleration and spatial angular velocity. The measurement device transmits the generated sensor data to the disease risk estimation device. The disease risk estimation device includes an acquisition unit, a risk estimation unit, and an output unit. The acquisition unit acquires sensor data measured according to the foot movements of a subject whose disease risk is to be estimated. The risk estimation unit includes a calculation unit and an estimation unit. The calculation unit calculates a gait index using the sensor data. The estimation unit inputs data including the gait index calculated using the sensor data into the disease risk estimation model. The disease risk estimation model outputs a disease risk score indicating the degree of disease risk for a specific disease in response to the input of data including the gait index. The estimation unit estimates disease risk information according to the disease risk score output from the disease risk estimation model. The output unit outputs disease risk information according to the estimated disease risk.

[0104] As described above, the disease risk estimation device of this embodiment estimates the disease risk of a specific disease using sensor data measured in accordance with the sensor data related to the foot movements of a subject. That is, according to this embodiment, the risk of developing a disease can be estimated using sensor data measured in accordance with the foot movements.

[0105] In one aspect of this embodiment, the estimation unit includes a physical ability estimation unit and a disease risk estimation unit. The physical ability estimation unit inputs data including a gait index calculated using the sensor data to a physical ability estimation model that outputs a physical ability score indicating physical ability in response to input data including a gait index. The physical ability estimation unit estimates physical ability information according to the physical ability score output from the physical ability estimation model. The disease risk estimation unit inputs the gait index calculated using the sensor data and the physical ability score estimated by the physical ability estimation unit to the disease risk estimation model. The disease risk estimation unit estimates disease risk information according to the disease risk score output from the disease risk estimation model. According to this aspect, the risk of disease occurrence can be estimated using the physical ability score estimated using the gait index and the gait index.

[0106] In one aspect of this embodiment, the physical ability estimation model and the disease risk estimation model are models trained using a machine learning technique. For example, the disease risk estimation model includes an incomplete heterogeneous variational autoencoder. According to this aspect, it is possible to estimate the disease risk of a subject even if there are some deficiencies in physical information (attributes), gait indicators, physical information, and other features.

[0107] In one aspect of this embodiment, the physical ability estimation model outputs a physical ability score related to at least one of the physical abilities of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance in response to input of the subject's physical information and gait index. The disease risk estimation model outputs a disease risk score related to a specific disease in response to input of the subject's physical information, gait index, and physical ability score. According to this aspect, it is possible to estimate a disease risk score according to the physical ability score related to at least one of the physical abilities of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance.

[0108] In one aspect of this embodiment, the risk estimation unit estimates physical information using gait indices calculated using sensor data. The risk estimation unit estimates physical ability information and disease risk information using the estimated physical information. This approach improves usability by reducing the number of input items for physical information.

[0109] In one aspect of this embodiment, the disease risk estimation device displays estimated disease risk information for a subject, optimized for that subject, on a screen of a terminal device viewable by a user. According to this aspect, disease risk information for a subject can be provided in a manner optimized for that subject.

[0110] Second Embodiment Next, a disease risk estimation device according to a second embodiment will be described with reference to the drawings. The disease risk estimation device of this embodiment has a simplified configuration of the disease risk estimation device included in the disease risk estimation system of the first embodiment.

[0111] 13 is a block diagram showing an example of the configuration of a disease risk estimation device 20 according to the present disclosure. The disease risk estimation device 20 includes an acquisition unit 21, a risk estimation unit 25, and an output unit 27.

[0112] The acquisition unit 21 acquires sensor data measured according to the foot movements of a subject whose disease risk is to be estimated. The risk estimation unit 25 estimates the disease risk of a specific disease using the acquired sensor data. The output unit 27 outputs disease risk information according to the estimated disease risk.

[0113] (Operation) Next, the operation of the disease risk estimation device 20 will be described with reference to the drawings. Fig. 14 is a flowchart for explaining an example of the operation of the disease risk estimation device 20. In explaining the processing according to the flowchart of Fig. 14, the components of the disease risk estimation device 20 will be described as the actors performing the operations. The actor performing the processing according to the flowchart of Fig. 14 may be the disease risk estimation device 20.

[0114] In FIG. 14, first, the acquisition unit 21 acquires sensor data measured in accordance with the movement of the feet of a subject whose disease risk is to be estimated (step S21).

[0115] The risk estimation unit 25 estimates the disease risk for the specific disease using the acquired sensor data (step S22).

[0116] The output unit 27 outputs disease risk information according to the estimated disease risk (step S23).

[0117] As described above, the disease risk estimation device of this embodiment estimates the disease risk of a specific disease using sensor data measured in accordance with the sensor data related to the foot movements of a subject. That is, according to this embodiment, the risk of developing a disease can be estimated using sensor data measured in accordance with the foot movements.

[0118] (Hardware) Next, a hardware configuration for executing the control and processing in the present disclosure will be described with reference to the drawings. Here, an information processing device 90 (computer) in Fig. 15 is given as an example of such a hardware configuration. The information processing device 90 in Fig. 15 is an example configuration for executing the control and processing in the present disclosure and does not limit the scope of the present disclosure.

[0119] As shown in Fig. 15, an information processing device 90 includes a processor 91, a main storage device 92, an auxiliary storage device 93, an input / output interface 95, and a communication interface 96. In Fig. 15, interface is abbreviated as I / F (Interface). The processor 91, the main storage device 92, the auxiliary storage device 93, the input / output interface 95, and the communication interface 96 are connected to each other via a bus 98 so as to be able to communicate data with each other. The processor 91, the main storage device 92, the auxiliary storage device 93, and the input / output interface 95 are also connected to a network such as the Internet or an intranet via the communication interface 96.

[0120] The processor 91 loads a program (instructions) stored in the auxiliary storage device 93 or the like onto the main storage device 92. For example, the program is a software program for executing the control and processing of the present disclosure. The processor 91 executes the program loaded onto the main storage device 92. The processor 91 executes the program to execute the control and processing of the present disclosure.

[0121] The main memory device 92 has an area in which programs are loaded. The processor 91 loads programs stored in the auxiliary memory device 93 or the like into the main memory device 92. The main memory device 92 is realized by a volatile memory such as a dynamic random access memory (DRAM). Alternatively, a non-volatile memory such as a magneto-resistive random access memory (MRAM) may be configured / added to the main memory device 92.

[0122] The auxiliary storage device 93 stores various data such as programs. The auxiliary storage device 93 is realized by a local disk such as a hard disk or flash memory. Note that it is also possible to configure the main storage device 92 to store various data, thereby omitting the auxiliary storage device 93.

[0123] The input / output interface 95 is an interface for connecting the information processing device 90 to peripheral devices based on standards and specifications. The communication interface 96 is an interface for connecting to external systems and devices via a network such as the Internet or an intranet based on standards and specifications. The input / output interface 95 and the communication interface 96 may be a common interface for connecting to external devices.

[0124] Input devices such as a keyboard, mouse, and touch panel may be connected to the information processing device 90 as needed. These input devices are used to input information and settings. When a touch panel is used as the input device, a screen having the function of the touch panel serves as the interface. The processor 91 and the input devices are connected via an input / output interface 95.

[0125] The information processing device 90 may be equipped with a display device for displaying information. When the display device is equipped, the information processing device 90 is equipped with a display control device (not shown) for controlling the display of the display device. The information processing device 90 and the display device are connected via an input / output interface 95.

[0126] The information processing device 90 may be equipped with a drive device. The drive device acts as an intermediary between the processor 91 and a recording medium (program recording medium) to read data and programs stored on the recording medium and to write processing results of the information processing device 90 to the recording medium. The information processing device 90 and the drive device are connected via an input / output interface 95.

[0127] The above is an example of a hardware configuration for enabling the control and processing in the present disclosure. The hardware configuration in Fig. 15 is an example of a hardware configuration for executing the control and processing in the present disclosure and does not limit the scope of the present disclosure. A program that causes a computer to execute the control and processing in the present disclosure is also included in the scope of the present disclosure.

[0128] A program recording medium on which the program of the present disclosure is recorded is also included within the scope of the present disclosure. The recording medium can be realized, for example, as an optical recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc). The recording medium may also be realized as a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. The recording medium may also be realized as a magnetic recording medium such as a flexible disk or other recording medium. When a program executed by a processor is recorded on a recording medium, the recording medium corresponds to a program recording medium.

[0129] The components in the present disclosure may be combined in any manner. The components in the present disclosure may be realized by software. The components in the present disclosure may be realized by circuits.

[0130] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0131] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A disease risk estimation device comprising: an acquisition unit that acquires sensor data measured according to foot movement of a subject whose disease risk is to be estimated; a risk estimation unit that estimates a disease risk for a specific disease using the acquired sensor data; and an output unit that outputs disease risk information according to the estimated disease risk. (Supplementary Note 2) The disease risk estimation device according to Supplementary Note 1, wherein the risk estimation unit comprises: a calculation unit that calculates a gait index using the sensor data; and an estimation unit that inputs data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating the degree of the disease risk for the specific disease in response to input of data including the gait index, and estimates disease risk information according to the disease risk score output from the disease risk estimation model. (Supplementary Note 3) The disease risk estimation device according to Supplementary Note 2, wherein the estimation unit includes: a physical ability estimation unit that inputs data including the gait index calculated using the sensor data into a physical ability estimation model that outputs a physical ability score indicating physical ability in response to input of data including the gait index, and estimates physical ability information corresponding to the physical ability score output from the physical ability estimation model, and a disease risk estimation unit that inputs the gait index calculated using the sensor data and the physical ability score estimated by the physical ability estimation unit into the disease risk estimation model, and estimates the disease risk information corresponding to the disease risk score output from the disease risk estimation model. (Supplementary Note 4) The disease risk estimation device according to Supplementary Note 3, wherein the physical ability estimation model and the disease risk estimation model are models trained using a machine learning technique, and the disease risk estimation model includes an incomplete heterogeneous variational autoencoder.(Supplementary Note 5) The disease risk estimation device according to Supplementary Note 3, wherein the physical ability estimation model outputs the physical ability score related to at least one of physical abilities of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance in response to input of physical information and the gait index of the subject, and the disease risk estimation model outputs the disease risk score related to the specific disease in response to input of the physical information, the gait index, and the physical ability score of the subject. (Supplementary Note 6) The disease risk estimation device according to Supplementary Note 3, wherein the risk estimation unit estimates physical information using the gait index calculated using the sensor data, and estimates the physical ability information and the disease risk information using the estimated physical information. (Supplementary Note 7) A disease risk estimation system comprising: the disease risk estimation device according to any one of Supplements 1 to 6; and a measurement device that is installed in footwear of a user who is a target for disease risk information estimation, measures spatial acceleration and spatial angular velocity, generates sensor data using the measured spatial acceleration and spatial angular velocity, and transmits the generated sensor data to the disease risk estimation device. (Supplementary Note 8) The disease risk estimation system according to Supplementary Note 7, wherein the disease risk estimation device displays the disease risk information optimized for the subject on a screen of a terminal device viewable by the user. (Supplementary Note 9) A disease risk estimation method, in which a computer acquires sensor data measured according to foot movements of a subject whose disease risk is to be estimated, estimates a disease risk for a specific disease using the acquired sensor data, and outputs disease risk information according to the estimated disease risk. (Supplementary Note 10) The disease risk estimation method according to Supplementary Note 9, in which a computer calculates a gait index using the sensor data, inputs data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating the degree of the disease risk for the specific disease in response to input of data including the gait index, and estimates disease risk information according to the disease risk score output from the disease risk estimation model.(Supplementary Note 11) The disease risk estimation method according to Supplementary Note 10, wherein a computer inputs data including the gait index calculated using the sensor data into a physical ability estimation model that outputs a physical ability score indicating physical ability in response to input of data including the gait index, estimates physical ability information corresponding to the physical ability score output from the physical ability estimation model, inputs the gait index calculated using the sensor data and the estimated physical ability score into the disease risk estimation model, and estimates the disease risk information corresponding to the disease risk score output from the disease risk estimation model. (Supplementary Note 12) The disease risk estimation method according to Supplementary Note 11, wherein the physical ability estimation model and the disease risk estimation model are models trained using a machine learning technique, and the disease risk estimation model includes an incomplete heterogeneous variational autoencoder. (Supplementary Note 13) The disease risk estimation method according to Supplementary Note 11, wherein the physical ability estimation model outputs the physical ability score related to at least one of physical abilities of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance in response to input of the subject's physical information and the gait index, and the disease risk estimation model outputs the disease risk score related to the specific disease in response to input of the subject's physical information, the gait index, and the physical ability score. (Supplementary Note 14) The disease risk estimation method according to Supplementary Note 11, wherein a computer estimates physical information using the gait index calculated using the sensor data, and estimates the physical ability information and the disease risk information using the estimated physical information. (Supplementary Note 15) A computer-readable, non-transitory recording medium having recorded thereon a program causing a computer to execute the following processes: acquiring sensor data measured according to foot movement of a subject whose disease risk is to be estimated; estimating a disease risk related to a specific disease using the acquired sensor data; and outputting disease risk information corresponding to the estimated disease risk.(Supplementary Note 16) The computer-readable non-transitory recording medium according to Supplementary Note 15, having recorded thereon a program that causes a computer to execute the following processes: a process of calculating a gait index using the sensor data, a process of inputting data including the gait index into a disease risk estimation model that outputs a disease risk score indicating the degree of disease risk for the specific disease in response to input of data including the gait index, and a process of estimating disease risk information corresponding to the disease risk score output from the disease risk estimation model. (Supplementary Note 17) The computer-readable non-transitory recording medium according to Supplementary Note 16, having recorded thereon a program that causes a computer to execute the following processes: a process of inputting data including the gait index calculated using the sensor data into a physical ability estimation model that outputs a physical ability score indicating physical ability in response to input of data including the gait index, and estimating physical ability information corresponding to the physical ability score output from the physical ability estimation model, a process of inputting the gait index calculated using the sensor data and the estimated physical ability score into the disease risk estimation model, and a process of estimating the disease risk information corresponding to the disease risk score output from the disease risk estimation model. (Supplementary Note 18) The computer-readable non-transitory recording medium according to Supplementary Note 17, wherein the physical ability estimation model and the disease risk estimation model are models trained using a machine learning technique, and the disease risk estimation model includes an incomplete heterogeneous variational autoencoder. (Supplementary Note 19) The computer-readable non-transitory recording medium according to Supplementary Note 17, wherein the physical ability estimation model outputs the physical ability score related to at least any of physical abilities among grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance in response to input of physical information and the gait index of the subject, and the disease risk estimation model outputs the disease risk score related to the specific disease in response to input of the physical information, the gait index, and the physical ability score of the subject.(Supplementary Note 20) A computer-readable non-transitory recording medium according to Supplementary Note 17, having recorded thereon a program that causes a computer to execute the following processes: a process of estimating physical information using the gait index calculated using the sensor data; and a process of estimating the physical ability information and the disease risk information using the estimated physical information.

[0132] REFERENCE SIGNS LIST 1 Disease risk estimation system 10 Measurement device 13, 20 Disease risk estimation device 15 Risk estimation unit 21 Acquisition unit 25 Risk estimation unit 27 Output unit 110 Sensor 111 Acceleration sensor 112 Angular velocity sensor 113 Control unit 115 Communication unit 117 Power supply 130 Calculation unit 131 Acquisition unit 132 Waveform processing unit 133 Gait index calculation unit 134 Memory unit 135 Physical ability estimation unit 136 Disease risk estimation unit 137 Output unit 140 Estimation unit

Claims

1. an acquisition unit that acquires sensor data measured according to foot movements of a subject whose disease risk is to be estimated; a risk estimation unit that estimates a disease risk related to a specific disease using the acquired sensor data; A disease risk estimation device comprising: an output unit that outputs disease risk information according to the estimated disease risk.

2. The risk estimation unit a calculation unit that calculates a gait index using the sensor data; 2. The disease risk estimation device according to claim 1, further comprising: an estimation unit that inputs data including the gait index calculated using the sensor data into a disease risk estimation model that outputs a disease risk score indicating the degree of disease risk for the specific disease in response to input of data including the gait index, and estimates disease risk information according to the disease risk score output from the disease risk estimation model.

3. The estimation unit a physical ability estimation unit that inputs data including the gait index calculated using the sensor data into a physical ability estimation model that outputs a physical ability score indicating physical ability in response to input of data including the gait index, and estimates physical ability information according to the physical ability score output from the physical ability estimation model; 3. The disease risk estimation device according to claim 2, further comprising: a disease risk estimation unit that inputs the gait index calculated using the sensor data and the physical ability score estimated by the physical ability estimation unit into the disease risk estimation model, and estimates the disease risk information according to the disease risk score output from the disease risk estimation model.

4. the physical ability estimation model and the disease risk estimation model are models trained using a machine learning technique, The disease risk estimation model is The disease risk estimation device of claim 3 , comprising an incomplete heterogeneous variational autoencoder.

5. The physical ability estimation model is outputting the physical ability score relating to at least one of grip strength, dynamic balance, lower limb muscle strength, mobility, and static balance in response to input of the subject's physical information and the gait index; The disease risk estimation model is The disease risk estimation device according to claim 3 , wherein the disease risk score for the specific disease is output in response to input of the subject's physical information, the gait index, and the physical ability score.

6. The risk estimation unit estimating physical information using the gait index calculated using the sensor data; The disease risk estimation device according to claim 3 , wherein the estimated physical information is used to estimate the physical ability information and the disease risk information.

7. A disease risk estimation device according to any one of claims 1 to 6; A disease risk estimation system comprising: a measuring device that is installed in the footwear of a user whose disease risk information is to be estimated, measures spatial acceleration and spatial angular velocity, generates sensor data using the measured spatial acceleration and spatial angular velocity, and transmits the generated sensor data to the disease risk estimation device.

8. The disease risk estimation device includes: The disease risk estimation system according to claim 7 , wherein the disease risk information optimized for the subject is displayed on a screen of a terminal device viewable by the user.

9. The computer Acquire sensor data measured according to the foot movements of a subject whose disease risk is to be estimated; Estimating a disease risk for a specific disease using the acquired sensor data; A disease risk estimation method that outputs disease risk information according to the estimated disease risk.

10. A process of acquiring sensor data measured according to foot movements of a subject whose disease risk is to be estimated; A process of estimating a disease risk related to a specific disease using the acquired sensor data; and outputting disease risk information according to the estimated disease risk.

Images