Frailty estimation device, estimation system, frailty estimation method, and program

Abstract

To provide a frailty estimation device capable of estimating a frailty based on the gait of a subject.SOLUTION: The frailty estimation device comprises: a reception unit which acquires walking waveform data including the characteristics of the gait of a subject and feature amount data including a feature amount extracted from the walking waveform data; an estimation unit which estimates the grip of the subject by using the feature amount data, estimates the walking speed of the subject by using the walking waveform data, and estimates the frailty of the subject by using the estimated grip and walking speed; and an output unit which outputs information about the estimated frailty.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This disclosure relates to a frailty estimation device, etc., that estimates the possibility of frailty using data related to gait. [Background technology]

[0002] With the growing interest in healthcare, services that provide information based on gait patterns are attracting attention. For example, technologies are being developed that analyze gait patterns using sensor data measured by sensors implemented in footwear such as shoes. The time-series data of the sensor data reveals features associated with gait events (also called walking events) that are related to the body's physical state.

[0003] Patent Document 1 discloses a device for detecting foot abnormalities based on the characteristics of a pedestrian's gait. The device in Patent Document 1 uses data acquired from sensors installed on footwear to extract characteristic gait features of a pedestrian wearing footwear. Based on the extracted gait features, the device in Patent Document 1 detects abnormalities in a pedestrian wearing footwear. For example, the device in Patent Document 1 extracts characteristic areas related to hallux valgus from gait waveform data for one step cycle. The device in Patent Document 1 uses the extracted gait features of the characteristic areas to estimate the progression of hallux valgus.

[0004] If the possibility of frailty, which indicates age-related physical and mental decline, can be estimated based on information about gait, it may be possible to prevent elderly people from becoming dependent on care. One diagnostic criterion for frailty is the J-CHS criteria (Japan-Cardiovascular Health Study criteria) (Non-Patent Literature 1). In the J-CHS criteria, frailty is evaluated by five items: muscle weakness, walking speed, weight loss, fatigue, and physical activity. If three or more of the five items apply, the person is judged to be frail. If one or two of the five items apply, the person is judged to be pre-frail. If none of the five items apply, the person is judged to be robust (healthy). For example, muscle weakness is evaluated by grip strength. Grip strength is an index for evaluating overall muscle strength of the whole body (also called total whole-body muscle strength). Grip strength can also be an important index for evaluating the risk of falls.

[0005] Patent Document 2 discloses a leg muscle strength estimation device that estimates information related to a subject's leg muscle strength using measurement data from a communication-type grip strength meter. The device in Patent Document 2 uses grip strength value data measured by a communication-type grip strength meter and personal data input from a personal data input means to calculate the individual's maximum leg extension muscle strength / body weight data. The device in Patent Document 2 uses the individual's maximum leg extension muscle strength / body weight data and personal data to calculate fall age data, which is the age at which the likelihood of falling increases.

[0006] Non-Patent Document 2 discloses the initial symptoms and phenotypes of frailty. Non-Patent Document 2 also discloses a diagram (Figure 1 in Non-Patent Document) relating to the frailty cycle. Non-Patent Document 2 shows that frailty progresses through the interrelationship of factors such as body weight, activity level, walking speed, muscle strength, and balance. According to Non-Patent Document 2, a decrease in muscle strength makes it easier for walking speed to decrease and balance problems to occur.

[0007] Non-Patent Document 3 discloses differences in characteristics of walking speed depending on the presence or absence of frailty symptoms (Table 4 in Non-Patent Document 3). According to Non-Patent Document 3, subjects exhibiting frailty symptoms tend to have decreased walking speed and a wider distribution of walking speeds. [Prior art documents] [Patent Documents]

[0008] [Patent Document 1] International Publication No. 2021 / 140658 [Patent Document 2] Japanese Patent Publication No. 2014-221139 [Non-patent literature]

[0009] [Non-Patent Document 1] S. Satake and H. Arai, “The revised Japanese version of the Cardiovascular Health Study criteria (revised J-CHS criteria)”, Geriatr Gerontol Int., 2020 Oct, 20(10), pp. 992-993. [Non-Patent Document 2] Q. Xue. et al., “Initial Manifestations of Frailty Criteria and the Development of Frailty Phenotype in the Women's Health and Aging Study II”, Journal of Gerontology: MEDICAL SCIENCES, 2008, 63A(9), pp.984-990. [Non-Patent Document 3] M. Schwenk, et al., “Wearable Sensor-Based In-Home Assessment of Gait, Balance, and Physical Activity for Discrimination of Frailty Status: Baseline Results of the Arizona Frailty Cohort Study”, Gerontology, 2015, 61(3), pp.258-67.

Summary of the Invention

Problems to be Solved by the Invention

[0010] In the method of Patent Document 1, the progression state of hallux valgus is estimated using the gait feature amount of the feature part extracted from the data acquired from the sensor installed in the footwear. Patent Document 1 does not disclose estimating the possibility of frailty using the gait feature amount of the feature part extracted from the data acquired from the sensor installed in the footwear.

[0011] In the method of Patent Document 2, the maximum leg extension muscle strength / body weight data of the individual is calculated using the measurement data by the communication type grip strength meter and the input personal data. Patent Document 2 does not disclose estimating the possibility of frailty using the grip strength measured using the communication type grip strength meter.

[0012] An object of the present disclosure is to provide a frailty estimation device or the like that can estimate frailty based on the gait of a subject.

Means for Solving the Problems

[0013] A frailty estimation device according to an aspect of the present disclosure includes a receiving unit that acquires walking waveform data including characteristics of a subject's gait and feature quantity data including feature quantities extracted from the walking waveform data, an estimation unit that estimates the grip strength of the subject using the feature quantity data, estimates the walking speed of the subject using the walking waveform data, and estimates the frailty of the subject using the estimated grip strength and walking speed, and an output unit that outputs information regarding the estimated frailty.

[0014] In a frailty estimation method according to an aspect of the present disclosure, walking waveform data including characteristics of a subject's gait and feature quantity data including feature quantities extracted from the walking waveform data are acquired, the grip strength of the subject is estimated using the feature quantity data, the walking speed of the subject is estimated using the walking waveform data, the frailty of the subject is estimated using the estimated grip strength and walking speed, and information regarding the estimated frailty is output.

[0015] A program according to an aspect of the present disclosure causes a computer to execute a process of acquiring walking waveform data including characteristics of a subject's gait and feature quantity data including feature quantities extracted from the walking waveform data, a process of estimating the grip strength of the subject using the feature quantity data, a process of estimating the walking speed of the subject using the walking waveform data, a process of estimating the frailty of the subject using the estimated grip strength and walking speed, and a process of outputting information regarding the estimated frailty.

Effect of the Invention

[0016] According to the present disclosure, it is possible to provide a frailty estimation device or the like that can estimate frailty based on a subject's gait.

Brief Description of the Drawings

[0017] [Figure 1] It is a block diagram showing an example of the configuration of an estimation system according to the first embodiment. [Figure 2] It is a block diagram showing an example of the configuration of a gait measurement device included in the estimation system according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the arrangement of a gait measurement device according to the first embodiment. [Figure 4] This is a conceptual diagram illustrating an example of the relationship between the local coordinate system and the world coordinate system set in the gait measurement device according to the first embodiment. [Figure 5] This is a conceptual diagram illustrating the human body surface used in the description of the gait measurement device according to the first embodiment. [Figure 6] This is a conceptual diagram illustrating the gait cycle used in the description of the gait measurement device according to the first embodiment. [Figure 7] This graph illustrates an example of time-series data of sensor data measured by a gait measurement device according to the first embodiment. [Figure 8] This figure illustrates an example of normalization of gait waveform data extracted from time-series data of sensor data measured by a gait measurement device according to the first embodiment. [Figure 9] This is a conceptual diagram illustrating an example of a gait phase cluster from which the feature data generation unit of the gait measurement device according to the first embodiment extracts features. [Figure 10] This is a block diagram showing an example of the configuration of a frailty estimation device included in the estimation system according to the first embodiment. [Figure 11] This is a table of specific examples of features extracted by a gait measurement device in the estimation system according to the first embodiment in order to estimate a man's grip strength. [Figure 12] This is a block diagram showing an example of a man's grip strength estimation using a frailty estimation device included in the estimation system according to the first embodiment. [Figure 13] This is a table of specific examples of features extracted by a gait measurement device in the estimation system according to the first embodiment in order to estimate a woman's grip strength. [Figure 14] This is a block diagram showing an example of a woman's grip strength estimation using a frailty estimation device provided in the estimation system according to the first embodiment. [Figure 15]This is a flowchart illustrating an example of the operation of a gait measurement device included in the estimation system according to the first embodiment. [Figure 16] This is a flowchart illustrating an example of the operation of the frailty estimation device included in the estimation system according to the first embodiment. [Figure 17] This is a flowchart illustrating an example of grip strength estimation processing by a flail estimation device included in the estimation system according to the first embodiment. [Figure 18] This is a flowchart illustrating an example of walking speed estimation processing by a frailty estimation device included in the estimation system according to the first embodiment. [Figure 19] This is a conceptual diagram illustrating an example of the application of the estimation system according to the first embodiment. [Figure 20] This is a conceptual diagram illustrating an example of the application of the estimation system according to the first embodiment. [Figure 21] This is a block diagram showing an example of the configuration of a frailty estimation device according to the second embodiment. [Figure 22] Block diagram showing an example of a hardware configuration for executing the processing of each embodiment. [Modes for carrying out the invention]

[0018] The embodiments for carrying out the present invention will be described below with reference to the drawings. However, the embodiments described below have technically preferred limitations for carrying out the present invention, but the scope of the invention is not limited thereto. In all the figures used in the description of the embodiments below, the same parts are denoted by the same reference numerals unless there is a particular reason not to. Also, in the embodiments below, repeated explanations of similar configurations and operations may be omitted.

[0019] (First embodiment) First, the estimation system according to the first embodiment will be described with reference to the drawings. The estimation system of this embodiment measures sensor data related to the movement of the subject's feet in accordance with their walking. The estimation system of this embodiment estimates the subject's grip strength using the measured sensor data. The estimation system of this embodiment also estimates the subject's walking speed using the measured sensor data. Based on the estimated grip strength and walking speed, the estimation system of this embodiment estimates the likelihood that the subject is frail. Note that the sensor data is not limited to sensor data related to foot movement, but may include features related to gait. For example, the sensor data may be sensor data that includes features related to gait, measured using motion capture or smart apparel, etc.

[0020] (composition) Figure 1 is a block diagram showing an example of the configuration of the estimation system 1 according to this embodiment. The estimation system 1 comprises a gait measurement device 10 and a frailty estimation device 13. In this embodiment, an example in which the gait measurement device 10 and the frailty estimation device 13 are configured on separate hardware will be described. For example, the gait measurement device 10 is installed on the footwear of the subject (user) whose frailty is to be estimated. For example, the functions of the frailty estimation device 13 are installed on a portable terminal carried by the subject (user). The configurations of the gait measurement device 10 and the frailty estimation device 13 will be described individually below.

[0021] [Gait Measurement Device] Figure 2 is a block diagram showing an example of the configuration of a gait measurement device 10. The gait measurement device 10 includes a sensor 11 and a feature data generation unit 12. In this embodiment, an example is given in which the sensor 11 and the feature data generation unit 12 are integrated. The sensor 11 and the feature data generation unit 12 may be provided as separate devices. In the following, the configurations of the sensor 11 and the feature data generation unit 12 will be described individually.

[0022] <Sensor> As shown in Figure 2, sensor 11 includes an acceleration sensor 111 and an angular velocity sensor 112. Figure 2 shows an example in which the acceleration sensor 111 and the angular velocity sensor 112 are included in sensor 11. Sensor 11 may also include sensors other than the acceleration sensor 111 and the angular velocity sensor 112. The description of sensors other than the acceleration sensor 111 and the angular velocity sensor 112 that may be included in sensor 11 is omitted.

[0023] The acceleration sensor 111 is a sensor that measures acceleration in three axes (also called spatial acceleration). The acceleration sensor 111 measures acceleration (also called spatial acceleration) as a physical quantity related to the movement of the foot. The acceleration sensor 111 outputs the measured acceleration to the feature data generation unit 12. For example, the acceleration sensor 111 can be a piezoelectric, piezoresistive, or capacitive type sensor. The sensor used as the acceleration sensor 111 is not limited to any measurement method as long as it can measure acceleration.

[0024] 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 the movement of the foot. The angular velocity sensor 112 outputs the measured angular velocity to the feature data generation unit 12. For example, the angular velocity sensor 112 can use sensors of the vibration type, capacitive type, etc. The sensor used as the angular velocity sensor 112 is not limited to any measurement method as long as it can measure angular velocity.

[0025] Sensor 11 can be implemented, for example, by an inertial measurement device that measures acceleration and angular velocity. An example of an inertial measurement device is an IMU (Inertial Measurement Unit). An IMU includes an acceleration sensor 111 that measures acceleration in three axes and an angular velocity sensor 112 that measures angular velocity around three axes. Sensor 11 may also be implemented by an inertial measurement device such as a VG (Vertical Gyro) or AHRS (Attitude Heading). Alternatively, sensor 11 may be implemented by a GPS / INS (Global Positioning System / Inertial Navigation System). Sensor 11 may also be implemented by a device other than an inertial measurement device, as long as it can measure physical quantities related to foot movement.

[0026] Figure 3 is a conceptual diagram showing an example of how a gait measurement device 10 is positioned inside a shoe 100 for the right foot. In the example in Figure 3, the gait measurement device 10 is installed in a position corresponding to the underside of the arch of the foot. For example, the gait measurement device 10 is placed in an insole inserted into the shoe 100. For example, the gait measurement device 10 may be placed on the bottom surface of the shoe 100. For example, the gait measurement device 10 may be embedded in the body of the shoe 100. The gait measurement device 10 may or may not be detachable from the shoe 100. The gait measurement device 10 may be installed in a position other than the underside of the arch of the foot, as long as it can measure sensor data related to foot movement. The gait measurement device 10 may also be installed in the socks worn by the subject or in anklets or other ornaments worn by the subject. The gait measurement device 10 may also be directly attached to the foot or embedded in the foot. Figure 3 shows an example in which the gait measurement device 10 is installed in the right shoe 100. The gait measurement device 10 may also be installed in both shoes 100.

[0027] In the example shown in Figure 3, a local coordinate system is set with the gait measurement device 10 (sensor 11) as the reference point, including the x-axis in the left-right direction, the y-axis in the front-back direction, and the z-axis in the up-down direction. The x-axis is positive to the left, the y-axis is positive backward, and the z-axis is positive upward. The orientation of the axes set on the sensor 11 may be the same for both the left and right feet, or it may be different for each foot. For example, if sensors 11 manufactured to the same specifications are placed inside the left and right shoes 100, the up-down orientation (orientation in the Z-axis direction) of the sensors 11 placed in the left and right shoes 100 will be the same. In that case, the three axes of the local coordinate system set for the sensor data originating from the left foot and the three axes of the local coordinate system set for the sensor data originating from the right foot will be the same for both the left and right feet.

[0028] Figure 4 is a conceptual diagram illustrating the local coordinate system (x-axis, y-axis, z-axis) set for the gait measurement device 10 (sensor 11) installed on the underside of the arch of the foot, and the world coordinate system (X-axis, Y-axis, Z-axis) set relative to the ground. In the world coordinate system (X-axis, Y-axis, Z-axis), with the subject standing upright and facing the direction of travel, the subject's lateral direction is set as the X-axis (leftward is positive), the subject's rear direction is set as the Y-axis (backward is positive), and the direction of gravity is set as the Z-axis (vertically upward is positive). Note that the example in Figure 4 conceptually shows 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 show the relationship between the local coordinate system and the world coordinate system that changes according to the subject's gait.

[0029] Figure 5 is a conceptual diagram illustrating the planes (also called body planes) set on the human body. In this embodiment, the sagittal plane divides the body into left and right halves, the coronal plane divides the body into front and back halves, and the horizontal plane divides the body horizontally. In this embodiment, rotation in the sagittal plane with the x-axis as the axis of rotation is defined as roll, rotation in the coronal plane with the y-axis as the axis of rotation is defined as pitch, and rotation in the horizontal plane with the z-axis as the axis of rotation is defined as yaw. Furthermore, the angle of rotation in the sagittal plane with the x-axis as the axis of rotation is defined as the roll angle, the angle of rotation in the coronal plane with the y-axis as the axis of rotation is defined as the pitch angle, and the angle of rotation in the horizontal plane with the z-axis as the axis of rotation is defined as the yaw angle.

[0030] <Feature Data Generation Unit> As shown in Figure 2, the feature data generation unit 12 (also called a feature data generation device) includes an acquisition unit 121, a normalization unit 122, an extraction unit 123, a generation unit 125, and a transmission unit 127. For example, the feature data generation unit 12 is implemented by a microcomputer or microcontroller that performs overall control and data processing of the gait measurement device 10. For example, the feature data generation unit 12 includes a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc. The feature data generation unit 12 controls the acceleration sensor 111 and the angular velocity sensor 112 to measure angular velocity and acceleration. For example, the feature data generation unit 12 may be implemented on the side of a portable terminal (not shown) carried by the subject (user).

[0031] The acquisition unit 121 acquires acceleration in three axes from the acceleration sensor 111. The acquisition unit 121 also acquires angular velocity around the three axes from the angular velocity sensor 112. For example, the acquisition unit 121 performs analog-to-digital conversion (AD conversion) on the acquired physical quantities (analog data) such as angular velocity and acceleration. Note that the physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted to digital data by the acceleration sensor 111 and the angular velocity sensor 112, respectively. The acquisition unit 121 outputs the converted digital data (also called sensor data) to the normalization unit 122. The acquisition unit 121 may be configured to store the sensor data in a storage unit (not shown). The sensor data includes at least the acceleration data converted to digital data and the angular velocity data converted to digital data. The acceleration data includes acceleration vectors in three axes. The angular velocity data includes angular velocity vectors around the three axes. The acquisition time of the acceleration data and angular velocity data is associated with the data. The acquisition unit 121 may also apply corrections to the acceleration data and angular velocity data, such as correction for mounting errors, temperature correction, and linearity correction.

[0032] The normalization unit 122 acquires sensor data from the acquisition unit 121. The normalization unit 122 extracts time-series data equivalent to one walking cycle (also called walking waveform data) from the time-series data of acceleration in the three axes and angular velocity around the three axes included in the sensor data. The normalization unit 122 normalizes the time of the extracted walking waveform data equivalent to one walking cycle to a walking cycle of 0 to 100% (percent) (also called first normalization). Timings such as 1% and 10% included in the 0 to 100% walking cycle are also called walking phases. Furthermore, the normalization unit 122 normalizes the walking waveform data equivalent to one walking cycle that has been first normalized so that the stance phase accounts for 60% and the swing phase accounts for 40% (also called second normalization). The stance phase is the period during which at least a portion of the sole of the foot is in contact with the ground. The swing phase is the period during which the sole of the foot is off the ground. By applying second normalization to gait waveform data, the shift in the gait phase from which features are extracted can be suppressed by the influence of external disturbances.

[0033] Figure 6 is a conceptual diagram illustrating gait events detected in a single gait cycle based on the right foot. The horizontal axis of Figure 6 represents the gait cycle normalized with the right foot's gait cycle set as 100 percent (%). The point when the right heel touches the ground is defined as the starting point (0%), and the point when the right heel touches the ground again is defined as the ending point (100%). Each of the multiple timings included in a gait cycle is called a gait phase. A single gait cycle of one foot is broadly divided into the stance phase, in which at least a portion of the sole of the foot is in contact with the ground, and the swing phase, in which the sole of the foot is off the ground. In the example in Figure 6, the gait cycle is normalized so that the stance phase accounts for 60% and the swing phase accounts for 40%. The stance phase is subdivided into early stance T1, mid-stance T2, late stance T3, and early swing T4. The swing phase is subdivided into early swing T5, mid-swing T6, and late swing T7. The gait waveform for one gait cycle does not necessarily have to start from the moment the heel touches the ground. For example, the starting point of the gait waveform for one gait cycle may be set to the midpoint of the stance phase. In this embodiment, an example is given in which the midpoint of the stance phase is used as the start / end point of one gait cycle.

[0034] Walking event E1 represents heel contact (HC), the beginning of a single step cycle. Heel contact occurs when the heel of the right foot, which was off the ground during the swing phase, lands on the ground. Walking event E2 represents opposite toe off (OTO). Opposite toe off occurs when the toes of the left foot leave the ground while the sole of the right foot remains in contact with the ground. Walking event E3 represents heel rise (HR). Heel rise occurs when the heel of the right foot lifts off the ground while the sole of the right foot remains in contact with the ground. Walking event E4 represents opposite heel strike (OHS). Opposite heel strike occurs when the heel of the left foot, which was off the ground during the swing phase of the left foot, lands on the ground. Walking event E5 represents toe-off (TO). Toe-off is the event where the toes of the right foot leave the ground while the sole of the left foot remains in contact with the ground. Walking event E6 represents foot-adjacent (FA). Foot-adjacent is the event where the left and right feet cross while the sole of the left foot remains in contact with the ground. Walking event E7 represents tibia vertical (TV). Tibia vertical is the event where the tibia of the right foot becomes nearly perpendicular to the ground while the sole of the left foot remains in contact with the ground. Walking event E8 represents heel strike (HS), the end of one walking cycle. Walking event E8 corresponds to the end of the walking cycle that began with walking event E1, and also to the beginning of the next walking cycle.

[0035] Figure 7 illustrates an example of detecting heel strike (HC) and toe-off (TO) from time-series data (solid line) of forward acceleration (Y-direction acceleration). The timing of heel strike (HC) is the timing of the minimum peak immediately following the maximum peak in the time-series data of forward acceleration (Y-direction acceleration). The maximum peak that serves as a marker for the timing of heel strike (HC) corresponds to the maximum peak of the gait waveform data for one step cycle. The interval between consecutive heel strike (HC) is one step cycle. The timing of toe-off (TO) is the timing of the rise of the maximum peak that appears after the stance phase period in the time-series data of forward acceleration (Y-direction acceleration) where no fluctuations are observed. Figure 7 also shows time-series data (dashed line) of roll angle (angular velocity around the X-axis). The midpoint between the timing of the minimum roll angle and the timing of the maximum roll angle (also called the midpoint of the stance phase) corresponds to the timing of the center of the stance phase. For example, parameters such as walking speed, stride length, circumference, internal / external rotation, and plantarflexion / dorsiflexion (also called gait parameters) can be determined based on the timing of the midpoint of the stance phase.

[0036] Figure 8 illustrates an example of gait waveform data normalized by the normalization unit 122. The normalization unit 122 detects heel strike (HC) and toe-off (TO) from time-series data of acceleration in the direction of travel (Y-direction acceleration). The normalization unit 122 extracts the interval between consecutive heel strikes (HC) as gait waveform data for one step cycle. Through first normalization, the normalization unit 122 converts the horizontal axis (time axis) of the gait waveform data for one step cycle to a gait cycle of 0-100%. Figure 7 shows the gait waveform data after first normalization as a dashed line. In the gait waveform data after first normalization (dashed line), the timing of toe-off (TO) is shifted from 60%.

[0037] In the example shown in Figure 8, the normalization unit 122 normalizes the section from heel strike (HC) at 0% of the walking phase to toe-off (TO) following that heel strike to 60%. The normalization unit 122 also normalizes the section from toe-off (TO) to heel strike (HC) at 100% of the walking phase following that toe-off to 60% to 100%. As a result, the walking waveform data for one walking cycle is normalized into a section where the walking cycle is 0-60% (stance phase) and a section where the walking cycle is 60-100% (swing phase). Figure 8 shows the walking waveform data after the second normalization as a solid line. In the walking waveform data after the second normalization (solid line), the timing of toe-off (TO) coincides with 60%.

[0038] Figures 7 and 8 show an example of extracting and normalizing walking waveform data for one step cycle based on the acceleration in the direction of travel (Y-direction acceleration). For accelerations / angular velocities other than the acceleration in the direction of travel (Y-direction acceleration), the normalization unit 122 extracts and normalizes walking waveform data for one step cycle in accordance with the walking cycle of the acceleration in the direction of travel (Y-direction acceleration). Alternatively, the normalization unit 122 may generate time-series data of angles around the three axes by integrating the time-series data of angular velocities around the three axes. In that case, the normalization unit 122 also extracts and normalizes walking waveform data for one step cycle with respect to angles around the three axes in accordance with the walking cycle of the acceleration in the direction of travel (Y-direction acceleration).

[0039] The normalization unit 122 may extract and normalize walking waveform data for one step cycle based on acceleration / angular velocity other than the acceleration in the direction of travel (Y direction acceleration). For example, the normalization unit 122 may detect heel strike (HC) and toe-off (TO) from the time-series data of vertical acceleration (Z direction acceleration). The timing of heel strike (HC) 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) is approximately 0. The minimum peak that serves as a marker for the timing of heel strike (HC) corresponds to the smallest peak in the walking waveform data for one step cycle. The interval between consecutive heel strike (HC) is one step cycle. The timing of toe-off (TO) is the timing of an inflection point in the time-series data of vertical acceleration (Z direction acceleration) that gradually increases after passing through an interval of small fluctuation following the maximum peak immediately after heel strike (HC). Furthermore, the normalization unit 122 may extract and normalize walking waveform data for one step cycle based on both forward acceleration (Y-direction acceleration) and vertical acceleration (Z-direction acceleration). Alternatively, the normalization unit 122 may extract and normalize walking waveform data for one step cycle based on accelerations other than forward acceleration (Y-direction acceleration) and vertical acceleration (Z-direction acceleration), such as angular velocity or angle.

[0040] The extraction unit 123 acquires walking waveform data for one walking cycle, which has been normalized by the normalization unit 122. The extraction unit 123 extracts features used for grip strength estimation from the walking waveform data for one walking cycle. The extraction unit 123 extracts features for each walking phase cluster based on pre-set conditions. A walking phase cluster is a cluster that integrates temporally consecutive walking phases. A walking phase cluster contains at least one walking phase. A walking phase cluster may consist of a single walking phase. The walking waveform data and walking phases from which features used for grip strength estimation are extracted will be described later.

[0041] Figure 9 is a conceptual diagram illustrating an example of extracting features for estimating grip strength from walking waveform data for one step cycle. For example, the extraction unit 123 extracts temporally continuous walking phases i to i+m as a walking phase cluster C (where i and m are natural numbers). The walking phase cluster C contains m walking phases (components). That is, the number of walking phases (components) constituting the walking phase cluster C (also called the number of components) is m. Figure 9 shows an example where the walking phases are integer values, but the walking phases may be subdivided to decimal places. When the walking phases are subdivided to decimal places, the number of components in the walking phase cluster C will be a number corresponding to the number of data points in the interval of the walking phase cluster. The extraction unit 123 extracts features from each of the walking phases i to i+m. When the walking phase cluster C is composed of a single walking phase j, the extraction unit 123 extracts features from that single walking phase j (where j is a natural number).

[0042] The generation unit 125 generates the features of the walking phase cluster (second features) by applying a feature construct formula to the features extracted from each of the walking phases constituting the walking phase cluster (first features). The feature construct formula is a pre-set calculation formula for generating the features of the walking phase cluster. For example, the feature construct formula is a calculation formula related to arithmetic operations. For example, the second features calculated using the feature construct formula are the integral mean, arithmetic mean, slope, and variability of the first features in each walking phase included in the walking phase cluster. For example, the generation unit 125 applies a calculation formula that calculates the slope and variability of the first features extracted from each of the walking phases constituting the walking phase cluster as the feature construct formula. For example, if the walking phase cluster consists of a single walking phase, it is not possible to calculate the slope and variability, so a feature construct formula that calculates the integral mean or arithmetic mean should be used.

[0043] The transmitting unit 127 transmits feature data (secondary features) for each walking phase cluster, which are generated by the generating unit 125. The transmitting unit 127 also transmits walking waveform data for one walking cycle, which has been normalized by the normalization unit 122. The transmitting unit 127 transmits the feature data and walking waveform data to the frailty estimation device 13 that uses them. For example, the walking speed may be calculated in the gait measurement device 10. In that case, the transmitting unit 127 transmits the walking speed to the frailty estimation device 13 instead of the walking waveform data. If walking speed is transmitted instead of walking waveform data, communication capacity can be reduced.

[0044] For example, the transmitter 127 transmits feature data to the frailty estimation device 13 via wireless communication. For example, the transmitter 127 is configured to transmit feature data to the frailty estimation device 13 via a wireless communication function (not shown) conforming to standards such as Bluetooth® or WiFi®. The communication function of the transmitter 127 may conform to standards other than Bluetooth® or WiFi®. The transmitter 127 may also transmit feature data to the frailty estimation device 13 via a wired connection such as a cable.

[0045] [Frailty Estimation Device] Figure 10 is a block diagram showing an example of the configuration of the frailty estimation device 13. The frailty estimation device 13 includes a receiving unit 131, a storage unit 132, a grip strength estimation unit 133, a walking speed estimation unit 134, a frailty estimation unit 135, and an output unit 137. The storage unit 132, the grip strength estimation unit 133, the walking speed estimation unit 134, and the frailty estimation unit 135 constitute the estimation unit 130. The estimation unit 130 may be composed of the grip strength estimation unit 133, the walking speed estimation unit 134, and the frailty estimation unit 135.

[0046] The receiving unit 131 receives feature data and gait waveform data from the gait measurement device 10. The receiving unit 131 outputs the received feature data to the grip strength estimation unit 133. The receiving unit 131 also outputs the received gait waveform data to the gait speed estimation unit 134. For example, the receiving unit 131 receives feature data from the gait measurement device 10 via wireless communication. For example, the receiving unit 131 is configured to receive feature data from the gait measurement device 10 via a wireless communication function (not shown) conforming to standards such as Bluetooth® or WiFi®. The communication function of the receiving unit 131 may conform to standards other than Bluetooth® or WiFi®. The receiving unit 131 may also receive feature data from the gait measurement device 10 via a wired connection such as a cable.

[0047] The memory unit 132 stores a grip strength estimation model used to estimate grip strength. The grip strength estimation model is a model that outputs an estimated grip strength value in response to the input of feature data used for grip strength estimation. The grip strength estimation model is a model that has learned the relationship between grip strength and feature data related to the grip strength of multiple subjects. The walking phase cluster from which the feature data used for grip strength estimation is extracted differs by gender. Therefore, the memory unit 132 may store estimation models for men and estimation models for women. In other words, the memory unit 132 may store grip strength estimation models according to attributes.

[0048] For example, the grip strength estimation model may be stored in the memory unit 132 at the time of factory shipment of the product. For example, the grip strength estimation model may also be stored in the memory unit 132 at the time of calibration before use of the estimation system 1. For example, the system may be configured to use a grip strength estimation model stored in a storage device such as an external server. In that case, the system may be configured to use the grip strength estimation model via an interface (not shown) connected to the storage device.

[0049] Furthermore, the memory unit 132 stores the estimated grip strength value estimated by the grip strength estimation unit 133 and the estimated walking speed value estimated by the walking speed estimation unit 134. The memory unit 132 stores the estimated grip strength and walking speed values ​​for multiple walking cycles. The memory unit 132 stores the estimated grip strength and walking speed values ​​associated with walking cycles. The memory unit 132 includes a memory area for storing the grip strength estimation model and a memory area for storing the estimated grip strength and walking speed values. The memory area for storing the grip strength estimation model and the memory area for storing the estimated grip strength and walking speed values ​​may be configured in different memory devices.

[0050] The grip strength estimation unit 133 acquires feature data equivalent to one step cycle from the receiving unit 131. The grip strength estimation unit 133 estimates the grip strength using the acquired feature data. The grip strength estimation unit 133 inputs the feature data into the grip strength estimation model stored in the memory unit 132. The grip strength estimation unit 133 outputs the estimated grip strength value output from the estimation model. When using a grip strength estimation model stored in an external storage device built on a cloud or server, the grip strength estimation unit 133 accesses the estimation model via an interface (not shown) connected to that storage device. The grip strength estimation unit 133 stores the estimated grip strength value in the memory unit 132.

[0051] Furthermore, the grip strength estimation unit 133 retrieves the estimated grip strength values ​​for a predetermined number of measurements once they have been stored in the storage unit 132. For example, the predetermined number of measurements is 10. For example, if measurements are taken three times a day, 21 feature data points will be stored in a week. The grip strength estimation unit 133 uses the estimated grip strength values ​​for a predetermined number of measurements stored in the storage unit 132 to estimate the probability distribution of grip strength. For example, the grip strength estimation unit 133 calculates the mean (expected value) and variance of the estimated grip strength values ​​for a predetermined number of measurements to generate a probability function of grip strength. In this embodiment, it is assumed that the distribution of feature data follows a normal distribution. If feature data measured at a single measurement opportunity is used, there will be variability in the estimated grip strength for each measurement opportunity. Therefore, in this embodiment, a probability function of grip strength measured at multiple measurement opportunities is generated. The grip strength estimation unit 133 stores the calculated probability distribution of grip strength in the storage unit 132. The grip strength estimation unit 133 may output the calculated probability distribution of grip strength to the frailty estimation unit 135.

[0052] The walking speed estimation unit 134 acquires walking waveform data for two consecutive walking cycles from the receiving unit 131. The walking speed estimation unit 134 detects the midpoint of the stance foot from the acquired walking waveform data for two walking cycles. Only one midpoint of the stance foot is detected from the walking waveform data for one walking cycle. That is, the walking speed estimation unit 134 detects two midpoints of the stance foot from the walking waveform data for two walking cycles. The walking speed estimation unit 134 calculates the trajectory of the foot in the horizontal plane using the walking waveform data between the two midpoints of the stance foot. The walking speed estimation unit 134 calculates the trajectory of the foot in the horizontal plane using the spatial acceleration and spatial angular velocity included in the walking waveform data. The walking speed estimation unit 134 calculates the distance between the start and end points of the calculated foot trajectory as the distance traveled. The walking speed estimation unit 134 calculates the walking speed by dividing the distance traveled in the horizontal plane by the time between the two midpoints of the stance foot. The walking speed estimation unit 134 stores the estimated walking speed in the storage unit 132.

[0053] Furthermore, the walking speed estimation unit 134 retrieves estimated walking speeds for a predetermined number of measurements once those estimates have been stored in the storage unit 132. For example, the predetermined number of measurements is 10. The walking speed estimation unit 134 uses the estimated walking speeds for the predetermined number of measurements to estimate the probability distribution of walking speed. For example, the walking speed estimation unit 134 calculates the mean (expected value) and variance of the estimated values ​​for the predetermined number of measurements to generate a probability function of walking speed. In this embodiment, it is assumed that the distribution of walking waveform data follows a normal distribution. If feature data measured at a single measurement opportunity is used, there will be variability in the estimated walking speed for each measurement opportunity. Therefore, in this embodiment, a probability function of walking speed measured at multiple measurement opportunities is generated. The walking speed estimation unit 134 stores the calculated probability distribution of walking speed in the storage unit 132. The walking speed estimation unit 134 may output the calculated probability distribution of walking speed to the frailty estimation unit 135.

[0054] The frailty estimation unit 135 obtains the probability distribution of the subject's grip strength from the grip strength estimation unit 133. The frailty estimation unit 135 also obtains the probability distribution of the subject's walking speed from the walking speed estimation unit 134. The frailty estimation unit 135 uses the probability distribution of grip strength and the probability distribution of walking speed to estimate the subject's frailty. Alternatively, the frailty estimation unit 135 may estimate the subject's frailty using only grip strength and walking speed.

[0055] One of the diagnostic criteria for frailty is the J-CHS criteria (Japan-Cardiovascular Health Study criteria) (Non-patent Literature 1: S. Satake and H. Arai, "The revised Japanese version of the Cardiovascular Health Study criteria (revised J-CHS criteria)", Geriatr Gerontol Int., 2020 Oct, 20(10), pp. 992-993). In the J-CHS criteria, frailty is evaluated based on five items: muscle weakness, walking speed, weight loss, fatigue, and physical activity. If three or more of the five items apply, the person is judged to be frail. If one or two of the five items apply, the person is judged to be pre-frail. If none of the five items apply, the person is judged to be robust (healthy). For example, muscle weakness is evaluated by grip strength. Grip strength is an index for evaluating overall muscle strength of the whole body (also called overall muscle strength of the whole body). Grip strength can also be an important indicator for assessing the risk of falls.

[0056] The frailty estimation unit 135 uses grip strength and walking speed, two of the five items in the J-CHS criteria, to estimate frailty. Different criteria are set for grip strength for men and women. For men, if grip strength is less than 26 kilograms, it is judged that muscle strength is reduced. For women, if grip strength is less than 18 kilograms, it is judged that muscle strength is reduced. A common criterion is set for walking speed for both men and women. If walking speed is less than 1 meter per second, it is judged that walking speed is reduced.

[0057] The frailty estimation unit 135 determines that a subject may be frail if they meet two criteria regarding grip strength and walking speed. The frailty estimation unit 135 determines that a subject is pre-frail if they meet one of the criteria regarding grip strength and walking speed. The frailty estimation unit 135 determines that a subject is robust (healthy) if they do not meet any of the criteria regarding grip strength and walking speed.

[0058] When it is determined that there is a possibility of frailty (when it corresponds to the two items of grip strength and walking speed), additional evaluation may be performed on the three items of weight loss, fatigue, and physical activity. For example, the additional evaluation may be performed by a questionnaire method. If at least any one of the three items of weight loss, fatigue, and physical activity is a check target, it corresponds to three or more of the five items of the J-CHS standard, and thus it is determined to be frail. Regarding weight loss, if there is a weight loss of 2 kilograms or more in six months, it is a check target for frailty. Regarding fatigue, if one feels tired without any reason (in the past two weeks), it is a check target for frailty. Regarding physical activity, if neither "light exercise / gymnastics" nor "regular exercise / sports" is performed, it is a check target for frailty. If none of the three items of weight loss, fatigue, and physical activity is a check target, it corresponds to two of the five items of the J-CHS standard, and thus it is determined to be pre-frail.

[0059] The frailty estimation unit 135 uses the probability distribution P H (H) and the probability distribution P v (v) of the walking speed to estimate the probability P F of being frail. H indicates the estimated value of the grip strength. v indicates the walking speed. The frailty estimation unit 135 estimates the probability P F (also referred to as the frailty probability) regarding frailty based on the following formula 1.

[0060]

Equation

[0061] The frailty estimation unit 135 estimates the subject's frailty using the above formula 1. Probability P F The larger the value, the higher the probability of frailty. Here, we set the threshold for determining pre-frailty (also called the third threshold) to 0.3 and the threshold for determining frailty (also called the fourth threshold) to 0.6. Under these conditions, probability P F If the probability P is between 0.3 and 0.6, the frailty estimation unit 135 estimates that the subject is pre-frail. F If the probability P exceeds 0.6, the frailty estimation unit 135 estimates that the subject is likely to be frail. F If the value is less than 0.3, the frailty estimation unit 135 estimates that the subject is robust (healthy). The lower threshold for determining pre-frailty and the lower threshold for determining frailty may be set to values ​​different from those above. For example, the frailty estimation unit 135 uses the probability distribution P of grip strength. H (H>H th ) and the probability distribution P of walking speed v (v>v th ) can be used to individually verify grip strength and walking speed.

[0062] The output unit 137 outputs the frailty estimation results from the frailty estimation unit 135. For example, the output unit 137 displays the frailty estimation results on the screen of the subject's (user's) mobile device. For example, the output unit 137 outputs the estimation results to an external system that uses the estimation results. There are no particular limitations on how the frailty estimation results output from the frailty estimation device 13 are used.

[0063] For example, the frailty estimation device 13 is connected to an external system built on a cloud or server via a mobile terminal (not shown) carried by the subject (user). The mobile terminal (not shown) is a portable communication device. For example, the mobile terminal is a portable communication device with communication functions such as a smartphone, smartwatch, or mobile phone. For example, the frailty estimation device 13 is connected to the mobile terminal via a wired connection such as a cable. For example, the frailty estimation device 13 is connected to the mobile terminal via wireless communication. For example, the frailty estimation device 13 is connected to the mobile terminal via wireless communication function (not shown) conforming to standards such as Bluetooth® or WiFi®. Note that the communication function of the frailty estimation device 13 may conform to standards other than Bluetooth® or WiFi®. The grip strength estimation result may be used by an application installed on the mobile terminal. In that case, the mobile terminal performs processing using the estimation result by application software installed on the mobile terminal.

[0064] [Estimated grip strength of men] Next, we will explain the correlation between male grip strength and feature data, referring to the diagram. Figure 11 is a correspondence table summarizing the features used to estimate male grip strength. The correspondence table in Figure 11 associates the feature number, the gait waveform data from which the feature is extracted, the gait phase (%) from which the gait phase cluster is extracted, and the associated muscles. In men, there is a correlation between quadriceps femoris activity and grip strength. Therefore, to estimate male grip strength, features M1 to M4 extracted from the gait phase, which exhibits characteristics of quadriceps femoris activity, are used.

[0065] Feature vector M1 is extracted from the 3% interval of the walking phase of the walking waveform data Ay, which relates to the time-series data of acceleration in the direction of movement (Y-direction acceleration). The 3% walking phase is included in the initial stance phase T1. Feature vector M1 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis muscles of the quadriceps femoris.

[0066] Feature vector M2 is extracted from the 59-62% interval of the gait phase of the gait waveform data Ay, which relates to the time-series data of acceleration in the direction of movement (Y-direction acceleration). The 59-62% gait phase is included in the early swing phase T4. Feature vector M2 mainly contains features related to the movement of the rectus femoris muscle, a part of the quadriceps femoris.

[0067] Feature vector M3 is extracted from the 59-62% interval of the gait phase of the gait waveform data Az, which relates to the time-series data of vertical acceleration (Z-direction acceleration). The 59-62% gait phase is included in the early swing phase T4. Feature vector M3 mainly contains features related to the movement of the rectus femoris muscle, a part of the quadriceps femoris.

[0068] Feature M4 is the ratio of the time from heel strike to opposite foot toe-off (DST1) during the period when both feet are simultaneously in contact with the ground (DST: Double Support Time). DST1 is the ratio of the time from heel strike to opposite foot toe-off in one step cycle. Feature M4 mainly includes features attributable to the quadriceps femoris muscle.

[0069] Figure 12 is a conceptual diagram showing an example in which an estimated grip strength is output by inputting features M1-M4 extracted from sensor data measured during a subject's walking into an estimation model 151 that has been pre-built to estimate a man's grip strength. Estimation model 151 (also called the male estimation model) outputs an estimated grip strength in response to the input of features M1-M4. For example, estimation model 151 is generated by learning using training data in which the features M1-M4 used to estimate a man's grip strength are used as explanatory variables and the grip strength of a man is used as the dependent variable. As long as an estimation result regarding grip strength is output in response to the input of feature data for estimating a man's grip strength, there are no limitations on the estimation results of estimation model 151. For example, estimation model 151 may be a model that estimates a man's grip strength using attributes such as age and height as explanatory variables in addition to the features M1-M4 used to estimate a man's grip strength.

[0070] For example, the memory unit 132 stores an estimation model for estimating a man's grip strength using a multiple regression prediction method. For example, the memory unit 132 stores parameters for estimating a man's grip strength GM using the following equation 2.

[0071]

number

[0072] [Estimation of a woman's grip strength] Next, we will explain the correlation between women's grip strength and feature data, including an example of verification. Figure 13 is a correspondence table summarizing the features used to estimate women's grip strength. The correspondence table in Figure 13 associates the feature number, the gait waveform data from which the feature is extracted, the gait phase (%) from which the gait phase cluster is extracted, and the associated muscles. In women, there is a correlation between the activity of the vastus lateralis, vastus intermedius, and vastus medialis muscles of the quadriceps femoris and grip strength. Therefore, to estimate women's grip strength, features F1 to F3 extracted from gait phases that show the characteristics of the activity of the vastus lateralis, vastus intermedius, and vastus medialis muscles are used.

[0073] Feature vector F1 is extracted from the 13% interval of the gait phase of the gait waveform data Ax, which relates to the time-series data of lateral acceleration (X-direction acceleration). The 13% gait phase is included in mid-stance T2. Feature vector F1 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis muscles of the quadriceps femoris.

[0074] Feature vector F2 is extracted from the gait waveform data Gy during the 7-10% gait phase, which is related to the time-series data of angular velocity (pitch angular velocity) within the coronal plane (around the Y-axis). The 7-10% gait phase is included in the initial stance phase T1. Feature vector F2 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis muscles.

[0075] Feature F3 is the ratio of the period from heel strike of the opposite foot to toe-off (DST2) to the time when both feet are simultaneously in contact with the ground (DST: Double Support Time). DST2 is the ratio of the period from heel strike of the opposite foot to toe-off in one step cycle. The sum of DST1 and DST2 corresponds to the period when both feet are simultaneously in contact with the ground in one step cycle. Feature F3 mainly includes features related to the movement of the vastus lateralis, vastus intermedius, and vastus medialis muscles.

[0076] Figure 14 is a conceptual diagram showing an example in which an estimated grip strength is output by inputting feature data extracted from sensor data measured during a subject's walking into an estimation model 152 that has been pre-built to estimate a woman's grip strength. Estimation model 152 (also called the estimation model for women) outputs grip strength, which is a muscle strength index, in response to the input of feature data. For example, estimation model 152 is generated by learning using training data in which the feature data used to estimate a woman's grip strength is used as the explanatory variable and a woman's grip strength is used as the dependent variable. As long as an estimation result for grip strength, which is a muscle strength index, is output in response to the input of feature data for estimating a woman's grip strength, there are no limitations on the estimation results of estimation model 152. For example, estimation model 152 may be a model that estimates a woman's grip strength using attributes such as age and height as explanatory variables in addition to the feature data used to estimate a woman's grip strength.

[0077] For example, the memory unit 132 stores an estimation model for estimating a woman's grip strength using a multiple regression prediction method. For example, the memory unit 132 stores parameters for estimating a woman's grip strength GF using the following equation 3.

[0078]

number

[0079] For example, the estimation model is generated by learning using a linear regression algorithm. For example, the estimation model is generated by learning using a support vector machine (SVM) algorithm. For example, the estimation model is generated by learning using a Gaussian process regression (GPR) algorithm. For example, the estimation model is generated by learning using a random forest (RF) algorithm. For example, the estimation model may be generated by unsupervised learning that classifies the subjects who generated the feature data according to the feature data. There are no particular limitations on the learning algorithm used to generate the estimation model.

[0080] The estimation model may be generated by learning using walking waveform data for one step cycle as explanatory variables. For example, the estimation model may be generated by supervised learning using walking waveform data of acceleration in three axes, angular velocity around three axes, and angles (postural angles) around three axes as explanatory variables, and grip strength, which is the target of estimation, as the dependent variable.

[0081] (operation) Next, the operation of the estimation system 1 will be explained with reference to the diagrams. Here, the gait measurement device 10 and the frailty estimation device 13 included in the estimation system 1 will be explained individually. Regarding the gait measurement device 10, the operation of the feature data generation unit 12 included in the gait measurement device 10 will be explained.

[0082] [Gait Measurement Device] Figure 15 is a flowchart illustrating an example of the operation of the feature data generation unit 12 included in the gait measurement device 10. In the explanation following the flowchart in Figure 15, the feature data generation unit 12 will be described as the main operator.

[0083] In Figure 15, first, the feature data generation unit 12 acquires time-series data of sensor data related to gait (step S101).

[0084] Next, the feature data generation unit 12 extracts a walking waveform for one step cycle from the time-series data of the sensor data (step S102). The feature data generation unit 12 detects heel strike and toe-off from the time-series data of the sensor data. The feature data generation unit 12 extracts the time-series data of the interval between consecutive heel strikes as a walking waveform for one step cycle.

[0085] Next, the feature data generation unit 12 normalizes the extracted walking waveform for one step (step S103). The feature data generation unit 12 normalizes the walking waveform for one step to a walking period of 0 to 100% (first normalization). Furthermore, the feature data generation unit 12 normalizes the ratio of the stance phase to the swing phase of the walking waveform for the first normalized one step to 60:40 (second normalization). The normalized walking waveform is called walking waveform data.

[0086] Next, the feature data generation unit 12 extracts features from the normalized gait waveform data, specifically from the gait phase used to estimate grip strength (step S104). For example, the feature data generation unit 12 extracts features to be input into estimation models constructed for each gender.

[0087] Next, the feature data generation unit 12 generates feature data for each walking phase cluster using the extracted features (step S105).

[0088] Next, the feature data generation unit 12 integrates the features for each walking phase cluster to generate feature data for one step cycle (step S106).

[0089] Next, the feature data generation unit 12 transmits the generated feature data to the frailty estimation device 13 (step S107).

[0090] [Frailty Estimation Device] Figure 16 is a flowchart illustrating the operation of the frailty estimation device 13. In the explanation following the flowchart in Figure 16, the frailty estimation device 13 will be described as the main operator.

[0091] In Figure 16, first, the frailty estimation device 13 receives feature data / gait waveform data transmitted from the gait measurement device 10 (step S111).

[0092] Next, the frailty estimation device 13 executes the grip strength estimation process (step S112) and the walking speed estimation process (step S113) in parallel. Details of the grip strength estimation process and the walking speed estimation process will be described later. The grip strength estimation process and the walking speed estimation process may be executed sequentially.

[0093] Next, the frailty estimation device 13 estimates frailty using the probability distribution of grip strength estimated by the grip strength estimation process and the probability distribution of walking speed estimated by the walking speed estimation process (step S114).

[0094] Next, the frailty estimation device 13 outputs information regarding the estimated frailty (step S115). For example, the information regarding frailty is output to a terminal device (not shown) carried by the subject. For example, the information regarding frailty is output to a system that performs processing using that information.

[0095] <Grip strength estimation process> Next, the grip strength estimation process by the frailty estimation device 13 (step S112 in Figure 16) will be explained with reference to the diagram. Figure 17 is a flowchart for explaining the grip strength estimation process. In the explanation following the flowchart in Figure 17, the frailty estimation device 13 will be described as the main operating component.

[0096] In Figure 17, first, the frailty estimation device 13 acquires feature data equivalent to one walking cycle (step S121). For example, the frailty estimation device 13 acquires feature data equivalent to one walking cycle measured for the subject during the evaluation period. For example, the evaluation period is set to a period that makes it easy to statistically aggregate the variability of the estimated grip strength, such as one week or one month.

[0097] Next, the frailty estimation device 13 estimates the subject's grip strength using the acquired feature data (step S122). For example, the frailty estimation device 13 estimates the subject's grip strength using estimation models specific to each gender.

[0098] Next, the frailty estimation device 13 stores the estimated grip strength in the memory unit 132 (step S123).

[0099] If it is time to aggregate the grip strength estimates (Yes in step S124), the probability distribution of grip strength is estimated using multiple grip strength estimates during the evaluation period (step S125). The estimated grip strength probability distribution is used to estimate frailty in step S114 in Figure 16. On the other hand, if it is not time to aggregate the grip strength estimates (No in step S124), the process returns to step S121. The timing for aggregating the grip strength estimates can be set arbitrarily. For example, the aggregation timing is when all grip strength estimations for the evaluation period have been completed. For example, the aggregation timing is when the grip strength estimations for a predetermined walking cycle have been completed.

[0100] <Walking speed estimation process> Next, the grip strength estimation process by the frailty estimation device 13 (step S113 in Figure 16) will be explained with reference to the diagram. Figure 18 is a flowchart for explaining the walking speed estimation process. In the explanation following the flowchart in Figure 18, the frailty estimation device 13 will be described as the main operating device.

[0101] In Figure 18, the frailty estimation device 13 first acquires gait waveform data for two consecutive gait cycles (step S131). For example, the frailty estimation device 13 acquires gait waveform data for two consecutive gait cycles measured for the subject during the evaluation period. For example, the evaluation period is set to a period that makes it easy to statistically aggregate the variability of the estimated gait speed, such as one week or one month.

[0102] Next, the frailty estimation device 13 detects the midpoint of the stance phase from the gait waveform data for two gait cycles that it has acquired (step S132). The frailty estimation device 13 detects one midpoint of the stance phase from each of the gait waveform data for two gait cycles.

[0103] Next, the frailty estimation device 13 calculates the distance the foot moves in the horizontal plane using the gait waveform data between the midpoints of the stance legs (step S133). For example, the frailty estimation device 13 calculates the trajectory between the midpoints of the stance legs using the spatial acceleration and spatial angular velocity included in the gait waveform data between the midpoints of the stance legs. The frailty estimation device 13 calculates the distance between the start and end points of the calculated trajectory as the distance the foot moves in the horizontal plane.

[0104] Next, the frailty estimation device 13 estimates the walking speed by dividing the distance traveled by the time between the midpoints of the stance phase (step S134).

[0105] Next, the frailty estimation device 13 stores the estimated walking speed in the storage unit 132 (step S135).

[0106] If it is time to aggregate the estimated walking speeds (Yes in step S136), the probability distribution of walking speed is estimated using multiple estimated walking speeds during the evaluation period (step S137). The estimated probability distribution of grip strength is used to estimate frailty in step S114 of Figure 16. On the other hand, if it is not time to aggregate the estimated walking speeds (No in step S136), the process returns to step S131. The timing for aggregating the estimated walking speeds can be set arbitrarily. For example, the aggregation timing is when all walking speed estimations for the evaluation period have been completed. For example, the aggregation timing is when the walking speed estimations for a predetermined number of walking cycles have been completed.

[0107] (Examples of application) Next, an example of application of this embodiment will be described with reference to the drawings. In the following example, an example of estimating frailty is shown using feature data / gait waveform data measured by a gait measurement device 10 placed in a shoe. The following frailty estimation is performed by the frailty estimation unit 135.

[0108] Figures 19-20 are conceptual diagrams showing an example of displaying the estimation results from the frailty estimation device 13 on the screen of a portable terminal 160 carried by a subject walking while wearing shoes 100 equipped with a gait measurement device 10. The functions of the frailty estimation device 13 are installed on the portable terminal 160 carried by the subject (user). Figures 19-20 are examples of displaying information about frailty estimated using feature data / gait waveform data corresponding to sensor data measured during the subject's (user's) walking on the screen of the portable terminal 160.

[0109] Figure 19 shows an example of information related to frailty estimation, where information corresponding to the estimated grip strength is displayed on the screen of the mobile terminal 160. In the example of Figure 19, only grip strength was checked out of the two items (grip strength and walking speed), so the information regarding the frailty estimation, "You are in the pre-frail category," is displayed on the display of the mobile terminal 160. In the example of Figure 19, depending on the estimated grip strength, the information regarding the grip strength estimation result, "Your grip strength has decreased," is displayed on the display of the mobile terminal 160.

[0110] Furthermore, in the example shown in Figure 19, recommendation information corresponding to the frailty estimation result is displayed on the mobile device 160, such as, "We recommend training A, which strengthens the whole body's muscles. Please watch the video below." After checking the information displayed on the mobile device 160, the subject can refer to the video of training A and perform the exercises, thereby engaging in training that leads to an increase in overall whole-body muscle strength.

[0111] Figure 20 shows an example of how information regarding frailty estimation is displayed on the screen of the mobile terminal 160. In the example in Figure 20, both grip strength and walking speed were checked, so it is determined that there is a possibility of frailty. In the example in Figure 20, information regarding the frailty estimation result, such as "There is a possibility of frailty," is displayed on the display of the mobile terminal 160.

[0112] Furthermore, in the example shown in Figure 20, recommendation information corresponding to the frailty estimation result is displayed on the display of the mobile terminal 160, stating, "Please check the applicable items in the following categories." In the example in Figure 20, checkboxes are displayed for three of the five J-CHS criteria items (weight loss, fatigue, and activity level), excluding grip strength and walking speed. In addition, a checkbox is displayed for cases where none of the three items apply. After reviewing the information displayed on the mobile terminal 160, the subject selects the appropriate checkbox according to the recommendation information. For example, if at least one of the three checkboxes is checked, three of the five J-CHS criteria items are selected, and the subject is judged to be frail. On the other hand, if none of the three checkboxes are checked, two of the five J-CHS criteria items are selected, and the subject is judged to be pre-frail.

[0113] As described above, the estimation system of this embodiment comprises a gait measurement device and a frailty estimation device. The gait measurement device is installed on the footwear of the subject whose frailty is to be estimated. The gait measurement device has a sensor that measures sensor data related to foot movement, and a feature data generation unit that generates walking waveform data and feature data using the time-series data of the sensor measured by the sensor. The sensor measures spatial acceleration and spatial angular velocity, and generates sensor data related to foot movement using the measured spatial acceleration and spatial angular velocity. The sensor outputs the generated sensor data to the feature data generation unit. The feature data generation unit acquires time-series data of the sensor data. The feature data generation unit extracts walking waveforms for one step period from the time-series data of the sensor data. The feature data generation unit normalizes the extracted walking waveforms to generate walking waveform data. The feature data generation unit extracts features used for grip strength estimation from the walking waveform data. The feature data generation unit generates feature data including the extracted features. The feature data generation unit transmits the generated feature data and gait waveform data to the frailty estimation device.

[0114] The frailty estimation device comprises a receiving unit, an estimation unit, and an output unit. The receiving unit acquires gait waveform data including the characteristics of the subject's gait, and feature data including features extracted from the gait waveform data. The estimation unit estimates the subject's grip strength using the feature data. The estimation unit estimates the subject's walking speed using the gait waveform data. The estimation unit estimates the subject's frailty using the estimated grip strength and walking speed. The output unit outputs information regarding the estimated frailty.

[0115] In this embodiment, walking speed is estimated using walking waveform data that includes the characteristics of the subject's gait measured by a gait measurement device. Furthermore, in this embodiment, the subject's grip strength is estimated using feature quantities extracted from the subject's walking waveform data. Finally, in this embodiment, the subject's frailty is estimated using the estimated grip strength and walking speed. In other words, according to this embodiment, frailty can be estimated based on the subject's gait.

[0116] In one embodiment of this system, the receiving unit acquires gait waveform data generated using time-series data of sensor data relating to foot movement, and feature data including features for estimating grip strength extracted from the gait waveform data. According to this embodiment, by using sensor data relating to foot movement, frailty can be appropriately estimated in daily life without using devices to measure grip strength or walking speed.

[0117] In one embodiment of this system, the estimation unit includes a grip strength estimation unit, a walking speed estimation unit, and a frailty estimation unit. The grip strength estimation unit estimates the subject's grip strength using features for estimating grip strength included in feature data extracted from walking waveform data. The grip strength estimation unit estimates the probability distribution of grip strength during the evaluation period using the estimated grip strength of the subject estimated at multiple points in time included in the evaluation period. The walking speed estimation unit calculates the distance the foot moves in one walking cycle using walking waveform data. The walking speed estimation unit estimates the subject's walking speed by dividing the calculated distance the foot moves by the time corresponding to one walking cycle. The walking speed estimation unit estimates the probability distribution of walking speed during the evaluation period using the estimated walking speed of the subject estimated at multiple points in time included in the evaluation period. The frailty estimation unit estimates the subject's frailty using the probability distributions of grip strength and walking speed during the evaluation period. According to this embodiment, by using the probability distribution of grip strength and walking speed during the evaluation period, the subject's frailty can be accurately estimated even if there is variability in the data.

[0118] In one embodiment of this system, the frailty estimation unit calculates a first probability distribution when the estimated value of the subject's grip strength is greater than a first threshold, which is a criterion for determining frailty related to grip strength. The frailty estimation unit calculates a second probability distribution when the estimated value of the subject's walking speed is greater than a second threshold, which is a criterion for determining frailty related to walking speed. The frailty estimation unit calculates the frailty probability by subtracting the product of the first and second probability distributions from 1. The frailty estimation unit estimates the subject to be healthy if the frailty probability is less than or equal to a third threshold for determining pre-frailty. The frailty estimation unit estimates the subject to be pre-frail if the frailty probability is greater than the third threshold but less than or equal to a fourth threshold for determining frailty. The frailty estimation unit estimates the subject to be frail if the frailty probability is greater than the fourth threshold. According to this embodiment, the frailty of the subject can be estimated based on the frailty probability.

[0119] In one embodiment of this system, the frailty estimation unit estimates the likelihood of a subject being frail based on a first threshold, which is a frailty determination criterion related to grip strength, and a second threshold, which is a frailty determination criterion related to walking speed. The frailty estimation unit estimates that a subject may be frail if the estimated value of the subject's grip strength is greater than the first threshold and the estimated value of the subject's walking speed is greater than the second threshold. The frailty estimation unit estimates that a subject is pre-frail if the estimated value of the subject's grip strength is greater than the first threshold and the estimated value of the subject's walking speed is less than or equal to the second threshold. The frailty estimation unit estimates that a subject is pre-frail if the estimated value of the subject's grip strength is less than or equal to the first threshold and the estimated value of the subject's walking speed is greater than the second threshold. The frailty estimation unit estimates that a subject is healthy if the estimated value of the subject's grip strength is less than or equal to the first threshold and the estimated value of the subject's walking speed is less than or equal to the second threshold. According to this embodiment, the subject's frailty can be estimated based on thresholds set for grip strength and walking speed, respectively.

[0120] In one embodiment of this system, if the estimated grip strength of the subject is greater than a first threshold and the estimated walking speed of the subject is greater than a second threshold, the frailty estimation unit acquires the subject's status regarding three items: weight loss, fatigue, and activity level. The frailty estimation unit estimates the subject to be frail if at least one of the three items—weight loss, fatigue, and activity level—meets the criteria for frailty. The frailty estimation unit estimates the subject to be pre-frail if none of the three items—weight loss, fatigue, and activity level—meet the criteria for frailty. In this embodiment, in addition to grip strength and walking speed, the system also verifies whether the three items—weight loss, fatigue, and activity level—meet the criteria for frailty. Therefore, according to this embodiment, the subject's frailty can be estimated more accurately.

[0121] In one embodiment of this system, the frailty estimation device displays information about frailty estimated according to the subject's leg movements on the screen of the terminal device. For example, the frailty estimation device displays information on the terminal device screen corresponding to grip strength estimated according to the user's leg movements. For example, the frailty estimation device displays information on the terminal device screen corresponding to walking speed estimated according to the user's leg movements. For example, the frailty estimation device displays recommendation information on the terminal device screen corresponding to the level of frailty estimated according to the user's leg movements. For example, the frailty estimation device displays training videos for strengthening whole-body muscle strength related to grip strength as recommendation information corresponding to the level of frailty estimated according to the user's leg movements on the screen of the terminal device. According to this embodiment, by displaying information about frailty estimated according to the characteristics of the subject's gait on a screen visible to the subject, the subject can check information about their own frailty.

[0122] (Second embodiment) Next, a frailty estimation device according to the second embodiment will be described with reference to the drawings. The frailty estimation device of this embodiment has a simplified configuration compared to the frailty estimation device included in the estimation system of the first embodiment.

[0123] Figure 21 is a block diagram showing an example of the configuration of the frailty estimation device 23 according to this embodiment. The frailty estimation device 23 comprises a receiving unit 231, an estimation unit 233, and an output unit 237.

[0124] The receiving unit 231 acquires gait waveform data including the subject's gait characteristics and feature data including features extracted from the gait waveform data. The estimation unit 233 estimates the subject's grip strength using the feature data. The estimation unit 233 estimates the subject's walking speed using the gait waveform data. The estimation unit 233 estimates the subject's frailty using the estimated grip strength and walking speed. The output unit 237 outputs information regarding the estimated frailty.

[0125] In this embodiment, walking speed is estimated using gait waveform data that includes the characteristics of the subject's gait. Furthermore, in this embodiment, the subject's grip strength is estimated using features extracted from the subject's gait waveform data. Then, in this embodiment, the subject's frailty is estimated using the estimated grip strength and walking speed. In other words, according to this embodiment, frailty can be estimated based on the subject's gait.

[0126] (Hardware) Here, the hardware configuration for executing the processing according to each embodiment of this disclosure will be described using the information processing device 90 in Figure 22 as an example. Note that the information processing device 90 in Figure 22 is an example configuration for executing the processing of each embodiment and does not limit the scope of this disclosure.

[0127] As shown in Figure 22, the information processing device 90 comprises a processor 91, main memory 92, auxiliary storage 93, input / output interface 95, and communication interface 96. In Figure 22, interface is abbreviated as I / F (Interface). The processor 91, main memory 92, auxiliary storage 93, input / output interface 95, and communication interface 96 are connected to each other via a bus 98, enabling data communication. Furthermore, the processor 91, main memory 92, auxiliary storage 93, and input / output interface 95 are connected to a network such as the Internet or an intranet via the communication interface 96.

[0128] The processor 91 loads the program stored in the auxiliary storage device 93, etc., into the main memory 92. The processor 91 executes the program loaded into the main memory 92. In this embodiment, a configuration using software programs installed in the information processing device 90 is sufficient. The processor 91 executes the processing according to each embodiment.

[0129] The main memory 92 has an area where the program is loaded. The processor 91 loads the program stored in the auxiliary memory 93, etc., into the main memory 92. The main memory 92 is implemented by volatile memory such as DRAM (Dynamic Random Access Memory). Alternatively, non-volatile memory such as MRAM (Magnetoresistive Random Access Memory) may be configured / added as the main memory 92.

[0130] The auxiliary storage device 93 stores various data, such as programs. The auxiliary storage device 93 is implemented by a local disk such as a hard disk or flash memory. It is also possible to omit the auxiliary storage device 93 by configuring the system to store various data in the main memory device 92.

[0131] 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 common as interfaces for connecting to external devices.

[0132] The information processing device 90 may be connected to input devices such as a keyboard, mouse, or touch panel, as needed. These input devices are used to input information and settings. When a touch panel is used as an input device, the display screen of the display device may also serve as the interface for the input device. Data communication between the processor 91 and the input device can be mediated by the input / output interface 95.

[0133] Furthermore, the information processing device 90 may be equipped with a display device for displaying information. If a display device is provided, it is preferable that the information processing device 90 is equipped with a display control device (not shown) for controlling the display of the display device. The display device can be connected to the information processing device 90 via an input / output interface 95.

[0134] Furthermore, the information processing device 90 may be equipped with a drive device. The drive device mediates between the processor 91 and the recording medium (program recording medium), such as reading data and programs from the recording medium and writing the processing results of the information processing device 90 to the recording medium. The drive device can be connected to the information processing device 90 via an input / output interface 95.

[0135] The above is an example of a hardware configuration for enabling the processing according to each embodiment of the present invention. Note that the hardware configuration in Figure 22 is an example of a hardware configuration for executing the processing according to each embodiment and does not limit the scope of the present invention. Furthermore, a program that causes a computer to execute the processing according to each embodiment is also included in the scope of the present invention. Moreover, a program recording medium that records the program according to each embodiment is also included in the scope of the present invention. The recording medium can be, for example, an optical recording medium such as a CD (Compact Disc) or DVD (Digital Versatile Disc). The recording medium may also be a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. Furthermore, the recording medium may also be a magnetic recording medium such as a flexible disk, or other recording media. When a program executed by a processor is recorded on a recording medium, that recording medium corresponds to a program recording medium.

[0136] The components of each embodiment may be combined in any way. Furthermore, the components of each embodiment may be implemented by software or by circuitry.

[0137] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the above embodiments. Various modifications to the configuration and details of the present invention can be made that will be understood by those skilled in the art within the scope of the present invention. [Explanation of Symbols]

[0138] 1 Estimation System 10 Gait Measurement Device 11 sensors 12 Feature Data Generation Unit 13. Frailty estimation device 111 Accelerometer 112 Angular velocity sensor 121 Acquisition Department 122 Normalization section 123 Extraction part 125 Generation part 127 Transmitter 130, 233 Estimation part 131, 231 Receiving section 132 Storage section 133 Grip strength estimation unit 134 Walking speed estimation unit 135 Frailty Estimation Unit 137, 237 Output section

Claims

1. A receiving means for acquiring gait waveform data including gait characteristics generated using time-series data of sensor data relating to the movement of a subject's feet, and feature data including features for estimating grip strength extracted from the gait waveform data, An estimation means for estimating the subject's grip strength using the feature data, estimating the subject's walking speed using the walking waveform data, and estimating the subject's frailty using the estimated grip strength and walking speed, The system includes an output means for outputting information regarding the estimated frailty of the subject, The estimation means is, A grip strength estimation means that estimates the grip strength of the subject using features for estimating grip strength included in the feature data extracted from the walking waveform data, and estimates the probability distribution of grip strength during the evaluation period using the estimated grip strength of the subject estimated at multiple points in time included in the evaluation period. A walking speed estimation means that calculates the distance the foot moves in one step cycle using the walking waveform data, estimates the subject's walking speed by dividing the calculated distance the foot moves by the time corresponding to one step cycle, and estimates the probability distribution of the walking speed during the evaluation period using the estimated values ​​of the subject's walking speed estimated at multiple points in time included in the evaluation period. A frailty estimation device comprising: a frailty estimation means for estimating the frailty of a subject using the probability distributions of grip strength and walking speed during the evaluation period.

2. The aforementioned flail estimation means is The first probability distribution is calculated for cases where the estimated grip strength of the subject is greater than the first threshold, which is the criterion for determining frailty related to grip strength. The second probability distribution is calculated when the estimated value of the subject's walking speed is greater than the second threshold, which is the criterion for determining frailty related to walking speed. The probability of frailty is calculated by subtracting the product of the first probability distribution and the second probability distribution from 1. If the frailty probability is below the third threshold for determining pre-frailty, the subject is presumed to be healthy. If the frailty probability exceeds the third threshold but is less than or equal to the fourth threshold for determining frailty, the subject is estimated to be pre-frail. The frailty estimation device according to claim 1, wherein if the probability of frailty exceeds the fourth threshold, the subject is estimated to be frail.

3. The aforementioned flail estimation means is If the estimated grip strength of the subject is lower than the first threshold, which is the criterion for determining frailty related to grip strength, and the estimated walking speed of the subject is lower than the second threshold, which is the criterion for determining frailty related to walking speed, then it is estimated that the subject may be frail. If the estimated grip strength of the subject is greater than or equal to the first threshold, and the estimated walking speed of the subject is less than the second threshold, the subject is estimated to be pre-frail. If the estimated grip strength of the subject is less than the first threshold, and the estimated walking speed of the subject is greater than or equal to the second threshold, the subject is estimated to be pre-frail. The frailty estimation device according to claim 1, wherein if the estimated grip strength of the subject is equal to or greater than the first threshold, and the estimated walking speed of the subject is equal to or greater than the second threshold, the subject is estimated to be healthy.

4. The aforementioned flail estimation means is If the estimated grip strength of the subject is less than the first threshold and the estimated walking speed of the subject is less than the second threshold, the subject's status regarding the three items of weight loss, fatigue, and activity level is obtained. If at least one of the following three items—weight loss, fatigue, and activity level—meets the criteria for frailty, the subject is presumed to be frail. The frailty estimation device according to claim 3, wherein if none of the three items of weight loss, fatigue, and activity level meet the criteria for frailty, the subject is estimated to be pre-frail.

5. A frailty estimation device according to any one of claims 1 to 4, A gait measurement device comprising: a sensor installed on the footwear of a subject whose frailty is to be estimated and which measures sensor data related to foot movement; and a feature data generation means that generates gait waveform data and feature data using the time-series data of the sensor measured by the sensor, The aforementioned sensor is The spatial acceleration and spatial angular velocity are measured, and the sensor data relating to the movement of the foot is generated using the measured spatial acceleration and spatial angular velocity. The generated sensor data is output to the feature data generation means. The aforementioned feature data generation means is The time-series data of the aforementioned sensor is acquired, From the time-series data of the aforementioned sensor data, a walking waveform corresponding to one step cycle is extracted. The extracted walking waveform is normalized to generate the walking waveform data. From the aforementioned walking waveform data, feature quantities used to estimate grip strength are extracted. The feature data containing the extracted features is generated, An estimation system that transmits the generated feature data and gait waveform data to the frailty estimation device.

6. The aforementioned frailty estimation device is The estimation system according to claim 5, which displays information regarding frailty estimated in accordance with the foot movements of the subject on the screen of a terminal device.

7. Computers We obtain gait waveform data, which includes gait characteristics generated using time-series sensor data related to the movement of the subject's feet, and feature data, which includes features for estimating grip strength extracted from the gait waveform data. Using the aforementioned feature data, the grip strength of the subject is estimated. Using the aforementioned walking waveform data, the walking speed of the subject is estimated. Using the estimated grip strength and walking speed, the subject's frailty is estimated. Output information regarding the estimated frailty of the subject, In estimating the frailty of the subject, The grip strength of the subject is estimated using the features for estimating grip strength included in the feature data extracted from the walking waveform data. Using the estimated grip strength of the subject estimated at multiple points in time included in the evaluation period, the probability distribution of grip strength during the evaluation period is estimated. Using the aforementioned walking waveform data, the distance the foot travels during one step is calculated. The calculated distance traveled by the foot is divided by the time corresponding to the one-step cycle to estimate the subject's walking speed. Using the estimated walking speeds of the subject estimated at multiple points in time within the evaluation period, the probability distribution of walking speed during the evaluation period is estimated. A method for estimating the frailty of a subject using the probability distributions of grip strength and walking speed during the evaluation period.

8. A process for obtaining gait waveform data, which includes gait characteristics generated using time-series sensor data related to the movement of a subject's feet, and feature data, which includes features for estimating grip strength extracted from the gait waveform data. A process for estimating the grip strength of the subject using the aforementioned feature data, A process for estimating the walking speed of the subject using the aforementioned walking waveform data, A process for estimating the frailty of the subject using estimated grip strength and walking speed, A process that outputs information regarding the estimated frailty of the subject, In the process of estimating the frailty of the subject, A process for estimating the grip strength of the subject using features for estimating grip strength included in the feature data extracted from the gait waveform data, A process for estimating the probability distribution of grip strength during the evaluation period using estimated grip strength values ​​of the subject estimated at multiple points in time included in the evaluation period, A process to calculate the distance the foot moves in one step cycle using the aforementioned walking waveform data, A process to estimate the subject's walking speed by dividing the calculated distance traveled by the foot by the time corresponding to the one-step cycle, A process to estimate the probability distribution of walking speed during the evaluation period using estimated values ​​of the subject's walking speed estimated at multiple points in time included in the evaluation period, A program that causes a computer to perform a process to estimate the frailty of a subject using the probability distributions of grip strength and walking speed during the evaluation period.

Images