Sarcopenia assessment device and storage medium

By detecting the angle and displacement parameters of the knee joint and toe in the walking data, combined with the prediction model, the problem of insufficient accuracy in evaluating muscle attenuation in the prior art is solved, and a high-precision and simple evaluation method is achieved.

CN112438722BActive Publication Date: 2024-11-08PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA
View PDF 16 Cites 0 Cited by

Patent Information

Application Number
CN202010834841.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-02-14
Filing Date
2020-08-19
Publication Date
2024-11-08
Estimated Expiration
2040-08-19

AI Technical Summary

Technical Problem

The prior art is difficult to evaluate muscular attenuation in the elderly with simple and high accuracy, especially the problems of insufficient accuracy and high complexity through the evaluation of walking parameters.

Method used

By obtaining the walking data of the test subjects, the angle of the knee joint during the foot and the suspended foot, the displacement of the toes during the foot and the suspended foot, and the angle of the ankle joint were detected. These parameters were used to determine whether it was muscular attenuation. Predictive models are evaluated.

Benefits of technology

High-precision evaluation of musculosac disease is achieved, the evaluation process is simplified, and large devices are not required, and the preparation population for musculosac disease and musculosac disease is quickly and accurately judged.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112438722B_ABST
    Figure CN112438722B_ABST
Patent Text Reader

Abstract

Provided are a method for assessing muscle wasting, an assessment device, and a storage medium. The method for assessing muscle wasting provided by the present invention is a method for assessing muscle wasting of a muscle wasting assessment device based on the walking movements of a test subject, and acquires walking data related to the walking of the test subject; based on the walking data, detects at least one of the angle of the knee joint of one leg of the test subject during the stance period of one leg, the angle of the knee joint of one leg during the foot suspension period of one leg, the displacement of the toe of one leg in the vertical direction during the stance period, the displacement of the toe of one leg in the vertical direction during the foot suspension period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot suspension period; and uses at least one walking parameter to determine whether the test subject has muscle wasting. According to this configuration, muscle wasting can be assessed simply and with high accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a technology for evaluating sarcopenia based on the walking movements of a test subject. Background Art

[0002] In recent years, in order to understand the health status of the elderly, technology that can easily estimate physical functions has been developed. In particular, the elderly have a decrease in muscle mass and an increase in fat mass as they age. The state that generally indicates a decrease in skeletal muscle mass as they age is called sarcopenia. It is said that sarcopenia is closely related to falls, fractures, bedriddenness, and weakness. Therefore, it is necessary to detect elderly people with sarcopenia as early as possible and take countermeasures.

[0003] Conventionally, there has been proposed a technique for evaluating cognitive function or motor function based on parameters measured from daily walking.

[0004] For example, Japanese Patent Application Laid-Open No. 2013-255786 discloses a method for evaluating the incidence of geriatric disorders (risk of geriatric disorders) based on walking parameters measured in walking behavior.

[0005] Moreover, for example, an evaluation method is also disclosed in Japanese Patent Publication No. 2018-114319, which measures the front-to-back acceleration, left-to-right acceleration, and up-and-down acceleration of the test subject during movement by installing an acceleration sensor on the waist of the test subject, and evaluates the mobility based on the changes in the front-to-back acceleration, left-to-right acceleration, and up-and-down acceleration over time.

[0006] However, the above-mentioned conventional technologies have difficulty in simply and accurately evaluating sarcopenia, and further improvement is needed. Summary of the invention

[0007] The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide a technology that can evaluate sarcopenia simply and with high accuracy.

[0008] One aspect of the present invention relates to a method for evaluating muscle wasting, which is a method for evaluating muscle wasting using a device for evaluating muscle wasting based on the walking movements of a test subject, and comprises the following steps: acquiring walking data related to the walking of the test subject; detecting, based on the walking data, an angle of a knee joint of one leg of the test subject during a stance period of the leg, an angle of the knee joint of the leg during a foot-hanging period of the leg, a displacement of the toe of the leg in a vertical direction during the stance period, and a displacement of the toe of the leg in a vertical direction during a foot-hanging period. The method comprises the following steps: determining whether the test subject suffers from muscle wasting by using at least one of the displacement in the vertical direction of the toe portion during the stance period, the angle of the ankle joint of the one leg during the stance period, and the angle of the ankle joint of the one leg during the foot suspension period; and determining whether the test subject suffers from muscle wasting by using at least one of the angle of the knee joint during the stance period, the angle of the knee joint during the foot suspension period, the displacement of the toe portion in the vertical direction during the stance period, the displacement of the toe portion in the vertical direction during the foot suspension period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot suspension period. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a block diagram showing the structure of a sarcopenia assessment system according to an embodiment of the present invention.

[0010] Figure 2 This is a schematic diagram for explaining the process of extracting skeleton data from two-dimensional image data in the present embodiment.

[0011] Figure 3 It is a schematic diagram for explaining the walking cycle of this embodiment.

[0012] Figure 4 This is a flowchart for explaining the sarcopenia evaluation process using the walking motion of the test subject in the present embodiment.

[0013] Figure 5 It is used to illustrate Figure 4 Flow chart of the sarcopenia determination process of step S4.

[0014] Figure 6 It is used to illustrate Figure 4 This is a flowchart of another example of the sarcopenia determination process of step S4.

[0015] Figure 7 Schematic diagram showing changes in the angle of the knee joint of one leg during one gait cycle in the present embodiment.

[0016] Figure 8This is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of this embodiment.

[0017] Fig. 9 Schematic diagram showing ROC curves obtained from the results of judging healthy subjects and a pre-sarcopenia population using the prediction model of the present embodiment.

[0018] Fig.10 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the first modification example of the present embodiment.

[0019] Fig.11 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model according to the first modification example of the present embodiment.

[0020] Fig.12 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the second modification example of the present embodiment.

[0021] Fig.13 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model according to the second modification of the present embodiment.

[0022] Fig.14 This is a schematic diagram showing a second variant of the present embodiment, which is an average of average values ​​of time series data of the knee joint angle of one leg of test subjects with sarcopenia, an average of average values ​​of time series data of the knee joint angle of one leg of test subjects who are a sarcopenia preparation group, and an average of average values ​​of time series data of the knee joint angle of one leg of test subjects who are healthy people.

[0023] Fig.15 1 is a schematic diagram showing the displacement of the toe portion of one leg in the vertical direction during one gait cycle in the third modified example of the present embodiment.

[0024] Fig.16 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the third modification example of the present embodiment.

[0025] Fig.17 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the third modification example of the present embodiment.

[0026] Fig.18Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the fourth modification example of the present embodiment.

[0027] Fig.19 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the fourth modification example of the present embodiment.

[0028] Fig. 20 1 is a schematic diagram showing the displacement of the toe portion of one leg in the vertical direction during one gait cycle in the fifth modification example of the present embodiment.

[0029] Fig.21 Schematic diagram showing an ROC curve obtained from the result of determining whether a person has sarcopenia or is a sarcopenia-preparatory group using the prediction model of the fifth modification example of the present embodiment.

[0030] Fig. 22 It is a schematic diagram showing, in the fifth variant of the present embodiment, the average of the mean values ​​of time series data of the displacement of the toe of one leg in the vertical direction of the test subjects who are sarcopenia or sarcopenia preparation population, and the average of the mean values ​​of time series data of the displacement of the toe of one leg in the vertical direction of the test subjects who are healthy people.

[0031] Fig.23 This is a schematic diagram showing changes in the angle of the ankle joint of one leg during one gait cycle in the sixth variation of the present embodiment.

[0032] Fig.24 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the sixth modification example of the present embodiment.

[0033] Fig.25 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the sixth modification example of the present embodiment.

[0034] Fig.26 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the seventh modification example of the present embodiment.

[0035] Fig. 27 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the seventh modification example of the present embodiment.

[0036] Fig.28Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the eighth modification example of the present embodiment.

[0037] Fig.29 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the ninth variation of the present embodiment.

[0038] Fig.30 It is a schematic diagram showing the average stride distances of one leg of the test subjects who are sarcopenia and the average stride distances of one leg of the test subjects who are healthy people in the ninth modification example of the present embodiment.

[0039] Fig.31 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the tenth modification example of the present embodiment.

[0040] Fig.32 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model according to the eleventh modification of the present embodiment.

[0041] Fig.33 FIG. 1 is a schematic diagram showing a twelfth variation of the present embodiment, showing changes in the angle of a knee joint of one leg during one gait cycle.

[0042] Fig.34 Schematic diagram showing an ROC curve obtained from the result of determining whether a person has sarcopenia or is a sarcopenia-preparatory group using the prediction model of the twelfth variation of the present embodiment.

[0043] Fig.35 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the thirteenth variation of the present embodiment.

[0044] Fig.36 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the fourteenth variation of the present embodiment.

[0045] Fig.37 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the fifteenth variation of the present embodiment.

[0046] Fig.38Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the sixteenth variation of the present embodiment.

[0047] Fig.39 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the seventeenth variation of the present embodiment.

[0048] Fig.40 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the eighteenth modification example of the present embodiment.

[0049] Fig.41 It is a schematic diagram showing an example of the evaluation result screen displayed in this embodiment. DETAILED DESCRIPTION

[0050] (Basic knowledge of the present invention)

[0051] The measurement of walking parameters disclosed in Japanese Patent Publication No. 2013-255786 utilizes a sheet type pressure sensor or a three-dimensional motion analysis system. The sheet type pressure sensor measures the pressure distribution during walking and measures the walking parameters based on the pressure distribution. The three-dimensional motion analysis system obtains image information of tags installed on the feet from multiple cameras and measures walking parameters by analyzing the movements based on the image information. However, setting up such a sheet type pressure sensor or a three-dimensional motion analysis system is time-consuming and troublesome. Therefore, the technology disclosed in Japanese Patent Publication No. 2013-255786 is difficult to simply assess the risk of geriatric disorders.

[0052] Moreover, as walking parameters disclosed in Japanese Patent Publication No. 2013-255786, two or more are selected from step frequency, stride, walking ratio, stride length, step interval, walking angle, toe angle, left-right difference of stride, left-right difference of step interval, left-right difference of walking angle, and left-right difference of double-foot support period. The walking angle is the angle formed by a straight line connecting the left and right heels of one foot and the other heel and the direction of travel. The toe angle is the angle formed by a straight line connecting the heel and the toe and the direction of travel. Moreover, the technology of Japanese Patent Publication No. 2013-255786 evaluates the risk of elderly disorders selected from at least knee pain, low back pain, urinary incontinence, dementia, and sarcopenia. However, Japanese Patent Publication No. 2013-255786 does not disclose the content of evaluating the risk of elderly disorders using walking parameters other than the above, and the accuracy of evaluating the risk of elderly disorders can be further improved by using other walking parameters.

[0053] The mobility evaluation device disclosed in Japanese Patent Publication No. 2018-114319 evaluates at least one of the front-to-back balance, weight shift, and left-to-right balance of the test subject during movement based on the front-to-back acceleration, left-to-right acceleration, and up-and-down acceleration of the test subject during movement. However, Japanese Patent Publication No. 2018-114319 does not disclose the use of parameters other than the above to evaluate sarcopenia. By using other walking parameters, the accuracy of sarcopenia evaluation can be further improved.

[0054] In order to solve the above problems, one aspect of the present invention is a method for evaluating muscle wasting based on the walking movements of a test subject, and is a method for evaluating muscle wasting using a device for evaluating muscle wasting, comprising the following steps: acquiring walking data related to the walking of the test subject; detecting, based on the walking data, an angle of a knee joint of one leg of the test subject during a stance period of the leg, an angle of the knee joint of the leg during a foot suspension period of the leg, a displacement of the toe of the leg in a vertical direction during the stance period, and a displacement of the toe of the leg in a vertical direction during a foot suspension period; At least one of the displacement in the vertical direction, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot hanging period; using at least one of the angle of the knee joint during the stance period, the angle of the knee joint during the foot hanging period, the displacement of the toe in the vertical direction during the stance period, the displacement of the toe in the vertical direction during the foot hanging period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot hanging period, to determine whether the test subject suffers from muscle wasting disease.

[0055] According to this configuration, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of one leg, the angle of the knee joint of one leg during the foot-hanging phase of one leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase is used as a parameter related to the subject's muscle wasting. There is a different tendency between the walking movements of the subject with muscle wasting and the walking movements of the subject without muscle wasting. In this way, by using the parameters related to the muscle wasting of the walking test subject to determine whether the subject has muscle wasting, the subject's muscle wasting can be evaluated with high accuracy.

[0056] Furthermore, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of the leg, the angle of the knee joint of one leg during the foot-hanging phase of the leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase can be easily detected based on image data obtained by photographing the walking test subject, without requiring a large device. Therefore, according to this configuration, the muscle wasting disease of the test subject can be easily evaluated.

[0057] Moreover, in the muscle wasting disease assessment method, it may be that, in the detection, the time series data of the angle of the knee joint during the specified period of the foot hanging period is detected, and in the judgment, the average value of the time series data of the angle of the knee joint is used to judge whether the test subject suffers from the muscle wasting disease.

[0058] The angle of the knee joint of one leg of the test subject who is walking during the prescribed period of the foot of one leg hanging in the air is significantly different between the test subject with sarcopenia and the test subject without sarcopenia. Therefore, according to this configuration, by using the average value of the time series data of the angle of the knee joint of one leg of the test subject who is walking during the prescribed period of the foot of one leg hanging in the air, the sarcopenia of the test subject can be reliably evaluated.

[0059] Moreover, in the sarcopenia assessment method, the period from when one foot of the test subject touches the ground to when the foot touches the ground again may be represented as a walking cycle, and when the one walking cycle is represented by 1% to 100%, the specified period may be a period from 61% to 100% of the one walking cycle.

[0060] According to this configuration, the period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one gait cycle, and one gait cycle is represented by 1% to 100%. In this case, by using the average value of the time series data of the angle of the knee joint of one leg during the period from 61% to 100% of one gait cycle, the sarcopenia of the test subject can be reliably evaluated.

[0061] Moreover, in the muscle wasting disease assessment method, it may be that, in the detection, the time series data of the angle of the knee joint during the specified period of the stance phase is detected, and in the judgment, the average value of the time series data of the angle of the knee joint is used to judge whether the test subject suffers from the muscle wasting disease.

[0062] The angle of the knee joint of one leg of the walking test subject during the predetermined period of the stance phase of one leg is significantly different between the test subject with sarcopenia and the test subject without sarcopenia. Therefore, according to this configuration, by using the average value of the time series data of the angle of the knee joint of one leg of the walking test subject during the predetermined period of the stance phase of one leg, the sarcopenia of the test subject can be reliably evaluated.

[0063] Moreover, in the sarcopenia assessment method, the period from when one foot of the test subject touches the ground to when the foot touches the ground again may be represented as a walking cycle, and when the one walking cycle is represented by 1% to 100%, the specified period may be a period from 50% to 60% of the one walking cycle.

[0064] According to this configuration, the period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one gait cycle, and one gait cycle is represented by 1% to 100%. In this case, by using the average value of the time series data of the angle of the knee joint of one leg during 50% to 60% of one gait cycle, the sarcopenia of the test subject can be reliably evaluated.

[0065] Moreover, in the muscle wasting disease assessment method, it may be that, in the detection, the time series data of the displacement of the toe portion in the vertical direction during the specified period of the stance period is detected, and in the judgment, the average value of the time series data of the displacement of the toe portion in the vertical direction is used to judge whether the test subject suffers from the muscle wasting disease.

[0066] The displacement of the toe portion of one leg of the walking test subject in the vertical direction during the predetermined period of the stance period of one leg is significantly different between the test subject with sarcopenia and the test subject without sarcopenia. Therefore, according to this configuration, the sarcopenia of the test subject can be reliably evaluated by using the average value of the time series data of the displacement of the toe portion of one leg of the walking test subject in the vertical direction during the predetermined period of the stance period of one leg.

[0067] Moreover, in the sarcopenia assessment method, the period from the time one foot of the test subject touches the ground to the time the foot touches the ground again may be represented as a walking cycle, and when the one walking cycle is represented by 1% to 100%, the specified period may be a period from 1% to 60% of the one walking cycle.

[0068] According to this configuration, the period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one gait cycle, and one gait cycle is represented by 1% to 100%. In this case, by using the average value of the time series data of the vertical displacement of the toe portion of one leg during 50% to 60% of one gait cycle, the sarcopenia of the test subject can be reliably evaluated.

[0069] Moreover, in the muscle wasting disease assessment method, it may be that, in the detection, the time series data of the displacement of the toe portion in the vertical direction during the specified period of the foot hanging in the air is detected, and in the judgment, the average value of the time series data of the displacement of the toe portion in the vertical direction is used to judge whether the test subject suffers from the muscle wasting disease.

[0070] The displacement of the toe portion of one leg of the walking test subject in the vertical direction during the prescribed period of the foot of one leg in the air significantly differs between the test subject with sarcopenia and the test subject without sarcopenia. Therefore, according to this configuration, by using the average value of the time series data of the displacement of the toe portion of one leg of the walking test subject in the vertical direction during the prescribed period of the foot of one leg in the air, the sarcopenia of the test subject can be reliably evaluated.

[0071] Moreover, in the sarcopenia assessment method, the period from the time one foot of the test subject touches the ground to the time the foot touches the ground again may be represented as a walking cycle, and when the walking cycle is represented by 1% to 100%, the specified period may be a period from 65% to 70% of the walking cycle.

[0072] According to this configuration, the period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one gait cycle, and one gait cycle is represented by 1% to 100%. In this case, by using the average value of the time series data of the vertical displacement of the toe portion of one leg during 65% to 70% of one gait cycle, the sarcopenia of the test subject can be reliably evaluated.

[0073] Moreover, in the muscle wasting assessment method, it may be that, in the detection, time series data of a first angle of the ankle joint in a first period of the stance period and time series data of a second angle of the ankle joint in a second period of the foot hanging period are detected, and in the judgment, an average value of the time series data of the first angle of the ankle joint and an average value of the time series data of the second angle of the ankle joint are used to judge whether the test subject suffers from the muscle wasting.

[0074] According to this configuration, by combining the average value of time series data of a first angle of an ankle joint of one leg during a first period of a stance period of one leg and the average value of time series data of a second angle of an ankle joint of one leg during a second period of a foot suspension period of one leg, muscle wasting disease can be evaluated with higher accuracy than using the above average values ​​alone.

[0075] Moreover, in the muscle wasting assessment method, it may also be that, in the detection, the time series data of the displacement of the toe portion in the vertical direction during the first period of the stance period, the time series data of the angle of the knee joint during the second period of the stance period, the time series data of the angle of the knee joint during the third period of the foot hanging period, and the time series data of the angle of the knee joint during the fourth period of the foot hanging period are detected; in the judgment, the average value of the time series data of the displacement of the toe portion in the vertical direction during the first period and the average value of the time series data of the angle of the knee joint during the second period, the third period and the fourth period are used to judge whether the test subject suffers from the muscle wasting.

[0076] According to this configuration, by combining and utilizing the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the second period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the third period of the foot of one leg in the air, and the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the foot of one leg in the air, muscle wasting disease can be evaluated with higher accuracy than by utilizing the above average values ​​alone.

[0077] Moreover, in the muscle wasting assessment method, it may also be that, in the detection, the time series data of the displacement of the toe portion in the vertical direction during the first period of the stance period, the time series data of the angle of the ankle joint during the second period of the stance period, the time series data of the angle of the ankle joint during the third period of the stance period, the time series data of the angle of the ankle joint during the fourth period of the foot hanging period, and the time series data of the angle of the ankle joint during the fifth period of the foot hanging period are detected; in the judgment, the average value of the time series data of the displacement of the toe portion in the vertical direction during the first period and the average value of the time series data of the angle of the ankle joint during the second period, the third period, the fourth period and the fifth period are used to judge whether the test subject suffers from the muscle wasting.

[0078] According to this configuration, by combining and utilizing the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the second period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the third period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the foot of one leg in the air, and the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot of one leg in the air, muscle wasting disease can be evaluated with higher accuracy than by utilizing the above average values ​​alone.

[0079] Moreover, in the muscle wasting assessment method, it may also be that, in the detection, the time series data of the angle of the knee joint in the first period of the stance period, the time series data of the angle of the knee joint in the second period of the foot hanging period, the time series data of the angle of the knee joint in the third period of the foot hanging period, the time series data of the angle of the ankle joint in the fourth period of the stance period, the time series data of the angle of the ankle joint in the fifth period of the foot hanging period, and the time series data of the angle of the ankle joint in the sixth period of the foot hanging period are detected; in the judgment, the average value of the time series data of the angle of the knee joint in the first period, the second period and the third period and the average value of the time series data of the angle of the ankle joint in the fourth period, the fifth period and the sixth period are used to judge whether the test subject has the muscle wasting.

[0080] According to this configuration, by combining and utilizing the average value of the time series data of the angle of the knee joint of one leg during the first period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the second period of the foot of one leg in the air, the average value of the time series data of the angle of the knee joint of one leg during the third period of the foot of one leg in the air, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot of one leg in the air, and the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the foot of one leg in the air, muscle wasting disease can be evaluated with higher accuracy than by utilizing the above average values ​​alone.

[0081] Moreover, in the muscle wasting assessment method, it may also be that, in the detection, the time series data of the displacement of the toe portion in the vertical direction during the first period of the stance period, the time series data of the displacement of the toe portion in the vertical direction during the second period of the stance period, the time series data of the displacement of the toe portion in the vertical direction during the third period of the foot hanging period, the time series data of the angle of the knee joint during the fourth period of the stance period, the time series data of the angle of the knee joint during the fifth period of the stance period and the foot hanging period, the time series data of the angle of the ankle joint during the sixth period of the stance period, and the time series data of the angle of the ankle joint during the stance period and the foot hanging period are detected; in the judgment, the average value of the time series data of the displacement of the toe portion in the vertical direction during the first period, the second period and the third period, the average value of the time series data of the angle of the knee joint during the fourth period and the fifth period, and the average value of the time series data of the angle of the ankle joint during the sixth period and the seventh period are used to judge whether the test subject has the muscle wasting.

[0082] According to this configuration, by combining and utilizing the average value of time series data of displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of time series data of displacement of the toe of one leg in the vertical direction during the second period of the stance period of one leg, the average value of time series data of displacement of the toe of one leg in the vertical direction during the third period of the foot hanging period of one leg, the average value of time series data of the angle of the knee joint of one leg during the fourth period of the stance period of one leg, the average value of time series data of the angle of the knee joint of one leg during the fifth period of the stance period of one leg and the foot hanging period, the average value of time series data of the angle of the ankle joint of one leg during the sixth period of the stance period of one leg, and the average value of time series data of the angle of the ankle joint of one leg during the seventh period of the stance period of one leg and the foot hanging period, muscle wasting disease can be evaluated with higher accuracy than by utilizing the above average values ​​alone.

[0083] Moreover, in the muscle wasting assessment method, it can also be further determined whether the test subject is a muscle wasting preparation group who may develop muscle wasting in the future by further using at least one of the angle of the knee joint during the stance period, the angle of the knee joint during the foot hanging period, the displacement of the toe in the vertical direction during the stance period, the displacement of the toe in the vertical direction during the foot hanging period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot hanging period.

[0084] According to this configuration, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of one leg, the angle of the knee joint of one leg during the foot-hanging phase of one leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase is used as a parameter related to the sarcopenia of the test subject. There is a different tendency between the walking movements of the test subject who is a sarcopenia candidate population who may become sarcopenia in the future and the walking movements of the test subject who is not a sarcopenia candidate population. In this way, by using the parameters related to the sarcopenia of the walking test subject to determine whether the test subject is a sarcopenia candidate population, the sarcopenia of the test subject can be evaluated with high accuracy.

[0085] Moreover, in the muscle wasting assessment method, it may be that, in the judgment, when the angle of the knee joint during the stance period is greater than a threshold value, when the angle of the knee joint during the foot hanging period is greater than a threshold value, when the displacement of the toe portion in the vertical direction during the stance period is greater than a threshold value, when the displacement of the toe portion in the vertical direction during the foot hanging period is greater than a threshold value, when the angle of the ankle joint during the stance period is greater than a threshold value, or when the angle of the ankle joint during the foot hanging period is greater than a threshold value, the test subject is judged to have the muscle wasting.

[0086] According to this configuration, the test subject can be judged to have muscle wasting disease when the angle of the knee joint of one leg during the stance period of one leg is greater than a threshold value, when the angle of the knee joint of one leg during the foot suspension period of one leg is greater than a threshold value, when the displacement of the toe of one leg in the vertical direction during the stance period of one leg is greater than a threshold value, when the displacement of the toe of one leg in the vertical direction during the foot suspension period of one leg is greater than a threshold value, when the angle of the ankle joint of one leg during the stance period of one leg is greater than a threshold value, or when the angle of the ankle joint of one leg during the foot suspension period of one leg is greater than a threshold value.

[0087] Therefore, by comparing the angle of the knee joint of one leg during the stance period of one leg, the angle of the knee joint of one leg during the foot suspension period of one leg, the displacement of the toe of one leg in the vertical direction during the stance period of one leg, the displacement of the toe of one leg in the vertical direction during the foot suspension period of one leg, the angle of the ankle joint of one leg during the stance period of one leg, or the angle of the ankle joint of one leg during the foot suspension period of one leg with a threshold value, it is possible to simply determine whether the test subject suffers from muscle wasting.

[0088] Moreover, in the muscle wasting assessment method, it may also be that, in the judgment, by inputting at least one of the detected angle of the knee joint in the stance period, the angle of the knee joint in the foot-in-the-air period, the displacement of the toe in the vertical direction in the stance period, the displacement of the toe in the vertical direction in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period into a prediction model, it is judged whether the test subject has the muscle wasting, wherein the prediction model is a prediction model that uses at least one of the angle of the knee joint in the stance period, the angle of the knee joint in the foot-in-the-air period, the displacement of the toe in the vertical direction in the stance period, the displacement of the toe in the vertical direction in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period as input values, and uses whether the test subject has the muscle wasting as an output value.

[0089] According to this configuration, the prediction model is a prediction model that uses as input values ​​at least one of the angle of the knee joint of one leg during the stance period of one leg, the angle of the knee joint of one leg during the foot suspension period of one leg, the displacement of the toe of one leg in the vertical direction during the stance period of one leg, the displacement of the toe of one leg in the vertical direction during the foot suspension period of one leg, the angle of the ankle joint of one leg during the stance period of one leg, and the angle of the ankle joint of one leg during the foot suspension period of one leg, and uses as an output value whether the test subject has muscle wasting disease. Furthermore, by inputting at least one of the detected angle of the knee joint of one leg in the stance phase of one leg, the angle of the knee joint of one leg in the foot-hanging phase of one leg, the displacement of the toe portion of one leg in the vertical direction in the stance phase of one leg, the displacement of the toe portion of one leg in the vertical direction in the foot-hanging phase of one leg, the angle of the ankle joint of one leg in the stance phase of one leg, and the angle of the ankle joint of one leg in the foot-hanging phase of one leg into the prediction model, it is determined whether the test subject has sarcopenia. Therefore, by pre-storing the prediction model, it is possible to easily determine whether the test subject has sarcopenia.

[0090] Another aspect of the present invention relates to a muscle wasting disease assessment device, which is a muscle wasting disease assessment device for assessing muscle wasting disease based on the walking movements of a test subject, comprising: an acquisition unit, which acquires walking data related to the walking of the test subject; a detection unit, which detects, based on the walking data, the angle of the knee joint of one leg of the test subject during the stance period of the leg, the angle of the knee joint of the leg when the foot of the leg is suspended in the air, the displacement of the toe of the leg in the vertical direction during the stance period, the displacement of the toe of the leg in the vertical direction when the foot is suspended in the air, The judgment unit judges whether the test subject suffers from muscle wasting disease by using at least one of the angle of the ankle joint of the one leg during the stance period and the angle of the ankle joint of the one leg during the foot suspension period; and the judgment unit judges whether the test subject suffers from muscle wasting disease by using at least one of the angle of the knee joint during the stance period, the angle of the knee joint during the foot suspension period, the displacement of the toe portion in the vertical direction during the stance period, the displacement of the toe portion in the vertical direction during the foot suspension period, the angle of the ankle joint during the stance period and the angle of the ankle joint during the foot suspension period.

[0091] According to this configuration, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of one leg, the angle of the knee joint of one leg during the foot-hanging phase of one leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase is used as a parameter related to the subject's muscle wasting. There is a different tendency between the walking movements of the subject with muscle wasting and the walking movements of the subject without muscle wasting. In this way, by using the parameters related to the muscle wasting of the walking test subject to determine whether the subject has muscle wasting, the subject's muscle wasting can be evaluated with high accuracy.

[0092] Furthermore, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of the leg, the angle of the knee joint of one leg during the foot-hanging phase of the leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase can be easily detected based on image data obtained by photographing the walking test subject, without requiring a large device. Therefore, according to this configuration, the muscle wasting disease of the test subject can be easily evaluated.

[0093] Another aspect of the present invention relates to a storage medium, which is a non-temporary computer-readable storage medium storing a sarcopenia assessment program, wherein the sarcopenia assessment program assesses sarcopenia based on the walking movements of the test subject, and the sarcopenia assessment program enables the computer to have the following functions: obtaining walking data related to the walking of the test subject; based on the walking data, detecting the angle of the knee joint of one leg of the test subject during the stance period of the leg, the angle of the knee joint of the leg when the foot of the leg is suspended, the displacement of the toe of the leg in the vertical direction during the stance period, and the displacement of the toe of the leg in the vertical direction during the stance period. at least one of the displacement of the toe portion in the vertical direction during the period when the foot is suspended in the air, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the period when the foot is suspended in the air; and judging whether the test subject suffers from muscle wasting disease by using at least one of the angle of the knee joint during the stance period, the angle of the knee joint during the foot is suspended in the air, the displacement of the toe portion in the vertical direction during the stance period, the displacement of the toe portion in the vertical direction during the foot is suspended in the air, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot is suspended in the air.

[0094] According to this configuration, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of one leg, the angle of the knee joint of one leg during the foot-hanging phase of one leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase is used as a parameter related to the subject's muscle wasting. There is a different tendency between the walking movements of the subject with muscle wasting and the walking movements of the subject without muscle wasting. In this way, by using the parameters related to the muscle wasting of the walking test subject to determine whether the subject has muscle wasting, the subject's muscle wasting can be evaluated with high accuracy.

[0095] Furthermore, at least one of the angle of the knee joint of one leg of the walking test subject during the stance phase of the leg, the angle of the knee joint of one leg during the foot-hanging phase of the leg, the displacement of the toe portion of one leg in the vertical direction during the stance phase, the displacement of the toe portion of one leg in the vertical direction during the foot-hanging phase, the angle of the ankle joint of one leg during the stance phase, and the angle of the ankle joint of one leg during the foot-hanging phase can be easily detected based on image data obtained by photographing the walking test subject, without requiring a large device. Therefore, according to this configuration, the muscle wasting disease of the test subject can be easily evaluated.

[0096] The embodiments of the present invention are described below with reference to the accompanying drawings. In addition, the embodiments described below are all examples of the present invention, and are not intended to limit the technical protection scope of the present invention.

[0097] (Implementation Method)

[0098] The following is based on Figure 1 The sarcopenia assessment system according to this embodiment will be described.

[0099] Figure 1 This is a block diagram showing the structure of a sarcopenia assessment system according to an embodiment of the present invention.

[0100] Figure 1 The illustrated sarcopenia assessment system includes a sarcopenia assessment device 1 , a camera 2 , and a display unit 3 .

[0101] The camera 2 captures the walking test subject. The camera 2 outputs dynamic image data showing the walking test subject to the sarcopenia-evaluating device 1. The camera 2 is connected to the sarcopenia-evaluating device 1 by wire or wirelessly.

[0102] The sarcopenia-assessing device 1 includes a processor 11 and a memory 12 .

[0103] The processor 11 is, for example, a CPU (central processing unit), and includes a data acquisition unit 111 , a walking parameter detection unit 112 , a sarcopenia determination unit 113 , and an evaluation result presentation unit 114 .

[0104] The memory 12 is a storage device that can store various information, such as RAM (Random Access Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory.

[0105] The data acquisition unit 111 acquires walking data related to the walking of the test subject. The walking data is, for example, dynamic image data obtained by photographing the walking test subject. The data acquisition unit 111 acquires dynamic image data output by the camera 2.

[0106] The walking parameter detection unit 112 extracts skeletal data representing the skeleton of the test subject from the dynamic image data acquired by the data acquisition unit 111. The skeletal data is represented by the coordinates of a plurality of feature points representing the joints of the test subject and the straight lines connecting the feature points. The walking parameter detection unit 112 may also use software (such as OpenPose or 3D pose-baseline) that detects the coordinates of the feature points of a person from two-dimensional image data.

[0107] Here, the process of extracting skeleton data from two-dimensional image data will be described.

[0108] Figure 2 This is a schematic diagram for explaining the process of extracting skeleton data from two-dimensional image data in the present embodiment.

[0109] The walking parameter detection unit 112 extracts skeleton data 21 from the two-dimensional image data 20 including the image of the walking test subject 200. The skeleton data 21 includes a feature point 201 indicating the head, a feature point 202 indicating the center of both shoulders, a feature point 203 indicating the right shoulder, a feature point 204 indicating the right elbow, a feature point 205 indicating the right hand, a feature point 206 indicating the left shoulder, a feature point 207 indicating the left elbow, a feature point 208 indicating the left hand, a feature point 209 indicating the waist, a feature point 210 indicating the right hip joint, a feature point 211 indicating the right knee joint, a feature point 212 indicating the right ankle joint, a feature point 213 indicating the right toe, a feature point 214 indicating the left hip joint, a feature point 215 indicating the left knee joint, a feature point 216 indicating the left ankle joint, and a feature point 217 indicating the left toe.

[0110] The dynamic image data is composed of a plurality of two-dimensional image data. The walking parameter detection unit 112 extracts time-series bone data from each of the plurality of two-dimensional image data constituting the dynamic image data. In addition, the walking parameter detection unit 112 may extract bone data from the two-dimensional image data of all frames or from the two-dimensional image data of each predetermined frame. Moreover, in the present embodiment, sarcopenia is evaluated mainly based on the movement of the lower limbs of the test subject during walking. For this purpose, the walking parameter detection unit 112 may also extract only the bone data of the lower limbs of the test subject.

[0111] Then, the walking parameter detection unit 112 extracts the skeleton data corresponding to one walking cycle of the test subject from the time series skeleton data. The skeleton data is extracted from the dynamic image data. The walking motion of a person is a periodic motion.

[0112] Here, the walking cycle of the test subject is described.

[0113] Figure 3 It is a schematic diagram for explaining the walking cycle of this embodiment.

[0114] like Figure 3 As shown, the period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one walking cycle. Figure 3The one walking cycle shown is the period from when the right foot of the test subject touches the ground to when the right foot touches the ground again. Moreover, one walking cycle is standardized to 1% to 100%. The period from 1% to 60% of one walking cycle is called the stance period when one foot (for example, the right foot) is touching the ground, and the period from 61% to 100% of one walking cycle is called the foot suspension period when one foot (for example, the right foot) is leaving the ground. One walking cycle includes the stance period and the foot suspension period. In addition, one walking cycle can also be the period from when the left foot of the test subject touches the ground to when the left foot touches the ground again.

[0115] The walking parameter detection unit 112 detects at least one of the angle of the knee joint of one leg of the test subject during the stance period, the angle of the knee joint of one leg during the foot-in-the-air period, the displacement of the toe of one leg in the vertical direction during the stance period, the displacement of the toe of one leg in the vertical direction during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period based on the walking data.

[0116] In this embodiment, the walking parameter detection unit 112 detects the angle of the knee joint of one leg of the test subject during the foot-in-the-air period based on the walking data. The walking parameter detection unit 112 detects the angle of the knee joint of one leg of the test subject during the foot-in-the-air period from the time series of skeletal data corresponding to one captured walking cycle. Figure 2 As shown, the angle γ of the knee joint in the sagittal plane is the angle formed between the straight line connecting the feature point 211 representing the right knee joint and the feature point 210 representing the right hip joint and the straight line connecting the feature point 211 representing the right knee joint and the feature point 212 representing the right ankle joint.

[0117] In particular, the walking parameter detection unit 112 detects the time series data of the angle of the knee joint of one leg during the predetermined period of the foot-in-the-air period. Specifically, the predetermined period is a period from 61% to 100% of one walking cycle. The walking parameter detection unit 112 calculates the average value of the time series data of the angle of the knee joint of one leg during the predetermined period of the foot-in-the-air period as the walking parameter.

[0118] In addition, the detection of the angle of the knee joint of one leg of the test subject during the stance period, the displacement of the toe of one leg in the vertical direction during the stance period, the displacement of the toe of one leg in the vertical direction when the foot is suspended in the air, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg when the foot is suspended in the air is described in a variant example of the present embodiment.

[0119] The muscle wasting disease judging unit 113 judges whether the test subject has muscle wasting disease by using at least one of the angle of the knee joint of one leg during the stance period, the angle of the knee joint of one leg during the foot hanging period, the displacement of the toe of one leg in the vertical direction during the stance period, the displacement of the toe of one leg in the vertical direction during the foot hanging period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot hanging period.

[0120] In the present embodiment, the sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the angle of the knee joint of one leg during the foot-in-the-air period.

[0121] Moreover, the muscle wasting disease judging unit 113 judges whether the test subject has muscle wasting disease by inputting at least one of the detected angle of the knee joint of one leg during the stance period, the angle of the knee joint of one leg during the foot-in-the-air period, the displacement of the toe part of one leg in the vertical direction during the stance period, the displacement of the toe part of one leg in the vertical direction during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period into the prediction model, wherein the prediction model uses at least one of the angle of the knee joint of one leg during the stance period, the angle of the knee joint of one leg during the foot-in-the-air period, the displacement of the toe part of one leg in the vertical direction during the stance period, the displacement of the toe part of one leg in the vertical direction during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period as an output value, and generates whether the test subject has muscle wasting disease as the output value.

[0122] In this embodiment, the sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the angle of the knee joint of one leg during the foot-suspended period detected by the walking parameter detection unit 112 into a prediction model, wherein the prediction model uses the angle of the knee joint of one leg during the foot-suspended period as an input value and generates whether the test subject has sarcopenia as an output value.

[0123] In addition, the judgment of muscle wasting disease of the test subject using the angle of the knee joint of one leg during the stance period, the displacement of the toe of one leg in the vertical direction during the stance period, the displacement of the toe of one leg in the vertical direction during the foot hanging period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot hanging period is described in a modified example of the present embodiment.

[0124] Furthermore, in the present embodiment, the sarcopenia determination unit 113 not only determines whether the test subject has sarcopenia. The sarcopenia determination unit 113 also determines whether the test subject is a sarcopenia candidate population who may develop sarcopenia in the future, using at least one of the angle of the knee joint of one leg in the stance phase, the angle of the knee joint of one leg in the foot-in-the-air phase, the displacement of the toe portion of one leg in the vertical direction in the stance phase, the displacement of the toe portion of one leg in the vertical direction in the foot-in-the-air phase, the angle of the ankle joint of one leg in the stance phase, and the angle of the ankle joint of one leg in the foot-in-the-air phase. That is, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, sarcopenia candidate population, or healthy person.

[0125] Sarcopenia indicates a state in which the subject's muscle mass decreases and the muscle strength or physical fitness decreases. Furthermore, the sarcopenia preparatory population indicates a state in which the subject's muscle mass decreases although the muscle strength and physical fitness do not decrease. The muscle mass is obtained, for example, by measuring the skeletal muscle mass of the subject's limbs. When the skeletal muscle mass of the limbs is lower than a threshold value, it can be determined that the muscle mass is decreasing. Furthermore, the muscle strength is obtained, for example, by measuring the subject's grip strength. When the grip strength is lower than a threshold value, it can be determined that the muscle strength is decreasing. Furthermore, the physical fitness is obtained, for example, by measuring the subject's walking speed. When the walking speed is lower than a threshold value, it can be determined that the physical fitness is decreasing.

[0126] The memory 12 pre-stores a prediction model generated by taking the angle of the knee joint of one leg during the foot-in-the-air period as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the time series data of the angle of the knee joint of one leg during a specified period of the foot-in-the-air period of a walking cycle as an explanatory variable. The prediction model outputs one of a value indicating that the test subject is sarcopenia (e.g., 2), a value indicating that the test subject is a sarcopenia candidate group (e.g., 1), and a value indicating that the test subject is not sarcopenia and is a sarcopenia candidate group, that is, a healthy person (e.g., 0).

[0127] In particular, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person using the average value of the time series data of the angle of the knee joint of one leg during the foot-in-the-air period. Specifically, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person using the average value of the time series data of the angle of the knee joint of one leg during the period from 61% to 100% of one walking cycle.

[0128] In addition, the prediction model can also be generated by machine learning. As machine learning, for example, there is teacher learning that uses teacher data that gives labels (output information) to input information to learn the relationship between input and output, untaught learning that has no labels and constructs data only according to the input, semi-taught learning that can have labels or no labels, and reinforcement learning that maximizes the action of reward through trial and error learning. Moreover, as specific methods of machine learning, there are neural networks (including deep learning using multi-layer neural networks), genetic algorithms, decision trees, Bayesian networks, or support vector machines (SVM), etc. In the machine learning of the present invention, any of the specific examples listed above can be used.

[0129] Moreover, the prediction model may also output a value indicating that the test subject may have sarcopenia. The value indicating that the test subject may have sarcopenia is represented by, for example, 0.0 to 2.0. In this case, for example, the sarcopenia determination unit 113 may also determine that the test subject is a healthy person when the value indicating that the test subject may have sarcopenia is below 0.5, determine that the test subject is a sarcopenia candidate when the value indicating that the test subject may have sarcopenia is greater than 0.5 and less than 1.5, and determine that the test subject has sarcopenia when the value indicating that the test subject may have sarcopenia is greater than 1.5.

[0130] Moreover, the memory 12 may also store a first prediction model for determining whether the test subject has sarcopenia and a second prediction model for determining whether the test subject is a sarcopenia candidate population. In this case, the sarcopenia determination unit 113 inputs at least one of the angle of the knee joint of one leg during the stance period, the angle of the knee joint of one leg during the foot-in-the-air period, the displacement of the toe portion of one leg in the vertical direction during the stance period, the displacement of the toe portion of one leg in the vertical direction during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period into the first prediction model to determine whether the test subject has sarcopenia. The sarcopenia judging unit 113, when judging that the test subject does not have sarcopenia, inputs at least one of the angle of the knee joint of one leg during the stance period, the angle of the knee joint of one leg during the foot-in-the-air period, the displacement of the toe portion of one leg in the vertical direction during the stance period, the displacement of the toe portion of one leg in the vertical direction during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period into the second prediction model to judge whether the test subject is a sarcopenia candidate population. When judging that the test subject is not a sarcopenia candidate population, the sarcopenia judging unit 113 judges that the test subject is a healthy person.

[0131] The evaluation result presenting unit 114 presents the evaluation result of sarcopenia determined by the sarcopenia determining unit 113. The evaluation result presenting unit 114 outputs the evaluation result determined by the sarcopenia determining unit 113 to the display unit 3. The evaluation result is at least one of information indicating whether the test subject determined by the sarcopenia determining unit 113 has sarcopenia and an evaluation message. The evaluation result presenting unit 114 may present the evaluation result indicating whether the test subject determined by the sarcopenia determining unit 113 has sarcopenia, a sarcopenia candidate group, or a healthy person.

[0132] The display unit 3 displays the evaluation result output from the evaluation result presenting unit 114. The display unit 3 is, for example, a liquid crystal display panel or a light emitting element.

[0133] In addition, the display unit 3 may display the transition of the value indicating that the test subject may have sarcopenia in a graph in order to compare the value indicating that the test subject determined this time may have sarcopenia with the value indicating that the test subject in the past may have sarcopenia. In addition, the value indicating that the test subject in the past may have sarcopenia is stored in the memory 12 and can be read from the memory 12.

[0134] In addition, the sarcopenia assessment device 1 may include a camera 2 and a display unit 3. Furthermore, the sarcopenia assessment device 1 may include a display unit 3. The sarcopenia assessment device 1 may be a personal computer or a server.

[0135] Secondly, use Figure 4 The sarcopenia assessment process according to the present embodiment will be described.

[0136] Figure 4 This is a flowchart for explaining the sarcopenia evaluation process using the walking motion of the test subject in the present embodiment. Figure 4 The flowchart shown represents the steps of evaluating sarcopenia using the sarcopenia evaluating device 1 .

[0137] The test subject walks in front of the camera 2. The camera 2 captures the test subject walking. The camera 2 transmits dynamic image data of the test subject walking to the sarcopenia-evaluating device 1.

[0138] First, in step S1 , the data acquisition unit 111 acquires the moving image data transmitted from the camera 2 .

[0139] Next, in step S2 , the walking parameter detection unit 112 extracts time-series skeleton data from the moving image data.

[0140] Next, in step S3, the walking parameter detection unit 112 detects walking parameters for determining sarcopenia from the time series skeletal data. Here, the walking parameter of this embodiment is the average value of the time series data of the angle of the knee joint of one leg during the foot-in-the-air period during a predetermined period of the foot-in-the-air period of one leg in one walking cycle. The predetermined period is, for example, a period from 61% to 100% of one walking cycle. In addition, the method for determining the walking parameter will be described later.

[0141] Next, in step S4, the sarcopenia determination unit 113 executes a sarcopenia determination process for determining whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person using the walking parameters. The sarcopenia determination process will be described later.

[0142] Next, in step S5, the evaluation result presentation unit 114 outputs the evaluation result of sarcopenia determined by the sarcopenia determination unit 113 to the display unit 3. The evaluation result of sarcopenia indicates whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person. The evaluation result presentation unit 114 may not only output to the display unit 3 whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person, but may also output to the display unit 3 an evaluation message corresponding to sarcopenia, a sarcopenia candidate group, or a healthy person. The display unit 3 displays the evaluation result of sarcopenia output from the evaluation result presentation unit 114.

[0143] Here, Figure 4The sarcopenia determination process of step S4 will be described.

[0144] Figure 5 It is used to illustrate Figure 4 Flow chart of the sarcopenia determination process of step S4.

[0145] First, in step S11 , the sarcopenia assessment unit 113 reads the prediction model from the memory 12 .

[0146] Next, in step S12, the sarcopenia determination unit 113 inputs the walking parameter detected by the walking parameter detection unit 112 into the prediction model. The walking parameter of this embodiment is the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle. The sarcopenia determination unit 113 inputs the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle into the prediction model.

[0147] Next, in step S13, the sarcopenia determination unit 113 obtains the determination result of sarcopenia from the prediction model. The sarcopenia determination unit 113 obtains whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person from the prediction model as the determination result.

[0148] In addition, in the sarcopenia determination process of the present embodiment, the walking parameter is input into the pre-generated prediction model to determine whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person, but the present invention is not limited to this. In other examples of the sarcopenia determination process of the present embodiment, the walking parameter can also be compared with a pre-stored threshold value to determine whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person.

[0149] In this case, the memory 12 pre-stores a first threshold value for determining whether the test subject has sarcopenia and a second threshold value for determining whether the test subject is a sarcopenia candidate. The second threshold value is lower than the first threshold value.

[0150] Moreover, the sarcopenia judgment unit 113 may also judge that the test subject has sarcopenia when the angle of the knee joint of one leg during the stance period is greater than the first threshold, when the angle of the knee joint of one leg during the foot-in-the-air period is greater than the first threshold, when the displacement of the toe of one leg in the vertical direction during the stance period is greater than the first threshold, when the displacement of the toe of one leg in the vertical direction during the foot-in-the-air period is greater than the first threshold, when the angle of the ankle joint of one leg during the stance period is greater than the first threshold, or when the angle of the ankle joint of one leg during the foot-in-the-air period is greater than the first threshold.

[0151] In the present embodiment, the sarcopenia determination unit 113 may also determine that the test subject has sarcopenia when the angle of the knee joint of one leg during the foot-in-the-air period is greater than a first threshold. The sarcopenia determination unit 113 determines whether the average value of the time series data of the angle of the knee joint of one leg of the test subject during a period from 61% to 100% of a gait cycle is greater than the first threshold. The sarcopenia determination unit 113 determines that the test subject has sarcopenia when the average value of the time series data of the angle of the knee joint of one leg of the test subject during a period from 61% to 100% of a gait cycle is greater than the first threshold.

[0152] On the other hand, the sarcopenia determination unit 113 may also determine whether the angle of the knee joint of one leg in the stance phase is greater than the second threshold value when the angle of the knee joint of one leg in the stance phase is less than the first threshold value. Furthermore, the sarcopenia determination unit 113 may also determine whether the angle of the knee joint of one leg in the foot-in-the-air phase is greater than the second threshold value when the angle of the knee joint of one leg in the foot-in-the-air phase is less than the first threshold value. Furthermore, the sarcopenia determination unit 113 may also determine whether the displacement of the toe portion of one leg in the vertical direction in the stance phase is greater than the second threshold value when the displacement of the toe portion of one leg in the vertical direction in the foot-in-the-air phase is less than the first threshold value. Furthermore, the sarcopenia determination unit 113 may also determine whether the displacement of the toe portion of one leg in the vertical direction in the foot-in-the-air phase is greater than the second threshold value when the displacement of the toe portion of one leg in the vertical direction in the foot-in-the-air phase is less than the first threshold value. Furthermore, the sarcopenia determination unit 113 may also determine whether the angle of the ankle joint of one leg in the stance phase is greater than the second threshold value when the angle of the ankle joint of one leg in the stance phase is less than the first threshold value. Furthermore, the sarcopenia determination unit 113 may determine whether the angle of the ankle joint of one leg during the foot-in-the-air period is greater than a second threshold when the angle of the ankle joint of one leg during the foot-in-the-air period is less than a first threshold.

[0153] The sarcopenia judgment unit 113 may also judge that the test subject is a preparatory population for sarcopenia when the angle of the knee joint of one leg during the stance period is greater than the second threshold, the angle of the knee joint of one leg during the foot-in-the-air period is greater than the second threshold, the displacement of the toe of one leg in the vertical direction during the stance period is greater than the second threshold, the displacement of the toe of one leg in the vertical direction during the foot-in-the-air period is greater than the second threshold, the angle of the ankle joint of one leg during the stance period is greater than the second threshold, or the angle of the ankle joint of one leg during the foot-in-the-air period is greater than the second threshold.

[0154] In this embodiment, the sarcopenia determination unit 113 may also determine that the test subject is a sarcopenia candidate population when the angle of the knee joint of one leg during the foot-in-the-air period is greater than the second threshold. The sarcopenia determination unit 113 determines whether the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of a walking cycle is greater than the second threshold. The sarcopenia determination unit 113 determines that the test subject is a sarcopenia candidate population when the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of a walking cycle is greater than the second threshold. On the other hand, the sarcopenia determination unit 113 determines that the test subject is not a sarcopenia candidate population, that is, the test subject is a healthy person, when the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of a walking cycle is less than the second threshold.

[0155] Figure 6 It is used to illustrate Figure 4 This is a flowchart of another example of the sarcopenia determination process of step S4.

[0156] First, in step S21 , the sarcopenia determination unit 113 reads the first threshold value and the second threshold value from the memory 12 .

[0157] Next, in step S22, the sarcopenia determination unit 113 determines whether the walking parameter detected by the walking parameter detection unit 112 is greater than the first threshold value. The walking parameter of this embodiment is the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle. The sarcopenia determination unit 113 determines whether the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle is greater than the first threshold value.

[0158] Here, when it is determined that the walking parameter is greater than the first threshold value ("Yes" in step S22), the sarcopenia determination unit 113 determines that the test subject suffers from sarcopenia in step S23.

[0159] On the other hand, when it is determined that the walking parameter is less than the first threshold value (No in step S22), in step S24, the sarcopenia determination unit 113 determines whether the walking parameter detected by the walking parameter detection unit 112 is greater than the second threshold value. The walking parameter of this embodiment is the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle. The sarcopenia determination unit 113 determines whether the average value of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle is greater than the second threshold value.

[0160] Here, when it is determined that the walking parameter is greater than the second threshold value (“Yes” in step S24 ), in step S25 , the sarcopenia determination unit 113 determines that the test subject is a sarcopenia preparatory group.

[0161] On the other hand, when it is determined that the walking parameter is below the second threshold (No in step S24), in step S26, the sarcopenia determination unit 113 determines that the test subject is not a sarcopenia preparatory group, that is, the test subject is a healthy person.

[0162] As described above, in this embodiment, the angle of the knee joint of one leg of the walking subject during the foot-in-the-air period is a parameter related to the subject's sarcopenia. The walking motion of the subject with sarcopenia has different tendencies from the walking motion of the subject without sarcopenia. Therefore, since the subject's sarcopenia is determined using the parameter related to the subject's sarcopenia during walking, the subject's sarcopenia can be evaluated with high accuracy.

[0163] Furthermore, since the angle of the knee joint of one leg of the walking test subject during the foot-in-the-air period can be easily detected from, for example, image data obtained by photographing the walking test subject, no large-scale device is required. Therefore, according to this structure, the muscle weakness of the test subject can be easily evaluated.

[0164] The walking parameters and prediction model of this embodiment can be determined by experiments. Hereinafter, the method of determining the walking parameters and prediction model of this embodiment will be described.

[0165] The total number of subjects who participated in the experiment was 65. All subjects were female. There are various criteria for judging sarcopenia. The criteria for judging sarcopenia adopted this time is that the skeletal muscle mass of the limbs is less than 5.8 (kg / m 2 ) and the grip strength is less than 19.3 (kg) or the limb skeletal muscle mass is less than 5.8 (kg / m 2 ) and the walking speed is less than 1.19 (m / s). The skeletal muscle mass of the limbs is the total muscle mass of the arms and legs divided by the square of the height. 2 ) and the grip strength is less than 19.3 (kg) or the skeletal muscle mass of the limbs is less than 5.8 (kg / m 2 ) and the walking speed is less than 1.19 (m / s), the test subject is judged to have sarcopenia. In addition, the reference value used in the above judgment is for women. In the case of male test subjects, when the skeletal muscle mass of the limbs is less than 7.0 (kg / m 2) and the grip strength is less than 30.3 (kg) or the skeletal muscle mass of the limbs is less than 7.0 (kg / m 2 ) and the walking speed is less than 1.27 (m / s), the test subject is judged to have sarcopenia.

[0166] Furthermore, if only the skeletal muscle mass of the limbs is lower than the reference value, the test subjects are judged to be sarcopenia-preparatory population. 2 ) in the case of sarcopenia, the test subjects were judged to be a preparatory population for sarcopenia.

[0167] The above-mentioned criteria for determining sarcopenia are merely examples and are not limited to the above-mentioned numerical values.

[0168] As a result of the judgment, among the test subjects, 9 were test subjects with sarcopenia, 30 were test subjects in the sarcopenia preparatory group, and 26 were test subjects who were healthy. During the experiment, the test subjects walked in front of the camera. The walking test subjects were filmed with a camera, and the bone data of each test subject was extracted from the dynamic image data. In addition, the time series data of the angle of the knee joint of one leg of each test subject was detected from the extracted bone data.

[0169] Figure 7 Schematic diagram showing the change in the angle of the knee joint of one leg during one walking cycle in this embodiment. Figure 7 In the figure, the vertical axis represents the angle of the knee joint, and the horizontal axis represents a normalized walking cycle. Figure 7 In the figure, the dotted line represents the average waveform of the angle of the knee joint of one leg of the healthy test subjects, the dashed line represents the average waveform of the angle of the knee joint of one leg of the test subjects of the sarcopenia preparation group, and the solid line represents the average waveform of the angle of the knee joint of one leg of the test subjects with sarcopenia.

[0170] In the experiment, a standardized walking cycle was divided into ten intervals, and the average angle of the knee joint of one leg in one interval or two or more consecutive intervals was calculated for each test subject. In addition, a prediction model was created with the test subject being sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average angle of the knee joint of one leg during 61% to 100% of a walking cycle as the explanatory variable. The prediction model was evaluated by cross-validation. Leave-one-out cross-validation was used as cross-validation. In addition, the ROC (Receiver Operating Characteristic) curve of the prediction model for healthy people and sarcopenia and the ROC curve of the prediction model for healthy people and sarcopenia preparation group were calculated. In addition, the AUC (Area Under Curve) values ​​of the two ROC curves of the prediction model were calculated respectively.

[0171] Figure 8 This is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of this embodiment.

[0172] The prediction model of this embodiment is created by taking the test subject as sarcopenia, sarcopenia candidate group, or healthy person as the target variable, and the average value of the angle of the knee joint of one leg during 61% to 100% of a walking cycle as the explanatory variable. Figure 8 In the graph, the vertical axis represents the true positive rate (True Positive Rate) and the horizontal axis represents the false positive rate (False Positive Rate). The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0173] Figure 8 The ROC curve shown is a curve depicting the true positive rate and the false positive rate of a prediction model created with the average value of the angle of the knee joint of one leg during 61% to 100% of one walking cycle as an explanatory variable. Figure 8 The AUC value of the ROC curve shown is 0.699. The AUC value is the area of ​​the lower half of the ROC curve. It can be considered that the larger the AUC value (the closer to 1), the higher the performance of the prediction model.

[0174] Fig. 9 Schematic diagram showing the ROC curve obtained from the results of judging healthy subjects and sarcopenia candidate groups using the prediction model of this embodiment. Fig. 9In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0175] Fig. 9 The ROC curve shown is a curve depicting the true positive rate and the false positive rate of a prediction model created with the average value of the angle of the knee joint of one leg during 61% to 100% of one walking cycle as an explanatory variable. Fig. 9 The AUC value of the ROC curve shown is 0.604.

[0176] In this embodiment, the average value of the angle of the knee joint of one leg during the period from 61% to 100% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created by using the average value of the angle of the knee joint of one leg during the period from 61% to 100% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0177] The memory 12 stores in advance a prediction model, which takes as input the average value of the time series data of the angle of the knee joint of one leg during the period from 61% to 100% of a gait cycle, and generates as an output value whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person. The walking parameter detection unit 112 detects the time series data of the angle of the knee joint of one leg during the period from 61% to 100% of a gait cycle. The sarcopenia determination unit 113 inputs the average value of the time series data of the angle of the knee joint of one leg during the period from 61% to 100% of a gait cycle into the prediction model, and obtains from the prediction model a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person.

[0178] Moreover, in Figure 7In the period from 61% to 100% of one gait cycle shown in FIG. 1 , the average waveform of the angle of the knee joint of one leg of the test subjects who are sarcopenia is larger than the average waveform of the angle of the knee joint of one leg of the test subjects who are a sarcopenia preparation group. Therefore, a value between the average of the time series data of the angle of the knee joint of one leg of the test subjects who are sarcopenia during the period from 61% to 100% of one gait cycle obtained by the experiment and the average of the time series data of the angle of the knee joint of one leg of the test subjects who are a sarcopenia preparation group during the period from 61% to 100% of one gait cycle can be stored in the memory 12 as a first threshold. The sarcopenia determination unit 113 can also determine whether the test subject has sarcopenia by comparing the average of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one gait cycle with the pre-stored first threshold.

[0179] Moreover, in Figure 7 In the period from 61% to 100% of one walking cycle shown in the figure, the average waveform of the angle of the knee joint of one leg of the test subjects who are the sarcopenia preparation group is larger than the average waveform of the angle of the knee joint of one leg of the test subjects who are healthy people. Therefore, the value between the average of the time series data of the angle of the knee joint of one leg of the test subjects who are the sarcopenia preparation group obtained by the experiment and the average of the time series data of the angle of the knee joint of one leg of the test subjects who are healthy people during the period from 61% to 100% of one walking cycle can be stored in the memory 12 as the second threshold value. The sarcopenia determination unit 113 can also determine whether the test subject is a sarcopenia preparation group by comparing the average of the time series data of the angle of the knee joint of one leg of the test subject during the period from 61% to 100% of one walking cycle with the pre-stored second threshold value.

[0180] In this embodiment, the walking parameter is the average value of the time series data of the angle of the knee joint of one leg during 61% to 100% of one walking cycle, but the present invention is not limited thereto. Various examples of the walking parameter of this embodiment are described below.

[0181] First, walking parameters according to a first modified example of the present embodiment will be described.

[0182] The walking parameter of the first modified example of the present embodiment may be an average value of time series data of the angle of the knee joint of one leg during a predetermined period of the stance phase of one leg of the test subject.

[0183] In the first variant of the present embodiment, similar to the above-mentioned experiment, time series data of the angle of the knee joint of each of the multiple test subjects is detected from the skeletal data of multiple test subjects including test subjects with sarcopenia, test subjects in the sarcopenia preparation group, and test subjects of healthy people. In addition, a prediction model is created, which uses whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and uses the average value of the time series data of the angle of the knee joint of one leg during a specified period of the stance phase as the explanatory variable. The specified period is a period from 1% to 60% of a walking cycle. The prediction model is evaluated by cross validation. Leave-one-out cross validation is used as cross validation. In addition, the ROC curve of the prediction model is calculated. Furthermore, the AUC value of the ROC curve of the prediction model is calculated.

[0184] Fig.10 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the first modification example of the present embodiment.

[0185] The prediction model of the first variant of this embodiment is created by taking the test subject's type of sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average value of the angle of the knee joint of one leg during 1% to 60% of a walking cycle as the explanatory variable. Fig.10 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0186] Fig.10 The ROC curve shown is a curve depicting the true positive rate and the false positive rate of a prediction model created using the average value of the angle of the knee joint of one leg during 1% to 60% of one walking cycle as an explanatory variable. Fig.10 The AUC value of the ROC curve shown is 0.586.

[0187] Fig.11 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model according to the first modification example of the present embodiment.

[0188] exist Fig.11In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0189] Fig.11 The ROC curve shown is a curve depicting the true positive rate and the false positive rate of a prediction model created using the average value of the angle of the knee joint of one leg during 1% to 60% of one walking cycle as an explanatory variable. Fig.11 The AUC value of the ROC curve shown is 0.537.

[0190] In the first modified example of the present embodiment, the average value of the angle of the knee joint of one leg during the period from 1% to 60% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the angle of the knee joint of one leg during the period from 1% to 60% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0191] The walking parameter detection unit 112 detects the angle of the knee joint of one leg during a specified period of the stance phase of one leg of the test subject from the walking data. The walking parameter detection unit 112 detects the angle of the knee joint of one leg during a specified period of the stance phase from the time series skeletal data corresponding to a captured walking cycle. In particular, the walking parameter detection unit 112 detects the time series data of the angle of the knee joint during a specified period of the stance phase of one leg. Specifically, the specified period is a period from 1% to 60% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the angle of the knee joint of one leg during a period from 1% to 60% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the angle of the knee joint of one leg during a period from 1% to 60% of one walking cycle.

[0192] The memory 12 stores in advance a prediction model, which uses the angle of the knee joint of one leg during 1% to 60% of a walking cycle as an input value and generates as an output value whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person. The prediction model is a regression model that uses as a target variable whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person and uses as an explanatory variable the time series data of the angle of the knee joint of one leg during 1% to 60% of a walking cycle. In particular, the memory 12 stores in advance a prediction model that uses as an input value the average value of the time series data of the angle of the knee joint of one leg during 1% to 60% of a walking cycle and generates as an output value whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person.

[0193] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the average value of the time series data of the angle of the knee joint of one leg during the prescribed period of the stance phase. The prescribed period is a period from 1% to 60% of one walking cycle. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the average value of the time series data of the angle of the knee joint of one leg during the prescribed period of the stance phase detected by the walking parameter detection unit 112 into a prediction model, which uses the average value of the time series data of the angle of the knee joint of one leg during the prescribed period of the stance phase as an input value and generates whether the test subject has sarcopenia as an output value.

[0194] Moreover, the sarcopenia determination unit 113 uses the average value of the time series data of the angle of the knee joint during the prescribed period of the stance phase of one leg to determine whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person. The prescribed period is a period from 1% to 60% of a walking cycle. Specifically, the sarcopenia determination unit 113 uses the average value of the time series data of the angle of the knee joint of one leg during the period from 1% to 60% of a walking cycle to determine whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person from the prediction model by inputting the average value of the time series data of the angle of the knee joint of one leg during the period from 1% to 60% of a walking cycle into the prediction model.

[0195] Next, walking parameters according to a second modified example of the present embodiment will be described.

[0196] The walking parameter of the second modified example of the present embodiment may be an average value of time series data of the angle of the knee joint of one leg during a period from 50% to 60% of one walking cycle.

[0197] In the second variant of the present embodiment, similar to the above-mentioned experiment, the time series data of the angle of the knee joint of one leg of each of the multiple test subjects is detected. Furthermore, a prediction model is created with the target variable being whether the test subject is a person with sarcopenia, a sarcopenia preparation group, or a healthy person, and the average value of the angle of the knee joint of one leg during 50% to 60% of a walking cycle as an explanatory variable. The prediction model is evaluated by cross-validation. Leave-one-out cross-validation is used as the cross-validation. Furthermore, the ROC curve of the prediction model is calculated. The AUC value of the ROC curve of the prediction model is further calculated.

[0198] Fig.12 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the second modification example of the present embodiment.

[0199] The prediction model of the second variant of this embodiment is created by taking the test subject's type of sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average value of the angle of the knee joint of one leg during 50% to 60% of a walking cycle as the explanatory variable. Fig.12 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0200] Fig.12 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created by using the average value of the angle of the knee joint of one leg during 50% to 60% of one walking cycle as an explanatory variable. Fig.12 The AUC value of the ROC curve shown is 0.6786.

[0201] Fig.13 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model according to the second modification of the present embodiment.

[0202] exist Fig.13In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0203] Fig.13 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created by using the average value of the angle of the knee joint of one leg during 50% to 60% of one walking cycle as an explanatory variable. Fig.13 The AUC value of the ROC curve shown is 0.6135.

[0204] In the second variant of the present embodiment, the average value of the angle of the knee joint of one leg during 50% to 60% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the angle of the knee joint of one leg during 50% to 60% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0205] The walking parameter detection unit 112 detects the time series data of the angle of the knee joint during a predetermined period of the stance phase of one leg. Specifically, the predetermined period is a period from 50% to 60% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the angle of the knee joint of one leg during a period from 50% to 60% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the angle of the knee joint of one leg during a period from 50% to 60% of one walking cycle.

[0206] The memory 12 pre-stores a prediction model generated by taking the angle of the knee joint of one leg during 50% to 60% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the time series data of the angle of the knee joint of one leg during 50% to 60% of a walking cycle as an explanatory variable. In particular, the memory 12 pre-stores the prediction model generated by taking the average value of the time series data of the angle of the knee joint of one leg during 50% to 60% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value.

[0207] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the average value of the time series data of the angle of the knee joint of one leg during the prescribed period of the stance phase. The prescribed period is a period of 50% to 60% of one walking cycle. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the average value of the time series data of the angle of the knee joint of one leg during the prescribed period of the stance phase detected by the walking parameter detection unit 112 into a prediction model, which uses the average value of the time series data of the angle of the knee joint of one leg during the prescribed period of the stance phase as an input value and generates whether the test subject has sarcopenia as an output value.

[0208] Furthermore, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person by using the average value of the time series data of the angle of the knee joint during a specified period of the stance phase of one leg. The specified period is a period from 50% to 60% of a walking cycle. Specifically, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person by using the average value of the time series data of the angle of the knee joint of one leg during a period from 50% to 60% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person from the prediction model by inputting the average value of the time series data of the angle of the knee joint of one leg during a period from 50% to 60% of a walking cycle into the prediction model.

[0209] Fig.14 This is a schematic diagram showing a second variant of the present embodiment, which is an average of average values ​​of time series data of the knee joint angle of one leg of test subjects with sarcopenia, an average of average values ​​of time series data of the knee joint angle of one leg of test subjects who are a sarcopenia preparation group, and an average of average values ​​of time series data of the knee joint angle of one leg of test subjects who are healthy people.

[0210] like Fig.14 As shown, the average value of the time series data of the angle of the knee joint of one leg of the test subjects with sarcopenia during the period from 50% to 60% of one gait cycle is 15.3 degrees, the average value of the time series data of the angle of the knee joint of one leg of the test subjects who are a preparation group for sarcopenia during the period from 50% to 60% of one gait cycle is 12.4 degrees, and the average value of the time series data of the angle of the knee joint of one leg of the test subjects who are healthy people during the period from 50% to 60% of one gait cycle is 9.3 degrees.

[0211] Thus, the average of the time series data of the angle of the knee joint of one leg of the test subjects who are sarcopenia during 50% to 60% of one gait cycle is greater than the average of the time series data of the angle of the knee joint of one leg of the test subjects who are a sarcopenia preparation group. For this reason, the value between the average of the time series data of the angle of the knee joint of one leg of the test subjects who are sarcopenia during 50% to 60% of one gait cycle obtained by the experiment and the average of the time series data of the angle of the knee joint of one leg of the test subjects who are a sarcopenia preparation group during 50% to 60% of one gait cycle can be stored in the memory 12 as a first threshold. The sarcopenia determination unit 113 can also determine whether the test subject has sarcopenia by comparing the average of the time series data of the angle of the knee joint of one leg of the test subject during 50% to 60% of one gait cycle with the pre-stored first threshold.

[0212] Moreover, the average of the time series data of the angle of the knee joint of one leg of the test subjects who are the sarcopenia preparation group during the period of 50% to 60% of one walking cycle is greater than the average of the time series data of the angle of the knee joint of one leg of the test subjects who are healthy people. For this reason, the value between the average of the time series data of the angle of the knee joint of one leg of the test subjects who are the sarcopenia preparation group obtained by the experiment and the average of the time series data of the angle of the knee joint of one leg of the healthy people during the period of 50% to 60% of one walking cycle can be stored in the memory 12 as the second threshold. The sarcopenia determination unit 113 can also determine whether the test subject is a sarcopenia preparation group by comparing the average of the time series data of the angle of the knee joint of one leg of the test subject during the period of 50% to 60% of one walking cycle with the pre-stored second threshold.

[0213] Next, walking parameters according to a third modified example of the present embodiment will be described.

[0214] The walking parameter of the third modified example of the present embodiment may be an average value of time series data of the displacement of the toe portion of one leg in the vertical direction during a predetermined period of the stance phase of one leg.

[0215] Fig.15 FIG. 4 is a schematic diagram showing the displacement of the toe portion of one leg in the vertical direction during one walking cycle in the third variant of the present embodiment. Fig.15 In the figure, the vertical axis represents the displacement of the toe in the vertical direction, and the horizontal axis represents a standardized walking cycle. Fig.15 In the figure, the dotted line represents the average waveform of the displacement of the toes of one leg of healthy people in the vertical direction, the dash-dotted line represents the average waveform of the displacement of the toes of one leg of the test subjects who are a preparation group for sarcopenia, and the solid line represents the average waveform of the displacement of the toes of one leg of the test subjects who are sarcopenia.

[0216] The third variant of this embodiment is similar to the above-mentioned experiment, in which time series data of the displacement of the toe portion of one leg of each of the multiple test subjects in the vertical direction is detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory group, and the test subjects of healthy people. Figure 2 As shown, the displacement β of the toe portion in the vertical direction represents the displacement of the characteristic point 213 of the toe portion in the vertical direction.

[0217] In the experiment, a standardized walking cycle was divided into ten intervals, and the average displacement of the toe of one leg in the vertical direction in one interval or two or more consecutive intervals was calculated for each test subject. In addition, a prediction model was created with the test subject being sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average displacement of the toe of one leg in the vertical direction during 1% to 60% of a walking cycle as the explanatory variable. The prediction model was evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation was used. In addition, the ROC curve of the prediction model for judging healthy people and sarcopenia and the ROC curve of the prediction model for judging healthy people and sarcopenia preparation group were calculated. The AUC values ​​of the two ROC curves of the prediction model were further calculated.

[0218] Fig.16 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the third modification example of the present embodiment.

[0219] The prediction model of the third variant of this embodiment is created by taking whether the test subject is sarcopenia, sarcopenia preparation group or healthy person as the target variable, and taking the average value of the vertical displacement of the toe of one leg during 1% to 60% of a walking cycle as the explanatory variable. Fig.16 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0220] Fig.16The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the vertical displacement of the toe portion of one leg during 1% to 60% of one gait cycle as an explanatory variable. Fig.16 The AUC value of the ROC curve shown is 0.636.

[0221] Fig.17 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the third modification example of the present embodiment.

[0222] exist Fig.17 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0223] Fig.17 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the vertical displacement of the toe portion of one leg during 1% to 60% of one gait cycle as an explanatory variable. Fig.17 The AUC value of the ROC curve shown is 0.560.

[0224] In the third modified example of the present embodiment, the average value of the displacement of the toe portion of one leg in the vertical direction during the period from 1% to 60% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during the period from 1% to 60% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0225] The walking parameter detection unit 112 detects the displacement of the toe of one leg of the test subject in the vertical direction based on the walking data. The walking parameter detection unit 112 detects the displacement of the toe of one leg of the test subject in the vertical direction from the time series of skeletal data corresponding to one walking cycle that is intercepted. In particular, the walking parameter detection unit 112 detects the time series data of the displacement of the toe of one leg in the vertical direction during a specified period of the stance period of one leg. Specifically, the specified period is a period from 1% to 60% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the displacement of the toe of one leg in the vertical direction during a period from 1% to 60% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe of one leg in the vertical direction during a period from 1% to 60% of one walking cycle.

[0226] Furthermore, in the third modified example of the present embodiment, since one gait cycle is the period from when the right foot of the subject lands on the ground until the right foot lands on the ground again, the gait parameter detection unit 112 detects the displacement β of the toe portion of the right foot in the vertical direction when the right foot is in the stance phase. In the case where one gait cycle is the period from when the left foot of the subject lands on the ground until the left foot lands on the ground again, the gait parameter detection unit 112 may detect the displacement β of the toe portion of the left foot in the vertical direction when the left foot is in the stance phase.

[0227] The memory 12 pre-stores a prediction model generated by taking the displacement of the toe of one leg in the vertical direction during 1% to 60% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 60% of a walking cycle as an explanatory variable. In particular, the memory 12 pre-stores the prediction model generated by taking the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 60% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value.

[0228] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the displacement of the toe of one leg in the vertical direction. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the displacement of the toe of one leg in the vertical direction detected by the walking parameter detection unit 112 into a prediction model, which uses the displacement of the toe of one leg in the vertical direction as an input value and generates whether the test subject has sarcopenia as an output value.

[0229] Furthermore, the sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a prescribed period of the stance period of one leg. The prescribed period is a period from 1% to 60% of a walking cycle. The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 1% to 60% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject suffers from sarcopenia from the prediction model by inputting the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 1% to 60% of a walking cycle into the prediction model.

[0230] Furthermore, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the stance phase of one leg. The prescribed period is a period from 1% to 60% of a walking cycle. Specifically, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the period from 1% to 60% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person from the prediction model by inputting the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the period from 1% to 60% of a walking cycle into the prediction model.

[0231] Next, walking parameters according to a fourth modified example of the present embodiment will be described.

[0232] The walking parameter of the fourth modified example of the present embodiment may be an average value of time series data of the displacement of the toe portion of one leg of the test subject in the vertical direction during a predetermined period of time when the foot of one leg is in the air.

[0233] The fourth variant of the present embodiment is the same as the above-mentioned experiment, in which the time series data of the displacement of the toe of one leg in the vertical direction of each of the multiple test subjects is detected from the skeletal data of multiple test subjects including test subjects with sarcopenia, test subjects in the sarcopenia preparation group, and test subjects of healthy people. In addition, a prediction model is created, which takes whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and takes the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the specified period of the foot hanging as the explanatory variable. The specified period is the period from 61% to 100% of a walking cycle. The prediction model is evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation is used. In addition, the ROC curve of the prediction model is calculated. The AUC value of the ROC curve of the prediction model is further calculated.

[0234] Fig.18 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the fourth modification example of the present embodiment.

[0235] The prediction model of the fourth variant of this embodiment is created by taking whether the test subject is sarcopenia, sarcopenia preparation group or healthy person as the target variable, and taking the average value of the vertical displacement of the toe of one leg during 61% to 100% of a walking cycle as the explanatory variable. Fig.18 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0236] Fig.18 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the vertical displacement of the toe portion of one leg during 61% to 100% of one gait cycle as an explanatory variable. Fig.18 The AUC value of the ROC curve shown is 0.514.

[0237] Fig.19 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the fourth modification example of the present embodiment.

[0238] exist Fig.19 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0239] Fig.19 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the vertical displacement of the toe portion of one leg during 61% to 100% of one gait cycle as an explanatory variable. Fig.19 The AUC value of the ROC curve shown is 0.626.

[0240] In the fourth modified example of the present embodiment, the average value of the displacement of the toe portion of one leg in the vertical direction during the period from 61% to 100% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during the period from 61% to 100% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0241] The walking parameter detection unit 112 detects the displacement of the toe portion of one leg of the test subject in the vertical direction during the prescribed period of the foot suspension period of one leg based on the walking data. The walking parameter detection unit 112 detects the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot suspension period from the time series skeletal data corresponding to one captured walking cycle. In particular, the walking parameter detection unit 112 detects the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot suspension period of one leg. Specifically, the prescribed period is a period from 61% to 100% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the displacement of the toe portion of one leg in the vertical direction during the period from 61% to 100% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the period from 61% to 100% of one walking cycle.

[0242] The memory 12 pre-stores a prediction model generated by taking the displacement of the toe of one leg in the vertical direction during 61% to 100% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the time series data of the displacement of the toe of one leg in the vertical direction during 61% to 100% of a walking cycle as an explanatory variable. In particular, the memory 12 pre-stores the prediction model generated by taking the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 61% to 100% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value.

[0243] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot hanging in the air. The prescribed period is a period from 61% to 100% of a walking cycle. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot hanging in the air detected by the walking parameter detection unit 112 into a prediction model, which uses the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot hanging in the air as an input value and generates whether the test subject has sarcopenia as an output value.

[0244] Furthermore, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a prescribed period of the foot of one leg in the air. The prescribed period is a period from 61% to 100% of a walking cycle. Specifically, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 61% to 100% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person from the prediction model by inputting the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 61% to 100% of a walking cycle into the prediction model.

[0245] Next, walking parameters according to a fifth modified example of the present embodiment will be described.

[0246] The walking parameter of the fifth modified example of the present embodiment may be an average value of time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 65% to 70% of one walking cycle.

[0247] Fig. 20 FIG. 5 is a schematic diagram showing the displacement of the toe portion of one leg in the vertical direction during one walking cycle in the fifth variation of the present embodiment. Fig. 20 In the figure, the vertical axis represents the displacement of the toe in the vertical direction, and the horizontal axis represents a standardized walking cycle. Fig. 20 In the figure, the dotted line represents the average waveform of the displacement of the toe of one leg in the vertical direction of healthy subjects, and the solid line represents the average waveform of the displacement of the toe of one leg in the vertical direction of the test subjects who are sarcopenia or sarcopenia preparation groups.

[0248] In addition, in the fourth modification of the present embodiment, it is determined whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person, but in the fifth modification of the present embodiment, it is determined whether the test subject is sarcopenia or a sarcopenia candidate group. In addition, the test subject who is not sarcopenia or a sarcopenia candidate group is determined to be a healthy person.

[0249] The fifth variant of the present embodiment is the same as the above-mentioned experiment, and the time series data of the displacement of the toe of one leg of each test subject in the vertical direction is detected. In addition, a prediction model is created, which takes whether the test subject is sarcopenia or a sarcopenia candidate as the target variable, and takes the average value of the displacement of the toe of one leg in the vertical direction during 65% to 70% of a walking cycle as the explanatory variable. The prediction model is evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation is used. In addition, the ROC curve of the prediction model that determines whether it is sarcopenia or a sarcopenia candidate is calculated. The AUC value of the ROC curve of the prediction model is further calculated.

[0250] Fig.21 Schematic diagram showing an ROC curve obtained from the result of determining whether a person has sarcopenia or is a sarcopenia-preparatory population using the prediction model of the fifth modification example of the present embodiment.

[0251] The prediction model of the fifth variant of this embodiment is created by taking whether the test subject is a sarcopenia patient or a sarcopenia candidate as the target variable and the average displacement of the toe of one leg in the vertical direction during 65% to 70% of a walking cycle as the explanatory variable. Fig.21 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia or sarcopenia candidate population as sarcopenia or sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as sarcopenia or sarcopenia candidate population.

[0252] Fig.21 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of one gait cycle as an explanatory variable. Fig.21 The AUC value of the ROC curve shown is 0.6525.

[0253] In the fifth modification of the present embodiment, the average value of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0254] The walking parameter detection unit 112 detects the time series data of the displacement of the toe portion of one leg in the vertical direction during a predetermined period of time when the foot of one leg is suspended in the air. Specifically, the predetermined period is a period from 65% to 70% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 65% to 70% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during a period from 65% to 70% of one walking cycle.

[0255] The memory 12 pre-stores a prediction model generated by taking the displacement of the toe of one leg in the vertical direction during 65% to 70% of a walking cycle as an input value and whether the test subject is sarcopenia or a sarcopenia candidate as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia or a sarcopenia candidate as a target variable and takes the time series data of the displacement of the toe of one leg in the vertical direction during 65% to 70% of a walking cycle as an explanatory variable. In particular, the memory 12 pre-stores the prediction model generated by taking the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 65% to 70% of a walking cycle as an input value and whether the test subject is sarcopenia or a sarcopenia candidate as an output value.

[0256] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot hanging in the air. The prescribed period is a period of 65% to 70% of a walking cycle. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot hanging in the air detected by the walking parameter detection unit 112 into a prediction model, which uses the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during the prescribed period of the foot hanging in the air as an input value and generates whether the test subject has sarcopenia as an output value.

[0257] Moreover, the sarcopenia determination unit 113 uses the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the prescribed period when the foot of one leg is suspended in the air to determine whether the test subject has sarcopenia or a sarcopenia candidate group. The prescribed period is a period from 65% to 70% of a walking cycle. Specifically, the sarcopenia determination unit 113 uses the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the period from 65% to 70% of a walking cycle to determine whether the test subject has sarcopenia or a sarcopenia candidate group. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject has sarcopenia or a sarcopenia candidate group from the prediction model by inputting the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the period from 65% to 70% of a walking cycle into the prediction model.

[0258] Fig. 22 It is a schematic diagram showing the average of the average values ​​of time series data of displacement of the toe of one leg in the vertical direction of the test subjects who are sarcopenia or sarcopenia preparation population in the fifth variant of the present embodiment, and the average of the average values ​​of time series data of displacement of the toe of one leg in the vertical direction of the test subjects who are healthy people.

[0259] like Fig. 22 As shown, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 65% to 70% of a gait cycle of the test subjects who were sarcopenia or sarcopenia preparation groups was 37 mm, and the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 65% to 70% of a gait cycle of the test subjects who were healthy people was 31 mm.

[0260] Thus, the average of the time series data of the displacement of the toe of one leg of the test subjects who are sarcopenia or sarcopenia candidate population in the vertical direction during 65% to 70% of one gait cycle is greater than the average of the time series data of the displacement of the toe of one leg of the test subjects who are healthy subjects in the vertical direction. Therefore, a value between the average of the time series data of the displacement of the toe of one leg of the test subjects who are sarcopenia or sarcopenia candidate population in the vertical direction during 65% to 70% of one gait cycle obtained by the experiment and the average of the time series data of the displacement of the toe of one leg of the test subjects who are healthy subjects in the vertical direction during 65% to 70% of one gait cycle can be stored in the memory 12 as a threshold value. The sarcopenia determination unit 113 can also determine whether the test subject is sarcopenia or sarcopenia candidate population by comparing the average of the time series data of the displacement of the toe of one leg of the test subject in the vertical direction during 65% to 70% of one gait cycle with the pre-stored threshold value.

[0261] Next, walking parameters according to a sixth modified example of the present embodiment will be described.

[0262] The walking parameter of the sixth modification of the present embodiment may be an average value of time series data of the angle of the ankle joint of one leg during a predetermined period of the stance phase of one leg.

[0263] Fig.23 Schematic diagram showing the change in angle of the ankle joint of one leg during one walking cycle in the sixth variation of the present embodiment. Fig.23 In the figure, the vertical axis represents the angle of the ankle joint, and the horizontal axis represents a normalized walking cycle. Fig.23 In the figure, the dotted line represents the average waveform of the angle of the ankle joint of one leg of a healthy person, the dashed line represents the average waveform of the angle of the ankle joint of one leg of the test subjects who are a preparatory group for sarcopenia, and the solid line represents the average waveform of the angle of the ankle joint of one leg of the test subjects who are sarcopenia.

[0264] The sixth variation of this embodiment is similar to the above-mentioned experiment, in which time series data of the angle of the ankle joint of one leg of each of the multiple test subjects is detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory group, and the test subjects of healthy people. Figure 2As shown, the angle θ of the ankle joint is the angle formed by the straight line connecting the feature point 212 representing the right ankle joint and the feature point 211 representing the right knee joint on the arrow-shaped plane and the straight line connecting the feature point 212 representing the right ankle joint and the feature point 213 representing the right toe.

[0265] In the experiment, a standardized walking cycle was divided into ten intervals, and the average angle of the ankle joint of one leg in one interval or two or more consecutive intervals was calculated for each test subject. In addition, a prediction model was created with the test subject being sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average angle of the ankle joint of one leg during 1% to 60% of a walking cycle as the explanatory variable. The prediction model was evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation was used. In addition, the ROC curve of the prediction model for judging healthy people and sarcopenia and the ROC curve of the prediction model for judging healthy people and sarcopenia preparation group were calculated. The AUC values ​​of the two ROC curves of the prediction model were further calculated.

[0266] Fig.24 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the sixth modification example of the present embodiment.

[0267] The prediction model of the sixth variant of this embodiment is created by taking the test subject's type of sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average value of the angle of the ankle joint of one leg during 1% to 60% of a walking cycle as the explanatory variable. Fig.24 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0268] Fig.24 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model that uses the average value of the angle of the ankle joint of one leg during 1% to 60% of one walking cycle as an explanatory variable. Fig.24 The AUC value of the ROC curve shown is 0.498.

[0269] Fig.25 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the sixth modification example of the present embodiment.

[0270] exist Fig.25In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0271] Fig.25 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model that uses the average value of the angle of the ankle joint of one leg during 1% to 60% of one walking cycle as an explanatory variable. Fig.25 The AUC value of the ROC curve shown is 0.610.

[0272] In the sixth variation of the present embodiment, the average value of the angle of the ankle joint of one leg during the period from 1% to 60% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the angle of the ankle joint of one leg during the period from 1% to 60% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0273] The walking parameter detection unit 112 detects the angle of the ankle joint of one leg of the test subject during the stance phase of one leg from the walking data. The walking parameter detection unit 112 detects the angle of the ankle joint of one leg of the test subject during the stance phase from the time series skeletal data corresponding to one walking cycle that is intercepted. In particular, the walking parameter detection unit 112 detects the time series data of the angle of the ankle joint of one leg during a specified period of the stance phase of one leg. Specifically, the specified period is a period from 1% to 60% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the angle of the ankle joint of one leg during a period from 1% to 60% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the angle of the ankle joint of one leg during a period from 1% to 60% of one walking cycle.

[0274] In the sixth modification of the present embodiment, since one gait cycle is the period from when the subject's right foot lands on the ground until the right foot lands on the ground again, the gait parameter detection unit 112 detects the angle θ of the ankle joint of the right leg. In the case where one gait cycle is the period from when the subject's left foot lands on the ground until the left foot lands on the ground again, the gait parameter detection unit 112 may detect the angle θ of the ankle joint of the left leg.

[0275] The memory 12 pre-stores a prediction model generated by taking the angle of the ankle joint of one leg during 1% to 60% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the time series data of the angle of the ankle joint of one leg during 1% to 60% of a walking cycle as an explanatory variable. In particular, the memory 12 pre-stores the prediction model generated by taking the average value of the time series data of the angle of the ankle joint of one leg during 1% to 60% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value.

[0276] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the angle of the ankle joint of one leg during the stance phase. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the angle of the ankle joint of one leg during the stance phase detected by the walking parameter detection unit 112 into a prediction model that uses the angle of the ankle joint of one leg during the stance phase as an input value and generates whether the test subject has sarcopenia as an output value.

[0277] Furthermore, the sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia using the average value of the time series data of the angle of the ankle joint of one leg during a prescribed period of the stance phase of one leg. The prescribed period is a period from 1% to 60% of a walking cycle. The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia using the average value of the time series data of the angle of the ankle joint of one leg during a period from 1% to 60% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject suffers from sarcopenia from the prediction model by inputting the average value of the time series data of the angle of the ankle joint of one leg during a period from 1% to 60% of a walking cycle into the prediction model.

[0278] Furthermore, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person by using the average value of the time series data of the angle of the ankle joint of one leg during the prescribed period of the stance phase of one leg. The prescribed period is a period from 1% to 60% of a walking cycle. Specifically, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person by using the average value of the time series data of the angle of the ankle joint of one leg during the period from 1% to 60% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person from the prediction model by inputting the average value of the time series data of the angle of the ankle joint of one leg during the period from 1% to 60% of a walking cycle into the prediction model.

[0279] Moreover, in Fig.23 During the period from 1% to 60% of a walking cycle as shown, the average waveform of the angle of the ankle joint of the test subjects who are sarcopenia is larger than the average waveform of the angle of the ankle joint of the test subjects who are a sarcopenia preparation group. For this reason, the value between the average of the time series data of the angle of the ankle joint of the test subjects who are sarcopenia during the period from 1% to 60% of a walking cycle obtained by the experiment and the average of the time series data of the angle of the ankle joint of the test subjects who are a sarcopenia preparation group during the period from 1% to 60% of a walking cycle can be stored in the memory 12 as a first threshold. The sarcopenia determination unit 113 can also determine whether the test subject has sarcopenia by comparing the average of the time series data of the angle of one ankle joint of the test subject during the period from 1% to 60% of a walking cycle with the pre-stored first threshold.

[0280] Moreover, in Fig.23During the period from 1% to 60% of a walking cycle shown in the figure, the average waveform of the angle of the ankle joint of the test subjects who are a sarcopenia preparation group is larger than the average waveform of the angle of the ankle joint of the test subjects who are healthy people. For this reason, a value between the average of the time series data of the angle of the ankle joint of the test subjects who are a sarcopenia preparation group during the period from 1% to 60% of a walking cycle obtained by the experiment and the average of the time series data of the angle of the ankle joint of the test subjects who are healthy people during the period from 1% to 60% of a walking cycle can be stored in the memory 12 as a second threshold. The sarcopenia determination unit 113 can also determine whether the test subject is a sarcopenia preparation group by comparing the average of the time series data of the angle of one ankle joint of the test subject during the period from 1% to 60% of a walking cycle with the pre-stored second threshold.

[0281] Next, walking parameters according to a seventh modified example of the present embodiment will be described.

[0282] The walking parameter of the seventh modified example of the present embodiment may be an average value of time series data of the angle of the ankle joint of one leg during a predetermined period of time when the foot of one leg is in the air.

[0283] The seventh variant of the present embodiment is the same as the above-mentioned experiment, in which time series data of the angle of an ankle joint of each of a plurality of test subjects is detected from the skeletal data of a plurality of test subjects including test subjects with sarcopenia, test subjects in a sarcopenia preparation group, and test subjects of healthy people.

[0284] In the experiment, a standardized walking cycle was divided into ten intervals, and the average angle of the ankle joint of one leg in one interval or two or more consecutive intervals was calculated for each test subject. In addition, a prediction model was created with the test subject being sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average angle of the ankle joint of one leg during 61% to 100% of a walking cycle as the explanatory variable. The prediction model was evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation was used. In addition, the ROC curve of the prediction model that judged healthy people and sarcopenia and the ROC curve of the prediction model that judged healthy people and sarcopenia preparation group were calculated. The AUC values ​​of the two ROC curves of the prediction model were further calculated.

[0285] Fig.26 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the seventh modification example of the present embodiment.

[0286] The prediction model of the seventh variant of this embodiment is created by taking whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and taking the average value of the angle of the ankle joint of one leg during 61% to 100% of a walking cycle as the explanatory variable. Fig.26 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0287] Fig.26 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the angle of the ankle joint of one leg during 61% to 100% of one walking cycle as an explanatory variable. Fig.26 The AUC value of the ROC curve shown is 0.389.

[0288] Fig. 27 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the seventh modification example of the present embodiment.

[0289] exist Fig. 27 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0290] Fig. 27 The ROC curve shown is a curve that plots the true positive rate and the false positive rate of a prediction model created using the average value of the angle of the ankle joint of one leg during 61% to 100% of one walking cycle as an explanatory variable. Fig. 27 The AUC value of the ROC curve shown is 0.622.

[0291] In the seventh variation of the present embodiment, the average value of the angle of the ankle joint of one leg during the period from 61% to 100% of one gait cycle is determined as the gait parameter. Furthermore, the prediction model created using the average value of the angle of the ankle joint of one leg during the period from 61% to 100% of one gait cycle as an explanatory variable is determined as the prediction model used by the sarcopenia determination unit 113.

[0292] The walking parameter detection unit 112 detects the angle of the ankle joint of one leg of the test subject during the period when the foot of one leg is suspended in the air from the walking data. The walking parameter detection unit 112 detects the angle of the ankle joint of one leg of the test subject during the period when the foot is suspended in the air from the skeleton data of the time series corresponding to one walking cycle that is intercepted. In particular, the walking parameter detection unit 112 detects the time series data of the angle of the ankle joint of one leg during a specified period when the foot of one leg is suspended in the air. Specifically, the specified period is a period from 61% to 100% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the angle of the ankle joint of one leg during a period from 61% to 100% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the angle of the ankle joint of one leg during a period from 61% to 100% of one walking cycle.

[0293] The memory 12 pre-stores a prediction model generated by taking the angle of the ankle joint of one leg during the period from 61% to 100% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the time series data of the angle of the ankle joint of one leg during the period from 61% to 100% of a walking cycle as an explanatory variable. In particular, the memory 12 pre-stores the prediction model generated by taking the average value of the time series data of the angle of the ankle joint of one leg during the period from 61% to 100% of a walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value.

[0294] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by using the angle of the ankle joint of one leg during the foot-in-the-air period. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the angle of the ankle joint of one leg during the foot-in-the-air period detected by the walking parameter detection unit 112 into a prediction model, wherein the prediction model uses the angle of the ankle joint of one leg during the foot-in-the-air period as an input value and generates whether the test subject has sarcopenia as an output value.

[0295] Furthermore, the sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the angle of the ankle joint of one leg during a specified period when the foot of one leg is suspended in the air. The specified period is a period from 61% to 100% of a walking cycle. The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the angle of the ankle joint of one leg during a period from 61% to 100% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject suffers from sarcopenia from the prediction model by inputting the average value of the time series data of the angle of the ankle joint of one leg during a period from 61% to 100% of a walking cycle into the prediction model.

[0296] Furthermore, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person by using the average value of the time series data of the angle of the ankle joint of one leg during the prescribed period of the foot of one leg hanging in the air. The prescribed period is the period from 61% to 100% of a walking cycle. Specifically, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person by using the average value of the time series data of the angle of the ankle joint of one leg during the period from 61% to 100% of a walking cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject is sarcopenia, sarcopenia candidate group, or healthy person from the prediction model by inputting the average value of the time series data of the angle of the ankle joint of one leg during the period from 61% to 100% of a walking cycle into the prediction model.

[0297] Next, walking parameters according to an eighth modified example of the present embodiment will be described.

[0298] The walking parameter of the eighth variant of the present embodiment may also be the average value of the time series data of the first angle of the ankle joint in the first period of the stance period of one leg and the average value of the time series data of the second angle of the ankle joint in the second period of the foot suspension period of one leg.

[0299] The eighth variant of the present embodiment is the same as the above-mentioned experiment, in which time series data of the angle of an ankle joint of each of the multiple test subjects is detected from the skeletal data of multiple test subjects including test subjects with sarcopenia, test subjects in the sarcopenia preparation group, and test subjects of healthy people. In addition, a prediction model is created, which takes whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and takes the average value of the angle of the ankle joint of one leg during 11% to 40% of a walking cycle and the average value of the angle of the ankle joint of one leg during 71% to 80% of a walking cycle as explanatory variables. The prediction model is evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation is used. In addition, the ROC curve of the prediction model for judging healthy people and sarcopenia is calculated. The AUC value of the ROC curve of the prediction model is further calculated.

[0300] Fig.28 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the eighth modification example of the present embodiment.

[0301] The prediction model of the eighth variant of this embodiment is created by taking the test subject's type of sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and the average value of the angle of the ankle joint of one leg during 11% to 40% of a walking cycle and the average value of the angle of the ankle joint of one leg during 71% to 80% of a walking cycle as explanatory variables. Fig.28 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0302] Fig.28 The ROC curve shown is a curve depicting the true positive rate and false positive rate of a prediction model created by using the average value of the angle of the ankle joint of one leg during 11% to 40% of a walking cycle and the average value of the angle of the ankle joint of one leg during 71% to 80% of a walking cycle as explanatory variables. Fig.28 The AUC value of the ROC curve shown is 0.608.

[0303] In the eighth modification of the present embodiment, the average value of the angle of the ankle joint of one leg during 11% to 40% of one gait cycle and the average value of the angle of the ankle joint of one leg during 71% to 80% of one gait cycle are determined as walking parameters. Furthermore, a prediction model created using the average value of the angle of the ankle joint of one leg during 11% to 40% of one gait cycle and the average value of the angle of the ankle joint of one leg during 71% to 80% of one gait cycle as explanatory variables is determined as the prediction model used by the sarcopenia determination unit 113.

[0304] The walking parameter detection unit 112 detects time series data of a first angle of the ankle joint in a first period of a stance period of one leg and time series data of a second angle of the ankle joint in a second period of a foot-free period of one leg. The first period is a period from 11% to 40% of one walking cycle, and the second period is a period from 71% to 80% of one walking cycle. The walking parameter detection unit 112 detects time series data of the angle of the ankle joint of one leg in a period from 11% to 40% of one walking cycle and time series data of the angle of the ankle joint of one leg in a period from 71% to 80% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates an average value of the time series data of the angle of the ankle joint of one leg in a period from 11% to 40% of one walking cycle and an average value of the time series data of the angle of the ankle joint of one leg in a period from 71% to 80% of one walking cycle.

[0305] The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia using the average value of the time series data of the first angle of the ankle joint and the average value of the time series data of the second angle of the ankle joint.

[0306] The memory 12 pre-stores a prediction model generated by taking as input the average value of time series data of a first angle of an ankle joint in a first period of a stance period of one leg and the average value of time series data of a second angle of an ankle joint in a second period of a foot-free period of one leg and taking as output the whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person. The memory 12 pre-stores a prediction model generated by taking as input the average value of angles of an ankle joint of one leg in a period of 11% to 40% of a walking cycle and the average value of angles of an ankle joint of one leg in a period of 71% to 80% of a walking cycle and taking as output the whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person.

[0307] The sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person, using the average value of the time series data of the angle of the ankle joint of one leg during 11% to 40% of one gait cycle and the average value of the time series data of the angle of the ankle joint of one leg during 71% to 80% of one gait cycle. The sarcopenia determination unit 113 inputs the average value of the time series data of the angle of the ankle joint of one leg during 11% to 40% of one gait cycle and the average value of the time series data of the angle of the ankle joint of one leg during 71% to 80% of one gait cycle into the prediction model, and obtains a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate, or a healthy person from the prediction model.

[0308] Thus, the AUC value obtained by judging sarcopenia from the prediction model created using only the average value of the angle of the ankle joint during the stance period was 0.498, and the AUC value obtained by judging sarcopenia from the prediction model created using only the average value of the angle of the ankle joint during the foot-hanging period was 0.389. On the other hand, the AUC value obtained by judging sarcopenia from the prediction model created using the average value of the angle of the ankle joint during two periods was 0.608. Therefore, compared with the prediction model created using only the average value of the angle of the ankle joint during one period, the prediction model created using the average value of the angle of the ankle joint during two periods can judge sarcopenia with high accuracy.

[0309] Next, walking parameters according to a ninth modified example of the present embodiment will be described.

[0310] The walking parameter in the ninth modified example of the present embodiment may be the stride of one leg.

[0311] The ninth variation of the present embodiment is similar to the above-mentioned experiment, and detects the span of one leg of each of the multiple test subjects from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparation group, and the test subjects of the healthy subjects. The span is the distance from the point where the heel touches the ground to the point where the heel touches the ground again. In the case where one walking cycle is the period from the right foot of the test subject touching the ground to the right foot touching the ground again, the span is the distance from the point where the heel of the right foot touches the ground to the point where the heel of the right foot touches the ground again.

[0312] In the experiment, the span of one leg was calculated for each test subject. Furthermore, a prediction model was created with the test subject being sarcopenia, sarcopenia candidate, or healthy as the target variable, and the span of one leg in one walking cycle as the explanatory variable. The prediction model was evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation was used. Furthermore, the ROC curve of the prediction model for judging healthy people and sarcopenia was calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0313] Fig.29 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the ninth variation of the present embodiment.

[0314] The prediction model of the ninth variant of this embodiment is created by taking whether the test subject is a sarcopenia patient, a sarcopenia candidate, or a healthy person as the target variable, and taking the stride of one leg in one walking cycle as the explanatory variable. Fig.29 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0315] Fig.29 The ROC curve shown is a curve that depicts the true positive rate and false positive rate of a prediction model generated using the stride of one leg in one walking cycle as an explanatory variable. Fig.29 The AUC value of the ROC curve shown is 0.6677.

[0316] In the ninth variation of the present embodiment, the stride of one leg in one gait cycle is determined as a gait parameter. Furthermore, a prediction model created using the stride of one leg in one gait cycle as an explanatory variable is determined as a prediction model used by the sarcopenia determination unit 113 .

[0317] The walking parameter detection unit 112 detects the stride of one leg of the test subject from the walking data. The walking parameter detection unit 112 detects the stride of one leg of the test subject from the time-series skeleton data corresponding to one walking cycle.

[0318] In the ninth modification of the present embodiment, since one walking cycle is the period from when the right foot of the test subject lands on the ground to when the right foot lands again, the walking parameter detection unit 112 detects the stride from the point where the heel of the right foot lands on the ground to the point where the heel of the right foot lands again. In the case where one walking cycle is the period from when the left foot of the test subject lands on the ground to when the left foot lands again, the walking parameter detection unit 112 may detect the stride from the point where the heel of the left foot lands on the ground to the point where the heel of the left foot lands again. Furthermore, the walking parameter detection unit 112 may detect a plurality of strides in a plurality of walking cycles and calculate the average value of the plurality of detected strides.

[0319] The memory 12 pre-stores a prediction model generated by taking the stride of one leg in one walking cycle as an input value and taking whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as an output value. The prediction model is a regression model that takes whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person as a target variable and takes the stride of one leg in one walking cycle as an explanatory variable.

[0320] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia using the stride of one leg in one gait cycle. The sarcopenia determination unit 113 determines whether the test subject has sarcopenia by inputting the stride of one leg in one gait cycle detected by the gait parameter detection unit 112 into a prediction model, wherein the prediction model uses the stride of one leg in one gait cycle as an input value and generates whether the test subject has sarcopenia as an output value. Furthermore, the sarcopenia determination unit 113 obtains a determination result indicating whether the test subject has sarcopenia from the prediction model by inputting the stride of one leg in one gait cycle into the prediction model.

[0321] Furthermore, the sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person using the stride length of one leg in one gait cycle. The sarcopenia determination unit 113 inputs the stride length of one leg in one gait cycle into the prediction model, and obtains a determination result indicating whether the test subject is sarcopenia, a sarcopenia candidate group, or a healthy person from the prediction model.

[0322] Fig.30 This is a schematic diagram showing the average span of one leg of the test subjects who are sarcopenia and the average span of one leg of the test subjects who are healthy people in the ninth modification example of the present embodiment.

[0323] like Fig.30As shown, the average span of one leg of the test subjects with sarcopenia in one walking cycle was 1.28 m, and the average span of one leg of the test subjects who were healthy people in one walking cycle was 1.39 m.

[0324] Thus, in one walking cycle, the average span of one leg of the test subjects with sarcopenia is smaller than the average span of one leg of the test subjects who are healthy people. For this reason, a value between the average span of one leg of the test subjects with sarcopenia in one walking cycle and the average span of one leg of the test subjects who are healthy people obtained through the experiment can be stored in the memory 12 as a threshold. The sarcopenia determination unit 113 can also determine whether the test subject has sarcopenia by comparing the span of one leg of the test subject in one walking cycle with a pre-stored threshold. The sarcopenia determination unit 113 can also determine that the test subject has sarcopenia when the span of one leg is smaller than the threshold.

[0325] Next, walking parameters according to a tenth modified example of the present embodiment will be described.

[0326] The walking parameters of the tenth variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the second period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the third period of the foot of one leg in the air, and the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the foot of one leg in the air.

[0327] The tenth variation of the present embodiment is similar to the above-mentioned experiment, in which time series data of displacement of the toe portion of one leg of each of the multiple test subjects in the vertical direction and time series data of angle of the knee joint of one leg of each of the multiple test subjects are detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. Furthermore, in the experiment, one standardized walking cycle is divided into ten intervals, and the average value of displacement of the toe portion of one leg in the vertical direction in one interval or two or more consecutive intervals and the average value of angle of the knee joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0328] Furthermore, a prediction model was created with the objective variable being whether the test subject was sarcopenia, a sarcopenia preparatory group, or a healthy person, and the average value of the time series data of the vertical displacement of the toe portion of one leg in the first period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the second period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the third period of the foot-in-the-air period, and the average value of the time series data of the angle of the knee joint of one leg in the fourth period of the foot-in-the-air period as explanatory variables. The first period was a period from 1% to 30% of a walking cycle, the second period was a period from 1% to 50% of a walking cycle, the third period was a period from 61% to 70% of a walking cycle, and the fourth period was a period from 81% to 100% of a walking cycle. The prediction model was evaluated by cross-validation. As cross-validation, leave-one-out cross-validation was used. Furthermore, the ROC curve of the prediction model for judging healthy people and sarcopenia was calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0329] Fig.31 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and sarcopenia using the prediction model of the tenth modification example of the present embodiment.

[0330] The prediction model of the tenth variant of the present embodiment uses the target variable as to whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person, and uses the average displacement of the toe of one leg in the vertical direction during 1% to 30% of a walking cycle, and the average angle of the knee joint of one leg during 1% to 50%, 61% to 70%, and 81% to 100% of a walking cycle as explanatory variables. Fig.31 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0331] Fig.31 The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the displacement of the toe of one leg in the vertical direction during 1% to 30% of a walking cycle, the average value of the angle of the knee joint of one leg during 1% to 50% of a walking cycle, the average value of the angle of the knee joint of one leg during 61% to 70% of a walking cycle, and the average value of the angle of the knee joint of one leg during 81% to 100% of a walking cycle as explanatory variables. Fig.31 The AUC value of the ROC curve shown is 0.790.

[0332] In the tenth variation of the present embodiment, the average value of the displacement of the toe portion of one leg in the vertical direction during 1% to 30% of one gait cycle, the average value of the angle of the knee joint of one leg during 1% to 50% of one gait cycle, the average value of the angle of the knee joint of one leg during 61% to 70% of one gait cycle, and the average value of the angle of the knee joint of one leg during 81% to 100% of one gait cycle are determined as walking parameters. Furthermore, a prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during 1% to 30% of one gait cycle, the average value of the angle of the knee joint of one leg during 1% to 50% of one gait cycle, the average value of the angle of the knee joint of one leg during 61% to 70% of one gait cycle, and the average value of the angle of the knee joint of one leg during 81% to 100% of one gait cycle as explanatory variables is determined as the prediction model used by the sarcopenia determination unit 113.

[0333] The walking parameter detection unit 112 detects time series data of displacement of the toe portion of one leg in the vertical direction in a first period of the stance period, time series data of the angle of the knee joint of one leg in a second period of the stance period, time series data of the angle of the knee joint of one leg in a third period of the foot-in-the-air period, and time series data of the angle of the knee joint of one leg in a fourth period of the foot-in-the-air period. The first period is a period from 1% to 30% of one walking cycle, the second period is a period from 1% to 50% of one walking cycle, the third period is a period from 61% to 70% of one walking cycle, and the fourth period is a period from 81% to 100% of one walking cycle. The walking parameter detection unit 112 detects the time series data of the displacement of the toe portion of one leg in the vertical direction during 1% to 30% of one walking cycle, the time series data of the angle of the knee joint of one leg during 1% to 50% of one walking cycle, the time series data of the angle of the knee joint of one leg during 61% to 70% of one walking cycle, and the time series data of the angle of the knee joint of one leg during 81% to 100% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during 1% to 30% of one walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 1% to 50% of one walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 61% to 70% of one walking cycle, and the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of one walking cycle.

[0334] The memory 12 pre-stores a prediction model which uses the average value of time series data of displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of time series data of the angle of the knee joint of one leg during the second period of the stance period, the average value of time series data of the angle of the knee joint of one leg during the third period of the foot hanging period, and the average value of time series data of the angle of the knee joint of one leg during the fourth period of the foot hanging period as input values, and uses whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person as an output value. The memory 12 pre-stores a prediction model that uses as input values ​​the average value of time series data of the displacement of the toe of one leg in the vertical direction during 1% to 30% of a gait cycle, the average value of time series data of the angle of the knee joint of one leg during 1% to 50% of a gait cycle, the average value of time series data of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, and the average value of time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, and uses as output values ​​whether the test subject is sarcopenia, a sarcopenia preparatory group, or a healthy person.

[0335] The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period and the average value of the time series data of the angle of the knee joint of one leg during the second period, the third period and the fourth period.

[0336] The sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 30% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 1% to 50% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, and the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle. The sarcopenia judgment unit 113 inputs into a prediction model the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 30% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 1% to 50% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, and the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, and obtains a judgment result indicating whether the test subject is sarcopenia, a sarcopenia preparatory group, or a healthy person from the prediction model.

[0337] Thus, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the displacement of the toe of one leg in the vertical direction during the stance period was 0.636, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the knee joint of one leg during the stance period was 0.586, and the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the knee joint of one leg during the foot-in-the-air period was 0.699. Correspondingly, the AUC value obtained by judging the result of sarcopenia from the prediction model created using the displacement of the toe of one leg in the vertical direction during the stance period, the angle of the knee joint of one leg during the stance period, and the angle of the knee joint of one leg during the foot-in-the-air period was 0.790.

[0338] Therefore, compared with a prediction model created using only the vertical displacement of the toe of one leg during the stance period, the angle of the knee joint of one leg during the stance period, and the angle of the knee joint of one leg during the foot-in-the-air period, the prediction model created using the vertical displacement of the toe of one leg during the stance period, the angle of the knee joint of one leg during the stance period, and the angle of the knee joint of one leg during the foot-in-the-air period can judge muscle wasting disease with high accuracy.

[0339] Next, walking parameters according to an eleventh modified example of the present embodiment will be described.

[0340] The walking parameters of the eleventh variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the second period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the third period of the stance period of one leg, and the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the foot of one leg in the air.

[0341] In the eleventh variation of the present embodiment, similar to the above-mentioned experiment, time series data of displacement of the toe portion of one leg of each of the multiple test subjects in the vertical direction and time series data of angle of the knee joint of one leg of each of the multiple test subjects are detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. Moreover, in the experiment, one standardized walking cycle is divided into ten intervals, and the average value of displacement of the toe portion of one leg in the vertical direction in one interval or two or more consecutive intervals and the average value of angle of the knee joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0342] Furthermore, a prediction model was created with the objective variable being whether the test subject was sarcopenia, a sarcopenia candidate group, or a healthy person, and the average value of the time series data of the vertical displacement of the toe portion of one leg in the first period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the second period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the third period of the stance period, and the average value of the time series data of the angle of the knee joint of one leg in the fourth period of the foot-in-the-air period as explanatory variables. The first period was a period of 31% to 40% of a walking cycle, the second period was a period of 1% to 10% of a walking cycle, the third period was a period of 41% to 50% of a walking cycle, and the fourth period was a period of 71% to 100% of a walking cycle. The prediction model was evaluated by cross-validation. As cross-validation, leave-one-out cross-validation was used. Furthermore, the ROC curve of the prediction model for judging the healthy person and the sarcopenia candidate group was calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0343] Fig.32 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model according to the eleventh modification of the present embodiment.

[0344] The prediction model of the eleventh variant of the present embodiment is created by taking the test subject as sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and taking the average displacement of the toe of one leg in the vertical direction during 31% to 40% of a walking cycle, and the average angle of the knee joint of one leg during 1% to 10%, 41% to 50%, and 71% to 100% of a walking cycle as explanatory variables. Fig.32 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0345] Fig.32 The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the displacement of the toe of one leg in the vertical direction during 31% to 40% of a walking cycle, the average value of the angle of the knee joint of one leg during 1% to 10% of a walking cycle, the average value of the angle of the knee joint of one leg during 41% to 50% of a walking cycle, and the average value of the angle of the knee joint of one leg during 71% to 100% of a walking cycle as explanatory variables. Fig.32 The AUC value of the ROC curve shown is 0.772.

[0346] In the eleventh variation of the present embodiment, the average value of the displacement of the toe portion of one leg in the vertical direction during 31% to 40% of one gait cycle, the average value of the angle of the knee joint of one leg during 1% to 10% of one gait cycle, the average value of the angle of the knee joint of one leg during 41% to 50% of one gait cycle, and the average value of the angle of the knee joint of one leg during 71% to 100% of one gait cycle are determined as walking parameters. Furthermore, a prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during 31% to 40% of one gait cycle, the average value of the angle of the knee joint of one leg during 1% to 10% of one gait cycle, the average value of the angle of the knee joint of one leg during 41% to 50% of one gait cycle, and the average value of the angle of the knee joint of one leg during 71% to 100% of one gait cycle as explanatory variables is determined as the prediction model used by the sarcopenia determination unit 113.

[0347] The walking parameter detection unit 112 detects time series data of displacement of the toe portion of one leg in the vertical direction in a first period of the stance period, time series data of angle of the knee joint of one leg in a second period of the stance period, time series data of angle of the knee joint of one leg in a third period of the stance period, and time series data of angle of the knee joint of one leg in a fourth period of the foot-in-the-air period. The first period is a period of 31% to 40% of one walking cycle, the second period is a period of 1% to 10% of one walking cycle, the third period is a period of 41% to 50% of one walking cycle, and the fourth period is a period of 71% to 100% of one walking cycle.

[0348] The walking parameter detection unit 112 detects time series data of the displacement of the toe of one leg in the vertical direction during 31% to 40% of a walking cycle, time series data of the angle of the knee joint of one leg during 1% to 10% of a walking cycle, time series data of the angle of the knee joint of one leg during 41% to 50% of a walking cycle, and time series data of the angle of the knee joint of one leg during 71% to 100% of a walking cycle.

[0349] Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 31% to 40% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 1% to 10% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 41% to 50% of a walking cycle, and the average value of the time series data of the angle of the knee joint of one leg during 71% to 100% of a walking cycle.

[0350] The memory 12 pre-stores a prediction model which uses the average value of time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of time series data of the angle of the knee joint of one leg during the second period of the stance period, the average value of time series data of the angle of the knee joint of one leg during the third period of the stance period, and the average value of time series data of the angle of the knee joint of one leg during the fourth period of the foot hanging period as input values, and uses whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person as an output value.

[0351] The memory 12 pre-stores a prediction model that uses as input values ​​the average value of time series data of displacement of the toe of one leg in the vertical direction during 31% to 40% of a gait cycle, the average value of time series data of angle of the knee joint of one leg during 1% to 10% of a gait cycle, the average value of time series data of angle of the knee joint of one leg during 41% to 50% of a gait cycle, and the average value of time series data of angle of the knee joint of one leg during 71% to 100% of a gait cycle, and uses as output values ​​whether the test subject is sarcopenia, a sarcopenia preparatory group, or a healthy person.

[0352] The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period and the average value of the time series data of the angle of the knee joint of one leg during the second period, the third period and the fourth period.

[0353] The sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia preparatory group, or a healthy person by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 31% to 40% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 41% to 50% of a gait cycle, and the average value of the time series data of the angle of the knee joint of one leg during 71% to 100% of a gait cycle.

[0354] The sarcopenia judgment unit 113 inputs the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 31% to 40% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 41% to 50% of a gait cycle, and the average value of the time series data of the angle of the knee joint of one leg during 71% to 100% of a gait cycle into the prediction model, and obtains a judgment result indicating whether the test subject is sarcopenia, a sarcopenia preparatory group, or a healthy person from the prediction model.

[0355] Thus, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the displacement of the toe of one leg in the vertical direction during the stance period was 0.560, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the knee joint of one leg during the stance period was 0.537, and the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the knee joint of one leg during the foot-in-the-air period was 0.604. Correspondingly, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using the displacement of the toe of one leg in the vertical direction during the stance period, the angle of the knee joint of one leg during the stance period, and the angle of the knee joint of one leg during the foot-in-the-air period was 0.772.

[0356] Therefore, compared with the prediction model created by using only the displacement of the toe of one leg in the vertical direction during the stance period, the angle of the knee joint of one leg during the stance period, and the angle of the knee joint of one leg during the foot-in-the-air period, the prediction model created by using the displacement of the toe of one leg in the vertical direction during the stance period, the angle of the knee joint of one leg during the stance period, and the angle of the knee joint of one leg during the foot-in-the-air period can judge the sarcopenia preparation population with high accuracy.

[0357] Next, walking parameters according to a twelfth modified example of the present embodiment will be described.

[0358] The walking parameters of the twelfth variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the foot suspension period of one leg, and the average value of the time series data of the angle of the knee joint of one leg during the second period of the foot stance period of one leg.

[0359] Fig.33 1 is a schematic diagram showing the change in angle of the knee joint of one leg in one walking cycle in the twelfth variant of the present embodiment. Fig.33 In the figure, the vertical axis represents the angle of the knee joint, and the horizontal axis represents a normalized walking cycle. Fig.33 In the figure, the dotted line represents the average waveform of the angle of the knee joint of one leg of healthy people, and the solid line represents the average waveform of the angle of the knee joint of one leg of the test subjects who are sarcopenia or sarcopenia preparatory groups.

[0360] In the twelfth variation of the present embodiment, it is determined whether the test subject has sarcopenia or a sarcopenia candidate group. In addition, the test subject who does not have sarcopenia or a sarcopenia candidate group is determined to be a healthy person.

[0361] Furthermore, the average waveform of the vertical displacement of the toes of one leg of the healthy subjects and the average waveform of the vertical displacement of the toes of one leg of the test subjects who are sarcopenia or sarcopenia preparation groups are as follows: Fig. 20 shown.

[0362] The twelfth variant of the present embodiment, as in the above-mentioned experiment, detects the time series data of the displacement of the toe of one leg of each of the multiple test subjects in the vertical direction and the time series data of the angle of the knee joint of one leg of each of the multiple test subjects from the skeletal data of multiple test subjects including the test subjects of sarcopenia, the test subjects of the sarcopenia preparation group and the test subjects of the healthy person. In addition, a prediction model is created with whether the test subject is sarcopenia or the sarcopenia preparation group as the target variable, and the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the foot hanging period and the average value of the time series data of the angle of the knee joint of one leg during the second period of the foot standing period as the explanatory variables. The first period is the period of 65% to 70% of a walking cycle, and the second period is the period of 45% to 50% of a walking cycle. The prediction model is evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation is adopted. In addition, the ROC curve of the prediction model for judging whether it is sarcopenia or the sarcopenia preparation group is calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0363] Fig.34 Schematic diagram showing an ROC curve obtained from the result of determining whether a person has sarcopenia or is a sarcopenia-preparatory group using the prediction model of the twelfth variation of the present embodiment.

[0364] The prediction model of the twelfth variant of the present embodiment is created by taking whether the test subject is sarcopenia or sarcopenia preparation as the target variable, and taking the average value of the vertical displacement of the toe of one leg during 65% to 70% of a walking cycle and the average value of the angle of the knee joint of one leg during 45% to 50% of a walking cycle as explanatory variables. Fig.34 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia or sarcopenia candidate population as sarcopenia or sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as sarcopenia or sarcopenia candidate population.

[0365] Fig.34The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the vertical displacement of the toe of one leg during 65% to 70% of a walking cycle and the average value of the angle of the knee joint of one leg during 45% to 50% of a walking cycle as explanatory variables. Fig.34 The AUC value of the ROC curve shown is 0.6680.

[0366] In the twelfth variation of the present embodiment, the average value of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of one gait cycle and the average value of the angle of the knee joint of one leg during 45% to 50% of one gait cycle are determined as walking parameters. Furthermore, a prediction model created using the average value of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of one gait cycle and the average value of the angle of the knee joint of one leg during 45% to 50% of one gait cycle as explanatory variables is determined as the prediction model used by the sarcopenia determination unit 113.

[0367] The walking parameter detection unit 112 detects time series data of displacement of the toe portion of one leg in the vertical direction during a first period of the foot-in-the-air period and time series data of the angle of the knee joint of one leg during a second period of the foot-in-the-foot period. The first period is a period from 65% to 70% of one walking cycle, and the second period is a period from 45% to 50% of one walking cycle. The walking parameter detection unit 112 detects time series data of displacement of the toe portion of one leg in the vertical direction during a period from 65% to 70% of one walking cycle and time series data of the angle of the knee joint of one leg during a period from 45% to 50% of one walking cycle. Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of displacement of the toe portion of one leg in the vertical direction during a period from 65% to 70% of one walking cycle and the average value of the time series data of the angle of the knee joint of one leg during a period from 45% to 50% of one walking cycle.

[0368] The memory 12 pre-stores a prediction model generated by taking as input the average value of time series data of displacement of the toe portion of one leg in the vertical direction during a first period of the foot-hanging period and the average value of time series data of angle of the knee joint of one leg during a second period of the foot-stance period, and taking as output whether the test subject is sarcopenia or a sarcopenia candidate population. The memory 12 pre-stores a prediction model generated by taking as input the average value of time series data of displacement of the toe portion of one leg in the vertical direction during a period of 65% to 70% of a walking cycle and the average value of time series data of angle of the knee joint of one leg during a period of 45% to 50% of a walking cycle, and taking as output whether the test subject is sarcopenia or a sarcopenia candidate population.

[0369] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period and the average value of the time series data of the angle of the knee joint of one leg during the second period.

[0370] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia or a sarcopenia candidate population by using the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of a gait cycle and the average value of the time series data of the angle of the knee joint of one leg during 45% to 50% of a gait cycle. The sarcopenia determination unit 113 obtains a determination result indicating whether the test subject has sarcopenia or a sarcopenia candidate population from the prediction model by inputting the average value of the time series data of the displacement of the toe portion of one leg in the vertical direction during 65% to 70% of a gait cycle and the average value of the time series data of the angle of the knee joint of one leg during 45% to 50% of a gait cycle into the prediction model.

[0371] Next, walking parameters according to a thirteenth modified example of the present embodiment will be described.

[0372] The walking parameters of the thirteenth variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the second period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the third period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the foot of one leg in the air, and the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot of one leg in the air.

[0373] In the thirteenth variation of the present embodiment, as in the above-mentioned experiment, time series data of displacement of the toe portion of one leg of each of the multiple test subjects in the vertical direction and time series data of angle of the ankle joint of one leg of each of the multiple test subjects are detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. Moreover, in the experiment, one standardized walking cycle is divided into ten intervals, and the average value of displacement of the toe portion of one leg in the vertical direction in one interval or two or more consecutive intervals and the average value of angle of the ankle joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0374] Furthermore, a prediction model was created with the objective variable being whether the test subject was sarcopenia, a sarcopenia preparatory group, or a healthy person, and the average value of the time series data of the vertical displacement of the toe portion of one leg in the first period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg in the second period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg in the third period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg in the fourth period of the foot-in-the-air period, and the average value of the time series data of the angle of the ankle joint of one leg in the fifth period of the foot-in-the-air period as explanatory variables. The first period is a period from 1% to 50% of a walking cycle, the second period is a period from 1% to 10% of a walking cycle, the third period is a period from 21% to 60% of a walking cycle, the fourth period is a period from 71% to 80% of a walking cycle, and the fifth period is a period from 91% to 100% of a walking cycle. The prediction model was evaluated by cross validation. As the cross validation, leave-one-out cross validation was used. Then, the ROC curve of the prediction model for judging healthy people and sarcopenia was calculated, and the AUC value of the ROC curve of the prediction model was calculated.

[0375] Fig.35 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the thirteenth variation of the present embodiment.

[0376] The prediction model of the thirteenth variant of the present embodiment uses the target variable as to whether the test subject is sarcopenia, sarcopenia preparation group or healthy person, and uses the average displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, and the average angle of the ankle joint of one leg during 1% to 50%, 21% to 60%, 71% to 80% and 91% to 100% of a walking cycle as explanatory variables. Fig.35 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0377] Fig.35The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, the average value of the angle of the ankle joint of one leg during 21% to 60% of a walking cycle, the average value of the angle of the ankle joint of one leg during 71% to 80% of a walking cycle, and the average value of the angle of the ankle joint of one leg during 91% to 100% of a walking cycle as explanatory variables. Fig.35 The AUC value of the ROC curve shown is 0.787.

[0378] In the thirteenth variant of the present embodiment, the average value of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the angle of the ankle joint of one leg during 21% to 60% of a gait cycle, the average value of the angle of the ankle joint of one leg during 71% to 80% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle are determined as walking parameters. Furthermore, a prediction model created using as explanatory variables the average value of the vertical displacement of the toe of one leg during 1% to 50% of a gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the angle of the ankle joint of one leg during 21% to 60% of a gait cycle, the average value of the angle of the ankle joint of one leg during 71% to 80% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle is determined as the prediction model used by the sarcopenia judgment unit 113.

[0379] The walking parameter detection unit 112 detects time series data of displacement of the toe portion of one leg in the vertical direction during the first period of the stance period, time series data of the angle of the ankle joint of one leg during the second period of the stance period, time series data of the angle of the ankle joint of one leg during the third period of the stance period, time series data of the angle of the ankle joint of one leg during the fourth period of the foot-in-the-air period, and time series data of the angle of the ankle joint of one leg during the fifth period of the foot-in-the-air period. The first period is a period from 1% to 50% of one walking cycle, the second period is a period from 1% to 10% of one walking cycle, the third period is a period from 21% to 60% of one walking cycle, the fourth period is a period from 71% to 80% of one walking cycle, and the fifth period is a period from 91% to 10% of one walking cycle.

[0380] The walking parameter detection unit 112 detects time series data of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, time series data of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, time series data of the angle of the ankle joint of one leg during 21% to 60% of a walking cycle, time series data of the angle of the ankle joint of one leg during 71% to 80% of a walking cycle, and time series data of the angle of the ankle joint of one leg during 91% to 100% of a walking cycle.

[0381] Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 21% to 60% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 71% to 80% of a walking cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 91% to 100% of a walking cycle.

[0382] The memory 12 pre-stores a prediction model which uses as input values ​​the average value of time series data of displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of time series data of the angle of the ankle joint of one leg during the second period of the stance period, the average value of time series data of the angle of the ankle joint of one leg during the third period of the stance period, the average value of time series data of the angle of the ankle joint of one leg during the fourth period of the foot hanging period, and the average value of time series data of the angle of the ankle joint of one leg during the fifth period of the foot hanging period, and uses as output values ​​whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person.

[0383] The memory 12 pre-stores a prediction model that uses as input values ​​the average value of time series data of displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of time series data of angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of time series data of angle of the ankle joint of one leg during 21% to 60% of a gait cycle, the average value of time series data of angle of the ankle joint of one leg during 71% to 80% of a gait cycle, and the average value of time series data of angle of the ankle joint of one leg during 91% to 100% of a gait cycle, and uses as output values ​​whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person.

[0384] The muscle wasting disease judgment unit 113 judges whether the test subject suffers from muscle wasting disease by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period and the average value of the time series data of the angle of the ankle joint of one leg during the second period, the third period, the fourth period and the fifth period.

[0385] The sarcopenia determination unit 113 determines whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 21% to 60% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 71% to 80% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle.

[0386] The sarcopenia judgment unit 113 inputs into a prediction model the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 21% to 60% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 71% to 80% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle, and obtains a judgment result indicating whether the test subject has sarcopenia, a sarcopenia preparatory group, or a healthy person from the prediction model.

[0387] Thus, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the displacement of the toe of one leg in the vertical direction during the stance period was 0.636, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the ankle joint during the stance period was 0.498, and the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the ankle joint during the foot-in-the-air period was 0.389. Correspondingly, the AUC value obtained by judging the result of sarcopenia from the prediction model created using the displacement of the toe of one leg in the vertical direction during the stance period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period was 0.787.

[0388] Therefore, compared with a prediction model created by using only the vertical displacement of the toe of one leg during the stance period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot hanging period, the prediction model created by using the vertical displacement of the toe of one leg during the stance period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot hanging period can judge muscle wasting disease with high accuracy.

[0389] Next, walking parameters according to a fourteenth modified example of the present embodiment will be described.

[0390] The walking parameters of the fourteenth variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the second period of the foot suspension period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the third period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the stance period and the foot suspension period of one leg, and the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot suspension period of one leg.

[0391] In the fourteenth variation of the present embodiment, similar to the above-mentioned experiment, time series data of displacement of the toe portion of one leg of each of the multiple test subjects in the vertical direction and time series data of angle of the ankle joint of one leg of each of the multiple test subjects are detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. Moreover, in the experiment, one standardized walking cycle is divided into ten intervals, and the average value of displacement of the toe portion of one leg in the vertical direction in one interval or two or more consecutive intervals and the average value of angle of the ankle joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0392] Furthermore, a prediction model was created with the objective variable being whether the test subject was sarcopenia, sarcopenia preparatory group, or healthy person, and the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the second period of the foot-in-the-air period, the average value of the time series data of the angle of the ankle joint of one leg during the third period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the stance period and the foot-in-the-air period, and the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot-in-the-air period as explanatory variables. The first period was a period from 1% to 50% of a walking cycle, the second period was a period from 71% to 100% of a walking cycle, the third period was a period from 1% to 10% of a walking cycle, the fourth period was a period from 51% to 70% of a walking cycle, and the fifth period was a period from 81% to 100% of a walking cycle. The prediction model was evaluated by cross-validation. As the cross-validation, leave-one-out cross-validation was used. Then, the ROC curve of the prediction model for judging the healthy subjects and the sarcopenia candidate group was calculated, and the AUC value of the ROC curve of the prediction model was further calculated.

[0393] Fig.36 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the fourteenth variation of the present embodiment.

[0394] The prediction model of the fourteenth variant of the present embodiment is created by taking the test subject as sarcopenia, sarcopenia preparation group, or healthy person as the target variable, and taking the average displacement of the toe of one leg in the vertical direction during 1% to 50% and 71% to 100% of a walking cycle, and the average angle of the ankle joint of one leg during 1% to 10%, 51% to 70%, and 81% to 100% of a walking cycle as explanatory variables. Fig.36 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0395] Fig.36The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, the average value of the displacement of the toe of one leg in the vertical direction during 71% to 100% of a walking cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, the average value of the angle of the ankle joint of one leg during 51% to 70% of a walking cycle, and the average value of the angle of the ankle joint of one leg during 81% to 100% of a walking cycle as explanatory variables. Fig.36 The AUC value of the ROC curve shown is 0.764.

[0396] In the fourteenth variant of the present embodiment, the average value of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of the displacement of the toe of one leg in the vertical direction during 71% to 100% of a gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the angle of the ankle joint of one leg during 51% to 70% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 81% to 100% of a gait cycle are determined as walking parameters. Furthermore, a prediction model created using as explanatory variables the average value of the vertical displacement of the toe of one leg during 1% to 50% of a gait cycle, the average value of the vertical displacement of the toe of one leg during 71% to 100% of a gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the angle of the ankle joint of one leg during 51% to 70% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 81% to 100% of a gait cycle is determined to be the prediction model used by the sarcopenia judgment unit 113.

[0397] The walking parameter detection unit 112 detects time series data of displacement of the toe portion of one leg in the vertical direction during a first period of the stance period, time series data of displacement of the toe portion of one leg in the vertical direction during a second period of the foot-in-the-air period, time series data of angle of the ankle joint of one leg during a third period of the stance period, time series data of angle of the ankle joint of one leg during a fourth period of the stance period and the foot-in-the-air period, and time series data of angle of the ankle joint of one leg during a fifth period of the foot-in-the-air period. The first period is a period from 1% to 50% of one walking cycle, the second period is a period from 71% to 100% of one walking cycle, the third period is a period from 1% to 10% of one walking cycle, the fourth period is a period from 51% to 70% of one walking cycle, and the fifth period is a period from 81% to 100% of one walking cycle.

[0398] The walking parameter detection unit 112 detects time series data of displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, time series data of displacement of the toe of one leg in the vertical direction during 71% to 100% of a walking cycle, time series data of angle of the ankle joint of one leg during 1% to 10% of a walking cycle, time series data of angle of the ankle joint of one leg during 51% to 70% of a walking cycle, and time series data of angle of the ankle joint of one leg during 81% to 100% of a walking cycle.

[0399] Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a walking cycle, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 71% to 100% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 51% to 70% of a walking cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 81% to 100% of a walking cycle.

[0400] The memory 12 pre-stores a prediction model which uses as input values ​​the average value of time series data of displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of time series data of displacement of the toe of one leg in the vertical direction during the second period of the foot hanging period, the average value of time series data of the angle of the ankle joint of one leg during the third period of the stance period, the average value of time series data of the angle of the ankle joint of one leg during the fourth period of the stance period and the foot hanging period, and the average value of time series data of the angle of the ankle joint of one leg during the fifth period of the foot hanging period, and takes as output values ​​whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person.

[0401] The memory 12 pre-stores a prediction model that uses as input values ​​the average value of time series data of displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of time series data of displacement of the toe of one leg in the vertical direction during 71% to 100% of a gait cycle, the average value of time series data of angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of time series data of angle of the ankle joint of one leg during 51% to 70% of a gait cycle, and the average value of time series data of angle of the ankle joint of one leg during 81% to 100% of a gait cycle, and uses as output values ​​whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person.

[0402] The muscle wasting disease judgment unit 113 judges whether the test subject has muscle wasting disease by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period and the second period and the average value of the time series data of the angle of the ankle joint of one leg during the third period, the fourth period and the fifth period.

[0403] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia, a sarcopenia preparation group, or a healthy person by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 71% to 100% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 51% to 70% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 81% to 100% of a gait cycle.

[0404] The sarcopenia judgment unit 113 inputs into a prediction model an average value of time series data of displacement of the toe of one leg in the vertical direction during 1% to 50% of a gait cycle, an average value of time series data of displacement of the toe of one leg in the vertical direction during 71% to 100% of a gait cycle, an average value of time series data of angle of the ankle joint of one leg during 1% to 10% of a gait cycle, an average value of time series data of angle of the ankle joint of one leg during 51% to 70% of a gait cycle, and an average value of time series data of angle of the ankle joint of one leg during 81% to 100% of a gait cycle, and obtains a judgment result indicating whether the test subject has sarcopenia, a sarcopenia preparatory group, or a healthy person from the prediction model.

[0405] Thus, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the displacement of the toe of one leg in the vertical direction during the stance period was 0.560, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the displacement of the toe of one leg in the vertical direction during the foot-in-the-air period was 0.626, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the ankle joint during the stance period was 0.610, and the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the ankle joint during the foot-in-the-air period was 0.622. Correspondingly, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using the displacement of the toe of one leg in the vertical direction during the stance period, the displacement of the toe of one leg in the vertical direction during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period was 0.764.

[0406] Therefore, compared with the prediction model created by using only the vertical displacement of the toe of one leg during the stance period, the vertical displacement of the toe of one leg during the foot-in-the-air period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot-in-the-air period, the prediction model created by using the vertical displacement of the toe of one leg during the stance period, the vertical displacement of the toe of one leg during the foot-in-the-air period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot-in-the-air period can judge the muscle wasting preparation population with high accuracy.

[0407] Next, walking parameters according to a fifteenth modified example of the present embodiment will be described.

[0408] The walking parameter of the fifteenth variant of the present embodiment may also be the average value of the time series data of the angle of the knee joint of one leg during the first period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the second period of the foot of one leg in the air, the average value of the time series data of the angle of the knee joint of one leg during the third period of the foot of one leg in the air, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot of one leg in the air, and the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the foot of one leg in the air.

[0409] In the fifteenth variation of the present embodiment, as in the above-mentioned experiment, time series data of the angle of the knee joint of one leg of each of the multiple test subjects and time series data of the angle of the ankle joint of one leg of each of the multiple test subjects are detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. Furthermore, in the experiment, one standardized walking cycle is divided into ten intervals, and the average value of the angle of the knee joint of one leg in one interval or two or more consecutive intervals and the average value of the angle of the ankle joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0410] Furthermore, a prediction model is created with the target variable being whether the test subject is sarcopenia, a sarcopenia preparatory group, or a healthy person, and the average value of the time series data of the angle of the knee joint of one leg in the first period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the second period of the foot-in-the-air period, the average value of the time series data of the angle of the knee joint of one leg in the third period of the foot-in-the-air period, the average value of the time series data of the angle of the ankle joint of one leg in the fourth period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg in the fifth period of the foot-in-the-air period, and the average value of the time series data of the angle of the ankle joint of one leg in the sixth period of the foot-in-the-air period as explanatory variables. The first period is a period from 1% to 40% of one walking cycle, the second period is a period from 61% to 70% of one walking cycle, the third period is a period from 81% to 100% of one walking cycle, the fourth period is a period from 1% to 50% of one walking cycle, the fifth period is a period from 61% to 70% of one walking cycle, and the sixth period is a period from 91% to 100% of one walking cycle. The prediction model was evaluated by cross validation. Leave-one-out cross validation was used as cross validation. In addition, the ROC curve of the prediction model for healthy people and sarcopenia was calculated. Furthermore, the AUC value of the ROC curve of the prediction model was calculated.

[0411] Fig.37 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the fifteenth variation of the present embodiment.

[0412] The prediction model of the fifteenth variant of the present embodiment uses the target variable as to whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person, and uses the average value of the angle of the knee joint of one leg during 1% to 40%, 61% to 70%, and 81% to 100% of a walking cycle, and the average value of the angle of the ankle joint of one leg during 1% to 50%, 61% to 70%, and 91% to 100% of a walking cycle as explanatory variables. Fig.37 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0413] Fig.37The ROC curve shown is a curve depicting the true positive rate and false positive rate of a prediction model created using the average value of the angle of the knee joint of one leg during 1% to 40% of a walking cycle, the average value of the angle of the knee joint of one leg during 61% to 70% of a walking cycle, the average value of the angle of the knee joint of one leg during 81% to 100% of a walking cycle, the average value of the angle of the ankle joint of one leg during 1% to 50% of a walking cycle, the average value of the angle of the ankle joint of one leg during 61% to 70% of a walking cycle, and the average value of the angle of the ankle joint of one leg during 91% to 100% of a walking cycle as explanatory variables. Fig.37 The AUC value of the ROC curve shown is 0.865.

[0414] In the fifteenth variant of the present embodiment, an average value of the angle of the knee joint of one leg during 1% to 40% of a gait cycle, an average value of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, an average value of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, an average value of the angle of the ankle joint of one leg during 1% to 50% of a gait cycle, an average value of the angle of the ankle joint of one leg during 61% to 70% of a gait cycle, and an average value of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle are determined as walking parameters. Furthermore, a prediction model created using as explanatory variables the average value of the angles of the knee joint of one leg during 1% to 40% of a gait cycle, the average value of the angles of the knee joint of one leg during 61% to 70% of a gait cycle, the average value of the angles of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of the angles of the ankle joint of one leg during 1% to 50% of a gait cycle, the average value of the angles of the ankle joint of one leg during 61% to 70% of a gait cycle, and the average value of the angles of the ankle joint of one leg during 91% to 100% of a gait cycle.

[0415] The walking parameter detection unit 112 detects time series data of the angle of the knee joint of one leg in a first period of the stance period, time series data of the angle of the knee joint of one leg in a second period of the foot-in-the-air period, time series data of the angle of the knee joint of one leg in a third period of the foot-in-the-air period, time series data of the angle of the ankle joint of one leg in a fourth period of the stance period, time series data of the angle of the ankle joint of one leg in a fifth period of the foot-in-the-air period, and time series data of the angle of the ankle joint of one leg in a sixth period of the foot-in-the-air period. The first period is a period from 1% to 40% of one walking cycle, the second period is a period from 61% to 70% of one walking cycle, the third period is a period from 81% to 100% of one walking cycle, the fourth period is a period from 1% to 50% of one walking cycle, the fifth period is a period from 61% to 70% of one walking cycle, and the sixth period is a period from 91% to 100% of one walking cycle.

[0416] The walking parameter detection unit 112 detects time series data of the angle of the knee joint of one leg during 1% to 40% of a walking cycle, time series data of the angle of the knee joint of one leg during 61% to 70% of a walking cycle, time series data of the angle of the knee joint of one leg during 81% to 100% of a walking cycle, time series data of the angle of the ankle joint of one leg during 1% to 50% of a walking cycle, time series data of the angle of the ankle joint of one leg during 61% to 70% of a walking cycle, and time series data of the angle of the ankle joint of one leg during 91% to 100% of a walking cycle.

[0417] Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the angle of the knee joint of one leg during 1% to 40% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 61% to 70% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 50% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 61% to 70% of a walking cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 91% to 100% of a walking cycle.

[0418] The memory 12 pre-stores a prediction model which uses the average value of the time series data of the angle of the knee joint of one leg during the first period of the stance period, the average value of the time series data of the angle of the knee joint of one leg during the second period of the foot hanging period, the average value of the time series data of the angle of the knee joint of one leg during the third period of the foot hanging period, the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the foot hanging period, and the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the foot hanging period as input values ​​and takes as the output value whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person.

[0419] The memory 12 pre-stores a prediction model that uses as input values ​​the average value of time series data of the angle of the knee joint of one leg during 1% to 40% of a gait cycle, the average value of time series data of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, the average value of time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of time series data of the angle of the ankle joint of one leg during 1% to 50% of a gait cycle, the average value of time series data of the angle of the ankle joint of one leg during 61% to 70% of a gait cycle, and the average value of time series data of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle, and uses as output values ​​the average value of time series data of the angle of the knee joint of one leg during 1% to 50% of a gait cycle, the average value of time series data of the angle of the ankle joint of one leg during 61% to 70% of a gait cycle, and the average value of time series data of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle.

[0420] The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the angle of the knee joint of one leg in the first period, the second period and the third period and the average value of the time series data of the angle of the ankle joint of one leg in the fourth period, the fifth period and the sixth period.

[0421] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia, a sarcopenia preparatory group, or a healthy person by using the average value of the time series data of the angle of the knee joint of one leg during 1% to 40% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 50% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 61% to 70% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle.

[0422] The sarcopenia judgment unit 113 inputs the average value of the time series data of the angle of the knee joint of one leg during 1% to 40% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 61% to 70% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 50% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 61% to 70% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle into a prediction model, and obtains a judgment result indicating whether the test subject has sarcopenia, a sarcopenia preparatory group, or a healthy person from the prediction model.

[0423] Thus, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the knee joint of one leg in the stance phase was 0.586, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the knee joint of one leg in the foot-in-the-air phase was 0.699, the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the ankle joint in the stance phase was 0.498, and the AUC value obtained by judging the result of sarcopenia from the prediction model created using only the angle of the ankle joint in the foot-in-the-air phase was 0.389. Correspondingly, the AUC value obtained by judging the result of sarcopenia from the prediction model created using the angle of the knee joint of one leg in the stance phase, the angle of the knee joint of one leg in the foot-in-the-air phase, the angle of the ankle joint of one leg in the stance phase, and the angle of the ankle joint of one leg in the foot-in-the-air phase was 0.865.

[0424] Therefore, compared with a prediction model created using only the angle of the knee joint of one leg in the stance period, the angle of the knee joint of one leg in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period, the prediction model created using the angle of the knee joint of one leg in the stance period, the angle of the knee joint of one leg in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period can judge muscle wasting disease with high accuracy.

[0425] Next, walking parameters according to a sixteenth modification of the present embodiment will be described.

[0426] The walking parameter of the sixteenth variant of the present embodiment may also be the average value of the time series data of the angle of the knee joint of one leg during the first period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the second period of the foot of one leg in the air, the average value of the time series data of the angle of the ankle joint of one leg during the third period of the stance period of one leg, and the average value of the time series data of the angle of the ankle joint of one leg during the fourth period of the stance period and the foot in the air.

[0427] In the sixteenth variation of the present embodiment, similar to the above-mentioned experiment, time series data of the angle of the knee joint of one leg of each of the multiple test subjects and time series data of the angle of the ankle joint of one leg of each of the multiple test subjects are detected from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. Moreover, in the experiment, one standardized walking cycle is divided into ten intervals, and the average value of the angle of the knee joint of one leg in one interval or two or more consecutive intervals and the average value of the angle of the ankle joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0428] Furthermore, a prediction model was created with the target variable being whether the test subject was sarcopenia, a sarcopenia candidate group, or a healthy person, and the average value of the time series data of the angle of the knee joint of one leg in the first period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the second period of the foot-in-the-air period, the average value of the time series data of the angle of the ankle joint of one leg in the third period of the stance period, and the average value of the time series data of the angle of the ankle joint of one leg in the fourth period of the stance period and the foot-in-the-air period as explanatory variables. The first period was a period from 1% to 10% of a walking cycle, the second period was a period from 81% to 100% of a walking cycle, the third period was a period from 1% to 10% of a walking cycle, and the fourth period was a period from 21% to 70% of a walking cycle. The prediction model was evaluated by cross-validation. As cross-validation, leave-one-out cross-validation was used. Furthermore, the ROC curve of the prediction model for judging the healthy person and the sarcopenia candidate group was calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0429] Fig.38 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the sixteenth variation of the present embodiment.

[0430] The prediction model of the sixteenth variant of the present embodiment uses the target variable as to whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person, and uses the average value of the angle of the knee joint of one leg during 1% to 10% and 81% to 100% of a walking cycle and the average value of the angle of the ankle joint of one leg during 1% to 10% and 21% to 70% of a walking cycle as explanatory variables. Fig.38 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0431] Fig.38 The ROC curve shown is a curve depicting the true positive rate and false positive rate of a prediction model created using the average value of the angle of the knee joint of one leg during 1% to 10% of a walking cycle, the average value of the angle of the knee joint of one leg during 81% to 100% of a walking cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, and the average value of the angle of the ankle joint of one leg during 21% to 70% of a walking cycle as explanatory variables. Fig.38The AUC value of the ROC curve shown is 0.743.

[0432] In the sixteenth variation of the present embodiment, the average value of the angle of the knee joint of one leg during 1% to 10% of one gait cycle, the average value of the angle of the knee joint of one leg during 81% to 100% of one gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of one gait cycle, and the average value of the angle of the ankle joint of one leg during 21% to 70% of one gait cycle are determined as walking parameters. Furthermore, a prediction model created using the average value of the angle of the knee joint of one leg during 1% to 10% of one gait cycle, the average value of the angle of the knee joint of one leg during 81% to 100% of one gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 10% of one gait cycle, and the average value of the angle of the ankle joint of one leg during 21% to 70% of one gait cycle as explanatory variables is determined as the prediction model used by the sarcopenia determination unit 113.

[0433] The walking parameter detection unit 112 detects time series data of the angle of the knee joint of one leg in a first period of the stance period, time series data of the angle of the knee joint of one leg in a second period of the foot-in-the-air period, time series data of the angle of the ankle joint of one leg in a third period of the stance period, and time series data of the angle of the ankle joint of one leg in a fourth period of the stance period and the foot-in-the-air period. The first period is a period of 1% to 10% of one walking cycle, the second period is a period of 81% to 100% of one walking cycle, the third period is a period of 1% to 10% of one walking cycle, and the fourth period is a period of 21% to 70% of one walking cycle.

[0434] The walking parameter detection unit 112 detects time series data of the angle of the knee joint of one leg during 1% to 10% of a walking cycle, time series data of the angle of the knee joint of one leg during 81% to 100% of a walking cycle, time series data of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, and time series data of the angle of the ankle joint of one leg during 21% to 70% of a walking cycle.

[0435] Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the angle of the knee joint of one leg during 1% to 10% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a walking cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 21% to 70% of a walking cycle.

[0436] The memory 12 pre-stores a prediction model which uses the average value of the time series data of the angle of the knee joint of one leg in the first period of the stance period, the average value of the time series data of the angle of the knee joint of one leg in the second period of the foot hanging period, the average value of the time series data of the angle of the ankle joint of one leg in the third period of the stance period, and the average value of the time series data of the angle of the ankle joint of one leg in the fourth period of the stance period and the foot hanging period as input values, and uses as an output value whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person.

[0437] The memory 12 pre-stores a prediction model that uses the average value of time series data of the angle of the knee joint of one leg during 1% to 10% of a gait cycle, the average value of time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of time series data of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, and the average value of time series data of the angle of the ankle joint of one leg during 21% to 70% of a gait cycle as input values, and uses as an output value whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person.

[0438] The sarcopenia determination unit 113 determines whether the test subject suffers from sarcopenia by using the average value of the time series data of the angle of the knee joint of one leg in the first period and the second period and the average value of the time series data of the angle of the ankle joint of one leg in the third period and the fourth period.

[0439] The sarcopenia determination unit 113 determines whether the test subject has sarcopenia, a sarcopenia preparation group, or a healthy person by using the average value of the time series data of the angle of the knee joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 21% to 70% of a gait cycle.

[0440] The sarcopenia judgment unit 113 inputs the average value of the time series data of the angle of the knee joint of one leg during 1% to 10% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 81% to 100% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 10% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 21% to 70% of a gait cycle into a prediction model, and obtains a judgment result indicating whether the test subject has sarcopenia, a sarcopenia preparatory group, or a healthy person from the prediction model.

[0441] Thus, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the knee joint of one leg in the stance phase was 0.537, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the knee joint of one leg in the foot-free phase was 0.604, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the ankle joint in the stance phase was 0.610, and the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using only the angle of the ankle joint in the foot-free phase was 0.622. Correspondingly, the AUC value obtained by judging the results of the sarcopenia preparation population from the prediction model created using the angle of the knee joint of one leg in the stance phase, the angle of the knee joint of one leg in the foot-free phase, the angle of the ankle joint of one leg in the stance phase, and the angle of the ankle joint of one leg in the foot-free phase was 0.743.

[0442] Therefore, compared with the prediction model created by using only the angle of the knee joint of one leg in the stance period, the angle of the knee joint of one leg in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period, the prediction model created by using the angle of the knee joint of one leg in the stance period, the angle of the knee joint of one leg in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period can judge the sarcopenia preparation population with high accuracy.

[0443] Next, walking parameters according to a seventeenth modification of the present embodiment will be described.

[0444] The walking parameter of the seventeenth variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the second period of the stance period of one leg, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the third period of the foot suspended period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the fifth period of the stance period of one leg and the foot suspended period, the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the stance period of one leg, and the average value of the time series data of the angle of the ankle joint of one leg during the seventh period of the stance period of one leg and the foot suspended period.

[0445] The seventeenth variation of the present embodiment is similar to the above-mentioned experiment, and detects the time series data of the displacement of the toe of one leg of each of the multiple test subjects in the vertical direction, the time series data of the angle of the knee joint of one leg of each of the multiple test subjects, and the time series data of the angle of the ankle joint of one leg of each of the multiple test subjects from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. In addition, in the experiment, a standardized walking cycle is divided into ten intervals, and the average value of the displacement of the toe of one leg in the vertical direction in one interval or two or more consecutive intervals, the average value of the angle of the knee joint of one leg in one interval or two or more consecutive intervals, and the average value of the angle of the ankle joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0446] Furthermore, a prediction model is created with the target variable being whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person, and with the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the second period of the stance period, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the third period of the foot hanging period, the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the stance period, the average value of the time series data of the angle of the knee joint of one leg during the fifth period of the stance period and the foot hanging period, the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the stance period, and the average value of the time series data of the angle of the ankle joint of one leg during the seventh period of the stance period and the foot hanging period as explanatory variables. The first period is a period from 21% to 30% of a walking cycle, the second period is a period from 51% to 60% of a walking cycle, the third period is a period from 81% to 100% of a walking cycle, the fourth period is a period from 11% to 20% of a walking cycle, the fifth period is a period from 41% to 80% of a walking cycle, the sixth period is a period from 1% to 20% of a walking cycle, and the seventh period is a period from 51% to 80% of a walking cycle. The prediction model was evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation was used. In addition, the ROC curve of the prediction model for judging healthy people and sarcopenia was calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0447] Fig.39 It is a schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and those with sarcopenia using the prediction model of the seventeenth variation of the present embodiment.

[0448] The prediction model of the seventeenth variant of the present embodiment is created by taking as the target variable whether the test subject is sarcopenia, sarcopenia preparation group or healthy person, and taking as the explanatory variables the average displacement of the toe of one leg in the vertical direction during 21% to 30%, 51% to 60% and 81% to 100% of a gait cycle, the average angle of the knee joint of one leg during 11% to 20% and 41% to 80% of a gait cycle, and the average angle of the ankle joint of one leg during 1% to 20% and 51% to 80% of a gait cycle. Fig.39 In the graph, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects with sarcopenia as having sarcopenia, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects who are healthy as having sarcopenia.

[0449] Fig.39 The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the displacement of the toe of one leg in the vertical direction during 21% to 30% of a gait cycle, the average value of the displacement of the toe of one leg in the vertical direction during 51% to 60% of a gait cycle, the average value of the displacement of the toe of one leg in the vertical direction during 81% to 100% of a gait cycle, the average value of the angle of the knee joint of one leg during 11% to 20% of a gait cycle, the average value of the angle of the knee joint of one leg during 41% to 80% of a gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 20% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 51% to 80% of a gait cycle as explanatory variables. Fig.39 The AUC value of the ROC curve shown is 0.881.

[0450] In the seventeenth variant of the present embodiment, an average value of the displacement of the toe of one leg in the vertical direction during 21% to 30% of a gait cycle, an average value of the displacement of the toe of one leg in the vertical direction during 51% to 60% of a gait cycle, an average value of the displacement of the toe of one leg in the vertical direction during 81% to 100% of a gait cycle, an average value of the angle of the knee joint of one leg during 11% to 20% of a gait cycle, an average value of the angle of the knee joint of one leg during 41% to 80% of a gait cycle, an average value of the angle of the ankle joint of one leg during 1% to 20% of a gait cycle, and an average value of the angle of the ankle joint of one leg during 51% to 80% of a gait cycle are determined as walking parameters.

[0451] Furthermore, a prediction model created using as explanatory variables the average value of the vertical displacement of the toe of one leg during 21% to 30% of a gait cycle, the average value of the vertical displacement of the toe of one leg during 51% to 60% of a gait cycle, the average value of the vertical displacement of the toe of one leg during 81% to 100% of a gait cycle, the average value of the angle of the knee joint of one leg during 11% to 20% of a gait cycle, the average value of the angle of the knee joint of one leg during 41% to 80% of a gait cycle, the average value of the angle of the ankle joint of one leg during 1% to 20% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 51% to 80% of a gait cycle, is determined as the prediction model used by the sarcopenia judgment unit 113.

[0452] The walking parameter detection unit 112 detects time series data of displacement of the toe of one leg in the vertical direction during the first period of the stance period, time series data of displacement of the toe of one leg in the vertical direction during the second period of the stance period, time series data of displacement of the toe of one leg in the vertical direction during the third period of the foot hanging period, time series data of the angle of the knee joint of one leg during the fourth period of the stance period, time series data of the angle of the knee joint of one leg during the fifth period of the stance period and the foot hanging period, time series data of the angle of the ankle joint of one leg during the sixth period of the stance period, and time series data of the angle of the ankle joint of one leg during the seventh period of the stance period and the foot hanging period. The first period is a period from 21% to 30% of a walking cycle, the second period is a period from 51% to 60% of a walking cycle, the third period is a period from 81% to 100% of a walking cycle, the fourth period is a period from 11% to 20% of a walking cycle, the fifth period is a period from 41% to 80% of a walking cycle, the sixth period is a period from 1% to 20% of a walking cycle, and the seventh period is a period from 51% to 80% of a walking cycle.

[0453] The walking parameter detection unit 112 detects time series data of displacement of the toe of one leg in the vertical direction during 21% to 30% of a walking cycle, time series data of displacement of the toe of one leg in the vertical direction during 51% to 60% of a walking cycle, time series data of displacement of the toe of one leg in the vertical direction during 81% to 100% of a walking cycle, time series data of angle of the knee joint of one leg during 11% to 20% of a walking cycle, time series data of angle of the knee joint of one leg during 41% to 80% of a walking cycle, time series data of angle of the ankle joint of one leg during 1% to 20% of a walking cycle, and time series data of angle of the ankle joint of one leg during 51% to 80% of a walking cycle.

[0454] Furthermore, the walking parameter detection unit 112 calculates the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 21% to 30% of a walking cycle, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 51% to 60% of a walking cycle, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 81% to 100% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 11% to 20% of a walking cycle, the average value of the time series data of the angle of the knee joint of one leg during 41% to 80% of a walking cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 20% of a walking cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 51% to 80% of a walking cycle.

[0455] The memory 12 pre-stores a prediction model which uses as input values ​​the average value of time series data of displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of time series data of displacement of the toe of one leg in the vertical direction during the second period of the stance period, the average value of time series data of displacement of the toe of one leg in the vertical direction during the third period of the foot hanging period, the average value of time series data of angle of the knee joint of one leg during the fourth period of the stance period, the average value of time series data of angle of the knee joint of one leg during the fifth period of the stance period and the foot hanging period, the average value of time series data of angle of the ankle joint of one leg during the sixth period of the stance period, and the average value of time series data of angle of the ankle joint of one leg during the seventh period of the stance period and the foot hanging period, and takes as output values ​​whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person.

[0456] The memory 12 pre-stores a prediction model which uses as input values ​​an average value of time series data of displacement of the toe of one leg in the vertical direction during 21% to 30% of a gait cycle, an average value of time series data of displacement of the toe of one leg in the vertical direction during 51% to 60% of a gait cycle, an average value of time series data of displacement of the toe of one leg in the vertical direction during 81% to 100% of a gait cycle, an average value of time series data of angle of the knee joint of one leg during 11% to 20% of a gait cycle, an average value of time series data of angle of the knee joint of one leg during 41% to 80% of a gait cycle, an average value of time series data of angle of the ankle joint of one leg during 1% to 20% of a gait cycle, and an average value of time series data of angle of the ankle joint of one leg during 51% to 80% of a gait cycle, and uses as output values ​​an average value of time series data of displacement of the toe of one leg in the vertical direction during 51% to 80% of a gait cycle of the test subject, and generates a prediction model.

[0457] The muscle wasting disease judging unit 113 judges whether the test subject suffers from muscle wasting disease by using the average value of the time series data of the displacement of the toe part of one leg in the vertical direction in the first period, the second period and the third period, the average value of the time series data of the angle of the knee joint of one leg in the fourth period and the fifth period, and the average value of the time series data of the angle of the ankle joint of one leg in the sixth period and the seventh period.

[0458] The sarcopenia determination unit 113 determines whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person by using the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 21% to 30% of a gait cycle, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 51% to 60% of a gait cycle, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during 81% to 100% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 11% to 20% of a gait cycle, the average value of the time series data of the angle of the knee joint of one leg during 41% to 80% of a gait cycle, the average value of the time series data of the angle of the ankle joint of one leg during 1% to 20% of a gait cycle, and the average value of the time series data of the angle of the ankle joint of one leg during 51% to 80% of a gait cycle.

[0459] The sarcopenia judgment unit 113 inputs into a prediction model an average value of time series data of vertical displacement of the toe of one leg during 21% to 30% of a gait cycle, an average value of time series data of vertical displacement of the toe of one leg during 51% to 60% of a gait cycle, an average value of time series data of vertical displacement of the toe of one leg during 81% to 100% of a gait cycle, an average value of time series data of angle of the knee joint of one leg during 11% to 20% of a gait cycle, an average value of time series data of angle of the knee joint of one leg during 41% to 80% of a gait cycle, an average value of time series data of angle of the ankle joint of one leg during 1% to 20% of a gait cycle, and an average value of time series data of angle of the ankle joint of one leg during 51% to 80% of a gait cycle, and obtains a judgment result indicating whether the test subject is sarcopenia, sarcopenia preparatory group, or healthy person from the prediction model.

[0460] Thus, the AUC value obtained by judging the result of muscle wasting from the prediction model created only by using the displacement of the toe of one leg in the vertical direction during the stance period was 0.636, the AUC value obtained by judging the result of muscle wasting from the prediction model created only by using the displacement of the toe of one leg in the vertical direction during the foot suspension period was 0.514, the AUC value obtained by judging the result of muscle wasting from the prediction model created only by using the angle of the knee joint during the stance period was 0.586, the AUC value obtained by judging the result of muscle wasting from the prediction model created only by using the angle of the knee joint during the foot suspension period was 0.699, the AUC value obtained by judging the result of muscle wasting from the prediction model created only by using the angle of the ankle joint during the stance period was 0.498, and the AUC value obtained by judging the result of muscle wasting from the prediction model created only by using the angle of the ankle joint during the foot suspension period was 0.389.

[0461] Correspondingly, the AUC value obtained by judging the result of muscle wasting disease from the prediction model created by using the displacement of the toe of one leg in the vertical direction during the first and second periods of the stance period, the displacement of the toe of one leg in the vertical direction during the third period of the foot hanging period, the angle of the knee joint of one leg in the fourth period of the stance period, the angle of the knee joint of one leg in the fifth period of the stance period and the foot hanging period, the angle of the ankle joint of one leg in the sixth period of the stance period, and the angle of the ankle joint of one leg in the seventh period of the stance period and the foot hanging period was 0.881.

[0462] Therefore, compared with a prediction model created using only the vertical displacement of the toe of one leg during the stance period, the vertical displacement of the toe of one leg during the foot-in-the-air period, the angle of the knee joint of one leg during the stance period, the angle of the knee joint of one leg during the foot-in-the-air period, the angle of the ankle joint of one leg during the stance period, and the angle of the ankle joint of one leg during the foot-in-the-air period, a prediction model created using the vertical displacement of the toe of one leg during the first and second periods of the stance period, the vertical displacement of the toe of one leg during the third period of the foot-in-the-air period, the angle of the knee joint of one leg during the fourth period of the stance period, the angle of the knee joint of one leg during the fifth period of the stance period and the foot-in-the-air period, the angle of the ankle joint of one leg during the sixth period of the stance period, and the angle of the ankle joint of one leg during the seventh period of the stance period and the foot-in-the-air period can judge muscle wasting disease with high accuracy.

[0463] Next, walking parameters according to an eighteenth modified example of the present embodiment will be described.

[0464] The walking parameters of the eighteenth variant of the present embodiment may also be the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period of one leg, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the second period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the third period of the stance period of one leg, the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the foot of one leg in the air, the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the stance period of one leg, the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the stance period and the foot in the air, and the average value of the time series data of the angle of the ankle joint of one leg during the seventh period of the foot in the air.

[0465] The eighteenth variation of the present embodiment is similar to the above-mentioned experiment, and detects the time series data of the displacement of the toe of one leg of each of the multiple test subjects in the vertical direction, the time series data of the angle of the knee joint of one leg of each of the multiple test subjects, and the time series data of the angle of the ankle joint of one leg of each of the multiple test subjects from the skeletal data of multiple test subjects including the test subjects with sarcopenia, the test subjects of the sarcopenia preparatory population, and the test subjects of the healthy subjects. In addition, in the experiment, a standardized walking cycle is divided into ten intervals, and the average value of the displacement of the toe of one leg in the vertical direction in one interval or two or more consecutive intervals, the average value of the angle of the knee joint of one leg in one interval or two or more consecutive intervals, and the average value of the angle of the ankle joint of one leg in one interval or two or more consecutive intervals are calculated for each test subject.

[0466] Furthermore, a prediction model is created with the target variable being whether the test subject is sarcopenia, a sarcopenia preparation group, or a healthy person, and with the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the first period of the stance period, the average value of the time series data of the displacement of the toe of one leg in the vertical direction during the second period of the stance period, the average value of the time series data of the angle of the knee joint of one leg during the third period of the stance period, the average value of the time series data of the angle of the knee joint of one leg during the fourth period of the foot-in-the-air period, the average value of the time series data of the angle of the ankle joint of one leg during the fifth period of the stance period, the average value of the time series data of the angle of the ankle joint of one leg during the sixth period of the stance period and the foot-in-the-air period, and the average value of the time series data of the angle of the ankle joint of one leg during the seventh period of the foot-in-the-air period as explanatory variables. The first period is a period from 11% to 20% of a walking cycle, the second period is a period from 41% to 60% of a walking cycle, the third period is a period from 41% to 50% of a walking cycle, the fourth period is a period from 61% to 100% of a walking cycle, the fifth period is a period from 11% to 20% of a walking cycle, the sixth period is a period from 31% to 70% of a walking cycle, and the seventh period is a period from 91% to 100% of a walking cycle. The prediction model was evaluated by cross-validation. As a cross-validation, leave-one-out cross-validation was used. In addition, the ROC curve of the prediction model for judging healthy people and sarcopenia preparation population was calculated. The AUC value of the ROC curve of the prediction model was further calculated.

[0467] Fig.40 Schematic diagram showing an ROC curve obtained from the results of judging healthy subjects and a sarcopenia candidate population using the prediction model of the eighteenth modification example of the present embodiment.

[0468] The prediction model of the eighteenth variant of the present embodiment uses the target variable as to whether the test subject is sarcopenia, sarcopenia preparation group, or healthy person, and uses the average displacement of the toe of one leg in the vertical direction during 11% to 20% and 41% to 60% of a gait cycle, the average angle of the knee joint of one leg during 41% to 50% and 61% to 100% of a gait cycle, and the average angle of the ankle joint of one leg during 11% to 20%, 31% to 70%, and 91% to 100% of a gait cycle as explanatory variables. Fig.40 In the figure, the vertical axis represents the true positive rate and the horizontal axis represents the false positive rate. The true positive rate represents the rate at which the prediction model correctly judges the test subjects of the sarcopenia candidate population as the sarcopenia candidate population, and the false positive rate represents the rate at which the prediction model incorrectly judges the test subjects of healthy people as the sarcopenia candidate population.

[0469] Fig.40 The ROC curve shown is a curve depicting the true positive rate and false positive rate of the prediction model, which is created using the average value of the displacement of the toe of one leg in the vertical direction during 11% to 20% of a gait cycle, the average value of the displacement of the toe of one leg in the vertical direction during 41% to 60% of a gait cycle, the average value of the angle of the knee joint of one leg during 41% to 50% of a gait cycle, the average value of the angle of the knee joint of one leg during 61% to 100% of a gait cycle, the average value of the angle of the ankle joint of one leg during 11% to 20% of a gait cycle, the average value of the angle of the ankle joint of one leg during 31% to 70% of a gait cycle, and the average value of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle as explanatory variables. Fig.40 The AUC value of the ROC curve shown is 0.861.

[0470] In the eighteenth variant of the present embodiment, an average value of the displacement of the toe of one leg in the vertical direction during 11% to 20% of a gait cycle, an average value of the displacement of the toe of one leg in the vertical direction during 41% to 60% of a gait cycle, an average value of the angle of the knee joint of one leg during 41% to 50% of a gait cycle, an average value of the angle of the knee joint of one leg during 61% to 100% of a gait cycle, an average value of the angle of the ankle joint of one leg during 11% to 20% of a gait cycle, an average value of the angle of the ankle joint of one leg during 31% to 70% of a gait cycle, and an average value of the angle of the ankle joint of one leg during 91% to 100% of a gait cycle are determined as w...

Claims

1. A sarcopenia assessment device for assessing sarcopenia based on the walking movements of a test subject, characterized in that include: an acquisition unit, which acquires walking data related to the walking of the test subject; a detection unit, based on the walking data, detecting at least one of an angle of a knee joint of one leg of the test subject during a stance period of the one leg, a displacement of a toe portion of the one leg in a vertical direction during the stance period, a displacement of the toe portion of the one leg in a vertical direction during a foot-in-the-air period, an angle of an ankle joint of the one leg during the stance period, and an angle of the ankle joint of the one leg during the foot-in-the-air period; as well as, The judging unit judges whether the test subject has sarcopenia by using at least one of the angle of the knee joint in the stance phase, the displacement of the toe portion in the vertical direction in the stance phase, the displacement of the toe portion in the vertical direction in the foot-suspended phase, the angle of the ankle joint in the stance phase, and the angle of the ankle joint in the foot-suspended phase, The detection unit detects time series data of a predetermined period of at least one of the parameters, The determination unit determines whether the test subject suffers from sarcopenia using an average value of the time series data.

2. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the angle of the knee joint during a predetermined period of the foot-in-the-air period, The determination unit determines whether the test subject suffers from the sarcopenia by using an average value of the time series data of the angle of the knee joint.

3. The sarcopenia assessment device according to claim 2, characterized in that: The period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one walking cycle, and when the one walking cycle is represented by 1% to 100%, The predetermined period is a period from 61% to 100% of the one walking cycle.

4. The sarcopenia assessment device according to claim 1, wherein: The detection unit detects time series data of the angle of the knee joint during a predetermined period of the stance phase, The determination unit determines whether the test subject suffers from the sarcopenia by using an average value of the time series data of the angle of the knee joint.

5. The sarcopenia assessment device according to claim 4, characterized in that: The period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one walking cycle, and when the one walking cycle is represented by 1% to 100%, The predetermined period is a period from 50% to 60% of the one walking cycle.

6. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the displacement of the toe portion in the vertical direction during a predetermined period of the stance phase, The determination unit determines whether the test subject suffers from the sarcopenia by using an average value of the time series data of the displacement of the toe portion in the vertical direction.

7. The sarcopenia assessment device according to claim 6, characterized in that: The period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one walking cycle, and when the one walking cycle is represented by 1% to 100%, The predetermined period is a period from 1% to 60% of the one walking cycle.

8. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the displacement of the toe portion in the vertical direction during a predetermined period of the foot-in-the-air period, The determination unit determines whether the test subject suffers from the sarcopenia by using an average value of the time series data of the displacement of the toe portion in the vertical direction.

9. The sarcopenia assessment device according to claim 8, characterized in that: The period from when one foot of the test subject touches the ground to when the foot touches the ground again is represented as one walking cycle, and when the one walking cycle is represented by 1% to 100%, The predetermined period is a period from 65% to 70% of the one walking cycle.

10. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of a first angle of the ankle joint during a first period of the stance period and time series data of a second angle of the ankle joint during a second period of the foot-in-the-air period, The determination unit determines whether the test subject suffers from sarcopenia by using an average value of the time series data of the first angle of the ankle joint and an average value of the time series data of the second angle of the ankle joint.

11. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the displacement of the toe portion in the vertical direction during the first period of the stance period, time series data of the angle of the knee joint during the second period of the stance period, time series data of the angle of the knee joint during the third period of the foot-in-the-air period, and time series data of the angle of the knee joint during the fourth period of the foot-in-the-air period, The judgment unit determines whether the test subject suffers from muscle wasting by using the average value of the time series data of the displacement of the toe in the vertical direction during the first period and the average value of the time series data of the angle of the knee joint during the second period, the third period and the fourth period.

12. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the displacement of the toe portion in the vertical direction during a first period of the stance period, time series data of the angle of the ankle joint during a second period of the stance period, time series data of the angle of the ankle joint during a third period of the stance period, time series data of the angle of the ankle joint during a fourth period of the foot hanging period, and time series data of the angle of the ankle joint during a fifth period of the foot hanging period, The judgment unit determines whether the test subject suffers from muscle wasting by using the average value of the time series data of the displacement of the toe in the vertical direction during the first period and the average value of the time series data of the angle of the ankle joint during the second period, the third period, the fourth period and the fifth period.

13. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the angle of the knee joint during a first period of the stance period, time series data of the angle of the knee joint during a second period of the foot-in-the-air period, time series data of the angle of the knee joint during a third period of the foot-in-the-air period, time series data of the angle of the ankle joint during a fourth period of the stance period, time series data of the angle of the ankle joint during a fifth period of the foot-in-the-air period, and time series data of the angle of the ankle joint during a sixth period of the foot-in-the-air period, The judgment unit judges whether the test subject suffers from muscle wasting by using the average value of the time series data of the angle of the knee joint in the first period, the second period and the third period, and the average value of the time series data of the angle of the ankle joint in the fourth period, the fifth period and the sixth period.

14. The sarcopenia assessment device according to claim 1, characterized in that: The detection unit detects time series data of the displacement of the toe portion in the vertical direction during a first period of the stance period, time series data of the displacement of the toe portion in the vertical direction during a second period of the stance period, time series data of the displacement of the toe portion in the vertical direction during a third period of the foot-in-the-air period, time series data of the angle of the knee joint during a fourth period of the stance period, time series data of the angle of the knee joint during a fifth period of the stance period and the foot-in-the-air period, time series data of the angle of the ankle joint during a sixth period of the stance period, and time series data of the angle of the ankle joint during a seventh period of the stance period and the foot-in-the-air period, The judgment unit determines whether the test subject suffers from muscle wasting by using the average value of the time series data of the displacement of the toe in the vertical direction during the first period, the second period and the third period, the average value of the time series data of the angle of the knee joint during the fourth period and the fifth period, and the average value of the time series data of the angle of the ankle joint during the sixth period and the seventh period.

15. The sarcopenia assessment device according to claim 1, characterized in that: The judgment unit further uses at least one of the angle of the knee joint during the stance period, the angle of the knee joint during the foot suspension period, the displacement of the toe in the vertical direction during the stance period, the displacement of the toe in the vertical direction during the foot suspension period, the angle of the ankle joint during the stance period, and the angle of the ankle joint during the foot suspension period to judge whether the test subject is a preparatory group for muscle wasting who may develop muscle wasting in the future.

16. The sarcopenia assessment device according to claim 1, characterized in that: The judgment unit judges that the test subject has muscle wasting disease when the angle of the knee joint during the stance period is greater than a threshold, when the angle of the knee joint during the foot hanging period is greater than a threshold, when the displacement of the toe part in the vertical direction during the stance period is greater than a threshold, when the displacement of the toe part in the vertical direction during the foot hanging period is greater than a threshold, when the angle of the ankle joint during the stance period is greater than a threshold, or when the angle of the ankle joint during the foot hanging period is greater than a threshold.

17. The sarcopenia assessment device according to claim 1, characterized in that: The judgment unit judges whether the test subject suffers from the muscle wasting disease by inputting at least one of the detected angle of the knee joint in the stance period, the angle of the knee joint in the foot-in-the-air period, the displacement of the toe portion in the vertical direction in the stance period, the displacement of the toe portion in the vertical direction in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period into the prediction model, wherein the prediction model is a prediction model generated by taking at least one of the angle of the knee joint in the stance period, the angle of the knee joint in the foot-in-the-air period, the displacement of the toe portion in the vertical direction in the stance period, the displacement of the toe portion in the vertical direction in the foot-in-the-air period, the angle of the ankle joint in the stance period, and the angle of the ankle joint in the foot-in-the-air period as input values ​​and taking whether the test subject suffers from the muscle wasting disease as an output value.

18. A storage medium, which is a non-transitory computer-readable storage medium storing a sarcopenia assessment program, wherein the sarcopenia assessment program assesses sarcopenia based on a test subject's walking movements, wherein: The sarcopenia assessment program enables the computer to: acquiring walking data related to walking of the test subject; Detecting, based on the walking data, at least one of an angle of a knee joint of one leg of the test subject during a stance period of the leg, a displacement of a toe portion of the leg in a vertical direction during a stance period, a displacement of the toe portion of the leg in a vertical direction during a foot-in-the-air period, an angle of an ankle joint of the leg during a stance period, and an angle of the ankle joint of the leg during a foot-in-the-air period; using at least one of the angle of the knee joint in the stance phase, the displacement of the toe portion in the vertical direction in the stance phase, the displacement of the toe portion in the vertical direction in the foot-in-the-air phase, the angle of the ankle joint in the stance phase, and the angle of the ankle joint in the foot-in-the-air phase, to determine whether the test subject suffers from sarcopenia, In the detection, time series data of a predetermined period of at least one of the parameters is detected, In the judgment, the average value of the time series data is used to judge whether the test subject suffers from the sarcopenia.

Citation Information

Patent Citations

  • Evaluation method for senile disorder risk

    JP2013255786A

  • Moving ability evaluation device, moving ability evaluation system, moving ability evaluation program, and moving ability evaluation method

    JP2018114319A

  • Method and apparatus for monitoring quality of a dynamic activity of a body

    CA2924835A1

  • Fitness effect evaluation system based on electromyographic signal and body movement detection

    CN105597298A

  • Knee joint disease prediction apparatus and system

    CN108305683A