JP6664746B2 - Walking evaluation system and operation method of walking evaluation system - Google Patents

Description

  The present invention relates to a walking evaluation system and a walking evaluation method for performing walking evaluation from walking data.

  With increasing number of elderly people, locomotor syndrome (locomotive syndrome; hereinafter locomo) due to a decrease in leg and hip motor function has become a social problem. Therefore, prolongation of healthy life expectancy and reduction of medical expenses are expected by preventing locomotion not only in hospitals but also in areas closely related to daily life. Locomo measures require not only a quantitative increase in the number of steps but also a quality improvement in the way of walking, and it is important to evaluate the walking state of an individual in walking.

  If there is a problem with walking, an expert such as a physiotherapist performs a visual diagnosis based on a predetermined index (for example, rhythm, momentum, stability, etc.) to evaluate walking. However, the number of specialists is overwhelmingly short of the number of elderly people at nursing facilities other than hospitals, public halls, and fitness clubs that are places where community-based comprehensive care systems go, and the individual walking functions are understood in detail. There is a problem that it is difficult to obtain a satisfactory diagnosis because it cannot be performed. In some hospitals, there are cases in which the index of the walking evaluation has not been unified, and there is variation in the evaluation by visual confirmation.

  On the other hand, there is known a system capable of acquiring and analyzing walking data of a subject and determining whether walking is performed normally (for example, see Patent Documents 1 to 4).

  Among these, Patent Literature 1 discloses a gait analysis system that calculates a gait analysis result based on knee joint torque from three-dimensional angle information of a foot pressure and an inertial pressure sensing element of a knee. Patent Literature 2 discloses a walking evaluation device that evaluates at least one of a kick foot, a tempo, a foot height, and a stride from a foot acceleration, a tilt, and an angular velocity sensor. Patent Literature 3 discloses a walking evaluation device that calculates a frequency spectrum distribution from the acceleration of a foot and determines whether or not the walking is healthy based on the relationship between a first peak and a second peak. Patent Literature 4 discloses a walking analysis system that calculates a walking speed, a stride, and a pace from waist acceleration data and determines a fall risk.

JP 2017-144237 A JP 2009-000391 A JP 2013-059489 A JP 2009-261595 A

  However, in the methods disclosed in Patent Literatures 1 to 4, gait evaluation is performed by focusing on specific gait parameters obtained from gait data of a subject. On the other hand, in the visual diagnosis of a subject's walking, walking evaluation is performed by using a predetermined index instead of a specific parameter. Therefore, it is desired to develop a system for performing a walking evaluation based on an index adopted at the time of visual diagnosis, thereby suppressing variations in the walking evaluation and improving the reliability of the walking evaluation.

  The present invention has been made in view of such a point, and an object of the present invention is to provide a walking evaluation system and a walking evaluating method that can improve the reliability of walking evaluation.

The present invention
A walking evaluation system for performing walking evaluation from the walking data of the subject,
A walking data acquisition unit that acquires the walking data of the subject,
An extracting unit that extracts a walking parameter from the walking data acquired by the walking data acquiring unit,
A coefficient storage unit storing coefficients,
The walking parameter extracted by the extraction unit, based on the coefficient stored in the coefficient storage unit, based on a walking evaluation model, an evaluation value calculation unit that calculates the walking evaluation value of the subject,
The coefficient stored in the coefficient storage unit is a value obtained from the walking evaluation model based on a walking parameter extracted from walking data of the evaluation reference person and a walking evaluation reference value of the evaluation reference person. There is a walking evaluation system,
I will provide a.

In the walking evaluation system described above,
An input unit for inputting the walking evaluation reference value of the evaluation reference person,
Coefficient calculation for calculating the coefficient from the walking evaluation model based on the walking parameter extracted from the walking data of the evaluation reference person by the extraction unit and the walking evaluation reference value input by the input unit And a part,
The coefficient stored in the coefficient storage unit may be a value calculated by the coefficient calculation unit.

In the walking evaluation system described above,
The walking evaluation reference value of the evaluation reference person is a value determined by an expert,
You may do so.

In the walking evaluation system described above,
A display unit that displays a walking evaluation result of the subject based on the walking evaluation value calculated by the evaluation value calculating unit,
You may do so.

In the walking evaluation system described above,
The walking evaluation model is a multiple regression model or a logistic regression model,
You may do so.

In the walking evaluation system described above,
The apparatus further includes a determination unit that determines the walking of the subject based on the walking evaluation value calculated by the evaluation value calculation unit,
You may do so.

In the walking evaluation system described above,
The walking evaluation model is a multiple regression model,
The evaluation value calculation unit calculates a plurality of the walking evaluation values,
The determination unit determines the walking of the subject based on the sum of the plurality of walking evaluation values calculated by the evaluation value calculation unit,
You may do so.

In the walking evaluation system described above,
The walking evaluation criterion value is a value corresponding to a score representing the abnormality of walking defined by the modified walking abnormality scale,
You may do so.

In the walking evaluation system described above,
The walking evaluation criterion value is a score representing the abnormality of walking defined by the modified walking abnormality scale, and is a value obtained by adding scores based on a plurality of indices.
You may do so.

In the walking evaluation system described above,
The extraction unit extracts a walking parameter associated with the stance phase and a walking parameter associated with the swing phase.
You may do so.

In the walking evaluation system described above,
The extraction unit is configured to extract a walking parameter associated with the heel rocker period, a walking parameter associated with the ankle rocker period, and a walking parameter associated with the forefoot rocker period,
You may do so.

Also, the present invention
A walking evaluation method for performing a walking evaluation from the walking data of the subject,
A data acquisition step of acquiring the walking data of the subject,
An extraction step of extracting a walking parameter from the walking data,
An evaluation value calculation step of calculating a walking evaluation value of the subject from a walking evaluation model based on the walking parameters and the coefficients stored in the coefficient storage unit,
The coefficient stored in the coefficient storage unit is a value obtained from the walking evaluation model based on a walking parameter extracted from walking data of the evaluation reference person and a walking evaluation reference value of the evaluation reference person. There is a walking evaluation method,
I will provide a.

In the walking evaluation method described above,
A data acquisition step of acquiring the walking data of the evaluation criterion,
An extraction step of extracting a walking parameter from the walking data of the evaluation criterion,
A determination step of visually determining the walking of the evaluation reference person and determining the walking evaluation reference value;
A coefficient calculating step of calculating the coefficient from the walking evaluation model based on the walking parameter of the evaluation reference person and the walking evaluation reference value,
The coefficient stored in the coefficient storage unit is a value calculated in the coefficient calculation step,
You may do so.

In the walking evaluation method described above,
In the determining step, the determination of the walking evaluation reference value is performed by an expert by visually observing the walking of the evaluation reference person,
You may do so.

  According to the present invention, the reliability of walking evaluation can be improved.

FIG. 1 is a block diagram illustrating a configuration of a walking evaluation system according to an embodiment of the present invention. FIG. 2 is a table for explaining a corrected gait abnormality scale used in the gait evaluation system shown in FIG. FIG. 3 is a perspective view showing an example of the walking data acquisition unit shown in FIG. FIG. 4 is a flowchart showing a walking evaluation method according to the embodiment of the present invention. FIG. 5 is a graph showing walking data acquired from the walking data acquiring unit in FIG. FIG. 6 is a diagram for explaining a method of extracting a walking parameter from the walking data obtained in FIG. FIG. 7 is a diagram for explaining the sole pressure during walking. FIG. 8 is a diagram illustrating a display example of the results of the walking evaluation of the subject on the display unit illustrated in FIG. 1. FIG. 9 is a diagram showing another display example of the walking evaluation result shown in FIG. FIG. 10 is a table for explaining a sensor configuration according to the first embodiment. FIG. 11 is a table showing Gars reference values of the walking data obtained in the first embodiment. FIG. 12 is a table showing the adjusted coefficient of freedom, the RMSE, and the correct answer rate obtained in the first embodiment. FIG. 13 is a table showing the recall rate and the correct answer rate obtained in Example 2.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  A walking evaluation system and a walking evaluation method according to an embodiment of the present invention will be described with reference to FIGS. As shown in FIG. 1, a walking evaluation system 200 according to the present embodiment is a system for performing walking evaluation from walking data of a subject using a walking evaluation model. Although FIG. 1 shows a block diagram of the walking evaluation system 200, the lines connecting the blocks are drawn to indicate the flow of information.

  In the present embodiment, a modified Gait Abnormality Rating Scale (GARS-M) is used as an example of a scale for evaluating whether there is an abnormality in human walking. Regarding the modified gait abnormality scale, for example, Mariko Kobayashi and five others, “Inter-rater reliability of the gait abnormality scale by video observation in the elderly in the community” (Physical Therapy 2012, Vol. 39, No. 7) Pp. 397-403). In GARS-M, the abnormalities of gait given based on the modified gait abnormalities scale of the seven indices (Gars1 to Gars7) shown in FIG. 2 are represented by scores. The score is given from 0 to 3 points, and indicates that the larger the score, the more serious the abnormality. Normally, points are given as integers and are evaluated on a four-point scale.

  Generally, when a physiotherapist or the like evaluates a subject's gait, the gait of the subject is visually diagnosed, and seven points of GARS-M are evaluated to determine a score. The walking evaluation system 200 according to the present embodiment evaluates the walking of the subject by automatically calculating a numerical value (gait evaluation value) corresponding to the score for each of these seven indices (Gars1 to Gars7). Here, the term “expert” refers to a person who has expertise in walking evaluation. Examples of specialists include physiotherapists, prosthetics and orthotics, rehabilitation specialists, and orthopedic surgeons, but are not limited to those with expertise in gait evaluation.

  As shown in FIG. 1, the walking evaluation system 200 includes a walking data acquisition unit (data acquisition device) 1 and a system main body 201. The system body 201 includes a data receiving unit 202, a data storage unit 203, a model storage unit 204, an extraction unit 205, a coefficient storage unit 206, an evaluation value calculation unit 207, an input unit 208, a coefficient calculation unit A unit 209, a determination unit 210, and a display unit 211 are provided. The system main body 201 can be composed of, for example, a personal computer.

  The walking data acquisition unit 1 is configured to acquire walking data of a subject and an evaluation reference person. The walking data acquisition unit 1 has at least one sensor as described later. When a subject (or an evaluation reference person) wearing the walking data acquisition unit 1 walks, the walking data of the subject is calculated based on the sensor measurement value. You can get it. Details of the walking data acquisition unit 1 will be described later.

  The data receiving unit 202 is configured to receive the walking data transmitted from the walking data obtaining unit 1. The data receiving unit 202 has a wireless or wired communication unit, and communicates with the walking data acquisition unit 1 by a predetermined communication method.

  The data storage unit 203 is configured to store the walking data received by the data receiving unit 202. That is, the walking data obtained from the subject is stored, and the walking data obtained from the evaluation reference person is stored.

  The model storage unit 204 is configured to store a walking evaluation model used in an evaluation value calculation unit 207 and a coefficient calculation unit 209 described below. The walking evaluation model will be described later.

  The extracting unit 205 is configured to extract a plurality of walking parameters (feature amounts) from the walking data acquired by the walking data acquiring unit 1. The extraction unit 205 may extract a walking parameter associated with the stance phase and a walking parameter associated with the swing phase. Of these, for the stance phase, a walking parameter associated with the heel rocker phase, a walking parameter associated with the ankle rocker phase, and a walking parameter associated with the forefoot rocker phase may be extracted.

  More specifically, the extraction unit 205 extracts a walking parameter from bending data, pressure data, and acceleration data as shown in FIG. For example, a minimum value, a maximum value, a range value, a gradient, and the like of the MP bending measurement values in the heel rocker period, the ankle rocker period, and the forefoot rocker period are calculated from MP bending data described later. The details of the method for extracting the walking parameter will be described later.

  Based on the plurality of walking parameters extracted by the extraction unit 205 and the plurality of coefficients stored in the coefficient storage unit 206, the evaluation value calculation unit 207 calculates a subject's walking evaluation value (hereinafter, Gars value) from the walking evaluation model. ) Is calculated. The evaluation value calculation unit 207 calculates a Gars value in each of Gars1 to Gars7 using the walking evaluation model stored in the model storage unit 204 described above.

  The walking evaluation model calculates a Gars value from a walking parameter and a coefficient. The gait evaluation model may calculate the Gars value by using a regression analysis technique. Examples of the gait evaluation model include a simple regression model, a multiple regression model, and a logistic regression model. In the present embodiment, a multiple regression model will be described as an example.

ここで、ｘ_１〜ｘ_ｎは、説明変数としての各歩行パラメータ（例えば、ヒールロッカー期におけるＭＰ曲げの最小値等）である。ａ_０〜ａ_ｎは係数（より詳細には、偏回帰係数）であるが、ａ_０は、定数項とも呼ばれる。ｙは、目的変数としてのＧａｒｓ値（歩行評価値）であり、０〜３の範囲での任意の値（整数以外の値を含む）をとる。すなわち、本実施の形態では、評価値算出部２０７は、式（１）のｘ_１〜ｘ_ｎに評価対象の被験者に関連付けられた歩行パラメータを代入するとともに、式（１）のａ_０〜ａ_ｎに係数記憶部２０６に記憶された係数を代入して、Ｇａｒｓ値を算出する。算出されたＧａｒｓ値は、ＧＡＲＳ−Ｍで規定された歩行の異常性を表わす点数に相当する値になる。Ｇａｒｓ値は、Ｇａｒｓ１〜Ｇａｒｓ７の各々について算出される。すなわち、係数は、後述するように、Ｇａｒｓ１〜Ｇａｒｓ７の各指標に関連付けられて記憶されているため、Ｇａｒｓ値として算出するＧａｒｓ指標に対応する係数を用いて、所望のＧａｒｓ指標に対応するＧａｒｓ値が算出される。 The multiple regression model is represented by the following equation (1).

Here, x _{1 to} x _n are each walking parameter (for example, the minimum value of the MP bending in the heel rocker period) as an explanatory variable. (more specifically, partial regression coefficients) a ₀ ~a _n coefficient is a, _{a 0} is also referred to as a constant term. y is a Gars value (gait evaluation value) as an objective variable, and takes an arbitrary value (including a value other than an integer) in a range of 0 to 3. That is, in this embodiment, the evaluation value calculation section 207 is configured to substitute the gait parameters associated with the evaluated subjects _x 1 ~x _n of formula (1), _a 0 in the formula (1) ~a _The Gars value is calculated by substituting the coefficient stored in the coefficient storage unit 206 for _n . The calculated Gars value is a value corresponding to a score representing the abnormality of walking defined by GARS-M. The Gars value is calculated for each of Gars1 to Gars7. That is, since the coefficient is stored in association with each index of Gars1 to Gars7 as described later, the Gars value corresponding to the desired Gars index is calculated using the coefficient corresponding to the Gars index calculated as the Gars value. Is calculated.

  The coefficient storage unit 206 is configured to store a plurality of coefficients used in the walking evaluation model described above. Each coefficient is associated with each index of Gars1 to Gars7 and is also associated with a corresponding walking parameter. The coefficient storage unit 206 includes a storage medium such as a hard disk drive (HDD), a solid state drive (SSD), a memory device, a memory card (eg, an SD card), or a USB memory. The coefficient storage unit 206 may be configured by a storage medium common to the data storage unit 203 and the model storage unit 204 described above.

  The coefficients stored in the coefficient storage unit 206 are based on the walking parameters extracted from the walking data of the evaluation reference person and the walking evaluation reference values obtained when the walking parameters of the evaluation reference person are obtained. It is a value obtained from the gait evaluation model obtained. The walking evaluation reference value is a score determined by an expert who visually diagnoses the walking of the evaluation reference person different from the subject, and is a value that is a reference value of the walking evaluation value (Gars value) in the walking evaluation system 200. is there. This value is referred to as a Gars reference value in this specification. The calculation of such a coefficient is performed by a coefficient calculation unit 209 described later.

The coefficient calculating unit 209 calculates the walking evaluation model represented by the above equation (1) based on the walking parameters extracted from the walking data of the evaluation reference person and the Gars reference value (walking evaluation reference value) determined by the expert. It is configured to calculate a coefficient from. The coefficient calculation unit 209 calculates a coefficient in each of Gars1 to Gars7 using the walking evaluation model stored in the model storage unit 204 described above. That is, the coefficient calculation unit 209 substitutes the Gars reference values of the respective evaluation reference persons determined in advance by the expert visually diagnosed into y of the above-described equation (1), and also uses x ₁ to x _n of the equation (1). Is substituted for the walking parameter associated with the evaluation criterion, and the coefficient is calculated. The coefficient is calculated for each of Gars1 to Gars7. The calculated coefficients are stored in the coefficient storage unit 206 in association with Gars1 to Gars7.

  The input unit 208 is configured to input a Gars reference value determined by an expert. The input unit 208 includes, for example, an input device such as a keyboard, a mouse, or a touch panel.

  The determination unit 210 is configured to determine the walking of the subject based on the Gars value calculated by the evaluation value calculation unit 207. More specifically, the determination unit 210 calculates the sum of the plurality of Gars values calculated by the evaluation value calculation unit 207, and determines the walking of the subject based on the sum of the Gars values. For example, the Gars values calculated in each of Gars 1 to Gars 7 are summed, and the determining unit 210 determines whether or not the sum of the obtained Gars values exceeds nine points, which are the determination reference values. When the sum of the Gars values exceeds nine points, the determination unit 210 determines that the subject's walking is abnormal and the fall risk is high. On the other hand, when the sum of the Gars values is 9 or less, the determination unit 210 determines that there is no abnormality in the subject's walking and the fall risk is low. In addition, what is necessary is just to set the point which can be considered that a fall risk becomes high as a determination reference point, and is not limited to nine points.

  The display unit 211 is configured to display the walking evaluation result of the subject based on the Gars value calculated by the evaluation value calculation unit 207.

  For example, as shown in FIG. 8, a deviation value calculated from the Gars value as a walking evaluation result may be displayed on a radar chart. FIG. 8 shows an example in which Gars values corresponding to Gars 1 to Gars 5 are displayed. Here, "rhythm" corresponds to Gars1, "power" corresponds to Gars2, "stability" corresponds to Gars3, "ground contact" corresponds to Gars4, and "movable range" corresponds to Gars5. . Here, Gars values corresponding to Gars1 to Gars5 are indicated by deviation values when 80 points are averaged. The deviation value may be calculated by the determination unit 210 described above.

  Further, for example, as shown in FIG. 9, the deviation value of the Gars value may be displayed as the number of star marks as the walking evaluation result. FIG. 9 shows an example in which Gars values calculated in each of Gars1 to Gars5 are displayed by star marks.

  Further, for example, although not shown in FIG. 8 or FIG. 9, the determination result of the walking of the subject by the determination unit 210 described above may be displayed. In this case, if the sum of the Gars values obtained by the determination unit 210 exceeds 9 points, the fact that the risk of falling of the subject is high is displayed, and if the sum of the Gars values is 9 points or less, the subject's Indicates that the fall risk is low.

  The display unit 211 may include any display device. For example, when the system main body 201 is configured by a personal computer, the system main body 201 may include a display device such as an LCD display or a CRT (cathode ray tube) display attached to or incorporated in the personal computer. Alternatively, for example, a display device such as an LCD (liquid crystal display) or an OLED (organic EL display) of a portable information terminal (a mobile phone, a smartphone, a tablet terminal, or the like) may be included.

  Next, the walking data acquisition unit 1 according to the present embodiment will be described. Here, as an example, an example in which the walking data acquisition unit 1 disclosed in Japanese Patent Application Laid-Open No. 2018-011890 is applied will be schematically described with reference to FIG. The configuration of the walking data acquisition unit 1 is not limited to the configuration illustrated in FIG. 3 as long as the walking data of the subject (or evaluation reference person) can be acquired. For example, the configuration of another embodiment disclosed in Japanese Patent Application Laid-Open No. 2018-011890 may be employed, or a configuration other than the configuration disclosed in this publication may be employed. Alternatively, the walking data acquisition unit 1 may be configured by a portable terminal or a tablet terminal having an acceleration sensor. Even in the case of a mobile terminal or a tablet terminal, acceleration data can be created by relating the acceleration measured by the acceleration sensor to the measurement time. Further, the data acquisition unit 1 has a sensor such as a pressure sensor attached to the foot F of the subject (or evaluation reference person), and creates walking data by relating the measurement value measured by the sensor to the measurement time. Any configuration can be applied as long as the configuration is possible.

  The walking data acquisition unit 1 illustrated in FIG. 3 includes an accessory 10 that can be worn on the subject's foot F, a bending measurement unit 20, and a pressure measurement unit 30. In the present embodiment, an example in which the accessory 10 is the sock 11 is shown, but it may be a shoe or an insole. The bending measuring unit 20 and the pressure measuring unit 30 are attached to a sock 11 as the accessory 10.

  The bending measurement unit 20 includes an MP bending sensor 21 that measures the degree of bending of the subject's foot F about the MP joint axis, and a leg bending sensor 22 that measures the degree of bending of the ankle A. The bending degrees measured by the bending sensors 21 and 22 are associated with the measurement time, and bending data (see FIGS. 5 and 6), which is an example of walking data, is created.

  The pressure measuring unit 30 measures the sole pressure of the subject. The pressure measurement unit 30 shown in FIG. 3 includes a heel pressure sensor 31 that measures the pressure of the heel on the back side of the subject's foot F, and an MP pressure sensor 32 that measures the pressure of the MP joint on the back side of the subject's foot F. And a toe pressure sensor 33 that measures the pressure of the toe (an example of a toe) on the back side of the subject's foot F. The pressure measured by each of the sensors 31 to 33 is associated with the measurement time, and pressure data (see FIGS. 5 and 6), which is an example of walking data, is created.

  The walking data acquisition unit 1 shown in FIG. 3 further includes an acceleration sensor 40 (acceleration measurement unit) that measures the acceleration of the lower leg L of the subject. The acceleration sensor 40 is housed in the box 12 and attached by the belt 13. The acceleration sensor 40 is configured to be able to measure acceleration in three axial directions, and measures acceleration in the vertical direction, longitudinal acceleration, and lateral (inward and outward directions of the foot F) of the lower leg L. The acceleration measured by the acceleration sensor 40 is associated with the measurement time to create vertical acceleration data, longitudinal acceleration data, and lateral acceleration data (see FIG. 5), which are examples of walking data.

  Each of the walking data created as described above is output from an output unit (not shown) of the walking data acquisition unit 1 and transmitted to the data receiving unit 202 of the system main body 201 described above. The walking data acquisition unit 1 has a wireless or wired communication unit corresponding to the data reception unit 202, and performs communication by a predetermined communication method.

  Next, the operation of the present embodiment having such a configuration will be described. Here, a walking evaluation method for performing walking evaluation from the walking data of the subject will be mainly described with reference to FIG. The data storage unit 203 of the walking evaluation system 200 stores programs for controlling the execution of various processes, and the system body 201 reads out and executes the programs to operate the walking evaluation system 200. Is controlled, and the walking evaluation method described below is realized. The operation of the walking data acquisition section 1 may be controlled by a program stored in the data storage section 203, but independently of this program, the walking data acquisition section 1 executes its own program stored therein. The operation may be controlled.

  Before calculating the walking evaluation value of the subject, the coefficient of the walking evaluation model is calculated from the walking data of the evaluation reference person and stored in the coefficient storage unit 206. That is, the coefficients of the walking evaluation model are calculated from the walking data of a plurality of evaluation reference persons different from the subject. The number of evaluation reference persons (or the number of walking data obtained from the evaluation reference persons) can be determined according to the walking evaluation accuracy of the subject or the accuracy of the coefficients of the walking evaluation model.

  First, as the mounting step S101, for example, the walking data acquisition unit 1 illustrated in FIG. 3 is mounted on the evaluation reference person. In this case, the socks 11 of the walking data acquisition unit 1 in which each sensor is attached to both feet F of the evaluation reference person are attached. Further, the belt 13 to which the above-described box 12 is attached is wound around the lower leg L of the evaluation reference person.

  After the mounting step S101, as the data obtaining step S102, the walking data obtaining unit 1 mounted on the evaluation reference person obtains the walking data of the evaluation reference person.

  Specifically, first, reference values of each bending sensor and acceleration sensor are measured. In this case, the evaluation reference person stands still for about 10 seconds in the standing posture. The measurement value measured in this state is set as a zero point (measurement reference value) of each bending sensor and acceleration sensor. The pressure sensor may be set to a zero point before the walking data acquisition unit 1 is attached to the evaluation reference person.

  Next, the walking data of the evaluation reference person is measured. In this case, the evaluation reference person walks, for example, about 10 m. During this time, the walking data is created by associating the measurement value measured by each sensor with the measurement time. The created walking data is stored in a storage unit (not shown) of the walking data acquisition unit 1.

  After the measurement is completed, the walking data stored in the storage unit of the walking data acquisition unit 1 is transmitted (output) to the data receiving unit 202. In this way, the walking data of the evaluation reference person as shown in FIG. 5 can be obtained. FIG. 5 shows heel pressure data (waveform A), MP pressure data (waveform B), toe pressure data (waveform C), MP bending data (waveform D), and thigh bending data (waveform) as examples of walking data. E), lateral acceleration data (waveform F), longitudinal acceleration data (waveform G), and vertical acceleration data (waveform H).

  While the evaluation criterion is walking, as a determination step S103, an expert who is a physiotherapist visually diagnoses the gait of the evaluation criterion and determines the Gars reference value (gait evaluation criterion value) of the evaluation criterion. . In this case, an expert who visually diagnoses the walking of the evaluation reference person assigns an integer in the range of 0 to 3 points in each of Gars1 to Gars7. Each score is input to the input unit 208 as a Gars reference value for each of Gars1 to Gars7. Note that, in the determination step S103, a moving image of the walking state of the evaluation reference person may be captured, and thereafter, the expert may visually diagnose the moving image to determine the Gars reference value. Also in this case, the determined Gars reference value is input to the input unit 208.

  After the data acquisition step S102, as an extraction step S104, a walking parameter is extracted by the extraction unit 205 from the acquired walking data of the evaluation reference person.

  In this case, the walking data is first divided into a plurality of periods for extracting walking parameters as shown in FIGS. More specifically, the walking data is divided into (1) a heel rocker period, (2) an ankle rocker period, (3) a forefoot rocker period, (4) a first half swing period, and (5) a second half swing period. . A method for extracting the walking parameter will be described below.

  One walking cycle is divided into a stance phase in which the foot F is in contact with the floor and a swing phase in which the foot F is away from the floor. As shown in FIG. 6, the stance phase includes (1) a heel rocker phase (early stance phase), (2) an ankle rocker phase (middle stance phase), and (3) a forefoot rocker phase (end stance phase). It is divided. The swing phase is divided into (4) the first swing phase and (5) the second swing phase. In FIG. 6, the abscissa indicates a dimensionless time when one walking cycle is 100%, and the ordinate indicates a measurement value measured by each sensor as a dimensionless number. In FIG. 6, as an example, heel pressure data is shown in FIG. 6 (a), MP pressure data is shown in FIG. 6 (b), MP bending data is shown in FIG. 6 (c), and FIG. 9 shows the thigh bending data.

  As shown in FIG. 7, the heel rocker period is a period from when the heel portion 100 touches the floor surface to when the MP joint portion 101 touches the floor surface. More specifically, in the heel rocker period, from the time when the pressure of the heel 100 becomes a positive value (heel contact time T1), the time when the pressure of the MP joint 101 becomes a positive value (the MP touch time) The period up to T2) is reached. Normally, at the MP contact point T2, the toe 102 is not in contact with the ground, and the pressure of the toe 102 is zero. In the heel rocker period, as shown in FIG. 7, the foot F and the lower leg L are deformed such that the foot F and the lower leg L rotate in a direction in which the entire foot F comes into contact with the floor, mainly around the heel 100.

  The ankle rocker period is a period from when the MP joint portion 101 touches the floor to when the heel portion 100 separates from the floor. More specifically, in the ankle rocker period, from the time when the pressure of the MP joint portion 101 becomes a positive value (the MP touching time T2), the time when the pressure of the heel portion 100 becomes zero (the heel off time T3) ). Normally, at the heel take-off time T3, the MP joint 101 is grounded, and the pressure of the MP joint 101 becomes a positive value. In the ankle rocker period, as shown in FIG. 7, the lower leg L is rotated to the front side while the entire foot F is grounded on the floor surface mainly around the talar joint axis 103 of the ankle A. The ankle A is deformed.

  The forefoot rocker period is a period from when the heel part 100 separates from the floor to when the toe 102 separates from the floor. More specifically, in the forefoot rocker period, from the time when the pressure of the heel part 100 becomes zero (heel off time T3), the time when the pressure of the toe 102 becomes zero (toe off time T4) ). Normally, at the toe takeoff time T4, the MP joint 101 is taken off, and the pressure of the MP joint 101 becomes zero. In the forefoot rocker period, as shown in FIG. 7, the foot F is deformed so that the foot F rotates in the direction in which the heel 100 is lifted while the toes are grounded on the floor mainly around the MP joint axis. .

  When the walking data is divided into the above-described periods, a heel rocker period, an ankle rocker period, and a forefoot rocker period are determined from the heel pressure data, the MP pressure data, and the toe pressure data. In this case, the heel contact time point T1 at which the pressure of the heel part 100 becomes a positive value from zero is specified from the heel pressure data. Also, from the MP pressure data, the MP touch point T2 at which the pressure of the MP joint portion 101 becomes a positive value from zero is specified. Then, from the heel pressure data, the heel take-off time T3 at which the pressure of the heel part 100 becomes zero from a positive value is specified, and from the graph of the toe pressure data, the pressure of the toe 102 becomes zero from the positive value. The toe takeoff time T4 is specified. As shown in FIG. 6, (1) the heel rocker period, (2) the ankle rocker period, and (3) the forefoot rocker period can be determined by these specified time points T1 to T4.

  Then, (4) the first half swing period and (5) the second half swing period can be determined. That is, the period from the toe take-off time T4 to the next heel contact time T1 is the swing phase. This swing phase can be divided into halves (at an intermediate time point T5), and (4) a first half swing phase and (5) a second half swing phase can be determined.

  Then, as a walking parameter relating to the walking data, a minimum value, a maximum value, a range value in each period, a slope of a waveform in the period, and the like are calculated. The range value is a difference between the maximum value and the minimum value in the period. The slope is a value obtained by dividing the difference between the value at the beginning and the value at the end of the period by the time from the beginning to the end.

  By the way, as shown in FIG. 5, a plurality of each of the above-mentioned periods appears in the walking data acquired by the walking data acquiring unit 1. For this reason, when calculating the walking parameter in the heel rocker period, the walking parameter may be calculated from the waveform in one of the heel rocker periods. Alternatively, an averaging waveform or a standard deviation waveform may be created from a plurality of heel rocker periods, and a walking parameter may be calculated from the averaging waveform or the standard deviation waveform. When the walking data acquisition unit 1 is worn on both feet F of the subject, the walking parameters are calculated for each of the right foot and the left foot. That is, the walking parameter may be calculated for the left foot while calculating the walking parameter for the right foot. Alternatively, an average value of the walking parameter of the right foot and the walking parameter of the left foot may be calculated as the walking parameter. Further, a variation coefficient between the walking parameter of the right foot and the walking parameter of the left foot may be calculated as the walking parameter. The same applies to the walking parameters in other periods. In this way, a plurality of walking parameters can be extracted from the walking data.

After the extraction step S104, as a coefficient calculation step S105, based on the walking parameters extracted from the walking data of the evaluation reference person and the Gars reference value input to the input unit 208, the coefficient calculation unit 209 executes Calculate the coefficient. More specifically, relates Gars1, walking parameters one criteria's, as well as substituted into _x 1 ~x _n in the above formula indicates a gait assessment model (1), Gars standards for Gars1 of the criteria's The value is substituted for y in the above equation (1). By doing this for each criteria's coefficients _a 0 ~a _n associated with Gars1 is calculated. The calculation of the coefficients is performed in each Gars1～Gars7, coefficient _a 0 ~a _n associated with Gars1～Gars7 are calculated respectively.

After the coefficient calculation step S105, as the storage step S106, the coefficient _a 0 ~a _n calculated is stored in the coefficient storage unit 206. That is, the coefficient stored in the storage step S106 is based on the walking parameters extracted from the walking data of the evaluation reference person and the Gars reference values obtained when the walking parameters of the evaluation reference person are obtained. This is the value obtained from the evaluation model.

  After each coefficient of the walking evaluation model is stored in the coefficient storage unit 206 in this way, the walking evaluation of the subject can be performed as follows.

  First, as the mounting step S201, the walking data acquisition unit 1 shown in FIG. 3 is mounted on the subject. The mounting of the walking data acquisition unit 1 can be performed in the same manner as the mounting step S101 of the evaluation reference person described above.

  After the mounting step S201, in a data obtaining step S202, the walking data of the subject is obtained by the walking data obtaining unit 1 mounted on the subject. That is, the walking data of the subject is acquired by a sensor that measures the same measurement items (pressure, bending, acceleration) as the sensor used when acquiring the walking data of the evaluation reference person. The acquisition of the walking data can be performed in the same manner as in the data acquisition step S102 of the evaluation reference person described above.

  After the data acquisition step S202, as an extraction step S203, the extraction unit 205 extracts walking parameters from the subject's walking data. The extraction of the walking parameter can be performed in the same manner as in the step of extracting the evaluation reference person S104 described above.

After the extraction step S203, the evaluation value calculation unit 207 calculates the Gars value of the subject from the walking evaluation model based on the extracted walking parameters and the coefficients stored in the coefficient storage unit 206 in an evaluation value calculation step S204. I do. Coefficient more specifically relates Gars1, the walking parameters of a subject, as well as substituted into _x 1 ~x _n in the above formula indicates a gait assessment model (1), associated with the Gars1 stored in the coefficient storage unit 206 and it is substituted into _a 0 ~a _n in the above formula (1). As a result, the value of y is calculated as the Gars value for Gars1. The calculation of the Gars value is performed in each of Gars2 to Gars7, and seven Gars values corresponding to Gars1 to Gars7 are calculated respectively.

  After the evaluation value calculation step S204, in a determination step S205, the walking of the subject is determined by the determination unit 210 based on the Gars value calculated in the evaluation value calculation step S204. Here, the sum of the Gars values of Gars1 to Gars7 is calculated, and the walking of the subject is determined based on the sum of the Gars values. For example, as described above, when the sum of the Gars values exceeds 9 points, the fall risk of the subject is determined to be high, and when the sum of the Gars values is 9 or less, the fall risk of the subject is determined to be low. Is also good.

  After the determination step S205, as a display step S206, the walking evaluation result of the subject is displayed on the display unit 211 based on the Gars value of the subject. For example, the walking evaluation result may be displayed as shown in FIG. 8 or FIG. Alternatively, the determination result by the determination unit 210 may be displayed on the display unit 211.

  Next, effects of the present embodiment will be described.

  According to the present embodiment, the Gars value (gait evaluation value) of the subject is calculated from the gait evaluation model based on the gait parameters extracted from the gait data of the subject and the coefficients stored in coefficient storage unit 206. You. The coefficients stored in the coefficient storage unit 206 include the walking parameters extracted from the walking data of the evaluation reference person different from the subject and the Gars reference values (gait evaluation values) determined when the walking data of the evaluation reference person are acquired. (Reference value) based on the walking evaluation model. That is, a score based on a predetermined index (in this case, any one of Gars1 to Gars7) at the time of performing a visual diagnosis can be adopted as the Gars reference value of the evaluation reference person. The obtained walking evaluation value of the subject can be a numerical value (that is, a Gars value) corresponding to the score based on the index. As a result, it is possible to obtain a subject's walking evaluation based on the index used at the time of visual diagnosis. In addition, since such a walking evaluation can be performed based on the coefficient stored in the coefficient storage unit 206, the walking evaluation can be unified, and variations in the walking evaluation can be suppressed. As a result, the reliability of the walking evaluation can be improved.

  Further, according to the present embodiment, the Gars reference value of the evaluation reference person is input, and the walking evaluation is performed based on the walking parameters extracted from the walking data of the evaluation reference person and the input Gars reference value. The coefficients of the model are calculated. Thereby, the walking evaluation system 200 according to the present embodiment can calculate the coefficients of the walking evaluation model and the Gars value of the subject, and can improve the convenience.

  Further, according to the present embodiment, the Gars reference value of the evaluation reference person is a value determined by an expert. As a result, the Gars value of the subject can be set to a value that incorporates a diagnosis made by a specialist. That is, since the diagnosis by the expert is incorporated, the Gars value of the subject can be provided with higher accuracy than when the diagnosis of the expert is not incorporated, and the reliability of the gait evaluation is further improved. Can be.

  More specifically, in the walking evaluation model according to the present embodiment, the walking evaluation of the subject is performed based on the Gars reference value of the evaluation reference person predetermined by the expert. As a result, a Gars reference value into which a diagnosis by an expert is incorporated can be used as an index of the walking evaluation. For this reason, the reliability of the walking evaluation index can be improved, and the accuracy of the walking evaluation of the subject can be further improved.

  In the walking evaluation model according to the present embodiment, the Gars reference value of the evaluation reference person determined by the expert is stored in coefficient storage unit 206. Thereby, even when there is no expert (in other words, even if they do not have specialized knowledge) when performing a walking diagnosis of the subject, it is possible to perform a walking evaluation incorporating the diagnosis by the expert. Therefore, walking evaluation with improved reliability can be easily performed.

  Further, according to the present embodiment, the walking evaluation result of the subject is displayed based on the calculated Gars value. As a result, the walking evaluation result of the subject can be quickly and easily known, and the convenience can be improved.

  Further, according to the present embodiment, the walking evaluation model is a multiple regression model. The multiple regression model has an advantage that the calculation can be simplified and an advantage that the selection of the explanatory variable (gait parameter) can be tried. The multiple regression model also has the advantage that the degree of influence and cause of the explanatory variable contributing to the objective variable can be easily examined. This can be used to provide guidance for improving the walking of the subject. For example, when it is indicated that the degree of influence of a certain parameter is high regarding Gars1, it is possible to instruct the subject to walk so as to increase the numerical value indicated by this parameter. In this case, the score of Gars1 of the subject can be reduced, and as a result, walking can be improved.

  Further, according to the present embodiment, the walking of the subject is determined based on the calculated Gars value. This makes it possible to quickly and easily know whether or not the subject has an abnormality in walking, thereby improving convenience. For example, the walking of the subject may be determined based on the sum of the Gars values corresponding to Gars1 to Gars7. In this case, the comprehensive determination result regarding the presence or absence of abnormalities in the walking of the subject is quickly and easily known. be able to.

  Further, according to the present embodiment, the evaluation reference value is a value indicating the gait abnormality scale defined by the modified gait abnormality scale (GARS-M). Since this modified gait abnormality scale is a scale in which there is little variation in the evaluation by the individual expert, the determination of the evaluation reference value is prevented from being varied by the individual expert (for example, an inexperienced expert). be able to. For this reason, the reliability of the walking evaluation can be further improved. In addition, in order to reduce the variation in the evaluation by the expert when determining the evaluation reference value, for example, a coefficient may be calculated from the average value of the evaluation reference values determined by a plurality of experts. Good.

  Further, according to the present embodiment, the walking parameters extracted from the walking data include the walking parameters associated with the stance phase and the walking parameters associated with the swing phase. This makes it possible to specify whether the parameter having a high degree of influence on the Gars value is related to the stance phase or the swing phase during the guidance for improving the walking of the subject. For this reason, it is possible to narrow the points for improving walking and to provide appropriate guidance.

  Further, according to the present embodiment, the walking parameters extracted from the walking data are the walking parameters associated with the forefoot rocker period, the walking parameters associated with the ankle rocker period, and the walking parameters associated with the forefoot rocker period. Walking parameters. This makes it possible to specify which locker period a parameter having a high degree of influence on the Gars value at the time of instructing the subject to improve walking. For this reason, the improvement guidance points of walking can be further narrowed down, and appropriate guidance can be provided.

  As described above, the embodiments of the present invention have been described in detail. However, the gait evaluation system 200 and the gait evaluation method according to the present invention are not limited to the above embodiments at all, and do not depart from the gist of the present invention. Various changes are possible in.

(Modification)
In the above-described embodiment, an example has been described in which the walking evaluation model is a multiple regression model. However, the present invention is not limited to this, and the walking evaluation model may be a logistic regression model.

説明変数ｘ_１〜ｘ_ｎ、係数ａ_０〜ａ_ｎおよび目的変数ｙは、上述した式（１）と同様であるが、ロジスティック回帰モデルでは、目的変数ｙは、０〜１の値をとる。このため、専門家の目視診断により決定されるＧａｒｓ基準値は、０点〜１点の点数を整数で付けることする。例えば、専門家の目視診断によりＧａｒｓ基準値が０点と決定された場合には、異常が無いという診断になるためＧａｒｓ基準値を０点とし、専門家の目視診断によりＧａｒｓ基準値が１点〜３点と決定された場合には、比較的小さなものも含めて異常があるという診断になるためＧａｒｓ基準値を１点としてもよい。しかしながら、専門家の目視診断によるＧａｒｓ基準値が１点以下の場合に式（２）に代入するＧａｒｓ基準値を０点とし、目視診断によるＧａｒｓ基準値が２点以上の場合に式（２）に代入するＧａｒｓ基準値を１点としてもよく、任意である。歩行評価モデルとして、この式（２）を式（１）の代わりに用いることにより、同様にして被験者の歩行評価を行うことができ、このような変形例によれば、ロジスティック曲線を利用したモデルとなるために、目的変数ｙを０〜１の範囲内の数値とすることができ、歩行評価モデルの計算上都合が良く、また算出された歩行評価値が異常度の割合を示す数値となるために被験者の異常度合い（レベル）を推測しやすくすることができる。 The logistic regression model is represented by the following equation (2).

Explanatory variable _x 1 ~x _n, coefficients _a 0 ~a _n and objective variable y is the same as equation (1) described above, in the logistic regression model, objective variable y takes a value of 0-1. For this reason, the Gars reference value determined by the visual diagnosis of an expert is assigned an integer from 0 to 1 point. For example, when the Gars reference value is determined to be 0 point by a visual inspection of an expert, the Gars reference value is set to 0 because it is a diagnosis that there is no abnormality, and the Gars reference value is set to 1 point by a visual diagnosis of the expert. If it is determined to be 3 points, it can be diagnosed that there is an abnormality including a relatively small point, so that the Gars reference value may be set to 1 point. However, when the Gars reference value obtained by the visual diagnosis of the expert is 1 point or less, the Gars reference value substituted into the equation (2) is set to 0 point, and when the Gars reference value obtained by the visual diagnosis is 2 points or more, the equation (2) is obtained. The Gars reference value to be assigned to the parameter may be set to one point, which is arbitrary. By using this equation (2) as the gait evaluation model instead of the equation (1), the gait evaluation of the subject can be performed in the same manner. According to such a modification, a model using a logistic curve is used. Therefore, the objective variable y can be a numerical value within the range of 0 to 1, which is convenient for the calculation of the walking evaluation model, and the calculated walking evaluation value is a numerical value indicating the ratio of the degree of abnormality. Therefore, it is possible to easily estimate the degree of abnormality (level) of the subject.

  Further, the walking evaluation model is not limited to a multiple regression model or a logistic regression model. For example, a decision tree, a support vector machine (SVM), a random forest (RF), or the like may be applied to the walking evaluation model.

In the above-described embodiment, an example has been described in which the Gars reference value of the evaluation reference person is determined in each of Gars1 to Gars7 (Gars index), and the Gars value of the subject is calculated in each of Gars1 to Gars7. However, in addition to (or instead of) the seven indices Gars1 to Gars7, as another index, the sum of the Gars reference values of Gars1 to Gars7 may be used as the target variable. In this case, the sum of the respective Gars reference value Gars1~Gars7 are substituted into y of the equation (1), the coefficient associated with the index _a 0 ~a _n is calculated. Based on this coefficient and the walking parameters extracted from the walking data of the subject, the sum of the Gars values of the subject is calculated from the above equation (1). In this case, it is possible to quickly and easily know the comprehensive determination result regarding the presence or absence of the walking abnormality of the subject.

  According to the present invention described above, it is possible to provide a walking evaluation system and a walking evaluation method capable of improving the reliability of walking evaluation. Therefore, the present invention is an invention that can be used industrially. For example, the present invention can be used in various fields such as the electrical equipment industry, software industry, sock manufacturing industry, shoe manufacturing industry, insole manufacturing industry, medical and rehabilitation fields, and the like.

  The suitability and accuracy of walking evaluation by the walking evaluation system 200 and the walking evaluation method according to the present embodiment described above were examined. In the embodiment described below, as an example only, an example will be described in which walking data is acquired with two sensor configurations, and the fitness and accuracy of the walking evaluation model are checked. As described above, the gait evaluation system and the gait evaluation method according to the present invention can improve gait evaluation reliability by extracting gait parameters from gait data having various characteristics and calculating coefficients. For this reason, the walking evaluation system and the walking evaluation method according to the present invention are not limited to the sensor configuration described below, and the reliability of the walking evaluation can be improved with an arbitrary sensor configuration.

(Example 1)
In Example 1, the fitness and the accuracy of the walking evaluation model were examined when the walking evaluation model was a multiple regression model. In the first embodiment, the walking data is acquired when the sensor of the walking data acquisition unit 1 is configured with the first sensor configuration as shown in FIG. 10 and when the sensor is configured with the second sensor configuration. The bending sensors used in the first sensor configuration are the MP bending sensor 21 and the thigh bending sensor 22 shown in FIG. 3, and the pressure sensors are the heel pressure sensor 31, the MP pressure sensor 32, and the toe pressure sensor 33 shown in FIG. And The number of walking parameters used in each sensor configuration is as shown in FIG.

  In the first embodiment, walking data was obtained from 29 men and 29 women, and 101 walking data were obtained for each sensor configuration. The 101 pieces of walking data include walking data of at least one of the right foot and the left foot of each subject. For each gait data, a gait diagnosis was performed by a physiotherapist to determine the Gars reference value. The classification of the Gars reference value is as shown in FIG.

  The walking data associated with each sensor configuration was randomly sampled, and 3/4 walking data was used as the walking data of the evaluation reference person to calculate the coefficients of the walking evaluation model. The remaining quarter of the walking data was used to calculate Gars values as walking data of the subject.

The Gars value was calculated in the same manner as the calculation method described in the above-described embodiment. Based on the calculated Gars value, a coefficient of freedom adjusted for each sensor configuration was calculated. For this calculation, statistical software (SPSS Statistics ver. 17.0) was used. More specifically, the degree of freedom adjusted determination coefficient was calculated using the following equation.

は、自由度調整済み決定係数である。Ｒ^２は、決定係数であり、Ｇａｒｓ値の分散に対する予測値の分散の割合を示す。 here,

Is the coefficient of determination adjusted for the degree of freedom. R ² is the coefficient of determination indicates the percentage of the variance of the predicted value for the variance of Gars value.

は、予測値（すなわち、歩行評価モデルで得られたＧａｒｓ値）であり、

は、予測値の平均値であり、

は、Ｇａｒｓ基準値の平均値である。 y _i is the Gars reference value of the evaluator,

Is the predicted value (ie, the Gars value obtained by the walking evaluation model),

Is the average of the predicted values,

Is the average of the Gars reference values.

  N is the number of walking data (the number of samples), and p is the number of independent variables (the number of walking parameters selected by the model in the present embodiment).

  The determination coefficient after the degree of freedom adjustment is calculated for each of Gars1 to Gars7, and the average value thereof is shown in FIG.

  As shown in FIG. 12, the determination coefficients after the degree of freedom adjustment in the first sensor configuration and the second sensor configuration both exceeded 0.5. If the coefficient of determination adjusted with the degree of freedom exceeds 0.5, it is generally considered that the model has good fitness (for example, see “Medical Multivariate Data Analysis with SPSS” (Tokyo Shuppan), 2008, p. 52). From this, it is considered that the walking evaluation system 200 and the walking evaluation method have a good fitness.

ここで、ｘ_ｉは歩行評価モデルで得られたＧａｒｓ値であり、ｙ_ｉは評価基準者のＧａｒｓ基準値である。 The root mean square error (RMSE) of each sensor configuration was calculated based on the calculated Gars value. The following equation was used for this calculation.

Here, x _i is the Gars value obtained by the walking evaluation model, and y _i is the Gars reference value of the evaluation reference person.

  The root mean square error is calculated for each of Gars1 to Gars7, and their average values are shown in FIG.

  As shown in FIG. 12, the root mean square error of the first sensor configuration and the second sensor configuration were both less than 0.5. If the root mean square error is less than 0.5, it is possible to prevent the calculated Gars value from being shifted by one or more points when the calculated Gars value is rounded to an integer. That is, it is possible to prevent the accuracy of the Gars value from decreasing due to rounding. Therefore, it is considered that the walking evaluation system 200 and the walking evaluation method have good accuracy.

ここで、ＴＰは、真陽性（True Positive）のデータ数であり、ＴＮは、真陰性（True Negative）のデータ数であり、ＦＰは、偽陽性（False Positive）のデータ数であり、ＦＮは、偽陰性（False Negative）のデータ数である。また、算出されたＧａｒｓ値は、それを四捨五入してＧａｒｓ基準値と比較することで、ＴＰ、ＴＮ、ＦＰ、ＦＮのいずれに属するかを決定した。 Further, based on the calculated Gars value, the correct answer rate (Accuracy) in each sensor configuration was obtained. More specifically, a mixing matrix was created from the Gars value obtained from the gait evaluation model and the Gars reference value (true value) of an expert, and was obtained from the following equation.

Here, TP is the number of true-positive data, TN is the number of true-negative data, FP is the number of false-positive data, and FN is the number of false-positive data. , The number of false negative data. Further, the calculated Gars value was rounded off and compared with the Gars reference value to determine which of the TP, TN, FP and FN it belongs to.

  The correct answer rate is calculated for each of Gars1 to Gars7, and the average value thereof is shown in FIG.

  As shown in FIG. 12, the correct answer ratio in the first sensor configuration and the second sensor configuration both exceeded 0.8. Therefore, it is considered that the walking evaluation system 200 and the walking evaluation method have good accuracy.

(Example 2)
In Example 2, the fitness and the accuracy of the walking evaluation were examined when the walking evaluation model was a logistic regression model. The walking data, the sensor configuration of the walking data acquisition unit 1 and the walking parameters used in the second embodiment were the same as those in the first embodiment.

  Also in the second embodiment, the walking data used in the first embodiment is used as the walking data of the evaluation reference person, and the walking data used in the first embodiment is used as the walking data of the subject.

ここで、ＴＰ、ＦＮは、実施例１と同様である。 The Gars value was calculated in the same manner as in the above-described modification. Based on the calculated Gars value, a recall (Recall) in each sensor configuration was obtained. More specifically, a mixing matrix was created from the Gars value obtained from the gait evaluation model and the Gars reference value (true value) of an expert, and was obtained from the following equation.

Here, TP and FN are the same as in the first embodiment.

  The recall is calculated for each of Gars1 to Gars7, and the average value thereof is shown in FIG.

  As shown in FIG. 13, the recall in the first sensor configuration and the second sensor configuration both exceeded 0.7. Therefore, it is considered that the walking evaluation system 200 and the walking evaluation method have good accuracy.

  Further, based on the calculated Gars value, the correct answer rate (Accuracy) in each sensor configuration was obtained. The correct answer rate was obtained in the same manner as in Example 1.

  The correct answer rate is calculated for each of Gars1 to Gars7, and the average value thereof is shown in FIG.

  As shown in FIG. 13, the correct answer rate in both the first sensor configuration and the second sensor configuration exceeded 0.8. Therefore, it is considered that the walking evaluation system 200 and the walking evaluation method have good accuracy.

1 walking data acquisition unit 200 walking evaluation system 205 extraction unit 206 coefficient storage unit 207 evaluation value calculation unit 208 input unit 209 coefficient calculation unit 210 determination unit 211 display unit

Claims (15)

A walking evaluation system for performing walking evaluation from the walking data of the subject,
A walking data acquisition unit that acquires the walking data of the subject,
An extracting unit that extracts a walking parameter from the walking data acquired by the walking data acquiring unit,
A coefficient storage unit storing coefficients,
The walking parameter extracted by the extraction unit, based on the coefficient stored in the coefficient storage unit, based on a walking evaluation model, an evaluation value calculation unit that calculates a walking evaluation value of the subject,
The coefficient stored in the coefficient storage unit is a value obtained from the walking evaluation model based on a walking parameter extracted from walking data of the evaluation reference person and a walking evaluation reference value of the evaluation reference person. Oh it is,
The gait evaluation system, wherein the gait evaluation reference value is a score representing the gait abnormality specified by the modified gait abnormality scale . Wherein the calculated by the evaluation value calculation section based on the walking evaluation value, the further comprising a determination unit which walking of the subject, gait assessment system according to claim 1. The walking evaluation model is a multiple regression model,
The evaluation value calculation unit calculates a plurality of the walking evaluation values,
The walking evaluation system according to claim 2 , wherein the determining unit determines the walking of the subject based on a sum of the plurality of walking evaluation values calculated by the evaluation value calculating unit. A walking evaluation system for performing walking evaluation from the walking data of the subject,
A walking data acquisition unit that acquires the walking data of the subject,
An extracting unit that extracts a walking parameter from the walking data acquired by the walking data acquiring unit,
A coefficient storage unit storing coefficients,
The walking parameter extracted by the extraction unit, based on the coefficient stored in the coefficient storage unit, based on a walking evaluation model, an evaluation value calculation unit that calculates a walking evaluation value of the subject,
The coefficient stored in the coefficient storage unit is a value obtained from the walking evaluation model based on a walking parameter extracted from walking data of the evaluation reference person and a walking evaluation reference value of the evaluation reference person. Oh it is,
The gait evaluation system, wherein the gait evaluation reference value is a score representing a gait abnormality defined by the modified gait abnormality scale, and is a value obtained by adding a score based on a plurality of indices . The walking evaluation system according to claim 4 , further comprising a determining unit that determines whether the subject is walking based on the walking evaluation value calculated by the evaluation value calculating unit. An input unit for inputting the walking evaluation reference value of the evaluation reference person,
Coefficient calculation for calculating the coefficient from the walking evaluation model based on the walking parameter extracted from the walking data of the evaluation reference person by the extraction unit and the walking evaluation reference value input by the input unit And a part,
The walking evaluation system according to any one of claims 1 to 5, wherein the coefficient stored in the coefficient storage unit is a value calculated by the coefficient calculation unit. The walking evaluation system according to any one of claims 1 to 6 , wherein the walking evaluation reference value of the evaluation reference person is a value determined by an expert. The walking evaluation system according to any one of claims 1 to 7 , further comprising a display unit that displays a walking evaluation result of the subject based on the walking evaluation value calculated by the evaluation value calculating unit. The walking evaluation system according to any one of claims 1 to 8 , wherein the walking evaluation model is a multiple regression model or a logistic regression model.   The walking evaluation system according to any one of claims 1 to 9, wherein the extraction unit extracts a walking parameter associated with a stance phase and a walking parameter associated with a swing phase.   The walker according to any one of claims 1 to 10, wherein the extraction unit extracts a walking parameter associated with a heel rocker period, a walking parameter associated with an ankle rocker period, and a walking parameter associated with a forefoot rocker period. The walking evaluation system according to claim 1. An operation method of a walking evaluation system for performing walking evaluation from the walking data of the subject,
A walking data acquisition unit of the walking evaluation system, a data acquisition step of acquiring walking data of the subject,
An extraction step of extracting the walking parameter from the walking data , wherein the extraction unit of the walking evaluation system ;
An evaluation value calculation unit of the walking evaluation system includes an evaluation value calculation step of calculating a walking evaluation value of the subject from a walking evaluation model based on the walking parameters and a coefficient stored in a coefficient storage unit. ,
The coefficient stored in the coefficient storage unit is a value obtained from the walking evaluation model based on a walking parameter extracted from walking data of the evaluation reference person and a walking evaluation reference value of the evaluation reference person. Oh it is,
The method for operating a walking evaluation system, wherein the walking evaluation reference value is a score representing a walking abnormality specified by a modified walking abnormality scale . An operation method of a walking evaluation system for performing walking evaluation from the walking data of the subject,
A walking data acquisition unit of the walking evaluation system, a data acquisition step of acquiring walking data of the subject,
An extraction step of extracting the walking parameter from the walking data , wherein the extraction unit of the walking evaluation system ;
An evaluation value calculation unit of the walking evaluation system includes an evaluation value calculation step of calculating a walking evaluation value of the subject from a walking evaluation model based on the walking parameters and a coefficient stored in a coefficient storage unit. ,
The coefficient stored in the coefficient storage unit is a value obtained from the walking evaluation model based on a walking parameter extracted from walking data of the evaluation reference person and a walking evaluation reference value of the evaluation reference person. Oh it is,
The method for operating a walking evaluation system, wherein the walking evaluation reference value is a score representing a walking abnormality defined by the modified walking abnormality scale, and is a value obtained by adding points based on a plurality of indices . A data acquisition step in which the walking data acquisition unit acquires the walking data of the evaluation criterion,
An extraction step wherein the extracting unit, which extracts the gait parameters from the gait data of the evaluation criteria's,
The input of the gait assessment system, an input step of the walking evaluation reference value of the evaluation criteria's are entered,
A coefficient calculating unit of the walking evaluation system , further comprising: a coefficient calculating step of calculating the coefficient from the walking evaluation model based on the walking parameters of the evaluation reference person and the walking evaluation reference value;
The coefficients stored in the coefficient storage unit is a value calculated in the coefficient calculating step, a method of operating a gait assessment system according to claim 12 or 13. The operation method of the walking evaluation system according to claim 14 , wherein the walking evaluation reference value of the evaluation reference person is a value determined by an expert.

Images