Cognitive function estimation device, cognitive function estimation method, cognitive function estimation program, and cognitive function estimation system
The cognitive function estimation system using foot-mounted inertial sensors accurately identifies MCI by measuring gait parameters, enhancing detection accuracy to 84.2% and facilitating timely interventions.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- IWAI AI CO LTD
- Filing Date
- 2023-06-30
- Publication Date
- 2026-06-04
Smart Images
Figure 0007870081000008 
Figure 0007870081000009 
Figure 0007870081000010
Abstract
Description
Technical Field
[0001] The present invention relates to a cognitive function estimation device, a cognitive function estimation method, a cognitive function estimation program, and a cognitive function estimation system.
Background Art
[0002] A method for easily determining whether a subject has dementia has been studied. Patent Document 1 discloses a dementia determination program that determines whether a subject has dementia by using walking data based on lumbar acceleration information.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] Mild cognitive impairment (MCI) is a state in which cognitive functions such as memory and attention are impaired but dementia has not yet occurred, corresponding to a state intermediate between a normal state and dementia. It is known that the recovery rate is higher when appropriate measures are taken at the MCI stage than when treatment is started after dementia has occurred. Therefore, it is important to detect symptoms at the MCI stage. However, it is difficult to undergo hospital tests at the MCI stage because it places a heavy burden on the test subjects. In addition, conventional simple methods for estimating dementia have low estimation accuracy.
[0005] An object of the present invention is to provide a cognitive function estimation device, a cognitive function estimation method, a cognitive function estimation program, and a cognitive function estimation system that can easily and accurately estimate the cognitive function of a subject.
Means for Solving the Problems
[0006] The cognitive function estimation device according to the present invention comprises a gait information acquisition unit, an estimation parameter calculation unit, and a determination unit. The aforementioned walking information acquisition unit is configured to acquire walking information obtained by an inertial sensor attached to the subject's foot. The walking information includes at least one of the information relating to the acceleration of the subject's foot during walking and information relating to its angular velocity. The estimation parameter calculation unit is configured to calculate cognitive function estimation parameters based on the walking information. The determination unit is configured to determine whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameters.
[0007] The cognitive function estimation method according to the present invention is a cognitive function estimation method comprising a gait information acquisition step, an estimation parameter calculation step, and a determination step, The aforementioned gait information acquisition step acquires gait information measured by an inertial sensor attached to the subject's foot, The walking information includes at least one of the information relating to the acceleration of the subject's foot during walking and information relating to its angular velocity. The aforementioned estimation parameter calculation step calculates cognitive function estimation parameters based on the walking information, The determination step determines whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameters.
[0008] The cognitive function estimation program according to the present invention is a cognitive function estimation program that causes a computer to perform a gait information acquisition procedure, an estimation parameter calculation procedure, and a judgment procedure, The aforementioned gait information acquisition procedure acquires gait information obtained by an inertial sensor attached to the subject's foot, The walking information includes at least one of the information relating to the acceleration of the subject's foot during walking and information relating to its angular velocity. The above-mentioned procedure for calculating estimated parameters involves calculating estimated cognitive function parameters based on the gait information, The aforementioned determination procedure determines whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameters.
[0009] The cognitive function estimation system according to the present invention is a cognitive function estimation system comprising a cognitive function estimation device and a measurement device according to the present invention, The measuring device comprises an inertial sensor and a communication unit. The communication unit is capable of communicating with the cognitive function estimation device and can transmit the walking information to the cognitive function estimation device. [Effects of the Invention]
[0010] According to the present invention, a cognitive function estimation device, a cognitive function estimation method, a cognitive function estimation program, and a cognitive function estimation system can be provided that can estimate a subject's cognitive function simply and accurately. [Brief explanation of the drawing]
[0011] [Figure 1] Figure 1 is a block diagram showing the configuration of a cognitive function estimation system according to one embodiment of the present invention. [Figure 2] Figure 2 is a block diagram showing the configuration of a cognitive function estimation device according to one embodiment of the present invention. [Figure 3] Figure 3 is a block diagram showing an example of the configuration of a measuring device. [Figure 4] Figure 4 shows a subject walking with a measurement device attached. [Figure 5] Figure 5 is a partially enlarged view of Figure 4, illustrating an example of how the measuring device is mounted. [Figure 6] Figure 6 is a flowchart showing an example of processing in a cognitive function estimation device according to one embodiment of the present invention. [Figure 7] Figure 7 is a block diagram showing an example of the configuration of a cognitive function estimation device according to another embodiment of the present invention. [Figure 8] Figure 8 is a flowchart showing an example of processing in a cognitive function estimation device according to another embodiment of the present invention.
Embodiments for Carrying Out the Invention
[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the present invention is not limited to these embodiments.
[0013] [Embodiment 1] FIG. 1 is a block diagram showing a cognitive function estimation system 100 according to an embodiment of the present invention. The cognitive function estimation system 100 according to an embodiment of the present invention includes a cognitive function estimation device 1 (hereinafter referred to as the estimation device 1) and a measurement device 2. The estimation device 1 includes a walking information acquisition unit 11, an estimation parameter calculation unit 12, a determination unit 13, and an output unit 14. The measurement device 2 includes an inertial sensor 21 and a communication unit 22. As shown in FIG. 1, the communication unit 22 of the measurement device 2 can communicate with the estimation device 1 via, for example, a communication line network 3. However, the communication between the estimation device 1 and the measurement device 2 is not limited to this mode. For example, a wired connection using a cable or a wireless connection by wireless communication may be used. Thereby, the communication unit 22 can transmit the walking information described later to the estimation device 1. The cognitive function estimation system 100 may include, for example, a plurality of measurement devices 2. Examples of the wireless connection include Wi-Fi (registered trademark), Bluetooth (registered trademark), LPWA (Low Power Wide Area), etc. As the wireless communication, either a form in which each device communicates directly (Ad Hoc communication) or an indirect communication via an access point can be used. The estimation device 1 of the present embodiment may be incorporated into a server as a system. Further, the estimation device 1 of the present embodiment may be a personal computer (PC), a tablet terminal, etc. in which the program of the present invention is installed. Although not shown, the estimation device 1 can also be connected to an external terminal of the system administrator via, for example, the communication line network 3, and the system administrator may manage the estimation device 1 from the external terminal.
[0014] The communication network 3 is not particularly limited and can use any publicly known network, such as a wired or wireless network. The communication network 3 may be, for example, an Internet connection, WWW (World Wide Web), telephone line, LAN (Local Area Network), Wi-Fi, LPWA (Low Power Wide Area), etc.
[0015] Figure 2 is a block diagram of the hardware configuration of the estimation device 1 according to this embodiment. The estimation device 1 includes, for example, a CPU (central processing unit) 101, memory 102, bus 103, storage device 104, input device 106, display 107, communication device 108, etc. Each part of the estimation device 1 is connected via the bus 103 by its respective interface (I / F).
[0016] The CPU 101 operates in conjunction with other components, such as a controller (system controller, I / O controller, etc.), and is responsible for the overall control of the estimation device 1. In the estimation device 1, the CPU 101 executes, for example, the program 105 of the present invention and other programs, and also reads and writes various types of information. Specifically, for example, the CPU 101 functions as a walking information acquisition unit 11, an estimation parameter calculation unit 12, a determination unit 13, and an output unit 14. The estimation device 1 is equipped with a CPU as its processing unit, but it may also be equipped with other processing units such as a GPU (Graphics Processing Unit) or an APU (Accelerated Processing Unit) instead of a CPU, or a combination of a CPU and these.
[0017] Memory 102 includes, for example, main memory. Main memory is also called primary memory. When the CPU 101 performs processing, memory 102 reads various operational programs, such as the program 105 of the present invention, which is stored in the storage device 104 (auxiliary storage device) described later. The CPU 101 then reads and decodes the data from memory 102 and executes the program. Main memory is, for example, RAM (Random Access Memory). Memory 102 also includes, for example, ROM (Read-Only Memory).
[0018] Bus 103 can also be connected to external devices, for example. Examples of external devices include external storage devices (external databases, etc.) and printers. Estimation device 1 can be connected to the communication network 3, for example, via a communication device 108 connected to bus 103, and can also be connected to external devices via the communication network 3. Furthermore, estimation device 1 can also be connected to measurement device 2 via the communication device 108 and the communication network 3.
[0019] The storage device 104 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 104 stores an operating program including the program 105 of the present invention. The storage device 104 includes, for example, a storage medium and a drive for reading and writing to the storage medium. The storage medium is not particularly limited and may be internal or external, and may be an HD (hard disk), SSD, FD (floppy disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The drive is not particularly limited. The storage device 104 may be, for example, a hard disk drive (HDD) in which the storage medium and the drive are integrated. If the estimation device 1 includes, for example, a storage unit, the storage device 104 functions as a storage unit.
[0020] The estimation device 1 further comprises, for example, an input device 106 and a display 107. The input device 106 may be, for example, a pointing device such as a touch panel, trackpad, or mouse; a keyboard; imaging means such as a camera or scanner; a card reader such as an IC card reader or magnetic card reader; or an audio input means such as a microphone. The display 107 may be, for example, a display device such as an LED display or a liquid crystal display. In this embodiment 1, the input device 106 and the display 107 are configured separately, but the input device 106 and the display 107 may be configured as an integrated unit, such as in a touch panel display.
[0021] In the estimation device 1, the memory 102 and the storage device 104 can also store user access information and log information, as well as information obtained from an external database (not shown).
[0022] Figure 3 is a block diagram showing an example of the hardware configuration of the measurement device 2. As shown in Figure 3, the measurement device 2 includes, for example, a CPU 201, memory 202, bus 203, storage device 204, input device 206, communication device (communication unit 22), display 207, inertial sensor 21, etc. Each part of the measurement device 2 is connected via the bus 203 by its respective interface (I / F). For explanations of each component of the measurement device 2 other than the inertial sensor 21, the explanations of each component of the estimation device 1 can be used as a reference.
[0023] The inertial sensor 21 is a sensor capable of measuring acceleration, angular velocity, or both. The inertial sensor 21 is, for example, a 6-axis sensor capable of measuring acceleration in 3 axes and angular velocity in 3 axes. The measuring device 2 is attached to the subject's foot and is configured to measure the acceleration, angular velocity, or both of the subject's foot using the inertial sensor 21.
[0024] Next, an example of the process for estimating cognitive function using the cognitive function estimation system according to this embodiment will be described.
[0025] Figure 4 shows a subject S whose cognitive function is to be estimated according to this embodiment. First, the measurement device 2 is attached to the foot of subject S. The measurement device 2 may be directly attached to the foot of subject S, or it may be attached indirectly by sandwiching it between shoes, socks, tights, etc. The specific location where the measurement device 2 is attached is not particularly limited and it can be attached to the instep, toes, heel, side, or sole of subject S's foot. From the viewpoint of reducing disturbances in measurement data due to impacts during walking, it is preferable to attach the measurement device 2 to the instep or side of the foot. Figure 5 is an enlarged view of the area enclosed by the dashed line V in Figure 4, and shows an example of how the measurement device 2 is attached. In the embodiment shown in Figure 5, the measurement device 2 is attached to a position corresponding to the instep of subject S's shoelace 30.
[0026] Preferably, the measurement device 2 is attached to the subject's waist in addition to their feet. By using gait information obtained from the subject's waist movements in conjunction with the measurement device, the accuracy of estimating cognitive function can be further improved.
[0027] The measuring device 2 measures the subject's walking information. Here, "walking information" refers to information representing the subject's walking state, specifically information regarding the acceleration or angular velocity of a part of the subject's body during walking, as measured by the inertial sensor 21. In this embodiment, the walking information includes at least one of the information regarding the acceleration and angular velocity of the subject's feet during walking. The walking information may further include information regarding the acceleration or angular velocity of the subject's hips.
[0028] The measurement device 2 transmits the measured gait information to the estimation device 1 via the communication network 3 using the communication unit 22. At this time, the measurement device 2 may transmit the acceleration or angular velocity data of the subject's feet measured by the inertial sensor 21 directly to the estimation device 1 as gait information, or it may extract or calculate the data necessary for calculating the cognitive function estimation parameters described later, and transmit that data to the estimation device 1 as gait information. Alternatively, the measurement device 2 may calculate some or all of the cognitive function estimation parameters described later, and transmit the calculated cognitive function estimation parameters to the estimation device 1 as gait information.
[0029] Next, processing by the estimation device 1 is started. Figure 6 is a flowchart showing an example of processing in the estimation device 1. First, the walking information acquisition unit 11 of the estimation device 1 acquires the subject's walking information (S1, walking information acquisition step). Specifically, the walking information acquisition unit 11 acquires walking information transmitted from the measurement device 2 via the communication network 3 using the communication device 108. If the estimation device 1 is equipped with a storage unit, the estimation device 1 may store the acquired walking information in the storage unit. If the storage unit of the estimation device 1 is storing walking information, the walking information acquisition unit 11 may read the walking information stored in the storage unit and acquire the subject's walking information. Also, for example, if the walking information measured by the measurement device 2 is stored in an external database, the walking information acquisition unit 11 may acquire the subject's walking information from the database.
[0030] Next, the estimation parameter calculation unit 12 calculates cognitive function estimation parameters based on the acquired gait information (S2, estimation parameter calculation step). Cognitive function estimation parameters are various parameters for estimating the cognitive function of the subject. If cognitive function estimation parameters are calculated in the measurement device 2 and transmitted as gait information to the estimation device 1, the estimation parameter calculation unit may calculate the gait information directly as cognitive function estimation parameters without performing any calculation processing.
[0031] Examples of cognitive function estimation parameters include the subject's gait, stance time, ground contact time / stance time, heel lift time / stance time, walking speed, maximum swing speed, lift-off angle, foot trajectory length per step, maximum heel height per step, maximum toe height per step, stride length, angular velocity waveform similarity, and acceleration waveform similarity. In particular, individuals with MCI tend to walk with their feet not lifting high and shuffling along the ground, a condition known as "shuffling." This "shuffling" condition is clearly reflected in parameters such as maximum swing speed, lift-off angle, maximum heel height per step, and maximum toe height per step. Therefore, it is preferable that the estimation parameter calculation unit be configured to calculate at least one of the parameters that easily reflect the "shuffling" condition, namely maximum swing speed, lift-off angle, maximum heel height per step, and maximum toe height per step, as cognitive function estimation parameters. Such a configuration further improves the accuracy of cognitive function assessment.
[0032] The following details the parameters for estimating cognitive function. In the following explanation, the x-axis represents the subject's direction of movement during walking (forward / backward), the y-axis represents the left / right direction, and the z-axis represents the height direction (up / down). The x, y, and z axes are also shown in Figure 4.
[0033] Stride is the number of steps per unit of time. One step is counted from the moment one foot touches the ground until it lifts off again.
[0034] The stance phase is the time spent in the stance stage of a step. The stance phase is the period from when one foot is on the ground and the other foot leaves the ground until the other foot touches the ground again.
[0035] Ground contact time is the time from when the foot touches the ground until it leaves the ground again, and can be rephrased as the time per step.
[0036] Heel-lift time is the time from when the heel lifts off the ground while the entire foot is in contact with the ground until the entire foot lifts off the ground again. In other words, it is the time when the toes are in contact with the ground but the heel is off the ground.
[0037] Maximum swing speed is the maximum speed of the foot in the x-axis direction during the period from when the foot leaves the ground until it touches the ground again (swing phase).
[0038] The lift-off angle is the angle between the foot and the ground at the moment the toes leave the ground during the foot-to-foot transition.
[0039] The length of a single step is the length of the trajectory the foot traces from the moment it leaves the ground until it touches the ground again. This value is measured in three-dimensional space, not as a unidirectional projection. The maximum heel height of a single step is the maximum height the heel reaches from the moment it leaves the ground until it touches the ground again. The maximum toe height of a single step is the maximum height the toes reach from the moment it leaves the ground until it touches the ground again.
[0040] Waveform similarity is an index that indicates how similar the waveforms are when multiple waveforms are superimposed by taking a step-by-step sample of the acceleration or angular velocity along a certain axis. In this specification, for example, the acceleration waveform similarity in the x-axis direction is denoted as "x-axis acceleration waveform similarity," and the angular velocity waveform similarity in the y-axis direction is denoted as "y-axis angular velocity waveform similarity."
[0041] Waveform similarity can be calculated, for example, by the following procedure. First, the offset component of the waveform is removed, and the waveform Wj for each step (stride) is identified by the peak value. Next, the waveform for each step is linearly interpolated so that it consists of 100 points to obtain Wj(s) (s is an integer between 1 and 100). Next, the average of each stride Wj(s) is taken as shown in equation (i) below to obtain Wmean(s). Finally, the similarity γj between each stride Wj and Wmean is calculated using equation (ii) below, and the average value of the similarity γj is taken as the waveform similarity.
[0042]
number
[0043] Of the cognitive function estimation parameters mentioned above, stance time, ground contact time, heel lift time, maximum swing speed, lift-off angle, maximum heel height per step, and maximum toe height per step cannot be obtained solely from gait information measured by inertial sensors attached to the waist, but rather from gait information measured by inertial sensors attached to the feet.
[0044] Next, the determination unit 13 of the estimation device 1 determines whether or not the subject has MCI based on the cognitive function estimation parameters (S3, determination step).
[0045] The determination unit 13 determines whether or not the subject has MCI based on cognitive function estimation parameters such as gait, stance time, ground contact time / stance time, heel lift time / stance time, walking speed, maximum swing speed, lift-off angle, foot trajectory length per step, maximum heel height per step, maximum toe height per step, stride length, angular velocity waveform similarity, and acceleration waveform similarity, using the following equation (1). In equation (1), x1 to x n These are parameters for estimating cognitive function, and α1~α n And β is a coefficient, and p is a probability. α1~α n The coefficients of β and β can be determined, for example, by performing a binomial logistic regression analysis as in the example described later. To determine whether or not it is MCI, for example, the calculated cognitive function estimation parameters are substituted into equation (1) to obtain the probability p, and if p is 0.5 or greater, it is determined to be MCI, and if p is less than 0.5, it is determined not to be MCI.
[0046]
number
[0047] Next, the output unit 14 outputs the result of the determination made by the determination unit 13 (S4, output step). The output unit 14 may output the determination result to the display 107, for example, or to an external device via the communication device 108. The external device may be, for example, a printer, a mobile device such as a tablet terminal, or a measuring device 2. Then, the processing by the estimation device 1 is completed.
[0048] When the output unit 14 outputs the judgment result to the measuring device 2, the display 207 of the measuring device 2 may be capable of displaying the judgment result.
[0049] According to this embodiment, cognitive function is estimated using gait information, which includes information on the acceleration or angular velocity of the subject's feet, making it possible to accurately estimate whether or not the subject has MCI (Mild Cognitive Impairment).
[0050] [Embodiment 2] Next, another embodiment of the present invention will be described. Figure 7 is a block diagram showing the configuration of an example of the estimation device 1A of this embodiment. As shown in Figure 7, the estimation device 1A further includes a cognitive function estimation unit 15 in addition to the configuration of the estimation device 1 described above. The hardware configuration of the estimation device 1A is the same as that of the estimation device 1 in Figure 2, except that the CPU 101 has the configuration of the estimation device 1A in Figure 7.
[0051] An example of processing in the estimation system including the estimation device 1A and the measurement device 2 of this embodiment will be explained based on the flowchart in Figure 8. Figure 8 is a flowchart of an example of processing (S1-S3, S11, S4) of the estimation device 1A. An example of processing for estimating cognitive function according to this embodiment will be explained below.
[0052] First, the gait information acquisition step S1, the estimated parameter calculation step S2, and the determination step S3 are performed in the same manner as the processing by the estimation device 1 described above to determine whether or not the subject has MCI.
[0053] If it is determined in the determination step S3 that the subject has MCI (YES in S3), the cognitive function estimation unit 15 of the estimation device 1A estimates the subject's cognitive function level (S11, cognitive function estimation step).
[0054] The cognitive function level of a subject can be estimated by the cognitive function estimation unit 15, for example, using a predetermined regression equation. The cognitive function level can be estimated based on, for example, the Revised Hasegawa Dementia Scale (HDS-R score) or the Mini-Mental State Examination (MMSE). For example, when using the HDS-R score as the basis, first, the HDS-R scores of multiple subjects and cognitive function estimation parameters obtained from gait information are measured. Next, a multiple regression analysis is performed with the HDS-R score as the dependent variable and the cognitive function estimation parameters as independent variables to determine the coefficients α1'~αn' and β' in the regression equation (2) that estimates the HDS-R score. By substituting the subject's cognitive function estimation parameters into the regression equation (2) obtained in this way, the subject's cognitive function level (estimated HDS-R score) can be calculated.
[0055]
number
[0056] Then, the output unit 14 of the estimation device 1A outputs at least one of the judgment result in the judgment step S3 and the cognitive function level calculated in the cognitive function estimation step S11 (S4, output step). For example, the output unit 14 outputs the judgment result and the cognitive function level for subjects who are determined to have MCI, and outputs the judgment result for subjects who are determined not to have MCI (NO in the judgment step S3). Then, the processing by the estimation device 1A ends.
[0057] According to this embodiment, in addition to determining whether or not a subject has MCI (Mild Cognitive Impairment), the cognitive function level can also be estimated, allowing for a more detailed estimation of the subject's cognitive function.
[0058] [Embodiment 3] Yet another embodiment of the present invention relates to a cognitive function estimation method. The cognitive function estimation method according to this embodiment is a cognitive function estimation method having a gait information acquisition step S1, an estimation parameter calculation step S2, and a determination step S3, as shown in the flowchart of Figure 6. The cognitive function estimation method may further have an output step S4.
[0059] The gait information acquisition step S1 is a step of acquiring gait information measured by an inertial sensor 21 attached to the subject's foot. The gait information includes at least one of the information regarding the acceleration and angular velocity of the subject's foot during walking. The estimated parameter calculation step S2 is a step of calculating estimated cognitive function parameters based on the gait information. The determination step S3 is a step of determining whether or not the subject has mild cognitive impairment (MCI) based on the estimated cognitive function parameters. The output step S4 is a step of outputting the determination result from the determination step S3.
[0060] As shown in the flowchart of Figure 8, the cognitive function estimation method according to this embodiment may include a cognitive function estimation step S11 for estimating the cognitive function level of a subject who has been determined to have MCI in the determination step S3.
[0061] According to the cognitive function estimation method of this embodiment, the cognitive function of a subject can be estimated simply and accurately. Specific details and preferred configurations of each step of the cognitive function estimation method according to this embodiment are omitted here, as they are based on the descriptions of Embodiments 1 and 2 described above.
[0062] [Embodiment 4] Yet another embodiment of the present invention relates to a cognitive function estimation program. The cognitive function estimation program according to this embodiment is a cognitive function estimation program that causes a computer to perform a gait information acquisition procedure, an estimation parameter calculation procedure, and a judgment procedure. The cognitive function estimation program may also cause the computer to perform an output procedure.
[0063] The gait information acquisition procedure is a procedure for acquiring gait information obtained by inertial sensors attached to the subject's feet. The gait information includes at least one of the following: information on the acceleration of the subject's feet during walking and information on angular velocity. The estimated parameter calculation procedure is a procedure for calculating estimated cognitive function parameters based on the gait information. The determination procedure is a procedure for determining whether or not the subject has mild cognitive impairment (MCI) based on the estimated cognitive function parameters.
[0064] The cognitive function estimation program according to this embodiment may also cause the computer to further execute a cognitive function estimation procedure that estimates the cognitive function level of a subject who has been determined to have MCI in the determination procedure.
[0065] The cognitive function estimation program according to this embodiment allows for the simple and accurate estimation of a subject's cognitive function. The gait information acquisition procedure, estimation parameter calculation procedure, judgment procedure, output procedure, and cognitive function estimation procedure of the cognitive function estimation program according to this embodiment correspond to the gait information acquisition step S1, estimation parameter calculation step S2, judgment step S3, output step S4, and cognitive function estimation step S11 in Embodiments 1 and 2 described above, respectively. Specific aspects and preferred configurations of each procedure are omitted here, as they are based on the descriptions of Embodiments 1 and 2 described above. Furthermore, the cognitive function estimation program according to this embodiment may be recorded on a computer-readable recording medium. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples include random access memory (RAM), read-only memory (ROM), hard disk (HD), SSD, optical disk, floppy disk (FD), etc. [Examples]
[0066] The present invention will be further described below with reference to examples, but the present invention is not limited to these examples.
[0067] [Example 1] (1) Subjects The subjects were 38 elderly individuals (23 males and 15 females) with an average age of 74 years (65-89 years). The subjects were informed about the purpose and objectives of the study and how the results would be handled, and informed consent was obtained before the study was conducted. This particular study was conducted with the approval of the Ethics Committee of Ichinoseki National College of Technology.
[0068] (2) Measurement of gait information and calculation of cognitive function estimation parameters A measuring device equipped with a 6-axis inertial sensor capable of measuring 3-axis acceleration and 3-axis angular velocity was attached to the subject's shoelace (corresponding to the instep) and waist using clips. Each subject was instructed to walk normally. The walking distance was set to 10m, and measurements were taken twice for each subject. Based on the obtained walking information, cognitive function estimation parameters were calculated, including gait, stance time, ground contact time / stance time, heel lift time / stance time, walking speed, maximum swing speed, lift-off angle, foot trajectory length per step, maximum heel height per step, maximum toe height per step, stride length, y-axis angular velocity waveform similarity (waist), and x-axis acceleration waveform similarity (waist).
[0069] (3) Measurement of cognitive function level For each subject, the level of cognitive function was measured using the Mini-Mental State Examination (MMSE), a cognitive screening test. The MMSE is a cognitive function test with a maximum score of 30 points, consisting of 11 items: orientation to time, orientation to place, immediate and delayed recall of 3 words, calculation, object naming, sentence repetition, 3-level verbal command, written command, sentence writing, and figure copying. According to the MMSE evaluation criteria, a score of 23 or less suggests dementia, and a score of 27 or less suggests mild cognitive impairment (MCI). In this example, subjects with a score of 27 or less were classified as having mild cognitive impairment (MCI), and subjects with a score of 30 were classified as healthy (Normal). Notably, there were no subjects with an MMSE score of 28 or 29. Furthermore, the scores of subjects classified as MCI were all within the range of 25 to 27 points, and there were no subjects with a score of 23 or less, which suggests dementia.
[0070] (4)Analysis First, a binary logistic regression analysis was performed with each subject's estimated cognitive function parameters as independent variables and whether or not they had MCI (Mild Cognitive Impairment) as the dependent variable. As a result of the regression analysis, the following regression equation (3) was obtained.
[0071]
number
[0072] To verify the suitability of equation (3), the Hosmer-Lemeshow test was performed, yielding a p-value of 0.890. Since a p-value of 0.05 or higher indicates a good fit, equation (3) can be said to be a good fit.
[0073] To verify the accuracy of equation (3), cognitive function was estimated based on the cognitive function estimation parameters of each subject. The results are shown in Table 1. As shown in Table 1, the accuracy of equation (3) was 84.2%, indicating that the estimation accuracy of equation (3) is very high.
[0074] [Table 1]
[0075] [Comparative Example 1] In Example 1, a binary logistic regression analysis was performed using only the cognitive function estimation parameters of the 38 subjects, namely gait, walking speed, waveform similarity, and stride length, in the same manner as in Example 1. Gait, walking speed, waveform similarity, and stride length are all parameters that can be calculated solely from information obtained from inertial sensors attached to the waist. This yielded the following regression equation (4).
[0076]
number
[0077] Using equation (4), cognitive function was estimated based on the cognitive function estimation parameters of each subject, similar to Example 1. The results are shown in Table 2. As shown in Table 2, the accuracy of equation (4) was 71.1%.
[0078] [Table 2]
[0079] The results from Example 1 and Comparative Example 1 showed that using estimated parameters calculated from information obtained from inertial sensors attached to the feet significantly improved accuracy. In particular, the accuracy rate for 14 subjects determined to have MCI by MMSE was 42.9% in Comparative Example 1, compared to 78.6% in Example 1, showing a significant improvement. Accurately identifying subjects with MCI is especially beneficial because it allows for appropriate intervention before subjects with MCI develop dementia.
[0080] Although the present invention has been described above with reference to specific embodiments and examples, the present invention is not limited to these examples and is intended to be expressed in the claims, with all modifications within the meaning and scope equivalent to the claims being included.
[0081] In the above embodiment, binary logistic regression analysis was performed to calculate the cognitive function estimation parameters, but for example, the cognitive function estimation parameters may be calculated using deep learning based on gait information and cognitive function level. In the above embodiment, specific physical quantities such as gait and walking speed were used as cognitive function estimation parameters, but the cognitive function estimation parameters do not have to be specific physical quantities and can be any parameters for estimating cognitive function.
[0082] In the above embodiment, the inertial sensor 21 was attached to the measuring device 2, and walking information was sent from the measuring device 2 to the estimation device 1 via the communication unit 22. However, the estimation device 1 may also be equipped with the inertial sensor 21. For example, the estimation device 1 may be a smartphone equipped with an inertial sensor. [Explanation of symbols]
[0083] 1. Cognitive function estimation device 2. Measuring devices 3. Communication Network 11. Pedestrian Information Acquisition Unit 12 Estimated parameter calculation unit 13 Judgment section 14 Output section 15. Cognitive function estimation unit 21 Inertial Sensor 22 Communications Department 30 shoes 100 Cognitive Function Estimation Systems 101,201 CPU 102,202 memory 103,203 bus 104,204 Storage device 105 Programs 106,206 Input devices 107,207 displays S Subject
Claims
1. A cognitive function estimation device comprising a gait information acquisition unit, an estimated parameter calculation unit, and a determination unit, The aforementioned walking information acquisition unit is configured to acquire walking information obtained by an inertial sensor attached to the subject's foot. The walking information includes at least one of the information relating to the acceleration of the subject's foot during walking and information relating to its angular velocity. The estimation parameter calculation unit is configured to calculate cognitive function estimation parameters based on the walking information. The determination unit is configured to determine whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameters. The estimation parameter calculation unit is configured to calculate, as the cognitive function estimation parameter, at least one selected from the group consisting of the lift-off angle, the maximum heel height for one step, and the maximum toe height for one step, based on the walking information. The determination unit is configured to determine whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameter, which includes at least one selected from the group consisting of the bed exit angle, the maximum heel height of one step, and the maximum toe height of one step. Cognitive function estimation device.
2. Furthermore, it is equipped with a cognitive function estimation unit, The cognitive function estimation device according to claim 1, wherein the cognitive function estimation unit estimates the cognitive function level of a subject who has been determined to have mild cognitive impairment (MCI) based on the cognitive function estimation parameters.
3. The cognitive function estimation device according to claim 1, wherein the gait information further includes at least one of information relating to the acceleration and angular velocity of the subject's waist, measured by an inertial sensor attached to the subject's waist.
4. A cognitive function estimation method performed by a cognitive function estimation device having a gait information acquisition step, an estimated parameter calculation step, and a determination step, The gait information acquisition step involves the cognitive function estimation device acquiring gait information measured by an inertial sensor attached to the subject's foot. The walking information includes at least one of the information relating to the acceleration of the subject's foot during walking and information relating to its angular velocity. The above-mentioned estimation parameter calculation step involves the cognitive function estimation device calculating cognitive function estimation parameters based on the walking information, The determination step involves the cognitive function estimation device determining, based on the cognitive function estimation parameters, whether or not the subject has mild cognitive impairment (MCI). The estimation parameter calculation step involves the cognitive function estimation device calculating, as the cognitive function estimation parameter, at least one selected from the group consisting of the step-off angle, the maximum heel height for one step, and the maximum toe height for one step, based on the walking information. The determination step involves the cognitive function estimation device determining whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameters, which include at least one selected from the group consisting of the bed exit angle, the maximum heel height of one step, and the maximum toe height of one step. Cognitive function estimation method.
5. A cognitive function estimation program that causes a computer to perform a procedure for acquiring gait information, a procedure for calculating estimated parameters, and a judgment procedure, The aforementioned gait information acquisition procedure acquires gait information obtained by an inertial sensor attached to the subject's foot, The walking information includes at least one of the information relating to the acceleration of the subject's foot during walking and information relating to its angular velocity. The above-mentioned procedure for calculating estimated parameters involves calculating estimated cognitive function parameters based on the gait information, The aforementioned determination procedure determines whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameters, The above-mentioned estimation parameter calculation procedure calculates at least one of the group consisting of the lift-off angle, the maximum heel height for one step, and the maximum toe height for one step, based on the gait information, as the cognitive function estimation parameter. The determination procedure determines whether or not the subject has mild cognitive impairment (MCI) based on the cognitive function estimation parameter, which includes at least one selected from the group consisting of the bed exit angle, the maximum heel height of one step, and the maximum toe height of one step. A cognitive function estimation program.
6. A cognitive function estimation system comprising a cognitive function estimation device and a measurement device as described in claim 1, The measuring device comprises an inertial sensor and a communication unit. The communication unit is capable of communicating with the cognitive function estimation device and can transmit the walking information to the cognitive function estimation device. Cognitive function estimation system.