Cognitive function disorder risk evaluation system, device, method, and program

Abstract

To provide a cognitive function disorder risk evaluation system capable of accurately evaluating a cognitive function disorder risk on the basis of walking data without imposing a physical, mental, and temporal burden on a user by eliminating randomness from results of measurement on a waling activity in a daily life.SOLUTION: A cognitive function disorder risk evaluation system includes as main components: a motion information acquisition device 10 carried or worn by a user for continuously measuring at least position information; and a risk evaluation device 20 for extracting walking data from time series data on measured position information and evaluating a cognitive function disorder risk of the user. The motion information acquisition device 10 is either implemented on a general purpose wearable terminal such as a smartphone and a smart watch as an application, or provided as a dedicated wearable terminal specialized for the acquisition of motion information, and transmits the recorded time-series data on the position information to the risk evaluation device 20 as log data. The risk evaluation device 20 generates walking data on the basis of the time series data on the position information, and determines an MCI symptom.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a system, device, method, and program for assessing the risk of cognitive impairment, and in particular to a system, device, method, and program for assessing the risk of age-related cognitive impairment based on walking data measured during walking. [Background technology]

[0002] Mild cognitive impairment (MCI), known as a precursor to dementia, is important for early detection because early and appropriate treatment can prevent the onset of dementia or even improve the condition.

[0003] The x-minute walking test and dual-task walking test are known as methods for early detection of MCI symptoms. These tests allow for quantitative evaluation of MCI symptoms by analyzing the user's walking state.

[0004] Patent Document 1 discloses a method and system for assessing the likelihood of developing geriatric disorders such as knee pain (risk of geriatric disorders) based on parameters measured during walking. Non-Patent Document 1 discloses a decrease in walking speed with aging. Non-Patent Documents 2 and 3 disclose the relationship between cognitive impairment and walking speed. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-255786 [Non-patent literature]

[0006] [Non-Patent Document 1] https: / / europepmc.org / article / med / 3367751 [Non-patent document 2] https: / / www.sciencedirect.com / science / article / abs / pii / S1568163716300095 [Non-patent document 3] https: / / www.ncbi.nlm.nih.gov / pmc / articles / PMC2921227 / Summary of the Invention [Problem to be solved by the invention]

[0007] In conventional walking test-based evaluations, users must travel to a facility such as a medical institution or research institute that has a testing environment, and go through certain preparations and procedures to acquire and analyze their walking data. Therefore, if a user lives far from the facility or if there is no facility with a testing environment nearby, they cannot take the evaluation test.

[0008] Furthermore, in conventional technology, walking data is acquired while the user is aware that they will be taking an evaluation test, which makes accurate evaluation difficult due to mental stress, tension, or unfamiliarity.

[0009] Furthermore, since users have to travel to the facility, it is time-consuming and physically demanding, which has led to the problem of users being reluctant to take the evaluation test.

[0010] Furthermore, to accurately assess MCI symptoms, it is desirable to conduct a follow-up evaluation that continuously measures walking data, but there is also the issue that follow-up evaluation is difficult with evaluation tests conducted at facilities.

[0011] The object of the present invention is to solve the above-mentioned technical problems and to provide a cognitive dysfunction risk assessment system, device, method, and program that can continuously and accurately assess the risk of cognitive dysfunction without imposing physical, mental, or time burdens on the user by eliminating or focusing on randomness in walking speed, distance, purpose, etc. from the results of measuring walking behavior in daily life. [Means for solving the problem]

[0012] In order to achieve the above object, the present invention is characterized in that a system for assessing a risk of cognitive impairment based on a user's walking data has the following configuration.

[0013] (1) The device is equipped with a means for being carried by or worn by a user and for continuously measuring at least position information, and a means for generating walking data based on a time series of the position information.

[0014] (2) The means for generating walking data includes means for extracting a period of movement during which the user is moving from the time series of the position information, and generates walking data based on the time series of the position information during the period of movement.

[0015] (3) In order to eliminate the randomness of everyday walking behavior, the system is provided with means for extracting periods in which the user is walking in a straight line from the user's movement period, means for excluding periods in which the user is walking on an uneven road surface, means for excluding periods in which the user is not walking, means for excluding periods in which the user is walking unnaturally, and means for excluding periods in which the user is walking non-daily.

[0016] (4) In order to focus on the randomness of everyday walking behavior, walking speed, the ratio of the number of steps to the walking distance, the degree of deviation from the walking route, the number of times the person staggered while walking, the degree of reduction in the range of movement, and the degree of reduction in stride length were extracted from the walking data as walking content data, and a means was established to evaluate the risk of cognitive impairment based on the extracted walking content data. [Effects of the Invention]

[0017] According to the present invention, the following effects can be achieved.

[0018] (1) Since walking data is automatically collected as users go about their daily lives, users no longer need to travel to a facility equipped with a testing environment, and can take evaluation tests without imposing physical, mental, or time burdens.

[0019] (2) Gait data is collected during daily movement, making it possible to continuously and easily collect gait data suitable for assessing MCI symptoms.

[0020] (3) While extracting periods of straight walking from the time series of location information measured during daily life, periods of walking on uneven ground, periods of non-walking, periods of unnatural walking, and periods of non-daily walking are not included in the walking data. This makes it possible to eliminate the randomness of everyday walking behavior and generate walking data suitable for assessing MCI symptoms.

[0021] (4) We focus on the walking behavior, which is an indicator of cognitive impairment in daily life, and evaluate the risk of cognitive impairment based on that walking behavior data. This makes it possible to evaluate risk by focusing on the randomness of everyday walking behavior. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a diagram showing the configuration of a cognitive impairment risk assessment system to which the present invention is applied. [Figure 2] FIG. 1 is a diagram conceptually illustrating a method for extracting a movement period from daily walking. [Figure 3] FIG. 2 is a functional block diagram showing the configurations of an information acquisition device and a risk assessment device. [Figure 4] FIG. 2 is a functional block diagram showing the configuration of a walking speed data generating unit. [Figure 5] 10 is a flowchart showing a procedure for generating walking speed data. [Figure 6]FIG. 10 is a diagram illustrating a procedure for generating walking speed data. [Figure 7] FIG. 10 is a diagram showing a method for determining signs of MCI based on walking speed data. [Figure 8] FIG. 10 is a functional block diagram showing another configuration of the information acquisition device and the risk assessment device. [Figure 9] FIG. 2 is a functional block diagram showing the configuration of a walking content data generating unit. DETAILED DESCRIPTION OF THE INVENTION

[0023] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Fig. 1 is a diagram showing the overall configuration of a cognitive impairment risk assessment system 1 to which the present invention is applied, and Fig. 2 is a diagram conceptually showing a method for generating walking data used in assessing the risk of cognitive impairment in the present invention.

[0024] In this invention, by measuring walking data while walking in daily life, the user is relieved of physical, mental, and time burdens. However, such measurement methods result in the walking data being influenced by randomness in walking speed, distance, purpose, location, topography, environment, etc. Therefore, as shown in Figure 2, by excluding the walking period that is influenced by randomness from the measurement results in daily life, walking data suitable for assessing the risk of cognitive impairment is generated, equivalent to a walking test.

[0025] As shown in Figure 1, the cognitive dysfunction risk assessment system 1 of the present invention mainly comprises a movement information acquisition device 10 that is carried by or worn by user T and continuously measures at least location information, and a risk assessment device 20 that generates walking data from a time series of the measured location information and assesses the cognitive dysfunction risk of user T. In addition, a map information database (DB) 31, an attribute information DB 32, a walking speed DB 33, and a walking history DB 34 are connected and stored so as to be freely accessible from the risk assessment device 20.

[0026] The attribute information DB 32 stores information about the age, sex, weight, etc. of each user T. The walking history DB 34 stores walking history (date and time, place, content, etc.) of each user T.

[0027] The movement information acquisition device 10 is implemented as an application in a general-purpose wearable (portable) terminal such as a smartphone or a smartwatch, or is provided as a dedicated wearable terminal specialized for acquiring movement information.

[0028] The movement information acquisition device 10 transmits the time series data of the recorded position information as log data to the risk assessment device 20 via the wireless base station BS and the Internet NW. The movement information acquisition device 10 and the risk assessment device 20 may be connected by wired connection or short-range wireless communication, etc.

[0029] FIG. 3 is a functional block diagram showing the configuration of the main parts of the movement information acquisition device 10 and the risk assessment device 20, and components not necessary for explaining the present invention are omitted from the illustration.

[0030] In a movement information acquisition device (wearable terminal) 10, a GPS 11 determines the current position based on GPS signals received from multiple satellites and keeps track of the current time. An acceleration sensor 12 detects acceleration and outputs an acceleration signal. A gyro sensor 13 detects rotation and changes in orientation and outputs a rotation vector.

[0031] The measurement results of the current position, acceleration, and rotation vector are temporarily stored in the memory unit 14 in chronological order along with the current time, and are transmitted as log data from the transmission unit 15 to the risk assessment device 20 together with a user ID unique to the user T at a predetermined interval or at an appropriate timing such as when a link is established with the risk assessment device 20.

[0032] In the risk assessment device 20, the receiving unit 21 acquires the log data from the movement information acquisition device 10. The receiving unit 21 further acquires necessary information as appropriate from the map information DB 31, the attribute information DB 32, the walking speed DB 33, and the walking history DB 34. The movement period extraction unit 22 extracts a movement period during which it can be estimated that the user T is moving, based on the time series of the position information acquired from the movement information acquisition device 10.

[0033] The walking data generation unit 23 includes a walking speed data generation unit 231, and generates walking data suitable for assessing the risk of cognitive impairment in a manner similar to a walking test. The walking speed data generation unit 231 generates walking speed data for assessing the risk of cognitive impairment based on the user's walking speed from a time series of position information measured during movement in daily life.

[0034] The MCI symptom determination unit 24 includes a walking speed-based determination unit 241 that determines MCI symptoms based on the walking speed data generated by the walking speed data generation unit 231, and determines MCI symptoms based on the user T's daily walking.

[0035] FIG. 4 is a functional block diagram showing the configuration of the main parts of the walking speed data generation unit 231, which includes a normal walking period extraction unit 2310, a preceding and following period exclusion unit 2311, a short walking period combination unit 2312, and an appropriate walking period extraction unit 2313, and generates walking data suitable for assessing the risk of cognitive impairment from the time series of position information measured during walking in daily life.

[0036] The normal walking period extraction unit 2310 further includes a straight walking extraction unit 2315, a non-flat walking exclusion unit 2316, a non-walking exclusion unit 2317, an unnatural walking exclusion unit 2318, and an abnormal walking exclusion unit 2319, and extracts a normal walking period by eliminating randomness inherent in everyday walking from the movement period.

[0037] The straight line walking extraction unit 2315 extracts, from the movement period, a straight line walking period during which it can be estimated that the user T is walking straight (in a straight line), based on the time series of the position information.

[0038] The non-flat walking exclusion unit 2316 determines the period during which the user T is walking on a non-flat road surface such as an uphill or downhill slope based on map information or GPS positioning results, and removes the non-flat walking period from the movement period.

[0039] The non-walking exclusion unit 2317 determines non-walking periods in which the user T is walking quickly or jogging based on the time series of the position information, and removes the non-walking periods from the movement period.

[0040] The unnatural walking exclusion unit 2318 determines a period of unnatural walking in which the user T walks with an unnatural behavior based on the acceleration signal and the rotation vector, and removes the period of unnatural walking from the movement period.

[0041] The non-routine walking exclusion unit 2319 determines whether the extracted period of movement is habitual walking such as a stroll based on the user T's past movement history, and while maintaining the period of habitual walking, excludes the period of non-habitual walking as non-routine walking.

[0042] The preceding and following period excluding unit 2311 removes the predetermined period at the start of walking and the predetermined period at the end of walking of the normal walking period extracted as described above from the normal walking period.

[0043] The short walking period combining unit 2312 combines a plurality of short normal walking periods, the distance of which is less than a predetermined reference distance, from among the normal walking periods, to generate a combined normal walking period whose distance exceeds the reference distance.

[0044] The appropriate walking period extraction unit 2313 further extracts, as an appropriate walking period, a walking period of a predetermined distance required for MCI evaluation from both the normal walking period that exceeds the reference distance and the combined normal walking period that is combined so as to exceed the reference distance.

[0045] Fig. 5 is a flowchart showing the procedure for generating walking speed data by the walking speed data generating unit 231, and will be described here using as an example a case where a position information time series is measured as shown in Fig. 6. In Fig. 6, the movement trajectory of user T is expressed on a two-dimensional plane.

[0046] 5, the movement period extraction unit 22 extracts the movement period of the user T, distinguishing it from the stay period, based on the time series of the location information acquired as log data from the movement information acquisition device 10. In this embodiment, the movement trajectory of the user T based on the location information measured by GPS is analyzed, and the period in which movement is recognized is extracted as the movement period, and the rest is excluded from the evaluation as the stay period.

[0047] In the example of Figure 6, the extracted movement periods are represented by double arrows, and the stay periods are represented by black circles. If user T repeatedly moves and stays, multiple movement periods will be extracted.

[0048] In steps S2 to S6, the normal walking period extraction unit 2310 extracts a normal walking period by eliminating randomness inherent in everyday walking from each of the extracted movement periods.

[0049] In step S2, the straight walking extraction unit 2315 extracts straight walking periods from each of the extracted movement periods. In this embodiment, based on a movement trajectory based on a time series of position information measured by GPS, sections in which it can be estimated that the user T is moving straight are extracted as straight walking periods P1-P6.

[0050] In step S3, the non-flat walking exclusion unit 2316 compares each straight-line walking period P1-P6 with map information to remove non-flat periods such as uphill and downhill periods from each moving period. If altitude information can be acquired from the GPS positioning results, periods in which the change in altitude within each straight-line walking period P1-P6 exceeds a predetermined reference value may be excluded as non-flat.

[0051] In step S4, the non-walking exclusion unit 2317 excludes non-walking periods from each movement period. In this embodiment, based on the movement speed calculated from the movement trajectory measured by GPS, periods of jogging or brisk walking where the movement speed is outside the normal speed range (for example, 1.04-1.32 m / s) are excluded as non-walking periods.

[0052] In step S5, the unnatural walking exclusion unit 2318 determines, from the straight walking period, a moving period in which the user T is exhibiting unnatural behavior, based on the acceleration signal and the rotation vector, and removes the walking period as an unnatural walking period in which, for example, "unsteadiness" occurs. In this embodiment, a period in which the acceleration / deceleration calculated based on the acceleration signal or the direction and magnitude of the rotation vector exceed a predetermined threshold is excluded as an unnatural walking period.

[0053] Additionally, the number of steps per unit moving distance may be calculated, and periods in which the number of steps is significantly greater (shorter stride length) or fewer (wider stride length) may be excluded as periods of unnatural walking.

[0054] In step S6, the non-routine walking exclusion unit 2319 determines whether the walking behavior during each movement period is routine or not based on the user T's past movement history, and keeps the movement periods due to habitual, routine walking behavior while excluding the non-habitual movement periods.

[0055] Generally, walking data suitable for MCI assessment can be obtained in areas, dates, times, days of the week, etc. that are familiar to walking in, such as everyday walking courses, but data suitable for MCI assessment cannot be obtained in unusual areas, dates, times, days of the week, etc. that are unfamiliar to walking in. Therefore, in this embodiment, location information and calendar information are referenced, and walking data is generated based only on the time series of location information measured during everyday walking behavior within the extracted movement period.

[0056] In step S7, the preceding and following period exclusion unit 2311 further excludes a walking start period and a walking end period from each straight walking period. In this embodiment, the first 5 m of each straight walking period is excluded as the walking start period, and the last 5 m of each straight walking period is excluded as the walking end period. In Figure 6, the walking start period and the walking end period are not shown.

[0057] In step S8, the distance is referenced for each straight walking period excluding non-flat, non-walking, unnatural walking, unusual walking, and periods before and after, and for a straight walking period P2 of 10 m or more, the process proceeds to step S10. In step S10, the appropriate walking period extraction unit 2313 stores the first 10 m of the straight walking period P2 exceeding 10 m as the walking period to be evaluated.

[0058] On the other hand, for the straight-line walking periods P1, P3, P4, P5, and P6 of less than 10 m, the process proceeds to step S9. In step S9, the short-term walking period combining unit 2312 combines multiple straight-line walking periods of less than 10 m into a straight-line walking period of 10 m or more, and extracts and stores the 10 m portion of that as the walking period to be evaluated.

[0059] Returning to FIG. 3, once the walking data for evaluation is generated by the above procedure, the walking speed-based determination section 241 of the MCI sign determination section 24 determines an MCI sign based on the walking speed data generated by the walking speed data generation section 231.

[0060] The walking speed DB33 stores the average walking speed of healthy people by gender, age, and weight, as shown in an example in FIG. 7. In this embodiment, if the walking speed of user T is significantly lower than that of healthy people and the rate of decrease is less than a predetermined threshold (e.g., 15% incomplete), the MCI symptoms are determined to be "low," and if it is 15% or more, the MCI symptoms are determined to be "high."

[0061] In addition, MCI signs may be determined to be high in a recursive manner in accordance with a decrease in walking speed, or in accordance with a decrease in stride length, which is one of the symptoms of MCI, in comparison with the past based on historical information, in accordance with an increase in the number of steps taken when the user walks the same distance (e.g., 2 km).

[0062] According to this embodiment, the presence and severity of MCI symptoms can be evaluated simply by measuring user T's daily walking behavior, making it possible to evaluate cognitive dysfunction without imposing physical, mental, or time burdens on user T.

[0063] In the first embodiment described above, walking data suitable for a walking test is extracted by eliminating randomness from walking data measured in daily life, but the randomness to be eliminated may contain signs of cognitive impairment, such as unsteadiness or a decrease in stride length. Therefore, in the second embodiment described below, the risk of cognitive impairment is evaluated by focusing on the randomness of walking data measured in daily life.

[0064] FIG. 8 is a functional block diagram showing the configuration of the second embodiment of the movement information acquisition device 10 and the risk assessment device 20, and the same reference numerals as those used above represent the same or equivalent parts, so a description thereof will be omitted.

[0065] In the risk assessment device 20, the walking data generation unit 23 includes a walking content data generation unit 232. The walking content data generation unit 232 generates walking content data for assessing the risk of cognitive impairment based on the walking content of the user from various information including a time series of position information measured during movement in daily life.

[0066] The MCI symptom determination unit 24 includes a gait content-based determination unit 242 that determines MCI symptoms based on the gait content data generated by the gait content data generation unit 232, and determines MCI symptoms based on the user T's daily walking.

[0067] Figure 9 is a functional block diagram showing the configuration of the main parts of the walking content data generation unit 232, which includes a walking route evaluation unit 2321, a movement range evaluation unit 2322, and a walking state evaluation unit 2323, and generates walking content data suitable for evaluating the risk of cognitive impairment based on position information, acceleration, rotation vectors, etc. measured during walking in daily life.

[0068] The walking route evaluation unit 2321 compares the measured walking route with past walking routes stored in the walking history DB 34, and determines the degree of deviation of the current walking route from the past walking rules, for example, based on the distance between the current walking route and the past walking rules.

[0069] The movement range evaluation unit 2322 compares the movement range of the measured walking route with the movement range of past walking routes stored in the walking history DB 34 to find the degree of reduction in the movement range.

[0070] The walking state evaluation unit 2323 compares changes in walking posture, a decrease in stride length, a decrease in walking speed, a decrease in the number of times the arms are swung, and the like with past records stored in the walking history DB 34 .

[0071] When the walking data for evaluation is generated by the above procedure, the walking content-based determination unit 242 of the MCI sign determination unit 24 determines MCI signs based on the walking content data generated by the walking content data generation unit 232. For example, if "walking speed," "number of steps," and "walking distance" are generated as walking content data, MCI signs can be determined based on "walking speed" and "number of steps / walking distance."

[0072] Furthermore, if the walking speed reduction degree K1, the walking route deviation degree K2, the number of staggers per unit time K3, the movement range reduction degree K4, and the stride length reduction degree K5 are generated as walking content data, MCI signs may be regressively determined by applying each evaluation value Kx to the following formula (1), where α, β, γ, δ, and ε are weighting coefficients for each evaluation value Kx. Note that only some of the evaluation values Kx may be used.

[0073] MCI symptom level = α × K1 + β × K2 + γ × K3 + δ × K4 + ε × K5 (1)

[0074] According to this embodiment, the risk of cognitive dysfunction can be evaluated by focusing on the randomness of walking data measured in daily life, making it possible to evaluate the risk of cognitive dysfunction without imposing physical, mental, or time burdens on user T.

[0075] In the above embodiment, an example has been described in which signs of MCI are determined based on walking speed data and walking content data. However, the present invention is not limited to this. Since a correlation has been found between walking data and the risk of early mortality, cardiovascular disease, cancer, Parkinson's disease, and the like, the present invention can also be applied to the evaluation of these diseases and disorders.

[0076] As described above, according to the present invention, the presence and severity of MCI symptoms can be evaluated simply by measuring the daily walking behavior of user T, making it possible to evaluate cognitive impairment without imposing a physical, mental, or time burden on user T. This makes it possible to contribute to Goal 3 "Good health and well-being," Goal 9 "Industry, innovation and infrastructure," and Goal 11 "Sustainable cities and communities" of the Sustainable Development Goals (SDGs) led by the United Nations. [Explanation of symbols]

[0077] 1...cognitive impairment risk assessment system, 10...movement information acquisition device, 11...GPS, 12...acceleration sensor, 13...gyro sensor, 20...risk assessment device, 21...receiving unit, 22...movement period extraction unit, 23...walking data generation unit, 24...MCI symptom determination unit, 31...map information DB, 32...attribute information DB, 33...walking speed DB, 34...walking history DB, 231...walking speed data generation unit, 232...walking content data generation unit, 241...walking speed based determination unit, 242...walking content based determination unit, 2310...normal walking period extraction unit, 2311...previous and following period exclusion unit, 2312...short-term walking period combination unit, 2313...appropriate walking period extraction unit, 2315...Straight walking extraction unit, 2316...Non-flat walking excluding unit, 2317...Non-walking excluding unit, 2318...Unnatural walking excluding unit, 2319...Unusual walking excluding unit, 2321...Walking route evaluation unit, 2322...Movement range evaluation unit, 2323...Walking state evaluation unit

Claims

1. A system for assessing the risk of cognitive impairment based on a user's walking data, a means carried by or worn by a user for continuously measuring at least position information; and a means for generating walking data based on the time series of the position information.

2. The cognitive impairment risk assessment system according to claim 1, characterized in that the means for generating walking data includes means for extracting a period of movement during which the user is estimated to be moving based on the time series of the location information, and generates walking data based on the time series of location information during the period of movement.

3. The cognitive impairment risk assessment system according to claim 2, characterized in that the means for generating walking data includes means for extracting a normal walking period from the movement period, eliminating the randomness inherent in everyday walking, and generating walking data based on a time series of position information during the normal walking period.

4. The cognitive impairment risk assessment system according to claim 3, characterized in that the means for extracting the normal walking period includes means for extracting a straight-line walking period in which the user is walking in a straight line from the movement period, and generates walking data based on a time series of position information during the straight-line walking period.

5. The cognitive impairment risk assessment system according to claim 3, characterized in that the means for extracting the normal walking period includes means for excluding from the moving period any non-flat period in which the user is walking on an uneven road surface.

6. The cognitive impairment risk assessment system according to claim 3, characterized in that the means for extracting the normal walking period includes means for excluding from the moving period a non-walking period in which the moving speed is outside a predetermined walking speed range.

7. The cognitive impairment risk assessment system according to claim 3, characterized in that the means for extracting the normal walking period includes means for excluding from the movement period an unnatural walking period in which the user's behavior is unnatural.

8. The cognitive impairment risk assessment system according to claim 3, wherein the means for extracting the normal walking period includes means for excluding the user's non-daily walking period from the movement period.

9. A cognitive impairment risk assessment system as described in any one of claims 3 to 8, characterized in that the means for generating walking data includes means for excluding a predetermined period of at least one of the start and end of movement from the normal walking period.

10. The cognitive impairment risk assessment system according to claim 9, characterized in that the means for generating walking data generates walking data based on a time series of position information during a normal walking period in which the travel distance is greater than or equal to a predetermined value.

11. The cognitive impairment risk assessment system of claim 9, characterized in that the means for generating walking data includes means for combining multiple normal walking periods in which the walking distance is less than a predetermined value so that the total distance is equal to or greater than a predetermined value, and generates walking data based on a time series of position information during the combined normal walking periods.

12. The cognitive impairment risk assessment system described in claim 10, characterized in that the means for generating walking data generates walking data based on a time series of position information at a specified distance at the beginning of a normal walking period in which the distance is greater than or equal to a specified value.

13. The cognitive impairment risk assessment system described in claim 1 or 2, further comprising a means for extracting at least one of walking speed and the ratio of the number of steps to walking distance as walking content data from the generated walking data, and assessing the risk of cognitive impairment based on the extracted walking content data.

14. The cognitive impairment risk assessment system described in claim 1 or 2, further comprising a means for extracting at least one of the following as walking content data from the generated walking data: the degree of deviation from the walking route, the number of times the walking staggers, the degree of reduction in the range of movement, and the degree of reduction in stride length, and for assessing the risk of cognitive impairment based on the extracted walking content data.

15. 1. A device for assessing a risk of cognitive impairment based on walking data of a user, a means for acquiring a time series of location information from a means carried by or worn by a user and for continuously measuring at least location information; and means for generating walking data based on the time series of the acquired position information.

16. 1. A method for assessing a risk of cognitive impairment by a computer based on walking data of a user, comprising: Continuously measuring at least location information using a device carried or worn by a user; A method for assessing the risk of cognitive impairment, characterized by generating walking data based on the time series of the position information.

17. In a program that assesses the risk of cognitive impairment based on a user's walking data, A procedure in which a device carried by or worn by a user continuously measures at least location information; generating walking data based on the time series of the position information; A cognitive impairment risk assessment program characterized by executing the above on a computer.

Images