JP2023014057A - Cognitive function estimating device and program - Google Patents

Abstract

An object of the present invention is to estimate cognitive function with high accuracy. A physical data acquiring unit 102 of a cognitive function estimating device 10 acquires physical data indicating the age and sex of a subject. The odor selection unit 104 uses the correlation/average information database 100 to select odor components corresponding to the physical data of the subject. The olfactory data collection unit 101 emits the odor component selected by the odor selection unit 104 to the subject and collects an olfactory score indicating the olfactory ability of the subject. The cognitive function evaluation unit 108 acquires the average value of the olfactory scores in, for example, the age and sex groups to which the subject belongs, and derives the cognitive function evaluation value for the subject. The presentation unit 110 presents information about cognitive functions. Thus, the cognitive function estimation device 10 uses the correlation/average information database 100 to estimate the cognitive function. [Selection drawing] Fig. 10

Description

The present disclosure relates to a cognitive function estimation device and program.

Conventionally, techniques related to measurement of olfactory ability are known. In Patent Document 1, a plurality of images including correct answers are displayed, an odor component is emitted, a subject's selection is accepted, and an olfactory age is derived based on whether the correct answer matches the selection result. In addition, in Non-Patent Document 1, the risk of developing dementia is determined using 10 odor cards that are closely related to brain function, presenting odors extracted from correlation with MMSE (cognitive function test).

Cognitive decline risk checker “Hakarame”, URL “http://hakarame-ge.com/”

JP 2019-180664 A

In the technique of Patent Literature 1, an odor component is released, and the olfactory age of the subject is derived from the response. The technique of Patent Document 1 is a technique based on medical knowledge that olfactory ability declines with age, and consideration of dementia risks such as deterioration of cognitive function with respect to olfactory ability is insufficient. Therefore, there is room for improvement when estimating cognitive function.

In addition, in the technique of Non-Patent Document 1, the same 10 types of odor cards are used for each of a plurality of subjects. Improving accuracy is difficult and there is room for improvement when estimating cognitive function.

The present disclosure has been made in consideration of the above facts, and aims to provide a cognitive function estimation device and a program capable of highly accurately estimating cognitive function through a simple olfactory test.

A first aspect of the present disclosure includes an acquisition unit that acquires identification information including the age of the subject for identifying a subject whose cognitive function is estimated, and a predetermined cognitive function test to identify the subject. Based on the correlation information including information indicating the correlation between the odor component and the cognitive function test, and the correlation between the odor component and the test value of the cognitive function test, with respect to the identification information including the age of an odor component setting unit that sets an odor component having a correlation with a subject; and the test result of the odor component by the olfactory sense of the subject when the set odor component is emitted, and the recognition in the correlation information. and an estimating unit for estimating a cognitive function evaluation value for the subject based on test values of a function test.

A second aspect is the cognitive function estimating device of the first aspect, wherein the correlation information derives the type of the odor component and the correlation with the test value of the odor component for a plurality of subjects. The odor components are classified according to ages with age as a boundary, and the average value of the inspection results for the odor components is derived as the inspection value of the odor components for each of the classified ages.

A third aspect is the cognitive function estimation device of the first aspect or the second aspect, further comprising a presenting unit that presents the cognitive function evaluation value for the subject estimated by the estimating unit, wherein the estimating unit If the cognitive function evaluation value exceeds a predetermined threshold value, recommendation information recommending that the cognitive function test be taken is presented.

A fourth aspect is the cognitive function estimating device according to any one aspect of the first to third aspects, wherein the identification information includes physical data including the age and sex of the subject, smoking data including whether or not the subject has ever smoked, It includes at least one information of stay data indicating the stay position and stay period, and education involvement time data involved in the education.

A fifth aspect is the cognitive function estimating device according to the fourth aspect, wherein the gender of the physical data indicates one of two types of first gender and second gender, and the odor component setting unit Odor components including vanilla, rag smell, yellow peach, and socks are set for gender, and odor components including caramel and socks are set for the second sex.

A sixth aspect comprises a computer, an acquisition unit that acquires identification information including the age of the subject for identifying a subject whose cognitive function is to be estimated, and a subject that has undergone a predetermined cognitive function test. With respect to identification information including age, the subject based on correlation information including information indicating the correlation between the odor component and the cognitive function test, and the correlation between the odor component and the test value of the cognitive function test an odor component setting unit that sets an odor component that has a correlation with a subject; and when the set odor component is released, the inspection result of the odor component by the olfactory sense of the subject and the recognition in the correlation information. A program for functioning as an estimation unit for estimating a cognitive function evaluation value for the subject based on test values of a function test.

A seventh aspect comprises an odorant component releasing section that releases each of a plurality of odorant components to a subject while changing the concentration of each odorant component in a plurality of stages, and the odorant component released from the odorant component release section. a score setting unit for setting a score corresponding to the concentration indicating the correct answer when the subject's answer indicating which odor component is correct; and the plurality of odors having the score set by the score setting unit. and an estimating unit for estimating a cognitive function evaluation value for the subject based on the total value of the components.

An eighth aspect is the cognitive function estimating device according to the seventh aspect, wherein the odor components are odor components of vanilla, mint, yellow peach, and socks.

A ninth aspect is the cognitive function estimation device of the seventh aspect,
The estimation unit uses constants a and b to
Cognitive function evaluation value = a × total score + b
An evaluation value of cognitive function based on the formula represented by is estimated as the cognitive function.

A tenth aspect is the cognitive function estimation device according to any one of the seventh to ninth aspects, wherein the score is set to a higher value as the concentration of correct answers decreases.

An eleventh aspect is the cognitive function estimating device of the seventh aspect, in which test values of the cognitive function test obtained by performing a predetermined cognitive function test on the plurality of subjects and releasing each of the plurality of odor components to the plurality of subjects. Based on the correspondence relationship in which each of the odor components is associated with the score, the odor components have a correlation with the cognitive function test and the number of components is less than the number of components of the plurality of odor components. and an odor component setting unit that sets an odor component group that combines the odor component groups, and the odor component release unit releases the odor component group set by the odor component setting unit as the plurality of odor components.

A twelfth aspect is the cognitive function estimation device according to the eleventh aspect, wherein the odor component setting unit sets the test value of the cognitive function test to the total value of the plurality of odor components for the plurality of subjects. A plurality of odor components of which the information on the discriminant power evaluation value obtained by analyzing the distribution of the subjects exceeding the predetermined test value and the subjects below the predetermined test value exceeds a predetermined correlation value is set as the odor component group.

A thirteenth aspect is the cognitive function estimating device according to the seventh aspect, wherein the estimating unit calculates the sum of the scores of the odor components for a plurality of subjects, and the cognition A cognitive function evaluation value for the subject is estimated based on the correlation of the ratio of subjects whose test values in the function test exceed a predetermined test value and subjects whose test values are less than or equal to the predetermined test value.

A fourteenth aspect is the cognitive function estimation device according to any one aspect of the seventh aspect to the thirteenth aspect, further comprising a presenting unit that presents the cognitive function evaluation value for the subject estimated by the estimating unit, The estimating unit presents recommendation information that recommends taking the cognitive function test when the cognitive function evaluation value exceeds a predetermined threshold.

A fifteenth aspect is a program for causing a computer to execute a process of estimating a cognitive function of a subject, wherein the computer controls the subject to obtain each of a plurality of odor components, A score for setting a score corresponding to the correct concentration when the subject's answer indicating which odor component is the odor component released from the odor component releasing part that releases the odor component in multiple stages is correct. A program for functioning as a setting unit and an estimating unit for estimating a cognitive function evaluation value for the subject based on the total value of the plurality of odor components of the scores set by the score setting unit.

A sixteenth aspect is an acquisition unit that acquires identification information including physical data indicating the age and sex of the subject for identifying the subject whose cognitive function is to be estimated, and smoking data indicating whether or not the subject has ever smoked, and the subject An odor component releasing part for releasing each of a plurality of odor components while changing the concentration of each odor component in a plurality of steps, and which odor component is the odor component released from the odor component releasing part. a score setting unit for setting a score corresponding to the concentration indicating the correct answer when the subject's answer is correct; the identification information obtained by the obtaining unit; and the identification information set by the score setting unit. an estimating unit for estimating a cognitive function evaluation value for the subject, based on the total score for the plurality of odor components.

A seventeenth aspect is the cognitive function estimating device of the sixteenth aspect, wherein the estimating unit includes, for a plurality of subjects, the identification information, the type of the odor component, the test value of the odor component, and the test value of the cognitive function test. A cognitive function evaluation value for the subject is estimated based on the correlation with.

An eighteenth aspect is the cognitive function estimation device of the seventeenth aspect,
The estimation unit
Let A, B, C, and D be constants,
Let pa be (A × total score),
Let pb be (B x age),
Let pc be (C x gender),
When pd is (D × smoking history),
p=1/[1+exp{−(pa+pb+pc+pd)}]
The evaluation value of cognitive function is derived using the estimation formula represented by

A nineteenth aspect is the cognitive function estimating device of the sixteenth aspect, wherein test values of the cognitive function test obtained by performing a predetermined cognitive function test on the plurality of subjects and releasing each of the plurality of odor components to the plurality of subjects. Based on the correspondence relationship in which each of the odor components is associated with the score, the odor components have a correlation with the cognitive function test and the number of components is less than the number of components of the plurality of odor components. and an odor component setting unit that sets an odor component group that combines the odor component groups, and the odor component release unit releases the odor component group set by the odor component setting unit as the plurality of odor components.

A twentieth aspect is the cognitive function estimation device according to the nineteenth aspect, wherein the odor component setting unit sets the test value of the cognitive function test to the total value of the plurality of odor components for the plurality of subjects. A plurality of odor components of which the information on the discriminant power evaluation value obtained by analyzing the distribution of the subjects exceeding the predetermined test value and the subjects below the predetermined test value exceeds a predetermined correlation value is set as the odor component group.

A twenty-first aspect is the cognitive function estimating device according to the sixteenth aspect, wherein the odor components released from the odor component releasing unit are a first odor component predetermined as an odor component that makes the subject feel refreshed; It includes at least a component set with a second odor component predetermined as an odor component that makes a person feel uncomfortable.

A twenty-second aspect is the cognitive function estimating device according to the twenty-first aspect, wherein the first odor component is mint, and the second odor component is an odor component indicating a rag odor or a socks odor.

A twenty-third aspect is an acquisition unit that acquires identification information including body data indicating the age and sex of the subject for identifying the subject whose cognitive function is to be estimated, and smoking data indicating whether or not the person has ever smoked. , an odor component release control unit for controlling an odor component release unit that releases each of a plurality of odor components to a subject while varying the concentration of each odor component in a plurality of steps; a score setting unit for setting a score corresponding to a concentration indicating a correct answer when the subject's answer indicating which odor component is the identified odor component is correct; and the identification information obtained by the obtaining unit. and the total value of the plurality of odor components of the score set by the score setting unit.

ADVANTAGE OF THE INVENTION According to this indication, the effect that a cognitive function can be estimated with high precision by a simple olfactory test is acquired.

BRIEF DESCRIPTION OF THE DRAWINGS It is a block diagram which shows the whole schematic structure of the cognitive function estimation system which concerns on 1st Embodiment. It is a block diagram which shows the hardware constitutions of the cognitive function estimation apparatus which concerns on 1st Embodiment. It is a block diagram which shows an example of the functional structure in the learning phase of the cognitive function estimation apparatus which concerns on 1st Embodiment. 4 is a flowchart showing the flow of learning processing of the cognitive function estimation device according to the first embodiment; FIG. 4 is a diagram showing an example of an option screen according to the first embodiment; FIG. It is a figure which shows an example of the olfactory score which concerns on 1st Embodiment. FIG. 4 is a diagram showing an example of correlation values relating to odor components for the cognitive function test according to the first embodiment; FIG. 10 is a diagram showing an example of correlation values relating to odor components for another cognitive function test according to the first embodiment; It is a figure which shows an example of the average olfactory score which concerns on 1st Embodiment. It is a block diagram which shows an example of the functional structure in the estimation phase of the cognitive function estimation apparatus which concerns on 1st Embodiment. 4 is a flowchart showing the flow of estimation processing of the cognitive function estimation device according to the first embodiment; It is a block diagram which shows the whole schematic structure of the cognitive function estimation system which concerns on 2nd Embodiment. It is a block diagram which shows the functional structure in the learning phase of the cognitive function estimation apparatus which concerns on 2nd Embodiment. It is a flow chart which shows a flow of learning processing of a cognitive function estimating device concerning a 2nd embodiment. FIG. 10 is a diagram showing an example of a data table in which each data of the olfactory score for each odor component and the test result of cognitive function are associated with each other according to the second embodiment. FIG. 11 is a diagram showing an example of data indicating evaluation indexes according to the second embodiment; FIG. It is a figure which shows an example of the correspondence of an olfactory score and the number of people which concern on 2nd Embodiment. FIG. 11 is a diagram showing an example of the relationship between the test results of smell and the test results of cognitive function according to the second embodiment; It is a block diagram which shows the functional structure in the estimation phase of the cognitive function estimation apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the flow of the estimation process of the cognitive function estimation apparatus which concerns on 2nd Embodiment. It is a block diagram which shows the whole schematic structure of the cognitive function estimation system which concerns on 3rd Embodiment. It is a block diagram showing an example of functional composition of a cognitive function estimating device concerning a 3rd embodiment. 11 is a flowchart showing the flow of learning processing of the cognitive function estimation device according to the third embodiment; It is a figure which shows an example of the olfactory score which concerns on 3rd Embodiment. It is a figure which shows an example of the ROC curve which concerns on 3rd Embodiment. FIG. 11 is a diagram showing an example of correlation values relating to odor components for the cognitive function test according to the third embodiment; FIG. 11 is a diagram showing an example of correlation values relating to odor components for the cognitive function test according to the third embodiment; FIG. 12 is a block diagram showing another example of the functional configuration of the cognitive function estimation device according to the third embodiment; 10 is a flowchart showing the flow of estimation processing of the cognitive function estimation device according to the third embodiment;

Hereinafter, an example of an embodiment for implementing the technology of the present disclosure will be described in detail with reference to the drawings. Components and processes having the same actions, actions, and functions are given the same reference numerals throughout the drawings, and overlapping descriptions may be omitted. Each drawing is only schematically shown to the extent that the technology of the present disclosure can be fully understood. Therefore, the technology of the present disclosure is not limited only to the illustrated examples. Further, in this embodiment, descriptions of configurations that are not directly related to the present invention and well-known configurations may be omitted.

[First embodiment]

<Configuration of cognitive function estimation system>
FIG. 1 is a block diagram showing an overall schematic configuration of a cognitive function estimation system. As shown in FIG. 1, the cognitive function estimating system according to this embodiment includes a cognitive function estimating device 10 that estimates cognitive function from information obtained by releasing odor components from an odor component releasing device 20 . In addition, the cognitive function estimation device 10 calculates the identification information including the age of the subject who has undergone the cognitive function test, the type of odor component that has a correlation in the cognitive function test, and the correlation with the test value of the odor component. The cognitive function of the subject is estimated using the correlation/average information database 100 that stores the correlation information shown.

The identification information is data that includes age, etc., for identifying subjects whose cognitive functions are to be estimated by a simple olfactory test, and physical data, including age and gender, of subjects whose cognitive functions are to be estimated can be applied. is. In this embodiment, a case where body data is applied as identification information will be described. In addition, identification information is not limited to physical data including age and gender, smoking data including whether or not the subject has ever smoked, stay data indicating the location and length of stay of the subject, and the subject includes at least one piece of educational involvement time data.
Examples of the above-mentioned education involvement time data in which the subject was involved in education include the period (e.g., years) during which the subject received education and the period (e.g., years) during which the subject was in the educational field. The period during which the subject was present in the educational setting includes the period during which the subject led the education (for example, the instruction period of a teacher, leader, etc.) and the period during which the subject became a leader during the education.

An electrical configuration of the cognitive function estimation device 10 according to the present embodiment will be described with reference to FIG. 2 . FIG. 2 is a block diagram showing an example of the hardware configuration of the cognitive function estimation device 10. As shown in FIG. As shown in FIG. 2, the cognitive function estimation device 10 includes a computer body 10X. The computer main body 10X includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and an input/output interface (I/O) . The CPU 11, RAM 12, ROM 13, and I/O 14 are connected to the bus 15 so as to be able to communicate with each other. An input unit 16 , a display unit 17 , a communication unit 18 and a storage unit 19 are connected to the I/O 14 .

The CPU 11 is a central processing unit that executes various programs and controls each section. That is, the CPU 11 reads a program from the ROM 13 or the storage unit 19 and executes the program using the RAM 12 as a work area. The CPU 11 performs control of the above components and various arithmetic processing according to programs stored in the ROM 13 or the storage unit 19 . In the present embodiment, the ROM 13 or the storage unit 19 stores an estimation processing program for executing the cognitive function estimation processing, and a learning processing program for constructing the correlation/average information database 100 used for the cognitive function estimation processing. remembered. In this embodiment, a case where the estimation processing program and the learning processing program are stored in the ROM 13 will be described as an example.

Also, the ROM 13 stores various programs and various data. The RAM 12 temporarily stores programs or data as a work area. The storage unit 19 functions as a storage, is configured by a HDD (Hard Disk Drive) or SSD (Solid State Drive), and stores various programs including an operating system and various data.

The input unit 16 includes a pointing device such as a mouse, a keyboard, and a voice input device, and is used for various inputs.

The display unit 17 is, for example, a liquid crystal display or a speaker, and displays or reproduces various kinds of information. The display unit 17 may employ a touch panel system and function as the input unit 16 .

The communication unit 18 is an interface for communicating with other devices such as the odorant component emitting device 20. For example, interfaces based on standards such as Ethernet (registered trademark), FDDI, Wi-Fi (registered trademark), and LTE are used. be done.

Next, the functional configuration of the cognitive function estimation device 10 will be described. In the present embodiment, the cognitive function estimation device 10 includes a learning phase that constructs the correlation/average information database 100 used for cognitive function estimation processing, and an estimation phase that performs cognitive function estimation processing using the constructed correlation/average information database 100. and show different functional configurations.

(learning phase)
First, the cognitive function estimation device 10 that functions as a learning phase will be described.
FIG. 3 is a block diagram showing a functional configuration in the learning phase for constructing the correlation/average information database 100 in the cognitive function estimation device 10. As shown in FIG.

The cognitive function estimation device 10 has a function of constructing a correlation/average information database 100 as a learning phase by executing a learning processing program. That is, the learning processing program has an olfactory data collection function, a physical data acquisition function, a cognitive function test result acquisition function, a correlation/average information derivation function, and a registration function. In this learning phase, the cognitive function estimating device 10 generates identification information including the subject's age, types of odor components that have a correlation with predetermined cognitive function tests, and correlations between the test values of the cognitive function test using the odor components. Correlation information indicating the relationship is registered in the correlation/average information database 100 .

As shown in FIG. 3, in the learning phase, the CPU 11 of the cognitive function estimation device 10 includes an olfactory data collection unit 101, a physical data acquisition unit 102, a cognitive function test result acquisition unit 103, a correlation/average information derivation unit 105, and a registration It functions as part 106 .

FIG. 4 is a flow chart showing the flow of learning processing in the learning phase of the cognitive function estimation device 10. As shown in FIG. In the learning phase, the learning process shown in FIG. 4 is realized by the CPU 11 of the cognitive function estimation device 10 executing the learning process program. As will be described later, in the learning phase, information of each of the olfactory data collection unit 101, the physical data acquisition unit 102, and the cognitive function test result acquisition unit 103 is acquired for each subject.

In the cognitive function estimating device 10, when the construction process of the correlation/average information database 100 is started as the learning phase, the learning process program shown in FIG. 4 is executed. First, in step S100, the physical data acquisition unit 102 receives and acquires physical data indicating information related to the living body of the subject. The physical data includes at least information indicating the subject's age, and can further include information indicating gender. Physical data can also include genetic information (APoE). In this embodiment, a case where the physical data includes at least the age and sex of the subject will be described as an example. As the physical data acquired by the physical data acquisition unit 102, information input by the input unit 16 may be used, or information obtained by communication with another device via the communication unit 18 may be used. Also, the physical data acquired by the physical data acquiring unit 102 is passed to the correlation/average information deriving unit 105 .

Next, in step S102, the cognitive function test result acquisition unit 103 acquires information indicating the results of predetermined cognitive function tests such as MMSE and MoCA-J performed on the subject. Information indicating the result of the predetermined cognitive function test acquired by the cognitive function test result acquisition unit 103 is passed to the correlation/average information derivation unit 105 . For the information acquired by the cognitive function test result acquisition unit 103, information input by the input unit 16 may be used, or information obtained by communication with another device via the communication unit 18 may be used. MMSE is a dementia examination method known as Mini-Mental State Examination. MoCA-J is a dementia test known as the Japanese version of MoCA (Montreal Cognitive Assessment).

After the acquisition of information indicating the physical data and test results described above is completed, the olfactory data collection unit 101 emits an odor component to the subject. Then, the olfactory data collection unit 101 collects data (olfactory data) indicating the subject's olfactory ability to the released odor components.

Specifically, in step S104, the olfactory data collection unit 101 selects a predetermined odor component as the correct answer, and causes the display unit 17 to display options indicating images related to a plurality of odors, including an image indicating the odor component. Control.

That is, the olfactory data collection unit 101 displays to the subject an image of options for which a predetermined odor component is the correct answer, and an image of options for other odor components. For odor components, those related to cognitive functions are used. For example, vanilla, mint, rag smell, socks, caramel, yellow peach, etc. can be used as the smell component.

FIG. 5 shows a screen that displays images of vanilla, mint, rags, socks, caramel, and yellow peach as options, corresponding to odor components. The display of options is not limited to images showing each item, and may be anything that can be used to measure cognitive function, such as characters, moving images, and actual photographs. Also, although not shown, an option "I don't know" may be provided.

Further, in step S104, the olfactory data collection unit 101 controls the odor component releasing device 20 to release the odor component to the subject while changing the amount in stages. Specifically, the olfactory data collection unit 101 notifies the odor component releasing device 20 of a release instruction including the odor component to be released and the concentration level indicating the amount of the odor component to be released. Here, the odor component to be released is the correct odor component. Also, the density level is changed step by step. For example, the release amount is increased stepwise at predetermined time intervals from the start of release. In the present embodiment, a case where the density level is raised every predetermined time will be described as an example. Also, in this embodiment, a case in which there are three levels of density (low/middle/high) will be described as an example.

The olfactory data collection unit 101 first notifies the odor component releasing device 20 of the odor component to be released and the release instruction to set the concentration level to low. Then, after a predetermined period of time has elapsed, the olfactory data collection unit 101 notifies the odorant component release device 20 of the odorant component to be released and the release instruction to increase the concentration level by one level to a medium concentration. Further, after a predetermined period of time has elapsed, the olfactory data collection unit 101 notifies the odorant component release device 20 of the odorant component to be released and the release instruction to increase the concentration level by one level to a high concentration. Then, after a predetermined period of time has elapsed, the olfactory data collection unit 101 notifies the odorant component releasing device 20 of the release end instruction.

Moreover, the olfactory data collection unit 101 repeats the same processing when the correct odor component is changed. Note that the display unit 17 may display options after the olfactory data collection unit 101 releases the odor components, and the display unit 17 does not necessarily have to release the odor after the options are displayed.

In the next step S106, the olfactory data collection unit 101 generates an olfactory score of the odor according to the olfactory sense of the subject, which indicates the selection result in which the correct image is selected by the subject, corresponding to the notified odor component release conditions (type and concentration). is derived and recorded. The olfactory score derived by the olfactory data collection unit 101 is passed to the correlation/average information derivation unit 105 .

In step S107, the correlation/average information deriving unit 105 records the above-described data, that is, the physical data, the cognitive function test results, and the olfactory score for each odor component in association with each other.

FIG. 6 shows an example of data including the olfactory score derived by the olfactory data collection unit 101 . The olfactory score is derived so that the score increases as the degree of correctness for each odor component increases when the subject selects an image corresponding to the emitted odor component. In the example shown in FIG. 6, the olfactory score is "3 points" when the concentration of the emitted odor component is low and correct, and "2 points" when the concentration is low and medium concentration is correct. , "1 point" for incorrect answers at low and medium concentrations and correct answers at high concentrations, and "0 points" for incorrect answers at low, medium and high concentrations. Also, the test values of MMSE and MoCA-J shown as cognitive function tests are examples in which 30 points are the full score.

Whether or not the image selected by the subject is correct may be determined from the number indicating the image input by the subject, or may be automatically determined from the position of the image viewed by the subject. good. The position of the image visually observed by the subject is obtained by detecting point-of-regard data indicating the position gazed at by the subject using a detection device such as a camera (not shown), and the image displayed on the display unit 17 corresponding to the position of the detected point-of-regard data. can be identified from

The above-described processing is executed until the end condition indicating completion of execution for a predetermined number of subjects is met (affirmative determination in step S108). That is, if the processing for the predetermined number of subjects has not been completed, the CPU 11 makes a negative determination in step S108 and returns the processing to step S100. On the other hand, if an affirmative determination is made in step S108, the process proceeds to step S110.

In step S110, the correlation/average information derivation unit 105 classifies the data stored in step S107 according to a predetermined classification condition. Specifically, for each cognitive function test, ie, MMSE and MoCA-J, subjects are classified according to age and gender classification conditions. In this embodiment, the classification condition is a combination of two types of age classification conditions, under 65 years old and 65 years old and over, and two types of gender classification conditions, male as the first gender and female as the second gender, Classify by MMSE and MoCA-J.

Next, in step S112, the correlation/average information derivation unit 105 quantifies the possibility of the presence or absence of correlation between each odor component and each dementia test for each classified group. Specifically, the p-value of correlation is applied as correlation data that quantifies the possibility of correlation between each odor component and each dementia test. The p-value (0 to 1) of the correlation indicates whether the hypothesis "no correlation" is significantly different in the statistical hypothesis test (percentage of falsely rejecting the hypothesis), and the p-value is significant If it is below the level, it concludes that "the hypothesis of 'no correlation' is incorrect."
(Reference technical literature: Bivariate correlation test t-test Introduction to statistics URL <http://www.tamagaki.com/math/Statistics605.html>).

The significance level is expressed as Cp and values such as 10% (Cp=0.1), 5% (Cp=0.05), 1% (Cp=0.01) are applied.
(Reference technical document: URL <http://www1.meijigakuin.ac.jp/~iwamura/class/seminar_10_2012/statistics_chapter5.pdf.>

FIG. 7 shows an example of the p-value of the correlation for each odor component according to the classification criteria for the dementia test for MMSE. FIG. 8 shows an example of the p-value of the correlation for each odor component according to the classification conditions for the dementia test for MoCA-J. 7 and 8 show the correspondence of odor components with a p value of less than 0.1 (p<0.1).

In step S112, the correlation/average information derivation unit 105 derives a first average olfactory score and a second average olfactory score for smells correlated with each dementia test for each group. The first average olfactory score indicates the average value of the olfactory scores of subjects whose cognitive function test values are equal to or less than a predetermined threshold. A subject whose cognitive function test value is equal to or less than a predetermined threshold is an example of a subject with MCI (mild dementia). The second average olfactory score indicates the average value of the olfactory scores of subjects whose cognitive function test values exceeded a predetermined threshold. A subject whose test value in the cognitive function test exceeds a predetermined threshold is an example of a subject (so-called healthy subject) who does not fall under MCI (mild dementia). Therefore, the correlation/average information derivation unit 105 classifies subjects into subjects whose test values are equal to or less than a predetermined threshold and other subjects, and derives an average olfactory score for each of the classified subjects. That is, the cells are classified by age with a predetermined age (65 years old) as a boundary, and the average value of the inspection results for the odor components is derived as the inspection value of the odor components for each of the classified ages.

In FIG. 9, for each classification condition, the first average olfactory score (MCI average olfactory score) and the second average olfactory score (average of healthy subjects) correlated with the MMSE and MoCA-J cognitive function tests. An example of olfactory score) is shown.

Next, in step S114, the registration unit 106 registers data (FIGS. 7 and 8) indicating the p-value of the correlation for each odor component according to the classification conditions described above in the correlation/average information database 100. FIG. In addition, the registration unit 106 stores data ( FIG. 9 ) indicating the relationship between the first average olfactory score and the second average olfactory score, which are correlated with the cognitive function test for each classification condition described above, in the correlation/average information database. Register for 100.

Therefore, the cognitive function estimation device 10 constructs the correlation/average information database 100 in the learning phase as described above.

(estimation phase)
Next, the cognitive function estimation device 10 that functions as an estimation phase will be described.
FIG. 10 is a block diagram showing a functional configuration in an estimation phase in which cognitive function estimation processing is performed using the established correlation/average information database 100. As shown in FIG.
The cognitive function estimating device 10 has a function of estimating the cognitive function of a test subject (subject) using the constructed correlation/average information database 100 as an estimation phase by executing an estimation processing program. That is, the estimation processing program has an olfactory data collection function, a physical data acquisition function, an odor selection function, a correlation/average information extraction function, a cognitive function evaluation function, and a presentation function. In this estimation phase, the cognitive function estimating device 10 selects an odor component having a correlation with the identification information including the age and sex of the subject based on the correlation/average information database 100, and generates olfactory data based on the odor component. Estimate cognitive function from

As shown in FIG. 10, in the estimation phase, the CPU 11 of the cognitive function estimation device 10 includes an olfactory data collection unit 101, a body data acquisition unit 102, an odor selection unit 104, and an extraction unit that extracts data from the correlation/average information database 100. 107 , a cognitive function evaluation unit 108 , and a presentation unit 110 . The physical data acquisition unit 102 is an example of the acquisition unit of the present disclosure, the odor selection unit 104 is an example of the odor component setting unit of the present disclosure, and the cognitive function evaluation unit 108 is an example of the estimation unit of the present disclosure. Portion 110 is an example of a presentation portion of this disclosure.

FIG. 11 is a flowchart showing the flow of estimation processing in the estimation phase of the cognitive function estimation device 10. As shown in FIG. In the estimation phase, the CPU 11 of the cognitive function estimation device 10 executes the estimation processing program, thereby realizing the estimation processing shown in FIG. 11 .

In the cognitive function estimation device 10, when the process of estimating the subject's cognitive function is started as the estimation phase, the estimation process program shown in FIG. 11 is executed. First, in step S200, the physical data acquiring unit 102 receives and acquires physical data indicating information related to the living body of the subject. Here, data indicating the subject's age and sex are acquired as physical data. As the physical data acquired by the physical data acquisition unit 102, information input by the input unit 16 may be used, or information obtained by communication with another device via the communication unit 18 may be used. Also, the physical data acquired by the physical data acquisition unit 102 is passed to the odor selection unit 104 and the cognitive function evaluation unit 108 .

Next, in step S202, the odor selection unit 104 uses the registered correlation/average information database 100 to select odor components corresponding to the body data of the subject. Specifically, when the physical data is passed from the physical data acquiring unit 102, the odor selecting unit 104 supplies the extracting unit 107 with the body data corresponding to the physical data from the correlation/average information database 100 that has already been registered. Requests extraction of data showing odor components that are correlated with age and gender. As a response to the request from the odor selection unit 104, the extraction unit 107 delivers data (FIGS. 7 and 8) indicating the p-value of the correlation for each odor component according to the classification conditions corresponding to the body data. The odor selection unit 104 uses the data from the extraction unit 107 to select odor components corresponding to the physical data of the subject. Information indicating the odor components selected by the odor selection unit 104 is passed to the olfactory data collection unit 101 .

That is, the odor selection unit 104 selects odor components that are correlated with the cognitive function test in the group corresponding to the subject's age and sex from the data obtained by accessing the registered correlation/average information database 100. . For example, when the body data indicating that the subject is a woman aged 65 or older, the odor selection unit 104 selects odor components of "caramel" (FIG. 7) and "socks" (FIG. 8).

The olfactory data collection unit 101 emits the odor component to the subject according to the information indicating the odor component passed from the odor selection unit 104 . Then, the olfactory data collection unit 101 collects data indicating the subject's olfactory ability for the released odor components.

Specifically, in step S204, for each odor component passed from the odor selection unit 104, the olfactory data collection unit 101 selects a plurality of odors including an image representing the odor component as a correct answer that is a predetermined odor component. Control is performed so that options indicating images are displayed on the display unit 17 .

Also, in step S204, the olfactory data collection unit 101 changes the amount of the odorant component in the odorant component releasing device 20 stepwise, for example, at three levels (low/medium/high) of concentration levels for the subject. control the emission. Specifically, the olfactory data collection unit 101 notifies the odor component releasing device 20 of a release instruction including the odor component to be released and the concentration level indicating the amount of the odor component to be released. Here, the odor component to be released is the correct odor component.

Next, in step S206, the olfactory data collection unit 101 calculates the olfactory score of the odor obtained by the olfactory sense of the subject, which indicates the selection result in which the correct image is selected by the subject, corresponding to the release conditions (type and concentration) of the odor component. Derive and record. The olfactory score derived by the olfactory data collection unit 101 is passed to the cognitive function evaluation unit 108 .

In step S208, the cognitive function evaluation unit 108 acquires the average value of the olfactory scores in the classification corresponding to the subject. Specifically, the cognitive function evaluation unit 108 requests the extraction unit 107 to extract data indicating the average olfactory score in the group corresponding to the classification based on the physical data of the subject. In response to the request from the cognitive function evaluation unit 108, the extraction unit 107 extracts the first average olfactory score and the first average olfactory score and the first The data (Fig. 9) showing an average olfactory score of 2 are presented. Then, the cognitive function evaluation unit 108 acquires data ( FIG. 9 ) indicating the first average olfactory score and the second average olfactory score registered in the correlation/average information database 100 from the extraction unit 107 .

Next, in step S210, the cognitive function evaluation unit 108 derives a cognitive function evaluation value for the subject using the average value of the acquired olfactory scores. The indices derived by the cognitive function evaluation unit 108 are passed to the presentation unit 110 . The evaluation value of the cognitive function of the subject can be derived from the following arithmetic expression as an index SR indicating the evaluation value. The evaluation value derived by the arithmetic expression, that is, the index SR, is calculated so that the degree of possibility of deterioration of cognitive function (for example, the risk of dementia) decreases as it approaches "0".

SR = (Sc - Sa) / (Sc - Sn)
However, Sn indicates the first average olfactory score (average olfactory score of MCI), Sc indicates the second average olfactory score (average olfactory score of healthy subjects), and Sa indicates the olfactory score of the subject to be estimated. .

For example, in the case of a subject whose physical data indicate a woman aged 65 or older, the average olfactory score of the cognitive function test by MMSE, labeled as MMSE judgment in FIG. . Also, for the olfactory score for the odor component of "socks", the average olfactory score of the cognitive function test by MoCA-J, labeled as MoCA-J judgment in FIG. 9, is applied.

Then, the presentation unit 110 presents information about cognitive function in step S212. For example, the presentation unit 110 performs display control to display the index SR on the display unit 17 as information related to the test of cognitive function. Data indicating the presence or absence of the possibility of cognitive function deterioration and data regarding the degree (magnitude) of the possibility of cognitive function deterioration are applied to the information on the test of cognitive function. The data indicating whether or not there is a possibility that the cognitive function may be degraded is determined as follows: when the index SR is equal to or less than a predetermined threshold, there is no possibility of the cognitive function being degraded, and when the index SR exceeds the predetermined threshold, It is possible to assume that there is a possibility that cognitive function is declining. The data regarding the degree (magnitude) of the risk of cognitive function deterioration should be such that the degree (magnitude) of the risk of cognitive function deterioration increases as the index SR increases.

In addition, the presentation unit 110 can present a cognitive function test recommended based on the subject's olfactory score as information related to the test of cognitive function. In order to present a cognitive function test recommended from the subject's olfactory score, the presentation unit 110 may obtain information (recommended information) indicating a recommended cognitive function test from the cognitive function evaluation unit 108 . That is, the cognitive function evaluation unit 108 may derive a cognitive function test corresponding to the smell component indicated by the subject's olfactory score as a recommended cognitive function test, and notify the presentation unit 110 of the recommended cognitive function test. For example, when the index SR for the release of the odor component of "socks" is large (equal to or greater than a predetermined threshold value) for women under the age of 65, the correlation/average information database 100 is referenced, and the corresponding odor component (here, " The cognitive function test of MoCA-J, which has a correlation with the odor component of socks), can be presented to the subject as recommended information to recommend taking a desired cognitive function test.

Therefore, in the estimation phase, the cognitive function estimation device 10 estimates the cognitive function using the correlation/average information database 100 as described above.

As described above, according to the cognitive function device according to the present embodiment, a plurality of odor components are released with different concentrations, the subject selects the released odor components, and the correct and incorrect selections are made. Correspond to the results of multiple dementia tests for the correct olfactory score. In addition, the subjects are classified by age and sex, and the possibility of correlation between each odor component and each cognitive function test is quantified for each classified group. In addition, regarding odor components correlated with each dementia test, the average olfactory score of subjects who may have cognitive function deterioration (e.g., MCI: mild dementia subjects) and the cognitive function deterioration An average olfactory score is derived for subjects (for example, healthy subjects) who are less likely to have cognitive function decline than those who are at risk, and stored as a correlation/average information database. By using this correlation/average information database to derive an olfactory score based on the release of odor components, it becomes possible to derive an evaluation value (an index indicating the possibility of cognitive function deterioration).

In addition, it is possible to present a recommended cognitive function test to a subject who is likely to have cognitive function decline by using the correlation/average information database as described above.

In this way, the olfactory test can accurately and simply estimate the possibility of a decline in cognitive function, such as the risk of dementia, from the olfactory score. In addition, the subject can estimate the cognitive function only by conveying the results of the olfactory perception of the released odor components, thereby reducing the burden on the subject.

In the present embodiment, the correlation/average information database 100 is constructed in the cognitive function estimation device 10 (learning phase). It may be obtained as 100.

Also, the technology of the present disclosure is not limited to the above-described embodiments, and various modifications and applications are possible without departing from the gist of the present invention.

For example, in the above embodiment, the case where the release amount of the odor component is increased in stages has been described as an example, but the present invention is not limited to this. A configuration may be adopted in which the amount of released odor components is reduced in stages.

In addition, when the odor is emitted multiple times, the olfactory ability may be measured in consideration of the order of the question, which is a set of correct answers and alternatives. This is because the accuracy can be further improved by considering the correlation such as the similarity of the correct odor components depending on the order of each question.

[Second embodiment]
Next, a second embodiment according to the present disclosure will be described. Since the second embodiment has the same configuration as the first embodiment, the same parts are denoted by the same reference numerals, detailed explanations thereof are omitted, and different parts are explained.

In the first embodiment, the age and sex of a subject to be estimated (subject) are used to evaluate the cognitive function of the subject. In the second embodiment, the cognitive function of the subject is evaluated without using the age and sex of the subject.

Specifically, the cognitive function estimation system according to the second embodiment includes an odor component release section, a score setting section, and an estimation section. The odor component releasing section releases each of a plurality of odor components to the subject while varying the concentration of each odor component in a plurality of stages. The score setting unit sets a score corresponding to the correct concentration when the subject's answer indicating which odor component is the odor component released from the odor component releasing unit is correct. The estimation unit estimates a cognitive function evaluation value for the subject based on the total value of the scores set by the score setting unit for the plurality of odor components.

According to the cognitive function estimation system according to the second embodiment, it is possible to estimate the cognitive function with high accuracy through an olfactory test using certain odor components.

<Configuration of cognitive function estimation system>
FIG. 12 is a block diagram showing an overall schematic configuration of the cognitive function estimation system according to this embodiment. As shown in FIG. 12, in the cognitive function estimation system according to this embodiment, the cognitive function estimation device 10A includes a correlation/probability information database 100A instead of the correlation/average information database 100 shown in FIG. In addition, the cognitive function estimation device 10A estimates cognitive function using the correlation/probability information database 100A. The correlation/probability information database 100A contains correlation information indicating the correlation between the results of the cognitive function test of the subject who underwent the cognitive function test and the test results of the odor components determined by the combination of the odor components determined from the results of the cognitive function test. is stored. It should be noted that the odor component releasing device 20 is an example of the odor component releasing section of the present disclosure.

In addition, in this embodiment, physical data including the age and sex of the subject and the subject whose cognitive function is to be estimated are unnecessary.

The electrical configuration of the cognitive function estimation device 10A according to the present embodiment is the same configuration as that of the cognitive function estimation device 10 described above, so description thereof will be omitted.

Next, the functional configuration of the cognitive function estimation device 10A will be described. In the present embodiment, the cognitive function estimation device 10A includes a learning phase for constructing a correlation/probability information database 100A used for cognitive function estimation processing, and an estimation phase for cognitive function estimation processing using the constructed correlation/probability information database 100A. and show different functional configurations.

(learning phase)
First, the cognitive function estimation device 10A that functions as a learning phase will be described.
FIG. 13 is a block diagram showing the functional configuration in the learning phase for constructing the correlation/probability information database 100A in the cognitive function estimation device 10A.

The cognitive function estimation device 10A has a function of constructing a correlation/probability information database 100A as a learning phase by executing a learning processing program. That is, the learning processing program has an olfactory data collection function, a cognitive function test result acquisition function, and a registration function, excluding the physical data acquisition function and correlation/average information derivation function described above, and newly derives correlation/probability information. have a function. In this learning phase, the cognitive function estimation device 10A generates a combination of odor components having a correlation with a predetermined cognitive function test, and correlation information indicating the correlation between the test result of the odor component and the test result of the cognitive function test. is registered in the correlation/probability information database 100A.

As shown in FIG. 13 , in the learning phase, the CPU 11 of the cognitive function estimation device 10A functions as an olfactory data collection unit 101, a cognitive function test result acquisition unit 103, a correlation/probability information derivation unit 115, and a registration unit 116.

FIG. 14 is a flowchart showing the flow of learning processing in the learning phase of the cognitive function estimation device 10A. In the learning phase, the learning process shown in FIG. 14 is realized by the CPU 11 of the cognitive function estimation device 10A executing the learning process program. As will be described later, in the learning phase, each information of the olfactory data collection unit 101 and the cognitive function test result acquisition unit 103 is acquired for each subject.

In the cognitive function estimating device 10A, when the construction processing of the correlation/probability information database 100A is started as the learning phase, the learning processing program shown in FIG. 14 is executed. First, as in step S102 described above, in step S120, the cognitive function test result acquisition unit 103 acquires information indicating the results of a predetermined cognitive function test performed on subjects in the target group. . In this embodiment, the cognitive function test will be described as an example of a dementia screening test conducted by licensed medical practitioners, in which the MoCA-J described above is applied. In step S 120 , the information indicating the results of the cognitive function test by MoCA-J acquired by the cognitive function test result acquiring unit 103 is passed to the correlation/probability information deriving unit 115 .

When the acquisition of the information indicating the test result is completed, in step S122, similarly to step S104 described above, the olfactory data collection unit 101 emits an odor component to the subject, and detects the olfactory sense of the subject for the emitted odor component. Collect data that show your abilities. That is, the olfactory data collection unit 101 displays to the subject an image of options for which a predetermined odor component is the correct answer and an image of options for other odor components (FIG. 5). The component release device 20 performs control to change the amount stepwise and release it.

Next, in step S124, similarly to step S106 described above, the olfactory data collection unit 101 displays a selection result in which the correct image is selected by the subject in accordance with the odor component release conditions (type and concentration). Derive and record the olfactory score of the odor by the olfactory sense of The olfactory score derived by the olfactory data collection unit 101 is passed to the correlation/probability information derivation unit 115 .

In step S126, similar to step S107 described above, the correlation/probability information derivation unit 115 associates and records the data described above, that is, the test results of cognitive function and the olfactory score.

FIG. 15 shows an example of data in which the olfactory data including the olfactory score derived by the olfactory data collection unit 101 is associated with the test result data of cognitive function. FIG. 15 is an example of a data table in which each data of the olfactory score for each odor component and the test result of cognitive function is stored in association with the identification number that identifies the subject.

Next, similarly to step S108 described above, the above-described processing is performed until the end condition indicating completion of the execution for a predetermined number of subjects is satisfied (affirmative determination is made in step S128).

In step S130, the correlation/probability information derivation unit 115 uses the data of the odor test results (olfactory data including the olfactory score) and the cognitive function test results (MoCA-J data) in the estimation phase described later. A combination of odor components to be used is derived.

The processing for deriving the combination of odor components is performed by executing processing according to the following selection procedure.

In the first selection procedure, the data obtained from the above-described test for multiple subjects, that is, the MoCA-J data, which is the test result of cognitive function, and the olfactory score indicating the test result of olfactory function are associated. get the data In this embodiment, an olfactory score based on the release of six types of odor components, vanilla, rag smell, caramel, mint, socks, and yellow peach, was applied (see FIG. 15).

In the second selection procedure, the above data (olfactory data and MoCA-J data) are classified into persons suspected of having MCI and persons not corresponding to MCI (so-called healthy persons).

By the way, for the test value of the cognitive function test (MoCA-J data), the test value to determine "a person suspected of having MCI (mild dementia)" from a statistical point of view and an empirical point of view A predetermined threshold is determined in advance. Therefore, subjects whose cognitive function test values (MoCA-J data) exceed the threshold are set as so-called healthy subjects (hereinafter referred to as CN subjects) who do not correspond to MCI. On the other hand, subjects whose test values in the cognitive function test are below the threshold are set as subjects suspected of having MCI (hereinafter referred to as MCI subjects). Therefore, the correlation/probability information derivation unit 115 classifies the MCI subjects whose MoCA-J data is below the threshold and the CN subjects whose MoCA-J data exceeds the threshold. For example, when the MoCA-J data are distributed in a value range of 0 to 30, the threshold is set to 25, and subjects with a value of 25 or less are determined to be MCI subjects.

In the third selection procedure, for each combination of arbitrary odor components (hereinafter referred to as an odor component group) out of a plurality of odor components, the correlation with the test results of cognitive function is calculated for each different odor component group. Derive the evaluation index to be evaluated.

In this embodiment, for each of the odor component groups, the distribution of MCI and CN subjects with respect to the total olfactory score is analyzed to derive an evaluation index. For analysis of the distribution, analysis of Receiver Operating Characteristic (ROC) is applied. An evaluation index is derived by obtaining an AUC (Area Under the Curve) indicating a discrimination power evaluation value obtained from this ROC analysis. That is, in the third selection procedure, the ROC analysis of the distribution of the total value of the olfactory scores of a plurality of odor components for each odor component group between MCI and CN subjects is performed, and AUC, which is an evaluation index, is derived. Since the ROC analysis is a well-known technique, detailed description thereof will be omitted.

In the fourth selection procedure, an odor component group of evaluation indexes (AUC) that meet predetermined evaluation conditions is derived as a combination of odor components used in an estimation phase, which will be described later. The evaluation condition can be selected by extracting any of the odor component groups whose evaluation index (AUC) exceeds a predetermined threshold value (correlation value). In this case, it is possible to select the odor component group with the maximum value of the evaluation index (AUC) as the most preferable combination of odor components for the test of cognitive function.

FIG. 16 shows an example of data indicating the evaluation index. FIG. 16 is an example of an evaluation table in which correspondences between odor component groups and evaluation indices indicating AUC values in the results of ROC analysis are arranged in descending order of AUC values. In the column of combinations of odor components, identification numbers for identifying odor components are shown. That is, "1": vanilla, "2": rag odor, "3": caramel, "4": mint, "5": socks, and "6": yellow peach.

In the example shown in FIG. 16, the odor component group obtained by combining the four odors of "1" vanilla, "4" mint, "5" socks, and "6" yellow peach has the highest AUC (0.1 in FIG. 16). 649). As a result, the odor component group by combining the four odor components of "1" vanilla, "4" mint, "5" socks, and "6" yellow peach is the odor component that has the highest correlation with the test value of the cognitive function test. It is understood to be a combination of It is also possible to define the above-mentioned four odor components of rank 1 as the odor component group by setting 0.645 as the threshold value (correlation value). The threshold value (correlation value) is appropriately determined, and when a plurality of odor component groups are extracted, the component group with the maximum value may be selected as described above, and the odor component having a smaller number of combinations than the other component groups may be selected. may be selected.

Note that derivation of the evaluation index described above is not limited to deriving AUC by performing ROC analysis. For example, other analysis methods for analyzing the distribution of MCI and CN persons may be applied. When another analysis method is applied, an evaluation method for evaluating the analysis results by the other analysis method may be used.

In this way, the correlation/probability information derivation unit 115 derives combinations of odor components (here, vanilla, mint, socks, and yellow peach) using the data of the odor test results and the cognitive function test results. do.

Next, in step S132 of FIG. 14, the correlation/probability information derivation unit 115 indicates the correlation between the odor test results (olfactory data including the olfactory score) and the cognitive function test results (MoCA-J data). Derive the data.

The process of deriving the data indicating the correlation is performed by executing the process according to the following derivation procedure.

In the first derivation procedure, a plurality of subjects are classified into MCI subjects and CN subjects, and the number of persons for each olfactory data in the odor component group is derived.

First, the correlation/probability information deriving unit 115 uses the olfactory data and the cognitive function test result data (FIG. 15) to show the MoCA-J data, which is the cognitive function test result, and the olfactory function test result. Acquire the data associated with the olfactory score. Here, the olfactory score indicating the test results of the olfactory function is the olfactory component group derived by the selection procedure described above, that is, the olfactory score for the four types of odor components: vanilla, mint, socks, and yellow peach.

Next, the correlation/probability information derivation unit 115 calculates the total value of the olfactory scores (hereinafter referred to as the total score) for each of a plurality of subjects, and uses the data of MoCA-J for each total score. and CN persons, and calculate the number of persons classified.

FIG. 17 shows an example of data showing the correspondence relationship between the total score, the number of MCI persons and the number of CN persons. In the example shown in FIG. 17, the number of CN persons tends to increase as the value of the total score increases, while the number of MCI persons is random.

In the second derivation procedure, the ratio of the number of persons with MCI and persons with CN (hereinafter referred to as the MCI rate) is calculated based on the following arithmetic expression for each total value of olfactory scores.
(MCI rate) = (number of MCI persons) / {(number of MCI persons) + (number of CN persons)}

The third derivation procedure derives the correlation between the total olfactory score and the probability of being a person with MCI. The MCI rate can be considered as the probability that the subject is likely to have MCI with respect to the total value of the olfactory scores of the odor component group. Therefore, in this embodiment, the correlation between the total value of the olfactory score and the probability indicating the possibility of being a person with MCI is calculated using the test results of a large number of subjects. It is derived as the probability of

FIG. 18 shows an example of the relationship between the odor test results and the cognitive function test results, showing the two-dimensional relationship between the total score of the odor test results and the MCI rate. As shown in FIG. 18, the MCI rate decreases as the total score increases. In the third derivation procedure, the trend in the relationship shown in FIG. 18 is derived.

Specifically, the number of samples for each value of the MCI rate (the total number of subjects) is weighted as a coefficient, and the MCI rate is subjected to an analysis process of, for example, simple regression analysis using the total score. As a result of this analysis processing, the correlation between the total score and the probability of being a person with MCI can be represented by, for example, the following regression equation.
(MCI rate) = -0.04275 x (total score) + 0.6703

In the simple regression analysis, the relationship between the total score and the MCI rate (Fig. 18) is analyzed by generating the same number of samples as the number of subjects used in the calculation of the MCI rate. For example, there are 32 MCI persons with a total score of 0 and 18 CN persons, so the MCI rate is 0.64 (=32/(32+18)). Since the total number of people with a total score of 0 is 50, 50 samples with an MCI rate of 0.64 are generated for the results with a total score of 0, and simple regression is performed. In other words, the MCI rate calculated with a small number of people may be greatly affected by outliers, so the MCI rate calculated with a small number of people is neglected, and the MCI rate calculated with a large number of people is emphasized. and return.

Note that the above regression equation can be replaced with the following general equation.
f(x)=a*x+b
f(x) indicates the MCI rate and x indicates the total score. Coefficients a and b are coefficients (constants) obtained by analysis.

In this manner, the correlation/probability information derivation unit 115 derives the information on the regression equation as data indicating the correlation between the odor test results and the cognitive function test results.

Next, in step S134 shown in FIG. 14, the registration unit 116 registers the data indicating the above-described combination of odor components in the correlation/probability information database 100A. In addition, the registration unit 116 also registers data indicating the correlation between the above-described odor test results and cognitive function test results in the correlation/probability information database 100A.

As described above, the cognitive function estimation device 10A constructs the correlation/probability information database 100A in the learning phase described above.

(estimation phase)
Next, the cognitive function estimation device 10A that functions as an estimation phase will be described.
FIG. 19 is a block diagram showing a functional configuration in an estimation phase in which cognitive function estimation processing is performed using the constructed correlation/probability information database 100A.

The cognitive function estimating device 10A has a function of estimating the cognitive function of a test subject (subject) using the constructed correlation/probability information database 100A as an estimation phase by executing an estimation processing program. That is, the estimation processing program has an olfactory data collection function, an odor selection function, a correlation/probability information extraction function, a cognitive function evaluation function, and a presentation function. In this estimation phase, the cognitive function estimation device 10A selects an odor component having a correlation based on the correlation/probability information database 100A, and estimates the cognitive function from the olfactory data of the odor component.

As shown in FIG. 19, in the estimation phase, the CPU 11 of the cognitive function estimation device 10A includes an olfactory data collection unit 101, an odor selection unit 104, an extraction unit 117 that extracts data from the correlation/probability information database 100A, and a cognitive function evaluation unit. 118 and presentation unit 120 . The olfactory data collection unit 101 is an example of the score setting unit of the present disclosure, the odor selection unit 104 is an example of the odor component setting unit of the present disclosure, the cognitive function evaluation unit 118 is an example of the estimation unit of the present disclosure, Presentation unit 120 is an example of the presentation unit of the present disclosure.

FIG. 20 is a flowchart showing the flow of estimation processing in the estimation phase of the cognitive function estimation device 10A. In the estimation phase, the CPU 11 of the cognitive function estimation device 10A executes the estimation processing program, thereby realizing the estimation processing shown in FIG.

In the cognitive function estimation device 10A, when the process of estimating the cognitive function of the test subject (subject) is started as the estimation phase, the estimation process program shown in FIG. 20 is executed. First, in step S220, the odor selection unit 104 acquires data representing a combination of multiple odor components (odor component group) from the correlation/probability information database 100A. Specifically, the odor selection unit 104 requests the extraction unit 117 to extract data representing a combination of multiple odor components (a odor component group) from the correlation/probability information database 100A. As a response to the request from the odor selecting unit 104, the extracting unit 107 delivers data indicating a combination of multiple odor components (an odor component group).

Next, in step S222, the odor selection unit 104 selects the plurality of odor components (the odor component group) acquired in step S220 as the plurality of odor components (the odor component group) to be used for inspection. The odor selection unit 104 passes information indicating the plurality of selected odor components to the olfactory data collection unit 101 . Here, the odor selection unit 104 selects four types of odor components: vanilla, mint, socks, and yellow peach.

The olfactory data collection unit 101 emits the odor component to the subject according to the information indicating the odor component passed from the odor selection unit 104 in step S224, as in step S204 described above. Then, the olfactory data collection unit 101 collects data indicating the subject's olfactory ability for the released odor components.

Next, in step S226, similarly to step S206 described above, the olfactory data collection unit 101 selects a correct image according to the release conditions (type and concentration) of the odor component. Derive and record the olfactory score of the odor by the olfactory sense of The olfactory score derived by the olfactory data collection unit 101 is passed to the cognitive function evaluation unit 118 .

Cognitive function evaluation unit 118 acquires data indicating the correlation between the olfactory score and the cognitive function test results in step S228. Specifically, the cognitive function evaluation unit 118 requests the extraction unit 117 to extract data representing the regression equation described above. The extraction unit 117 delivers data representing the regression equation as a response to the request from the cognitive function evaluation unit 118 . Then, the cognitive function evaluation unit 118 acquires the data representing the regression equation registered in the correlation/probability information database 100A from the extraction unit 117 .

Next, in step S230, the cognitive function evaluation unit 118 first totals the olfactory scores for each odor component derived by the olfactory data collection unit 101 to derive a total score. Note that the total score may be derived and acquired by the olfactory data collection unit 101 . Next, using the total score and the regression equation, the cognitive function evaluation value for the subject, that is, the MCI rate (probability) value is derived. The indices derived by the cognitive function evaluation unit 118 are passed to the presentation unit 120 .

Then, the presentation unit 120 presents information about cognitive function in step S232. For example, the presentation unit 120 performs display control to display the value of the MCI rate (probability), which is an index, on the display unit 17 as information related to testing of cognitive function. The data displayed on the display unit 17 indicates that there is no possibility of cognitive function deterioration when the index is equal to or less than a predetermined threshold value, and that there is no possibility of cognitive function deterioration when the index SR exceeds the predetermined threshold value. Yes. The data on the degree (magnitude) of the possibility of cognitive function decline is such that the degree (magnitude) of the possibility of cognitive function decline increases as the value of the MCI rate, which is an index, increases. Just do it. Also, the MCI rate may be displayed as a probability.

Therefore, in the estimation phase, the cognitive function estimation device 10A estimates the cognitive function using the correlation/probability information database 100A as described above.

As described above, according to the cognitive function device according to the present embodiment, a plurality of odor components are released with different concentrations, the subject selects the released odor components, and the correct and incorrect selections are made. Correspond to the result of the cognitive function test for the correct olfactory score. In addition, for multiple odor components that are correlated in each cognitive function test, the total value of the olfactory scores (total score) was used to derive a regression formula that shows the correlation between the odor test results and the cognitive function test results. , the regression formula is stored as a correlation/probability information database. By using this correlation/probability information database to derive the total olfactory score from the release of odor components related to cognitive function, we derive an evaluation value (indicator) that indicates the possibility that cognitive function is declining. be possible.

[Third Embodiment]
Next, a third embodiment according to the present disclosure will be described. Since the third embodiment has the same configuration as the first embodiment, the same parts are denoted by the same reference numerals, detailed explanations thereof are omitted, and different parts are explained.

In the first embodiment, the age and sex of a subject to be estimated (subject) are used to evaluate the cognitive function of the subject. In the third embodiment, the subject's smoking history is further used to evaluate the cognitive function of the subject. That is, in the present embodiment, the identification information includes physical data indicating age and sex, and smoking data indicating the presence or absence of smoking experience as an example of smoking history.

<Configuration of cognitive function estimation system>
FIG. 21 is a block diagram showing an overall schematic configuration of a cognitive function estimation system according to the third embodiment. The cognitive function estimation system according to the present embodiment is a cognitive function estimation device that further uses smoking data of a subject to be estimated (subject) and estimates cognitive function from information obtained by odor component release by the odor component release device 20. 10B. That is, the cognitive function estimating device 10B includes identification information including the age, sex, and smoking history of the subject who has undergone the cognitive function test, the type of odor component that correlates with the cognitive function test, and the test value of the odor component. Cognitive function is estimated using a correlation/regression information database 100B that stores information associated with .

The smoking data included in the identification information can be applied to data including the presence or absence of smoking experience, and if you have a smoking experience of a predetermined period or more or a predetermined number of cigarettes If the number of cigarettes is less than the predetermined number, the smoking experience can be judged as null.

In the cognitive function estimation device 10B, the ROM 13 or the storage unit 19 (FIG. 2) stores an estimation processing program for executing a cognitive function estimation process, the details of which will be described later, and a correlation/regression information database 100B used for the cognitive function estimation process. A learning processing program for construction is stored.

Since the electrical configuration of the cognitive function estimation device 10B is the same configuration as the cognitive function estimation device 10 described above, the description thereof will be omitted.

Next, the functional configuration of the cognitive function estimation device 10B will be described. Cognitive function estimation device 10B has a learning phase in which correlation/regression information database 100B used for cognitive function estimation processing is constructed, and an estimation phase in which cognitive function estimation processing is performed using constructed correlation/regression information database 100B. Show configuration.

(learning phase)
First, the cognitive function estimation device 10B that functions as a learning phase will be described.
FIG. 22 is a block diagram showing the functional configuration in the learning phase for constructing the correlation/regression information database 100B in the cognitive function estimation device 10B.

The cognitive function estimation device 10B has a function of constructing a correlation/regression information database 100B as a learning phase by executing a learning processing program. That is, the learning processing program has an olfactory data collection function, a data acquisition function, a cognitive function test result acquisition function, a correlation/regression information derivation function, and a registration function. In this learning phase, the cognitive function estimating device 10B uses identification information including age, sex, and smoking history of the subject, types of odor components that have a correlation with a predetermined cognitive function test, and tests of the odor components and cognitive functions. Correlation information indicating the correlation with the result is registered in the correlation/regression information database 100B.

As shown in FIG. 23, in the learning phase, the CPU 11 of the cognitive function estimation device 10B includes an olfactory data collection unit 101, a data acquisition unit 122, a cognitive function test result acquisition unit 103, a correlation/regression information derivation unit 125, and a registration unit. 126.

FIG. 23 is a flowchart showing the flow of learning processing in the learning phase of cognitive function estimation device 10B. In the learning phase, the learning process shown in FIG. 24 is realized by the CPU 11 of the cognitive function estimation device 10B executing the learning process program. As will be described later, in the learning phase, information of each of the olfactory data collection unit 101, the data acquisition unit 122, and the cognitive function test result acquisition unit 103 is acquired for each subject.

In the cognitive function estimating device 10B, when the building processing of the correlation/regression information database 100B is started as the learning phase, the learning processing program shown in FIG. 24 is executed. First, in step S140, the data acquisition unit 122 receives and acquires physical data including information indicating the age and sex of the subject and smoking data. The data acquired by the data acquisition unit 122 is passed to the correlation/regression information derivation unit 125 .

In step S142, similarly to step S102, the cognitive function test result acquisition unit 103 acquires information indicating the results of predetermined cognitive function tests such as MMSE and MoCA-J performed on the subject. Information indicating the result of the predetermined cognitive function test acquired by the cognitive function test result acquiring unit 103 is passed to the correlation/regression information deriving unit 125 .

In step S144, as in step S104 above, the olfactory data collection unit 101 that collects data related to the olfactory test selects a predetermined odor component as the correct answer, and selects a plurality of odor-related images including an image representing the odor component. It is controlled to be displayed on the display unit 17 . Similar to the above examples, vanilla, mint, rag smell, socks, caramel, yellow peach, etc. can be used as the odor component.

In step S146, as in step S106 above, the olfactory data collection unit 101 selects the correct image by the subject in accordance with the notified odor component release conditions (type and concentration). Derive and record the olfactory score of the odor by The olfactory score derived by the olfactory data collection unit 101 is passed to the correlation/regression information derivation unit 125 .

In step S147, the correlation/regression information derivation unit 125 associates and records the data described above, that is, the physical data, the smoking data, the cognitive function test results, and the olfactory score.

FIG. 24 shows an example of data including the olfactory score derived by the olfactory data collection unit 101. As shown in FIG. As in the example shown in FIG. 6, the olfactory score is derived so that the score increases as the degree of correctness for each odor component increases when the subject selects an image corresponding to the emitted odor component. be. In addition, an example of a case where the above-mentioned 30 points is the full score is shown for the value of the cognitive function test.

The above-described processing is executed until the end condition indicating completion of execution for a predetermined number of subjects is met (affirmative determination in step S148). That is, if the processing for the predetermined number of subjects has not been completed, the CPU 11 makes a negative determination in step S148 and returns the processing to step S140. On the other hand, if an affirmative determination is made in step S148, the process proceeds to step S150.

In step S150, the correlation/regression information deriving unit 125 classifies the data stored in step S147 according to predetermined classification conditions. The predetermined classification condition in the present embodiment is a determination condition for determining whether a subject who has undergone a cognitive function test is an MCI person or a CN person. In the cognitive function test, a threshold value for determining whether the test value is a person with MCI or a person with CN is set in advance. This is because the standard of the test value for determining whether a person is an MCI person or a CN person is considered to differ depending on the type of cognitive function test.

For example, in MoCA-J, a threshold value of 25 points is set in advance for test values distributed in the range of 0 to 30 points. Therefore, a subject with a MoCA-J test score of 25 or less is highly likely to be a person with MCI, and a subject with a score of over 25 is less likely to be a person with MCI and more likely to be a person with CN. Note that the 25 inspection values set as thresholds in MoCA-J are an example, and the number is not limited to this number. On the other hand, in MMSE, a threshold value of 27 points is set in advance for inspection values distributed in the range of 0 to 30 points. Therefore, a subject with an MMSE test score of 27 or less is highly likely to be a person with MCI, and a subject with a score of over 27 is less likely to be a person with MCI and more likely to be a person with CN. Note that the 27 inspection values set as thresholds in MMSE are also an example, and are not limited to this number.

Therefore, in step S150, as a first step, subject data is classified for each type of cognitive function test, MMSE and MoCA-J. That is, the subject's identification information and olfactory score data are classified into MCI and CN subjects.

Next, in step S152, the correlation/regression information deriving unit 125 uses the classified data to derive the subject's data, the odor component, and data indicating the correlation between the odor component and the cognitive function test. Step S152 includes a process of analyzing the data distribution and deriving a combination of odor components according to the type of cognitive function test.

First, using the data classified as described above, the distribution of the data is analyzed to derive a combination of odor components according to the type of cognitive function test. This combination of odor components is performed using the AUC of the results analyzed using the regression model. In this embodiment, a logistic regression model is applied as the regression model.

Specifically, a logistic regression with the subject's data is performed on the total scores for different combinations of odor components to derive the AUC. Logistic regression is a well-known technique, so a detailed explanation is omitted, but for a variable that takes either 0 or 1, the probability that the variable will be 1 is an analysis method that predicts with a plurality of explanatory variables. be. In this embodiment, as logistic regression, the data of the subject, the body data and smoking data included in the subject's identification information, and the data indicating the age, gender and smoking history of the subject, and the olfactory score of the subject as explanatory variables, MCI subjects is "1" and CN is "0". Here, for a variable indicating MCI or CN (that is, a binary variable indicating 0 or 1), the probability px of being an MCI person (that is, a subject whose binary variable indicates 1) is expressed by multiple explanations. Perform predictive analysis by variables.

A logistic regression model can be represented by the following estimation formula.
px=1/[1+exp{-(pa+pb+pc+pd)}]
In the above formula,
When A, B, C, and D are constants,
pa indicates (total value of A × score),
pb indicates (B × age),
pc indicates (C x gender),
pd indicates (D x smoking history).

The constants A, B, C, D above are the logistic regression coefficients. Constants A, B, C, and D, which are coefficients of logistic regression, can be estimated using the maximum likelihood method (MLE: Maximum Likelihood Estimation). Since the maximum likelihood method is a well-known technique, detailed description is omitted, but the sample data, that is, the value of the parameter (logistic regression coefficient) optimized so that the probability obtained from the subject data is the highest It is a method of derivation.

Therefore, using the data indicating age, sex and smoking history by the subject's identification information (physical data and smoking data) and the olfactory score of the subject, so that the probability px based on the data of the subject who is an MCI person is high, Also, the constants A, B, C, and D are derived so that the probability px based on the data of the CN subjects is low. The constants A, B, C, and D are derived for each of the cognitive function test types MMSE and MoCA-J. Also, the constants A, B, C, and D are derived for each of all possible combinations of one or more of the six types of odor components described above. The derived constants A, B, C, and D are passed to the registration unit 126 in association with the combination of the type of cognitive function test and the odor component, and registered in the correlation/regression information database 100B.

Next, we evaluate the estimation of cognitive function by combining odor components. For the evaluation, the AUC obtained by the ROC analysis described above is applied as an evaluation index.

Using the estimation formula described above, it is possible to calculate the probability px that the subject is predicted to have MCI. If a subject with a high predicted probability px is an MCI subject and a subject with a low probability px is a CN subject, the prediction accuracy of the above estimation formula is high. By setting a threshold value called a cutoff value, it is possible to determine whether a person is an MCI person or a CN person. However, in general, when a threshold is set to increase the accuracy of predicting a subject suspected of MCI as a person with MCI, the accuracy of predicting a subject not suspected of having MCI as a person with CN generally decreases. On the other hand, if a threshold value is set to increase the accuracy of predicting a subject who is not suspected of having MCI as a CN subject, the accuracy of predicting a subject suspected of having MCI as having MCI decreases. Therefore, in the embodiment, the ROC curve is used to comprehensively evaluate the prediction accuracy instead of limiting to a specific threshold. Specifically, using subject data, an ROC curve in ROC analysis is derived, and AUC is derived.

FIG. 25 shows an example of the ROC curve. FIG. 25 is a diagram in which sensitivity is set on the vertical axis and (1-specificity) is set on the horizontal axis. Sensitivity indicates the proportion of subjects with suspected MCI who are predicted to have MCI. Specificity indicates the proportion of subjects without MCI who were predicted to be CN. AUC corresponds to the area on the lower side of the figure bounded by the ROC curve.

As the AUC value increases, the accuracy of predicting that the subject is a person with MCI improves. Therefore, here, an odor component group of an evaluation index (AUC) that meets predetermined evaluation conditions is derived as a combination of odor components used in the estimation phase, which will be described later. The evaluation condition is to extract and select any of the odor component groups whose evaluation index (AUC) exceeds a predetermined value. In this embodiment, a group of odor components having the maximum value of the evaluation index (AUC) is selected as the combination of odor components that is most preferable for the test of cognitive function.

26 and 27 show an example of data indicating the evaluation index (AUC). FIG. 26 is an example of an evaluation table in which the AUC values for the odor component group are arranged in descending order of the AUC values for the test results of the cognitive function test by MoCA-J. FIG. 27 is an example of an evaluation table in which the AUC values for the odor component group are arranged in descending order of the AUC values for the test results of the cognitive function test by MMSE. In the column of combination of odor components, the odor components are indicated by the identification numbers described above.

As shown in FIG. 26, in the results of the cognitive function test by MoCA-J, the odor component group with the combination of two odors, "4" mint and "5" socks, had the highest AUC. ing. Therefore, it is understood that the combination of two odor components, "4" mint and "5" socks, is the combination of odor components that has the strongest correlation with the test values of the cognitive function test by MoCA-J. be done. In addition, as shown in FIG. 27, in the test results of the cognitive function test by MMSE, the odor component group with the combination of two odors, "2" rag odor and "4" mint, has the highest AUC. It's becoming Therefore, it is understood that the odor component group of the combination of the two odor components of "2" rag odor and "4" mint is the combination of odor components having the strongest correlation with the test values of the cognitive function test by MMSE. be.

The mint odor component described above is an example of a first odor component predetermined as an odor component that makes the subject feel refreshed. Also, the odor of rags and the odor of socks are examples of the second odor components predetermined as the odor components that make the subject feel uncomfortable. A combination of mint and rag odor components and mint and socks odor components is an example of a component set of a first odor component and a second odor component.

In this way, the correlation/regression information derivation unit 125 uses the data of the subject (age, sex, smoking history), test results of odor components, and data of test results of cognitive function to obtain combinations of odor components (here, , mint and socks, mint and rag smell). In addition, subject data, odor components, and data showing correlations between odor components and cognitive function tests are derived.

Note that the logistic regression model described above is an example of a generalized linear model, and the present disclosure is not limited to using the logistic regression model as an analysis method, and other analysis models may be used. Moreover, the above-described derivation of the evaluation index is not limited to derivation of AUC by performing ROC analysis.

Next, in step S154, the registration unit 126 registers data indicating combinations of odor components (for example, mint and socks, and mint and rag odor) according to the type of cognitive function test in the correlation/regression information database 100B. do. Further, the registration unit 126 associates the data indicating the above-described correlation, that is, the constants A, B, C, and D in the above estimation formula with the combination of the type of cognitive function test and the odor component, to obtain correlation/regression information. Register in the database 100B.

Therefore, in the learning phase, the cognitive function estimation device 10 constructs the correlation/regression information database 100B as described above.

(estimation phase)
Next, the cognitive function estimation device 10B that functions as an estimation phase will be described. In this embodiment, to simplify the explanation, the cognitive function test will be described as an example of a dementia screening test conducted by licensed medical practitioners and applied to the estimation of MoCA-J described above.

FIG. 28 is a block diagram showing a functional configuration in an estimation phase in which cognitive function estimation processing is performed using the constructed correlation/regression information database 100B.
The cognitive function estimating device 10B has a function of estimating the subject's cognitive function as an estimation phase by executing an estimation processing program using the constructed correlation/regression information database 100B. That is, the estimation processing program has an olfactory data collection function, a subject data acquisition function, an odor selection function, a correlation/regression information extraction function, a cognitive function evaluation function, and a presentation function. In this estimation phase, the cognitive function estimating device 10B has a correlation between identification information including age, sex, and smoking history of the subject and the type of cognitive function test based on the correlation/regression information database 100B. An odor component is selected, and cognitive function is estimated from the olfactory data of the odor component.

As shown in FIG. 28, in the estimation phase, the CPU 11 of the cognitive function estimation device 10B includes an olfactory data collection unit 101, a data acquisition unit 122, an odor selection unit 124, and an extraction unit 127 that extracts data from the correlation/regression information database 100B. , the cognitive function evaluation unit 128 and the presentation unit 130 .

FIG. 29 is a flow chart showing the flow of estimation processing in the estimation phase of the cognitive function estimation device 10B. In the estimation phase, the CPU 11 of the cognitive function estimation device 10B executes the estimation processing program, thereby realizing the estimation processing shown in FIG. 29 .

In the cognitive function estimation device 10B, when the estimation process of the subject's cognitive function is started as the estimation phase, the estimation process program shown in FIG. 29 is executed. First, in step S240, the data acquisition unit 122 receives and acquires the subject's data input. Here, physical data indicating the subject's age and sex, and smoking data indicating the smoking history are acquired as the subject's data. The data obtained by the data obtaining unit 122 may be information input by the input unit 16 or information obtained by communication with another device via the communication unit 18 . The data acquired by the data acquisition unit 122 are passed to the odor selection unit 124 and the cognitive function evaluation unit 128 .

Next, in step S242, the odor selection unit 124 acquires data representing a combination of multiple odor components (odor component group) from the correlation/regression information database 100B. Specifically, the odor selection unit 124 requests the extraction unit 117 to extract data representing a combination of multiple odor components (odor component group) from the correlation/regression information database 100B. As a response to the request from the odor selecting unit 124, the extracting unit 127 delivers data indicating a combination of the plurality of registered odor components (a group of odor components). Here, the odor selection unit 124 acquires data representing an odor component group that is a combination of two types of odor components, mint and socks.

Next, in step S244, the odor selection unit 124 selects the plurality of odor components (the odor component group) acquired in step S242 as the plurality of odor components (the odor component group) used for the inspection. The odor selection unit 124 passes information indicating the selected odor components to the olfactory data collection unit 101 . Two types of odor components are selected here: mint and socks.

The olfactory data collection unit 101 emits the odor component to the subject according to the information indicating the odor component passed from the odor selection unit 124 in step S244, as in step S204 described above. Then, the olfactory data collection unit 101 collects data indicating the subject's olfactory ability for the released odor components.

Next, in step S246, similarly to step S206 described above, the olfactory data collection unit 101 selects a correct image according to the release conditions (type and concentration) of the odor component. Derive and record the olfactory score of the odor by the olfactory sense of The olfactory score derived by the olfactory data collection unit 101 is passed to the cognitive function evaluation unit 128 . The olfactory data collection unit 101 is an example of an ingredient release control unit.

The cognitive function evaluation unit 128 acquires data indicating the correlation between the olfactory score and the cognitive function test results in step S248. Specifically, the cognitive function evaluation unit 128 requests the extraction unit 127 for data indicating the estimation formula described above. In response to the request from the cognitive function evaluation unit 128, the extraction unit 127 delivers the estimation formula and data indicating the estimation formula. Then, the cognitive function evaluation unit 128 acquires the estimation formula registered in the correlation/regression information database 100B from the extraction unit 127 and the data indicating the constants of the estimation formula.

Next, the cognitive function evaluation unit 128 derives a cognitive function evaluation value (probability px) in step S250. First, the olfactory score for each odor component derived by the olfactory data collection unit 101 is totaled to derive a total score. Next, using the data indicating the subject's age, sex and smoking history, the total score, and the estimation formula, the cognitive function evaluation value for the subject, that is, the value of probability px is derived. The evaluation value derived by the cognitive function evaluation unit 128 is passed to the presentation unit 130 .

Then, in step S252, the presentation unit 130 presents information about cognitive function in the same manner as in step S212 described above. For example, the presentation unit 110 performs display control to display the value of the probability px, which is the evaluation value, on the display unit 17 as information related to the test of cognitive function. The data displayed on the display unit 17 indicates that there is no possibility of cognitive function deterioration when the probability px is equal to or less than a predetermined threshold, and that there is no possibility of cognitive function deterioration when the probability px exceeds the predetermined threshold. It is possible to have The data on the degree (magnitude) of the possibility that the cognitive function may be degraded may be such that the degree (magnitude) of the possibility that the cognitive function is degraded increases as the value of the probability px increases.

Therefore, in the estimation phase, the cognitive function estimation device 10B estimates the subject's cognitive function using the correlation/regression information database 100B as described above.

Note that when performing estimation processing according to the type of cognitive function test, the extraction unit 127 may acquire each data of a combination of odor components (a group of odor components) in association with the type of cognitive function test. Further, the olfactory data collection unit 101 derives an olfactory score for a combination of odor components (smell component group) for each type of cognitive function test, associates the olfactory score with the type of cognitive function test, and calculates the cognitive function evaluation unit 128. You can give it to In addition, the cognitive function evaluation unit 128 derives each evaluation value (probability px) using an estimation formula for each type of cognitive function test, that is, a constant, and calculates the evaluation value (probability px) for each cognitive function test. type, and passed to the presentation unit 130 .

As described above, according to the cognitive function device according to the present embodiment, data indicating the subject's age, sex, and smoking history, and the correlation between the olfactory score of the odor component and the results of the cognitive function test can be used to determine cognitive function. Select an odor component that correlates with the function test. Also, an estimation formula is derived as information indicating the correlation, and the estimation formula is registered in the correlation/regression information database. By using this estimation formula, it is possible to estimate the possibility of cognitive function deterioration based on the data indicating the subject's age, sex, and smoking history, and the sum of the olfactory scores (total score) of odor components related to cognitive function. It becomes possible to derive the evaluation value (probability) indicated.

[Other forms]
In the above, the technology of the present disclosure has been described in detail with respect to specific embodiments, but the technology of the present disclosure is not limited to such embodiments, and various other techniques can be used within the scope of the technology of the present disclosure. Embodiments are possible. For example, the configuration of the cognitive function estimation device described in the above embodiment is merely an example, and may be changed according to circumstances without departing from the gist of the invention.

Further, the flow of processing of the program described in the above embodiment is also an example, and unnecessary steps may be deleted, new steps added, or the processing order changed without departing from the scope of the invention. good too.

Further, in the above embodiment, the processing performed by executing the program stored in the storage unit has been described, but the processing of the program may be realized by hardware.

Moreover, in each of the above-described embodiments, a mode in which the program is stored (installed) in advance in a memory such as a ROM has been described, but the present invention is not limited to this. The program may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), and a USB memory. Also, the program may be downloaded from an external device via a network.

In the above embodiments, the processor refers to a processor in a broad sense, and includes a general-purpose processor (such as a CPU) and a dedicated processor (such as GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Arrays, programmable logic devices, etc.). Further, the operations of the processors in the above embodiments may be performed not only by one processor but also by cooperation of a plurality of physically separated processors. Also, the order of each operation of the processor is not limited to the order described in the above embodiments, and may be changed.

10 cognitive function estimation device 10X computer main body 11 CPU
12 RAMs
13 ROMs
14 Input/output interface 15 Bus 16 Input unit 17 Display unit 18 Communication unit 19 Storage unit 20 Odor component release device 100 Correlation/average information database 101 Olfactory data collection unit 102 Physical data acquisition unit 103 Cognitive function test result acquisition unit 104 Odor selection unit 105 correlation/average information derivation unit 106 registration unit 107 extraction unit 108 cognitive function evaluation unit 110 presentation unit

Claims (23)

an acquisition unit that acquires identification information including the age of the subject for identifying the subject whose cognitive function is to be estimated;
The correlation between the odor component and the cognitive function test, and the correlation between the odor component and the test value of the cognitive function test, with respect to identification information including age for identifying a subject who has undergone a predetermined cognitive function test. an odor component setting unit that sets an odor component having a correlation with the subject based on correlation information including information indicating a relationship;
Estimate the evaluation value of the cognitive function of the subject based on the test results of the odor component by the olfactory sense of the subject when the set odor component is emitted and the test value of the cognitive function test in the correlation information. an estimator that
Cognitive function estimation device with. The correlation information derives the type of the odor component and the correlation with the test value of the odor component for a plurality of subjects,
2. The cognitive function estimating device according to claim 1, further comprising: classifying by age with a predetermined age as a boundary, and deriving an average value of test results for odor components for each classified age as the test value for the odor component. further comprising a presentation unit that presents the cognitive function evaluation value for the subject estimated by the estimation unit;
The cognitive function estimation device according to claim 1, wherein the estimation unit presents recommendation information that recommends taking the cognitive function test when the evaluation value of the cognitive function exceeds a predetermined threshold. The identification information includes at least one of physical data including the subject's age and gender, smoking data including whether or not he or she has ever smoked, stay data indicating the location and length of stay, and education participation time data involved in education. Cognitive function estimation device according to claim 1. The gender of the physical data indicates one of two types of first gender and second gender,
The odor component setting unit sets odor components including vanilla, rag smell, yellow peach, and socks for the first gender, and sets odor components including caramel and socks for the second gender. The cognitive function estimating device according to claim 4. the computer,
an acquisition unit that acquires identification information including the age of the subject for identifying the subject whose cognitive function is to be estimated;
The correlation between the odor component and the cognitive function test, and the correlation between the odor component and the test value of the cognitive function test, with respect to identification information including age for identifying a subject who has undergone a predetermined cognitive function test. an odor component setting unit that sets an odor component having a correlation with the subject based on correlation information including information indicating a relationship; and
Estimate the evaluation value of the cognitive function of the subject based on the test results of the odor component by the olfactory sense of the subject when the set odor component is emitted and the test value of the cognitive function test in the correlation information. an estimator that
A program to function as an odorant component release unit that releases each of a plurality of odorant components to a subject while varying the concentration of each odorant component in a plurality of steps;
a score setting unit for setting a score corresponding to the correct concentration when the subject's answer indicating which odor component is the odor component released from the odor component releasing unit is correct;
an estimating unit for estimating a cognitive function evaluation value for the subject based on the total value of the scores set by the score setting unit for the plurality of odor components;
Cognitive function estimation device with. The cognitive function estimation device according to claim 7, wherein the odor components are odor components of vanilla, mint, yellow peach, and socks. The estimation unit uses constants a and b to
Cognitive function evaluation value = a × total score + b
The cognitive function estimating device according to claim 7, wherein an evaluation value of cognitive function based on a formula represented by is estimated as the cognitive function. The cognitive function estimation device according to claim 7, wherein the score is set to a higher value as the concentration of correct answers decreases. A test value of the cognitive function test obtained by performing a predetermined cognitive function test on a plurality of subjects is associated with the score of each of the odor components when each of the plurality of odor components is released to the plurality of subjects. an odor component setting unit configured to set, based on the correspondence relationship, an odor component group in which odor components having a correlation with the cognitive function test and having a smaller number of components than the number of components of the plurality of odor components are combined; prepared,
8. The cognitive function estimation device according to claim 7, wherein the odor component release unit releases the odor component group set by the odor component setting unit as the plurality of odor components. The odor component setting unit divides the total value of the plurality of odor components for the plurality of subjects into subjects whose test values in the cognitive function test exceed a predetermined test value and subjects whose test values are less than or equal to a predetermined test value. 12. The cognitive function estimating device according to claim 11, wherein a plurality of odor components in which the information on the discriminant power evaluation value obtained by analyzing the distribution of the odor components exceeds a predetermined correlation value is set as the odor component group. The estimating unit determines the sum of the scores of the odor components for a plurality of subjects, and the test value of the cognitive function test obtained by performing a predetermined cognitive function test on a plurality of subjects, and the subject and the predetermined test. The cognitive function estimating device according to claim 7, which estimates the cognitive function evaluation value for the subject based on the correlation of the ratio with the subjects below the value. further comprising a presentation unit that presents the cognitive function evaluation value for the subject estimated by the estimation unit;
The cognitive function estimation device according to claim 7, wherein the estimation unit presents recommendation information that recommends taking a cognitive function test when the evaluation value of the cognitive function exceeds a predetermined threshold. A program for causing a computer to execute processing for estimating the cognitive function of a subject,
said computer,
The response from the subject indicating which odor component is the odor component released from the odor component releasing unit that releases each of a plurality of odor components to the subject while changing the concentration of each odor component in a plurality of steps. a score setting unit that sets a score corresponding to the concentration indicating the correct answer when the answer is correct;
A program for functioning as an estimation unit for estimating a cognitive function evaluation value for the subject based on the total value of the plurality of odor components of the scores set by the score setting unit. an acquisition unit that acquires identification information including physical data indicating the age and sex of the subject for identifying the subject whose cognitive function is to be estimated, and smoking data indicating whether or not the subject has ever smoked;
an odorant component release unit that releases each of a plurality of odorant components to a subject while varying the concentration of each odorant component in a plurality of steps;
a score setting unit for setting a score corresponding to the correct concentration when the subject's answer indicating which odor component is the odor component released from the odor component releasing unit is correct;
An estimation unit for estimating a cognitive function evaluation value for the subject based on the identification information acquired by the acquisition unit and the total value of the plurality of odor components of the scores set by the score setting unit. When,
Cognitive function estimation device with. The estimation unit
For a plurality of subjects, the cognitive function evaluation value for the subject is estimated based on the correlation between the identification information, the type of the odor component, the test value of the odor component, and the test value of the cognitive function test. The cognitive function estimation device according to claim 16. The estimation unit
Let A, B, C, and D be constants,
Let pa be (A × total score),
Let pb be (B x age),
Let pc be (C x gender),
When pd is (D × smoking history),
p=1/[1+exp{−(pa+pb+pc+pd)}]
The cognitive function estimation device according to claim 17, wherein the evaluation value of the cognitive function is derived using the estimation formula represented by. A test value of the cognitive function test obtained by performing a predetermined cognitive function test on a plurality of subjects is associated with the score of each of the odor components when each of the plurality of odor components is released to the plurality of subjects. an odor component setting unit configured to set, based on the correspondence relationship, an odor component group in which odor components having a correlation with the cognitive function test and having a smaller number of components than the number of components of the plurality of odor components are combined; prepared,
17. The cognitive function estimation device according to claim 16, wherein the odor component release unit releases the odor component group set by the odor component setting unit as the plurality of odor components. The odor component setting unit divides the total value of the plurality of odor components for the plurality of subjects into subjects whose test values in the cognitive function test exceed a predetermined test value and subjects whose test values are less than or equal to a predetermined test value. 20. The cognitive function estimating device according to claim 19, wherein a plurality of odor components of which the information on the discrimination power evaluation value obtained by analyzing the distribution of the odor components exceeds a predetermined correlation value is set as the odor component group. The odor components emitted from the odor component emitting part are a first odor component that is predetermined as an odor component that makes the subject feel refreshed, and a second odor that is predetermined as an odor component that makes the subject feel uncomfortable. 17. The cognitive function estimation device according to claim 16, comprising at least a set of components. 22. The cognitive function estimation device according to claim 21, wherein the first odor component is mint, and the second odor component is an odor component representing a rag odor or an odor component representing a sock odor. the computer,
an acquisition unit that acquires identification information including physical data indicating the age and sex of the subject for identifying the subject whose cognitive function is to be estimated, and smoking data indicating whether or not the subject has ever smoked;
a component release control unit that controls an odor component release unit that releases each of a plurality of odor components to a subject while changing the concentration of each odor component in a plurality of stages;
a score setting unit for setting a score corresponding to the correct concentration when the subject's answer indicating which odor component is the odor component released from the odor component releasing unit is correct;
An estimation unit for estimating a cognitive function evaluation value for the subject based on the identification information acquired by the acquisition unit and the total value of the plurality of odor components of the scores set by the score setting unit. ,
A program to function as

Images