JP7573256B2 - Dementia risk indication system and method - Google Patents

Description

The present invention relates to a system and method for presenting a user's dementia risk.

Patent Document 1 describes a dementia risk assessment system that can assess the potential risk of dementia at an extremely early stage and provide a preventive opportunity to delay the onset of dementia. This system includes a biometric data detection sensor that acquires biometric data of a subject while sleeping, a sleep data generation device that generates sleep data including the depth of sleep and changes in body movement of the subject over time from the biometric data of the subject acquired by the biometric data detection sensor, and a dementia risk assessment device that has a memory unit that stores symptom-specific sleep data obtained from actual patients with a specified dementia symptom, and compares the subject's sleep data generated by the sleep data generation device with the sleep data of each symptom stored in the memory unit to assess the risk of three dementias from the subject's sleep data.

JP 2016-22310 A

It has been known that dementia can be slowed down in the early stages of onset (including not only when the disease has actually developed but also when it is suspected) by taking appropriate measures such as adjusting lifestyle habits such as the amount of exercise and alcohol consumed, and by administering appropriate treatment. As a result, there is a demand for early detection of the possibility of developing dementia or the degree of progression after onset. Accordingly, various systems have been proposed for detecting the risk of developing and progressing dementia (hereinafter simply referred to as "dementia risk").

The above-mentioned system for assessing dementia risk from hypnosis data infers the user's brain function from their sleep state, and recognizes the dementia risk based on the inference results. As a result, the accuracy of the dementia risk is also affected by the accuracy of the inference, making it difficult to properly recognize the dementia risk. Simply presenting the presence or absence of dementia risk poses the problem that it is difficult for those who do not have sufficient knowledge to properly understand the content of that dementia risk. For this reason, there is a demand for a system and method that can accurately recognize dementia risk and also present it in an easy-to-understand form.

One aspect of the present invention is a system having a first database in which sample brain health data including at least one of sample brain state data, which is data related to the brain state of a sample subject, and sample cognitive ability data, which is data related to cognitive ability, which is a brain function, is associated with individual characteristics including at least one of the age, sex, and physical information of the sample subject; a first recognition unit that recognizes user brain health data including at least one of user brain state data, which is data related to the user's brain state, and user cognitive ability data, which is data related to cognitive ability, which is a brain function; a second recognition unit that recognizes user individual characteristics, which are the individual characteristics of the user; and a risk presentation unit that presents an aging transition line showing the transition of the user's brain health data from the past to the present based on the past and current user brain health data, and a risk line for dementia determined by referring to the transition of the sample brain health data according to age, based on the sample brain health data associated with the individual characteristics corresponding to the user individual characteristics.

In this system, the user brain health data (data on brain health state) including at least one of data on the brain state of the user to be risk-judged (user brain state data) and user cognitive ability data, which is data on cognitive ability, which is brain function, is compared with data on the similar brain health state of a sample subject (sample brain health data) to recognize the dementia risk. The data on the brain state is direct data in the form of quantitative parameters based on the brain state that affects cognition, and is not indirect data in the form of brain function inferred from the user's brain waves, movements, etc., but is direct data in the form of data on the brain state. The cognitive ability test that obtains the cognitive ability data is enriched in terms of content as a criterion for judging dementia risk, and the state of brain function can be accurately judged. An example of the cognitive ability test is described in Patent Application No. 2018-33652, which has been filed by the applicant of the present application. Therefore, the dementia risk can be accurately recognized by comparing the user brain health data including either or both of these with the sample brain health data.

Furthermore, by presenting the dementia risk in a format that compares the risk line with an aging progression line, which is a line according to age, the user, etc. can simultaneously grasp not only the magnitude of the user's dementia risk, but also the trend of the user's dementia risk (whether it is worsening, improving, whether the deterioration is being prevented, etc.). Therefore, the user or a person who manages the user's health (hereinafter collectively referred to as "user, etc.") can intuitively grasp the magnitude of dementia risk from the information presented by this system, even if they do not have sufficient knowledge.

The risk presentation unit may include a first score presentation unit that presents a score indicating the user's dementia risk or a symbol corresponding to the score based on the result of a comparison between the user's brain health data and sample brain health data associated with individual characteristics corresponding to the user's individual characteristics. By presenting the dementia risk as a score or a symbol corresponding to the score (hereinafter referred to as "score, etc."), the user, etc. can more intuitively grasp the level of the user's dementia risk.

This system has a prediction unit that predicts an aging prediction line indicating the predicted transition of the user's brain health data from the present to the future based on the aging transition line, and the risk presentation unit may include a prediction presentation unit that presents the aging prediction line in addition to the aging transition line and the risk line. By presenting the aging prediction line, which is a prediction of the transition of dementia risk from the present to the future, in a manner comparable to the risk line, the user, etc. can more accurately grasp the tendency of the user's dementia risk.

The risk presentation unit may include a second score presentation unit that presents, together with or instead of the aging prediction line, a score indicating the user's future dementia risk or a symbol corresponding to the score based on a result of a comparison between the user brain health data for the first age on the aging prediction line and sample brain health data associated with individual characteristics corresponding to the individual characteristics obtained by adding the first age to the user's individual characteristics. The risk presentation unit may predict or forecast the user's future user brain health data for the first age separately from the aging prediction line, and present a score indicating the user's future dementia risk or a symbol corresponding to the score based on a result of a comparison between the predicted user brain health data and sample brain health data associated with individual characteristics corresponding to the individual characteristics obtained by adding the first age to the user's individual characteristics.

In the first database, the sample brain health data may be associated with individual characteristics and life characteristics including at least one of the lifestyle habits and living environment of the sample subject. The system may further have a third recognition unit that recognizes user life characteristics, which are the life characteristics of the user, and the prediction unit may predict the aging prediction line based on the sample brain health data and the aging transition line associated with the individual characteristics corresponding to the user individual characteristics, the life characteristics corresponding to the user life characteristics, and age. When recognizing the aging prediction line, by referring to the user life characteristics, a highly reliable aging prediction line (and thus a tendency toward dementia risk) can be recognized. This allows the user, etc., to more accurately grasp the tendency toward the user's dementia risk.

The risk presentation unit may include a third score presentation unit that presents, together with or instead of the aging prediction line, a score indicating the user's future dementia risk or a symbol corresponding to the score based on a result of a comparison between the user brain health data for the first age on the aging prediction line, an individual characteristic corresponding to the individual characteristic obtained by adding the first age to the user individual characteristic, and sample brain health data associated with the life characteristic corresponding to the user life characteristic. The risk presentation unit may predict user brain health data corresponding to a user life characteristic specified or arbitrarily selected by the user separately from the aging prediction line, and present a score indicating the user's future dementia risk or a symbol corresponding to the score based on a result of a comparison between the predicted user brain health data and sample brain health data associated with the life characteristic corresponding to the user life characteristic.

The prediction unit may include a comparison prediction unit that recognizes, for the same user, a first aging prediction line based on a first user lifestyle characteristic and a second aging prediction line based on a second user lifestyle characteristic, and the risk presentation unit may include a comparison presentation unit that presents the first aging prediction line and the second aging prediction line side-by-side or consecutively so as to be comparable. The user, etc., can intuitively grasp the fluctuation of the aging prediction line (and thus the dementia risk) according to the fluctuation of the lifestyle characteristic. This allows the user, etc., to grasp the specific lifestyle characteristics that should be improved, and thus provides an incentive for improving the lifestyle characteristics.

The risk presentation unit may include a fourth score presentation unit that presents a first score indicating the user's future dementia risk corresponding to the first aging prediction line and a second score indicating the user's future dementia risk corresponding to the second aging prediction line. Each score is calculated based on a result of a comparison between the user brain health data for the first age on each aging prediction line and an individual characteristic corresponding to the individual characteristic obtained by adding the first age to the user individual characteristic, and sample brain health data associated with the life characteristic corresponding to each user life characteristic. The risk presentation unit may predict the user's future dementia risk based on each user life characteristic separately from the aging prediction line, and present a first score and a second score indicating the risk.

The sample brain state data and the user brain state data may include data indicative of the total brain volume or the volume of at least one predetermined region of the brain, and may include brain images, cerebral blood flow, electroencephalograms, or other information that directly or indirectly indicates the state of the brain, such as blood biomarkers.

Another aspect of the present invention is a method for indicating a risk of dementia, using a system capable of referencing a first database in which sample brain health data including at least one of sample brain state data, which is data related to a brain state of a sample subject, and sample cognitive data, which is data related to cognition, which is a brain function, of the sample subject is associated with individual characteristics including at least one of age, sex, and physical information of the sample subject, and the method includes the following steps:
1. Recognizing user brain health data including at least one of user brain state data, which is data related to the state of the user's brain, and user cognitive ability data, which is data related to cognitive ability, which is a function of the brain.
2. Recognizing user individual characteristics, which are individual characteristics of a user.
3. Presenting risk using an aging transition line showing the transition of the user's brain health data from the past to the present based on the user's past and present brain health data, and a dementia risk line determined by referring to the transition of the sample brain health data according to age based on sample brain health data associated with individual characteristics corresponding to the user's individual characteristics.

The method may further include presenting a score indicative of the user's dementia risk, or a symbol corresponding to the score, based on a comparison of the user's brain health data with the sample brain health data associated with an individual characteristic corresponding to the user's individual characteristic.

The method may further include predicting an aging prediction line indicating a predicted transition of the user's brain health data from the present to the future based on the aging progression line, and presenting the risk may include presenting the aging prediction line in addition to the aging progression line and the risk line. The method may also include presenting a score indicating the user's future dementia risk, or a symbol corresponding to the score, together with or instead of the aging prediction line, based on a result of a comparison between the user's brain health data for the first age on the aging prediction line and sample brain health data associated with individual characteristics corresponding to the user's individual characteristics plus the first age.

In the first database, the sample brain health data may be associated with individual characteristics and life characteristics including at least one of lifestyle habits and living environment of the sample subject. The method may further include recognizing a user life characteristic that is a life characteristic of the user, and predicting may include predicting an aging prediction line based on the sample brain health data and the aging transition line associated with the individual characteristics corresponding to the user individual characteristics, the life characteristics corresponding to the user life characteristics, and age.

This method may further include presenting, together with or instead of the aging prediction line, a score indicating the user's future dementia risk or a symbol corresponding to the score based on a result of a comparison between the user's brain health data for the first age on the aging prediction line and individual characteristics corresponding to the individual characteristics obtained by adding the first age to the user's individual characteristics, and sample brain health data associated with the life characteristics corresponding to the user's life characteristics. This method may also predict user brain health data for a first age specified or arbitrarily selected by the user, separately from the aging prediction line, and present a score indicating the user's future dementia risk or a symbol corresponding to the score based on a result of a comparison between the user's brain health data and individual characteristics corresponding to the individual characteristics obtained by adding the first age to the user's individual characteristics, and sample brain health data associated with the life characteristics corresponding to the user's life characteristics.

The predicting may include predicting, for the same user, a first aging prediction line based on a first user lifestyle characteristic and a second aging prediction line based on a second user lifestyle characteristic, and the presenting the risk may include presenting the first aging prediction line and the second aging prediction line side-by-side or consecutively for comparison. The method may include presenting a score for the first age on the first aging prediction line and a score for the first age on the second aging prediction line. The method may present multiple scores for dementia risk, either specified by the user or predicted based on any user lifestyle characteristic.

Another aspect of the present invention is a program (program product) having instructions for operating a computer as the above-mentioned system. The program (program product) may be provided in a form recorded on any recording medium.

FIG. 1 is a diagram showing a schematic configuration of a dementia risk presentation system. FIG. 13 is a diagram showing an example of a report provided by the presentation system. This is a graph plotting brain condition data to be referenced when presenting dementia risk as a change over time, with the vertical axis representing hippocampal volume and the horizontal axis representing age. Similar to FIG. 3, this is a graph plotting brain condition data, with the 95% CI range also shown. An example of output including aged projection lines with estimated bands. 6A and 6B are examples showing changes in the display content of a report when lifestyle characteristics are changed, with FIG. 6A showing a case where drinking is done every day, and FIG. 6B showing a case where drinking is done 2-3 days a week. 7A and 7B are other examples showing changes in the display content of the report when lifestyle characteristics are changed, with FIG. 7A showing a case where drinking is done every day, and FIG. 7B showing a case where drinking is done 2-3 days a week. FIG. 11 is a diagram showing another example of a report provided by the presentation system. A diagram showing examples of tests to measure brain health. Continuing from FIG. 9, a diagram showing examples of tests or examinations to measure brain health. 1 is a flowchart showing an overview of the operation of the presentation system.

1 shows an example of a system including a device (system) that presents dementia risk. This system 1 includes a hospital 3 including an MRI (Magnetic Resonance Imaging) device (MRI) 3a, an information terminal (personal computer, tablet terminal) 2 that inputs various information about the user and outputs (displays) a report 50 about dementia risk, and an information providing device (dementia risk presentation device, dementia risk presentation system, presentation system) 10 that processes information received from the MRI 3a and the tablet 2 via the Internet 9 and transmits a report 50 including dementia risk and other information. In this example, the presentation system 10 includes computer resources such as memory and a CPU, and is implemented in a server 7 that can input and output information via the Internet (cloud) 9, but the presentation system 10 may be integrated with the user's information terminal 2, may be connected by wire or wirelessly, may be installed inside the hospital 3, and some or all of the functions of the presentation system 10 may be distributed and implemented in multiple information processing devices including the user terminal 2.

MRI 3a acquires data related to the user's brain state (user brain state data) and transmits the user brain state data 41 to the presentation system 10. The device that acquires the user brain state data 41 is not limited to MRI 3a, but may be any device that has a configuration that can recognize the user brain state data of the user who is the subject of dementia risk judgment. For example, it may be a CT (Computed Tomography) examination device, an ultrasound examination device, or a device that measures brain function (cerebral blood flow) such as FDG or SPECT, or a device that measures brain waves, blood biomarkers, etc., and information that can be measured by these may be included in the data related to the brain state. In addition, when using the amount of a certain protein in the brain instead of the shape or volume of the brain as data related to the brain state, a PET (Positron Emission Tomography) image acquisition device or the like may be used. The presentation system 10 may use the brain state data 41 obtained from MRI 3a, or may use brain state data 41 obtained in advance and stored in the user library 18.

In the following, an example will be described in which the value of the hippocampal volume (hippocampal volume) is used as the brain state data 41, but the brain state data 41 is not limited to this. Here, the "brain state" refers to the overall state of the brain, or the state of a brain region that affects cognition (e.g., the hippocampus, supramarginal gyrus, angular gyrus, superior frontal gyrus, middle frontal gyrus, inferior frontal gyrus, anterior cingulate cortex, etc.). The "state" includes the volume and shape of the entire brain or a specific region of the brain, as well as the amount of a specific protein in the brain (e.g., amyloid beta, etc.). The brain state data (data related to the brain state, data related to the brain state) 41 includes quantitative parameters based on the brain state, and includes, for example, the above-mentioned brain state itself (i.e., the shape of the entire brain or a specific region), or a numerical value of the brain volume or size. The brain state data 41 may relate to a single brain state, or may relate to multiple brain states. Specifically, for example, the brain state data 41 may include the volume of the hippocampus, or may include a value obtained by a predetermined formula based on the volume of the hippocampus and the volume of amyloid beta in the brain.

The tablet 2, which inputs information about the user to the presentation system 10 and receives a report 50 including information about the user's dementia risk from the presentation system 10, is equipped with a touch panel 2a (input/output unit). Via the touch panel 2a, the user's individual characteristics 43 are input in response to an inquiry 42 about individual characteristics from the presentation system 10, and the user's lifestyle characteristics 45 are input and changed in response to an inquiry 44 about lifestyle characteristics. Cognitive ability test questions 60 are also presented on the touch panel 2a, and cognitive ability data 61 including answers to the cognitive ability test are input to the presentation system 10. Furthermore, the report 50 including a presentation of dementia risk is displayed on the touch panel 2a.

The user terminal used for inputting and outputting this information is not limited to a tablet 2 having a touch panel 2a. The user terminal only needs to be capable of recognizing the individual characteristics of the user who is the subject of dementia risk assessment and presenting the dementia risk. For example, a personal computer, smartphone, etc. may be used instead of a tablet. Also, instead of a touch panel which is an input/output unit that integrates an output unit and an input unit, independent output unit and input unit may be used. Specifically, a keyboard, microphone, etc. may be used as the input unit, and a display, speaker, printing device, etc. may be used as the output unit.

In addition, the input and output units of the user terminal do not necessarily have to be provided in the same device, and do not have to be located close to each other, such as in a room. For example, a display, speaker, printing device, etc., serving as the output unit of the user terminal, may be located in a medical workstation provided in a location different from the location where the MRI device, etc. is installed.

The server 7 operating as the presentation system 10 includes a memory (data storage section, data storage area) 16, and a processor (CPU) 8 that operates as various functions (functional units, functional sections) by loading a program (program product) 19 stored in the memory 16. The memory 16 includes a database (first database) 17 including sample brain health data 17a including at least one of sample brain state data 17d, which is data relating to the brain state of a sample subject, and sample cognitive ability data 17e, which is data relating to cognitive ability, which is a brain function, and a user library 18 in which user brain health data (user brain health data) 18a is stored.

The database 17 further includes individual characteristics 17b including at least one of the sample subject's age, sex, and physical information, and the sample brain health data 17a is stored in association with the individual characteristics 17b. The database 17 further includes lifestyle characteristics 17c including at least one of the sample subject's lifestyle habits and living environment, and the sample brain health data 17a is stored in association with the lifestyle characteristics 17c.

Here, "sample subjects" include not only those who have dementia (including mild dementia) or are suspected of having dementia, but also healthy individuals who do not have dementia. Individual characteristics 17b include at least one of age, sex, and physical information. Furthermore, the "physical information" included in individual characteristics 17b refers to physical information that can be quantitatively expressed. Specific examples include height, weight, body fat percentage, BMI, cholesterol level, etc.

Lifestyle characteristics 17c include at least one of lifestyle habits and living environment. "Lifestyle habits" refers to habits in daily life that affect the increase or decrease of dementia risk. Specific examples include the amount of exercise, amount and type of food, length and quality of sleep, amount and frequency of communication, amount and frequency of hobby activities, amount and frequency of alcohol consumption, amount and frequency of smoking, etc. "Living environment" refers to the environment in daily life that affects the increase or decrease of dementia risk. Specific examples include address (living environment), occupation, educational background, annual income, number of cohabitants, etc.

In the database 17, sample brain health data 17a including data on the brain state of the sample subject (sample brain state data) 17d and data on the result of the cognitive ability test of the sample subject (sample cognitive ability data) 17e is stored in a format associated with the individual characteristics 17b and life characteristics 17c of the sample subject. In addition to the latest (current) user brain health data 18a including data on the user's brain state (user brain state data) 41 and data on the user's cognitive ability (user cognitive ability data) 61, data acquired in the past is stored. The user library 18 may store the individual characteristics (user individual characteristics) 43 and life characteristics (user life characteristics) 45 of each user. The presentation system 10 compares the data on the brain health state of the user to be risk-judged (user brain health data) 18a with the data on the brain state of the sample subject (sample brain state data) 17a to recognize the dementia risk.

Here, the brain state data 17a and 41 are direct data in the form of quantitative parameters based on the brain state that affect cognition. In other words, this dementia risk presentation system 10 uses direct data in the form of data related to the brain state, rather than indirect data in the form of brain function inferred from the user's brain waves, movements, etc., as in conventional systems. As a result, this presentation system 10 is not affected by the accuracy of inferring brain function when recognizing dementia risk. As a result, this presentation system 10 can recognize dementia risk with greater accuracy than conventional systems.

The presentation system 10 has a first recognition unit 11 that acquires (recognizes) user brain health data 18a including at least one of user brain state data 41, which is data related to the state of the user's brain, and user cognitive ability data 61, which is data related to cognitive ability, which is a function of the brain. The first recognition unit 11 includes an input unit (input function, input unit) 14 that acquires the user brain state data 41, and an input unit (input function, input unit) 15 that acquires the user cognitive ability data 61. The cognitive ability data input unit 15 sends a cognitive ability test 60 to the user's terminal 2 and recognizes the user cognitive ability data 61 from the answer. The cognitive ability data input unit 15 is not limited to direct information input from the terminal 2, and may indirectly acquire information about the user by input via paper media or by providing information via a doctor or other expert. The same applies to the recognition (acquisition, input) of other information.

An example of the cognitive test 60 is one that evaluates the function of each of the five cognitive domains. The cognitive domains include short-term memory, working memory, executive function, spatial cognition, and calculation. Short-term memory indicates the ability to retain and recall memorized content for a short period of time, and is said to involve the hippocampus of the brain. Working memory is the ability to manipulate retained memories in different ways, such as "remembering a phone number and pressing the button for that number to make a call," and is said to involve the prefrontal cortex and temporoparietal regions of the brain. Executive function is the ability to maintain and update rules, such as the "procedure" for cooking and "changing ingredients according to the situation," and to control behavior and thinking, and is said to involve the prefrontal cortex of the brain in particular. Spatial cognition is the ability to instantly grasp and understand which direction a shape or object is facing in space, and is said to involve the parietal lobe of the brain. Calculation is the ability to perform arithmetic operations, and involves various areas of the brain, but is said to involve the temporoparietal region of the brain in particular.

The cognitive ability data input unit 15 performs a cognitive ability test 60 and obtains an evaluation for each of these cognitive ability domains as user cognitive ability data 61. The cognitive ability data 61 can be used as an index for accurately assessing brain function by performing statistical processing of the evaluation for each cognitive ability domain as described below.

The presentation system 10 further includes a second recognition unit (individual characteristic input unit, second input unit) 12 that recognizes (acquires) user individual characteristics 43, which are the individual characteristics of the user, and a third recognition unit (lifestyle characteristic input unit, third input unit) 13 that recognizes (acquires) user lifestyle characteristics 45, which are the lifestyle characteristics of the user. The individual characteristic input unit 12 may send a questionnaire (questionnaire) 42 related to the individual characteristics to the user terminal 2 and recognize the individual characteristics 43 of each user from the answers thereto. In cases where an electronic medical record or the like for the user has been created in advance, the individual characteristic input unit 12 may recognize the user individual characteristics 43 based on the description of the electronic medical record or the like.

The lifestyle characteristic input unit 13 may send a questionnaire (questionnaire) 44 relating to lifestyle characteristics to the user terminal 2 and recognize each user's lifestyle characteristics 45 from the answers to the questionnaire. In cases where an electronic medical record or the like has been created in advance for the user, the lifestyle characteristic input unit 13 may recognize the user lifestyle characteristics 45 based on the description of the electronic medical record or the like.

The presentation system 10 further includes a recognition/prediction unit (prediction unit, prediction function, prediction unit) 20 that recognizes each user's current risk of dementia and predicts future risk, and a risk presentation unit (risk presentation function, risk presentation unit) 30 that presents information including the risk of dementia to the user. The recognition/prediction unit 20 includes a current risk recognition unit 21 that recognizes the current risk, a prediction unit 22 that predicts future risk, and a score calculation unit 23 that converts the risk into a score.

The current risk recognition unit 21 recognizes a dementia risk line determined by referring to an age-related progression line showing the progression of the user's brain health data 18a from the past to the present based on the past and present user brain health data 18a, and a progression of the sample brain health data 17a according to age based on the sample brain health data 17a associated with individual characteristics 17b corresponding to the user individual characteristics 43, and outputs the risk line to the user terminal 2 via the risk presentation unit 30.

The current risk recognition unit 21 acquires sample brain state data 17d and sample cognitive ability data 17e associated with individual characteristic 17b corresponding to user individual characteristic 43 from the database 17. Then, the sample brain state data 17d is compared with the user brain state data 41, and the sample cognitive ability data 17e is compared with the user cognitive ability data 61. Then, based on the results of these comparisons, the user's dementia risk may be recognized. As described above, the sample brain state data 17d and the user brain state data 41 are not limited to the hippocampus, and may be the entire brain volume or the volume of at least one specified area of the brain.

The prediction unit 22 predicts an aging prediction line indicating the predicted transition of the user's brain health data from the present to the future based on the aging transition line, and is able to present the aging prediction line in addition to the aging transition line and risk line via the risk presentation unit 30. The score calculation unit 23 determines a score indicating the user's dementia risk or a symbol corresponding to the score based on the result of comparing the current or future predicted user brain health data 18a with the sample brain health data 17a associated with the individual characteristic 17b corresponding to the user individual characteristic 43, and is able to present this via the risk presentation unit 30.

The risk presentation unit 30 includes a chart display unit 31 that displays the aging transition line, aging prediction line, risk line, etc. in a chart or graphic format, and a score presentation unit 32 that displays the obtained score. The chart display unit 31 includes a prediction presentation unit 31a that displays a prediction including the aging prediction line, and a comparison presentation unit 31b that displays the results of simulating multiple cases in which lifestyle characteristics are changed. The score presentation unit 32 includes a first score presentation unit 32a that displays the current risk score (including corresponding symbols, etc.), a second score presentation unit 32b that displays the predicted risk score, etc., a third score presentation unit 32c that displays the predicted risk score including lifestyle characteristics, etc., and a fourth score presentation unit 32d that displays the risk score, etc., of a case in which lifestyle characteristics are changed.

Figure 2 shows an example of a report 50 provided to the user by the presentation system 10. This report 50 may be a screen or digital data presented on the user terminal 2 when a dementia risk assessment is made, or it may be an audio file, or it may be a printed matter, booklet, etc. provided to the user by mail, with or without passing through the user terminal 2. The report 50 includes a brain image display area 59, an age-related change display area 51, a score display area 57, and a lifestyle characteristic display area 58, and information related to dementia risk or the user's lifestyle characteristics is presented in each area.

Specifically, the brain image display area 59 displays an image of the user's brain contained in the user brain state data 41 acquired by MRI 3a. The aging progression display area 51 displays a graph (chart) via the presentation unit 30 as the dementia risk recognized by the risk recognition and prediction unit 20. This graph shows the results of a comparison between the sample brain state data and the user brain state data. This graph includes an aging progression line 52, an aging prediction line 53, and a risk line 54.

In the score display area 57, a rank 55 related to the overall risk assessment indicated by the letters A to D and F, a brain age 56a indicated by a number, and an arrow 56b which is a symbol related to a long-term prediction are displayed as the dementia risk recognized by the risk recognition and prediction unit 20. In addition, a legend 56c related to the rank 55 is displayed in the score display area 57. The value of this rank 55, the value of the brain age 56a, and the inclination of the arrow 56b are determined according to the score obtained based on the result of the comparison between the sample brain state data 17d and the user brain state data 41, and the result of the comparison between the sample cognitive ability data 17e and the user cognitive ability data 61. Rank A indicates high brain function, rank B indicates normal brain function, rank C indicates that brain function is declining, and rank D indicates that attention should be paid to the decline in brain function. Rank F indicates that treatment has already been started due to the decline in brain function.

The user's lifestyle characteristics 45 are displayed in the lifestyle characteristics display area 58. Changes made to the user's lifestyle characteristics 45 via the touch panel 2a are reflected in the user's lifestyle characteristics 45.

Note that the method of presenting dementia risk in such a display format is merely one example. In other words, the method of presenting dementia risk using the presentation system 10 is not limited to this configuration, and any method may be used as long as it presents the results of a comparison between the user's brain health data 18a and the sample brain health data 17a associated with the user's individual characteristics and/or lifestyle characteristics. For example, the layout of the screen (report) 50 may be changed as appropriate. Also, only a graph or only display related to the score may be performed. Also, among the display related to the score, only one or two of the rank, brain age, and arrow may be displayed. It may be presented in a completely different format from the above display, for example, an image of the user's brain and an image of the brain of a sample subject who has the same individual characteristics as the user and is in an ideal health condition may be displayed side by side. Also, the results may be presented by audio.

The display contents in the aging progression display area 51 will be further explained. In this report 50, the aging progression display area 51 displays a graph showing dementia risk with hippocampal volume on the vertical axis and age on the horizontal axis. This graph includes an aging progression line 52, an aging prediction line 53, and a risk line 54. The aging progression line 52 shows the progression of the user's brain state data 41 from the past to the present. The aging prediction line 53 shows the predicted progression of the user's brain state data 41 from the present to the future. The risk line 54 indicates the degree of dementia risk that the user, etc. should be wary of, and divides the area in the graph into a reference range 54a and a caution zone 54b.

The user etc. can understand the level of the user's dementia risk and the tendency of the dementia risk by comparing the slope of the aging progression line 52 and the slope of the aging prediction line 53 with the slope of the risk line 54, and by referring to the position of the aging progression line 52 and the position of the aging prediction line 53 (specifically, whether they are within the reference range 54a or within the caution zone 54b).

When creating the aging transition line 52 and the aging prediction line 53, the user brain state recognition unit 14 first recognizes the user's current and past brain state data 41. Specifically, the user brain state recognition unit 14 uses a predetermined algorithm to calculate the hippocampal volume from cross-sectional images of the user's brain acquired using MRI 3a in the past (in this embodiment, when the user was 41 years old) and the present (at the time of dementia risk assessment (in this embodiment, when the user was 45 years old)). As the predetermined algorithm, a technology that predicts the hippocampal volume using a generation model of images over time using a neural network may be used. To further improve accuracy, biomarker data information that is highly correlated with lifestyle findings may be added.

The current risk recognition unit 21 of the risk recognition and prediction unit 20 recognizes the aging progression line 52 of the user's brain state based on the user's brain state 41 recognized by the user's brain state recognition unit 14.

Specifically, as shown in FIG. 3, the current risk recognition unit 21 first plots the user's past (age 41) hippocampal volume and the user's present (age 45) hippocampal volume on a graph with the vertical axis representing hippocampal volume and the horizontal axis representing age. The risk recognition unit 21 then generates an aging progression line 52 by connecting these with a line segment. Based on the user individual characteristics 43, the risk recognition unit 21 acquires sample brain state data 17d associated with individual characteristics 17b corresponding to the user individual characteristics 43 from the database 17.

An example of a user has an individual characteristic 43 of being male. The risk recognition unit 21 acquires sample brain state data (i.e., hippocampal volume) 17d associated with the individual characteristic 17b of being male. Next, the risk recognition unit 21 determines a risk line 54 by referring to the age-dependent progression of the sample brain state data 17d recognized based on the individual characteristic.

In FIG. 3, the vertical axis is hippocampal volume and the horizontal axis is age, and sample brain state data 17d extracted from individual characteristics 17b is plotted. The black and white circles in FIG. 3 represent each sample brain state data 17d, the white circles represent sample brain state data 17d belonging to the heavy drinker group, and the black circles represent other sample brain state data 17d. In the figure, a first average line 66 indicating the average hippocampal volume of the extracted sample brain state data 17d including the heavy drinker group is shown by a solid line, and a second average line 67 indicating the average hippocampal volume of the sample brain state data 17d only for the heavy drinker group is shown by a dashed line. Such statistical processing may be performed in advance or may be performed by the risk recognition unit 21.

The risk recognition unit 21 generates a risk line 54 shown by a dotted line below the first average line 66. Specifically, it generates a line (a line showing the bottom 2.3%) based on a value (x1-2σ) that is 2σ ("σ" represents the standard deviation of hippocampal volume (sample brain state data) by age) lower than each value x1 of the first average line 66, and recognizes that line as the risk line 54.

The method of recognizing the risk line 54 of the present invention is not limited to such a method, and may be any method that determines the risk line 54 by referring to the age-dependent progression of the sample brain state data 17d associated with the individual characteristic corresponding to the user's individual characteristic. For example, in the case where the user's individual characteristic is male as in this embodiment, the risk line 54 may be determined based on the average line of the sample brain state data 17d associated with the user's life characteristic 45 and the corresponding life characteristic 17c among the sample brain state data 17d, rather than all of the sample brain state data 17d associated with the individual characteristic of male. Specifically, the risk line 54 may be determined based on the second average line 67, which is a trend line for only the heavy alcohol drinking group.

For example, the risk line 54 may be the average line itself, rather than a line based on a value of (-2σ) for each value of the average line. The risk line 54 may also be generated using a different value (for example, a value of (-3σ) for each value of the average line). Instead of generating the risk line 54 based on such statistical data, the risk line 54 may be generated simply by referring to the ranking of the data. Specifically, for example, the risk line 54 may be generated based on data of a predetermined ranking (for example, data within the bottom three) from among the sample brain state data 17d associated with the individual characteristic corresponding to the user individual characteristic.

Next, the prediction unit 22 of the risk recognition and prediction unit 20 predicts (calculates) an aging prediction line 53 indicating the predicted transition of the user's brain health data from the present to the future based on the aging transition line 52. The prediction unit 22 includes a function of predicting the aging prediction line 53 based on the individual characteristics 17b corresponding to the user individual characteristics 43, the lifestyle characteristics 17c corresponding to the user lifestyle characteristics 45, and the sample brain health data 17a associated with age, and the aging transition line 52.

The prediction unit 22 generates an aging prediction line 53 based on the sample brain state data 17d associated with the lifestyle characteristic 17c corresponding to the user lifestyle characteristic 45, in this example, the second average line 67 of the sample brain state data (white circle) 17d of the individual characteristic that the user drinks a lot of alcohol, based on the user lifestyle characteristic 45. Specifically, the prediction unit 22 refers to the transition of the second average line 67 from the reference age of the user brain state data 41 (45 years old, which is the most recent age in this embodiment) to a predetermined age (50 years old in this embodiment), and generates, as the aging prediction line 53, a line that follows the same transition as the transition of the second average line 67, starting from the reference age of the aging transition line 52.

In this embodiment, the user's lifestyle characteristics 45 are referenced when recognizing the aging prediction line 53. This is to recognize a highly reliable aging prediction line (and thus a tendency of dementia risk). However, the method of recognizing the aging prediction line of the present invention is not limited to this method, and any method may be used as long as it is a method of recognition based on the aging progression line 52. For example, the slope of the aging progression line 52 may be recognized, and the aging prediction line 53 may be generated and recognized using the slope. Also, any method may be used as long as it is determined based on the sample brain state data 17d associated with the lifestyle characteristic 17c corresponding to the user's lifestyle characteristics 45, by referring to the progression of the sample brain state data 17d according to age. For example, sample brain state data 17d related to two or more lifestyle characteristics 17c may be referenced, not just one lifestyle characteristic 17c.

For an unspecified number of sample subjects of age z, if a regression equation of an evaluation factor x composed of at least one of three factors, namely, “sample brain state data”, “sample cognitive ability data”, and “user individual characteristics”, is expressed by the following equation (1), and for a sample subject having a predetermined lifestyle characteristic (e.g., drinking habit) among the unspecified number of sample subjects of age z, if a regression equation of the evaluation factor x is expressed by the following equation (2), then the evaluation factor x _t+ 1 at the next time point t+1 (t represents a discrete time such as 5 years or 10 years) is predicted according to the following equation (3) based on the evaluation factor x _t at the current time point t.
x = β ₀ + β ₁ z (β ₀ and β ₁ are regression coefficients) ... (1)
x' = β ₀ ' + β ₁ 'z (β ₀ ' and β ₁ ' are regression coefficients) ... (2)
_xt+1 = _xt + {IF have living properties THEN ( _xt+1' - _xt ') ELSE ( _xt+1 - _xt )}
...(3)

The prediction presentation unit 31a, which displays the chart of the risk presentation unit 30, displays the aging transition line 52, the aging prediction line 53, and the risk line 54 in parallel in the aging transition display area 51 of the report 50 for comparison. The prediction presentation unit 31a may display the plot showing the sample brain state data 17d, the first average line 66, and the second average line 67, but these are deleted to make it easier for users to see. The prediction presentation unit 31a may apply different colors to the reference range 54a above the risk line 54 and the caution zone 54b below it. In addition, the prediction presentation unit 31a plots the ages (41, 45, and 50 years old in this embodiment) that are the references for the aging transition line 52 and the aging prediction line 53 on the horizontal axis of the graph.

In this embodiment, the aging prediction line 53 being above the risk line 54 means that the value cdf(x _t+1 |μ _t+1 , σ _t+1 ) of the cumulative density function cdf(x|μ, σ) of the evaluation factor x shown in the following equation (4) at future time t+1 is greater than 2σ.
cdf(x|μ,σ)=(1/2) {1+erf(x−μ)/(2σ ² ) ^1/2 })
(erf is the error function) ... (4)

The prediction unit 22 may display the aging prediction line 53 with an estimated width 53w indicating a region of high probability. As shown in FIG. 4, the first average line 66 and the second average line 67 include an error, and the 95% CI (Confidence Interval) is indicated by lines 66a and 67a, respectively. The prediction unit 22 may determine the estimated width 53w of the aging prediction line 53 for each user's final time point t, using the estimated width of the second average line 67 for the same age at future time point t+1, and the prediction presentation unit 31a may display the estimated width 53w in the aging progress display area 51.

Figure 5 shows a different example of an aging prediction line 53 using an estimated range 53w. In this example, it is suggested that at future time t+1, the estimated range 53w of dementia risk may fall below the risk line 54 that leads from pre-MCI (the precursor to Mild Cognitive Impairment) to MCI, indicating that there is a probabilistic risk of developing AD (Alzheimer's Disease).

In this way, the presentation system 10 presents dementia risk in the form of a comparison with the aging progression line 52, the aging prediction line 53, and the risk line 54, which are lines according to age. This allows the user, etc., to simultaneously grasp not only the level of the user's dementia risk, but also the trend of the user's dementia risk (whether it is worsening, improving, whether the deterioration is being suppressed, etc.).

The prediction unit 22 of the presentation system 10 further includes a comparison prediction unit 22a that recognizes, for the same user, a first aging prediction line 53 based on the first user lifestyle characteristic 45 and a second aging prediction line 53a based on the second user lifestyle characteristic 45. When the user lifestyle characteristic 45 is changed by the user, etc., the display content related to dementia risk also changes according to the change. For this reason, the presentation system 10 includes a comparison prediction unit 22a that simulates the results of changing the user lifestyle characteristic 45, and a comparison presentation unit 31b that presents the results in a comparative arrangement or consecutively.

Figure 6 shows two types of reports 50 in which the aging prediction line 53 has changed by changing the user lifestyle characteristics 45. In the report 50 shown in Figure 6(a), the alcohol consumption amount in the lifestyle characteristics display area 58 is set to "everyday," while in the report 50 shown in Figure 6(b), the alcohol consumption amount in the lifestyle characteristics display area 58 has been changed to "two to three times a week." As a result, in the report 50 shown in Figure 6(b), the aging prediction line 53a displayed in the aging progress display area 51 is above the aging prediction line 53 shown in the report 50 in Figure 6(a) and slopes away from the risk line 54, indicating that the risk of dementia is reduced.

In the comparison prediction unit 22a, when the content of the amount of alcohol consumed in the user life characteristic 45 is changed from "everyday" to "two to three times a week," a sample with a low amount of alcohol consumed is extracted from the sample brain state data 17d extracted in FIG. 3 to obtain a new average line (third average line, not shown), and a new aging prediction line 53a is generated based on the average line by processing similar to that for the aging prediction line 53. The comparison presentation unit 31b may present the first aging prediction line 53 of the previous condition and the second aging prediction line 53a of the next condition as separate reports 50, or may present them side by side so that they can be referenced within the report 50. The comparison presentation unit 31b may display the first aging prediction line 53 and the second aging prediction line 53a consecutively so that they can be compared. Specifically, the first aging prediction line 53 may be hidden after a predetermined time has elapsed, and the second aging prediction line 53a may be displayed within a time period during which the user or the like can grasp the general shape of the first aging prediction line 53.

The comparison prediction unit 22a and the comparison presentation unit 31b may change the conditions of the user lifestyle characteristics 45 and obtain and present the aging prediction line 53 any number of times, not limited to twice. This function allows the user, etc., to use the presentation system 10 to intuitively grasp the fluctuations in dementia risk that correspond to the fluctuations in the lifestyle characteristics 45. This allows the user, etc., to grasp the specific lifestyle characteristics that should be improved, and thus provides an incentive for improving the lifestyle characteristics.

The risk recognition/prediction unit 20 of this presentation system 10 includes a score calculation unit 23 that converts the dementia risk into a score, and the risk presentation unit 30 includes a score presentation unit 32 that presents the dementia risk based on the score. The score calculation unit 23 compares the sample brain state data 17d and the sample cognitive ability data 17e recognized based on the user brain state data 41, the user cognitive ability data 61, the user individual characteristics 43, and the user lifestyle characteristics 45, and performs scoring based on the results of the comparison, and determines a rank, brain age, and corresponding symbol based on the score.

For example, the value cdf( _xt | _{μt,σt) of the cumulative density function cdf(x|μ} ,σ) of the evaluation factor x of the sample brain state data 17d or the like shown in formula ( ₄ ) at the current time t may be defined as the score S. The rank 55 may be determined according to which of a plurality of numerical ranges (for example, four numerical ranges of 0.0<S≦0.25, 0.25<S≦0.50, 0.50<S≦0.75, 0.75<S≦1.0) the score S is included in. The score calculation unit 23 may also include a function 23a for determining the brain age 56a by referring to a table in which various values of the score S or each of a plurality of numerical ranges is associated with each of a plurality of brain ages.

The score calculation unit 23 may also include a function 23b for determining a symbol 56b corresponding to the score based on the deviation of the value cdf(xt ₊₁ | _μt+1 ,σt ₊₁ ) of the cumulative density function cdf( _x |μ, _σ ) of the evaluation factor x at a future time t+1 from the value cdf(xt| _μt ,σt) at the current time t. If the deviation is a positive value or is equal to or greater than a predetermined positive value, there is a possibility of a decrease in risk. If the deviation is a negative value or is equal to or less than a predetermined negative value, there is a possibility of an increase in risk. If the deviation is 0 or its magnitude is less than a predetermined positive value and greater than a predetermined negative value, there is no change in risk. Then, the symbol 56b corresponding to the score S is determined according to whether the risk is "likely to decrease", "likely to increase", or "no change".

The symbol determining function 23b may include a function for determining the symbol 56b of the long-term prediction corresponding to the score S based on whether the value cdf(xt+1|μt+1,σt+1) of the evaluation factor x at the future time t+1 is greater than or equal to 0.023, which is equivalent to (-2σ, (the threshold indicating the bottom 2.3%)) of the population, or is smaller than this.

The method of calculating the score is not limited to a method using parametric modeling, such as the above-mentioned method using a cumulative density function. For example, a method using a non-parametric ranking may be used. Specifically, various quantile calculation methods using average rank, media rank, approximation, etc. may be used.

The score presentation unit 32 of the presentation system 10 displays (outputs) a rank 55 determined based on the score, a brain age 56a, an arrow 56b, and a legend 56c relating to the rank on the touch panel 2a of the tablet 2 or on the report 50. In this way, the presentation system 10 presents the dementia risk as a score or a symbol corresponding to the score. This allows the user, etc., to intuitively grasp the level of the user's dementia risk.

The score calculation unit 23 may include a function 23c for calculating the user's future dementia risk score, for example, one year from now, in addition to the function of calculating the current dementia risk score and displaying it via the first score presentation unit 32a. The future score calculation function 23c may obtain a score indicating the user's future dementia risk based on the result of a comparison between the user brain health data 18a of the first age on the aging prediction line 53 and the sample brain health data 17a associated with the individual characteristic corresponding to the individual characteristic 17b obtained by adding the first age to the user individual characteristic 43, and may output the calculated score or a symbol corresponding to the score by the second score presentation unit 32b together with or instead of the aging prediction line 53.

The function 23c for calculating a future score may obtain a score indicating the user's future dementia risk based on a result of a comparison between the user brain health data 18a for the first age on the aging prediction line 53 and the individual characteristic 17b corresponding to the individual characteristic obtained by adding the first age to the user individual characteristic 43, and the sample brain health data 17a associated with the life characteristic 17c corresponding to the user life characteristic 45, and may output the calculated score or a symbol corresponding to the score together with or instead of the aging prediction line 53 by the third score presenting unit 32c. The function 23c for calculating a future score may include a function for calculating a score based on the user brain health data 18a designated or arbitrarily selected by the user, instead of the user brain health data 18a on the aging prediction line 53.

The function 23c for calculating the future score may include a simulation function 23d for checking how the score changes by changing the user life characteristic 45. This function 23d calculates a first score indicating the user's future dementia risk based on a result of a comparison between the user brain health data 18a of the first age on the first aging prediction line 53 reflecting the first user life characteristic 45, the individual characteristic 17b corresponding to the individual characteristic obtained by adding the first age to the user individual characteristic 43, and the sample brain health data 17a associated with the life characteristic 17c corresponding to the first user life characteristic 45. Furthermore, this function 23d calculates a second score indicating the user's future dementia risk based on a result of a comparison between the user brain health data 18a of the first age on the second aging prediction line 53a based on the second user life characteristic 45, the individual characteristic 17b corresponding to the individual characteristic 43 obtained by adding the first age to the user individual characteristic, and the sample brain health data 17a associated with the life characteristic 17c corresponding to the second user life characteristic 45. The fourth score presentation unit 32d may output the first and second scores, or a symbol corresponding to them, together with or instead of the aging prediction line. If the user lifestyle characteristics are changed by the user, etc., the display content related to dementia risk also changes according to the changes.

In the report 50 shown in FIG. 7(a), the content of the amount of alcohol consumed in the lifestyle characteristic display area 58 is "everyday," while in the report 50 shown in FIG. 7(b), the content of the amount of alcohol consumed has been changed to "two to three times a week." In these reports 50, the dementia risk at a certain point in the future, for example one year from now, is displayed as a score, and by changing the content of the amount of alcohol consumed from "everyday" to "two to three times a week," the aging prediction line 53 changes, and the sample brain health data 17a to be compared changes from the "heavy drinker group" to the "light drinker group." In this case, the overall risk assessment 55 changes from "B" to "A," the brain age 56a becomes younger, and the long-term prediction symbol 56b also changes to a flatter direction.

In this way, the presentation system 10 can output the future dementia risk as a score or rank in response to changes in the user's lifestyle characteristics 45. This allows the user, etc. to intuitively grasp the changes in dementia risk in response to changes in lifestyle characteristics. This allows the user, etc. to grasp the specific lifestyle characteristics that should be improved, and therefore provides an incentive for improving the lifestyle characteristics.

FIG. 8 shows examples of different types of reports indicating the risk of dementia. This report 50 is output from the risk presentation unit 30 of the presentation system 10 in the same manner as described above. The report 50 includes an analysis result display area 75 of the user cognitive ability data 61 and an aging transition display area 71 of the user cognitive ability data 61 in addition to the score display area 57 and the aging transition display area 51 of the user brain state data 41. The score display area 57 includes a display of a CQ score (Cognitive Quotient Score) 76 in addition to the rank 55 and the brain age 56a. The CQ score 76 is a comprehensive score of an individual's cognitive ability and brain function based on each cognitive function test, and when the average is set to 100 and the standard deviation is set to 15, it becomes a scale compatible with the scoring of IQ (intelligence quotient) and other cognitive ability tests. The CQ score (cq) 76 is calculated by the following formula (5).
[Equation 5]

The variable xi is the evaluation result of each domain of the cognitive ability test 60, and in this report 50, it is the test result of each function of short-term memory, working memory, executive function, spatial cognition, and calculation. The test items (domains) included in the cognitive ability test 60 are not limited to these, and may be a combination of forward recitation, backward recitation, calculation, Stroop test, and mental rotation, or a combination of other test items. In formula (5), the scores of each test item (domain) are standardized (z) to normal distribution and then added together to obtain the total score (cq, CQ score) 76.

In this report 50, the cumulative density function cdf(cq|μ, σ) 77 for the same age is calculated using the cumulative density function shown in formula (4), and a rank 55 is calculated based on the numerical range in which the calculated CQ score 76 falls. For example, assuming a normal distribution with an average of 100 and a standard deviation of 15, the "Above" region where the standard score exceeds 110 is set as rank A, the "Average and Low Average" region where the standard score is 80-110 is set as rank B, the "Low" region where the standard score is 70-79 is set as rank C, and the "Very Low" region where the standard score is less than 70 is set as rank D.

Note that cognitive tests are not limited to these, and scores may be assessed according to the tests or tests listed in Figures 9 and 10 that measure brain health (including the state of cognitive function and the presence and severity of brain and mental disorders) or other similar types of tests or tests.

The analysis result display area 75 of the report 50 includes a radar chart 78 showing the results of each item of the cognitive ability test 60 (short-term memory, working memory, executive function, spatial cognition, calculation) and the standard for the same age. The aging trend display area 71 of the user cognitive ability data 61 shows aging trend lines 72a-72e for each item of the user cognitive ability data 61 (short-term memory, working memory, executive function, spatial cognition, calculation) and standard lines 74a-74e for the same age group as risk lines.

In the aging trend display area 51 of the report 50, in addition to the aging trend line 52 of the user's brain state data 41 and the risk line 54, an average trend line 65 for the same age group based on the user's individual characteristics 43 is displayed. By looking at the report 50, the user can clearly understand the risk of dementia and the progress of the health condition of the brain.

Figure 11 shows an overview of the processing in the presentation system 10 described above using a flowchart. In step 101, the first recognition unit 11 recognizes (acquires) user brain health data 18a including at least one of user brain state data 41, which is data related to the state of the user's brain, and user cognitive ability data 61, which is data related to cognitive ability, which is a brain function. In step 102, the second recognition unit (individual characteristic input unit) 12 recognizes (acquires) user individual characteristics 43, which are individual characteristics of the user. In step 103, the presentation system 10 determines whether prediction processing is requested, and if prediction processing is not requested, in step 104, the risk presentation unit 30 presents risk based on the past and present user brain health data 18a, using an aging transition line 52 showing the transition of the user's user brain health data 18a from the past to the present, and a dementia risk line 54 determined by referring to the transition according to age of the sample brain health data based on the sample brain health data 17a associated with the individual characteristic 17b corresponding to the user individual characteristic 43.

In step 105, the risk presenting unit 30 further presents a score 55 indicating the user's dementia risk, or a symbol corresponding to the score, based on the result of the comparison between the user brain health data 18a and the sample brain health data 17a associated with the individual characteristic 17b corresponding to the user individual characteristic 43. Furthermore, in step 106, the risk presenting unit 30 creates a report 50 including this information and provides it to the user. The report 50 at this stage does not include an aging prediction line.

When a prediction process is requested in step 103, in step 107, the presentation system 10 further determines whether or not a user life characteristic has been input. If the user life characteristic 45 has been input, in step 108, the third recognition unit (life characteristic input unit) 13 recognizes (acquires) the user life characteristic 45, which is the user's life characteristic. In step 109, the prediction unit 22 of the risk recognition and prediction unit 20 predicts (calculates) an aging prediction line 53 based on the individual characteristic 17b corresponding to the user individual characteristic 43, the life characteristic 17c corresponding to the user life characteristic 45, and the sample brain health data 17a associated with age and the aging transition line 52. In step 108, if the user life characteristic 45 has not been input, in step 109, the prediction unit 22 generates an aging prediction line 53 based on the sample brain health data 17a associated with the individual characteristic 17b and the aging transition line 52.

In step 110, the risk presentation unit 30 presents the aging prediction line 53 in addition to the aging transition line 52 and the risk line 54. In step 111, the score calculation unit 23 calculates a score 55 indicating the user's future dementia risk based on the result of comparing the user brain health data 18a of the first age on the aging prediction line 53 with the individual characteristic 17b corresponding to the individual characteristic obtained by adding the first age to the user individual characteristic 43, and the sample brain health data 17a associated with the life characteristic 17c corresponding to the user life characteristic 45, and the risk presentation unit 30 presents the score 55 or a symbol corresponding to the score together with or instead of the aging prediction line 53. In step 108, if the user life characteristic 45 has not been input, in step 110, the score calculation unit 23 calculates the score 55 based on the sample brain health data 17a associated with the individual characteristic 17b.

In step 112, the presentation system 10 determines whether a different (next) user life characteristic 45 is provided. If a different user life characteristic 45 is provided, the process returns to step 108 to obtain a different life characteristic (second user life characteristic) 45 and performs the same process as described above. In step 109, a second aging prediction line 53a related to the second user life characteristic 45 is predicted, and in step 110, the first aging prediction line 53 related to the previous life characteristic (first user life characteristic) 45 and the second aging prediction line 53a related to the second user life characteristic 45 are presented side by side or consecutively in a comparable manner. In step 111, a second score 55 on the second aging prediction line 53a related to the second user life characteristic 45 is calculated and presented together with or instead of the aging prediction lines 53 and 53a in a state comparable to the first score 55 on the first aging prediction line 53 related to the first user life characteristic 45.

If the next user lifestyle characteristic is not input in step 112, then in step 113, it is determined whether multiple predictions have been performed. If multiple predictions have not been performed, then in step 114, the risk presentation unit 30 creates a report 50 including an aging trend line 52, an aging prediction line 53, a risk line 54, a score 55, etc., and provides it to the user. If multiple aging prediction lines 53 have been generated, then in step 115, the risk presentation unit 30 creates a report 50 including simulated multiple aging prediction lines 53 and multiple scores 55, etc., and provides it to the user.

In this embodiment, when scoring dementia risk, brain state data and cognitive ability data are used with reference to the user's lifestyle characteristics. This is to recognize the reliability score (and thus the dementia risk). However, the scoring method of the present invention is not limited to such a method, and it is sufficient that scoring is performed based on the results of a comparison between the user's brain state data and sample brain state data associated with individual characteristics corresponding to the user's individual characteristics. For example, it is not necessary to refer to lifestyle characteristics, and it is also possible to use only brain state data without using cognitive ability data.

In addition, as in the report 50 shown in FIG. 2, when an age-related change display area 51 is provided in addition to a score display area 57 and the dementia risk based on brain state data is displayed in the age-related change display area 51, the score 55 etc. displayed in the score display area 57 may be determined by referring only to the cognitive ability data.

As described above, the presentation system 10 recognizes dementia risk by comparing brain health data including data relating to the brain state of the user who is the subject of risk assessment (user brain state data) with data relating to the brain state of a sample subject (sample brain state data). The data relating to the brain state is direct data in the form of quantitative parameters based on the brain state that affects cognition. In other words, the dementia risk presentation system 10 can use direct data in the form of data relating to the brain state, rather than indirect data in the form of brain function inferred from the user's brain waves, movements, etc., as in conventional systems.

Therefore, with this presentation system 10, the recognition of dementia risk is less affected by the accuracy of estimations regarding brain function. As a result, with this presentation system 10, dementia risk can be recognized more accurately than with conventional systems.

In addition, this presentation system 10 can present the recognized dementia risk to the user, etc., in the form of a result of comparing the user brain state data with the sample brain state data. As a result, according to this presentation system 10, even if the user, etc. does not have sufficient knowledge, the user, etc. can intuitively grasp the magnitude of the dementia risk. In addition, the presentation system 10 can present the dementia risk in a form that compares the aging transition line, which is a line according to age, with the risk line. Therefore, the user, etc. can simultaneously grasp not only the magnitude of the user's dementia risk, but also the trend of the user's dementia risk (whether it is worsening, improving, or suppressing deterioration, etc.). In addition, the aging prediction line, which is a prediction of the progression of the dementia risk from the present to the future, can be presented in a manner comparable to the risk line, and the user, etc. can more accurately grasp the trend of the user's dementia risk.

Furthermore, when recognizing the aging prediction line, the presentation system 10 can refer to one or more user lifestyle characteristics, and can recognize a highly reliable aging prediction line (and thus a dementia risk trend), while allowing the user to more accurately grasp the user's dementia risk trend. Furthermore, by presenting aging prediction lines for multiple user lifestyle characteristics in a form that allows comparison, the user can intuitively grasp the fluctuations in the aging prediction line (and thus the dementia risk) in response to fluctuations in the lifestyle characteristics. This allows the user to grasp the specific lifestyle characteristics that should be improved, and thus provides an incentive for improving the lifestyle characteristics.

Furthermore, the presentation system 10 can present the dementia risk as a score or the like. When recognizing the score or the like, the user can refer to the user lifestyle characteristics and recognize a highly reliable score or the like (and thus the dementia risk). This allows the user to more accurately grasp the tendency of the user's dementia risk. In addition, since the user can grasp the specific lifestyle characteristics that should be improved, an incentive is given to improve the lifestyle characteristics.

The above discloses a dementia risk presentation system that presents a user's dementia risk, comprising: a data storage unit in which sample brain state data, which is data relating to the brain state of a sample subject, is stored in association with individual characteristics including at least one of the age, sex, and physical information of the sample subject; a user brain state recognition unit that recognizes user brain state data, which is data relating to the brain state of the user; a user individual characteristic recognition unit that recognizes user individual characteristics, which are the individual characteristics of the user; a risk recognition unit that compares the user brain state data with the sample brain state data associated with the individual characteristics corresponding to the user individual characteristics; and a risk presentation unit that presents the results of the comparison made by the risk recognition unit. The sample brain state data and the user brain state data are data indicating the total brain volume or the volume of at least one specified region of the brain, and the risk recognition unit recognizes an aging transition line indicating the transition of the user's brain state data from the past to the present based on the past user brain state data and the current user brain state data, and recognizes a risk line determined by referring to the transition of the sample brain state data according to age based on the sample brain state data associated with the individual characteristic corresponding to the user's individual characteristic, and the risk presentation unit may present the aging transition line and the risk line in parallel for comparison.

The risk recognition unit may recognize the aging transition line and the risk line, and may recognize an aging prediction line showing a transition of the user's brain state data predicted from the present to the future based on the aging transition line, and the risk presentation unit may present the aging transition line, the aging prediction line, and the risk line in a comparable juxtaposed manner. The system includes a user life characteristic recognition unit that recognizes user life characteristics that are life characteristics including at least one of the user's lifestyle habits and life environment, and the data storage unit stores the sample brain state data in association with the individual characteristics and the life characteristics of the sample subject, and the risk recognition unit may recognize a trend line showing a transition of the sample brain state data according to age based on the sample brain state data associated with the life characteristics corresponding to the user life characteristics, and may recognize the aging prediction line based on the trend line and the aging transition line. When the user's lifestyle characteristics are changed, the risk recognition unit may re-recognize the aging prediction line based on the changed user's lifestyle characteristics, and the risk presentation unit may present the aging prediction line recognized based on the user's lifestyle characteristics before the change and the aging prediction line recognized based on the user's lifestyle characteristics after the change in a comparable juxtaposed manner or consecutively in a comparable manner.

The risk recognition unit may recognize the dementia risk of the user as a score based on a result of a comparison between the user brain state data and the sample brain state data associated with the individual characteristics corresponding to the user individual characteristics, and the risk presentation unit may present the score or a symbol corresponding to the score. The system includes a user life characteristic recognition unit that recognizes user life characteristics that are life characteristics of the user, and the data storage unit stores the sample brain state data in association with the individual characteristics and life characteristics including at least one of the lifestyle habits and living environment of the sample subject, and the risk recognition unit may recognize the dementia risk of the user as a score based on a result of a comparison between the user brain state data and the sample brain state data associated with the individual characteristics corresponding to the user individual characteristics and the sample brain state data associated with the life characteristics corresponding to the user life characteristics.

The system includes a user life characteristic recognition unit that recognizes user life characteristics that are life characteristics of the user, and the data storage unit stores the sample brain state data in association with the individual characteristics and life characteristics including at least one of the lifestyle habits and living environment of the sample subject, and when the user life characteristics are changed, the risk recognition unit recognizes the score again based on the changed user life characteristics, and the risk presentation unit may present the score or a symbol corresponding to the score recognized based on the user life characteristics before the change and the score or a symbol corresponding to the score recognized based on the changed user life characteristics in parallel or consecutively for comparison.

The above also discloses a dementia risk presentation method for presenting a user's dementia risk, comprising the steps of: a data storage unit storing sample brain state data, which is data relating to the brain state of a sample subject, in association with individual characteristics including at least one of the age, sex, and physical information of the sample subject; a user brain state recognition unit recognizing the user brain state data, which is data relating to the brain state of the user; a user individual characteristic recognition unit recognizing user individual characteristics, which are individual characteristics of the user; a risk recognition unit comparing the user brain state data with the sample brain state data associated with the individual characteristic corresponding to the user individual characteristic; and a risk presentation unit presenting a result of the comparison made by the risk recognition unit.

Although the illustrated embodiment has been described above, the present invention is not limited to such an embodiment. For example, in the presentation system of the above embodiment, the value of the hippocampal volume (hippocampal volume) is used as data related to the brain state. Furthermore, when determining the risk of dementia, the user's lifestyle characteristics are referenced in addition to the user's individual characteristics. However, the dementia risk presentation system of the present invention is not limited to such a configuration, and it is sufficient if it compares brain state data based on individual characteristics to determine the risk of dementia. For example, instead of the hippocampal volume, a value related to the entire brain or other regions may be used, and lifestyle characteristics may not be referenced. Furthermore, other modifications that can be conceived by a person skilled in the art are included in the scope of the present invention in accordance with the scope of the claims.

10 Presentation system, 17 Database

Claims (16)

A first database in which sample brain health data including sample brain state data, which is data relating to a brain state associated with a degree of dementia risk of a sample subject, is associated with individual characteristics including at least one of age, sex, and physical information of the sample subject;
A first recognition unit that recognizes user brain health data including user brain state data, which is data related to a brain state associated with a degree of dementia risk of the user;
A second recognition unit that recognizes a user individual characteristic that is an individual characteristic of the user;
A prediction unit that predicts brain state data indicating a degree of future dementia risk of the user based on the acquired user brain health data, the user individual characteristics, and the first database;
a risk presentation unit that presents information on the user's dementia risk, including data on the brain state predicted in the future of the user by the prediction unit ;
In the first database, the sample brain health data is associated with the individual characteristics and life characteristics including at least one of a lifestyle and a life environment of the sample subject;
The lifestyle habits include at least one of the amount of exercise, the amount and type of food, the length and quality of sleep, the amount and frequency of communication, the amount and frequency of hobby activities, the amount and frequency of alcohol consumption, and the amount and frequency of smoking, and the living environment includes at least one of the living environment, occupation, educational background, annual income, and the number of people living together,
the prediction unit includes a comparison prediction unit that predicts data of a future brain state of the user in a plurality of cases in which the life characteristics are changed for the user based on the first database;
The system , wherein the risk presentation unit includes a comparison presentation unit that presents data on predicted future brain states of the user in multiple cases in which the lifestyle characteristics are changed.
In claim 1,
The system includes a score presentation unit that presents a score indicating the user's dementia risk together with data on the user's predicted future brain state, or a symbol corresponding to the score. In claim 1 ,
The system, wherein the information on the user's dementia risk presented in the risk presentation unit includes an estimated range. In claim 1 or 3,
A third recognition unit that recognizes a user life characteristic that is a life characteristic of the user ,
The prediction unit predicts data of the user's future predicted brain state based on the acquired user's brain health data, the user's individual characteristics, the user's lifestyle characteristics, and the first database.
In claim 4,
the comparison prediction unit predicts, for a same user, data of a brain state predicted in a first future of the user based on a first of the user lifestyle characteristics, and data of a brain state predicted in a second future of the user based on a second of the user lifestyle characteristics;
The system, wherein the comparison presentation unit presents the data of the brain state predicted in the first future and the data of the brain state predicted in the second future in a comparative order or consecutively.
In claim 5 ,
The risk presenting unit includes a score presenting unit that presents a score indicating the user's dementia risk together with data on the user's predicted future brain state, or a symbol corresponding to the score,
The score presentation unit presents a first score indicating a predicted dementia risk of the user in the first future based on the first user lifestyle characteristics together with data on the brain state predicted in the first future, or a first symbol corresponding to the first score, and a second score indicating a predicted dementia risk of the user in the second future based on the second user lifestyle characteristics together with data on the brain state predicted in the second future, or a second symbol corresponding to the second score. In any one of claims 1 to 6 ,
The system, wherein the sample brain state data and the user brain state data include data indicative of at least one of total brain volume, volume of at least one predetermined region of the brain, brain images, electroencephalograms, and cerebral blood flow. In any one of claims 1 to 7 ,
A system in which the sample brain health data includes sample cognitive data, which is data relating to cognition, which is a function of the brain, and the user brain health data includes user cognitive data, which is data relating to cognition, which is a function of the brain of the user. In claim 1 ,
the sample brain state data and the user brain state data include data regarding at least a portion of a predetermined region of the brain that is associated with a degree of dementia risk;
The system includes a generative model in which the prediction unit predicts future brain state data of the user using an algorithm that calculates future predicted brain state data indicating the degree of dementia risk from data regarding at least a specified region of the brain. In claim 9 ,
The system, wherein the data on the brain state includes a volume of the hippocampus, and the data relating to at least a portion of a predetermined region of the brain includes data from which the volume of the hippocampus can be calculated. A method for presenting a risk of dementia using a system capable of referring to a first database in which sample brain health data including sample brain state data, which is data relating to a brain state associated with a degree of dementia risk of a sample subject, is associated with individual characteristics including at least one of age, sex, and physical information of the sample subject, comprising:
Recognizing user brain health data including user brain state data, which is data relating to a brain state associated with a degree of dementia risk of the user;
Recognizing a user individual characteristic, the user individual characteristic;
Predicting brain state data indicating a degree of future dementia risk of the user based on the acquired user brain health data, the user individual characteristics, and the first database;
presenting information on the user's dementia risk, including data on the brain state predicted in the future of the user, predicted by the prediction ;
In the first database, the sample brain health data is associated with the individual characteristics and life characteristics including at least one of a lifestyle and a life environment of the sample subject;
The lifestyle habits include at least one of the amount of exercise, the amount and type of food, the length and quality of sleep, the amount and frequency of communication, the amount and frequency of hobby activities, the amount and frequency of alcohol consumption, and the amount and frequency of smoking, and the living environment includes at least one of the living environment, occupation, educational background, annual income, and the number of people living together,
The predicting step includes predicting, for the user, future brain state data for a plurality of cases in which the life characteristics are changed based on the first database;
The method , wherein the presenting includes presenting data of predicted future brain states of the user for a plurality of cases in which the lifestyle characteristics are changed .
In claim 11 ,
The method, wherein the presenting includes presenting a score indicating the user's dementia risk along with data on the user's predicted future brain state, or a symbol corresponding to the score. In claim 11 ,
The method, wherein the presenting includes presenting information about the user's dementia risk including an estimated range. In claim 11 or 13,
Further comprising: recognizing a user lifestyle characteristic, the user lifestyle characteristic being a lifestyle characteristic of the user;
The method, wherein the predicting includes predicting data of a future predicted brain state of the user based on the acquired user brain health data, the user individual characteristics, the user life characteristics, and the first database.
In claim 14,
The predicting includes predicting, for the same user, data of a predicted brain state in a first future of the user based on a first of the user life characteristics, and data of a predicted brain state in a second future of the user based on a second of the user life characteristics;
The method, wherein the presenting includes presenting the data of the predicted brain state in the first future and the data of the predicted brain state in the second future side-by-side or consecutively for comparison. 11. A program having instructions for causing a computer to operate as a system according to any one of claims 1 to 10 .

Images