Evaluation device, evaluation method, generation method, evaluation system, and evaluation program

Abstract

To calculate an index value which indicates an object person's comprehensive oral function and the meaning of which can be easily understood.SOLUTION: An evaluation device (1) comprises: a data acquisition part (101) that acquires an object person's oral function data and physical function data; and an oral function age calculation part (103) that calculates an oral function age indicating to what age the object person's oral function corresponds, on the basis of a prediction model (111) obtained by modeling a relationship between an actual age and the oral function data and the physical function data of each of the plurality of object persons, and the object person's oral function data and physical function data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This invention relates to an evaluation device for evaluating oral function, etc. [Background technology]

[0002] When a healthy person becomes in need of care due to aging, it is said that they experience a state of physical weakness called frailty during the period from their healthy state to the state requiring care. Furthermore, frailty is said to begin with a state called oral frailty, in which oral function declines. If oral frailty is left untreated without taking measures to improve oral function, the decline in oral function will progress further, and consequently, other bodily functions will also decline, increasing the likelihood of becoming frail and eventually requiring care.

[0003] Frailty, including oral frailty, is reversible, and it is possible to return to a healthy state with appropriate measures. Therefore, in order to maintain a healthy life for as long as possible, it is important to evaluate oral function, understand the current situation, and take measures to prevent oral frailty or to address it if it is already present.

[0004] One example of a method for evaluating oral function is the method described in Patent Document 1 below. Specifically, Patent Document 1 discloses an oral function evaluation device that facilitates the repetitive saliva swallowing test, which evaluates the movement of the throat when swallowing saliva, and oral diadochokinesis (ODK), which evaluates the movement of the lips when pronouncing syllables. [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2008-289737 [Overview of the project] [Problems that the invention aims to solve]

[0006] However, the conventional technologies described above only evaluate some aspects of oral function, such as the ability to swallow saliva and move the lips, and do not provide a comprehensive evaluation of oral function. Furthermore, these conventional technologies use swallowing frequency and pronunciation frequency as evaluation results, but such numbers are unfamiliar to the general public, and there is room for improvement in that it is difficult to understand what the evaluation results mean.

[0007] One aspect of the present invention aims to realize an evaluation device that can show the overall oral function of a subject and calculate an index value that is easy to understand. [Means for solving the problem]

[0008] To solve the above problems, an evaluation device according to one aspect of the present invention includes a data acquisition unit that acquires oral function data relating to the oral function of a subject and physical function data relating to the physical function of the subject; an oral function age calculation unit that calculates an oral function age indicating what age the subject's oral function corresponds to, based on a prediction model that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the oral function data and physical function data of the subject acquired by the data acquisition unit.

[0009] Furthermore, an evaluation method according to one aspect of the present invention is an oral function evaluation method performed by one or more devices in order to solve the above problems, comprising: a data acquisition step of acquiring oral function data relating to the oral function of a subject and physical function data relating to the physical function of the subject; and an oral function age calculation step of calculating an oral function age indicating what age the subject's oral function corresponds to, based on a predictive model that models the relationship between the oral function data and physical function data of each of several subjects and their actual age, and the oral function data and physical function data of the subject acquired in the data acquisition step.

[0010] Furthermore, a generation method according to one aspect of the present invention is a method for generating a predictive model performed by one or more devices in order to solve the above problems, comprising: a data acquisition step of acquiring training data showing the relationship between oral function data relating to the oral function of multiple subjects and physical function data relating to the physical function of the subjects and the actual age of the subjects; and a predictive model generation step of using the training data to generate a predictive model for calculating the oral function age, which indicates what age the subject's oral function corresponds to, based on the subject's oral function data and physical function data.

[0011] Furthermore, an evaluation system according to one aspect of the present invention includes, in order to solve the above problems, a terminal device that accepts input of oral function data relating to the oral function of a subject and physical function data relating to the physical function of the subject; an evaluation device that calculates an oral function age indicating what age the subject's oral function corresponds to, based on a predictive model that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the oral function data and physical function data of the subject that the terminal device has accepted as input. [Effects of the Invention]

[0012] According to one aspect of the present invention, it becomes possible to calculate an easily understandable index value that shows the overall oral function of a subject in terms of age, comparing it to the general level of oral function for the subject's actual age. [Brief explanation of the drawing]

[0013] [Figure 1] This is a block diagram showing an example of the main components of an evaluation device according to one embodiment of the present invention. [Figure 2] This figure shows an example configuration of an evaluation system including the evaluation device described above. [Figure 3] This figure shows an example of a screen to be displayed on a terminal device included in the above evaluation system. [Figure 4]It is a flowchart showing an example of a process for generating a prediction model. [Figure 5] It is a diagram showing an example of a display screen of the calculation result of the oral function age. [Figure 6] It is a flowchart showing an example of a process for calculating the oral function age. [Figure 7] It is a diagram showing another configuration example of the above evaluation system.

Embodiments for Carrying Out the Invention

[0014] 〔System Configuration〕 The configuration of an oral function age evaluation system 5 according to an embodiment of the present invention will be described based on FIG. 2. FIG. 2 is a diagram showing a configuration example of the evaluation system 5. The evaluation system 5 is a system having a function of evaluating the oral function of a subject, and as shown in the figure, includes an evaluation device 1 and a terminal device 3. The evaluation device 1 and the terminal device 3 can communicate with each other via a network. The network may be any network through which the evaluation device 1 and the terminal device 3 can communicate.

[0015] The evaluation device 1 calculates the oral function age as an index value for evaluating the oral function of the subject. The oral function age indicates what age the oral function of the subject corresponds to. Although details will be described later, the evaluation device 1 uses oral function data regarding the oral function of the subject and physical function data regarding the physical function of the subject, and calculates the oral function age using a prediction model that models the relationship between the oral function data, physical function data, and actual age of each of a plurality of subjects. Note that the oral function data can also be said to be data indicating the degree of decline in oral function accompanying aging. Also, the physical function data can also be said to be data indicating the degree of decline in muscle strength accompanying aging.

[0016] The terminal device 3 functions as an input device that receives the input of various data necessary for calculating the oral functional age. As described above, the data necessary for calculating the oral functional age includes oral function data and physical function data. These data input to the terminal device 3 are transmitted to the evaluation device 1 via a network. Note that the method of transmitting the data input to the terminal device 3 to the evaluation device 1 is arbitrary, and for example, a method such as transmitting without passing through a network may be adopted.

[0017] Then, the evaluation device 1 calculates the oral functional age using the received data, transmits the calculated oral functional age to the terminal device 3 via the network, and the terminal device 3 displays the received oral functional age. That is, the terminal device 3 also functions as an output device that outputs the oral functional age calculated by the evaluation device 1. In the example of FIG. 2, a sentence "Your oral age is 64 years old" is displayed on the display unit of the terminal device 3, and "64 years old" included in this sentence is the oral functional age calculated by the evaluation device 1.

[0018] As described above, the evaluation system 5 of the present embodiment includes a terminal device 3 that receives the input of oral function data related to the oral function of the subject and physical function data related to the physical function of the subject, and an oral functional age indicating what age the oral function of the subject corresponds to, using a prediction model that models the relationship between the oral function data and physical function data of each of a plurality of subjects and their actual age, and an evaluation device 1 that calculates using the oral function data and physical function data input by the terminal device 3.

[0019] In addition, the terminal device 3 of the present embodiment executes a process of receiving the input of oral function data related to the oral function of the subject and physical function data related to the physical function of the subject, and a process of outputting the oral functional age calculated using the input oral function data and physical function data and a prediction model that models the relationship between the oral function data and physical function data of each of a plurality of subjects and their actual age.

[0020] Oral function age, which indicates the age equivalent of a subject's oral function, is a value whose meaning is easily understood by anyone. However, it was difficult to calculate oral function age, which represents a subject's overall oral function, from oral function data alone. Therefore, the inventors of this invention conducted extensive research and discovered that by calculating oral function age using not only oral function data but also physical function data, it is possible to calculate a more accurate oral function age with a higher correlation to actual age.

[0021] Therefore, the evaluation system 5, which calculates oral function age using not only oral function data but also physical function data, has the effect of clearly showing the subject's overall oral function in the form of age, making it highly valid and easy to understand as an index value that shows a comparison with the general oral function level for the subject's actual age. Furthermore, the evaluation device 1 and terminal device 3 have the same effect as the evaluation system 5. For example, if the oral function age is in the 20s or 30s, it can be understood that the person can eat anything without difficulty, and if the oral function age is 80 or older, it can be understood that the person has difficulty eating hard foods, etc.

[0022] Note that while Figure 2 shows an example where terminal device 3 is a tablet-type terminal device, terminal device 3 is not limited to a tablet and can have any of the functions described above. For example, a personal computer or other device could be used as terminal device 3, or a device primarily for other functions such as a game console could be used as terminal device 3. The same applies to evaluation device 1, and it is not limited to the example shown. Furthermore, terminal device 3 may also have the functions of evaluation device 1. In this case, oral functional age can be calculated using terminal device 3 alone.

[0023] [Configuration of the evaluation device] A more detailed description of the evaluation device 1 will be given based on Figure 1. Figure 1 is a block diagram showing an example of the main components of the evaluation device 1. As shown in the figure, the evaluation device 1 includes a control unit 10 that controls all parts of the evaluation device 1, a storage unit 11 that stores various data used by the evaluation device 1, and a communication unit 12 for the evaluation device 1 to communicate with other devices. The communication unit 12 is used for communication with the terminal device 3. Although not shown, the evaluation device 1 may also include an input unit that receives various data inputs to the evaluation device 1 and an output unit for the evaluation device 1 to output various data.

[0024] The control unit 10 includes a data acquisition unit 101, an index value calculation unit 102, an oral function age calculation unit 103, an output control unit 104, a training data generation unit 105, and a learning unit 106. The storage unit 11 stores the prediction model 111 and training data 112.

[0025] The data acquisition unit 101 acquires various data necessary for calculating oral functional age. As described above, this data includes oral function data and physical function data of the subject whose oral functional age is to be calculated. The data acquisition unit 101 may acquire this data from the terminal device 3, for example, by communication via the communication unit 12.

[0026] The index value calculation unit 102 calculates index values ​​used to calculate oral functional age using data acquired by the data acquisition unit 101. Details of the index values ​​will be explained later in the section "Configuration of the Prediction Model". Note that multiple index values ​​are used to calculate oral functional age. For this reason, an index value calculation unit 102 may be provided for each index value.

[0027] The oral function age calculation unit 103 calculates the oral function age of a subject based on the subject's oral function data and physical function data. As will be explained in detail in the "Configuration of the Predictive Model" section below, the calculation of oral function age uses a predictive model 111 that models the relationship between the oral function data and physical function data of multiple subjects and their actual age.

[0028] The output control unit 104 causes the oral function age calculated by the oral function age calculation unit 103 to be output to the output device. The output device may be an external device, such as the terminal device 3 shown in the example in Figure 2, or it may be an internal device of the evaluation device 1. The output method can be any method that allows the user to recognize the outputted information, and may be, for example, a display output, a printed output, or an audio output.

[0029] The training data generation unit 105 generates training data 112 used to generate or update the prediction model 111. More specifically, the training data generation unit 105 generates training data 112 by associating the oral function data and physical function data of multiple subjects with their actual age. The oral function data, physical function data, and actual age of each subject may, for example, be input into the evaluation device 1 by the user of the evaluation device 1, or the data acquisition unit 101 may access the storage device that stores the data and acquire it from said storage device.

[0030] Furthermore, the training data generation unit 105 generates training data 112 that shows the correspondence between the oral function data and physical function data of the subject to be calculated for oral function age, which are acquired by the data acquisition unit 101, and the subject's actual age. By including the training data generation unit 105, the evaluation device 1 can automatically generate training data 112 based on the subject's oral function data and physical function data. If the subject inputs their actual age into the terminal device 3, the data acquisition unit 101 can also acquire the actual age from the terminal device 3, and the training data generation unit 105 can then generate training data 112 using the actual age acquired in this way. The training data 112 generated based on the subject's oral function data and physical function data is used to update the prediction model 111.

[0031] The learning unit 106 generates a predictive model 111 through learning using the training data 112. Furthermore, if new training data 112 is added after the prediction model 111 has been generated, the learning unit 106 updates the prediction model 111 using the added training data 112. This makes it possible to maintain or improve the prediction accuracy of the prediction model 111 each time the oral function age of a subject is calculated.

[0032] As described above, the evaluation device 1 includes a data acquisition unit 101 that acquires oral function data related to the subject's oral function and physical function data related to the subject's physical function; a prediction model 111 that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and an oral function age calculation unit 103 that calculates the oral function age, which indicates what age the subject's oral function corresponds to; and an oral function age calculation unit 103 that calculates the oral function age based on the oral function data and physical function data acquired by the data acquisition unit 101. With this configuration, it becomes possible to calculate the oral function age as an index value that shows the subject's overall oral function in the form of age, comparing it to the general oral function level for the subject's actual age, and making its meaning easy to understand.

[0033] [Structure of the prediction model] The predictive model 111 only needs to model the relationship between oral function data, physical function data, and chronological age. For example, the predictive model 111 may be a model generated by multiple regression analysis. In this case, the dependent variable is chronological age, and the independent variables are oral function data and physical function data that correlate with chronological age.

[0034] Examples of oral function data that can be used as explanatory variables include (1) to (4) below. Examples of physical function data that can be used as explanatory variables include (5) to (7) below.

[0035] (1) Number of remaining teeth (this may include wisdom teeth) (2) Functional teeth (the number of teeth that are useful for chewing, including natural teeth, crowns, removable dentures, and implants) (3) Number of repeated pronunciations in oral diadochokinesis (4) Answers to various questions regarding oral health (5) Answers to various questions regarding physical function (6)Gender (7) Measurement values ​​indicating physical function such as BMI (Body Mass Index), body fat percentage, and muscle mass. The number of remaining teeth mentioned in (1) above and the number of functional teeth mentioned in (2) above can be entered by the subject being calculated for oral functional age. For example, the output control unit 104 may display an input screen for the number of remaining teeth and functional teeth on the terminal device 3, allowing the subject to input the number of remaining teeth and functional teeth. In this case, the subject may be asked to input a numerical value representing the number of remaining teeth and functional teeth, or to select a numerical range. For example, the output control unit 104 may display options such as "fewer than 12 teeth have been extracted," "13 to 22 teeth have been extracted," or "23 or more teeth have been extracted," and the data acquisition unit 101 may acquire information indicating the option selected by the user as oral functional data.

[0036] The number of remaining teeth and the number of functional teeth can be used directly as explanatory variables, or index values ​​calculated using the number of remaining teeth and functional teeth can be used as explanatory variables. In the latter case, the index value calculation unit 102 may calculate a numerical value corresponding to the range of the number of remaining teeth and functional teeth as an index value indicating the number of remaining teeth and functional teeth (hereinafter referred to as the tooth count index value). For example, the index value calculation unit 102 may set the tooth count index value to 1 when the number of remaining teeth is 5 or less, to 2 when the number of remaining teeth is between 6 and 15, and to 3 when the number of remaining teeth is 16 or more.

[0037] The number of pronunciations in (3) above may be obtained by having the subject or target repeatedly pronounce the single syllables "pa," "ta," and "ka" as quickly as possible within a predetermined measurement period (e.g., 5 seconds), and inputting the number of times they were able to pronounce each syllable. In this case, the data acquisition unit 101 acquires oral function data indicating the number of times the target pronounces "pa," "ta," and "ka," and the index value calculation unit 102 calculates an index value related to oral diadochokinesis (hereinafter referred to as the ODK index value) from these pronunciation counts. For example, the index value calculation unit 102 may use the minimum number of pronunciations of "pa," "ta," and "ka" as the ODK index value, or it may use the average number of pronunciations of "pa," "ta," and "ka" as the ODK index value.

[0038] Furthermore, the evaluation of oral function using oral diadochokinesis may be performed using terminal device 3. In this case, the output control unit 104 may display various information for the evaluation of oral function using oral diadochokinesis on terminal device 3. This will be explained with reference to Figure 3. Figure 3 is a diagram showing an example of a display screen to be displayed on terminal device 3.

[0039] Of the screens A and B shown in Figure 3, screen A is an example of a display screen that is shown when evaluating the number of times the "ka" sound is pronounced in oral diadochokinesis. Screen A displays text indicating that the pronunciation of "ka" is being checked and that the number of times "ka" can be said in 5 seconds is being measured. Screen A also displays an object containing the text "Start". The output control unit 104 may display such a screen on the terminal device 3.

[0040] When the subject selects the "Start" object on screen A, terminal device 3 begins recording the subject's pronunciation and generates recording data for a predetermined measurement period. The output control unit 104 also displays a screen similar to image A on terminal device 3 for the pronunciations of "pa" and "ka," and terminal device 3 generates recording data of those pronunciations. After the generation of the three recording data sets is complete, terminal device 3 transmits these recording data to evaluation device 1, and data acquisition unit 101 may acquire the recording data as oral function data. In this case, index value calculation unit 102 analyzes the acquired recording data to identify the number of times "pa," "ta," and "ka" are pronounced, and calculates the minimum or average value of these as the ODK index value.

[0041] In order to have the subject input their answers to the questions in (4) or (5) above, the output control unit 104 may display the questions on the terminal device 3. Screen B shown in Figure 3 is an example of a question display screen. Screen B displays the questions and the answer choices for those questions. Note that all the questions displayed on Screen B are questions related to physical function.

[0042] The participant selects the option that applies to them from the choices for each question, and the terminal device 3 transmits data indicating the option selected by the participant for each question to the evaluation device 1. The data acquisition unit 101 acquires this data as oral function data or physical function data, and the index value calculation unit 102 uses this data to calculate an index value corresponding to the answer (hereinafter referred to as the question answer index value).

[0043] The method for calculating the question response index value can be predetermined. For example, points may be predetermined for each option in each question, and the index value calculation unit 102 may calculate the total score or average score for all questions as the question response index value.

[0044] The index value calculated by the index value calculation unit 102 may be, for example, the SARC-F score (sarcopenia-frailty risk check score). In this case, the output control unit 104 simply displays the SARC-F questions on the terminal device 3 and has the subject answer them. The SARC-F questions include questions such as "I have difficulty eating hard foods compared to six months ago," "I sometimes choke on tea or soup," "I wear dentures (partial dentures or full dentures)," and "I have regular dental checkups." The subject answers these questions with "yes" or "no." The SARC-F score is the sum of the points pre-set for each answer choice.

[0045] In addition, the output control unit 104 may present questions such as, "Do you sometimes have difficulty eating dry foods?", "Do your lips get dry?", or "Does your mouth get dry and wake you up during the night?", and ask the user to answer how often each of these occurs. The output control unit 104 may also present questions such as, "How does the taste of food compare to when you were younger?", and ask the user to answer.

[0046] The gender mentioned in (6) above and the measured values ​​mentioned in (7) above should be entered by the subject. The index value calculation unit 102 should then calculate an index value according to the entered information. For example, the index value for males may be set to "0" and the index value for females to "1". Regarding the measured values ​​mentioned in (7) above, the index value calculation unit 102 may use the measured values ​​as they are as index values, or it may use a predetermined numerical value corresponding to the range of the measured values ​​as the index value. For example, the index value calculation unit 102 may set the BMI index value to "1" if the BMI is above the threshold, and set the index value to "0" if it is below the threshold.

[0047] As described above, the oral function data used to calculate oral function age may include at least one of the following: data indicating the number of remaining teeth of the subject, data indicating the number of times the subject was able to pronounce a given syllable during a given period, and data indicating the subject's responses to questions about oral frailty. Furthermore, the physical function data used to calculate oral function age may include at least data indicating the subject's responses to questions about physical function. Since all of these data have been confirmed to correlate with oral function age, it becomes possible to calculate a reasonable oral function age by using these data.

[0048] The above-mentioned index values ​​may be input as oral function data or physical function data; in this case, the index value calculation unit 102 is omitted. Furthermore, the prediction model 111 does not need to be a multiple regression model, as it does not need to model the relationship between oral function data, physical function data and actual age. For example, it is possible to use a prediction model 111 such as a neural network or a random forest.

[0049] [Processing flow (Method for generating a predictive model)] The process by which the learning unit 106 generates the prediction model 111 (method of generating the prediction model) will be explained based on Figure 4. Figure 4 is a flowchart showing an example of the process of generating the prediction model 111. Figure 4 shows the process in a state where training data 112, which associates oral function data and physical function data (more precisely, various index values ​​as described above calculated from oral function data and physical function data) of multiple subjects with their actual age, is stored in the memory unit 11.

[0050] In step S1 (data acquisition step), the learning unit 106 acquires the training data 112 stored in the storage unit 11. Next, in step S2 (prediction model generation step), the learning unit 106 generates a prediction model 111 using the training data 112 acquired in S1. Then, the learning unit 106 stores the generated prediction model 111 in the storage unit 11, and the process shown in Figure 4 is completed.

[0051] When generating a predictive model 111 using multiple regression analysis, the learning unit 106 calculates the values ​​of coefficients and constants to be multiplied by each explanatory variable using the training data 112, and stores the calculated values ​​as the predictive model 111 in the storage unit 11.

[0052] For example, if the explanatory variables are the index value of the number of remaining teeth, the ODK index value, the SARC-F score, and the question response index value calculated based on the answers to multiple questions about oral frailty, the predictive model 111 is represented by the following formula (1). In formula (1), a1 to a4 are regression coefficients, and b is a constant. These values ​​are calculated from the training data 112.

[0053] (Age) = a1 × (Indicator value of remaining teeth) + a2 × (ODK index value) + a3 × (SARC-F score) + a4 × (Indicator value of question response) + b …(1) The oral function age calculation unit 103 can calculate a predicted age of a subject by inputting the various indicator values ​​described above, which are calculated from the subject's oral function data and physical function data, into the formula (1) above. This predicted value is based on oral function data, which is data related to oral function, and physical function data, which is data related to physical function, and is a predicted value that takes into account both the decline in oral function and the decline in physical function. For this reason, this predicted value can be said to be an oral function age with high validity and credibility.

[0054] If the calculated oral function age is lower than the subject's actual age, it means the subject is younger than expected based on their oral and physical function data. On the other hand, if the calculated predicted value is higher than the subject's actual age, it means that the subject's oral function is aging faster than their age would suggest.

[0055] As described above, the method for generating the predictive model 111 of this embodiment includes a data acquisition step (S1) of acquiring training data 112 that shows the relationship between oral function data and physical function data of multiple subjects and the actual age of the subjects, and a predictive model generation step (S2) of using the training data 112 acquired in S1 to generate a predictive model 111 for calculating the oral function age, which indicates what age the subject's oral function corresponds to, based on the subject's oral function data and physical function data. This makes it possible to generate a predictive model 111 that can calculate the oral function age, which is an index value that shows the subject's overall oral function and is easy to understand.

[0056] [Regarding improvements in prediction accuracy] The learning unit 106 may also use the prediction model 111 obtained by adding the Z-score to the right-hand side of the above equation (1). Adding the Z-score can improve prediction accuracy. The Z-score is expressed by the following equation (2). Note that CA is the actual age, r is the correlation coefficient between the age predicted by equation (1) and CA, and σ BA σ is the standard deviation of the predicted age. CA This is the standard deviation of chronological age.

[0057] (Z score) = {CA - (mean value of CA)} {1 - r × (σ BA / σ CA )} …(2) When calculating oral functional age using formula (1) with the Z-score added to the right side, CA should be the subject's actual age, and the average value of CA should be the average of the actual ages in the training data 112. Also, r, σ BA , σ CA This can be calculated using the training data 112. The mean value of CA, r, and σ BA , σ CA This can be calculated by the learning unit 106 during training.

[0058] [Example of result display screen] The output control unit 104 causes the output device to output the oral functional age calculated using the prediction model 111 generated as described above. At this time, the output control unit 104 may also output various information related to oral functional age to the output device.

[0059] Information related to oral functional age includes, for example, the subject's actual age and the difference between their actual age and oral functional age. The output control unit 104 outputs the difference between oral functional age and actual age to the output device, thereby allowing the subject to easily recognize the degree of discrepancy between their oral functional age and actual age.

[0060] In addition, the output control unit 104 may output messages appropriate to the oral function age (such as being able to eat chewy foods properly) or advice on how to reduce the oral function age.

[0061] Furthermore, for subjects whose oral functional age has been calculated multiple times, information showing the trend of their oral functional age may be presented. This will be explained with reference to Figure 5. Figure 5 shows an example of a display screen for the calculation results of oral functional age.

[0062] Screen C, shown in Figure 5, displays a line graph showing the trend of the calculated oral function age. The output control unit 104 displays such a screen on the terminal device 3, allowing the user to easily recognize the trend of their oral function age. In Screen C, oral function age is shown as "oral age".

[0063] Furthermore, screen C displays a dashed line graph showing the actual age of the subject, along with a graph showing the trend of oral function age. This allows users to easily recognize the trend of the discrepancy between oral function age and actual age.

[0064] Furthermore, screen C allows users to switch the period for which trends are displayed between the last 10 periods, monthly, and yearly. This allows the user to view the changes in their oral function age over a period of interest to them. When displaying the changes in a user's oral function age, the oral function age calculation unit 103 simply stores the calculated oral function age in a storage device such as the memory unit 11, along with the user's identification information and the calculation date.

[0065] [Processing flow (calculation of oral functional age)] The process by which the evaluation device 1 calculates oral functional age (oral function evaluation method) is explained based on Figure 6. Figure 6 is a flowchart showing an example of the process for calculating oral functional age. Although Figure 6 also shows the generation of training data 112 and the updating of the prediction model 111, these processes are not essential for calculating oral functional age.

[0066] In step S11 (data acquisition step), the data acquisition unit 101 acquires the subject's oral function data and physical function data. For example, the data acquisition unit 101 may acquire the above data input to the terminal device 3 via communication through the communication unit 12. In addition, the data acquisition unit 101 may also acquire data indicating the subject's actual age at this time.

[0067] As mentioned above, when acquiring oral function data and physical function data, the output control unit 104 may display various display screens on the terminal device 3 for inputting oral function data and physical function data.

[0068] In S12, the index value calculation unit 102 calculates various index values ​​used to calculate oral function age from the oral function data and physical function data acquired in S11. The index values ​​calculated by the index value calculation unit 102 are explanatory variables of the prediction model 111.

[0069] In step S13 (Oral Functional Age Calculation Step), the Oral Functional Age Calculation Unit 103 calculates the subject's oral functional age. Specifically, the Oral Functional Age Calculation Unit 103 calculates the oral functional age by inputting the index values ​​calculated in S12 into the prediction model 111. The prediction model 111 may be a multiple regression model as shown in formula (1), or it may be a multiple regression model to which the Z-score shown in formula (2) has been added, or it may be generated by other machine learning methods.

[0070] In S14, the output control unit 104 causes the oral functional age calculated in S13 to be output to an output device (for example, terminal device 3). At this time, the output control unit 104 may also output the difference between the oral functional age calculated in S13 and the actual age, as well as the trend of the oral functional age.

[0071] In S15, the training data generation unit 105 generates training data. Specifically, the training data generation unit 105 generates training data 112 by associating the index values ​​calculated in S12 with the actual age of the subjects, and stores it in the storage unit 11. Note that the processing from S15 onward can be performed at any time after the completion of the processing in S12, for example, before the processing in S13-S14, or in parallel with the processing in S13-S14.

[0072] In S16, the learning unit 106 determines whether or not to update the prediction model 111. If the result in S16 is YES, the process proceeds to S17; if the result in S16 is NO, the process in Figure 6 ends. The conditions for updating the prediction model 111 can be predetermined. For example, the model may be updated after a predetermined period has elapsed since the generation of the prediction model 111 or since the last update, or after a predetermined number of new training data 112 have been accumulated. Alternatively, the process in S16 may be omitted, and the prediction model 111 may be updated each time new training data 112 is generated.

[0073] In S17, the learning unit 106 updates the prediction model 111. If the prediction model 111 is a multiple regression model, for example, as shown in equation (1), then in S17 the values ​​of a1 to a4 and b are updated. This completes the process shown in Figure 6.

[0074] As described above, the oral function evaluation method of this embodiment includes a data acquisition step (S11) in which oral function data relating to the subject's oral function and physical function data relating to the subject's physical function are acquired, and an oral function age calculation step (S13) in which an oral function age indicating the age equivalent of the subject's oral function is calculated based on a prediction model 111 that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the subject's oral function data and physical function data acquired in S11. Therefore, the oral function age can be calculated as an index value that shows the subject's overall oral function in the form of age, comparing it to the general oral function level for the subject's actual age, and its meaning can be easily understood.

[0075] [Other examples of system configurations] The entity executing each process described in the above embodiments is arbitrary and not limited to the examples given above. In other words, the devices constituting the evaluation system 5 can be changed as appropriate, as long as each process described in the above embodiments can be executed.

[0076] For example, an evaluation system 6 with the configuration shown in Figure 7 is also included in the scope of the present invention. Figure 7 is a diagram showing an example of the configuration of evaluation system 6. Evaluation system 6 is a system that has the function of calculating oral functional age, similar to evaluation system 5. As shown in the figure, evaluation system 6 includes an evaluation device 61, a display 62, a keyboard 63, a mouse 64, and a learning device 65.

[0077] The evaluation device 61, like the evaluation device 1 described above, has a function to calculate oral functional age. The display 62 is a display device that displays images and is used to display oral functional age (labeled as "oral age" in Figure 7) as shown in the figure. The keyboard 63 and mouse 64 are input devices used to input the subject's oral function data and physical function data. The learning device 65 is a device that generates the prediction model 111. Since the learning device 65 generates the prediction model 111, the evaluation device 61 does not need to have a learning unit 106, which is a component for generating the prediction model 111.

[0078] In the evaluation system 6, the learning device 65 generates a predictive model 111, and the evaluation device 61 acquires the predictive model 111 generated by the learning device 65. The subject inputs their oral function data and physical function data into the evaluation device 61 using the keyboard 63 and mouse 64, and the evaluation device 61 calculates the subject's oral function age using the various input data and the predictive model 111 generated by the learning device 65. Thus, the system may be configured to calculate the oral function age using a device that is directly operated by the subject.

[0079] Furthermore, the learning device 65 may also acquire the subject's oral function data, physical function data, and actual age, etc., which are input to the evaluation device 61, and perform processes such as generating training data 112 using this data, or updating the predictive model 111 using the generated training data 112.

[0080] Of course, the system configurations in Figure 7 and Figure 2 are merely illustrative examples, and the implementation of the present invention is not limited to these examples. For instance, the evaluation device 61 may be a notebook-type personal computer or a tablet-type terminal device.

[0081] Furthermore, the entity that executes each step of the prediction model generation method shown in Figure 4, and the entity that executes each step of the oral function evaluation method shown in Figure 6, are also arbitrary. In other words, each of these methods can be executed by a single device, or it can be executed by distributing the processing of each step among multiple devices.

[0082] [Examples of implementation using software] The functions of the evaluation device 1, terminal device 3, evaluation device 61, and learning device 65 (hereinafter referred to as "devices") can be realized by programs that cause the devices to function as computers, and by programs that cause the computers to function as each control block of the devices (especially each part included in the control unit 10) (evaluation program / predictive model generation program, etc.).

[0083] In this case, each of the above devices includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the above program. By executing the above program (an evaluation program or predictive model generation program that makes the computer function as evaluation device 1 / a program that makes the computer function as terminal device 3 / an evaluation program that makes the computer function as evaluation device 61 / a predictive model generation program that makes the computer function as learning device 67) using this control device and storage device, each of the functions described in each of the above embodiments is realized.

[0084] The above program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the above device. In the latter case, the program may be supplied to the above device via any wired or wireless transmission medium.

[0085] In addition, part or all of the functions of each of the above control blocks can also be realized by a logic circuit. For example, an integrated circuit in which a logic circuit functioning as each of the above control blocks is formed is also included in the scope of the present invention. In addition to this, for example, it is also possible to realize the functions of each of the above control blocks by a quantum computer.

[0086] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

[0087] 〔Summary〕 The evaluation device according to Aspect 1 of the present invention includes a data acquisition unit that acquires oral function data related to the oral function of a subject and physical function data related to the physical function of the subject, and an oral function age indicating what age the oral function of the subject corresponds to. An oral function age calculation unit that calculates based on a prediction model that models the relationship between the oral function data and the physical function data of each of a plurality of subjects and their actual age, and the oral function data and physical function data of the subject acquired by the data acquisition unit.

[0088] The evaluation device according to Aspect 2 of the present invention is, in the above Aspect 1, at least any one of data indicating the number of remaining teeth of the subject, data indicating the number of times the subject was able to pronounce a predetermined syllable within a predetermined period, and data indicating the response content of the subject to a question regarding oral frailty is included in the oral function data, and the physical function data includes at least data indicating the response content of the subject to a question regarding physical function.

[0089] The evaluation device according to Aspect 3 of the present invention is, in the above Aspect 1 or 2, the prediction model is a model obtained by adding the following value to a multiple regression model that calculates the oral function age from a plurality of explanatory variables generated from the oral function data and the physical function data, {CA - (average value of CA)}{1 - r×(σ BA / σCA )} CA is the actual age, r is the correlation coefficient between the predicted age predicted by the multiple regression model and CA, and σ is the correlation coefficient. BA σ is the standard deviation of the predicted age, CA This is the standard deviation of the actual age.

[0090] The evaluation apparatus according to aspect 4 of the present invention includes, in any of aspects 1 to 3 above, a training data generation unit that generates training data showing the correspondence between the oral function data and physical function data acquired by the data acquisition unit and the actual age of the subject.

[0091] The evaluation device according to aspect 5 of the present invention includes a learning unit that updates the prediction model using the training data, as described in aspect 4 above.

[0092] The evaluation apparatus according to embodiment 6 of the present invention includes, in any of embodiments 1 to 5 above, an output control unit that causes the output device to output the difference between the oral function age calculated by the oral function age calculation unit and the actual age of the subject.

[0093] An evaluation method according to aspect 7 of the present invention is an oral function evaluation method performed by one or more devices, comprising: a data acquisition step of acquiring oral function data relating to the oral function of a subject and physical function data relating to the physical function of the subject; and an oral function age calculation step of calculating an oral function age indicating what age the subject's oral function corresponds to, based on a predictive model that models the relationship between the oral function data and physical function data of each of several subjects and their actual age, and the oral function data and physical function data of the subject acquired in the data acquisition step.

[0094] A predictive model generation method according to aspect 8 of the present invention is a predictive model generation method performed by one or more devices, comprising: a data acquisition step of acquiring training data showing the relationship between oral function data relating to the oral function of a plurality of subjects and physical function data relating to the physical function of the subjects and the actual age of the subjects; and a predictive model generation step of using the training data to generate a predictive model for calculating the oral function age, which indicates what age the subject's oral function corresponds to, based on the subject's oral function data and physical function data.

[0095] An evaluation system according to aspect 9 of the present invention includes a terminal device that receives input of oral function data relating to the oral function of a subject and physical function data relating to the physical function of the subject; and an evaluation device that calculates an oral function age indicating the age at which the subject's oral function corresponds, based on a predictive model that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the oral function data and physical function data of the subject received by the terminal device.

[0096] An evaluation program according to aspect 10 of the present invention is an evaluation program for causing a computer to function as an evaluation device as described in Appendix 1, wherein the computer functions as the data acquisition unit and the oral function age calculation unit. [Explanation of Symbols]

[0097] 1. Evaluation device 101 Data Acquisition Unit 103 Oral function age calculation unit 104 Output Control Unit 105 Training Data Generation Unit 106 Learning Department 111 Predictive Models 112 Training Data 3 Terminal devices 5, 6 Evaluation System 61 Evaluation device

Claims

1. A data acquisition unit that acquires oral function data related to the subject's oral function and physical function data related to the subject's physical function, An evaluation device comprising: an oral function age calculation unit that calculates an oral function age indicating the age equivalent of the subject's oral function, based on a predictive model that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the oral function data and physical function data of the subject acquired by the data acquisition unit.

2. The oral function data includes at least one of the following: data indicating the number of remaining teeth of the subject, data indicating the number of times the subject was able to pronounce a predetermined syllable during a predetermined period, and data indicating the subject's responses to questions regarding oral frailty. The evaluation device according to claim 1, wherein the physical function data includes at least data showing the subject's responses to questions regarding physical function.

3. The prediction model is a multiple regression model that calculates the oral function age from multiple explanatory variables generated from the oral function data and the physical function data, with the following values ​​added: {CA - (mean value of CA)} {1 - r × (σ ＢＡ / σ ＣＡ )} CA is the actual age, r is the correlation coefficient between the predicted age predicted by the multiple regression model and CA, and σ is the correlation coefficient. ＢＡ σ is the standard deviation of the predicted age, ＣＡ The evaluation device according to claim 1 or 2, wherein is the standard deviation of the actual age.

4. The evaluation apparatus according to claim 1 or 2, further comprising a training data generation unit that generates training data showing the correspondence between the oral function data and physical function data acquired by the data acquisition unit and the actual age of the subject.

5. The evaluation device according to claim 4, further comprising a learning unit that updates the prediction model using the aforementioned training data.

6. The evaluation apparatus according to claim 1 or 2, further comprising an output control unit that causes an output device to output the difference between the oral function age calculated by the oral function age calculation unit and the actual age of the subject.

7. A method for evaluating oral function performed by one or more devices, A data acquisition step to acquire oral function data regarding the subject's oral function and physical function data regarding the subject's physical function, A method for evaluating oral function, comprising: an oral function age calculation step, which calculates an oral function age indicating the age equivalent of the subject's oral function, based on a predictive model that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the oral function data and physical function data of the subject obtained in the data acquisition step.

8. A method for generating a predictive model, which is performed by one or more devices, A data acquisition step involves obtaining training data showing the relationship between oral function data regarding the oral function of multiple subjects, physical function data regarding the physical function of those subjects, and the actual age of those subjects. A method for generating a predictive model, comprising: a predictive model generation step of generating a predictive model for calculating the oral function age, which indicates the age at which a subject's oral function corresponds, based on the subject's oral function data and physical function data, using the aforementioned training data.

9. A terminal device that accepts input of oral function data regarding the subject's oral function and physical function data regarding the subject's physical function, An evaluation system including an evaluation device that calculates an oral function age, which indicates the age equivalent of the subject's oral function, based on a predictive model that models the relationship between the oral function data and physical function data of multiple subjects and their actual age, and the subject's oral function data and physical function data received as input by the terminal device.

10. An evaluation program for causing a computer to function as an evaluation device according to claim 1, wherein the computer functions as the data acquisition unit and the oral function age calculation unit.

Images