Development month age estimation device, development month age estimation method, and development month age estimation program

Abstract

Relating to the estimation of the development month age of a child, the present invention obtains an estimation result with high objectivity regarding the development month age while increasing the degree of freedom of inspection items. [Solution] A development month age estimation device 3 comprises: a processor 15 for executing processing for estimating the development month age of a child which is the subject of inspection on the basis of inspection results for a plurality of inspection items; and a storage device 14 for storing data on a continuous probability distribution indicating a passage rate where month ages in a predetermined range are taken as a variable, for each of the plurality of inspection items. The processor 15 generates a development month age estimation function on the basis of data on a continuous probability distribution for two or more implementation inspection items used for inspection among the plurality of inspection items and an inspection result for each of the implementation inspection items, estimates the development month age of a child which is the subject of inspection on the basis of the mode value of a distribution of passage rates obtained by the development month age estimation function, and outputs an estimation result of the development month age.

Description

Developmental age estimation device, developmental age estimation method, and developmental age estimation program

[0001] The present disclosure relates to a developmental age estimation device, a developmental age estimation method, and a developmental age estimation program that estimate a child's developmental age.

[0002] It has been known that there are individual differences in the development of children (including infants and toddlers) in terms of motor, language, intelligence, and emotions. Caregivers of children may wish to compare their child's current developmental status with the standard developmental status of other children of the same age (or to understand any deviation from the standard developmental status). Furthermore, appropriately estimating a child's developmental age (i.e., a measure based on the number of months that indicates the developmental status of the child being tested) is also important in the fields of medicine and education.

[0003] A known technique for estimating a child's developmental age is, for example, a method in which an examiner (a medical or educational professional, etc.) uses an examination sheet that displays multiple examination items (e.g., movements and exercises that a child of the age being examined can perform) set according to the child's developmental stage, and uses tools to carry out an examination for each examination item on the child being examined, determines whether the child passes or fails each examination item, and graphically depicts the pass / fail results to estimate the developmental age of the child being examined (see Non-Patent Document 1).

[0004] "Tojoji Method: Infant Differential Development Testing Method," by Tojoji Munenori, Keio University Press, 2022 (revised and reprinted first edition, 7th printing)

[0005] In addition to the test disclosed in Non-Patent Document 1, various other testing methods have been developed for estimating a child's developmental age, and each method estimates the developmental age using its own unique set of test items. Therefore, in such conventional techniques, tests for estimating a child's developmental age must be conducted according to the test items specified for each testing method, regardless of the merits or suitability of the test items. Therefore, in conventional techniques, it is difficult to estimate a child's developmental age using a standardized test with a high degree of freedom in test items.

[0006] Furthermore, in the conventional technology described in Non-Patent Document 1, the estimation of the developmental age based on the test results is performed by the person in charge of the test (i.e., a human), and therefore the test results may vary depending on the subjectivity of the person in charge of the test. Furthermore, in the conventional technology, since the final estimation of the developmental age requires human judgment, there is also the problem that the test results cannot be obtained quickly.

[0007] As a result of extensive research, the inventors of the present application have found that by using data on the pass rate for each test item (i.e., the proportion of children in a certain age group who achieve that test item), it is possible to obtain highly objective estimation results regarding developmental age while increasing the degree of freedom in test items (i.e., flexibility in selection). Note that in the above-mentioned Non-Patent Document 1, the pass rate for each test item is only used for selecting and rearranging test items, and is not directly used for estimating developmental age.

[0008] In view of the above background, the present disclosure aims to provide a developmental age estimation device, a developmental age estimation method, and a developmental age estimation program that enable highly objective estimation results regarding developmental age while increasing the degree of freedom in test items.

[0009] In order to solve the above problem, one aspect of the present disclosure is a developmental age estimation device that estimates the developmental age of a child, comprising a processor that executes a process of estimating the developmental age of a child to be tested based on test results for a plurality of test items, and a storage device that stores data regarding a continuous probability distribution that indicates the pass rate for each of the plurality of test items, with age in months within a predetermined range as a variable, wherein the processor generates a developmental age estimation function based on the data regarding the continuous probability distribution for two or more implemented test items of the plurality of test items that were used to test the child to be tested, and the test results for each of the implemented test items, estimates the developmental age of the child to be tested based on the mode of the distribution of pass rates obtained by the developmental age estimation function, and outputs the estimated developmental age result.

[0010] According to this aspect, a developmental age estimation function is generated based on data regarding the continuous probability distribution of the implemented test items and the test results for each of those implemented test items, and the developmental age of the child being tested is estimated based on that developmental age estimation function, thereby making it possible to obtain highly objective estimation results regarding developmental age while increasing the degree of freedom in the test items.

[0011] In the above aspect, the processor may acquire, for each of the plurality of test items, data on a plurality of ages in months and a pass rate corresponding to each of the plurality of ages in months, and generate data on the continuous probability distribution based on the pass rate data.

[0012] According to this aspect, data relating to a continuous probability distribution can be easily obtained based on data on passage rates corresponding to a plurality of ages in months.

[0013] In the above aspect, the processor may determine two parameters of a probability density function of a beta distribution based on the data on the passage rate, and generate data regarding the continuous probability distribution based on a cumulative distribution function obtained by integrating the probability density function of the beta distribution.

[0014] According to this aspect, it is possible to obtain data relating to a continuous probability distribution suitable for estimating a child's developmental age in months, based on the probability density function of the beta distribution.

[0015] In the above aspect, the processor may set an age range for the passage rate data for each of the plurality of test items, and convert the age range into a range from 0 to 1.

[0016] According to this aspect, data relating to a continuous probability distribution can be appropriately acquired based on the probability density function of the beta distribution.

[0017] In the above aspect, the processor may set a probability function of the pass rate for each of the performed test items based on data regarding the continuous probability distribution and the test results, and the developmental age estimation function may include a product of the probability functions for each of the performed test items.

[0018] According to this aspect, the developmental age of the child being tested can be easily estimated based on the data regarding the continuous probability distribution for each of the test items and the test results.

[0019] In the above aspect, it is preferable to further include a display device that displays the estimation result of the developmental age.

[0020] According to this aspect, the user of the developmental age estimation device can easily check the estimation result of the developmental age.

[0021] In order to solve the above-mentioned problems, one aspect of the present disclosure is a developmental age estimation method using a developmental age estimation device that estimates the developmental age of a child, wherein the developmental age estimation device generates a developmental age estimation function based on data regarding continuous probability distributions for two or more implemented test items used in testing the child to be tested out of a plurality of test items for estimating the developmental age of the child to be tested and the test results for each of the implemented test items, estimates the developmental age of the child to be tested based on the mode of the distribution of pass rates obtained by the developmental age estimation function, and outputs the estimated developmental age result.

[0022] According to this aspect, a developmental age estimation function is generated based on data regarding the continuous probability distribution of the implemented test items and the test results for each of those implemented test items, and the developmental age of the child being tested is estimated based on that developmental age estimation function, thereby making it possible to obtain highly objective estimation results regarding developmental age while increasing the degree of freedom in the test items.

[0023] In order to solve the above-mentioned problems, one aspect of the present disclosure is a developmental age estimation program that causes a computer to execute a developmental age estimation process that estimates a child's developmental age, wherein the developmental age estimation process includes the steps of generating a developmental age estimation function based on data regarding continuous probability distributions for two or more implemented test items used in testing the child to be tested, out of multiple test items for estimating the developmental age of the child to be tested, and test results for each of the implemented test items, estimating the developmental age of the child to be tested based on the mode of the distribution of pass rates obtained by the developmental age estimation function, and outputting the estimated developmental age result.

[0024] According to this aspect, a developmental age estimation function is generated based on data regarding the continuous probability distribution of the implemented test items and the test results for each of those implemented test items, and the developmental age of the child being tested is estimated based on that developmental age estimation function, thereby making it possible to obtain highly objective estimation results regarding developmental age while increasing the degree of freedom in the test items.

[0025] According to the above aspect, it is possible to obtain highly objective estimation results regarding developmental age while increasing the degree of freedom in test items.

[0026] FIG. 1 is a block diagram of a developmental age estimation system including a developmental age estimation device according to an embodiment; FIG. 2 is an explanatory diagram showing an example of data on pass rates for a plurality of test items; FIG. 3 is an explanatory diagram showing examples of (A) a probability distribution and (B) a cumulative distribution for data on pass rates; FIG. 4 is an explanatory diagram showing an example of setting age intervals for each test item; FIG. 5 is an explanatory diagram showing an example of display content on a test item confirmation screen; and FIG. 6 is an explanatory diagram showing an example of a probability distribution of pass rates based on a developmental age estimation function.

[0027] Below, embodiments of a developmental age estimation system, a developmental age estimation device, a method for estimating a developmental age using a developmental age estimation device, and a program for executing a process for estimating a developmental age according to the present disclosure will be described with reference to the drawings.

[0028] As shown in Figure 1, the developmental age estimation system 1 includes a developmental age estimation device 2 that estimates a child's developmental age, and a user terminal 4 that is communicatively connected to the developmental age estimation device 2 via a communication network 3 such as the Internet.

[0029] The developmental age estimation device 2 is configured by a computer for executing a process for estimating a child's developmental age (hereinafter referred to as a "developmental age estimation process"). In this embodiment, the developmental age estimation device 2 is configured by a server that executes a process for estimating a child's developmental age in response to a request from a client used by a user (here, the user terminal 4).

[0030] The developmental age estimation process by the developmental age estimation device 2 is performed based on test result data for each of a plurality of test items that have been performed in the past, and test results for test items to be performed on the child who is currently being tested (hereinafter referred to as "performed test items"). Tests for the performed test items can be performed by an examiner in the same manner as conventional testing methods.

[0031] Data on past test results is obtained for each test item set for estimating a child's developmental age. In the developmental age estimation system 1, the test items used to estimate a child's developmental age can be, for example, the test items adopted in the above-mentioned Non-Patent Document 1. However, the developmental age estimation system 1 is not limited to this, and other known testing methods may also be used (for example, W. K. Frankenburg, MD, "DENVER II Denver Developmental Assessment Method," Japan Pediatric Health Association, 2016 (2nd edition, 2nd printing); Nakamura Junko, Okawa Ichiro, Nohara Rie, and Serizawa Nanami, "Tanaka-Binet Intelligence Test V," Taken Publishing Co., Ltd., 2003; Suzuki Harutaro, "Revised Edition Suzuki-Binet Intelligence Test," Furuichi Publishing, 2007; New Edition K-Type Developmental Test Research Group (editor), "New Edition K-Type Developmental Test Method 2001 Edition," Nakanishiya Publishing, 2008; Tsumori Makoto and Inage Noriko, "Infant Mental Development Diagnostic Method," Dainippon Tosho, 1961; Tanaka Misato et al., Revised Edition Voluntary Motor Development Test, Speech and Language Medicine, 1990, 31: Any test item adopted in the "Question-Response Relationship Test" by Tsuneo Satake, Escoal, 1997, p. 172-185 can be used.

[0032] In particular, it is preferable to use test items for which the reliability of data on the passing rate for multiple ages (for example, the percentage of children of a certain age who achieve that test item) has been established as test results in the developmental age estimation system 1. Note that, when data on the passing rate for multiple ages for a new test item is obtained, the developmental age estimation system 1 can also adopt the new test item.

[0033] In this embodiment, "children" primarily refers to preschool infants and school-age children aged 0 to 12 years old. However, the estimation of developmental ages using the system, device, method, and program according to the present disclosure is not limited to children, and can be applied to people of any chronological age (including adolescents and adults).

[0034] The user terminal 4 is configured as an information processing device with a communication function, such as a smartphone, tablet terminal, or PC, used by a user. The user may include, but is not limited to, a medical or educational professional, for example, and may also be someone other than such a professional (for example, a family member of a child). Also, although only one user terminal 4 is shown in FIG. 1, the developmental age estimation system 1 may include multiple user terminals.

[0035] In the present embodiment, the user terminal 4 is configured to cause the developmental age estimation device 2 to execute the developmental age estimation process, but this is not limiting, and the user terminal 4 may also function as the developmental age estimation device (i.e., execute the developmental age estimation process). In other words, the developmental age estimation device 2 is not limited to a server, and may be configured by an information processing device such as a smartphone, tablet terminal, or PC, similar to the user terminal 4. In this case, the developmental age estimation device 2 does not necessarily need to be connected to a communication network, and may be operated directly by a user. Furthermore, the developmental age estimation process in the developmental age estimation system 1 may be realized by the cloud (i.e., a collection of virtual resources and services).

[0036] The developmental age estimation device 2 includes a communication unit 11 , an input unit 12 , a display unit 13 , a storage unit 14 , and a control unit 15 .

[0037] The communication unit 11 includes an antenna, a communication circuit, etc., and performs wireless or wired communication with other devices (here, the user terminal 4, etc.) via the communication network 3 in accordance with a known communication protocol.

[0038] The input unit 12 includes a known input device (e.g., a keyboard) for inputting operation commands and the like to the developmental age estimation device 2. However, when operation commands and the like are input to the developmental age estimation device 2 from another device (e.g., the user terminal 4), the input unit 12 may be omitted.

[0039] The display unit 13 includes a known device (for example, a display device such as a liquid crystal display) for displaying (i.e., outputting) information used by the developmental age estimation device 2 and information generated by the developmental age estimation device 2. However, if information from the developmental age estimation device 2 is output to another device (for example, the user terminal 4), the display unit 13 may be omitted. Furthermore, such information may be output by sound (i.e., from a speaker not shown).

[0040] The memory unit 14 includes a storage device such as a storage for storing data and information necessary for processing by the developmental age estimation device 2. The memory unit 14 does not need to be provided integrally with the developmental age estimation device 2, and may be configured as an external storage device connected to the developmental age estimation device 2 via a network or the like. As will be described later, the memory unit 14 stores test item data 21, distribution function data 22, test result data 23, developmental age estimation function data 24, and the like.

[0041] The control unit 15 includes one or more processors (CPU, MPU, etc.), and the processor executes a predetermined control program (an example of a developmental age estimation program) to perform the processes required for estimating the developmental age. The control unit 15 also has overall control over the operation of the developmental age estimation device 2.

[0042] In the control unit 15, the test item data collection unit 31 collects data on multiple test items that have been performed in the past from data stored in another database (not shown), etc., and stores the data in the storage unit 14 as test item data 21. The test item data 21 includes, for example, as shown in FIG. 2 , data on the pass rates for multiple test items that have been performed in the past at multiple ages in months.

[0043] For example, Figure 2 shows the pass rate for test item No. 134, "walk two to three steps." More specifically, Figure 2 shows that 44.2% of 11-month-old children achieved "walk two to three steps" (i.e., they were able to "walk two to three steps"), 68.3% of 13-month-old children achieved it, 89.5% of 15-month-old children achieved it, and 98.0% of 17-month-old children achieved it. The pass rates for other test items are similar to that for test item No. 134.

[0044] The test item data 21 includes data on test items employed in known test methods as described above. The test item data 21 may also include data obtained on new test items. Note that at least a portion of the test item data 21 stored in the storage unit 14 may be data input in advance by an administrator of the developmental age estimation system 1, or the like.

[0045] In the control unit 15, the distribution function estimation unit 32 generates a probability density function and a cumulative distribution function for the pass rate for each inspection item based on the inspection item data 21.

[0046] In this embodiment, a beta distribution is used as the continuous probability distribution. The probability density function f(x;α,β) relating to the pass rate for each test item is expressed by the following equation (1). As will be described in detail later, when using the beta distribution, the age intervals in months for which the pass rate for each test item is obtained are converted so that they correspond to the range of the random variable from 0 to 1.

[0047]

[0048] where x: random variable (0≦x≦1) α, β: positive real numbers

[0049] However, the beta function B(α, β) in equation (1) is expressed by the following equation.

[0050]

[0051] ​​Furthermore, by integrating the probability density function f(x;α,β) of the beta distribution shown in equation (1), the cumulative distribution function F(x;α,β) of the beta distribution expressed by the following equation (2) is obtained.

[0052]

[0053] According to such a beta distribution probability density function f(x;α,β), the distribution function estimation unit 32 can appropriately control the peak and variance of the probability density distribution by determining two parameters α and β, as shown in Fig. 3A, for example.The distribution function estimation unit 32 determines the parameters α and β so as to fit the pass rate values ​​of each inspection item in the inspection item data 21 (i.e., actual measured values ​​obtained from past inspection results), and thereby can obtain an appropriate continuous probability distribution for the pass rate of each inspection item based on the cumulative distribution function F(x;α,β), as shown in Fig. 3B, for example.

[0054] For example, the distribution function estimation unit 32 can determine the parameters α and β so that the sum of squared residuals between the value of each pass rate for each test item in the test item data 21 and the pass rate at the corresponding age in months (more precisely, a predetermined value of the random variable converted from the age in months) calculated using the cumulative distribution function F(x;α,β) is minimized.

[0055] Note that the parameters α and β may be determined using a general-purpose scientific calculation library. For example, the parameters α and β may be determined using the BFGS (Broyden-Fletcher-Goldfarb-Shanno) method or the L-BFGS-B (Limited-memory Broyden-Fletcher-Goldfarb-Shanno with Box constraints) method in the minimize function of the optimize module in the Scipy library of Python.

[0056] The distribution function estimation unit 32 then converts the range of the random variable from 0 to 1 back into a lunar age interval, and obtains data on the cumulative distribution function F(x;α,β) of the passage rate with lunar age as a variable (an example of data related to a continuous probability distribution).

[0057] ​The data of the probability density function f(x;α,β) and cumulative distribution function F(x;α,β) of the beta distribution obtained for each test item are sequentially stored in the storage unit as distribution function data 22.

[0058] The distribution function estimation unit 32 can generate the probability density function and cumulative distribution function described above when a new test item is added to the test item data 21 or when the pass rate data for an existing test item is updated.

[0059] Here, with reference to FIG. 4 , a process (hereinafter referred to as "age conversion process") for converting age intervals in which a significant change occurs in the pass rate for each test item so that they correspond to a range of random variables between 0 and 1 will be described. It should be noted that, in addition to the processing method described below, a different processing method may be used to determine age intervals, as long as it includes all ages corresponding to the pass rate data and can determine appropriate parameters α and β. Furthermore, it is also possible to redefine age intervals by referencing parameters α and β that have already been obtained, and determine new parameters α and β. Furthermore, these processing methods do not necessarily need to be uniformly applied to all test items; different processing methods may be used as long as it is possible to define age intervals in which sufficiently appropriate parameters α and β can be determined for each test item.

[0060] In the moon age conversion process, first, the distribution function estimation unit 32 identifies the minimum value x_min and maximum value x_max of the moon age X in the data group of the test item to be processed in the test item data 21. Here, the data group of the test item is assumed to be composed of the moon ages and passage rates corresponding to the two white circles (◯) shown in Fig. 4. Similarly, the distribution function estimation unit 32 identifies the minimum value y_min and maximum value y_max of the passage rate Y in the data group of the test item.

[0061] Therefore, the distribution function estimation unit 32 creates a straight line passing through (x_min, y_min) and (x_max, y_max) on the XY plane (i.e., see the solid line connecting the circles (○) in Figure 4 and the dashed line extending from that line), and calculates the X coordinate of the intersection of that line with the lines y=0, y=1 (see the square (■) in Figure 4).

[0062] Next, the distribution function estimation unit 32 calculates the X coordinates of both ends of interval 2W, which is obtained by doubling interval W, whose ends are the X coordinates of the intersection points, and widening it around its midpoint (see the black circle (●) in Figure 4). Furthermore, the distribution function estimation unit 32 can determine the smallest interval that includes these X coordinates and whose ends are integers as the age interval to be subjected to the age conversion process for the target test item. The distribution function estimation unit 32 can convert the determined age interval so that its ends are 0 and 1, respectively.

[0063] 1 again, in the control unit 15, the implementation test item setting unit 33 sets the test items to be implemented from among the test items included in the test item data 21. For example, the implementation test item setting unit 33 can set multiple test items selected by the inspector (for example, input from the user terminal 4) as the implementation test items.

[0064] Here, the developmental age estimation device 2 can calculate in advance the age range for each test item (i.e., the age range in which a significant change occurs in the pass rate for each test item) based on the cumulative distribution function F(x;α,β) obtained for each of the multiple test items. The developmental age estimation device 2 can then generate a test item confirmation screen showing the age range calculated for each test item, as shown in FIG. 5, for example. When the tester selects the test item to be performed, the developmental age estimation device 2 can transmit the test item confirmation screen to an external device (here, the user terminal 4) and display it on its display.

[0065] The test item confirmation screen displays a list of each test item (see test item numbers 313 to 382 in Figure 5) along with a graphic (here, a bar for displaying the age range, hereinafter referred to as the "age range display bar") indicating the range of the age range covered by each test item. The length of the age range display bar is set to correspond to a specific range of pass rates (for example, 2.5% to 97.5%). The age range display bar also displays a symbol (here, a black circle (●)) indicating the age at which the pass rate is greatest.

[0066] By referring to the length of the age range display bar and the horizontal axis value indicating the age displayed below it, the examiner can understand the range of the age range that each test item targets (i.e., that is effective for estimating the developmental age). Furthermore, by checking the length of the age range display bar and the position of the symbol indicating the age at which the pass rate is highest, the examiner can determine whether the test item to be selected is appropriate for the current test. The examiner can set the desired test item (e.g., a letter) as the test item to be performed by selecting it (e.g., by touching the touch panel display) on the test item confirmation screen. Alternatively, a similar method can be used to perform a preliminary evaluation and only use test items that are determined to be appropriate for subsequent processing.

[0067] The test items to be performed do not necessarily have to be selected by the tester. For example, the test item setting unit 33 may randomly set test items to be performed from the test items included in the test item data 21, or may use a specific algorithm that sequentially selects optimal test items to be performed in accordance with the estimated developmental age.

[0068] In the control unit 15, the test result acquisition unit 34 acquires the test results for each test item selected for testing the child to be tested. For example, an examiner can conduct a test for each test item and input the test results to the developmental age estimation device 2 from the user terminal 4. However, the test results may also be input by an automatic testing device instead of the examiner. For example, the automatic testing device may have a trained model prepared in advance for the test and acquire the test results based on video footage of the child's movements for each test item. The test results acquired by the test result acquisition unit 34 are sequentially stored in the storage unit as test result data 23.

[0069] The test result data 23 includes, for example, an identifier indicating "achieved" or "not achieved" for each implemented test item. However, the test result data 23 may also include an identifier indicating "partial achievement" (i.e., a state in which it is difficult to determine whether the test item has been completely achieved) for each implemented test item.

[0070] In the control unit 15, the developmental age estimation function generation unit 35 generates a developmental age estimation function based on data on the cumulative distribution function F(x;α,β) for two or more implemented test items used in the test of the child being tested and the test results for each implemented test item.

[0071] Regarding the generation of the developmental age estimation function, the estimated passing rate distribution function Ei(m) for each test item by age is defined as follows:

[0072]

[0073] However, m: age in months lower :The lower limit of the age range (integer value) for each test item upper : Upper limit of age in months for each test item (integer value)

[0074] Also, the probability function Pi(m) of the passing rate according to the test results is defined as follows: However, it may be omitted in the case of "partial achievement".

[0075]

[0076] Where, i: Index number of each test item

[0077] The developmental age estimation function P(m) can be expressed as the following equation (3) using the above-mentioned probability function Pi(m) based on Bayes' theorem.

[0078]

[0079] Where, n: number of test items to be performed M lower : The minimum lower limit of the age range for each test item (integer value) upper : Maximum upper age limit (integer value) for each test item​​​

[0080] In the control unit 15, the developmental age estimation unit 36 ​​can estimate the developmental age of the child being tested based on the mode of the distribution of values ​​obtained by the developmental age estimation function P(m) (i.e., the conditional probability of obtaining given test items and their implementation results at each age). The probability distribution based on the developmental age estimation function P(m) produces a peak (i.e., the mode), as shown in FIG. 6 , for example, and the developmental age estimation unit 36 ​​can estimate the developmental age of the child being tested based on the age value corresponding to the peak. When indicating the estimated developmental age, the developmental age estimation unit 36 ​​may output the age value corresponding to the peak, or may output a predetermined range including the age value corresponding to the peak (e.g., the age value corresponding to the peak is used as the median).

[0081] The position of the peak of the probability distribution based on the developmental age estimation function P(m) depends on the likelihood function corresponding to the numerator in formula (3). Therefore, the developmental age estimation function P(m) shown in formula (3) may be expressed by only the likelihood function, omitting the denominator.

[0082] Furthermore, if the test results for all implemented test items are "achieved," it is not possible to obtain the peak estimated value of the developmental age or the upper limit of the estimated range, but it is possible to obtain the lower limit of the estimated range of the developmental age. If the test results for all implemented test items are "not achieved," it is not possible to obtain the peak estimated value of the developmental age or the lower limit of the estimated range, but it is possible to obtain the upper limit of the estimated range of the developmental age. In either case, the developmental age estimation unit 36 ​​can output the above results to the display unit 13 or the user terminal 4, but may also output an error message indicating that an appropriate estimation result could not be obtained.

[0083] Furthermore, when it is determined that there is a contradiction in the test results, the developmental age estimation unit 36 ​​can output an error message to the display unit 13 or the user terminal 4. For example, in the test items shown in Fig. 5, when the result of an implemented test item targeting a certain age range is "not achieved" and the result of an implemented test item targeting a higher age range than the not-achieved implemented test item is "achieved", the developmental age estimation unit 36 ​​can determine that there is a contradiction in the test results.

[0084] At least some of the functions of the units 31-36 in the control unit 15 can be realized by one or more processors executing predetermined control programs. The control unit 15 can also comprehensively control the operation of the developmental age estimation device 2.

[0085] In the developmental age estimation system 1 having the above configuration, the examiner can access the developmental age estimation device 2 from the user terminal 4 and execute the developmental age estimation process. In the developmental age estimation process, the examiner can input (i.e., select) desired test items (i.e., implemented test items) to the developmental age estimation device 2 from the user terminal 4. Furthermore, the examiner can input the test results of each implemented test item to the developmental age estimation device 2 from the user terminal 4. At this time, the examiner can input the test results to the developmental age estimation device 2 while sequentially implementing multiple implemented test items on the child to be tested (i.e., while sequentially obtaining the test results of each implemented test item).

[0086] Once the examiner has completed inputting the test results, the developmental age estimation device 2 generates a developmental age estimation function based on the data of the cumulative distribution function F(x;α,β) for each performed test item and the test results for each performed test item. The developmental age estimation device 2 then estimates the developmental age of the child being tested based on the mode of the probability distribution obtained by the generated developmental age estimation function. Furthermore, the developmental age estimation device 2 transmits the estimated developmental age to the user terminal 4 and displays it on the display of the user terminal 4.

[0087] In addition, when the user terminal 4 functions as a developmental age estimation device, the above-mentioned developmental age estimation process can be entirely executed by the user terminal 4.

[0088] In this way, the developmental age estimation system 1 generates a developmental age estimation function P(m) based on data on the cumulative distribution function F(x;α,β) of the pass rate for the implemented test items, with age as a variable, and the test results for each of those implemented test items, and estimates the developmental age of the child being tested based on that developmental age estimation function P(m).This makes it possible to obtain highly objective estimation results regarding developmental age while increasing the degree of freedom in the test items.

[0089] While the present disclosure has been described above based on specific embodiments, these embodiments are merely examples, and the present disclosure is not limited to these embodiments. The components of the developmental age estimation device, developmental age estimation method, and developmental age estimation program shown in the above embodiments are not necessarily all essential, and at least those skilled in the art can select appropriate components without departing from the scope of the present disclosure.

[0090] For example, in the present disclosure, the "monthly age" indicating a child's developmental stage does not necessarily have to be expressed in months, but may be expressed in years or years and months. Furthermore, the month-age intervals do not necessarily have to be integer values, but may include decimal values. Furthermore, in this embodiment, a beta distribution is used as a continuous probability distribution for the pass rate of each test item, but other probability density distribution functions can also be used as substitutes as long as the parameters specifying the distribution can be uniquely and appropriately determined using existing pass rate data.

[0091] 1: Developmental age estimation system 2: Developmental age estimation device 3: Communication network 4: User terminal 11: Communication unit 12: Input unit 13: Display unit 14: Memory unit 15: Control unit 21: Test item data 22: Distribution function data 23: Test result data 24: Developmental age estimation function data 31: Test item data collection unit 32: Distribution function estimation unit 33: Test item setting unit 34: Test result acquisition unit 35: Developmental age estimation function generation unit 36: Developmental age estimation unit

Claims

1. A developmental age estimation device that estimates the developmental age of a child, comprising: a processor that executes a process to estimate the developmental age of a child to be tested based on test results for a plurality of test items; and a storage device that stores data regarding a continuous probability distribution that indicates the pass rate for each of the plurality of test items, with age in months within a predetermined range as a variable, wherein the processor generates a developmental age estimation function based on the data regarding the continuous probability distribution for two or more implemented test items of the plurality of test items that were used to test the child to be tested, and the test results for each of the implemented test items; estimates the developmental age of the child to be tested based on the mode of the distribution of pass rates obtained by the developmental age estimation function; and outputs the estimated developmental age.

2. The developmental age estimation device of claim 1, wherein the processor acquires data on multiple ages and passing rates corresponding to each of the multiple test items, and generates data on the continuous probability distribution based on the passing rate data.

3. The developmental age estimation device according to claim 2, wherein the processor determines two parameters of a probability density function of a beta distribution based on the data on the passage rate, and generates data relating to the continuous probability distribution based on a cumulative distribution function obtained by integrating the probability density function of the beta distribution.

4. The developmental age estimation device according to claim 3, wherein the processor sets age intervals for the passing rate data for each of the plurality of test items, and converts the age intervals into a range from 0 to 1.

5. The developmental age estimation device of claim 1, wherein the processor sets a probability function of the pass rate for each of the performed test items based on data regarding the continuous probability distribution and the test results, and the developmental age estimation function includes a product of the probability functions for each of the performed test items.

6. The developmental age estimation device according to claim 1, further comprising a display device for displaying the estimation result of the developmental age.

7. A developmental age estimation method using a developmental age estimation device that estimates a child's developmental age, wherein the developmental age estimation device generates a developmental age estimation function based on data regarding continuous probability distributions for two or more implemented test items used in testing the child to be tested, out of a plurality of test items for estimating the developmental age of the child to be tested, and the test results for each of the implemented test items, estimates the developmental age of the child to be tested based on the mode of the distribution of pass rates obtained by the developmental age estimation function, and outputs the estimated developmental age result.

8. A developmental age estimation program that causes a computer to execute a developmental age estimation process for estimating a child's developmental age, the developmental age estimation process including the steps of: generating a developmental age estimation function based on data relating to continuous probability distributions for two or more implemented test items used in testing the child to be tested, out of a plurality of test items for estimating the developmental age of the child to be tested, and the test results for each of the implemented test items; estimating the developmental age of the child to be tested based on the mode of the distribution of pass rates obtained by the developmental age estimation function; and outputting the estimated developmental age result.

Images