Method of predicting precocious puberty based on growth age and providing solution using artificial intelligence model

Abstract

A method for predicting precocious puberty based on growth age and providing a solution using an artificial intelligence model trained on target data of a first Age of Peak Height Velocity (APHV) at which the growth rate of a plurality of sample subjects reaches a maximum value according to exemplary embodiments of the present invention, wherein the method may include: receiving biological data of a subject to be measured; extracting predicted Age of Peak Height Velocity (APHV) data, which is the age at which the growth rate is expected to reach a maximum value, using the biological data of the subject to be measured; predicting precocious puberty of the subject to be measured based on the predicted APHV; and providing a precocious puberty management solution based on the result of the precocious puberty prediction.

Description

Technology Field

[0001] The present invention relates to a method for classifying growth stages and predicting precocious puberty based on Age of Peak Height Velocity (APHV) data, which is the age at which the growth rate reaches its maximum value extracted from biological data of growing children and adolescents, and providing a growth management solution based on the classified growth stages and whether the predicted precocious puberty applies. Background Technology

[0002] With the recent advancement of artificial intelligence technology, AI technologies are being applied across various fields, and methods are being developed and used to generate additional information by extracting inherent features from data through neural network models, replacing conventional data processing methods.

[0003] Neural network models used for artificial intelligence can detect and recognize features within input data more quickly and accurately compared to general data processing through learning. Recently, AI technology has moved beyond simply tracking and detecting objects to being applied to learn from past history, predict the future, or derive current features that reflect time-series changes.

[0004] Among these, predictive analytics is a technology within the fields of statistics and data mining that extracts information from data and uses it to predict trends and behavioral patterns. Based on the information obtained from data, such predictive analytics can be applied to all areas requiring decision-making. The core of predictive analytics lies in understanding the relationships between variables and then predicting unknown variables.

[0005] To this end, various approaches are being used depending on data characteristics and the prediction target.

[0006] Among the various fields requiring predictive analysis, there is the field of physical growth in adolescents. There is significant interest among parents and adolescents regarding when height growth will occur and how much they will grow.

[0007] Conventional methods for predicting height growth involve predicting growth plates by X-ray imaging or analyzing the relationship with genetic and environmental factors (Registered Patent Publication No. 10-2075743, Registered Patent Publication No. 10-1866208), or they also propose methods for converting physical data from sample subjects with different measurement times or frequencies into a format suitable for training a growth prediction model (Registered Patent Publication No. 10-2198302).

[0008] While conventional methods for predicting physical growth in children and adolescents have been presented, research on methods for predicting the risk of occurrence and providing solutions for issues such as precocious puberty and obesity that may accompany growth, as mentioned above, is currently insufficient.

[0009] Furthermore, since children and adolescents have growth stages with distinct characteristics, considering this can enhance the reliability of solutions provided through predicted data and analysis.

[0010] Meanwhile, regarding conventional technologies disclosed to date, various methods for predicting growth by directly inputting the physical or biological data of children and adolescents into a predetermined growth prediction tool have been disclosed. However, these conventional technologies have the disadvantage that it is difficult to provide personalized solutions because they predict growth based solely on general indicators such as past and present height, weight, and BMI, without considering individual growth characteristics such as the growth rate of each child or adolescent or whether they have reached a growth stage faster than other sample subjects.

[0011] In addition, the SITAR (SuperImposition by Translation And Rotation) methodology has emerged in relation to height growth rate; however, there is a problem in that only ex post estimation is possible because measurements across the entire growth period are required to estimate the growth rate curve using the SITAR methodology.

[0012] Meanwhile, conventional height growth prediction models use height, weight, body composition, their quantiles, and current quantile-based benchmark growth rates as input variables to predict the height growth curve using an LGBM model. However, there is a possibility of upward bias in the estimation model in specific datasets where the proportion of observations is high due to higher height quantiles in later ages. Additionally, although conventional height growth prediction models have 52 body composition-related variables, they utilize only 8 variables centered on height, weight, and body mass, which has the disadvantage of low prediction accuracy.

[0013] Consequently, although the growth rate trend of sample subjects is important for height prediction in conventional height growth prediction models, information on past measurements is not reflected in the estimation model; therefore, it is necessary to measure tracking growth rate that incorporates past information.

[0014] Furthermore, the importance of a method utilizing these tracking growth rates to estimate biological growth age—that is, the age indicating the biological age of the body based on the state of growth—is emerging, rather than actual age, which is the temporal actual age calculated uniformly from the time of birth. Prior art literature

[0015] Registered Patent Publication No. 10-2075743 Registered Patent Publication No. 10-1866208 Registered Patent Publication No. 10-2198302 The problem to be solved

[0016] One of the various objectives of the present invention is to provide a method for classifying growth stages and predicting precocious puberty based on Age of Peak Height Velocity (APHV) data, which is the age at which the growth rate of children and adolescents reaches its maximum value, and then providing a growth management solution based on the classified growth stages and whether the predicted precocious puberty applies.

[0017] One of the various objectives of the present invention is to provide a method, apparatus, and computer program that predicts growth, such as height, obesity, and disease, based on the growth stages of children and adolescents using a growth age-based growth management model generated through artificial intelligence learning, and provides customized solutions for each growth stage. means of solving the problem

[0018] A method for predicting precocious puberty based on growth age and providing a solution using an artificial intelligence model trained on target data of a first Age of Peak Height Velocity (APHV) at which the growth rate of a plurality of sample subjects reaches a maximum value according to exemplary embodiments of the present invention, wherein the method may include: receiving biological data of a subject to be measured; extracting predicted Age of Peak Height Velocity (APHV) data, which is the age at which the growth rate is expected to reach a maximum value, using the biological data of the subject to be measured; predicting precocious puberty of the subject to be measured based on the predicted APHV; and providing a precocious puberty management solution based on the result of the precocious puberty prediction.

[0019] A method for predicting precocious puberty based on growth age and providing a solution using an artificial intelligence model according to exemplary embodiments of the present invention may further include the step of classifying the growth stage of the subject to measurement into one of a plurality of growth stages based on the predicted APHV data; wherein the plurality of growth stages may include a general growth stage, a rapid growth stage, a decelerated growth stage, a slowed growth stage, and a growth plate stage.

[0020] The above-mentioned precocious puberty prediction step may include: a step of determining the current growth stage of the subject being measured; and a step of determining the likelihood of precocious puberty occurring in the subject being measured; and the step of determining the likelihood of precocious puberty occurring may be controlled to determine that the subject being measured does not have precocious puberty if the subject being measured’s current growth stage corresponds to any one of the decelerated growth stage, the slowed growth stage, and the growth plate stage.

[0021] The step of determining the possibility of precocious puberty above can be controlled to determine that the subject has a possibility of precocious puberty if the subject's current growth stage corresponds to either the general growth stage or the rapid growth stage.

[0022] The above general growth period may be a growth stage with an end point that is earlier than the predicted APHV by the first growth period, and the above rapid growth period may be a growth stage with a start point that is earlier than the predicted APHV by the first growth period and an end point that is the predicted APHV.

[0023] The above precocious puberty prediction step can be controlled to determine that the subject has precocious puberty if the predicted APHV of the subject is prior to a specific point in time.

[0024] The above precocious puberty prediction step can be controlled to determine whether precocious puberty applies differently depending on the gender among the biological data of the subject received.

[0025] In the above precocious puberty prediction step, if the gender of the subject being measured is determined to be female and the predicted APHV corresponds to a time point prior to the first time point, the system may be controlled to determine that the subject being measured has precocious puberty.

[0026] The above first point in time may be 8 years of age.

[0027] In the above precocious puberty prediction step, if the gender of the subject being measured is determined to be male and the predicted APHV corresponds to a time point prior to the second time point, control can be exercised to determine that the subject being measured corresponds to that.

[0028] The above second point in time may be 9 years of age.

[0029] The above precocious puberty prediction step can be controlled to further determine the likelihood of precocious puberty based on the degree of physical secondary sexual characteristics expression among the biological data of the subject received above.

[0030] The above precocious puberty prediction step can be controlled to further determine the likelihood of precocious puberty based on sex hormone measurement data among the biological data of the subject received above. Effects of the invention

[0031] The method for predicting precocious puberty based on bio-data using artificial intelligence and providing a solution according to exemplary embodiments of the present invention estimates a growth rate curve by applying a tracking growth rate extracted from past information to a statistical methodology, extracts Age of Peak Height Velocity (APHV) data—which is the age at which the growth rate reaches its maximum value—from the growth rate curve, and utilizes the APHV data for predicting precocious puberty; thereby, the reliability of various prediction models, such as an integrated height growth prediction model, a precocious puberty prediction model, and an obesity prediction model constructed using the classified growth stages, can be maximized.

[0032] In addition, according to various embodiments of the present invention, a growth stage classification method constructed through artificial intelligence learning can accurately predict whether a child or adolescent has precocious puberty by considering their growth stage, and can provide solutions necessary for the prevention of precocious puberty by considering each growth stage. Brief explanation of the drawing

[0033] FIG. 1 is a configuration diagram illustrating the configuration of a growth age-based precocious puberty prediction and solution provision device using an artificial intelligence model according to exemplary embodiments of the present invention. FIG. 2 is a diagram showing predicted elongation and target elongation by growth stage according to exemplary embodiments of the present invention. FIG. 3 is a flowchart illustrating a method for predicting growth age-based precocious puberty and providing a solution using an artificial intelligence model according to exemplary embodiments of the present invention. Figure 4 is a diagram showing multiple first growth rate curves representing the growth rate of height relative to actual age using time-series biometric data of sample subjects. Figures 5 and 6 are figures showing the APHV estimation error according to the age in months for girls and boys, respectively. Figures 7 and 8 are figures showing the importance of APHV predictors for women and men, respectively. Figure 9 is a diagram showing the importance of variables in a conventional growth prediction model for women and men, and Figure 10 is a diagram showing the importance of variables in a growth prediction model of the present invention. Specific details for implementing the invention

[0034] Specific embodiments of the present invention will be described below. The following detailed description is provided to facilitate a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, this is merely illustrative and the present invention is not limited thereto.

[0035] In describing the embodiments of the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such detailed descriptions may unnecessarily obscure the essence of the present invention. Furthermore, the terms described below are defined in consideration of their functions within the present invention, and these may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification. Terms used in the detailed description are intended merely to describe the embodiments of the present invention and should not be limiting in any way. Unless explicitly stated otherwise, expressions in the singular form include the meaning of the plural form. In this description, expressions such as "include" or "comprise" are intended to refer to certain characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof, and should not be interpreted to exclude the existence or possibility of one or more other characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof other than those described.

[0036] In addition, terms such as first, second, A, B, (a), (b), etc. may be used when describing the components of the embodiments of the present invention. These terms are used merely to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the terms.

[0037] In the exemplary embodiments of the present invention, the term "children and adolescents" may be understood as a concept encompassing the period of human growth. More specifically, the term "children and adolescents" referring to the sample subjects in the exemplary embodiments of the present invention is defined below through the meanings of infant, child, adolescent, toddler, and pediatric.

[0038] Infants are a continuation of the neonatal period, a period during which they grow by sucking on their mother's nipple until two years after birth, and the experiences of nutrition, caress, and excretion during this period influence their general tendencies thereafter. Children are generally defined as individuals in the age group of 6 years or older but under 13 years, and in a broader sense, they may include toddlers (ages 1 to 5).

[0039] Adolescents refer to the intermediate stage between childhood and youth, generally meaning individuals aged 13 to under 19 years based on full age. Infants may refer to individuals from one year of age to five years of full age. Children may generally refer to children up to the age of 15.

[0040] Therefore, the term "children and adolescents" referring to the sample subjects mentioned above may mean, in a narrow sense, the period of 5 years of age and older and 19 years of age, including children and adolescents, and in a broad sense, the period that includes all general periods of physical growth, from infancy to adolescence.

[0041] FIG. 1 is a configuration diagram illustrating the configuration of a growth age-based precocious puberty prediction and solution provision device using an artificial intelligence model according to exemplary embodiments of the present invention.

[0042] Referring to FIG. 1, a growth age-based precocious puberty prediction and solution provision device using artificial intelligence according to exemplary embodiments of the present invention may include a bio-data input unit (10), a preprocessing unit (20), a growth rate curve estimation unit (30), a first APHV data extraction unit (40), a first APHV data learning unit (50), a predicted APHV data extraction unit (60), a second APHV data extraction unit (70), a growth age calculation unit (80), a growth stage classification unit (90), a precocious puberty prediction unit (100), a solution generation unit (110), and a display unit (120).

[0043] A bio-data-based growth stage classification model using artificial intelligence according to exemplary embodiments of the present invention can receive time-series physical information about a sample subject through a bio-data input unit (10). The physical information of the sample subject may include not only basic information such as grade (or age), gender, and height, but also additional information such as weight, protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, and hip circumference. Such physical information is merely an example to aid in understanding the present invention, and the present embodiment is not limited thereto; it is understood that the types of information constituting the physical information can be varied according to the embodiment.

[0044] The time-series physical information of the above sample subject may be continuous information or discontinuous information, but may be information included in at least one of the periods corresponding to the growth stages of FIG. 2.

[0045] More specifically, the time-series physical information of the sample subjects may vary in the time and frequency of collection. For example, in the case of the first sample subject, physical information measured up to 8 to 12 years of age, which is part of the childhood and adolescent period, may exist, and in the case of the second sample subject, physical information measured irregularly, such as at 8, 10 to 12, and 15 years of age. Additionally, in the case of the third sample subject, physical information measured multiple times within a certain period (within the period of any one of the multiple growth stages in Fig. 2), whereas in the case of the fourth sample subject, physical information measured only once within a certain period (within the period of any one of the multiple growth stages in Fig. 2).

[0046] As described above, depending on the time and frequency of collection, the physical information of the sample subject may be included in two or more of the growth stages of FIG. 2 (the first sample subject, the second sample subject), but there may also be cases where it is not (the third sample subject, the fourth sample subject).

[0047] The preprocessing unit (20) can be controlled to perform preprocessing on the time-series biometric data of the sample subjects.

[0048] In exemplary embodiments, the preprocessing unit (20) may be performed by determining all biometric data of a sample subject for which biometric data collected during a specific growth period does not exist as noise and removing it. This is intended to improve the prediction accuracy of the biometric data-based APHV estimation model according to the present invention and may not be applied when sufficient data has been accumulated. In this case, instead of determining all biometric data of a sample subject for which biometric data collected during a specific growth period does not exist as noise and removing it, preprocessing may be performed by supplementing or additionally generating some biometric data through various methods such as artificial intelligence models and big data analysis.

[0049] Meanwhile, the biometric data input unit (10) may be controlled to receive more body information of the subject for measurement, in addition to receiving time-series body information of the sample subject, for which APHV is to be estimated. At this time, the body information of the subject for measurement may include not only basic information such as grade (or age), gender, and height, but also additional information such as weight, protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, and hip circumference.

[0050] The growth rate curve estimation unit (30) can be controlled to estimate multiple first growth rate curves representing the growth rate of height relative to the actual age of each of the multiple sample subjects using time-series biometric data of the sample subjects.

[0051] In exemplary embodiments, the estimation of the first growth rate curve can be performed by extracting age data and height data from the time-series biometric data of the sample subjects and applying them to a curve transformation model that uses the age data and the height data as input variables.

[0052] At this time, the type of the curve transformation model is not particularly limited. That is, the curve transformation model may be a model constructed using a polynomial function, for example, the curve transformation model may be a model constructed using Equation 1.

[0053] [Mathematical Formula 1]

[0054]

[0055] Here, y it is α i , β i and γ i is a random correction value for adjusting the vertical shift, horizontal shift, and slope of the curve, respectively, h is a specific function related to height data, and t can be age data.

[0056] However, the concept of the present invention is not necessarily limited thereto, and may be a module constructed using a polynomial function other than the above mathematical formula 1.

[0057] The first APHV data extraction unit (40) can be controlled to extract first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate reaches a maximum value for each of the plurality of first growth rate curves.

[0058] The above first APHV data can be used to construct a growth stage diagnosis and estimation model and to derive the growth age, and the above growth age and tracking growth rate can ultimately be used to construct various prediction models, such as an integrated height growth prediction model, a precocious puberty prediction model, and an obesity prediction model.

[0059] Meanwhile, conventional height growth prediction models use height, weight, body composition, their quantiles, and current quantile-based benchmark growth rates as input variables to predict the height growth curve using an LGBM model. However, there is a possibility of upward bias in the estimation model in specific datasets where the proportion of observations is high due to higher height quantiles in later ages. Additionally, although conventional height growth prediction models have 52 body composition-related variables, they utilize only 8 variables centered on height, weight, and body mass, which has the disadvantage of low prediction accuracy.

[0060] In other words, although the growth rate trend of a sample is important for height prediction in conventional height growth prediction models, information on past measurements is not reflected in the estimation model; therefore, it is necessary to measure the tracking growth rate that incorporates past information. Accordingly, the bio-data-based APHV estimation model using artificial intelligence according to exemplary embodiments of the present invention is characterized by estimating a growth rate curve by applying a statistical methodology to the tracking growth rate extracted from past information, extracting APHV (Age of Peak Height Velocity) data—the age at which the growth rate reaches its maximum value—from the growth rate curve, and utilizing the APHV data in constructing various prediction models, such as an integrated height growth prediction model, a precocious puberty prediction model, and an obesity prediction model.

[0061] The first APHV data learning unit (50) can be controlled to input the first APHV data into an artificial intelligence model that uses the target data for learning.

[0062] The predicted APHV data extraction unit (60) can be controlled to extract predicted APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate of the subject is expected to reach its maximum value, by applying the biological data of the subject to be measured to an artificial intelligence model trained with the first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate of the plurality of sample subjects reaches its maximum value, as target data.

[0063] The second APHV data extraction unit (70) can be controlled to extract the second APHV data, which is the average value of the first APHV data. In exemplary embodiments, the second APHV data extraction unit (70) can be controlled to extract the second APHV data through an average value calculation algorithm that adds all observations and divides by the number of observations.

[0064] The growth age calculation unit (80) can be controlled to calculate the growth age of the subject to measurement based on the second APHV data, which is the average value of the first APHV data, and the predicted APHV.

[0065] At this time, the growth age calculation unit (80) can be controlled to calculate the growth age of the subject to measurement using the following mathematical formula 2, and

[0066] [Mathematical Formula 2]

[0067] GA i '= (CA i - APHV i ') + APHV G

[0068] Here, GA i ' is the estimated growth age of the subject being measured, and CA i is the chronological age (calendar age) of the subject being measured, and APHV i ' is the predicted APHV data including the estimated and predicted APHV values ​​of the above-mentioned measurement subject, and APHVG The second APHV data may be a representative value or average value of the first APHV data derived from the training data group.

[0069] In other words, conventional growth age estimation models generally calculate growth age using bone age, the degree of opening / closing of the growth plate, etc., but this has the disadvantage that objectivity is not guaranteed and accuracy is low because X-ray measurement of the bone or growth plate is absolutely necessary, and the growth age may be measured differently depending on the entity analyzing the X-ray of the bone or growth plate.

[0070] In contrast, the growth age estimation model based on bio-data using artificial intelligence according to exemplary embodiments of the present invention estimates a growth rate curve by applying a tracking growth rate extracted from past information to a statistical methodology, extracts Age of Peak Height Velocity (APHV) data—the age at which the growth rate reaches its maximum value—for the growth rate curve, and utilizes the APHV data to construct a growth age estimation model. Therefore, there is no need to perform additional processes such as X-ray measurement. Furthermore, since the growth age is determined by applying accurate numerical values ​​to a pre-set mathematical formula, there is no possibility that the growth age will be measured differently depending on the subject. Accordingly, the objectivity of the growth age estimation can be guaranteed, and there is an advantage of high accuracy.

[0071] The growth stage classification unit (90) can be controlled to classify the growth stage of the subject being measured into one of a plurality of growth stages based on the extracted predicted APHV (Age of Peak Height Velocity) data.

[0072] The growth stages classified by the growth stage classification unit (90) will be described in detail later with reference to FIG. 2 and FIG. 3.

[0073] The precocious puberty prediction unit (100) can be implemented as an artificial intelligence with a Recursive Neural Network (RNN) structure that can utilize not only current values ​​but also time-series values ​​as a type of prediction model. For example, the prediction model can be implemented with an architecture such as a Long Short Term Memory (LSTM) or Gated Recurrent Units (GRU), which are recurrent neural networks. Of course, various other conventional artificial intelligence architectures can also be applied to the prediction model of this embodiment.

[0074] In exemplary embodiments, the precocious puberty prediction unit (100) may be controlled to determine the current growth stage of the subject being measured and to determine the likelihood of precocious puberty occurring in the subject being measured.

[0075] Specifically, the precocious puberty prediction unit (100) can be controlled to determine that the subject has a possibility of having precocious puberty if the subject's current growth stage corresponds to either the general growth stage or the rapid growth stage, and can be controlled to determine that the subject does not have precocious puberty if the subject's current growth stage does not correspond to either the general growth stage or the rapid growth stage.

[0076] More specifically, the precocious puberty prediction unit (100) can be controlled to determine that the subject has precocious puberty if the predicted APHV of the subject is prior to a specific point in time.

[0077] Meanwhile, the precocious puberty prediction unit (100) may be controlled to determine whether precocious puberty applies differently depending on the gender among the biological data of the subject received above.

[0078] In one embodiment, the precocious puberty prediction unit (100) may be controlled to determine that the subject has precocious puberty if the gender of the subject is determined to be female and the predicted APHV corresponds to a first time point. At this time, the first time point may be 8 years of age.

[0079] In another embodiment, if the gender of the subject being measured is determined to be male and the predicted APHV corresponds to a second time point, the subject being measured may be controlled to be determined to be such. In this case, the second time point may be 9 years of age.

[0080] Additionally, the precocious puberty prediction unit (100) may be controlled to further determine the likelihood of precocious puberty based on the degree of physical secondary sexual characteristics expression among the biological data of the subject received above. In exemplary embodiments, the precocious puberty prediction unit (100) may be controlled to further determine the likelihood of precocious puberty based on sex hormone measurement data among the biological data of the subject received above.

[0081] The solution generation unit (110) can generate a precocious puberty management solution for the subject of measurement according to the classified growth stage, and the precocious puberty management solution will be explained with reference to FIG. 2.

[0082] Generally, the prediction of precocious puberty can be performed based on time-series physical information of the subject being measured, based on physical information corresponding to the general growth stage (301) among multiple growth stages, and the management solution for precocious puberty can be provided in a way that lowers the growth rate in multiple growth stages.

[0083] More specifically, when the subject is in a general growth stage (301), a solution for reducing the subject's growth prediction value (P) can be provided. The growth prediction value (P) is a value corresponding to the y-axis in FIG. 2, and the solution for reducing the growth prediction value (P) can be provided to the subject through various display units (120) for the expected target value (G) of the y-axis.

[0084] Examples of solutions provided through the above display unit (120) may include current height, predicted height, degree of obesity, body fat mass, skeletal muscle mass, protein mass, mineral mass, amount of sleep, amount of exercise, nutritional information, lifestyle habits, posture, etc. Each indicator may be displayed in stages such as caution, normal, good, etc., based on a preset range, or may be displayed as a level.

[0085] Additionally, the current status, customized solutions, and precautions for each indicator can be displayed. The current status can be displayed in steps or levels based on the target value (G), and the customized solutions may include details on adjusting protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), and basal metabolic rate to reach the current target value (G) based on the entered body information.

[0086] The precautions may include information on adjusting currently deficient protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, etc., based on the entered body information.

[0087] In addition, if the subject being measured corresponds to the rapid growth stage (303), a solution can be provided to reduce the duration of the subject being measured's rapid growth stage (303).

[0088] By reducing the duration of the rapid growth stage (303), the rapid growth stage (303) can generally be defined as a period that begins when secondary sexual characteristics start to appear and ends when secondary sexual characteristics are completed as described above. However, if the subject being measured is determined to be in a precocious stage through the prediction unit (50), the subject being measured is in a case where secondary sexual characteristics have already started in the general growth stage (301), and a solution can be provided to accelerate the time when secondary sexual characteristics are completed. In other words, various solutions to narrow the range of the x-axis corresponding to the rapid growth stage (303) in FIG. 2 can be provided to the subject being measured through the display unit (120).

[0089] By doing so, the progression of precocious puberty can be slowed down by reducing the rate of height increase. However, since the increase in height may not be distinct if the rate of height increase is reduced too much, the above target value (G) can be learned to be set within a predetermined range based on the value (P) predicted by precocious puberty.

[0090] The above-described measurement subject may include physical information considered when the subject is in a general growth stage (301), and may include information on the adjustment of indicators that can alleviate, in particular, cases where sex hormones increase abnormally.

[0091] Additionally, if the subject being measured corresponds to the deceleration growth stage (305), a solution for adjusting the duration of the subject being measured's deceleration growth stage (305) can be provided. The adjustment of the growth stage duration can be divided into cases where the subject being measured's physical information is located at the beginning of the deceleration growth stage (305) and cases where it is located in the middle to late part of the deceleration growth stage (305) among the growth stages classified based on the input physical information of the subject being measured.

[0092] The criteria for distinguishing the beginning and middle stages of the aforementioned deceleration growth stage (305) may be based on a predetermined range corresponding to the rapid growth stage (303) to the deceleration growth stage (305) based on the x-axis in FIG. 2, or based on whether secondary sexual characteristics have been completed based on the input body information of the subject being measured, if it has not been completed, it may be classified as the beginning of the deceleration growth stage (305), and if it has been completed, it may be classified as the middle stage of the deceleration growth stage (305).

[0093] Preferably, based on the input body information of the subject being measured, it is possible to determine whether secondary sexual characteristics have been completed and whether the current body information of the subject being measured is located at the beginning or middle-to-late part of the deceleration growth stage (305). If it is not possible to determine whether secondary sexual characteristics have been completed based on the input body information of the subject being measured, it is possible to determine whether the body information of the subject being measured is located at the beginning or middle-to-late part of the deceleration growth stage (305) based on a predetermined range corresponding to the rapid growth stage (303) to the deceleration growth stage (305).

[0094] Meanwhile, if the input body information of the subject being measured is located at the beginning of the deceleration growth stage (305), a time adjustment solution can be provided to accelerate the entry into the deceleration growth stage (305). As described above, since secondary sexual characteristics are being completed at the time of transition from the rapid growth stage (303) to the deceleration growth stage (305), a solution can be provided to accelerate the time when secondary growth is completed, and this may be similar to the solution provided when the subject being measured corresponds to the rapid growth stage (303). In other words, various solutions to move the range of the x-axis corresponding to the deceleration growth stage (305) in FIG. 2 to the left can be provided to the subject being measured through the display unit (120). In this case, the range of the deceleration growth stage (305) may increase depending on the body information of the subject being measured, or the range may decrease as the rapid growth stage (303) increases.

[0095] In addition, if the input body information of the subject being measured is located in the mid-to-late part of the deceleration growth stage (305), a period adjustment solution can be provided to increase the duration of the deceleration growth stage (305). As described above, the mid-to-late part of the deceleration growth stage (305) generally refers to the time when the subject's growth plates close after secondary sexual characteristics are completed. Generally, after 6 months have passed since entering the deceleration growth stage (305), about 50% of the growth plates close, and when the growth plates close and natural growth stops, the subject enters the no-growth stage (307). In this case, a solution can be provided to increase the duration of the deceleration growth stage (305). In other words, various solutions to expand the range of the x-axis corresponding to the deceleration growth stage (305) in FIG. 2 can be provided to the subject being measured through the display unit (120).

[0096] When the aforementioned subject of measurement corresponds to a general growth stage (301), the body information considered may include, in particular, the adjustment of an indicator that can alleviate the degree of growth plate closure.

[0097] Thus, as described above, in the case of precocious puberty, secondary sexual characteristics generally progress from the general growth stage (301), and it is necessary to reduce the growth rate during the general growth stage (301) and the rapid growth stage (303), but since the increase in final height after becoming an adult may not be distinct, it is necessary to increase the growth rate again during the mid-to-late part of the decelerated growth stage (303) and the growth plate period (307) described later after the secondary sexual characteristics are completed.

[0098] In addition, if the subject being measured is in a slowed growth phase (307), solutions for improving physical function through lifestyle habits, customized exercise, posture correction, and nutrient intake can be provided based on the entered physical information of the subject being measured.

[0099] During the slowed growth period (307), the growth rate slows down and gradually converges to zero before the growth plate closes. Therefore, based on the subject's weight, body fat, body water, muscle mass, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, hip circumference, etc., a solution can be provided to slow down the rate at which the subject's growth plate closes through lifestyle habits, customized exercise, posture correction, etc.

[0100] In addition, if the subject being measured corresponds to a non-growing plate device (309), a solution for improving physical function through lifestyle habits, customized exercise, posture correction, and nutrient intake can be provided based on the input body information of the subject being measured.

[0101] In the case of a non-growth plate device (309), the growth plate closes and natural growth stops, so a solution for improving physical function through lifestyle habits, customized exercise, and posture correction is provided based on the subject's weight, body fat, body water, muscle mass, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, hip circumference, etc., or a solution for improving physical function through nutrient intake is provided based on protein, mineral content, bone tissue (bone density), etc.

[0102] FIG. 2 is a diagram showing predicted elongation and target elongation by growth stage according to exemplary embodiments of the present invention.

[0103] Referring to FIG. 2, the growth stages may include a general growth period (301), a rapid growth period (303), a decelerated growth period (305), a slowed growth period, and a growth plate-free period (309).

[0104] Each growth stage can be classified according to the degree of growth, and the height gained each year varies depending on the stage; even within the same growth stage, the actual height gained can differ depending on the growth type.

[0105] The general growth period (301) usually refers to the period prior to puberty when secondary sexual characteristics appear. Children and adolescents in this period generally have open growth plates, and depending on the growth environment, they generally grow 4 to 5 cm per year in the case of a short growth type and grow 6 to 7 cm per year in the case of a tall growth type. In exemplary embodiments, the general growth period (301) may be defined as the period prior to the onset of rapid pubertal growth in children and adolescents, and may be a growth stage with an end point that is earlier than the predicted APHV by the first growth period. In one embodiment, the first growth period may be a period between 1 year and 2 years, for example, about 1.5 years.

[0106] The rapid growth period (303) is a period when secondary sexual characteristics begin to appear, during which the breasts of women swell and buds form, while the testicles of men enlarge, pubic hair begins to grow, and voice changes occur. The rapid growth period (303) generally lasts for about 2 to 3 years after the general growth period (301) and grows in the range of about 7 to 10 cm per year on average. In exemplary embodiments, the rapid growth period (303) may be defined as a period during which the growth rate increases from the onset of pubertal rapid growth until the APHV, and may be a growth stage with a starting point equal to the first growth period preceding the predicted APHV and an ending point at the predicted APHV. In one embodiment, the first growth period may be a period between 1 and 2 years, for example, about 1.5 years.

[0107] The deceleration period (305) refers to the period when secondary sexual characteristics are being completed. During this period, women can be distinguished by the onset of menstruation, while men can clearly see the changes through pubic hair, voice change, and underarm hair. When the deceleration period (305) begins, the rate of growth drops rapidly compared to the rapid growth period (303). It generally lasts for about 2 to 3 years, and natural growth stops as growth averages within a range of about 5 to 6 cm per year. The growth plates begin to close gradually after the rapid growth period (304), and about 50% close after about 6 months of entering the deceleration period (305). In exemplary embodiments, the decelerated growth period (305) may be defined as a period during which the growth rate gradually decreases from the APHV until the end of the pubertal rapid growth, and may be a growth stage with the predicted APHV as the starting point and a second growth period after the predicted APHV as the ending point. In one embodiment, the second growth period may be a period between one and two years, for example, about 1.5 years.

[0108] The slowing growth period (307) may refer to a period after the rapid growth of puberty and before entering the growth plate period, during which the growth rate approaches zero. In exemplary embodiments, the slowing growth period (307) may be defined as a period during which the growth rate gradually converges to zero after the rapid growth of puberty of a child or adolescent has ended, and may be a growth stage with a starting point that is two years past the predicted APHV and a ending point that is three years past the predicted APHV. In one embodiment, the third growth period may be a period between two and four years, for example, about three years.

[0109] The growth plate period (309) refers to a time when the growth plate has closed, meaning that although the growth period has not completely ended, natural height growth has become difficult. Generally, for women, the growth plate period (309) is entered approximately 1 year and 6 months to 2 years after the onset of menstruation, and for men, the growth plate period (309) is entered approximately 1 year and 6 months to 2 years after the time when body hair grows in the armpits. During the growth plate period (309), the growth plate closes and natural growth stops, but growth may be possible within a range of about 1 to 3 cm by changing bad lifestyle habits and improving physical function through customized exercise, posture correction, and nutrient intake. In exemplary embodiments, the growth plate period (309) may be defined as a period when the growth rate is close to zero after the growth plate has closed, and it may be a growth stage starting at a point that is 3 years past the predicted APHV. In one embodiment, the third growth period may be a period between 2 and 4 years, for example, about 3 years.

[0110] Meanwhile, precocious puberty is generally defined as the appearance of breasts or pubic hair in girls before the age of 8, or the appearance of pubic hair, enlargement of the penis, or enlargement of the testicles by more than 4 mL in boys before the age of 9.

[0111] In normal puberty in girls, hypothalamic-pituitary activation appears first, followed by the secretion of female hormones from the ovaries, which leads to breast development, and other physical changes (pubic hair development, rapid height growth, acne) appearing sequentially.

[0112] In normal puberty in boys, the activation of the hypothalamus-pituitary gland occurs first, followed by testicular enlargement, increased male hormone secretion, and the sequential appearance of other physical changes (pubic hair development, rapid height growth, acne).

[0113] Although the causes of precocious puberty are diverse, generally, sex hormones are secreted at an early age, affecting the body and leading to rapid growth (e.g., height growth). While this condition is more common in girls than boys, cases involving serious pathological causes are more frequent in boys.

[0114] More specifically, in girls, idiopathic cases, where precocious puberty occurs without a malicious underlying disease, account for the largest proportion at 80%, followed by cases caused by ovarian tumors at 15% and cases with cerebral lesions at 5%, whereas in boys, idiopathic cases without a malicious underlying disease account for 50%, cases with lesions in the cerebrum itself account for 20%, adrenal cortical hyperplasia or tumors account for 25%, and testicular tumors account for 5%, showing a distribution that varies depending on the age of onset.

[0115] In summary, precocious puberty can be understood as a group of physical change diseases caused by a wide variety of factors, but generally, it occurs in both boys and girls during the general growth period (301) of FIG. 2, and shows rapid growth during this period, and occurs more frequently in girls than in boys, but the probability of having a serious pathological cause is higher in boys.

[0116] FIG. 3 is a flowchart illustrating a method for predicting precocious puberty based on growth age and providing a solution using an artificial intelligence model according to exemplary embodiments of the present invention.

[0117] Referring to FIG. 3, the method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model according to exemplary embodiments of the present invention may be a method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model trained with a first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate of a plurality of sample subjects reaches a maximum value, as target data. The method may include the steps of receiving biological data of a subject (S10), extracting predicted APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate is expected to reach a maximum value using the biological data of the subject (S20), classifying the growth stage of the subject into one of a plurality of growth stages based on the predicted APHV data (S30), predicting precocious puberty of the subject based on the predicted APHV (S40), and providing a precocious puberty management solution based on the result of the precocious puberty prediction (S50). At this time, the plurality of growth stages may include a general growth period, a rapid growth period, a decelerated growth period, a slowed growth period, and a no-growth period.

[0118] The bio-data input step (S10) can be performed by receiving body information about the subject of measurement through the bio-data input unit (10). At this time, the body information about the subject of measurement may include not only basic information such as grade (or age), gender, and height, but also additional information such as weight, protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, and hip circumference. However, such body information is merely an example to aid in understanding the present invention, and the present embodiment is not limited thereto, and it is understood that the types of information constituting the body information can be varied according to the embodiment.

[0119] In addition, the body information of the subject being measured may be single body information measured once, or body information measured multiple times, that is, information that is continuous in a time series. However, the concept of the present invention is not necessarily limited thereto, and the body information of the subject being measured may be discontinuous in a time series. That is, the collection time and the number of times the body information of the subject being measured is collected may vary.

[0120] In one embodiment, the biometric data of the subject being measured may include at least two time-series biometric data measured at different age groups.

[0121] The predicted APHV extraction step (S20) can be performed using an artificial intelligence model, and the artificial intelligence model is described first as follows.

[0122] Specifically, the artificial intelligence model used in the predicted APHV extraction step (S20) may be an artificial intelligence model trained using the first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate of multiple sample subjects reaches a maximum value, as target data. The artificial intelligence model may be an artificial intelligence model constructed through the steps of: receiving time-series biometric data of multiple sample subjects; estimating multiple first growth rate curves representing the growth rate of height relative to the actual age of each of the multiple sample subjects using the time-series biometric data of the sample subjects; extracting the first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate reaches a maximum value for each of the multiple first growth rate curves; and inputting the first APHV data into an artificial intelligence model that uses the target data for training.

[0123] At this time, the first APHV data may be a set of data obtained by receiving the biometric data of the plurality of sample subjects, estimating a plurality of first growth rate curves representing the growth rate of height relative to the actual age of each of the plurality of sample subjects, and extracting the age at which the growth rate reaches a maximum value for each of the plurality of first growth rate curves.

[0124] Here, the step of estimating the first growth rate curve can be performed by extracting age data and height data from the time-series biometric data of the sample subjects and applying them to a curve transformation model that uses the age data and height data as input variables.

[0125] In exemplary embodiments, the curve transformation model may be a model constructed using a polynomial function.

[0126] In one embodiment, the curve transformation model may be a model constructed using Equation 1.

[0127] [Mathematical Formula 1]

[0128]

[0129] In the above mathematical formula 1, y it is α i , β i and γ i θ, θ, and θ are random correction values ​​for adjusting the vertical shift, horizontal shift, and slope of the curve, respectively, h is a specific function related to height data, and t can be age data.

[0130] Meanwhile, the artificial intelligence model according to the present invention is performed after the step of inputting time-series biometric data of the sample subjects, and may further include a step (not shown) of preprocessing the time-series biometric data of the sample subjects.

[0131] The above preprocessing step can be performed by determining all biometric data of sample subjects for whom biometric data collected during a specific growth period does not exist as noise and removing them.

[0132] In exemplary embodiments, the preprocessing step may be performed by classifying the growth periods of the plurality of sample subjects into a general growth period, a rapid growth period, and a decelerated growth period, and then removing all data of sample subjects for which biometric data corresponding to each of the classified growth stages does not exist as noise.

[0133] In one embodiment, the preprocessing step may be performed by further dividing the growth periods of the plurality of sample subjects into a slowed growth phase and a growth-free phase, and then removing all data of sample subjects for which biodata corresponding to each of the divided growth phases does not exist as noise.

[0134] For example, the above preprocessing step can be performed by classifying the age groups of the plurality of sample subjects into ages 8 to 18, and then removing all data of sample subjects as noise when the difference in input period between adjacent biometric data is 4 years or more.

[0135] Alternatively, the above preprocessing step may be performed by removing all data as noise from sample subjects for whom no biometric data was input during the period between 9 and 14 years among the age groups of the plurality of sample subjects.

[0136] The predicted APHV extraction step (S20) may include a step of estimating the expected shape of the growth rate using the biological data of the subject being measured, and a step of extracting a predicted AOGS (Age of Onset of Growth Spurt), which is the age at which the growth rate of the subject being measured begins to increase, and a predicted APHV (Age of Peak Height Velocity), which is the age at which the growth rate of the subject being measured has a maximum value.

[0137] In exemplary embodiments, in the predicted APHV extraction step (S20), the step of estimating the predicted growth rate of the subject being measured can be performed by generating a graph (hereinafter referred to as the second growth rate curve) representing the predicted growth rate of the subject being measured using a single or multiple data as shown in FIG. 4, and then extracting predicted AOGS data representing the predicted AOGS value and predicted APHV data representing the predicted APHV value from the second growth rate curve.

[0138] In the above description, the predicted APHV extraction step (S20) was described based on the fact that it is performed by generating the second growth rate curve based on the biological data of the subject being measured, and then extracting the predicted AOGS data and the predicted APHV data from the second growth rate curve; however, the concept of the present invention is not necessarily limited thereto. That is, the predicted APHV extraction step (S20) may be controlled to immediately extract the predicted AOGS data and the predicted APHV data through a preset algorithm without the need to generate the second growth rate curve, simply by inputting the biological data of the subject being measured into a growth age estimation model using an artificial intelligence model.

[0139] After the predicted APHV extraction step (S20) is performed, the growth stage classification step (S30) can be performed.

[0140] The growth stage classification step (S30) can be performed by classifying the growth stage of the subject to measurement into one of a plurality of growth stages, for example, a rapid growth stage and a deceleration growth stage, based on the predicted APHV data extracted through the predicted APHV extraction step (S20).

[0141] At this time, the rapid growth period can be defined as a period during which the growth rate gradually increases from the onset of rapid pubertal growth in children and adolescents until the predicted APHV, and the decelerated growth period can be defined as a period during which the growth rate gradually decreases from the predicted APHV until the point at which rapid pubertal growth in children and adolescents ends.

[0142] In exemplary embodiments, the rapid growth phase may be a growth stage with a starting point equal to a first growth period earlier than the predicted APHV and an ending point equal to the predicted APHV, and the deceleration growth phase may be a growth stage with a starting point equal to the predicted APHV and an ending point equal to a second growth period later than the predicted APHV.

[0143] In one embodiment, the first growth period and the second growth period may be set to the same period, for example, the first growth period and the second growth period may each be a period between 1 year and 2 years.

[0144] Additionally, the growth stage may further include a general growth stage, a slowed growth stage, and a no-growth stage, and the growth stage classification step may be performed to classify the growth stage of the subject to measurement into one of the general growth stage, rapid growth stage, decelerated growth stage, slowed growth stage, and no-growth stage based on the predicted APHV data.

[0145] At this time, the above general growth period can be defined as the period before the onset of rapid pubertal growth in children and adolescents, the above slowed growth period can be defined as the period after the end of rapid pubertal growth in children and adolescents during which the growth rate gradually converges to zero, and the above atresia period can be defined as the period when the growth plates of children and adolescents close and the growth rate is close to zero.

[0146] In exemplary embodiments, the general growth period may be a growth stage with an end point that is earlier than the predicted APHV by the first growth period, the slowed growth period may be a growth stage with a start point that is later than the predicted APHV by the second growth period and an end point that is later than the predicted APHV by the third growth period, and the no-growth period may be a growth stage with a start point that is later than the predicted APHV by the third growth period.

[0147] In one embodiment, the third growth period may be set as a period different from the first growth period and the second growth period, for example, the third growth period may be a period between 2 and 4 years.

[0148] Meanwhile, although not illustrated in the drawing, a growth age estimation step (not illustrated) may be further performed between the predicted APHV extraction step (S20) and the growth stage classification step (S30).

[0149] In this case, the above growth age calculation step can be performed using the following mathematical formula 2, and

[0150] [Mathematical Formula 2]

[0151] [Mathematical Formula 2]

[0152] GA i '= (CA i - APHV i ') + APHV G

[0153] Here, GA i ' is the estimated growth age of the subject being measured, and CA i is the chronological age (calendar age) of the subject being measured, and APHV i ' is the predicted APHV data including the estimated and predicted APHV values ​​of the above-mentioned measurement subject, and APHV G The second APHV data may be a representative value or average value of the first APHV data derived from the training data group.

[0154] That is, the growth age of the subject of measurement calculated through the above growth age calculation step (E ga ) is the above second APHV data (S AA ) That is, with respect to the average value of the above first APHV data, the actual age (E) of the subject being measured ra ) and the predicted APHV data (E) of the above measurement subject PA It can be calculated by correcting for the difference of ).

[0155] Accordingly, the biological growth age of the subject is estimated by applying the actual age of the subject, that is, the temporal actual age uniformly calculated from the time of birth, the predicted APHV data calculated using the subject's tracking growth rate, and the second APHV data corresponding to the group average APHV of the sample subjects. The biological growth age can be utilized in constructing a growth stage classification model, and the reliability of various prediction models, such as the integrated height growth prediction model, the precocious puberty prediction model, and the obesity prediction model, constructed based on the classified growth stages can be maximized.

[0156] The precocious puberty prediction step (40) may include a step of determining the current growth stage of the subject being measured, and a step of determining the likelihood of precocious puberty occurring in the subject being measured.

[0157] The step of determining the possibility of precocious puberty above can be controlled to determine that the subject does not have precocious puberty if the subject's current growth stage corresponds to any one of the decelerated growth stage, the slowed growth stage, and the growth plate-free stage.

[0158] That is, the step of determining the possibility of precocious puberty may be controlled to determine that the subject has a possibility of precocious puberty if the subject's current growth stage corresponds to either the general growth stage or the rapid growth stage.

[0159] At this time, the general growth period (301) may be a growth stage with an end point that is earlier than the predicted APHV by the first growth period, and the rapid growth period (303) may be a growth stage with an start point that is earlier than the predicted APHV by the first growth period and an end point that is the predicted APHV. Therefore, the precocious puberty prediction stage may be controlled to determine that the subject has precocious puberty if the predicted APHV of the subject is prior to a specific point in time.

[0160] More specifically, the precocious puberty prediction step (40) can be controlled so that if the predicted APHV of the subject being measured is prior to a specific point in time, the subject being measured is determined to have precocious puberty.

[0161] Meanwhile, the precocious puberty prediction step (40) may be controlled to determine whether precocious puberty applies differently depending on the gender among the biological data of the subject received above.

[0162] In one embodiment, the precocious puberty prediction step (40) may be controlled to determine that the subject has precocious puberty if the gender of the subject is determined to be female and the predicted APHV corresponds to a time point prior to the first time point. At this time, the first time point may be 8 years of age.

[0163] In another embodiment, the precocious puberty prediction step (40) may be controlled to determine that the subject is a male if the gender of the subject is determined to be male and the predicted APHV corresponds to a second time point. At this time, the second time point may be 9 years of age.

[0164] Additionally, the precocious puberty prediction step (40) may be controlled to further determine the likelihood of precocious puberty based on the degree of physical secondary sexual characteristics expression among the biological data of the subject received. In exemplary embodiments, the precocious puberty prediction step (40) may be controlled to further determine the likelihood of precocious puberty based on sex hormone measurement data among the biological data of the subject received.

[0165] Meanwhile, the precocious puberty prediction step (40) can be performed by using multiple models to input the first APHV data, the second APHV data and / or whether precocious puberty applies, and the predicted APHV data of the subject being measured into a trained neural network to predict the final height.

[0166] In exemplary embodiments, the precocious puberty prediction step (40) may include a first model and a second model, and may construct a pipeline in which at least a portion of the output of the second model is input to the first model.

[0167] More specifically, the first model may be a model that learns body information corresponding to at least one of a plurality of growth stages as training data, based on time-series body information of a plurality of sample subjects.

[0168] The first model is equipped with an LSTM neural network for time-series data learning, and trains the LSTM neural network using the first APHV data, the second APHV data, and / or whether precocious puberty applies among the past physical information of the plurality of sample subjects. Then, the predicted APHV data among the physical information of the current subject is input into the trained LSTM neural network to output a predicted growth rate for each growth stage.

[0169] Meanwhile, the above LSTM neural network may be trained for each growth stage. Thus, it can be trained with past body information of the corresponding growth stage for each of the general growth stage (301), rapid growth stage (303), deceleration growth stage (305), slowed growth stage (307), and non-growth stage (309).

[0170] For example, in the present embodiment, time-series physical information of a plurality of sample subjects is sequentially input as training data according to age or any period, and the result of calculation of a predicted value for a past point in time or growth rate, e.g., the first APHV data, the second APHV data, and / or whether precocious puberty applies, can be transmitted to the prediction of growth rate at the next age or any period.

[0171] Therefore, the above LSTM neural network can learn not only the prediction of growth based on the current subject's body information but also the extent to which prediction results for various indicators from past time points influence the current growth prediction, and through this, it is possible to extract items among the indicators that have a significant influence on the change in growth based on age or an arbitrary period and reflect them in the growth prediction.

[0172] Furthermore, for time-series learning, it is necessary to obtain physical data from multiple sample subjects over a regular period. However, as mentioned above, since it may be difficult to regularly acquire physical data for multiple sample subjects based on age or arbitrary periods, the data may be used after being temporally normalized by removing outliers or non-continuous physical data for each unit period.

[0173] Meanwhile, the above-mentioned second model can derive the degree of bone maturity (age) from the hand bone image using a convolutional neural network trained on the bone maturity data of the subject being measured.

[0174] More specifically, the convolutional neural network comprises a plurality of convolution layers that generate feature maps for features within the analysis target image among the hand bone images, and a pooling layer in which sub-sampling is performed between the plurality of convolution layers, thereby allowing different levels of features for the analysis target area to be extracted, and the features can be probabilistically inferred through an activation function, or the bone maturity can be derived through weight learning between nodes via regression analysis.

[0175] The bone maturity extracted through the second model above can be input into the LSTM neural network along with at least some of the body information of the subject being measured, for example, predicted APHV data, to increase the accuracy of predicting the growth of the subject being measured.

[0176] The growth management solution provision step (S50) can be controlled to provide different solutions depending on whether the subject being measured corresponds to one of the multiple growth stages.

[0177] Generally, the prediction of precocious puberty is performed based on time-series body information of the subject being measured, and based on body information corresponding to the general growth stage (301) among multiple growth stages. Based on this prediction method, a management solution for precocious puberty can be provided in a way that lowers the growth rate in multiple growth stages.

[0178] More specifically, the growth management solution provision step (S50) may provide a solution for reducing the growth prediction value (P) of the subject being measured when the subject is in the general growth stage (301). The growth prediction value (P) is a value corresponding to the y-axis in FIG. 2, and the solution for reducing the growth prediction value (P) may be provided to the subject being measured through various display units (120) for the expected target value (G) of the y-axis.

[0179] Examples of solutions provided through the above display unit (120) may include current height, predicted height, degree of obesity, body fat mass, skeletal muscle mass, protein mass, mineral mass, amount of sleep, amount of exercise, nutritional information, lifestyle habits, posture, etc. Each indicator may be displayed in stages such as caution, normal, good, etc., based on a preset range, or may be displayed as a level.

[0180] Additionally, the current status, customized solutions, and precautions for each indicator can be displayed. The current status can be displayed in steps or levels based on the target value (G), and the customized solutions may include details on adjusting protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), and basal metabolic rate to reach the current target value (G) based on the entered body information.

[0181] The precautions may include information on adjusting currently deficient protein, mineral content, body fat, body water, soft lean mass, fat-free mass, bone tissue, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, etc., based on the entered body information.

[0182] Additionally, the growth management solution provision step (S50) may provide a solution for reducing the duration of the rapid growth stage (303) of the subject to measurement when the subject to measurement is in the rapid growth stage (303).

[0183] By reducing the duration of the rapid growth stage (303), the rapid growth stage (303) can generally be defined as a period that begins when secondary sexual characteristics start to appear and ends when secondary sexual characteristics are completed as described above. However, if the subject being measured is determined to be in a precocious stage through the prediction unit (50), the subject being measured is in a case where secondary sexual characteristics have already started in the general growth stage (301), and a solution can be provided to accelerate the time when secondary sexual characteristics are completed. In other words, various solutions to narrow the range of the x-axis corresponding to the rapid growth stage (303) in FIG. 2 can be provided to the subject being measured through the display unit (120).

[0184] By doing so, the progression of precocious puberty can be slowed down by reducing the rate of height increase. However, since the increase in height may not be distinct if the rate of height increase is reduced too much, the above target value (G) can be learned to be set within a predetermined range based on the value (P) predicted by precocious puberty.

[0185] The above-described measurement subject may include physical information considered when the subject is in a general growth stage (301), and may include information on the adjustment of indicators that can alleviate, in particular, cases where sex hormones increase abnormally.

[0186] Additionally, the growth management solution provision step (S50) may provide a solution for adjusting the duration of the subject's deceleration growth stage (305) when the subject is in the deceleration growth stage (305). The adjustment of the growth stage duration may be divided into cases where the subject's physical information is located at the beginning of the deceleration growth stage (305) and cases where it is located in the middle to late part of the deceleration growth stage (305) among the growth stages classified based on the input physical information of the subject.

[0187] The criteria for distinguishing the beginning and middle stages of the aforementioned deceleration growth stage (305) may be based on a predetermined range corresponding to the rapid growth stage (303) to the deceleration growth stage (305) based on the x-axis in FIG. 2, or based on whether secondary sexual characteristics have been completed based on the input body information of the subject being measured, if it has not been completed, it may be classified as the beginning of the deceleration growth stage (305), and if it has been completed, it may be classified as the middle stage of the deceleration growth stage (305).

[0188] Preferably, based on the input body information of the subject being measured, it is possible to determine whether secondary sexual characteristics have been completed and whether the current body information of the subject being measured is located at the beginning or middle-to-late part of the deceleration growth stage (305). If it is not possible to determine whether secondary sexual characteristics have been completed based on the input body information of the subject being measured, it is possible to determine whether the body information of the subject being measured is located at the beginning or middle-to-late part of the deceleration growth stage (305) based on a predetermined range corresponding to the rapid growth stage (303) to the deceleration growth stage (305).

[0189] Meanwhile, if the input body information of the subject being measured is located at the beginning of the deceleration growth stage (305), a time adjustment solution can be provided to accelerate the entry into the deceleration growth stage (305). As described above, since secondary sexual characteristics are being completed at the time of transition from the rapid growth stage (303) to the deceleration growth stage (305), a solution can be provided to accelerate the time when secondary growth is completed, and this may be similar to the solution provided when the subject being measured corresponds to the rapid growth stage (303). In other words, various solutions to move the range of the x-axis corresponding to the deceleration growth stage (305) in FIG. 2 to the left can be provided to the subject being measured through the display unit (120). In this case, the range of the deceleration growth stage (305) may increase depending on the body information of the subject being measured, or the range may decrease as the rapid growth stage (303) increases.

[0190] In addition, if the input body information of the subject being measured is located in the mid-to-late part of the deceleration growth stage (305), a period adjustment solution can be provided to increase the duration of the deceleration growth stage (305). As described above, the mid-to-late part of the deceleration growth stage (305) generally refers to the time when the subject's growth plates close after secondary sexual characteristics are completed. Generally, after 6 months have passed since entering the deceleration growth stage (305), about 50% of the growth plates close, and when the growth plates close and natural growth stops, the subject enters the no-growth stage (307). In this case, a solution can be provided to increase the duration of the deceleration growth stage (305). In other words, various solutions to expand the range of the x-axis corresponding to the deceleration growth stage (305) in FIG. 2 can be provided to the subject being measured through the display unit (120).

[0191] When the aforementioned subject of measurement corresponds to a general growth stage (301), the body information considered may include, in particular, the adjustment of an indicator that can alleviate the degree of growth plate closure.

[0192] Thus, as described above, in the case of precocious puberty, secondary sexual characteristics generally progress from the general growth stage (301), and it is necessary to reduce the growth rate during the general growth stage (301) and the rapid growth stage (303), but since the increase in final height after becoming an adult may not be distinct, it is necessary to increase the growth rate again during the mid-to-late part of the decelerated growth stage (303) and the growth plate period (307) described later after the secondary sexual characteristics are completed.

[0193] In addition, the growth management solution provision step (S50) can provide a solution for improving physical function, such as lifestyle habits, customized exercise, posture correction, and nutrient intake, based on the input physical information of the subject being measured when the subject is in a slowed growth phase (307).

[0194] During the slowed growth period (307), the growth rate slows down and gradually converges to zero before the growth plate closes. Therefore, based on the subject's weight, body fat, body water, muscle mass, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, hip circumference, etc., a solution can be provided to slow down the rate at which the subject's growth plate closes through lifestyle habits, customized exercise, posture correction, etc.

[0195] In addition, the growth management solution provision step (S50) can provide a solution for improving physical function through lifestyle habits, customized exercise, posture correction, and nutrient intake based on the input body information of the subject being measured when the subject is a non-growth plate device (309).

[0196] In the case of a non-growth plate device (309), the growth plate closes and natural growth stops, so a solution for improving physical function through lifestyle habits, customized exercise, and posture correction is provided based on the subject's weight, body fat, body water, muscle mass, skeletal muscle mass, Body Mass Index (BMI), basal metabolic rate, neck circumference, chest circumference, abdominal circumference, thigh circumference, arm circumference, hip circumference, etc., or a solution for improving physical function through nutrient intake is provided based on protein, mineral content, bone tissue (bone density), etc.

[0197] Figure 4 is a diagram showing multiple first growth rate curves representing the growth rate of height relative to actual age using time-series biometric data of sample subjects.

[0198] FIG. 4 illustrates a plurality of first growth rate curves generated through a first growth rate curve estimation unit (30), and the first APHV data extraction unit (40) can be controlled to extract first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate reaches a maximum value, for each of the plurality of first growth rate curves. The first APHV data may represent data indicating the point at which the growth rate reaches a maximum during pubertal rapid growth, that is, the age at which the growth acceleration is 0.

[0199] Meanwhile, the first APHV data extraction unit (40) may be controlled to extract additional data in addition to the first APHV (Age of Peak Height Velocity) data, which is the age at which the growth rate reaches a maximum value for each of the plurality of first growth rate curves.

[0200] For example, the first APHV data extraction unit (40) can be controlled to further extract data such as Age of Onset of Growth Spurt (AOGS) data, which is the point where pubertal rapid growth begins, and Age of End of Growth Spurt (AEGS) data, which is the point where pubertal rapid growth ends.

[0201] The above AOGS data may represent the point where the growth rate slope increases rapidly and the growth acceleration reaches its maximum, and may represent data indicating an age approximately 1.5 years prior to the above first APHV data.

[0202] The above AEGS data may represent the point where the pubertal growth spurt ends, which is the point where the growth rate after APHV becomes equal to the growth rate (Onset of growth spurt velocity) at AOGS. It may also represent data indicating an age approximately 1.5 years after the first APHV data.

[0203] Figures 5 and 6 are figures showing the APHV estimation error according to the age in months for girls and boys, respectively.

[0204] Referring to FIGS. 5 and 6, predicted APHV data of subjects of various ages were extracted using a bio-data-based APHV estimation model using artificial intelligence according to exemplary embodiments of the present invention, and then the predicted APHV data and the actual APHV data of the subjects were compared.

[0205] Specifically, through the experimental results described above, it was confirmed that for girls aged 10 years or older, the average error between the predicted APHV data value and the actual APHV data value was 0.35 years, and for boys aged 12 years or older, the average error between the predicted APHV data value and the actual APHV data value was 0.39 years. In other words, as a result, it was confirmed that the bio-data-based APHV estimation model using artificial intelligence according to the exemplary embodiments of the present invention has very high APHV prediction accuracy, as the average error between the predicted data value and the actual data value at the average age at which secondary sexual characteristics appear for both girls and boys is within 0.5 years.

[0206] In addition, through the experiment described above, it was confirmed that the prediction accuracy of the APHV estimation model improves as the actual age of the subjects approaches the actual APHV data value.

[0207] Figures 7 and 8 are figures showing the importance of APHV predictors for women and men, respectively.

[0208] Referring to FIGS. 7 and 8, various variables for constructing a biodata-based APHV estimation model using artificial intelligence according to exemplary embodiments of the present invention were classified according to their importance.

[0209] Specifically, as shown in Fig. 7, the variable of highest importance in predicting APHV for women was found to be Previous Velocity, whereas as shown in Fig. 8, the variable of highest importance in predicting APHV for men was found to be Height Quantile.

[0210] Meanwhile, in predicting APHV for women, current growth rate (Velocity) was found to be the fourth most important variable, while in predicting APHV for men, previous growth rate (Previous Velocity) and current growth rate (Velocity) were found to be the second and sixth most important variables, respectively.

[0211] In other words, it was confirmed that previous velocity and current velocity act as very important variables for predicting APHV in women and men, respectively. Specifically, previous velocity was found to be the most important variable for women and the second most important variable for men. Consequently, it was confirmed that the accuracy of predicted APHV data extracted using the APHV estimation model can be significantly improved when there are two or more sets of biological data measured at different time points of the subject, allowing for the verification of the previous velocity.

[0212] In addition, it was confirmed that additional variables such as height quantile, waist-to-hip ratio (WHR), and body fat mass are required to increase the accuracy of the predicted APHV data extracted through the bio-data-based APHV estimation model using artificial intelligence according to exemplary embodiments of the present invention.

[0213] Figure 9 is a diagram showing the importance of variables in a conventional growth prediction model for women and men, and Figure 10 is a diagram showing the importance of variables in a growth prediction model of the present invention.

[0214] Referring to Figures 9 and 10, the most important variable in both the conventional growth prediction model for women and men and the growth prediction model of the present invention was found to be the growth rate, whereas in the case of the conventional growth prediction model, the second most important variable was the height quantile, and in the case of the growth prediction model of the present invention, the second most important variable was the age of peak height velocity (APHV).

[0215] In other words, in conventional growth prediction models prior to the application of the APHV concept, the Height Quantile appeared as the variable of second-highest importance after the Growth Rate; however, in the growth prediction model according to the present invention after the application of the APHV (Age of Peak Height Velocity) concept, the APHV was calculated to be more important than the Height Quantile, appearing as the variable of second-highest importance after the Growth Rate. Accordingly, it was confirmed that the importance of APHV is very high among the variables affecting the predicted final height.

[0216] As described above, the method for predicting precocious puberty based on biodata using artificial intelligence and providing a solution according to exemplary embodiments of the present invention estimates a growth rate curve by applying a statistical methodology to tracking growth rates extracted from past information, extracts Age of Peak Height Velocity (APHV) data—the age at which the growth rate reaches its maximum value—from the growth rate curve, and utilizes the APHV data for predicting precocious puberty; thereby, the reliability of various prediction models, such as an integrated height growth prediction model, a precocious puberty prediction model, and an obesity prediction model constructed using the classified growth stages, can be maximized.

[0217] In addition, according to various embodiments of the present invention, a growth stage classification method constructed through artificial intelligence learning can accurately predict whether a child or adolescent has precocious puberty by considering their growth stage, and can provide solutions necessary for the prevention of precocious puberty by considering each growth stage.

[0218] Although various embodiments of the present invention have been described in detail above, those skilled in the art will understand that various modifications can be made to the above-described embodiments without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims set forth below as well as equivalents thereof.

Claims

Claim 1 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model trained on target data of a first Age of Peak Height Velocity (APHV), which is the age at which the growth rate of multiple sample subjects reaches its maximum value, wherein the method comprises: a step of receiving biological data of a subject to be measured; a step of extracting predicted Age of Peak Height Velocity (APHV) data, which is the age at which the growth rate is expected to reach its maximum value, using the biological data of the subject to be measured; a step of classifying the growth stage of the subject to be measured into one of multiple growth stages based on the predicted APHV data; and a step of predicting precocious puberty of the subject to be measured based on the classified growth stage of the subject to be measured. A method for predicting and providing a precocious puberty solution based on growth age using an artificial intelligence model, comprising the step of providing a precocious puberty management solution based on the above-mentioned precocious puberty prediction result; wherein the artificial intelligence model estimates a plurality of first growth rate curves representing the growth rate of height relative to the actual age of each of the sample subjects using the biometric data of the sample subjects, and the first APHV data is a set of data obtained by extracting the age at which the growth rate reaches a maximum value for each of the plurality of first growth rate curves, and the predicted APHV data extraction step is performed by generating a second growth rate curve representing the expected growth rate of the measurement subject using the artificial intelligence model, and then extracting the predicted APHV from the second growth rate curve. Claim 2 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model, characterized in that, in claim 1, the plurality of growth stages include a general growth stage, a rapid growth stage, a decelerated growth stage, a slowed growth stage, and a growth plate stage. Claim 3 In paragraph 2, the precocious puberty prediction step comprises: a step of determining the current growth stage of the subject to measurement; and a step of determining the likelihood of precocious puberty occurring in the subject to measurement based on the subject's current growth stage; wherein the step of determining the likelihood of precocious puberty occurring is controlled to determine that the subject to measurement does not have precocious puberty if the subject's current growth stage corresponds to any one of the decelerated growth stage, the slowed growth stage, and the no-growth stage. Claim 4 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model, characterized in that, in paragraph 3, the step of determining the possibility of precocious puberty occurrence is controlled to determine that the subject is likely to have precocious puberty if the subject's current growth stage corresponds to either the general growth period or the rapid growth period. Claim 5 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model, characterized in that, in claim 4, the general growth period is a growth stage with an end point that is a first growth period earlier than the predicted APHV, and the rapid growth period is a growth stage with a start point that is a first growth period earlier than the predicted APHV and an end point that is the predicted APHV. Claim 6 A method for providing a growth age-based precocious puberty prediction and solution using an artificial intelligence model, wherein, in claim 1, the precocious puberty prediction step is controlled to determine that the subject has precocious puberty if the predicted APHV of the subject is prior to a specific point in time. Claim 7 A method for providing a growth age-based precocious puberty prediction and solution using an artificial intelligence model, wherein, in claim 6, the precocious puberty prediction step is controlled to determine whether precocious puberty applies differently depending on the gender among the biological data of the subject received as input. Claim 8 A method for providing a growth age-based precocious puberty prediction and solution using an artificial intelligence model, characterized in that, in the precocious puberty prediction step, the gender of the subject being measured is determined to be female and the predicted APHV corresponds to a time point prior to the first time point, the subject being measured is controlled to be determined to have precocious puberty. Claim 9 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model, characterized in that, in claim 8, the first point in time is 8 years of age. Claim 10 A method for providing a growth age-based precocious puberty prediction and solution using an artificial intelligence model, characterized in that, in the precocious puberty prediction step, the gender of the subject being measured is determined to be male and the predicted APHV corresponds to a time point prior to the second time point, the measurement subject is controlled to be determined to have precocious puberty. Claim 11 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model, characterized in that, in claim 10, the second point in time is 9 years of age. Claim 12 A method for providing a growth age-based precocious puberty prediction and solution using an artificial intelligence model, wherein, in claim 1, the precocious puberty prediction step is controlled to further determine the likelihood of precocious puberty based on the degree of manifestation of physical secondary sexual characteristics among the biological data of the subject received as input. Claim 13 A method for providing a growth age-based precocious puberty prediction and solution using an artificial intelligence model, wherein, in claim 1, the precocious puberty prediction step is controlled to further determine the likelihood of precocious puberty based on sex hormone measurement data among the biological data of the subject received as input. Claim 14 A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model, characterized by further including the step of calculating the growth age of the subject based on the second APHV data, which is the average value of the first APHV data, and the predicted APHV data in claim 1. Claim 15 In Clause 14, the growth age calculation step is performed using Mathematical Formula 1, and [Mathical Formula 1] GA i '=(CA i - APHV i ') + APHV G Here, GA i ' is the estimated growth age of the subject being measured, and CA i is the chronological age (calendar age) of the subject being measured, and APHV i ' is the predicted APHV data including the estimated and predicted APHV values ​​of the above-mentioned measurement subject, and APHV G A method for predicting and providing a solution for precocious puberty based on growth age using an artificial intelligence model characterized by the above-mentioned second APHV data.

Images