Search

KR-102960708-B1 - SYSTEM AND METHOD FOR ESTIMATING THE POSSIBILITY OF OBESITY BASED ON PHYSICAL GROWTH DATA USING GROWTH PREDICTION AI MODEL

KR102960708B1KR 102960708 B1KR102960708 B1KR 102960708B1KR-102960708-B1

Abstract

A method for predicting obesity based on growth and development data of infants and toddlers using a growth prediction AI model according to an embodiment of the present invention, the method comprises the steps of: acquiring first data, which is physical information data including gender, height, and weight of infants and toddlers, and storing it in a database; acquiring second data, which is physical activity data of infants and toddlers, and storing it in the database; normalizing and categorizing the first and second data; predicting obesity after n months through the growth curve of the growth prediction AI model based on the normalized first and second data; reacquiring the first and second data after n months and storing it in a database; training the growth prediction AI model based on the predicted obesity and the reacquired first data; predicting obesity after m months through the trained growth prediction AI model; and analyzing obesity risk based on the predicted obesity.

Inventors

  • 한병희
  • 정미리
  • 정호정

Assignees

  • 주식회사 엘레나휴먼바이오텍

Dates

Publication Date
20260507
Application Date
20221123

Claims (14)

  1. A method for predicting obesity based on infant and toddler growth and development data using a growth prediction AI model, wherein the method A step of acquiring first data, which is physical information data including gender, height, and weight of infants and toddlers, and storing it in a database; A step of acquiring second data, which is physical activity data for infants and toddlers, and storing it in the database; A step of normalizing and categorizing the above first and second data; A step of predicting the degree of obesity after n months through the infant growth curve of the growth prediction AI model based on the normalized first and second data; A step of reacquiring the first and second data after the above n months and storing them in a database; A step of training a growth prediction AI model based on the above-mentioned predicted obesity level and the reacquired first data; A step of predicting obesity level after m months using the above-mentioned learned growth prediction AI model; and A step of analyzing obesity risk based on the predicted obesity level above; Includes, The above obesity prediction value is a value obtained by calculating a prediction value based on the first data and a prediction value based on the second data, respectively, and summing each of the prediction values according to their respective weights. A method for predicting obesity based on infant growth and development data using a growth prediction AI model, characterized in that the above weight is the respective ratio of the predicted value based on the first data and the predicted value based on the second data for the predicted obesity value.
  2. In Article 1, A method for predicting obesity based on infant growth and development data using a growth prediction AI model, characterized in that the step of training the growth prediction AI model includes comparing the predicted obesity with the first data reacquired, and adjusting the weights used for obesity prediction according to the comparison result.
  3. delete
  4. In Article 1 or Article 2, A method for predicting obesity based on infant growth and development data using a growth prediction AI model characterized in that the second data above includes data regarding endurance, power, balance, and agility.
  5. In Article 1 or Article 2, A method for predicting obesity based on infant growth and development data using a growth prediction AI model, characterized by further including providing the above-described classified category information and/or analyzed obesity risk information to the user in a visualized form on a display.
  6. In Article 5, A method for predicting obesity based on infant growth and development data using a growth prediction AI model, characterized by further including a step of recommending a diet for infants based on the above-described classified category information or analyzed obesity risk information.
  7. In Article 5, A method for predicting obesity based on infant growth and development data using a growth prediction AI model, characterized by further including a step of recommending physical activity for infants based on the above-described classified category information or analyzed obesity risk information.
  8. In Article 1 or Article 2, A method for predicting obesity based on infant growth and development data using a growth prediction AI model, characterized in that the above first and second data are acquired periodically, and the period includes annual, quarterly, monthly, weekly, etc.
  9. As a system that predicts obesity based on infant and toddler growth and development data using artificial intelligence algorithms, A terminal providing physical information data including the user's gender, height, and weight, and physical activity data; and A obesity prediction server connected to the terminal via a network, which analyzes the body information data and physical activity data provided by the terminal to predict the obesity level at a predetermined point in time and provides the obesity level information to the terminal; The above obesity prediction server is, A storage unit that stores data provided from the above terminal by creating a database, An obesity prediction calculation unit that predicts the obesity level of the user at a predetermined point in time by learning the data of the storage unit using artificial intelligence (AI), and A obesity information providing unit that provides obesity information predicted by the obesity prediction calculation unit to the terminal, Includes, The above obesity prediction calculation unit is, A first prediction unit that predicts body information at a predetermined point in time based on the body information data from the above terminal, A second prediction unit that predicts body information at a predetermined point in time based on the body activity data from the above terminal, A weight determining unit that determines the weight assigned to each of the prediction values of the first prediction unit and the second prediction unit. Includes, A system for predicting obesity based on infant growth and development data using an artificial intelligence algorithm characterized in that the above weight is the respective ratio of the predicted value of the first prediction unit and the predicted value of the second prediction unit to the predicted obesity.
  10. In Article 9, A system for predicting obesity based on infant growth and development data using an artificial intelligence algorithm characterized in that the obesity level at the above-mentioned predetermined point in time is predicted based on the predicted values from the above-mentioned first prediction unit and second prediction unit and the weights from the above-mentioned weight determination unit.
  11. In Article 10, A system for predicting obesity based on infant growth and development data using an artificial intelligence algorithm characterized by the above-mentioned weight determination unit adjusting the weight by comparing the predicted obesity level at a predetermined time point with the obesity level from body information data obtained at the said predetermined time point.
  12. In any one of Articles 9 through 11, A system for predicting obesity based on infant growth and development data using an artificial intelligence algorithm characterized by the above-mentioned obesity information providing unit further providing recommendation information regarding diet and physical activity based on the above-mentioned predicted obesity information.
  13. A computer-readable recording medium having a built-in program that operates to perform the method according to claim 1 or 2.
  14. A program stored on a computer-readable recording medium that operates to perform the method according to claim 1 or 2.

Description

Method for predicting obesity based on growth and development data of infants and toddlers using a growth prediction AI model and system regarding the same {SYSTEM AND METHOD FOR ESTIMATING THE POSSIBILITY OF OBESITY BASED ON PHYSICAL GROWTH DATA USING GROWTH PREDICTION AI MODEL} The present invention generally relates to a system and method for predicting obesity based on growth and development data of infants and children (hereinafter referred to as "infants"), and more specifically, to a system and method for predicting obesity risk more accurately and standardizedly through a growth prediction AI model using body measurement data and physical activity data, rather than a medical diagnostic method. Obesity in infants and toddlers refers to a state of being relatively obese compared to their peer group, and the Body Mass Index (BMI), generally determined by height and weight, is known as a common and easy method to determine the degree of obesity. Obesity is divided into primary obesity, caused by genetic or environmental factors, and secondary obesity, caused by central nervous system abnormalities, endocrine diseases, or medications; over 99% of cases are classified as primary obesity. In fact, it is known that if both parents are obese, the probability of their child being obese is 70–80%, and if the mother is obese, the risk of obesity in the child doubles. Recently, due to the Westernization of dietary habits and excessive education, the physical activity levels of adolescents have decreased sharply, leading to a rising trend in the prevalence of obesity. In particular, it appears that obesity among children and adolescents, including infants and toddlers, has increased rapidly due to reduced physical activity caused by the COVID-19 outbreak in 2020. According to the National Health Insurance Service, the volume of obesity treatments for infants and toddlers aged 9 and under increased by 45.3% in the first half of 2021 compared to the first half of 2019, prior to COVID-19, and also increased by 29.6% for teenagers. Obesity in children and adolescents, including infants and toddlers, leads to obesity in adulthood and is a contributing factor to the early onset of metabolic diseases such as cardiovascular disease and diabetes. Furthermore, it affects the psychosocial development of children and adolescents, with reported problems including low self-esteem, depression, alienation from peers, and emotional instability caused by obesity. Despite these circumstances, society has not yet properly recognized the severity of the issue of obesity in infants and toddlers. Furthermore, until now, advice regarding the future risk of obesity in infants and toddlers can only be obtained through traditional medical services, where clinical specialists analyze growth and development data such as height and weight and counsel the children and guardians during direct hospital visits. According to this traditional service method, since specialists must personally diagnose and explain obesity, there are limitations in monitoring a large number of subjects, and disparities arise depending on each specialist's clinical ability to screen for obesity. Therefore, there is a need for a system capable of preventing systemic diseases such as adult obesity and hypertension by developing a standardized and systematized model of infant obesity to identify currently obese or high-risk infants early and take appropriate measures. The technology forming the background of the present invention is disclosed in Korean Published Patent Application No. 10-2014-0045759 (April 17, 2014) and No. 10-2021-00097515 (August 9, 2021). FIG. 1 is a flowchart illustrating a process for predicting obesity in infants and toddlers according to an embodiment of the present invention, and FIG. 2 is an exemplary diagram of an information source capable of acquiring body data according to an embodiment of the present invention, and FIG. 3 is a distribution of body mass index according to one embodiment of the present invention, and Figure 4 is a distribution plot in which the average of the body mass index in Figure 3 is standardized to 100, and Figure 5 is a distribution plot showing the flexibility item normalized, and Figure 6 is a distribution plot showing the endurance item normalized, and Figure 7 is a distribution plot showing the normalized speed item, and Figure 8 is a distribution plot showing the equilibrium item normalized, and Figure 9 is a distribution plot showing the agility item normalized, and FIG. 10 is a distribution plot showing the sum of the normalized values of FIG. 5 to 9 converted to 100 points and normalized. Figure 11 is a table showing the correlation between body information data and physical activity data, and FIG. 12 is a diagram illustrating an obesity prediction process according to an embodiment of the present invention, and FIG. 13 is a diagram illustrating an example of providing analysis data regarding the height of an